From b9a49520679e98700d3d89689cc91c08a1c88c1d Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sun, 19 Jan 2025 00:55:32 +0100
Subject: [PATCH 0001/1173] rcuref: Plug slowpath race in rcuref_put()

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

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

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

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

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

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

[ bigeasy: Add changelog ]

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

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

From 5c8f9a05336cf5cadbd57ad461621b386aadb762 Mon Sep 17 00:00:00 2001
From: Alexander Shiyan <eagle.alexander923@gmail.com>
Date: Thu, 30 Jan 2025 08:38:49 +0300
Subject: [PATCH 0002/1173] arm64: dts: rockchip: Fix broken tsadc pinctrl
 names for rk3588

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

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

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

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

From a6a7cba17c544fb95d5a29ab9d9ed4503029cb29 Mon Sep 17 00:00:00 2001
From: Tianling Shen <cnsztl@gmail.com>
Date: Sun, 19 Jan 2025 17:11:54 +0800
Subject: [PATCH 0003/1173] arm64: dts: rockchip: change eth phy mode to
 rgmii-id for orangepi r1 plus lts

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

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

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

From 4eee627ea59304cdd66c5d4194ef13486a6c44fc Mon Sep 17 00:00:00 2001
From: Lukasz Czechowski <lukasz.czechowski@thaumatec.com>
Date: Tue, 21 Jan 2025 13:56:03 +0100
Subject: [PATCH 0004/1173] arm64: dts: rockchip: Move uart5 pin configuration
 to px30 ringneck SoM

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

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

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

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

From 5ae4dca718eacd0a56173a687a3736eb7e627c77 Mon Sep 17 00:00:00 2001
From: Lukasz Czechowski <lukasz.czechowski@thaumatec.com>
Date: Tue, 21 Jan 2025 13:56:04 +0100
Subject: [PATCH 0005/1173] arm64: dts: rockchip: Disable DMA for uart5 on
 px30-ringneck
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

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

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

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

From 2f9eb5262e63396a315c7da34a6c80c5d335df9f Mon Sep 17 00:00:00 2001
From: Heiko Stuebner <heiko@sntech.de>
Date: Thu, 16 Jan 2025 15:36:31 +0100
Subject: [PATCH 0006/1173] arm64: dts: rockchip: fix fixed-regulator renames
 on rk3399-gru devices

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

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

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

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

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

From a1d939055a22be06d8c12bf53afb258b9d38575f Mon Sep 17 00:00:00 2001
From: Andy Yan <andyshrk@163.com>
Date: Mon, 13 Jan 2025 18:47:34 +0800
Subject: [PATCH 0007/1173] arm64: dts: rockchip: Fix lcdpwr_en pin for Cool Pi
 GenBook

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

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

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

From 33ea120582a638b2f2e380a50686c2b1d7cce795 Mon Sep 17 00:00:00 2001
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Date: Sun, 26 Jan 2025 09:47:25 +0200
Subject: [PATCH 0008/1173] x86/mm/pat: cpa-test: fix length for CPA_ARRAY test

The CPA_ARRAY test always uses len[1] as numpages argument to
change_page_attr_set() although the addresses array is different each
iteration of the test loop.

Replace len[1] with len[i] to have numpages matching the addresses array.

Fixes: ecc729f1f471 ("x86/mm/cpa: Add ARRAY and PAGES_ARRAY selftests")
Signed-off-by: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250126074733.1384926-2-rppt@kernel.org
---
 arch/x86/mm/pat/cpa-test.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/mm/pat/cpa-test.c b/arch/x86/mm/pat/cpa-test.c
index 3d2f7f0a6ed14..ad3c1feec990d 100644
--- a/arch/x86/mm/pat/cpa-test.c
+++ b/arch/x86/mm/pat/cpa-test.c
@@ -183,7 +183,7 @@ static int pageattr_test(void)
 			break;
 
 		case 1:
-			err = change_page_attr_set(addrs, len[1], PAGE_CPA_TEST, 1);
+			err = change_page_attr_set(addrs, len[i], PAGE_CPA_TEST, 1);
 			break;
 
 		case 2:

From 4ee788eb0781ba082709c1ac1d5146ebcc40b967 Mon Sep 17 00:00:00 2001
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Date: Sun, 26 Jan 2025 09:47:26 +0200
Subject: [PATCH 0009/1173] x86/mm/pat: drop duplicate variable in cpa_flush()

There is a 'struct cpa_data *data' parameter in cpa_flush() that is
assigned to a local 'struct cpa_data *cpa' variable.

Rename the parameter from 'data' to 'cpa' and drop declaration of the
local 'cpa' variable.

Signed-off-by: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250126074733.1384926-3-rppt@kernel.org
---
 arch/x86/mm/pat/set_memory.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index ef4514d64c052..1f7698caa6f7b 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -394,9 +394,8 @@ static void __cpa_flush_tlb(void *data)
 		flush_tlb_one_kernel(fix_addr(__cpa_addr(cpa, i)));
 }
 
-static void cpa_flush(struct cpa_data *data, int cache)
+static void cpa_flush(struct cpa_data *cpa, int cache)
 {
-	struct cpa_data *cpa = data;
 	unsigned int i;
 
 	BUG_ON(irqs_disabled() && !early_boot_irqs_disabled);

From 41d88484c71cd4f659348da41b7b5b3dbd3be1f6 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Sun, 26 Jan 2025 09:47:27 +0200
Subject: [PATCH 0010/1173] x86/mm/pat: restore large ROX pages after
 fragmentation

Change of attributes of the pages may lead to fragmentation of direct
mapping over time and performance degradation when these pages contain
executable code.

With current code it's one way road: kernel tries to avoid splitting
large pages, but it doesn't restore them back even if page attributes
got compatible again.

Any change to the mapping may potentially allow to restore large page.

Add a hook to cpa_flush() path that will check if the pages in the range
that were just touched can be mapped at PMD level. If the collapse at the
PMD level succeeded, also attempt to collapse PUD level.

The collapse logic runs only when a set_memory_ method explicitly sets
CPA_COLLAPSE flag, for now this is only enabled in set_memory_rox().

CPUs don't like[1] to have to have TLB entries of different size for the
same memory, but looks like it's okay as long as these entries have
matching attributes[2]. Therefore it's critical to flush TLB before any
following changes to the mapping.

Note that we already allow for multiple TLB entries of different sizes
for the same memory now in split_large_page() path. It's not a new
situation.

set_memory_4k() provides a way to use 4k pages on purpose. Kernel must
not remap such pages as large. Re-use one of software PTE bits to
indicate such pages.

[1] See Erratum 383 of AMD Family 10h Processors
[2] https://lore.kernel.org/linux-mm/1da1b025-cabc-6f04-bde5-e50830d1ecf0@amd.com/

[rppt@kernel.org:
 * s/restore/collapse/
 * update formatting per peterz
 * use 'struct ptdesc' instead of 'struct page' for list of page tables to
   be freed
 * try to collapse PMD first and if it succeeds move on to PUD as peterz
   suggested
 * flush TLB twice: for changes done in the original CPA call and after
   collapsing of large pages
 * update commit message
]

Signed-off-by: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Co-developed-by: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Signed-off-by: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250126074733.1384926-4-rppt@kernel.org
---
 arch/x86/include/asm/pgtable_types.h |   2 +
 arch/x86/mm/pat/set_memory.c         | 217 ++++++++++++++++++++++++++-
 include/linux/vm_event_item.h        |   2 +
 mm/vmstat.c                          |   2 +
 4 files changed, 219 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 4b804531b03c3..c90e9c51edb7a 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -33,6 +33,7 @@
 #define _PAGE_BIT_CPA_TEST	_PAGE_BIT_SOFTW1
 #define _PAGE_BIT_UFFD_WP	_PAGE_BIT_SOFTW2 /* userfaultfd wrprotected */
 #define _PAGE_BIT_SOFT_DIRTY	_PAGE_BIT_SOFTW3 /* software dirty tracking */
+#define _PAGE_BIT_KERNEL_4K	_PAGE_BIT_SOFTW3 /* page must not be converted to large */
 #define _PAGE_BIT_DEVMAP	_PAGE_BIT_SOFTW4
 
 #ifdef CONFIG_X86_64
@@ -64,6 +65,7 @@
 #define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE)
 #define _PAGE_SPECIAL	(_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL)
 #define _PAGE_CPA_TEST	(_AT(pteval_t, 1) << _PAGE_BIT_CPA_TEST)
+#define _PAGE_KERNEL_4K	(_AT(pteval_t, 1) << _PAGE_BIT_KERNEL_4K)
 #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
 #define _PAGE_PKEY_BIT0	(_AT(pteval_t, 1) << _PAGE_BIT_PKEY_BIT0)
 #define _PAGE_PKEY_BIT1	(_AT(pteval_t, 1) << _PAGE_BIT_PKEY_BIT1)
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index 1f7698caa6f7b..7bd0f62ba48fd 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -73,6 +73,7 @@ static DEFINE_SPINLOCK(cpa_lock);
 #define CPA_ARRAY 2
 #define CPA_PAGES_ARRAY 4
 #define CPA_NO_CHECK_ALIAS 8 /* Do not search for aliases */
+#define CPA_COLLAPSE 16 /* try to collapse large pages */
 
 static inline pgprot_t cachemode2pgprot(enum page_cache_mode pcm)
 {
@@ -105,6 +106,18 @@ static void split_page_count(int level)
 	direct_pages_count[level - 1] += PTRS_PER_PTE;
 }
 
+static void collapse_page_count(int level)
+{
+	direct_pages_count[level]++;
+	if (system_state == SYSTEM_RUNNING) {
+		if (level == PG_LEVEL_2M)
+			count_vm_event(DIRECT_MAP_LEVEL2_COLLAPSE);
+		else if (level == PG_LEVEL_1G)
+			count_vm_event(DIRECT_MAP_LEVEL3_COLLAPSE);
+	}
+	direct_pages_count[level - 1] -= PTRS_PER_PTE;
+}
+
 void arch_report_meminfo(struct seq_file *m)
 {
 	seq_printf(m, "DirectMap4k:    %8lu kB\n",
@@ -122,6 +135,7 @@ void arch_report_meminfo(struct seq_file *m)
 }
 #else
 static inline void split_page_count(int level) { }
+static inline void collapse_page_count(int level) { }
 #endif
 
 #ifdef CONFIG_X86_CPA_STATISTICS
@@ -394,6 +408,40 @@ static void __cpa_flush_tlb(void *data)
 		flush_tlb_one_kernel(fix_addr(__cpa_addr(cpa, i)));
 }
 
+static int collapse_large_pages(unsigned long addr, struct list_head *pgtables);
+
+static void cpa_collapse_large_pages(struct cpa_data *cpa)
+{
+	unsigned long start, addr, end;
+	struct ptdesc *ptdesc, *tmp;
+	LIST_HEAD(pgtables);
+	int collapsed = 0;
+	int i;
+
+	if (cpa->flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) {
+		for (i = 0; i < cpa->numpages; i++)
+			collapsed += collapse_large_pages(__cpa_addr(cpa, i),
+							  &pgtables);
+	} else {
+		addr = __cpa_addr(cpa, 0);
+		start = addr & PMD_MASK;
+		end = addr + PAGE_SIZE * cpa->numpages;
+
+		for (addr = start; within(addr, start, end); addr += PMD_SIZE)
+			collapsed += collapse_large_pages(addr, &pgtables);
+	}
+
+	if (!collapsed)
+		return;
+
+	flush_tlb_all();
+
+	list_for_each_entry_safe(ptdesc, tmp, &pgtables, pt_list) {
+		list_del(&ptdesc->pt_list);
+		__free_page(ptdesc_page(ptdesc));
+	}
+}
+
 static void cpa_flush(struct cpa_data *cpa, int cache)
 {
 	unsigned int i;
@@ -402,7 +450,7 @@ static void cpa_flush(struct cpa_data *cpa, int cache)
 
 	if (cache && !static_cpu_has(X86_FEATURE_CLFLUSH)) {
 		cpa_flush_all(cache);
-		return;
+		goto collapse_large_pages;
 	}
 
 	if (cpa->force_flush_all || cpa->numpages > tlb_single_page_flush_ceiling)
@@ -411,7 +459,7 @@ static void cpa_flush(struct cpa_data *cpa, int cache)
 		on_each_cpu(__cpa_flush_tlb, cpa, 1);
 
 	if (!cache)
-		return;
+		goto collapse_large_pages;
 
 	mb();
 	for (i = 0; i < cpa->numpages; i++) {
@@ -427,6 +475,10 @@ static void cpa_flush(struct cpa_data *cpa, int cache)
 			clflush_cache_range_opt((void *)fix_addr(addr), PAGE_SIZE);
 	}
 	mb();
+
+collapse_large_pages:
+	if (cpa->flags & CPA_COLLAPSE)
+		cpa_collapse_large_pages(cpa);
 }
 
 static bool overlaps(unsigned long r1_start, unsigned long r1_end,
@@ -1196,6 +1248,161 @@ static int split_large_page(struct cpa_data *cpa, pte_t *kpte,
 	return 0;
 }
 
+static int collapse_pmd_page(pmd_t *pmd, unsigned long addr,
+			     struct list_head *pgtables)
+{
+	pmd_t _pmd, old_pmd;
+	pte_t *pte, first;
+	unsigned long pfn;
+	pgprot_t pgprot;
+	int i = 0;
+
+	addr &= PMD_MASK;
+	pte = pte_offset_kernel(pmd, addr);
+	first = *pte;
+	pfn = pte_pfn(first);
+
+	/* Make sure alignment is suitable */
+	if (PFN_PHYS(pfn) & ~PMD_MASK)
+		return 0;
+
+	/* The page is 4k intentionally */
+	if (pte_flags(first) & _PAGE_KERNEL_4K)
+		return 0;
+
+	/* Check that the rest of PTEs are compatible with the first one */
+	for (i = 1, pte++; i < PTRS_PER_PTE; i++, pte++) {
+		pte_t entry = *pte;
+
+		if (!pte_present(entry))
+			return 0;
+		if (pte_flags(entry) != pte_flags(first))
+			return 0;
+		if (pte_pfn(entry) != pte_pfn(first) + i)
+			return 0;
+	}
+
+	old_pmd = *pmd;
+
+	/* Success: set up a large page */
+	pgprot = pgprot_4k_2_large(pte_pgprot(first));
+	pgprot_val(pgprot) |= _PAGE_PSE;
+	_pmd = pfn_pmd(pfn, pgprot);
+	set_pmd(pmd, _pmd);
+
+	/* Queue the page table to be freed after TLB flush */
+	list_add(&page_ptdesc(pmd_page(old_pmd))->pt_list, pgtables);
+
+	if (IS_ENABLED(CONFIG_X86_32) && !SHARED_KERNEL_PMD) {
+		struct page *page;
+
+		/* Update all PGD tables to use the same large page */
+		list_for_each_entry(page, &pgd_list, lru) {
+			pgd_t *pgd = (pgd_t *)page_address(page) + pgd_index(addr);
+			p4d_t *p4d = p4d_offset(pgd, addr);
+			pud_t *pud = pud_offset(p4d, addr);
+			pmd_t *pmd = pmd_offset(pud, addr);
+			/* Something is wrong if entries doesn't match */
+			if (WARN_ON(pmd_val(old_pmd) != pmd_val(*pmd)))
+				continue;
+			set_pmd(pmd, _pmd);
+		}
+	}
+
+	if (virt_addr_valid(addr) && pfn_range_is_mapped(pfn, pfn + 1))
+		collapse_page_count(PG_LEVEL_2M);
+
+	return 1;
+}
+
+static int collapse_pud_page(pud_t *pud, unsigned long addr,
+			     struct list_head *pgtables)
+{
+	unsigned long pfn;
+	pmd_t *pmd, first;
+	int i;
+
+	if (!direct_gbpages)
+		return 0;
+
+	addr &= PUD_MASK;
+	pmd = pmd_offset(pud, addr);
+	first = *pmd;
+
+	/*
+	 * To restore PUD page all PMD entries must be large and
+	 * have suitable alignment
+	 */
+	pfn = pmd_pfn(first);
+	if (!pmd_leaf(first) || (PFN_PHYS(pfn) & ~PUD_MASK))
+		return 0;
+
+	/*
+	 * To restore PUD page, all following PMDs must be compatible with the
+	 * first one.
+	 */
+	for (i = 1, pmd++; i < PTRS_PER_PMD; i++, pmd++) {
+		pmd_t entry = *pmd;
+
+		if (!pmd_present(entry) || !pmd_leaf(entry))
+			return 0;
+		if (pmd_flags(entry) != pmd_flags(first))
+			return 0;
+		if (pmd_pfn(entry) != pmd_pfn(first) + i * PTRS_PER_PTE)
+			return 0;
+	}
+
+	/* Restore PUD page and queue page table to be freed after TLB flush */
+	list_add(&page_ptdesc(pud_page(*pud))->pt_list, pgtables);
+	set_pud(pud, pfn_pud(pfn, pmd_pgprot(first)));
+
+	if (virt_addr_valid(addr) && pfn_range_is_mapped(pfn, pfn + 1))
+		collapse_page_count(PG_LEVEL_1G);
+
+	return 1;
+}
+
+/*
+ * Collapse PMD and PUD pages in the kernel mapping around the address where
+ * possible.
+ *
+ * Caller must flush TLB and free page tables queued on the list before
+ * touching the new entries. CPU must not see TLB entries of different size
+ * with different attributes.
+ */
+static int collapse_large_pages(unsigned long addr, struct list_head *pgtables)
+{
+	int collapsed = 0;
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	addr &= PMD_MASK;
+
+	spin_lock(&pgd_lock);
+	pgd = pgd_offset_k(addr);
+	if (pgd_none(*pgd))
+		goto out;
+	p4d = p4d_offset(pgd, addr);
+	if (p4d_none(*p4d))
+		goto out;
+	pud = pud_offset(p4d, addr);
+	if (!pud_present(*pud) || pud_leaf(*pud))
+		goto out;
+	pmd = pmd_offset(pud, addr);
+	if (!pmd_present(*pmd) || pmd_leaf(*pmd))
+		goto out;
+
+	collapsed = collapse_pmd_page(pmd, addr, pgtables);
+	if (collapsed)
+		collapsed += collapse_pud_page(pud, addr, pgtables);
+
+out:
+	spin_unlock(&pgd_lock);
+	return collapsed;
+}
+
 static bool try_to_free_pte_page(pte_t *pte)
 {
 	int i;
@@ -2119,7 +2326,8 @@ int set_memory_rox(unsigned long addr, int numpages)
 	if (__supported_pte_mask & _PAGE_NX)
 		clr.pgprot |= _PAGE_NX;
 
-	return change_page_attr_clear(&addr, numpages, clr, 0);
+	return change_page_attr_set_clr(&addr, numpages, __pgprot(0), clr, 0,
+					CPA_COLLAPSE, NULL);
 }
 
 int set_memory_rw(unsigned long addr, int numpages)
@@ -2146,7 +2354,8 @@ int set_memory_p(unsigned long addr, int numpages)
 
 int set_memory_4k(unsigned long addr, int numpages)
 {
-	return change_page_attr_set_clr(&addr, numpages, __pgprot(0),
+	return change_page_attr_set_clr(&addr, numpages,
+					__pgprot(_PAGE_KERNEL_4K),
 					__pgprot(0), 1, 0, NULL);
 }
 
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index f70d0958095cd..5a37cb2b6f93b 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -151,6 +151,8 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 #ifdef CONFIG_X86
 		DIRECT_MAP_LEVEL2_SPLIT,
 		DIRECT_MAP_LEVEL3_SPLIT,
+		DIRECT_MAP_LEVEL2_COLLAPSE,
+		DIRECT_MAP_LEVEL3_COLLAPSE,
 #endif
 #ifdef CONFIG_PER_VMA_LOCK_STATS
 		VMA_LOCK_SUCCESS,
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 16bfe1c694dd4..88998725f1c5a 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1435,6 +1435,8 @@ const char * const vmstat_text[] = {
 #ifdef CONFIG_X86
 	"direct_map_level2_splits",
 	"direct_map_level3_splits",
+	"direct_map_level2_collapses",
+	"direct_map_level3_collapses",
 #endif
 #ifdef CONFIG_PER_VMA_LOCK_STATS
 	"vma_lock_success",

From 925f426451182a9f3e0f7f0e7e928f32f81a966a Mon Sep 17 00:00:00 2001
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Date: Sun, 26 Jan 2025 09:47:28 +0200
Subject: [PATCH 0011/1173] execmem: don't remove ROX cache from the direct map

The memory allocated for the ROX cache was removed from the direct map to
reduce amount of direct map updates, however this cannot be tolerated by
/proc/kcore that accesses module memory using vread_iter() and the latter
does vmalloc_to_page() and copy_page_to_iter_nofault().

Instead of removing ROX cache memory from the direct map and mapping it as
ROX in vmalloc space, simply call set_memory_rox() that will take care of
proper permissions on both vmalloc and in the direct map.

Signed-off-by: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250126074733.1384926-5-rppt@kernel.org
---
 mm/execmem.c | 17 ++++-------------
 1 file changed, 4 insertions(+), 13 deletions(-)

diff --git a/mm/execmem.c b/mm/execmem.c
index 317b6a8d35be0..04b0bf1b5025a 100644
--- a/mm/execmem.c
+++ b/mm/execmem.c
@@ -257,7 +257,6 @@ static void *__execmem_cache_alloc(struct execmem_range *range, size_t size)
 static int execmem_cache_populate(struct execmem_range *range, size_t size)
 {
 	unsigned long vm_flags = VM_ALLOW_HUGE_VMAP;
-	unsigned long start, end;
 	struct vm_struct *vm;
 	size_t alloc_size;
 	int err = -ENOMEM;
@@ -275,26 +274,18 @@ static int execmem_cache_populate(struct execmem_range *range, size_t size)
 	/* fill memory with instructions that will trap */
 	execmem_fill_trapping_insns(p, alloc_size, /* writable = */ true);
 
-	start = (unsigned long)p;
-	end = start + alloc_size;
-
-	vunmap_range(start, end);
-
-	err = execmem_set_direct_map_valid(vm, false);
-	if (err)
-		goto err_free_mem;
-
-	err = vmap_pages_range_noflush(start, end, range->pgprot, vm->pages,
-				       PMD_SHIFT);
+	err = set_memory_rox((unsigned long)p, vm->nr_pages);
 	if (err)
 		goto err_free_mem;
 
 	err = execmem_cache_add(p, alloc_size);
 	if (err)
-		goto err_free_mem;
+		goto err_reset_direct_map;
 
 	return 0;
 
+err_reset_direct_map:
+	execmem_set_direct_map_valid(vm, true);
 err_free_mem:
 	vfree(p);
 	return err;

From 05e555b817262b5df6aa3a73df8b3dc9d388a3b4 Mon Sep 17 00:00:00 2001
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Date: Sun, 26 Jan 2025 09:47:29 +0200
Subject: [PATCH 0012/1173] execmem: add API for temporal remapping as RW and
 restoring ROX afterwards

Using a writable copy for ROX memory is cumbersome and error prone.

Add API that allow temporarily remapping of ranges in the ROX cache as
writable  and then restoring their read-only-execute permissions.

This API will be later used in modules code and will allow removing nasty
games with writable copy in alternatives patching on x86.

The restoring of the ROX permissions relies on the ability of architecture
to reconstruct large pages in its set_memory_rox() method.

Signed-off-by: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250126074733.1384926-6-rppt@kernel.org
---
 include/linux/execmem.h | 31 +++++++++++++++++++++++++++++++
 mm/execmem.c            | 22 ++++++++++++++++++++++
 2 files changed, 53 insertions(+)

diff --git a/include/linux/execmem.h b/include/linux/execmem.h
index 64130ae19690a..65655a5d1be28 100644
--- a/include/linux/execmem.h
+++ b/include/linux/execmem.h
@@ -65,6 +65,37 @@ enum execmem_range_flags {
  * Architectures that use EXECMEM_ROX_CACHE must implement this.
  */
 void execmem_fill_trapping_insns(void *ptr, size_t size, bool writable);
+
+/**
+ * execmem_make_temp_rw - temporarily remap region with read-write
+ *			  permissions
+ * @ptr:	address of the region to remap
+ * @size:	size of the region to remap
+ *
+ * Remaps a part of the cached large page in the ROX cache in the range
+ * [@ptr, @ptr + @size) as writable and not executable. The caller must
+ * have exclusive ownership of this range and ensure nothing will try to
+ * execute code in this range.
+ *
+ * Return: 0 on success or negative error code on failure.
+ */
+int execmem_make_temp_rw(void *ptr, size_t size);
+
+/**
+ * execmem_restore_rox - restore read-only-execute permissions
+ * @ptr:	address of the region to remap
+ * @size:	size of the region to remap
+ *
+ * Restores read-only-execute permissions on a range [@ptr, @ptr + @size)
+ * after it was temporarily remapped as writable. Relies on architecture
+ * implementation of set_memory_rox() to restore mapping using large pages.
+ *
+ * Return: 0 on success or negative error code on failure.
+ */
+int execmem_restore_rox(void *ptr, size_t size);
+#else
+static inline int execmem_make_temp_rw(void *ptr, size_t size) { return 0; }
+static inline int execmem_restore_rox(void *ptr, size_t size) { return 0; }
 #endif
 
 /**
diff --git a/mm/execmem.c b/mm/execmem.c
index 04b0bf1b5025a..e6c4f5076ca8d 100644
--- a/mm/execmem.c
+++ b/mm/execmem.c
@@ -335,6 +335,28 @@ static bool execmem_cache_free(void *ptr)
 
 	return true;
 }
+
+int execmem_make_temp_rw(void *ptr, size_t size)
+{
+	unsigned int nr = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	unsigned long addr = (unsigned long)ptr;
+	int ret;
+
+	ret = set_memory_nx(addr, nr);
+	if (ret)
+		return ret;
+
+	return set_memory_rw(addr, nr);
+}
+
+int execmem_restore_rox(void *ptr, size_t size)
+{
+	unsigned int nr = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	unsigned long addr = (unsigned long)ptr;
+
+	return set_memory_rox(addr, nr);
+}
+
 #else /* CONFIG_ARCH_HAS_EXECMEM_ROX */
 static void *execmem_cache_alloc(struct execmem_range *range, size_t size)
 {

From c287c072332905b7d878a8aade86cfef6b396343 Mon Sep 17 00:00:00 2001
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Date: Sun, 26 Jan 2025 09:47:30 +0200
Subject: [PATCH 0013/1173] module: switch to execmem API for remapping as RW
 and restoring ROX

Instead of using writable copy for module text sections, temporarily remap
the memory allocated from execmem's ROX cache as writable and restore its
ROX permissions after the module is formed.

This will allow removing nasty games with writable copy in alternatives
patching on x86.

Signed-off-by: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250126074733.1384926-7-rppt@kernel.org
---
 include/linux/module.h       |  8 +---
 include/linux/moduleloader.h |  4 --
 kernel/module/main.c         | 78 ++++++++++--------------------------
 kernel/module/strict_rwx.c   |  9 +++--
 4 files changed, 27 insertions(+), 72 deletions(-)

diff --git a/include/linux/module.h b/include/linux/module.h
index 23792d5d7b74b..ddf27ede7c91d 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -367,7 +367,6 @@ enum mod_mem_type {
 
 struct module_memory {
 	void *base;
-	void *rw_copy;
 	bool is_rox;
 	unsigned int size;
 
@@ -769,14 +768,9 @@ static inline bool is_livepatch_module(struct module *mod)
 
 void set_module_sig_enforced(void);
 
-void *__module_writable_address(struct module *mod, void *loc);
-
 static inline void *module_writable_address(struct module *mod, void *loc)
 {
-	if (!IS_ENABLED(CONFIG_ARCH_HAS_EXECMEM_ROX) || !mod ||
-	    mod->state != MODULE_STATE_UNFORMED)
-		return loc;
-	return __module_writable_address(mod, loc);
+	return loc;
 }
 
 #else /* !CONFIG_MODULES... */
diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h
index 1f5507ba5a128..e395461d59e5e 100644
--- a/include/linux/moduleloader.h
+++ b/include/linux/moduleloader.h
@@ -108,10 +108,6 @@ int module_finalize(const Elf_Ehdr *hdr,
 		    const Elf_Shdr *sechdrs,
 		    struct module *mod);
 
-int module_post_finalize(const Elf_Ehdr *hdr,
-			 const Elf_Shdr *sechdrs,
-			 struct module *mod);
-
 #ifdef CONFIG_MODULES
 void flush_module_init_free_work(void);
 #else
diff --git a/kernel/module/main.c b/kernel/module/main.c
index 1fb9ad289a6f8..5c127bedd3f07 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -1221,18 +1221,6 @@ void __weak module_arch_freeing_init(struct module *mod)
 {
 }
 
-void *__module_writable_address(struct module *mod, void *loc)
-{
-	for_class_mod_mem_type(type, text) {
-		struct module_memory *mem = &mod->mem[type];
-
-		if (loc >= mem->base && loc < mem->base + mem->size)
-			return loc + (mem->rw_copy - mem->base);
-	}
-
-	return loc;
-}
-
 static int module_memory_alloc(struct module *mod, enum mod_mem_type type)
 {
 	unsigned int size = PAGE_ALIGN(mod->mem[type].size);
@@ -1250,21 +1238,15 @@ static int module_memory_alloc(struct module *mod, enum mod_mem_type type)
 	if (!ptr)
 		return -ENOMEM;
 
-	mod->mem[type].base = ptr;
-
 	if (execmem_is_rox(execmem_type)) {
-		ptr = vzalloc(size);
+		int err = execmem_make_temp_rw(ptr, size);
 
-		if (!ptr) {
-			execmem_free(mod->mem[type].base);
+		if (err) {
+			execmem_free(ptr);
 			return -ENOMEM;
 		}
 
-		mod->mem[type].rw_copy = ptr;
 		mod->mem[type].is_rox = true;
-	} else {
-		mod->mem[type].rw_copy = mod->mem[type].base;
-		memset(mod->mem[type].base, 0, size);
 	}
 
 	/*
@@ -1280,16 +1262,26 @@ static int module_memory_alloc(struct module *mod, enum mod_mem_type type)
 	 */
 	kmemleak_not_leak(ptr);
 
+	memset(ptr, 0, size);
+	mod->mem[type].base = ptr;
+
 	return 0;
 }
 
+static void module_memory_restore_rox(struct module *mod)
+{
+	for_class_mod_mem_type(type, text) {
+		struct module_memory *mem = &mod->mem[type];
+
+		if (mem->is_rox)
+			execmem_restore_rox(mem->base, mem->size);
+	}
+}
+
 static void module_memory_free(struct module *mod, enum mod_mem_type type)
 {
 	struct module_memory *mem = &mod->mem[type];
 
-	if (mem->is_rox)
-		vfree(mem->rw_copy);
-
 	execmem_free(mem->base);
 }
 
@@ -2642,7 +2634,6 @@ static int move_module(struct module *mod, struct load_info *info)
 	for_each_mod_mem_type(type) {
 		if (!mod->mem[type].size) {
 			mod->mem[type].base = NULL;
-			mod->mem[type].rw_copy = NULL;
 			continue;
 		}
 
@@ -2659,7 +2650,6 @@ static int move_module(struct module *mod, struct load_info *info)
 		void *dest;
 		Elf_Shdr *shdr = &info->sechdrs[i];
 		const char *sname;
-		unsigned long addr;
 
 		if (!(shdr->sh_flags & SHF_ALLOC))
 			continue;
@@ -2680,14 +2670,12 @@ static int move_module(struct module *mod, struct load_info *info)
 				ret = PTR_ERR(dest);
 				goto out_err;
 			}
-			addr = (unsigned long)dest;
 			codetag_section_found = true;
 		} else {
 			enum mod_mem_type type = shdr->sh_entsize >> SH_ENTSIZE_TYPE_SHIFT;
 			unsigned long offset = shdr->sh_entsize & SH_ENTSIZE_OFFSET_MASK;
 
-			addr = (unsigned long)mod->mem[type].base + offset;
-			dest = mod->mem[type].rw_copy + offset;
+			dest = mod->mem[type].base + offset;
 		}
 
 		if (shdr->sh_type != SHT_NOBITS) {
@@ -2710,13 +2698,14 @@ static int move_module(struct module *mod, struct load_info *info)
 		 * users of info can keep taking advantage and using the newly
 		 * minted official memory area.
 		 */
-		shdr->sh_addr = addr;
+		shdr->sh_addr = (unsigned long)dest;
 		pr_debug("\t0x%lx 0x%.8lx %s\n", (long)shdr->sh_addr,
 			 (long)shdr->sh_size, info->secstrings + shdr->sh_name);
 	}
 
 	return 0;
 out_err:
+	module_memory_restore_rox(mod);
 	for (t--; t >= 0; t--)
 		module_memory_free(mod, t);
 	if (codetag_section_found)
@@ -2863,17 +2852,8 @@ int __weak module_finalize(const Elf_Ehdr *hdr,
 	return 0;
 }
 
-int __weak module_post_finalize(const Elf_Ehdr *hdr,
-				const Elf_Shdr *sechdrs,
-				struct module *me)
-{
-	return 0;
-}
-
 static int post_relocation(struct module *mod, const struct load_info *info)
 {
-	int ret;
-
 	/* Sort exception table now relocations are done. */
 	sort_extable(mod->extable, mod->extable + mod->num_exentries);
 
@@ -2885,24 +2865,7 @@ static int post_relocation(struct module *mod, const struct load_info *info)
 	add_kallsyms(mod, info);
 
 	/* Arch-specific module finalizing. */
-	ret = module_finalize(info->hdr, info->sechdrs, mod);
-	if (ret)
-		return ret;
-
-	for_each_mod_mem_type(type) {
-		struct module_memory *mem = &mod->mem[type];
-
-		if (mem->is_rox) {
-			if (!execmem_update_copy(mem->base, mem->rw_copy,
-						 mem->size))
-				return -ENOMEM;
-
-			vfree(mem->rw_copy);
-			mem->rw_copy = NULL;
-		}
-	}
-
-	return module_post_finalize(info->hdr, info->sechdrs, mod);
+	return module_finalize(info->hdr, info->sechdrs, mod);
 }
 
 /* Call module constructors. */
@@ -3499,6 +3462,7 @@ static int load_module(struct load_info *info, const char __user *uargs,
 				       mod->mem[type].size);
 	}
 
+	module_memory_restore_rox(mod);
 	module_deallocate(mod, info);
  free_copy:
 	/*
diff --git a/kernel/module/strict_rwx.c b/kernel/module/strict_rwx.c
index 74834ba15615f..03f4142cfbf4e 100644
--- a/kernel/module/strict_rwx.c
+++ b/kernel/module/strict_rwx.c
@@ -9,6 +9,7 @@
 #include <linux/mm.h>
 #include <linux/vmalloc.h>
 #include <linux/set_memory.h>
+#include <linux/execmem.h>
 #include "internal.h"
 
 static int module_set_memory(const struct module *mod, enum mod_mem_type type,
@@ -32,12 +33,12 @@ static int module_set_memory(const struct module *mod, enum mod_mem_type type,
 int module_enable_text_rox(const struct module *mod)
 {
 	for_class_mod_mem_type(type, text) {
+		const struct module_memory *mem = &mod->mem[type];
 		int ret;
 
-		if (mod->mem[type].is_rox)
-			continue;
-
-		if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
+		if (mem->is_rox)
+			ret = execmem_restore_rox(mem->base, mem->size);
+		else if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
 			ret = module_set_memory(mod, type, set_memory_rox);
 		else
 			ret = module_set_memory(mod, type, set_memory_x);

From 1d7e707af446134dd272ea8a89018c63cc17bb6a Mon Sep 17 00:00:00 2001
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Date: Sun, 26 Jan 2025 09:47:31 +0200
Subject: [PATCH 0014/1173] Revert "x86/module: prepare module loading for ROX
 allocations of text"

The module code does not create a writable copy of the executable memory
anymore so there is no need to handle it in module relocation and
alternatives patching.

This reverts commit 9bfc4824fd4836c16bb44f922bfaffba5da3e4f3.

Signed-off-by: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250126074733.1384926-8-rppt@kernel.org
---
 arch/um/kernel/um_arch.c           |  11 +-
 arch/x86/entry/vdso/vma.c          |   3 +-
 arch/x86/include/asm/alternative.h |  14 +--
 arch/x86/kernel/alternative.c      | 181 ++++++++++++-----------------
 arch/x86/kernel/ftrace.c           |  30 +++--
 arch/x86/kernel/module.c           |  45 +++----
 6 files changed, 117 insertions(+), 167 deletions(-)

diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index 79ea97d4797ec..8be91974e786d 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -440,25 +440,24 @@ void __init arch_cpu_finalize_init(void)
 	os_check_bugs();
 }
 
-void apply_seal_endbr(s32 *start, s32 *end, struct module *mod)
+void apply_seal_endbr(s32 *start, s32 *end)
 {
 }
 
-void apply_retpolines(s32 *start, s32 *end, struct module *mod)
+void apply_retpolines(s32 *start, s32 *end)
 {
 }
 
-void apply_returns(s32 *start, s32 *end, struct module *mod)
+void apply_returns(s32 *start, s32 *end)
 {
 }
 
 void apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
-		   s32 *start_cfi, s32 *end_cfi, struct module *mod)
+		   s32 *start_cfi, s32 *end_cfi)
 {
 }
 
-void apply_alternatives(struct alt_instr *start, struct alt_instr *end,
-			struct module *mod)
+void apply_alternatives(struct alt_instr *start, struct alt_instr *end)
 {
 }
 
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 39e6efc1a9cab..bfc7cabf4017b 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -48,8 +48,7 @@ int __init init_vdso_image(const struct vdso_image *image)
 
 	apply_alternatives((struct alt_instr *)(image->data + image->alt),
 			   (struct alt_instr *)(image->data + image->alt +
-						image->alt_len),
-			   NULL);
+						image->alt_len));
 
 	return 0;
 }
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index e3903b731305c..a2141665239b5 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -87,16 +87,16 @@ extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
  * instructions were patched in already:
  */
 extern int alternatives_patched;
-struct module;
 
 extern void alternative_instructions(void);
-extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end,
-			       struct module *mod);
-extern void apply_retpolines(s32 *start, s32 *end, struct module *mod);
-extern void apply_returns(s32 *start, s32 *end, struct module *mod);
-extern void apply_seal_endbr(s32 *start, s32 *end, struct module *mod);
+extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
+extern void apply_retpolines(s32 *start, s32 *end);
+extern void apply_returns(s32 *start, s32 *end);
+extern void apply_seal_endbr(s32 *start, s32 *end);
 extern void apply_fineibt(s32 *start_retpoline, s32 *end_retpoine,
-			  s32 *start_cfi, s32 *end_cfi, struct module *mod);
+			  s32 *start_cfi, s32 *end_cfi);
+
+struct module;
 
 struct callthunk_sites {
 	s32				*call_start, *call_end;
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index c71b575bf2292..8b66a555d2f03 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -392,10 +392,8 @@ EXPORT_SYMBOL(BUG_func);
  * Rewrite the "call BUG_func" replacement to point to the target of the
  * indirect pv_ops call "call *disp(%ip)".
  */
-static int alt_replace_call(u8 *instr, u8 *insn_buff, struct alt_instr *a,
-			    struct module *mod)
+static int alt_replace_call(u8 *instr, u8 *insn_buff, struct alt_instr *a)
 {
-	u8 *wr_instr = module_writable_address(mod, instr);
 	void *target, *bug = &BUG_func;
 	s32 disp;
 
@@ -405,14 +403,14 @@ static int alt_replace_call(u8 *instr, u8 *insn_buff, struct alt_instr *a,
 	}
 
 	if (a->instrlen != 6 ||
-	    wr_instr[0] != CALL_RIP_REL_OPCODE ||
-	    wr_instr[1] != CALL_RIP_REL_MODRM) {
+	    instr[0] != CALL_RIP_REL_OPCODE ||
+	    instr[1] != CALL_RIP_REL_MODRM) {
 		pr_err("ALT_FLAG_DIRECT_CALL set for unrecognized indirect call\n");
 		BUG();
 	}
 
 	/* Skip CALL_RIP_REL_OPCODE and CALL_RIP_REL_MODRM */
-	disp = *(s32 *)(wr_instr + 2);
+	disp = *(s32 *)(instr + 2);
 #ifdef CONFIG_X86_64
 	/* ff 15 00 00 00 00   call   *0x0(%rip) */
 	/* target address is stored at "next instruction + disp". */
@@ -450,8 +448,7 @@ static inline u8 * instr_va(struct alt_instr *i)
  * to refetch changed I$ lines.
  */
 void __init_or_module noinline apply_alternatives(struct alt_instr *start,
-						  struct alt_instr *end,
-						  struct module *mod)
+						  struct alt_instr *end)
 {
 	u8 insn_buff[MAX_PATCH_LEN];
 	u8 *instr, *replacement;
@@ -480,7 +477,6 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 	 */
 	for (a = start; a < end; a++) {
 		int insn_buff_sz = 0;
-		u8 *wr_instr, *wr_replacement;
 
 		/*
 		 * In case of nested ALTERNATIVE()s the outer alternative might
@@ -494,11 +490,7 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 		}
 
 		instr = instr_va(a);
-		wr_instr = module_writable_address(mod, instr);
-
 		replacement = (u8 *)&a->repl_offset + a->repl_offset;
-		wr_replacement = module_writable_address(mod, replacement);
-
 		BUG_ON(a->instrlen > sizeof(insn_buff));
 		BUG_ON(a->cpuid >= (NCAPINTS + NBUGINTS) * 32);
 
@@ -509,9 +501,9 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 		 *   patch if feature is *NOT* present.
 		 */
 		if (!boot_cpu_has(a->cpuid) == !(a->flags & ALT_FLAG_NOT)) {
-			memcpy(insn_buff, wr_instr, a->instrlen);
+			memcpy(insn_buff, instr, a->instrlen);
 			optimize_nops(instr, insn_buff, a->instrlen);
-			text_poke_early(wr_instr, insn_buff, a->instrlen);
+			text_poke_early(instr, insn_buff, a->instrlen);
 			continue;
 		}
 
@@ -521,12 +513,11 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 			instr, instr, a->instrlen,
 			replacement, a->replacementlen, a->flags);
 
-		memcpy(insn_buff, wr_replacement, a->replacementlen);
+		memcpy(insn_buff, replacement, a->replacementlen);
 		insn_buff_sz = a->replacementlen;
 
 		if (a->flags & ALT_FLAG_DIRECT_CALL) {
-			insn_buff_sz = alt_replace_call(instr, insn_buff, a,
-							mod);
+			insn_buff_sz = alt_replace_call(instr, insn_buff, a);
 			if (insn_buff_sz < 0)
 				continue;
 		}
@@ -536,11 +527,11 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 
 		apply_relocation(insn_buff, instr, a->instrlen, replacement, a->replacementlen);
 
-		DUMP_BYTES(ALT, wr_instr, a->instrlen, "%px:   old_insn: ", instr);
+		DUMP_BYTES(ALT, instr, a->instrlen, "%px:   old_insn: ", instr);
 		DUMP_BYTES(ALT, replacement, a->replacementlen, "%px:   rpl_insn: ", replacement);
 		DUMP_BYTES(ALT, insn_buff, insn_buff_sz, "%px: final_insn: ", instr);
 
-		text_poke_early(wr_instr, insn_buff, insn_buff_sz);
+		text_poke_early(instr, insn_buff, insn_buff_sz);
 	}
 
 	kasan_enable_current();
@@ -731,20 +722,18 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes)
 /*
  * Generated by 'objtool --retpoline'.
  */
-void __init_or_module noinline apply_retpolines(s32 *start, s32 *end,
-						struct module *mod)
+void __init_or_module noinline apply_retpolines(s32 *start, s32 *end)
 {
 	s32 *s;
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr = module_writable_address(mod, addr);
 		struct insn insn;
 		int len, ret;
 		u8 bytes[16];
 		u8 op1, op2;
 
-		ret = insn_decode_kernel(&insn, wr_addr);
+		ret = insn_decode_kernel(&insn, addr);
 		if (WARN_ON_ONCE(ret < 0))
 			continue;
 
@@ -772,9 +761,9 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end,
 		len = patch_retpoline(addr, &insn, bytes);
 		if (len == insn.length) {
 			optimize_nops(addr, bytes, len);
-			DUMP_BYTES(RETPOLINE, ((u8*)wr_addr),  len, "%px: orig: ", addr);
+			DUMP_BYTES(RETPOLINE, ((u8*)addr),  len, "%px: orig: ", addr);
 			DUMP_BYTES(RETPOLINE, ((u8*)bytes), len, "%px: repl: ", addr);
-			text_poke_early(wr_addr, bytes, len);
+			text_poke_early(addr, bytes, len);
 		}
 	}
 }
@@ -810,8 +799,7 @@ static int patch_return(void *addr, struct insn *insn, u8 *bytes)
 	return i;
 }
 
-void __init_or_module noinline apply_returns(s32 *start, s32 *end,
-					     struct module *mod)
+void __init_or_module noinline apply_returns(s32 *start, s32 *end)
 {
 	s32 *s;
 
@@ -820,13 +808,12 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end,
 
 	for (s = start; s < end; s++) {
 		void *dest = NULL, *addr = (void *)s + *s;
-		void *wr_addr = module_writable_address(mod, addr);
 		struct insn insn;
 		int len, ret;
 		u8 bytes[16];
 		u8 op;
 
-		ret = insn_decode_kernel(&insn, wr_addr);
+		ret = insn_decode_kernel(&insn, addr);
 		if (WARN_ON_ONCE(ret < 0))
 			continue;
 
@@ -846,35 +833,32 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end,
 
 		len = patch_return(addr, &insn, bytes);
 		if (len == insn.length) {
-			DUMP_BYTES(RET, ((u8*)wr_addr),  len, "%px: orig: ", addr);
+			DUMP_BYTES(RET, ((u8*)addr),  len, "%px: orig: ", addr);
 			DUMP_BYTES(RET, ((u8*)bytes), len, "%px: repl: ", addr);
-			text_poke_early(wr_addr, bytes, len);
+			text_poke_early(addr, bytes, len);
 		}
 	}
 }
 #else
-void __init_or_module noinline apply_returns(s32 *start, s32 *end,
-					     struct module *mod) { }
+void __init_or_module noinline apply_returns(s32 *start, s32 *end) { }
 #endif /* CONFIG_MITIGATION_RETHUNK */
 
 #else /* !CONFIG_MITIGATION_RETPOLINE || !CONFIG_OBJTOOL */
 
-void __init_or_module noinline apply_retpolines(s32 *start, s32 *end,
-						struct module *mod) { }
-void __init_or_module noinline apply_returns(s32 *start, s32 *end,
-					     struct module *mod) { }
+void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) { }
+void __init_or_module noinline apply_returns(s32 *start, s32 *end) { }
 
 #endif /* CONFIG_MITIGATION_RETPOLINE && CONFIG_OBJTOOL */
 
 #ifdef CONFIG_X86_KERNEL_IBT
 
-static void poison_cfi(void *addr, void *wr_addr);
+static void poison_cfi(void *addr);
 
-static void __init_or_module poison_endbr(void *addr, void *wr_addr, bool warn)
+static void __init_or_module poison_endbr(void *addr, bool warn)
 {
 	u32 endbr, poison = gen_endbr_poison();
 
-	if (WARN_ON_ONCE(get_kernel_nofault(endbr, wr_addr)))
+	if (WARN_ON_ONCE(get_kernel_nofault(endbr, addr)))
 		return;
 
 	if (!is_endbr(endbr)) {
@@ -889,7 +873,7 @@ static void __init_or_module poison_endbr(void *addr, void *wr_addr, bool warn)
 	 */
 	DUMP_BYTES(ENDBR, ((u8*)addr), 4, "%px: orig: ", addr);
 	DUMP_BYTES(ENDBR, ((u8*)&poison), 4, "%px: repl: ", addr);
-	text_poke_early(wr_addr, &poison, 4);
+	text_poke_early(addr, &poison, 4);
 }
 
 /*
@@ -898,23 +882,22 @@ static void __init_or_module poison_endbr(void *addr, void *wr_addr, bool warn)
  * Seal the functions for indirect calls by clobbering the ENDBR instructions
  * and the kCFI hash value.
  */
-void __init_or_module noinline apply_seal_endbr(s32 *start, s32 *end, struct module *mod)
+void __init_or_module noinline apply_seal_endbr(s32 *start, s32 *end)
 {
 	s32 *s;
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr = module_writable_address(mod, addr);
 
-		poison_endbr(addr, wr_addr, true);
+		poison_endbr(addr, true);
 		if (IS_ENABLED(CONFIG_FINEIBT))
-			poison_cfi(addr - 16, wr_addr - 16);
+			poison_cfi(addr - 16);
 	}
 }
 
 #else
 
-void __init_or_module apply_seal_endbr(s32 *start, s32 *end, struct module *mod) { }
+void __init_or_module apply_seal_endbr(s32 *start, s32 *end) { }
 
 #endif /* CONFIG_X86_KERNEL_IBT */
 
@@ -1136,7 +1119,7 @@ static u32 decode_caller_hash(void *addr)
 }
 
 /* .retpoline_sites */
-static int cfi_disable_callers(s32 *start, s32 *end, struct module *mod)
+static int cfi_disable_callers(s32 *start, s32 *end)
 {
 	/*
 	 * Disable kCFI by patching in a JMP.d8, this leaves the hash immediate
@@ -1148,23 +1131,20 @@ static int cfi_disable_callers(s32 *start, s32 *end, struct module *mod)
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr;
 		u32 hash;
 
 		addr -= fineibt_caller_size;
-		wr_addr = module_writable_address(mod, addr);
-		hash = decode_caller_hash(wr_addr);
-
+		hash = decode_caller_hash(addr);
 		if (!hash) /* nocfi callers */
 			continue;
 
-		text_poke_early(wr_addr, jmp, 2);
+		text_poke_early(addr, jmp, 2);
 	}
 
 	return 0;
 }
 
-static int cfi_enable_callers(s32 *start, s32 *end, struct module *mod)
+static int cfi_enable_callers(s32 *start, s32 *end)
 {
 	/*
 	 * Re-enable kCFI, undo what cfi_disable_callers() did.
@@ -1174,115 +1154,106 @@ static int cfi_enable_callers(s32 *start, s32 *end, struct module *mod)
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr;
 		u32 hash;
 
 		addr -= fineibt_caller_size;
-		wr_addr = module_writable_address(mod, addr);
-		hash = decode_caller_hash(wr_addr);
+		hash = decode_caller_hash(addr);
 		if (!hash) /* nocfi callers */
 			continue;
 
-		text_poke_early(wr_addr, mov, 2);
+		text_poke_early(addr, mov, 2);
 	}
 
 	return 0;
 }
 
 /* .cfi_sites */
-static int cfi_rand_preamble(s32 *start, s32 *end, struct module *mod)
+static int cfi_rand_preamble(s32 *start, s32 *end)
 {
 	s32 *s;
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr = module_writable_address(mod, addr);
 		u32 hash;
 
-		hash = decode_preamble_hash(wr_addr);
+		hash = decode_preamble_hash(addr);
 		if (WARN(!hash, "no CFI hash found at: %pS %px %*ph\n",
 			 addr, addr, 5, addr))
 			return -EINVAL;
 
 		hash = cfi_rehash(hash);
-		text_poke_early(wr_addr + 1, &hash, 4);
+		text_poke_early(addr + 1, &hash, 4);
 	}
 
 	return 0;
 }
 
-static int cfi_rewrite_preamble(s32 *start, s32 *end, struct module *mod)
+static int cfi_rewrite_preamble(s32 *start, s32 *end)
 {
 	s32 *s;
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr = module_writable_address(mod, addr);
 		u32 hash;
 
-		hash = decode_preamble_hash(wr_addr);
+		hash = decode_preamble_hash(addr);
 		if (WARN(!hash, "no CFI hash found at: %pS %px %*ph\n",
 			 addr, addr, 5, addr))
 			return -EINVAL;
 
-		text_poke_early(wr_addr, fineibt_preamble_start, fineibt_preamble_size);
-		WARN_ON(*(u32 *)(wr_addr + fineibt_preamble_hash) != 0x12345678);
-		text_poke_early(wr_addr + fineibt_preamble_hash, &hash, 4);
+		text_poke_early(addr, fineibt_preamble_start, fineibt_preamble_size);
+		WARN_ON(*(u32 *)(addr + fineibt_preamble_hash) != 0x12345678);
+		text_poke_early(addr + fineibt_preamble_hash, &hash, 4);
 	}
 
 	return 0;
 }
 
-static void cfi_rewrite_endbr(s32 *start, s32 *end, struct module *mod)
+static void cfi_rewrite_endbr(s32 *start, s32 *end)
 {
 	s32 *s;
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr = module_writable_address(mod, addr);
 
-		poison_endbr(addr + 16, wr_addr + 16, false);
+		poison_endbr(addr+16, false);
 	}
 }
 
 /* .retpoline_sites */
-static int cfi_rand_callers(s32 *start, s32 *end, struct module *mod)
+static int cfi_rand_callers(s32 *start, s32 *end)
 {
 	s32 *s;
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr;
 		u32 hash;
 
 		addr -= fineibt_caller_size;
-		wr_addr = module_writable_address(mod, addr);
-		hash = decode_caller_hash(wr_addr);
+		hash = decode_caller_hash(addr);
 		if (hash) {
 			hash = -cfi_rehash(hash);
-			text_poke_early(wr_addr + 2, &hash, 4);
+			text_poke_early(addr + 2, &hash, 4);
 		}
 	}
 
 	return 0;
 }
 
-static int cfi_rewrite_callers(s32 *start, s32 *end, struct module *mod)
+static int cfi_rewrite_callers(s32 *start, s32 *end)
 {
 	s32 *s;
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr;
 		u32 hash;
 
 		addr -= fineibt_caller_size;
-		wr_addr = module_writable_address(mod, addr);
-		hash = decode_caller_hash(wr_addr);
+		hash = decode_caller_hash(addr);
 		if (hash) {
-			text_poke_early(wr_addr, fineibt_caller_start, fineibt_caller_size);
-			WARN_ON(*(u32 *)(wr_addr + fineibt_caller_hash) != 0x12345678);
-			text_poke_early(wr_addr + fineibt_caller_hash, &hash, 4);
+			text_poke_early(addr, fineibt_caller_start, fineibt_caller_size);
+			WARN_ON(*(u32 *)(addr + fineibt_caller_hash) != 0x12345678);
+			text_poke_early(addr + fineibt_caller_hash, &hash, 4);
 		}
 		/* rely on apply_retpolines() */
 	}
@@ -1291,9 +1262,8 @@ static int cfi_rewrite_callers(s32 *start, s32 *end, struct module *mod)
 }
 
 static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
-			    s32 *start_cfi, s32 *end_cfi, struct module *mod)
+			    s32 *start_cfi, s32 *end_cfi, bool builtin)
 {
-	bool builtin = mod ? false : true;
 	int ret;
 
 	if (WARN_ONCE(fineibt_preamble_size != 16,
@@ -1311,7 +1281,7 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 	 * rewrite them. This disables all CFI. If this succeeds but any of the
 	 * later stages fails, we're without CFI.
 	 */
-	ret = cfi_disable_callers(start_retpoline, end_retpoline, mod);
+	ret = cfi_disable_callers(start_retpoline, end_retpoline);
 	if (ret)
 		goto err;
 
@@ -1322,11 +1292,11 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 			cfi_bpf_subprog_hash = cfi_rehash(cfi_bpf_subprog_hash);
 		}
 
-		ret = cfi_rand_preamble(start_cfi, end_cfi, mod);
+		ret = cfi_rand_preamble(start_cfi, end_cfi);
 		if (ret)
 			goto err;
 
-		ret = cfi_rand_callers(start_retpoline, end_retpoline, mod);
+		ret = cfi_rand_callers(start_retpoline, end_retpoline);
 		if (ret)
 			goto err;
 	}
@@ -1338,7 +1308,7 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 		return;
 
 	case CFI_KCFI:
-		ret = cfi_enable_callers(start_retpoline, end_retpoline, mod);
+		ret = cfi_enable_callers(start_retpoline, end_retpoline);
 		if (ret)
 			goto err;
 
@@ -1348,17 +1318,17 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 
 	case CFI_FINEIBT:
 		/* place the FineIBT preamble at func()-16 */
-		ret = cfi_rewrite_preamble(start_cfi, end_cfi, mod);
+		ret = cfi_rewrite_preamble(start_cfi, end_cfi);
 		if (ret)
 			goto err;
 
 		/* rewrite the callers to target func()-16 */
-		ret = cfi_rewrite_callers(start_retpoline, end_retpoline, mod);
+		ret = cfi_rewrite_callers(start_retpoline, end_retpoline);
 		if (ret)
 			goto err;
 
 		/* now that nobody targets func()+0, remove ENDBR there */
-		cfi_rewrite_endbr(start_cfi, end_cfi, mod);
+		cfi_rewrite_endbr(start_cfi, end_cfi);
 
 		if (builtin)
 			pr_info("Using FineIBT CFI\n");
@@ -1377,7 +1347,7 @@ static inline void poison_hash(void *addr)
 	*(u32 *)addr = 0;
 }
 
-static void poison_cfi(void *addr, void *wr_addr)
+static void poison_cfi(void *addr)
 {
 	switch (cfi_mode) {
 	case CFI_FINEIBT:
@@ -1389,8 +1359,8 @@ static void poison_cfi(void *addr, void *wr_addr)
 		 *	ud2
 		 * 1:	nop
 		 */
-		poison_endbr(addr, wr_addr, false);
-		poison_hash(wr_addr + fineibt_preamble_hash);
+		poison_endbr(addr, false);
+		poison_hash(addr + fineibt_preamble_hash);
 		break;
 
 	case CFI_KCFI:
@@ -1399,7 +1369,7 @@ static void poison_cfi(void *addr, void *wr_addr)
 		 *	movl	$0, %eax
 		 *	.skip	11, 0x90
 		 */
-		poison_hash(wr_addr + 1);
+		poison_hash(addr + 1);
 		break;
 
 	default:
@@ -1410,21 +1380,22 @@ static void poison_cfi(void *addr, void *wr_addr)
 #else
 
 static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
-			    s32 *start_cfi, s32 *end_cfi, struct module *mod)
+			    s32 *start_cfi, s32 *end_cfi, bool builtin)
 {
 }
 
 #ifdef CONFIG_X86_KERNEL_IBT
-static void poison_cfi(void *addr, void *wr_addr) { }
+static void poison_cfi(void *addr) { }
 #endif
 
 #endif
 
 void apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
-		   s32 *start_cfi, s32 *end_cfi, struct module *mod)
+		   s32 *start_cfi, s32 *end_cfi)
 {
 	return __apply_fineibt(start_retpoline, end_retpoline,
-			       start_cfi, end_cfi, mod);
+			       start_cfi, end_cfi,
+			       /* .builtin = */ false);
 }
 
 #ifdef CONFIG_SMP
@@ -1721,16 +1692,16 @@ void __init alternative_instructions(void)
 	paravirt_set_cap();
 
 	__apply_fineibt(__retpoline_sites, __retpoline_sites_end,
-			__cfi_sites, __cfi_sites_end, NULL);
+			__cfi_sites, __cfi_sites_end, true);
 
 	/*
 	 * Rewrite the retpolines, must be done before alternatives since
 	 * those can rewrite the retpoline thunks.
 	 */
-	apply_retpolines(__retpoline_sites, __retpoline_sites_end, NULL);
-	apply_returns(__return_sites, __return_sites_end, NULL);
+	apply_retpolines(__retpoline_sites, __retpoline_sites_end);
+	apply_returns(__return_sites, __return_sites_end);
 
-	apply_alternatives(__alt_instructions, __alt_instructions_end, NULL);
+	apply_alternatives(__alt_instructions, __alt_instructions_end);
 
 	/*
 	 * Now all calls are established. Apply the call thunks if
@@ -1741,7 +1712,7 @@ void __init alternative_instructions(void)
 	/*
 	 * Seal all functions that do not have their address taken.
 	 */
-	apply_seal_endbr(__ibt_endbr_seal, __ibt_endbr_seal_end, NULL);
+	apply_seal_endbr(__ibt_endbr_seal, __ibt_endbr_seal_end);
 
 #ifdef CONFIG_SMP
 	/* Patch to UP if other cpus not imminent. */
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 166bc0ea3bdff..cace6e8d7cc77 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -118,13 +118,10 @@ ftrace_modify_code_direct(unsigned long ip, const char *old_code,
 		return ret;
 
 	/* replace the text with the new text */
-	if (ftrace_poke_late) {
+	if (ftrace_poke_late)
 		text_poke_queue((void *)ip, new_code, MCOUNT_INSN_SIZE, NULL);
-	} else {
-		mutex_lock(&text_mutex);
-		text_poke((void *)ip, new_code, MCOUNT_INSN_SIZE);
-		mutex_unlock(&text_mutex);
-	}
+	else
+		text_poke_early((void *)ip, new_code, MCOUNT_INSN_SIZE);
 	return 0;
 }
 
@@ -321,7 +318,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	unsigned const char op_ref[] = { 0x48, 0x8b, 0x15 };
 	unsigned const char retq[] = { RET_INSN_OPCODE, INT3_INSN_OPCODE };
 	union ftrace_op_code_union op_ptr;
-	void *ret;
+	int ret;
 
 	if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) {
 		start_offset = (unsigned long)ftrace_regs_caller;
@@ -352,15 +349,15 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	npages = DIV_ROUND_UP(*tramp_size, PAGE_SIZE);
 
 	/* Copy ftrace_caller onto the trampoline memory */
-	ret = text_poke_copy(trampoline, (void *)start_offset, size);
-	if (WARN_ON(!ret))
+	ret = copy_from_kernel_nofault(trampoline, (void *)start_offset, size);
+	if (WARN_ON(ret < 0))
 		goto fail;
 
 	ip = trampoline + size;
 	if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
 		__text_gen_insn(ip, JMP32_INSN_OPCODE, ip, x86_return_thunk, JMP32_INSN_SIZE);
 	else
-		text_poke_copy(ip, retq, sizeof(retq));
+		memcpy(ip, retq, sizeof(retq));
 
 	/* No need to test direct calls on created trampolines */
 	if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) {
@@ -368,7 +365,8 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 		ip = trampoline + (jmp_offset - start_offset);
 		if (WARN_ON(*(char *)ip != 0x75))
 			goto fail;
-		if (!text_poke_copy(ip, x86_nops[2], 2))
+		ret = copy_from_kernel_nofault(ip, x86_nops[2], 2);
+		if (ret < 0)
 			goto fail;
 	}
 
@@ -381,7 +379,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	 */
 
 	ptr = (unsigned long *)(trampoline + size + RET_SIZE);
-	text_poke_copy(ptr, &ops, sizeof(unsigned long));
+	*ptr = (unsigned long)ops;
 
 	op_offset -= start_offset;
 	memcpy(&op_ptr, trampoline + op_offset, OP_REF_SIZE);
@@ -397,7 +395,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	op_ptr.offset = offset;
 
 	/* put in the new offset to the ftrace_ops */
-	text_poke_copy(trampoline + op_offset, &op_ptr, OP_REF_SIZE);
+	memcpy(trampoline + op_offset, &op_ptr, OP_REF_SIZE);
 
 	/* put in the call to the function */
 	mutex_lock(&text_mutex);
@@ -407,9 +405,9 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	 * the depth accounting before the call already.
 	 */
 	dest = ftrace_ops_get_func(ops);
-	text_poke_copy_locked(trampoline + call_offset,
-	      text_gen_insn(CALL_INSN_OPCODE, trampoline + call_offset, dest),
-	      CALL_INSN_SIZE, false);
+	memcpy(trampoline + call_offset,
+	       text_gen_insn(CALL_INSN_OPCODE, trampoline + call_offset, dest),
+	       CALL_INSN_SIZE);
 	mutex_unlock(&text_mutex);
 
 	/* ALLOC_TRAMP flags lets us know we created it */
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index 8984abd91c001..837450b6e882f 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -146,21 +146,18 @@ static int __write_relocate_add(Elf64_Shdr *sechdrs,
 		}
 
 		if (apply) {
-			void *wr_loc = module_writable_address(me, loc);
-
-			if (memcmp(wr_loc, &zero, size)) {
+			if (memcmp(loc, &zero, size)) {
 				pr_err("x86/modules: Invalid relocation target, existing value is nonzero for type %d, loc %p, val %Lx\n",
 				       (int)ELF64_R_TYPE(rel[i].r_info), loc, val);
 				return -ENOEXEC;
 			}
-			write(wr_loc, &val, size);
+			write(loc, &val, size);
 		} else {
 			if (memcmp(loc, &val, size)) {
 				pr_warn("x86/modules: Invalid relocation target, existing value does not match expected value for type %d, loc %p, val %Lx\n",
 					(int)ELF64_R_TYPE(rel[i].r_info), loc, val);
 				return -ENOEXEC;
 			}
-			/* FIXME: needs care for ROX module allocations */
 			write(loc, &zero, size);
 		}
 	}
@@ -227,7 +224,7 @@ int module_finalize(const Elf_Ehdr *hdr,
 		    const Elf_Shdr *sechdrs,
 		    struct module *me)
 {
-	const Elf_Shdr *s, *alt = NULL,
+	const Elf_Shdr *s, *alt = NULL, *locks = NULL,
 		*orc = NULL, *orc_ip = NULL,
 		*retpolines = NULL, *returns = NULL, *ibt_endbr = NULL,
 		*calls = NULL, *cfi = NULL;
@@ -236,6 +233,8 @@ int module_finalize(const Elf_Ehdr *hdr,
 	for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
 		if (!strcmp(".altinstructions", secstrings + s->sh_name))
 			alt = s;
+		if (!strcmp(".smp_locks", secstrings + s->sh_name))
+			locks = s;
 		if (!strcmp(".orc_unwind", secstrings + s->sh_name))
 			orc = s;
 		if (!strcmp(".orc_unwind_ip", secstrings + s->sh_name))
@@ -266,20 +265,20 @@ int module_finalize(const Elf_Ehdr *hdr,
 			csize = cfi->sh_size;
 		}
 
-		apply_fineibt(rseg, rseg + rsize, cseg, cseg + csize, me);
+		apply_fineibt(rseg, rseg + rsize, cseg, cseg + csize);
 	}
 	if (retpolines) {
 		void *rseg = (void *)retpolines->sh_addr;
-		apply_retpolines(rseg, rseg + retpolines->sh_size, me);
+		apply_retpolines(rseg, rseg + retpolines->sh_size);
 	}
 	if (returns) {
 		void *rseg = (void *)returns->sh_addr;
-		apply_returns(rseg, rseg + returns->sh_size, me);
+		apply_returns(rseg, rseg + returns->sh_size);
 	}
 	if (alt) {
 		/* patch .altinstructions */
 		void *aseg = (void *)alt->sh_addr;
-		apply_alternatives(aseg, aseg + alt->sh_size, me);
+		apply_alternatives(aseg, aseg + alt->sh_size);
 	}
 	if (calls || alt) {
 		struct callthunk_sites cs = {};
@@ -298,28 +297,8 @@ int module_finalize(const Elf_Ehdr *hdr,
 	}
 	if (ibt_endbr) {
 		void *iseg = (void *)ibt_endbr->sh_addr;
-		apply_seal_endbr(iseg, iseg + ibt_endbr->sh_size, me);
+		apply_seal_endbr(iseg, iseg + ibt_endbr->sh_size);
 	}
-
-	if (orc && orc_ip)
-		unwind_module_init(me, (void *)orc_ip->sh_addr, orc_ip->sh_size,
-				   (void *)orc->sh_addr, orc->sh_size);
-
-	return 0;
-}
-
-int module_post_finalize(const Elf_Ehdr *hdr,
-			 const Elf_Shdr *sechdrs,
-			 struct module *me)
-{
-	const Elf_Shdr *s, *locks = NULL;
-	char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
-
-	for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
-		if (!strcmp(".smp_locks", secstrings + s->sh_name))
-			locks = s;
-	}
-
 	if (locks) {
 		void *lseg = (void *)locks->sh_addr;
 		void *text = me->mem[MOD_TEXT].base;
@@ -329,6 +308,10 @@ int module_post_finalize(const Elf_Ehdr *hdr,
 					    text, text_end);
 	}
 
+	if (orc && orc_ip)
+		unwind_module_init(me, (void *)orc_ip->sh_addr, orc_ip->sh_size,
+				   (void *)orc->sh_addr, orc->sh_size);
+
 	return 0;
 }
 

From 602df3712979de594d268e8cbca46a93126c977d Mon Sep 17 00:00:00 2001
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Date: Sun, 26 Jan 2025 09:47:32 +0200
Subject: [PATCH 0015/1173] module: drop unused module_writable_address()

module_writable_address() is unused and can be removed.

Signed-off-by: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250126074733.1384926-9-rppt@kernel.org
---
 include/linux/module.h | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/include/linux/module.h b/include/linux/module.h
index ddf27ede7c91d..a76928c93692f 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -768,11 +768,6 @@ static inline bool is_livepatch_module(struct module *mod)
 
 void set_module_sig_enforced(void);
 
-static inline void *module_writable_address(struct module *mod, void *loc)
-{
-	return loc;
-}
-
 #else /* !CONFIG_MODULES... */
 
 static inline struct module *__module_address(unsigned long addr)
@@ -880,11 +875,6 @@ static inline bool module_is_coming(struct module *mod)
 {
 	return false;
 }
-
-static inline void *module_writable_address(struct module *mod, void *loc)
-{
-	return loc;
-}
 #endif /* CONFIG_MODULES */
 
 #ifdef CONFIG_SYSFS

From 64f6a4e10c05ed527f0f24b7954964255e0d3535 Mon Sep 17 00:00:00 2001
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Date: Sun, 26 Jan 2025 09:47:33 +0200
Subject: [PATCH 0016/1173] x86: re-enable EXECMEM_ROX support

after rework of execmem ROX caches

Signed-off-by: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250126074733.1384926-10-rppt@kernel.org
---
 arch/x86/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 87198d957e2f1..6df7779ed6da0 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -85,6 +85,7 @@ config X86
 	select ARCH_HAS_DMA_OPS			if GART_IOMMU || XEN
 	select ARCH_HAS_EARLY_DEBUG		if KGDB
 	select ARCH_HAS_ELF_RANDOMIZE
+	select ARCH_HAS_EXECMEM_ROX		if X86_64
 	select ARCH_HAS_FAST_MULTIPLIER
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL

From 3ef938c3503563bfc2ac15083557f880d29c2e64 Mon Sep 17 00:00:00 2001
From: Jann Horn <jannh@google.com>
Date: Fri, 3 Jan 2025 19:39:38 +0100
Subject: [PATCH 0017/1173] x86/mm: Fix flush_tlb_range() when used for zapping
 normal PMDs

On the following path, flush_tlb_range() can be used for zapping normal
PMD entries (PMD entries that point to page tables) together with the PTE
entries in the pointed-to page table:

    collapse_pte_mapped_thp
      pmdp_collapse_flush
        flush_tlb_range

The arm64 version of flush_tlb_range() has a comment describing that it can
be used for page table removal, and does not use any last-level
invalidation optimizations. Fix the X86 version by making it behave the
same way.

Currently, X86 only uses this information for the following two purposes,
which I think means the issue doesn't have much impact:

 - In native_flush_tlb_multi() for checking if lazy TLB CPUs need to be
   IPI'd to avoid issues with speculative page table walks.
 - In Hyper-V TLB paravirtualization, again for lazy TLB stuff.

The patch "x86/mm: only invalidate final translations with INVLPGB" which
is currently under review (see
<https://lore.kernel.org/all/20241230175550.4046587-13-riel@surriel.com/>)
would probably be making the impact of this a lot worse.

Fixes: 016c4d92cd16 ("x86/mm/tlb: Add freed_tables argument to flush_tlb_mm_range")
Signed-off-by: Jann Horn <jannh@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20250103-x86-collapse-flush-fix-v1-1-3c521856cfa6@google.com
---
 arch/x86/include/asm/tlbflush.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 02fc2aa06e9e0..3da6451397485 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -242,7 +242,7 @@ void flush_tlb_multi(const struct cpumask *cpumask,
 	flush_tlb_mm_range((vma)->vm_mm, start, end,			\
 			   ((vma)->vm_flags & VM_HUGETLB)		\
 				? huge_page_shift(hstate_vma(vma))	\
-				: PAGE_SHIFT, false)
+				: PAGE_SHIFT, true)
 
 extern void flush_tlb_all(void);
 extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,

From 003c0414318a1829a1a5b195ad81e8a7960c3f5d Mon Sep 17 00:00:00 2001
From: Ravi Bangoria <ravi.bangoria@amd.com>
Date: Wed, 15 Jan 2025 05:44:30 +0000
Subject: [PATCH 0018/1173] perf/amd/ibs: Remove IBS_{FETCH|OP}_CONFIG_MASK
 macros

Definition of these macros are very simple and they are used at only one
place. Get rid of unnecessary redirection.

Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/r/20250115054438.1021-2-ravi.bangoria@amd.com
---
 arch/x86/events/amd/ibs.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index e7a8b8758e088..4ca8006d22210 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -28,9 +28,6 @@ static u32 ibs_caps;
 #include <asm/nmi.h>
 #include <asm/amd-ibs.h>
 
-#define IBS_FETCH_CONFIG_MASK	(IBS_FETCH_RAND_EN | IBS_FETCH_MAX_CNT)
-#define IBS_OP_CONFIG_MASK	IBS_OP_MAX_CNT
-
 /* attr.config2 */
 #define IBS_SW_FILTER_MASK	1
 
@@ -688,7 +685,7 @@ static struct perf_ibs perf_ibs_fetch = {
 		.read		= perf_ibs_read,
 	},
 	.msr			= MSR_AMD64_IBSFETCHCTL,
-	.config_mask		= IBS_FETCH_CONFIG_MASK,
+	.config_mask		= IBS_FETCH_MAX_CNT | IBS_FETCH_RAND_EN,
 	.cnt_mask		= IBS_FETCH_MAX_CNT,
 	.enable_mask		= IBS_FETCH_ENABLE,
 	.valid_mask		= IBS_FETCH_VAL,
@@ -711,7 +708,7 @@ static struct perf_ibs perf_ibs_op = {
 		.read		= perf_ibs_read,
 	},
 	.msr			= MSR_AMD64_IBSOPCTL,
-	.config_mask		= IBS_OP_CONFIG_MASK,
+	.config_mask		= IBS_OP_MAX_CNT,
 	.cnt_mask		= IBS_OP_MAX_CNT | IBS_OP_CUR_CNT |
 				  IBS_OP_CUR_CNT_RAND,
 	.enable_mask		= IBS_OP_ENABLE,

From 88c7bcad71c83f52f24108dedcecae0d18dbc627 Mon Sep 17 00:00:00 2001
From: Ravi Bangoria <ravi.bangoria@amd.com>
Date: Wed, 15 Jan 2025 05:44:31 +0000
Subject: [PATCH 0019/1173] perf/amd/ibs: Remove pointless sample period check

Valid perf event sample period value for IBS PMUs (Fetch and Op both)
is limited to multiple of 0x10. perf_ibs_init() has this check:

  if (!event->attr.sample_freq && hwc->sample_period & 0x0f)
          return -EINVAL;

But it's broken since hwc->sample_period will always be 0 when
event->attr.sample_freq is 0 (irrespective of event->attr.freq value.)

One option to fix this is to change the condition:

  - if (!event->attr.sample_freq && hwc->sample_period & 0x0f)
  + if (!event->attr.freq && hwc->sample_period & 0x0f)

However, that will break all userspace tools which have been using IBS
event with sample_period not multiple of 0x10.

Another option is to remove the condition altogether and mask lower
nibble _silently_, same as what current code is inadvertently doing.
I'm preferring this approach as it keeps the existing behavior.

Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/r/20250115054438.1021-3-ravi.bangoria@amd.com
---
 arch/x86/events/amd/ibs.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 4ca8006d22210..bd8919e7c3b17 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -307,13 +307,8 @@ static int perf_ibs_init(struct perf_event *event)
 		if (config & perf_ibs->cnt_mask)
 			/* raw max_cnt may not be set */
 			return -EINVAL;
-		if (!event->attr.sample_freq && hwc->sample_period & 0x0f)
-			/*
-			 * lower 4 bits can not be set in ibs max cnt,
-			 * but allowing it in case we adjust the
-			 * sample period to set a frequency.
-			 */
-			return -EINVAL;
+
+		/* Silently mask off lower nibble. IBS hw mandates it. */
 		hwc->sample_period &= ~0x0FULL;
 		if (!hwc->sample_period)
 			hwc->sample_period = 0x10;

From 598bdf4fefff5af4ce6d26d16f7b2a20808fc4cb Mon Sep 17 00:00:00 2001
From: Ravi Bangoria <ravi.bangoria@amd.com>
Date: Wed, 15 Jan 2025 05:44:32 +0000
Subject: [PATCH 0020/1173] perf/amd/ibs: Fix ->config to sample period
 calculation for OP PMU

Instead of using standard perf_event_attr->freq=0 and ->sample_period
fields, IBS event in 'sample period mode' can also be opened by setting
period value directly in perf_event_attr->config in a MaxCnt bit-field
format.

IBS OP MaxCnt bits are defined as:

  (high bits) IbsOpCtl[26:20] = IbsOpMaxCnt[26:20]
  (low bits)  IbsOpCtl[15:0]  = IbsOpMaxCnt[19:4]

Perf event sample period can be derived from MaxCnt bits as:

  sample_period = (high bits) | ((low_bits) << 4);

However, current code just masks MaxCnt bits and shifts all of them,
including high bits, which is incorrect. Fix it.

Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/r/20250115054438.1021-4-ravi.bangoria@amd.com
---
 arch/x86/events/amd/ibs.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index bd8919e7c3b17..f95542b75b916 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -271,7 +271,7 @@ static int perf_ibs_init(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	struct perf_ibs *perf_ibs;
-	u64 max_cnt, config;
+	u64 config;
 	int ret;
 
 	perf_ibs = get_ibs_pmu(event->attr.type);
@@ -313,10 +313,19 @@ static int perf_ibs_init(struct perf_event *event)
 		if (!hwc->sample_period)
 			hwc->sample_period = 0x10;
 	} else {
-		max_cnt = config & perf_ibs->cnt_mask;
+		u64 period = 0;
+
+		if (perf_ibs == &perf_ibs_op) {
+			period = (config & IBS_OP_MAX_CNT) << 4;
+			if (ibs_caps & IBS_CAPS_OPCNTEXT)
+				period |= config & IBS_OP_MAX_CNT_EXT_MASK;
+		} else {
+			period = (config & IBS_FETCH_MAX_CNT) << 4;
+		}
+
 		config &= ~perf_ibs->cnt_mask;
-		event->attr.sample_period = max_cnt << 4;
-		hwc->sample_period = event->attr.sample_period;
+		event->attr.sample_period = period;
+		hwc->sample_period = period;
 	}
 
 	if (!hwc->sample_period)

From 46dcf85566170d4528b842bf83ffc350d71771fa Mon Sep 17 00:00:00 2001
From: Ravi Bangoria <ravi.bangoria@amd.com>
Date: Wed, 15 Jan 2025 05:44:33 +0000
Subject: [PATCH 0021/1173] perf/amd/ibs: Fix perf_ibs_op.cnt_mask for CurCnt

IBS Op uses two counters: MaxCnt and CurCnt. MaxCnt is programmed with
the desired sample period. IBS hw generates sample when CurCnt reaches
to MaxCnt. The size of these counter used to be 20 bits but later they
were extended to 27 bits. The 7 bit extension is indicated by CPUID
Fn8000_001B_EAX[6 / OpCntExt].

perf_ibs->cnt_mask variable contains bit masks for MaxCnt and CurCnt.
But IBS driver does not set upper 7 bits of CurCnt in cnt_mask even
when OpCntExt CPUID bit is set. Fix this.

IBS driver uses cnt_mask[CurCnt] bits only while disabling an event.
Fortunately, CurCnt bits are not read from MSR while re-enabling the
event, instead MaxCnt is programmed with desired period and CurCnt is
set to 0. Hence, we did not see any issues so far.

Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/r/20250115054438.1021-5-ravi.bangoria@amd.com
---
 arch/x86/events/amd/ibs.c         | 3 ++-
 arch/x86/include/asm/perf_event.h | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index f95542b75b916..d9c84f1d530f1 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -1245,7 +1245,8 @@ static __init int perf_ibs_op_init(void)
 	if (ibs_caps & IBS_CAPS_OPCNTEXT) {
 		perf_ibs_op.max_period  |= IBS_OP_MAX_CNT_EXT_MASK;
 		perf_ibs_op.config_mask	|= IBS_OP_MAX_CNT_EXT_MASK;
-		perf_ibs_op.cnt_mask    |= IBS_OP_MAX_CNT_EXT_MASK;
+		perf_ibs_op.cnt_mask    |= (IBS_OP_MAX_CNT_EXT_MASK |
+					    IBS_OP_CUR_CNT_EXT_MASK);
 	}
 
 	if (ibs_caps & IBS_CAPS_ZEN4)
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 1ac79f3616456..ee5581768fea7 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -514,6 +514,7 @@ struct pebs_xmm {
  */
 #define IBS_OP_CUR_CNT		(0xFFF80ULL<<32)
 #define IBS_OP_CUR_CNT_RAND	(0x0007FULL<<32)
+#define IBS_OP_CUR_CNT_EXT_MASK	(0x7FULL<<52)
 #define IBS_OP_CNT_CTL		(1ULL<<19)
 #define IBS_OP_VAL		(1ULL<<18)
 #define IBS_OP_ENABLE		(1ULL<<17)

From e1e7844ced88f9558a48579390a7d4eaac6a28eb Mon Sep 17 00:00:00 2001
From: Ravi Bangoria <ravi.bangoria@amd.com>
Date: Wed, 15 Jan 2025 05:44:34 +0000
Subject: [PATCH 0022/1173] perf/amd/ibs: Don't allow freq mode event creation
 through ->config interface

Most perf_event_attr->config bits directly maps to IBS_{FETCH|OP}_CTL
MSR. Since the sample period is programmed in these control registers,
IBS PMU driver allows opening an IBS event by setting sample period
value directly in perf_event_attr->config instead of using explicit
perf_event_attr->sample_period interface.

However, this logic is not applicable for freq mode events since the
semantics of control register fields are applicable only to fixed
sample period whereas the freq mode event adjusts sample period after
each and every sample. Currently, IBS driver (unintentionally) allows
creating freq mode event via ->config interface, which is semantically
wrong as well as detrimental because it can be misused to bypass
perf_event_max_sample_rate checks.

Don't allow freq mode event creation through perf_event_attr->config
interface.

Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/r/20250115054438.1021-6-ravi.bangoria@amd.com
---
 arch/x86/events/amd/ibs.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index d9c84f1d530f1..3e7ca1e2f25e3 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -315,6 +315,9 @@ static int perf_ibs_init(struct perf_event *event)
 	} else {
 		u64 period = 0;
 
+		if (event->attr.freq)
+			return -EINVAL;
+
 		if (perf_ibs == &perf_ibs_op) {
 			period = (config & IBS_OP_MAX_CNT) << 4;
 			if (ibs_caps & IBS_CAPS_OPCNTEXT)

From b2fc7b282bf7c1253b01c8da84e894539a3e709d Mon Sep 17 00:00:00 2001
From: Ravi Bangoria <ravi.bangoria@amd.com>
Date: Wed, 15 Jan 2025 05:44:35 +0000
Subject: [PATCH 0023/1173] perf/amd/ibs: Add PMU specific minimum period

0x10 is the minimum sample period for IBS Fetch and 0x90 for IBS Op.
Current IBS PMU driver uses 0x10 for both the PMUs, which is incorrect.
Fix it by adding PMU specific minimum period values in struct perf_ibs.

Also, bail out opening a 'sample period mode' event if the user requested
sample period is less than PMU supported minimum value. For a 'freq mode'
event, start calibrating sample period from PMU specific minimum period.

Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/r/20250115054438.1021-7-ravi.bangoria@amd.com
---
 arch/x86/events/amd/ibs.c | 24 ++++++++++++++++--------
 1 file changed, 16 insertions(+), 8 deletions(-)

diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 3e7ca1e2f25e3..7b54b76d39f5d 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -86,6 +86,7 @@ struct perf_ibs {
 	u64				cnt_mask;
 	u64				enable_mask;
 	u64				valid_mask;
+	u16				min_period;
 	u64				max_period;
 	unsigned long			offset_mask[1];
 	int				offset_max;
@@ -308,10 +309,14 @@ static int perf_ibs_init(struct perf_event *event)
 			/* raw max_cnt may not be set */
 			return -EINVAL;
 
-		/* Silently mask off lower nibble. IBS hw mandates it. */
-		hwc->sample_period &= ~0x0FULL;
-		if (!hwc->sample_period)
-			hwc->sample_period = 0x10;
+		if (event->attr.freq) {
+			hwc->sample_period = perf_ibs->min_period;
+		} else {
+			/* Silently mask off lower nibble. IBS hw mandates it. */
+			hwc->sample_period &= ~0x0FULL;
+			if (hwc->sample_period < perf_ibs->min_period)
+				return -EINVAL;
+		}
 	} else {
 		u64 period = 0;
 
@@ -329,10 +334,10 @@ static int perf_ibs_init(struct perf_event *event)
 		config &= ~perf_ibs->cnt_mask;
 		event->attr.sample_period = period;
 		hwc->sample_period = period;
-	}
 
-	if (!hwc->sample_period)
-		return -EINVAL;
+		if (hwc->sample_period < perf_ibs->min_period)
+			return -EINVAL;
+	}
 
 	/*
 	 * If we modify hwc->sample_period, we also need to update
@@ -353,7 +358,8 @@ static int perf_ibs_set_period(struct perf_ibs *perf_ibs,
 	int overflow;
 
 	/* ignore lower 4 bits in min count: */
-	overflow = perf_event_set_period(hwc, 1<<4, perf_ibs->max_period, period);
+	overflow = perf_event_set_period(hwc, perf_ibs->min_period,
+					 perf_ibs->max_period, period);
 	local64_set(&hwc->prev_count, 0);
 
 	return overflow;
@@ -696,6 +702,7 @@ static struct perf_ibs perf_ibs_fetch = {
 	.cnt_mask		= IBS_FETCH_MAX_CNT,
 	.enable_mask		= IBS_FETCH_ENABLE,
 	.valid_mask		= IBS_FETCH_VAL,
+	.min_period		= 0x10,
 	.max_period		= IBS_FETCH_MAX_CNT << 4,
 	.offset_mask		= { MSR_AMD64_IBSFETCH_REG_MASK },
 	.offset_max		= MSR_AMD64_IBSFETCH_REG_COUNT,
@@ -720,6 +727,7 @@ static struct perf_ibs perf_ibs_op = {
 				  IBS_OP_CUR_CNT_RAND,
 	.enable_mask		= IBS_OP_ENABLE,
 	.valid_mask		= IBS_OP_VAL,
+	.min_period		= 0x90,
 	.max_period		= IBS_OP_MAX_CNT << 4,
 	.offset_mask		= { MSR_AMD64_IBSOP_REG_MASK },
 	.offset_max		= MSR_AMD64_IBSOP_REG_COUNT,

From 1afbdd970f50f2e0431fae26b25d4e54e561fa7f Mon Sep 17 00:00:00 2001
From: Ravi Bangoria <ravi.bangoria@amd.com>
Date: Wed, 15 Jan 2025 05:44:36 +0000
Subject: [PATCH 0024/1173] perf/amd/ibs: Add ->check_period() callback

IBS Fetch and IBS Op PMUs have constraints on sample period. The sample
period is verified at the time of opening an event but not at the ioctl()
interface. Hence, a user can open an event with valid period but change
it later with ioctl(). Add a ->check_period() callback to verify the
period provided at ioctl() is also valid.

Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/r/20250115054438.1021-8-ravi.bangoria@amd.com
---
 arch/x86/events/amd/ibs.c | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 7b54b76d39f5d..aea893a971b6e 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -564,6 +564,28 @@ static void perf_ibs_del(struct perf_event *event, int flags)
 
 static void perf_ibs_read(struct perf_event *event) { }
 
+static int perf_ibs_check_period(struct perf_event *event, u64 value)
+{
+	struct perf_ibs *perf_ibs;
+	u64 low_nibble;
+
+	if (event->attr.freq)
+		return 0;
+
+	perf_ibs = container_of(event->pmu, struct perf_ibs, pmu);
+	low_nibble = value & 0xFULL;
+
+	/*
+	 * This contradicts with perf_ibs_init() which allows sample period
+	 * with lower nibble bits set but silently masks them off. Whereas
+	 * this returns error.
+	 */
+	if (low_nibble || value < perf_ibs->min_period)
+		return -EINVAL;
+
+	return 0;
+}
+
 /*
  * We need to initialize with empty group if all attributes in the
  * group are dynamic.
@@ -696,6 +718,7 @@ static struct perf_ibs perf_ibs_fetch = {
 		.start		= perf_ibs_start,
 		.stop		= perf_ibs_stop,
 		.read		= perf_ibs_read,
+		.check_period	= perf_ibs_check_period,
 	},
 	.msr			= MSR_AMD64_IBSFETCHCTL,
 	.config_mask		= IBS_FETCH_MAX_CNT | IBS_FETCH_RAND_EN,
@@ -720,6 +743,7 @@ static struct perf_ibs perf_ibs_op = {
 		.start		= perf_ibs_start,
 		.stop		= perf_ibs_stop,
 		.read		= perf_ibs_read,
+		.check_period	= perf_ibs_check_period,
 	},
 	.msr			= MSR_AMD64_IBSOPCTL,
 	.config_mask		= IBS_OP_MAX_CNT,

From fa5d0a824e3bbd1f793d962f9e012ab0a8ee11c5 Mon Sep 17 00:00:00 2001
From: Ravi Bangoria <ravi.bangoria@amd.com>
Date: Wed, 15 Jan 2025 05:44:37 +0000
Subject: [PATCH 0025/1173] perf/amd/ibs: Ceil sample_period to min_period

The sample_period needs to be recalibrated after every sample to match
the desired sampling freq for a 'freq mode event'. Since the next
sample_period is calculated by generic kernel, PMU specific constraints
are not (explicitly) reckoned.

The sample_period value is programmed in a MaxCnt field of IBS PMUs, and
the MaxCnt field has following constraints:

1) MaxCnt must be multiple of 0x10.

  Kernel keeps track of residual / over-counted period into period_left,
  which should take care of this constraint by programming MaxCnt with
  (sample_period & ~0xF) and adding remaining period into the next sample.

2) MaxCnt must be >= 0x10 for IBS Fetch PMU and >= 0x90 for IBS Op PMU.

  Currently, IBS PMU driver allows sample_period below min_period, which
  is an undefined HW behavior. Reset sample_period to min_period whenever
  it's less than that.

Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250115054438.1021-9-ravi.bangoria@amd.com
---
 arch/x86/events/amd/ibs.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index aea893a971b6e..7978d7910adc3 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -457,6 +457,9 @@ static void perf_ibs_start(struct perf_event *event, int flags)
 	WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
 	hwc->state = 0;
 
+	if (event->attr.freq && hwc->sample_period < perf_ibs->min_period)
+		hwc->sample_period = perf_ibs->min_period;
+
 	perf_ibs_set_period(perf_ibs, hwc, &period);
 	if (perf_ibs == &perf_ibs_op && (ibs_caps & IBS_CAPS_OPCNTEXT)) {
 		config |= period & IBS_OP_MAX_CNT_EXT_MASK;
@@ -1191,6 +1194,10 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
 	perf_sample_save_callchain(&data, event, iregs);
 
 	throttle = perf_event_overflow(event, &data, &regs);
+
+	if (event->attr.freq && hwc->sample_period < perf_ibs->min_period)
+		hwc->sample_period = perf_ibs->min_period;
+
 out:
 	if (throttle) {
 		perf_ibs_stop(event, 0);

From eae8a56ae0c74c1cf2f92a6709d215a9f329f60c Mon Sep 17 00:00:00 2001
From: Liao Chang <liaochang1@huawei.com>
Date: Fri, 24 Jan 2025 09:38:25 +0000
Subject: [PATCH 0026/1173] uprobes: Remove redundant spinlock in
 uprobe_deny_signal()

Since clearing a bit in thread_info is an atomic operation, the spinlock
is redundant and can be removed, reducing lock contention is good for
performance.

Signed-off-by: Liao Chang <liaochang1@huawei.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Acked-by: Oleg Nesterov <oleg@redhat.com>
Link: https://lore.kernel.org/r/20250124093826.2123675-2-liaochang1@huawei.com
---
 kernel/events/uprobes.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 2ca797cbe465f..33bd6083f7c40 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -2302,9 +2302,7 @@ bool uprobe_deny_signal(void)
 	WARN_ON_ONCE(utask->state != UTASK_SSTEP);
 
 	if (task_sigpending(t)) {
-		spin_lock_irq(&t->sighand->siglock);
 		clear_tsk_thread_flag(t, TIF_SIGPENDING);
-		spin_unlock_irq(&t->sighand->siglock);
 
 		if (__fatal_signal_pending(t) || arch_uprobe_xol_was_trapped(t)) {
 			utask->state = UTASK_SSTEP_TRAPPED;

From 3fb3cb4350befc4f901c54e0cb4a2a47b1302e08 Mon Sep 17 00:00:00 2001
From: Andrey Vatoropin <a.vatoropin@crpt.ru>
Date: Thu, 30 Jan 2025 09:00:34 +0000
Subject: [PATCH 0027/1173] power: supply: da9150-fg: fix potential overflow

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

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

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

Remove the explicit cast to u64 as it is meaningless.

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

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

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

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

From 64dd6edfc421479e416301c48b79cece8d0351fc Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 30 Jan 2025 15:00:35 +0100
Subject: [PATCH 0028/1173] power: supply: core: Fix extension related lockdep
 warning
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

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

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

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

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

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

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

Here is the lockdep report fixed by this change:

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

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

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

[   31.257630]  Possible unsafe locking scenario:

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

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

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

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

From d97505baea64d93538b16baf14ce7b8c1fbad746 Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Sun, 19 Jan 2025 14:36:13 +0200
Subject: [PATCH 0029/1173] RDMA/mlx5: Fix the recovery flow of the UMR QP

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

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

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

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

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

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

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

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

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

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

From 12d044770e12c4205fa69535b4fa8a9981fea98f Mon Sep 17 00:00:00 2001
From: Mark Zhang <markzhang@nvidia.com>
Date: Sun, 19 Jan 2025 14:39:46 +0200
Subject: [PATCH 0030/1173] IB/mlx5: Set and get correct qp_num for a DCT QP

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

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

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

From 98380110bd48fbfd6a798ee11fffff893d36062c Mon Sep 17 00:00:00 2001
From: Chris Morgan <macromorgan@hotmail.com>
Date: Fri, 31 Jan 2025 17:14:51 -0600
Subject: [PATCH 0031/1173] power: supply: axp20x_battery: Fix fault handling
 for AXP717

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

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

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

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

From c057b6e4213519e3ac167318238cd772b483f14a Mon Sep 17 00:00:00 2001
From: Vladimir Kondratiev <vladimir.kondratiev@mobileye.com>
Date: Wed, 29 Jan 2025 11:16:36 +0200
Subject: [PATCH 0032/1173] dt-bindings: interrupt-controller: Add risc-v,aplic
 hart indexes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Document optional property "riscv,hart-indexes"

The RISC-V APLIC specification defines "hart index" in:

  https://github.com/riscv/riscv-aia

Within a given interrupt domain, each of the domain’s harts has a unique
index number in the range 0 to 2^14 − 1 (= 16,383). The index number a
domain associates with a hart may or may not have any relationship to the
unique hart identifier (“hart ID”) that the RISC-V Privileged Architecture
assigns to the hart. Two different interrupt domains may employ entirely
different index numbers for the same set of harts.

Further, this document says in "4.5 Memory-mapped control region for an
interrupt domain":

The array of IDC structures may include some for potential hart index
numbers that are not actual hart index numbers in the domain. For example,
the first IDC structure is always for hart index 0, but 0 is not
necessarily a valid index number for any hart in the domain.

Support arbitrary hart indexes specified in a optional APLIC property
"riscv,hart-indexes" which is specificed as an array of u32 elements, one
per interrupt target. If this property is not specified, fallback to use
the logical hart indices within the domain.

Signed-off-by: Vladimir Kondratiev <vladimir.kondratiev@mobileye.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Anup Patel <anup@brainfault.org>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://lore.kernel.org/all/20250129091637.1667279-2-vladimir.kondratiev@mobileye.com
---
 .../bindings/interrupt-controller/riscv,aplic.yaml        | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/Documentation/devicetree/bindings/interrupt-controller/riscv,aplic.yaml b/Documentation/devicetree/bindings/interrupt-controller/riscv,aplic.yaml
index 190a6499c932e..bef00521d5dac 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/riscv,aplic.yaml
+++ b/Documentation/devicetree/bindings/interrupt-controller/riscv,aplic.yaml
@@ -91,6 +91,14 @@ properties:
       Firmware must configure interrupt delegation registers based on
       interrupt delegation list.
 
+  riscv,hart-indexes:
+    $ref: /schemas/types.yaml#/definitions/uint32-array
+    minItems: 1
+    maxItems: 16384
+    description:
+      A list of hart indexes that APLIC should use to address each hart
+      that is mentioned in the "interrupts-extended"
+
 dependencies:
   riscv,delegation: [ "riscv,children" ]
 

From b93afe8a3ac53ae52296d65acfaa9c5f582a48cc Mon Sep 17 00:00:00 2001
From: Vladimir Kondratiev <vladimir.kondratiev@mobileye.com>
Date: Wed, 29 Jan 2025 11:16:37 +0200
Subject: [PATCH 0033/1173] irqchip/riscv-aplic: Add support for hart indexes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

RISC-V APLIC specification defines "hart index" in:

  https://github.com/riscv/riscv-aia

Within a given interrupt domain, each of the domain’s harts has a unique
index number in the range 0 to 2^14 − 1 (= 16,383). The index number a
domain associates with a hart may or may not have any relationship to the
unique hart identifier (“hart ID”) that the RISC-V Privileged Architecture
assigns to the hart. Two different interrupt domains may employ entirely
different index numbers for the same set of harts.

Further, this document says in "4.5 Memory-mapped control region for an
interrupt domain":

The array of IDC structures may include some for potential hart index
numbers that are not actual hart index numbers in the domain. For example,
the first IDC structure is always for hart index 0, but 0 is not
necessarily a valid index number for any hart in the domain.

Support arbitrary hart indices specified in an optional APLIC property
"riscv,hart-indexes" which is specified as an array of u32 elements, one
per interrupt target. If this property is not specified, fallback to use
logical hart indices within the domain.

Signed-off-by: Vladimir Kondratiev <vladimir.kondratiev@mobileye.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Anup Patel <anup@brainfault.org>
Link: https://lore.kernel.org/all/20250129091637.1667279-3-vladimir.kondratiev@mobileye.com
---
 drivers/irqchip/irq-riscv-aplic-direct.c | 24 +++++++++++++++++++++---
 1 file changed, 21 insertions(+), 3 deletions(-)

diff --git a/drivers/irqchip/irq-riscv-aplic-direct.c b/drivers/irqchip/irq-riscv-aplic-direct.c
index 7cd6b646774b9..205ad61d15e49 100644
--- a/drivers/irqchip/irq-riscv-aplic-direct.c
+++ b/drivers/irqchip/irq-riscv-aplic-direct.c
@@ -31,7 +31,7 @@ struct aplic_direct {
 };
 
 struct aplic_idc {
-	unsigned int		hart_index;
+	u32			hart_index;
 	void __iomem		*regs;
 	struct aplic_direct	*direct;
 };
@@ -219,6 +219,20 @@ static int aplic_direct_parse_parent_hwirq(struct device *dev, u32 index,
 	return 0;
 }
 
+static int aplic_direct_get_hart_index(struct device *dev, u32 logical_index,
+				       u32 *hart_index)
+{
+	const char *prop_hart_index = "riscv,hart-indexes";
+	struct device_node *np = to_of_node(dev->fwnode);
+
+	if (!np || !of_property_present(np, prop_hart_index)) {
+		*hart_index = logical_index;
+		return 0;
+	}
+
+	return of_property_read_u32_index(np, prop_hart_index, logical_index, hart_index);
+}
+
 int aplic_direct_setup(struct device *dev, void __iomem *regs)
 {
 	int i, j, rc, cpu, current_cpu, setup_count = 0;
@@ -265,8 +279,12 @@ int aplic_direct_setup(struct device *dev, void __iomem *regs)
 		cpumask_set_cpu(cpu, &direct->lmask);
 
 		idc = per_cpu_ptr(&aplic_idcs, cpu);
-		idc->hart_index = i;
-		idc->regs = priv->regs + APLIC_IDC_BASE + i * APLIC_IDC_SIZE;
+		rc = aplic_direct_get_hart_index(dev, i, &idc->hart_index);
+		if (rc) {
+			dev_warn(dev, "hart index not found for IDC%d\n", i);
+			continue;
+		}
+		idc->regs = priv->regs + APLIC_IDC_BASE + idc->hart_index * APLIC_IDC_SIZE;
 		idc->direct = direct;
 
 		aplic_idc_set_delivery(idc, true);

From b2f10aa2eb18d289e48097e0ed973e714322175b Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 10 Dec 2024 16:16:50 +0100
Subject: [PATCH 0034/1173] x86/entry: Add __init to
 ia32_emulation_override_cmdline()

ia32_emulation_override_cmdline() is an early_param() arg and these
are only needed at boot time. In fact, all other early_param() functions
in arch/x86 seem to have '__init' annotation and
ia32_emulation_override_cmdline() is the only exception.

Fixes: a11e097504ac ("x86: Make IA32_EMULATION boot time configurable")
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Nikolay Borisov <nik.borisov@suse.com>
Link: https://lore.kernel.org/all/20241210151650.1746022-1-vkuznets%40redhat.com
---
 arch/x86/entry/common.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 94941c5a10ac1..51efd2da4d7fd 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -142,7 +142,7 @@ static __always_inline int syscall_32_enter(struct pt_regs *regs)
 #ifdef CONFIG_IA32_EMULATION
 bool __ia32_enabled __ro_after_init = !IS_ENABLED(CONFIG_IA32_EMULATION_DEFAULT_DISABLED);
 
-static int ia32_emulation_override_cmdline(char *arg)
+static int __init ia32_emulation_override_cmdline(char *arg)
 {
 	return kstrtobool(arg, &__ia32_enabled);
 }

From a96d3e2beca0e51c8444d0a3b6b3ec484c4c5a8f Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Date: Sun, 12 Jan 2025 01:08:11 +0100
Subject: [PATCH 0035/1173] iio: light: apds9306: fix max_scale_nano values
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

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

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

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

Update max_scale_nano initialization to use the right NANO fractional
parts.

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

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

From 34d93804199fea23da2645dde35d0feb38a5d445 Mon Sep 17 00:00:00 2001
From: Victor Duicu <victor.duicu@microchip.com>
Date: Fri, 17 Jan 2025 08:53:14 +0200
Subject: [PATCH 0036/1173] iio: adc: pac1921: Move ACPI_FREE() to cover all
 branches

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

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

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

From aa5119c36d19639397d29ef305aa53a5ecd72b27 Mon Sep 17 00:00:00 2001
From: Nayab Sayed <nayabbasha.sayed@microchip.com>
Date: Wed, 15 Jan 2025 11:37:04 +0530
Subject: [PATCH 0037/1173] iio: adc: at91-sama5d2_adc: fix sama7g5 realbits
 value

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

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

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

From 5d702aa2a47bbab6231382f9ead5be40a287a53b Mon Sep 17 00:00:00 2001
From: Dheeraj Reddy Jonnalagadda <dheeraj.linuxdev@gmail.com>
Date: Tue, 7 Jan 2025 18:05:10 +0530
Subject: [PATCH 0038/1173] iio: proximity: Fix use-after-free in
 hx9023s_send_cfg()

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

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

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

From 4eba4d92906c3814ca3ec65c16af27c46c12342e Mon Sep 17 00:00:00 2001
From: Ricardo Ribalda <ribalda@chromium.org>
Date: Mon, 16 Dec 2024 10:05:53 +0000
Subject: [PATCH 0039/1173] iio: hid-sensor-prox: Split difference from
 multiple channels

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

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

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

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

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

From 21d7241faf406e8aee3ce348451cc362d5db6a02 Mon Sep 17 00:00:00 2001
From: Markus Burri <markus.burri@mt.com>
Date: Fri, 24 Jan 2025 16:07:03 +0100
Subject: [PATCH 0040/1173] iio: adc: ad7192: fix channel select
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

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

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

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

From e17b9f20da7d2bc1f48878ab2230523b2512d965 Mon Sep 17 00:00:00 2001
From: Angelo Dureghello <adureghello@baylibre.com>
Date: Sat, 25 Jan 2025 17:24:32 +0100
Subject: [PATCH 0041/1173] iio: dac: ad3552r: clear reset status flag

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

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

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

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

From 02ccd7e5d81af4ae20852fc1ad67e7d943fa5778 Mon Sep 17 00:00:00 2001
From: Angelo Dureghello <adureghello@baylibre.com>
Date: Wed, 29 Jan 2025 12:03:02 +0100
Subject: [PATCH 0042/1173] dt-bindings: iio: dac: adi-axi-adc: fix ad7606
 pwm-names

Fix make dt_binding_check warning:

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

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

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

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

From bead181694df16de464ca2392d0cec2cf15fb978 Mon Sep 17 00:00:00 2001
From: Angelo Dureghello <adureghello@baylibre.com>
Date: Wed, 29 Jan 2025 12:03:04 +0100
Subject: [PATCH 0043/1173] iio: adc: ad7606: fix wrong scale available

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

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

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

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

From fcf5d353b09b3fc212ab24b89ef23a7a8f7b308e Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 22 Jan 2025 07:52:44 +0100
Subject: [PATCH 0044/1173] phy: rockchip: fix Kconfig dependency more

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

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

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

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

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

From 3126ea9be66b53e607f87f067641ba724be24181 Mon Sep 17 00:00:00 2001
From: Chukun Pan <amadeus@jmu.edu.cn>
Date: Mon, 6 Jan 2025 18:00:01 +0800
Subject: [PATCH 0045/1173] phy: rockchip: naneng-combphy: compatible reset
 with old DT

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

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

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

From e3cd85963a20d2b92e77046a8d9f0777815f1f71 Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Fri, 17 Jan 2025 15:48:59 +0100
Subject: [PATCH 0046/1173] x86/mtrr: Use str_enabled_disabled() helper in
 print_mtrr_state()

Remove hard-coded strings by using the str_enabled_disabled() helper
function.

Suggested-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/all/20250117144900.171684-2-thorsten.blum%40linux.dev
---
 arch/x86/kernel/cpu/mtrr/generic.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 2fdfda2b60e4f..6be3cade4134c 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -9,6 +9,7 @@
 #include <linux/io.h>
 #include <linux/mm.h>
 #include <linux/cc_platform.h>
+#include <linux/string_choices.h>
 #include <asm/processor-flags.h>
 #include <asm/cacheinfo.h>
 #include <asm/cpufeature.h>
@@ -646,10 +647,10 @@ static void __init print_mtrr_state(void)
 	pr_info("MTRR default type: %s\n",
 		mtrr_attrib_to_str(mtrr_state.def_type));
 	if (mtrr_state.have_fixed) {
-		pr_info("MTRR fixed ranges %sabled:\n",
-			((mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED) &&
-			 (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) ?
-			 "en" : "dis");
+		pr_info("MTRR fixed ranges %s:\n",
+			str_enabled_disabled(
+			 (mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED) &&
+			 (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)));
 		print_fixed(0x00000, 0x10000, mtrr_state.fixed_ranges + 0);
 		for (i = 0; i < 2; ++i)
 			print_fixed(0x80000 + i * 0x20000, 0x04000,
@@ -661,8 +662,8 @@ static void __init print_mtrr_state(void)
 		/* tail */
 		print_fixed_last();
 	}
-	pr_info("MTRR variable ranges %sabled:\n",
-		mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED ? "en" : "dis");
+	pr_info("MTRR variable ranges %s:\n",
+		str_enabled_disabled(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED));
 	high_width = (boot_cpu_data.x86_phys_bits - (32 - PAGE_SHIFT) + 3) / 4;
 
 	for (i = 0; i < num_var_ranges; ++i) {

From 1e66d6cf888fd206a89b8c476b1b28b63faf7fd6 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Mon, 7 Oct 2024 09:57:01 -0700
Subject: [PATCH 0047/1173] x86/cpu: Fix #define name for Intel CPU model 0x5A

This CPU was mistakenly given the name INTEL_ATOM_AIRMONT_MID. But it
uses a Silvermont core, not Airmont.

Change #define name to INTEL_ATOM_SILVERMONT_MID2

Reported-by: Christian Ludloff <ludloff@gmail.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/all/20241007165701.19693-1-tony.luck%40intel.com
---
 arch/x86/events/intel/core.c                                  | 2 +-
 arch/x86/include/asm/intel-family.h                           | 2 +-
 arch/x86/kernel/cpu/common.c                                  | 2 +-
 arch/x86/kernel/tsc_msr.c                                     | 2 +-
 drivers/powercap/intel_rapl_common.c                          | 2 +-
 .../staging/media/atomisp/include/linux/atomisp_platform.h    | 4 ++--
 drivers/thermal/intel/intel_tcc.c                             | 2 +-
 tools/power/x86/turbostat/turbostat.c                         | 2 +-
 8 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 7601196d1d18e..89880540ab434 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -6622,7 +6622,7 @@ __init int intel_pmu_init(void)
 	case INTEL_ATOM_SILVERMONT_D:
 	case INTEL_ATOM_SILVERMONT_MID:
 	case INTEL_ATOM_AIRMONT:
-	case INTEL_ATOM_AIRMONT_MID:
+	case INTEL_ATOM_SILVERMONT_MID2:
 		memcpy(hw_cache_event_ids, slm_hw_cache_event_ids,
 			sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs,
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 6d7b04ffc5fd0..8359113e3e58e 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -149,9 +149,9 @@
 #define INTEL_ATOM_SILVERMONT		IFM(6, 0x37) /* Bay Trail, Valleyview */
 #define INTEL_ATOM_SILVERMONT_D		IFM(6, 0x4D) /* Avaton, Rangely */
 #define INTEL_ATOM_SILVERMONT_MID	IFM(6, 0x4A) /* Merriefield */
+#define INTEL_ATOM_SILVERMONT_MID2	IFM(6, 0x5A) /* Anniedale */
 
 #define INTEL_ATOM_AIRMONT		IFM(6, 0x4C) /* Cherry Trail, Braswell */
-#define INTEL_ATOM_AIRMONT_MID		IFM(6, 0x5A) /* Moorefield */
 #define INTEL_ATOM_AIRMONT_NP		IFM(6, 0x75) /* Lightning Mountain */
 
 #define INTEL_ATOM_GOLDMONT		IFM(6, 0x5C) /* Apollo Lake */
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 7cce91b19fb2c..76598a93a8faa 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1164,7 +1164,7 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 
 	VULNWL_INTEL(INTEL_CORE_YONAH,		NO_SSB),
 
-	VULNWL_INTEL(INTEL_ATOM_AIRMONT_MID,	NO_SSB | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | MSBDS_ONLY),
+	VULNWL_INTEL(INTEL_ATOM_SILVERMONT_MID2,NO_SSB | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | MSBDS_ONLY),
 	VULNWL_INTEL(INTEL_ATOM_AIRMONT_NP,	NO_SSB | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
 
 	VULNWL_INTEL(INTEL_ATOM_GOLDMONT,	NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c
index deeb028256709..48e6cc1cb017a 100644
--- a/arch/x86/kernel/tsc_msr.c
+++ b/arch/x86/kernel/tsc_msr.c
@@ -152,7 +152,7 @@ static const struct x86_cpu_id tsc_msr_cpu_ids[] = {
 	X86_MATCH_VFM(INTEL_ATOM_SILVERMONT,	&freq_desc_byt),
 	X86_MATCH_VFM(INTEL_ATOM_SILVERMONT_MID,	&freq_desc_tng),
 	X86_MATCH_VFM(INTEL_ATOM_AIRMONT,	&freq_desc_cht),
-	X86_MATCH_VFM(INTEL_ATOM_AIRMONT_MID,	&freq_desc_ann),
+	X86_MATCH_VFM(INTEL_ATOM_SILVERMONT_MID2,	&freq_desc_ann),
 	X86_MATCH_VFM(INTEL_ATOM_AIRMONT_NP,	&freq_desc_lgm),
 	{}
 };
diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c
index 77d75e1f14a9f..5ccde39823142 100644
--- a/drivers/powercap/intel_rapl_common.c
+++ b/drivers/powercap/intel_rapl_common.c
@@ -1274,7 +1274,7 @@ static const struct x86_cpu_id rapl_ids[] __initconst = {
 	X86_MATCH_VFM(INTEL_ATOM_SILVERMONT,	&rapl_defaults_byt),
 	X86_MATCH_VFM(INTEL_ATOM_AIRMONT,	&rapl_defaults_cht),
 	X86_MATCH_VFM(INTEL_ATOM_SILVERMONT_MID, &rapl_defaults_tng),
-	X86_MATCH_VFM(INTEL_ATOM_AIRMONT_MID,	&rapl_defaults_ann),
+	X86_MATCH_VFM(INTEL_ATOM_SILVERMONT_MID2,&rapl_defaults_ann),
 	X86_MATCH_VFM(INTEL_ATOM_GOLDMONT,	&rapl_defaults_core),
 	X86_MATCH_VFM(INTEL_ATOM_GOLDMONT_PLUS,	&rapl_defaults_core),
 	X86_MATCH_VFM(INTEL_ATOM_GOLDMONT_D,	&rapl_defaults_core),
diff --git a/drivers/staging/media/atomisp/include/linux/atomisp_platform.h b/drivers/staging/media/atomisp/include/linux/atomisp_platform.h
index 049246774cede..6146555fe9cfd 100644
--- a/drivers/staging/media/atomisp/include/linux/atomisp_platform.h
+++ b/drivers/staging/media/atomisp/include/linux/atomisp_platform.h
@@ -172,10 +172,10 @@ void atomisp_unregister_subdev(struct v4l2_subdev *subdev);
 #define IS_BYT	__IS_SOC(INTEL_ATOM_SILVERMONT)
 #define IS_CHT	__IS_SOC(INTEL_ATOM_AIRMONT)
 #define IS_MRFD	__IS_SOC(INTEL_ATOM_SILVERMONT_MID)
-#define IS_MOFD	__IS_SOC(INTEL_ATOM_AIRMONT_MID)
+#define IS_MOFD	__IS_SOC(INTEL_ATOM_SILVERMONT_MID2)
 
 /* Both CHT and MOFD come with ISP2401 */
 #define IS_ISP2401 __IS_SOCS(INTEL_ATOM_AIRMONT, \
-			     INTEL_ATOM_AIRMONT_MID)
+			     INTEL_ATOM_SILVERMONT_MID2)
 
 #endif /* ATOMISP_PLATFORM_H_ */
diff --git a/drivers/thermal/intel/intel_tcc.c b/drivers/thermal/intel/intel_tcc.c
index 817421508d5c9..b2a615aea7c14 100644
--- a/drivers/thermal/intel/intel_tcc.c
+++ b/drivers/thermal/intel/intel_tcc.c
@@ -106,7 +106,7 @@ static const struct x86_cpu_id intel_tcc_cpu_ids[] __initconst = {
 	X86_MATCH_VFM(INTEL_ATOM_SILVERMONT_D,		&temp_broadwell),
 	X86_MATCH_VFM(INTEL_ATOM_SILVERMONT_MID,	&temp_broadwell),
 	X86_MATCH_VFM(INTEL_ATOM_AIRMONT,		&temp_broadwell),
-	X86_MATCH_VFM(INTEL_ATOM_AIRMONT_MID,		&temp_broadwell),
+	X86_MATCH_VFM(INTEL_ATOM_SILVERMONT_MID2,	&temp_broadwell),
 	X86_MATCH_VFM(INTEL_ATOM_AIRMONT_NP,		&temp_broadwell),
 	X86_MATCH_VFM(INTEL_ATOM_GOLDMONT,		&temp_goldmont),
 	X86_MATCH_VFM(INTEL_ATOM_GOLDMONT_D,		&temp_goldmont),
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 8d5011a0bf60d..26057af6b5a1f 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -1056,7 +1056,7 @@ static const struct platform_data turbostat_pdata[] = {
 	 * Missing support for
 	 * INTEL_ICELAKE
 	 * INTEL_ATOM_SILVERMONT_MID
-	 * INTEL_ATOM_AIRMONT_MID
+	 * INTEL_ATOM_SILVERMONT_MID2
 	 * INTEL_ATOM_AIRMONT_NP
 	 */
 	{ 0, NULL },

From ceb5faef848b2fbb5d1e99617093cc9d4deb2b30 Mon Sep 17 00:00:00 2001
From: Tanya Agarwal <tanyaagarwal25699@gmail.com>
Date: Fri, 24 Jan 2025 01:07:44 +0530
Subject: [PATCH 0048/1173] integrity: fix typos and spelling errors

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

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

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

From 57a0ef02fefafc4b9603e33a18b669ba5ce59ba3 Mon Sep 17 00:00:00 2001
From: Roberto Sassu <roberto.sassu@huawei.com>
Date: Tue, 4 Feb 2025 13:57:20 +0100
Subject: [PATCH 0049/1173] ima: Reset IMA_NONACTION_RULE_FLAGS after
 post_setattr

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

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

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

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

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

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

From 83179cd67846fae0e6aea5848c07faaa5d89a1de Mon Sep 17 00:00:00 2001
From: Liao Chang <liaochang1@huawei.com>
Date: Fri, 24 Jan 2025 09:38:26 +0000
Subject: [PATCH 0050/1173] uprobes: Remove the spinlock within
 handle_singlestep()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch introduces a flag to track TIF_SIGPENDING is suppress
temporarily during the uprobe single-step. Upon uprobe singlestep is
handled and the flag is confirmed, it could resume the TIF_SIGPENDING
directly without acquiring the siglock in most case, then reducing
contention and improving overall performance.

I've use the script developed by Andrii in [1] to run benchmark. The CPU
used was Kunpeng916 (Hi1616), 4 NUMA nodes, 64 cores@2.4GHz running the
kernel on next tree + the optimization for get_xol_insn_slot() [2].

before-opt
----------
uprobe-nop      ( 1 cpus):    0.907 ± 0.003M/s  (  0.907M/s/cpu)
uprobe-nop      ( 2 cpus):    1.676 ± 0.008M/s  (  0.838M/s/cpu)
uprobe-nop      ( 4 cpus):    3.210 ± 0.003M/s  (  0.802M/s/cpu)
uprobe-nop      ( 8 cpus):    4.457 ± 0.003M/s  (  0.557M/s/cpu)
uprobe-nop      (16 cpus):    3.724 ± 0.011M/s  (  0.233M/s/cpu)
uprobe-nop      (32 cpus):    2.761 ± 0.003M/s  (  0.086M/s/cpu)
uprobe-nop      (64 cpus):    1.293 ± 0.015M/s  (  0.020M/s/cpu)

uprobe-push     ( 1 cpus):    0.883 ± 0.001M/s  (  0.883M/s/cpu)
uprobe-push     ( 2 cpus):    1.642 ± 0.005M/s  (  0.821M/s/cpu)
uprobe-push     ( 4 cpus):    3.086 ± 0.002M/s  (  0.771M/s/cpu)
uprobe-push     ( 8 cpus):    3.390 ± 0.003M/s  (  0.424M/s/cpu)
uprobe-push     (16 cpus):    2.652 ± 0.005M/s  (  0.166M/s/cpu)
uprobe-push     (32 cpus):    2.713 ± 0.005M/s  (  0.085M/s/cpu)
uprobe-push     (64 cpus):    1.313 ± 0.009M/s  (  0.021M/s/cpu)

uprobe-ret      ( 1 cpus):    1.774 ± 0.000M/s  (  1.774M/s/cpu)
uprobe-ret      ( 2 cpus):    3.350 ± 0.001M/s  (  1.675M/s/cpu)
uprobe-ret      ( 4 cpus):    6.604 ± 0.000M/s  (  1.651M/s/cpu)
uprobe-ret      ( 8 cpus):    6.706 ± 0.005M/s  (  0.838M/s/cpu)
uprobe-ret      (16 cpus):    5.231 ± 0.001M/s  (  0.327M/s/cpu)
uprobe-ret      (32 cpus):    5.743 ± 0.003M/s  (  0.179M/s/cpu)
uprobe-ret      (64 cpus):    4.726 ± 0.016M/s  (  0.074M/s/cpu)

after-opt
---------
uprobe-nop      ( 1 cpus):    0.985 ± 0.002M/s  (  0.985M/s/cpu)
uprobe-nop      ( 2 cpus):    1.773 ± 0.005M/s  (  0.887M/s/cpu)
uprobe-nop      ( 4 cpus):    3.304 ± 0.001M/s  (  0.826M/s/cpu)
uprobe-nop      ( 8 cpus):    5.328 ± 0.002M/s  (  0.666M/s/cpu)
uprobe-nop      (16 cpus):    6.475 ± 0.002M/s  (  0.405M/s/cpu)
uprobe-nop      (32 cpus):    4.831 ± 0.082M/s  (  0.151M/s/cpu)
uprobe-nop      (64 cpus):    2.564 ± 0.053M/s  (  0.040M/s/cpu)

uprobe-push     ( 1 cpus):    0.964 ± 0.001M/s  (  0.964M/s/cpu)
uprobe-push     ( 2 cpus):    1.766 ± 0.002M/s  (  0.883M/s/cpu)
uprobe-push     ( 4 cpus):    3.290 ± 0.009M/s  (  0.823M/s/cpu)
uprobe-push     ( 8 cpus):    4.670 ± 0.002M/s  (  0.584M/s/cpu)
uprobe-push     (16 cpus):    5.197 ± 0.004M/s  (  0.325M/s/cpu)
uprobe-push     (32 cpus):    5.068 ± 0.161M/s  (  0.158M/s/cpu)
uprobe-push     (64 cpus):    2.605 ± 0.026M/s  (  0.041M/s/cpu)

uprobe-ret      ( 1 cpus):    1.833 ± 0.001M/s  (  1.833M/s/cpu)
uprobe-ret      ( 2 cpus):    3.384 ± 0.003M/s  (  1.692M/s/cpu)
uprobe-ret      ( 4 cpus):    6.677 ± 0.004M/s  (  1.669M/s/cpu)
uprobe-ret      ( 8 cpus):    6.854 ± 0.005M/s  (  0.857M/s/cpu)
uprobe-ret      (16 cpus):    6.508 ± 0.006M/s  (  0.407M/s/cpu)
uprobe-ret      (32 cpus):    5.793 ± 0.009M/s  (  0.181M/s/cpu)
uprobe-ret      (64 cpus):    4.743 ± 0.016M/s  (  0.074M/s/cpu)

Above benchmark results demonstrates a obivious improvement in the
scalability of trig-uprobe-nop and trig-uprobe-push, the peak throughput
of which are from 4.5M/s to 6.4M/s and 3.3M/s to 5.1M/s individually.

[1] https://lore.kernel.org/all/20240731214256.3588718-1-andrii@kernel.org
[2] https://lore.kernel.org/all/20240727094405.1362496-1-liaochang1@huawei.com

Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Liao Chang <liaochang1@huawei.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250124093826.2123675-3-liaochang1@huawei.com
---
 include/linux/uprobes.h | 1 +
 kernel/events/uprobes.c | 8 +++++---
 2 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index b1df7d792fa16..a40efdda9052b 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -143,6 +143,7 @@ struct uprobe_task {
 
 	struct uprobe			*active_uprobe;
 	unsigned long			xol_vaddr;
+	bool				signal_denied;
 
 	struct arch_uprobe              *auprobe;
 };
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 33bd6083f7c40..870f69780900e 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -2302,6 +2302,7 @@ bool uprobe_deny_signal(void)
 	WARN_ON_ONCE(utask->state != UTASK_SSTEP);
 
 	if (task_sigpending(t)) {
+		utask->signal_denied = true;
 		clear_tsk_thread_flag(t, TIF_SIGPENDING);
 
 		if (__fatal_signal_pending(t) || arch_uprobe_xol_was_trapped(t)) {
@@ -2735,9 +2736,10 @@ static void handle_singlestep(struct uprobe_task *utask, struct pt_regs *regs)
 	utask->state = UTASK_RUNNING;
 	xol_free_insn_slot(utask);
 
-	spin_lock_irq(&current->sighand->siglock);
-	recalc_sigpending(); /* see uprobe_deny_signal() */
-	spin_unlock_irq(&current->sighand->siglock);
+	if (utask->signal_denied) {
+		set_thread_flag(TIF_SIGPENDING);
+		utask->signal_denied = false;
+	}
 
 	if (unlikely(err)) {
 		uprobe_warn(current, "execute the probed insn, sending SIGILL.");

From 314dfe10576912e1d786b13c5d4eee8c51b63caa Mon Sep 17 00:00:00 2001
From: "Peter Zijlstra (Intel)" <peterz@infradead.org>
Date: Tue, 21 Jan 2025 07:23:00 -0800
Subject: [PATCH 0051/1173] perf/x86/intel: Apply static call for drain_pebs

The x86_pmu_drain_pebs static call was introduced in commit 7c9903c9bf71
("x86/perf, static_call: Optimize x86_pmu methods"), but it's not really
used to replace the old method.

Apply the static call for drain_pebs.

Fixes: 7c9903c9bf71 ("x86/perf, static_call: Optimize x86_pmu methods")
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20250121152303.3128733-1-kan.liang@linux.intel.com
---
 arch/x86/events/intel/core.c | 2 +-
 arch/x86/events/intel/ds.c   | 2 +-
 arch/x86/events/perf_event.h | 1 +
 3 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 7601196d1d18e..2acea83526c63 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3076,7 +3076,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 
 		handled++;
 		x86_pmu_handle_guest_pebs(regs, &data);
-		x86_pmu.drain_pebs(regs, &data);
+		static_call(x86_pmu_drain_pebs)(regs, &data);
 		status &= intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI;
 
 		/*
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index ba74e11983280..322963b02a912 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -957,7 +957,7 @@ static inline void intel_pmu_drain_pebs_buffer(void)
 {
 	struct perf_sample_data data;
 
-	x86_pmu.drain_pebs(NULL, &data);
+	static_call(x86_pmu_drain_pebs)(NULL, &data);
 }
 
 /*
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 31c2771545a6c..084e9196b4582 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -1107,6 +1107,7 @@ extern struct x86_pmu x86_pmu __read_mostly;
 
 DECLARE_STATIC_CALL(x86_pmu_set_period, *x86_pmu.set_period);
 DECLARE_STATIC_CALL(x86_pmu_update,     *x86_pmu.update);
+DECLARE_STATIC_CALL(x86_pmu_drain_pebs,	*x86_pmu.drain_pebs);
 
 static __always_inline struct x86_perf_task_context_opt *task_context_opt(void *ctx)
 {

From f9bdf1f953392c9edd69a7f884f78c0390127029 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Tue, 21 Jan 2025 07:23:01 -0800
Subject: [PATCH 0052/1173] perf/x86/intel: Avoid disable PMU if !cpuc->enabled
 in sample read

The WARN_ON(this_cpu_read(cpu_hw_events.enabled)) in the
intel_pmu_save_and_restart_reload() is triggered, when sampling read
topdown events.

In a NMI handler, the cpu_hw_events.enabled is set and used to indicate
the status of core PMU. The generic pmu->pmu_disable_count, updated in
the perf_pmu_disable/enable pair, is not touched.
However, the perf_pmu_disable/enable pair is invoked when sampling read
in a NMI handler. The cpuc->enabled is mistakenly set by the
perf_pmu_enable().

Avoid disabling PMU if the core PMU is already disabled.
Merge the logic together.

Fixes: 7b2c05a15d29 ("perf/x86/intel: Generic support for hardware TopDown metrics")
Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20250121152303.3128733-2-kan.liang@linux.intel.com
---
 arch/x86/events/intel/core.c | 41 ++++++++++++++++++++----------------
 arch/x86/events/intel/ds.c   | 11 +---------
 arch/x86/events/perf_event.h |  2 +-
 3 files changed, 25 insertions(+), 29 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 2acea83526c63..1ccc961f81821 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2785,28 +2785,33 @@ static u64 icl_update_topdown_event(struct perf_event *event)
 
 DEFINE_STATIC_CALL(intel_pmu_update_topdown_event, x86_perf_event_update);
 
-static void intel_pmu_read_topdown_event(struct perf_event *event)
+static void intel_pmu_read_event(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	if (event->hw.flags & (PERF_X86_EVENT_AUTO_RELOAD | PERF_X86_EVENT_TOPDOWN)) {
+		struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+		bool pmu_enabled = cpuc->enabled;
 
-	/* Only need to call update_topdown_event() once for group read. */
-	if ((cpuc->txn_flags & PERF_PMU_TXN_READ) &&
-	    !is_slots_event(event))
-		return;
+		/* Only need to call update_topdown_event() once for group read. */
+		if (is_metric_event(event) && (cpuc->txn_flags & PERF_PMU_TXN_READ))
+			return;
 
-	perf_pmu_disable(event->pmu);
-	static_call(intel_pmu_update_topdown_event)(event);
-	perf_pmu_enable(event->pmu);
-}
+		cpuc->enabled = 0;
+		if (pmu_enabled)
+			intel_pmu_disable_all();
 
-static void intel_pmu_read_event(struct perf_event *event)
-{
-	if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
-		intel_pmu_auto_reload_read(event);
-	else if (is_topdown_count(event))
-		intel_pmu_read_topdown_event(event);
-	else
-		x86_perf_event_update(event);
+		if (is_topdown_event(event))
+			static_call(intel_pmu_update_topdown_event)(event);
+		else
+			intel_pmu_drain_pebs_buffer();
+
+		cpuc->enabled = pmu_enabled;
+		if (pmu_enabled)
+			intel_pmu_enable_all(0);
+
+		return;
+	}
+
+	x86_perf_event_update(event);
 }
 
 static void intel_pmu_enable_fixed(struct perf_event *event)
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 322963b02a912..eb14b46423e58 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -953,7 +953,7 @@ int intel_pmu_drain_bts_buffer(void)
 	return 1;
 }
 
-static inline void intel_pmu_drain_pebs_buffer(void)
+void intel_pmu_drain_pebs_buffer(void)
 {
 	struct perf_sample_data data;
 
@@ -2094,15 +2094,6 @@ get_next_pebs_record_by_bit(void *base, void *top, int bit)
 	return NULL;
 }
 
-void intel_pmu_auto_reload_read(struct perf_event *event)
-{
-	WARN_ON(!(event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD));
-
-	perf_pmu_disable(event->pmu);
-	intel_pmu_drain_pebs_buffer();
-	perf_pmu_enable(event->pmu);
-}
-
 /*
  * Special variant of intel_pmu_save_and_restart() for auto-reload.
  */
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 084e9196b4582..536a112f6353e 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -1644,7 +1644,7 @@ void intel_pmu_pebs_disable_all(void);
 
 void intel_pmu_pebs_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in);
 
-void intel_pmu_auto_reload_read(struct perf_event *event);
+void intel_pmu_drain_pebs_buffer(void);
 
 void intel_pmu_store_pebs_lbrs(struct lbr_entry *lbr);
 

From 8ce939a0fa194939cc1f92dbd8bc1a7806e7d40a Mon Sep 17 00:00:00 2001
From: "Peter Zijlstra (Intel)" <peterz@infradead.org>
Date: Tue, 21 Jan 2025 07:23:02 -0800
Subject: [PATCH 0053/1173] perf: Avoid the read if the count is already
 updated

The event may have been updated in the PMU-specific implementation,
e.g., Intel PEBS counters snapshotting. The common code should not
read and overwrite the value.

The PERF_SAMPLE_READ in the data->sample_type can be used to detect
whether the PMU-specific value is available. If yes, avoid the
pmu->read() in the common code. Add a new flag, skip_read, to track the
case.

Factor out a perf_pmu_read() to clean up the code.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250121152303.3128733-3-kan.liang@linux.intel.com
---
 include/linux/perf_event.h  |  8 +++++++-
 kernel/events/core.c        | 33 ++++++++++++++++-----------------
 kernel/events/ring_buffer.c |  1 +
 3 files changed, 24 insertions(+), 18 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 8333f132f4a96..2d07bc1193f3a 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1062,7 +1062,13 @@ struct perf_output_handle {
 	struct perf_buffer		*rb;
 	unsigned long			wakeup;
 	unsigned long			size;
-	u64				aux_flags;
+	union {
+		u64			flags;		/* perf_output*() */
+		u64			aux_flags;	/* perf_aux_output*() */
+		struct {
+			u64		skip_read : 1;
+		};
+	};
 	union {
 		void			*addr;
 		unsigned long		head;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index bcb09e011e9e1..0f8c559907830 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1191,6 +1191,12 @@ static void perf_assert_pmu_disabled(struct pmu *pmu)
 	WARN_ON_ONCE(*this_cpu_ptr(pmu->pmu_disable_count) == 0);
 }
 
+static inline void perf_pmu_read(struct perf_event *event)
+{
+	if (event->state == PERF_EVENT_STATE_ACTIVE)
+		event->pmu->read(event);
+}
+
 static void get_ctx(struct perf_event_context *ctx)
 {
 	refcount_inc(&ctx->refcount);
@@ -3473,8 +3479,7 @@ static void __perf_event_sync_stat(struct perf_event *event,
 	 * we know the event must be on the current CPU, therefore we
 	 * don't need to use it.
 	 */
-	if (event->state == PERF_EVENT_STATE_ACTIVE)
-		event->pmu->read(event);
+	perf_pmu_read(event);
 
 	perf_event_update_time(event);
 
@@ -4618,15 +4623,8 @@ static void __perf_event_read(void *info)
 
 	pmu->read(event);
 
-	for_each_sibling_event(sub, event) {
-		if (sub->state == PERF_EVENT_STATE_ACTIVE) {
-			/*
-			 * Use sibling's PMU rather than @event's since
-			 * sibling could be on different (eg: software) PMU.
-			 */
-			sub->pmu->read(sub);
-		}
-	}
+	for_each_sibling_event(sub, event)
+		perf_pmu_read(sub);
 
 	data->ret = pmu->commit_txn(pmu);
 
@@ -7444,9 +7442,8 @@ static void perf_output_read_group(struct perf_output_handle *handle,
 	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
 		values[n++] = running;
 
-	if ((leader != event) &&
-	    (leader->state == PERF_EVENT_STATE_ACTIVE))
-		leader->pmu->read(leader);
+	if ((leader != event) && !handle->skip_read)
+		perf_pmu_read(leader);
 
 	values[n++] = perf_event_count(leader, self);
 	if (read_format & PERF_FORMAT_ID)
@@ -7459,9 +7456,8 @@ static void perf_output_read_group(struct perf_output_handle *handle,
 	for_each_sibling_event(sub, leader) {
 		n = 0;
 
-		if ((sub != event) &&
-		    (sub->state == PERF_EVENT_STATE_ACTIVE))
-			sub->pmu->read(sub);
+		if ((sub != event) && !handle->skip_read)
+			perf_pmu_read(sub);
 
 		values[n++] = perf_event_count(sub, self);
 		if (read_format & PERF_FORMAT_ID)
@@ -7520,6 +7516,9 @@ void perf_output_sample(struct perf_output_handle *handle,
 {
 	u64 sample_type = data->type;
 
+	if (data->sample_flags & PERF_SAMPLE_READ)
+		handle->skip_read = 1;
+
 	perf_output_put(handle, *header);
 
 	if (sample_type & PERF_SAMPLE_IDENTIFIER)
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 180509132d4b6..59a52b1a1f789 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -185,6 +185,7 @@ __perf_output_begin(struct perf_output_handle *handle,
 
 	handle->rb    = rb;
 	handle->event = event;
+	handle->flags = 0;
 
 	have_lost = local_read(&rb->lost);
 	if (unlikely(have_lost)) {

From e02e9b0374c378aab016ae8ace60d9d98ab8caa6 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Tue, 21 Jan 2025 07:23:03 -0800
Subject: [PATCH 0054/1173] perf/x86/intel: Support PEBS counters snapshotting

The counters snapshotting is a new adaptive PEBS extension, which can
capture programmable counters, fixed-function counters, and performance
metrics in a PEBS record. The feature is available in the PEBS format
V6.

The target counters can be configured in the new fields of MSR_PEBS_CFG.
Then the PEBS HW will generate the bit mask of counters (Counters Group
Header) followed by the content of all the requested counters into a
PEBS record.

The current Linux perf sample read feature can read all events in the
group when any event in the group is overflowed. But the rdpmc in the
NMI/overflow handler has a small gap from overflow. Also, there is some
overhead for each rdpmc read. The counters snapshotting feature can be
used as an accurate and low-overhead replacement.

Extend intel_update_topdown_event() to accept the value from PEBS
records.

Add a new PEBS_CNTR flag to indicate a sample read group that utilizes
the counters snapshotting feature. When the group is scheduled, the
PEBS configure can be updated accordingly.

To prevent the case that a PEBS record value might be in the past
relative to what is already in the event, perf always stops the PMU and
drains the PEBS buffer before updating the corresponding event->count.

Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250121152303.3128733-4-kan.liang@linux.intel.com
---
 arch/x86/events/core.c             |  13 ++
 arch/x86/events/intel/core.c       |  75 ++++++++---
 arch/x86/events/intel/ds.c         | 191 +++++++++++++++++++++++++++--
 arch/x86/events/perf_event.h       |  13 ++
 arch/x86/events/perf_event_flags.h |   2 +-
 arch/x86/include/asm/perf_event.h  |  15 +++
 6 files changed, 284 insertions(+), 25 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 8f218ac0d445c..7b6430e5a77b6 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -94,6 +94,8 @@ DEFINE_STATIC_CALL_NULL(x86_pmu_pebs_aliases, *x86_pmu.pebs_aliases);
 
 DEFINE_STATIC_CALL_NULL(x86_pmu_filter, *x86_pmu.filter);
 
+DEFINE_STATIC_CALL_NULL(x86_pmu_late_setup, *x86_pmu.late_setup);
+
 /*
  * This one is magic, it will get called even when PMU init fails (because
  * there is no PMU), in which case it should simply return NULL.
@@ -1298,6 +1300,15 @@ static void x86_pmu_enable(struct pmu *pmu)
 
 	if (cpuc->n_added) {
 		int n_running = cpuc->n_events - cpuc->n_added;
+
+		/*
+		 * The late setup (after counters are scheduled)
+		 * is required for some cases, e.g., PEBS counters
+		 * snapshotting. Because an accurate counter index
+		 * is needed.
+		 */
+		static_call_cond(x86_pmu_late_setup)();
+
 		/*
 		 * apply assignment obtained either from
 		 * hw_perf_group_sched_in() or x86_pmu_enable()
@@ -2035,6 +2046,8 @@ static void x86_pmu_static_call_update(void)
 
 	static_call_update(x86_pmu_guest_get_msrs, x86_pmu.guest_get_msrs);
 	static_call_update(x86_pmu_filter, x86_pmu.filter);
+
+	static_call_update(x86_pmu_late_setup, x86_pmu.late_setup);
 }
 
 static void _x86_pmu_read(struct perf_event *event)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 1ccc961f81821..8ce915abcd642 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2720,7 +2720,7 @@ static void update_saved_topdown_regs(struct perf_event *event, u64 slots,
  * modify by a NMI. PMU has to be disabled before calling this function.
  */
 
-static u64 intel_update_topdown_event(struct perf_event *event, int metric_end)
+static u64 intel_update_topdown_event(struct perf_event *event, int metric_end, u64 *val)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct perf_event *other;
@@ -2728,13 +2728,24 @@ static u64 intel_update_topdown_event(struct perf_event *event, int metric_end)
 	bool reset = true;
 	int idx;
 
-	/* read Fixed counter 3 */
-	rdpmcl((3 | INTEL_PMC_FIXED_RDPMC_BASE), slots);
-	if (!slots)
-		return 0;
+	if (!val) {
+		/* read Fixed counter 3 */
+		rdpmcl((3 | INTEL_PMC_FIXED_RDPMC_BASE), slots);
+		if (!slots)
+			return 0;
 
-	/* read PERF_METRICS */
-	rdpmcl(INTEL_PMC_FIXED_RDPMC_METRICS, metrics);
+		/* read PERF_METRICS */
+		rdpmcl(INTEL_PMC_FIXED_RDPMC_METRICS, metrics);
+	} else {
+		slots = val[0];
+		metrics = val[1];
+		/*
+		 * Don't reset the PERF_METRICS and Fixed counter 3
+		 * for each PEBS record read. Utilize the RDPMC metrics
+		 * clear mode.
+		 */
+		reset = false;
+	}
 
 	for_each_set_bit(idx, cpuc->active_mask, metric_end + 1) {
 		if (!is_topdown_idx(idx))
@@ -2777,17 +2788,19 @@ static u64 intel_update_topdown_event(struct perf_event *event, int metric_end)
 	return slots;
 }
 
-static u64 icl_update_topdown_event(struct perf_event *event)
+static u64 icl_update_topdown_event(struct perf_event *event, u64 *val)
 {
 	return intel_update_topdown_event(event, INTEL_PMC_IDX_METRIC_BASE +
-						 x86_pmu.num_topdown_events - 1);
+						 x86_pmu.num_topdown_events - 1,
+					  val);
 }
 
-DEFINE_STATIC_CALL(intel_pmu_update_topdown_event, x86_perf_event_update);
+DEFINE_STATIC_CALL(intel_pmu_update_topdown_event, intel_pmu_topdown_event_update);
 
 static void intel_pmu_read_event(struct perf_event *event)
 {
-	if (event->hw.flags & (PERF_X86_EVENT_AUTO_RELOAD | PERF_X86_EVENT_TOPDOWN)) {
+	if (event->hw.flags & (PERF_X86_EVENT_AUTO_RELOAD | PERF_X86_EVENT_TOPDOWN) ||
+	    is_pebs_counter_event_group(event)) {
 		struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 		bool pmu_enabled = cpuc->enabled;
 
@@ -2799,8 +2812,12 @@ static void intel_pmu_read_event(struct perf_event *event)
 		if (pmu_enabled)
 			intel_pmu_disable_all();
 
-		if (is_topdown_event(event))
-			static_call(intel_pmu_update_topdown_event)(event);
+		/*
+		 * If the PEBS counters snapshotting is enabled,
+		 * the topdown event is available in PEBS records.
+		 */
+		if (is_topdown_event(event) && !is_pebs_counter_event_group(event))
+			static_call(intel_pmu_update_topdown_event)(event, NULL);
 		else
 			intel_pmu_drain_pebs_buffer();
 
@@ -2943,7 +2960,7 @@ static int intel_pmu_set_period(struct perf_event *event)
 static u64 intel_pmu_update(struct perf_event *event)
 {
 	if (unlikely(is_topdown_count(event)))
-		return static_call(intel_pmu_update_topdown_event)(event);
+		return static_call(intel_pmu_update_topdown_event)(event, NULL);
 
 	return x86_perf_event_update(event);
 }
@@ -3109,7 +3126,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 	 */
 	if (__test_and_clear_bit(GLOBAL_STATUS_PERF_METRICS_OVF_BIT, (unsigned long *)&status)) {
 		handled++;
-		static_call(intel_pmu_update_topdown_event)(NULL);
+		static_call(intel_pmu_update_topdown_event)(NULL, NULL);
 	}
 
 	/*
@@ -3127,6 +3144,27 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 		if (!test_bit(bit, cpuc->active_mask))
 			continue;
 
+		/*
+		 * There may be unprocessed PEBS records in the PEBS buffer,
+		 * which still stores the previous values.
+		 * Process those records first before handling the latest value.
+		 * For example,
+		 * A is a regular counter
+		 * B is a PEBS event which reads A
+		 * C is a PEBS event
+		 *
+		 * The following can happen:
+		 * B-assist			A=1
+		 * C				A=2
+		 * B-assist			A=3
+		 * A-overflow-PMI		A=4
+		 * C-assist-PMI (PEBS buffer)	A=5
+		 *
+		 * The PEBS buffer has to be drained before handling the A-PMI
+		 */
+		if (is_pebs_counter_event_group(event))
+			x86_pmu.drain_pebs(regs, &data);
+
 		if (!intel_pmu_save_and_restart(event))
 			continue;
 
@@ -4074,6 +4112,13 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		event->hw.flags |= PERF_X86_EVENT_PEBS_VIA_PT;
 	}
 
+	if ((event->attr.sample_type & PERF_SAMPLE_READ) &&
+	    (x86_pmu.intel_cap.pebs_format >= 6) &&
+	    x86_pmu.intel_cap.pebs_baseline &&
+	    is_sampling_event(event) &&
+	    event->attr.precise_ip)
+		event->group_leader->hw.flags |= PERF_X86_EVENT_PEBS_CNTR;
+
 	if ((event->attr.type == PERF_TYPE_HARDWARE) ||
 	    (event->attr.type == PERF_TYPE_HW_CACHE))
 		return 0;
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index eb14b46423e58..13a78a8a2780d 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1294,6 +1294,19 @@ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
 	ds->pebs_interrupt_threshold = threshold;
 }
 
+#define PEBS_DATACFG_CNTRS(x)						\
+	((x >> PEBS_DATACFG_CNTR_SHIFT) & PEBS_DATACFG_CNTR_MASK)
+
+#define PEBS_DATACFG_CNTR_BIT(x)					\
+	(((1ULL << x) & PEBS_DATACFG_CNTR_MASK) << PEBS_DATACFG_CNTR_SHIFT)
+
+#define PEBS_DATACFG_FIX(x)						\
+	((x >> PEBS_DATACFG_FIX_SHIFT) & PEBS_DATACFG_FIX_MASK)
+
+#define PEBS_DATACFG_FIX_BIT(x)						\
+	(((1ULL << (x)) & PEBS_DATACFG_FIX_MASK)			\
+	 << PEBS_DATACFG_FIX_SHIFT)
+
 static void adaptive_pebs_record_size_update(void)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
@@ -1308,10 +1321,58 @@ static void adaptive_pebs_record_size_update(void)
 		sz += sizeof(struct pebs_xmm);
 	if (pebs_data_cfg & PEBS_DATACFG_LBRS)
 		sz += x86_pmu.lbr_nr * sizeof(struct lbr_entry);
+	if (pebs_data_cfg & (PEBS_DATACFG_METRICS | PEBS_DATACFG_CNTR)) {
+		sz += sizeof(struct pebs_cntr_header);
+
+		/* Metrics base and Metrics Data */
+		if (pebs_data_cfg & PEBS_DATACFG_METRICS)
+			sz += 2 * sizeof(u64);
+
+		if (pebs_data_cfg & PEBS_DATACFG_CNTR) {
+			sz += (hweight64(PEBS_DATACFG_CNTRS(pebs_data_cfg)) +
+			       hweight64(PEBS_DATACFG_FIX(pebs_data_cfg))) *
+			      sizeof(u64);
+		}
+	}
 
 	cpuc->pebs_record_size = sz;
 }
 
+static void __intel_pmu_pebs_update_cfg(struct perf_event *event,
+					int idx, u64 *pebs_data_cfg)
+{
+	if (is_metric_event(event)) {
+		*pebs_data_cfg |= PEBS_DATACFG_METRICS;
+		return;
+	}
+
+	*pebs_data_cfg |= PEBS_DATACFG_CNTR;
+
+	if (idx >= INTEL_PMC_IDX_FIXED)
+		*pebs_data_cfg |= PEBS_DATACFG_FIX_BIT(idx - INTEL_PMC_IDX_FIXED);
+	else
+		*pebs_data_cfg |= PEBS_DATACFG_CNTR_BIT(idx);
+}
+
+
+static void intel_pmu_late_setup(void)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct perf_event *event;
+	u64 pebs_data_cfg = 0;
+	int i;
+
+	for (i = 0; i < cpuc->n_events; i++) {
+		event = cpuc->event_list[i];
+		if (!is_pebs_counter_event_group(event))
+			continue;
+		__intel_pmu_pebs_update_cfg(event, cpuc->assign[i], &pebs_data_cfg);
+	}
+
+	if (pebs_data_cfg & ~cpuc->pebs_data_cfg)
+		cpuc->pebs_data_cfg |= pebs_data_cfg | PEBS_UPDATE_DS_SW;
+}
+
 #define PERF_PEBS_MEMINFO_TYPE	(PERF_SAMPLE_ADDR | PERF_SAMPLE_DATA_SRC |   \
 				PERF_SAMPLE_PHYS_ADDR |			     \
 				PERF_SAMPLE_WEIGHT_TYPE |		     \
@@ -1914,12 +1975,89 @@ static void adaptive_pebs_save_regs(struct pt_regs *regs,
 #endif
 }
 
+static void intel_perf_event_update_pmc(struct perf_event *event, u64 pmc)
+{
+	int shift = 64 - x86_pmu.cntval_bits;
+	struct hw_perf_event *hwc;
+	u64 delta, prev_pmc;
+
+	/*
+	 * A recorded counter may not have an assigned event in the
+	 * following cases. The value should be dropped.
+	 * - An event is deleted. There is still an active PEBS event.
+	 *   The PEBS record doesn't shrink on pmu::del().
+	 *   If the counter of the deleted event once occurred in a PEBS
+	 *   record, PEBS still records the counter until the counter is
+	 *   reassigned.
+	 * - An event is stopped for some reason, e.g., throttled.
+	 *   During this period, another event is added and takes the
+	 *   counter of the stopped event. The stopped event is assigned
+	 *   to another new and uninitialized counter, since the
+	 *   x86_pmu_start(RELOAD) is not invoked for a stopped event.
+	 *   The PEBS__DATA_CFG is updated regardless of the event state.
+	 *   The uninitialized counter can be recorded in a PEBS record.
+	 *   But the cpuc->events[uninitialized_counter] is always NULL,
+	 *   because the event is stopped. The uninitialized value is
+	 *   safely dropped.
+	 */
+	if (!event)
+		return;
+
+	hwc = &event->hw;
+	prev_pmc = local64_read(&hwc->prev_count);
+
+	/* Only update the count when the PMU is disabled */
+	WARN_ON(this_cpu_read(cpu_hw_events.enabled));
+	local64_set(&hwc->prev_count, pmc);
+
+	delta = (pmc << shift) - (prev_pmc << shift);
+	delta >>= shift;
+
+	local64_add(delta, &event->count);
+	local64_sub(delta, &hwc->period_left);
+}
+
+static inline void __setup_pebs_counter_group(struct cpu_hw_events *cpuc,
+					      struct perf_event *event,
+					      struct pebs_cntr_header *cntr,
+					      void *next_record)
+{
+	int bit;
+
+	for_each_set_bit(bit, (unsigned long *)&cntr->cntr, INTEL_PMC_MAX_GENERIC) {
+		intel_perf_event_update_pmc(cpuc->events[bit], *(u64 *)next_record);
+		next_record += sizeof(u64);
+	}
+
+	for_each_set_bit(bit, (unsigned long *)&cntr->fixed, INTEL_PMC_MAX_FIXED) {
+		/* The slots event will be handled with perf_metric later */
+		if ((cntr->metrics == INTEL_CNTR_METRICS) &&
+		    (bit + INTEL_PMC_IDX_FIXED == INTEL_PMC_IDX_FIXED_SLOTS)) {
+			next_record += sizeof(u64);
+			continue;
+		}
+		intel_perf_event_update_pmc(cpuc->events[bit + INTEL_PMC_IDX_FIXED],
+					    *(u64 *)next_record);
+		next_record += sizeof(u64);
+	}
+
+	/* HW will reload the value right after the overflow. */
+	if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
+		local64_set(&event->hw.prev_count, (u64)-event->hw.sample_period);
+
+	if (cntr->metrics == INTEL_CNTR_METRICS) {
+		static_call(intel_pmu_update_topdown_event)
+			   (cpuc->events[INTEL_PMC_IDX_FIXED_SLOTS],
+			    (u64 *)next_record);
+		next_record += 2 * sizeof(u64);
+	}
+}
+
 #define PEBS_LATENCY_MASK			0xffff
 
 /*
  * With adaptive PEBS the layout depends on what fields are configured.
  */
-
 static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 					    struct pt_regs *iregs, void *__pebs,
 					    struct perf_sample_data *data,
@@ -2049,6 +2187,28 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 		}
 	}
 
+	if (format_group & (PEBS_DATACFG_CNTR | PEBS_DATACFG_METRICS)) {
+		struct pebs_cntr_header *cntr = next_record;
+		unsigned int nr;
+
+		next_record += sizeof(struct pebs_cntr_header);
+		/*
+		 * The PEBS_DATA_CFG is a global register, which is the
+		 * superset configuration for all PEBS events.
+		 * For the PEBS record of non-sample-read group, ignore
+		 * the counter snapshot fields.
+		 */
+		if (is_pebs_counter_event_group(event)) {
+			__setup_pebs_counter_group(cpuc, event, cntr, next_record);
+			data->sample_flags |= PERF_SAMPLE_READ;
+		}
+
+		nr = hweight32(cntr->cntr) + hweight32(cntr->fixed);
+		if (cntr->metrics == INTEL_CNTR_METRICS)
+			nr += 2;
+		next_record += nr * sizeof(u64);
+	}
+
 	WARN_ONCE(next_record != __pebs + basic->format_size,
 			"PEBS record size %u, expected %llu, config %llx\n",
 			basic->format_size,
@@ -2202,13 +2362,21 @@ __intel_pmu_pebs_last_event(struct perf_event *event,
 	}
 
 	if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
-		/*
-		 * Now, auto-reload is only enabled in fixed period mode.
-		 * The reload value is always hwc->sample_period.
-		 * May need to change it, if auto-reload is enabled in
-		 * freq mode later.
-		 */
-		intel_pmu_save_and_restart_reload(event, count);
+		if ((is_pebs_counter_event_group(event))) {
+			/*
+			 * The value of each sample has been updated when setup
+			 * the corresponding sample data.
+			 */
+			perf_event_update_userpage(event);
+		} else {
+			/*
+			 * Now, auto-reload is only enabled in fixed period mode.
+			 * The reload value is always hwc->sample_period.
+			 * May need to change it, if auto-reload is enabled in
+			 * freq mode later.
+			 */
+			intel_pmu_save_and_restart_reload(event, count);
+		}
 	} else
 		intel_pmu_save_and_restart(event);
 }
@@ -2543,6 +2711,11 @@ void __init intel_ds_init(void)
 			break;
 
 		case 6:
+			if (x86_pmu.intel_cap.pebs_baseline) {
+				x86_pmu.large_pebs_flags |= PERF_SAMPLE_READ;
+				x86_pmu.late_setup = intel_pmu_late_setup;
+			}
+			fallthrough;
 		case 5:
 			x86_pmu.pebs_ept = 1;
 			fallthrough;
@@ -2567,7 +2740,7 @@ void __init intel_ds_init(void)
 					  PERF_SAMPLE_REGS_USER |
 					  PERF_SAMPLE_REGS_INTR);
 			}
-			pr_cont("PEBS fmt4%c%s, ", pebs_type, pebs_qual);
+			pr_cont("PEBS fmt%d%c%s, ", format, pebs_type, pebs_qual);
 
 			if (!is_hybrid() && x86_pmu.intel_cap.pebs_output_pt_available) {
 				pr_cont("PEBS-via-PT, ");
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 536a112f6353e..a698e6484b3b6 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -115,6 +115,11 @@ static inline bool is_branch_counters_group(struct perf_event *event)
 	return event->group_leader->hw.flags & PERF_X86_EVENT_BRANCH_COUNTERS;
 }
 
+static inline bool is_pebs_counter_event_group(struct perf_event *event)
+{
+	return event->group_leader->hw.flags & PERF_X86_EVENT_PEBS_CNTR;
+}
+
 struct amd_nb {
 	int nb_id;  /* NorthBridge id */
 	int refcnt; /* reference count */
@@ -800,6 +805,7 @@ struct x86_pmu {
 	u64		(*update)(struct perf_event *event);
 	int		(*hw_config)(struct perf_event *event);
 	int		(*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign);
+	void		(*late_setup)(void);
 	unsigned	eventsel;
 	unsigned	perfctr;
 	unsigned	fixedctr;
@@ -1108,6 +1114,7 @@ extern struct x86_pmu x86_pmu __read_mostly;
 DECLARE_STATIC_CALL(x86_pmu_set_period, *x86_pmu.set_period);
 DECLARE_STATIC_CALL(x86_pmu_update,     *x86_pmu.update);
 DECLARE_STATIC_CALL(x86_pmu_drain_pebs,	*x86_pmu.drain_pebs);
+DECLARE_STATIC_CALL(x86_pmu_late_setup,	*x86_pmu.late_setup);
 
 static __always_inline struct x86_perf_task_context_opt *task_context_opt(void *ctx)
 {
@@ -1149,6 +1156,12 @@ extern u64 __read_mostly hw_cache_extra_regs
 
 u64 x86_perf_event_update(struct perf_event *event);
 
+static inline u64 intel_pmu_topdown_event_update(struct perf_event *event, u64 *val)
+{
+	return x86_perf_event_update(event);
+}
+DECLARE_STATIC_CALL(intel_pmu_update_topdown_event, intel_pmu_topdown_event_update);
+
 static inline unsigned int x86_pmu_config_addr(int index)
 {
 	return x86_pmu.eventsel + (x86_pmu.addr_offset ?
diff --git a/arch/x86/events/perf_event_flags.h b/arch/x86/events/perf_event_flags.h
index 6c977c19f2cd7..1d9e385649b57 100644
--- a/arch/x86/events/perf_event_flags.h
+++ b/arch/x86/events/perf_event_flags.h
@@ -9,7 +9,7 @@ PERF_ARCH(PEBS_LD_HSW,		0x00008) /* haswell style datala, load */
 PERF_ARCH(PEBS_NA_HSW,		0x00010) /* haswell style datala, unknown */
 PERF_ARCH(EXCL,			0x00020) /* HT exclusivity on counter */
 PERF_ARCH(DYNAMIC,		0x00040) /* dynamic alloc'd constraint */
-			/*	0x00080	*/
+PERF_ARCH(PEBS_CNTR,		0x00080) /* PEBS counters snapshot */
 PERF_ARCH(EXCL_ACCT,		0x00100) /* accounted EXCL event */
 PERF_ARCH(AUTO_RELOAD,		0x00200) /* use PEBS auto-reload */
 PERF_ARCH(LARGE_PEBS,		0x00400) /* use large PEBS */
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index ee5581768fea7..73b104049f8cf 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -141,6 +141,12 @@
 #define PEBS_DATACFG_XMMS	BIT_ULL(2)
 #define PEBS_DATACFG_LBRS	BIT_ULL(3)
 #define PEBS_DATACFG_LBR_SHIFT	24
+#define PEBS_DATACFG_CNTR	BIT_ULL(4)
+#define PEBS_DATACFG_CNTR_SHIFT	32
+#define PEBS_DATACFG_CNTR_MASK	GENMASK_ULL(15, 0)
+#define PEBS_DATACFG_FIX_SHIFT	48
+#define PEBS_DATACFG_FIX_MASK	GENMASK_ULL(7, 0)
+#define PEBS_DATACFG_METRICS	BIT_ULL(5)
 
 /* Steal the highest bit of pebs_data_cfg for SW usage */
 #define PEBS_UPDATE_DS_SW	BIT_ULL(63)
@@ -460,6 +466,15 @@ struct pebs_xmm {
 	u64 xmm[16*2];	/* two entries for each register */
 };
 
+struct pebs_cntr_header {
+	u32 cntr;
+	u32 fixed;
+	u32 metrics;
+	u32 reserved;
+};
+
+#define INTEL_CNTR_METRICS		0x3
+
 /*
  * AMD Extended Performance Monitoring and Debug cpuid feature detection
  */

From a7dd183f0b3848c056bbeed78ef5d5c52fe94d83 Mon Sep 17 00:00:00 2001
From: Patryk Wlazlyn <patryk.wlazlyn@linux.intel.com>
Date: Wed, 5 Feb 2025 17:52:08 +0200
Subject: [PATCH 0055/1173] x86/smp: Allow calling mwait_play_dead with an
 arbitrary hint

Introduce a helper function to allow offlined CPUs to enter idle states
with a specific MWAIT hint. The new helper will be used in subsequent
patches by the acpi_idle and intel_idle drivers.

No functional change intended.

Signed-off-by: Patryk Wlazlyn <patryk.wlazlyn@linux.intel.com>
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lore.kernel.org/all/20250205155211.329780-2-artem.bityutskiy%40linux.intel.com
---
 arch/x86/include/asm/smp.h |  3 ++
 arch/x86/kernel/smpboot.c  | 88 ++++++++++++++++++++------------------
 2 files changed, 50 insertions(+), 41 deletions(-)

diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index ca073f40698fa..80f8bfd83fc7b 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -114,6 +114,7 @@ void wbinvd_on_cpu(int cpu);
 int wbinvd_on_all_cpus(void);
 
 void smp_kick_mwait_play_dead(void);
+void mwait_play_dead(unsigned int eax_hint);
 
 void native_smp_send_reschedule(int cpu);
 void native_send_call_func_ipi(const struct cpumask *mask);
@@ -164,6 +165,8 @@ static inline struct cpumask *cpu_llc_shared_mask(int cpu)
 {
 	return (struct cpumask *)cpumask_of(0);
 }
+
+static inline void mwait_play_dead(unsigned int eax_hint) { }
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_DEBUG_NMI_SELFTEST
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index c10850ae6f094..8aad14e43f549 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1258,47 +1258,9 @@ void play_dead_common(void)
 	local_irq_disable();
 }
 
-/*
- * We need to flush the caches before going to sleep, lest we have
- * dirty data in our caches when we come back up.
- */
-static inline void mwait_play_dead(void)
+void __noreturn mwait_play_dead(unsigned int eax_hint)
 {
 	struct mwait_cpu_dead *md = this_cpu_ptr(&mwait_cpu_dead);
-	unsigned int eax, ebx, ecx, edx;
-	unsigned int highest_cstate = 0;
-	unsigned int highest_subcstate = 0;
-	int i;
-
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
-	    boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
-		return;
-	if (!this_cpu_has(X86_FEATURE_MWAIT))
-		return;
-	if (!this_cpu_has(X86_FEATURE_CLFLUSH))
-		return;
-
-	eax = CPUID_LEAF_MWAIT;
-	ecx = 0;
-	native_cpuid(&eax, &ebx, &ecx, &edx);
-
-	/*
-	 * eax will be 0 if EDX enumeration is not valid.
-	 * Initialized below to cstate, sub_cstate value when EDX is valid.
-	 */
-	if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED)) {
-		eax = 0;
-	} else {
-		edx >>= MWAIT_SUBSTATE_SIZE;
-		for (i = 0; i < 7 && edx; i++, edx >>= MWAIT_SUBSTATE_SIZE) {
-			if (edx & MWAIT_SUBSTATE_MASK) {
-				highest_cstate = i;
-				highest_subcstate = edx & MWAIT_SUBSTATE_MASK;
-			}
-		}
-		eax = (highest_cstate << MWAIT_SUBSTATE_SIZE) |
-			(highest_subcstate - 1);
-	}
 
 	/* Set up state for the kexec() hack below */
 	md->status = CPUDEAD_MWAIT_WAIT;
@@ -1319,7 +1281,7 @@ static inline void mwait_play_dead(void)
 		mb();
 		__monitor(md, 0, 0);
 		mb();
-		__mwait(eax, 0);
+		__mwait(eax_hint, 0);
 
 		if (READ_ONCE(md->control) == CPUDEAD_MWAIT_KEXEC_HLT) {
 			/*
@@ -1341,6 +1303,50 @@ static inline void mwait_play_dead(void)
 	}
 }
 
+/*
+ * We need to flush the caches before going to sleep, lest we have
+ * dirty data in our caches when we come back up.
+ */
+static inline void mwait_play_dead_cpuid_hint(void)
+{
+	unsigned int eax, ebx, ecx, edx;
+	unsigned int highest_cstate = 0;
+	unsigned int highest_subcstate = 0;
+	int i;
+
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
+	    boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
+		return;
+	if (!this_cpu_has(X86_FEATURE_MWAIT))
+		return;
+	if (!this_cpu_has(X86_FEATURE_CLFLUSH))
+		return;
+
+	eax = CPUID_LEAF_MWAIT;
+	ecx = 0;
+	native_cpuid(&eax, &ebx, &ecx, &edx);
+
+	/*
+	 * eax will be 0 if EDX enumeration is not valid.
+	 * Initialized below to cstate, sub_cstate value when EDX is valid.
+	 */
+	if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED)) {
+		eax = 0;
+	} else {
+		edx >>= MWAIT_SUBSTATE_SIZE;
+		for (i = 0; i < 7 && edx; i++, edx >>= MWAIT_SUBSTATE_SIZE) {
+			if (edx & MWAIT_SUBSTATE_MASK) {
+				highest_cstate = i;
+				highest_subcstate = edx & MWAIT_SUBSTATE_MASK;
+			}
+		}
+		eax = (highest_cstate << MWAIT_SUBSTATE_SIZE) |
+			(highest_subcstate - 1);
+	}
+
+	mwait_play_dead(eax);
+}
+
 /*
  * Kick all "offline" CPUs out of mwait on kexec(). See comment in
  * mwait_play_dead().
@@ -1391,7 +1397,7 @@ void native_play_dead(void)
 	play_dead_common();
 	tboot_shutdown(TB_SHUTDOWN_WFS);
 
-	mwait_play_dead();
+	mwait_play_dead_cpuid_hint();
 	if (cpuidle_play_dead())
 		hlt_play_dead();
 }

From 541ddf31e30022b8e6f44b3a943964e8f0989d15 Mon Sep 17 00:00:00 2001
From: Patryk Wlazlyn <patryk.wlazlyn@linux.intel.com>
Date: Wed, 5 Feb 2025 17:52:09 +0200
Subject: [PATCH 0056/1173] ACPI/processor_idle: Add FFH state handling

Recent Intel platforms will depend on the idle driver to pass the
correct hint for playing dead via mwait_play_dead_with_hint(). Expand
the existing enter_dead interface with handling for FFH states and pass
the MWAIT hint to the mwait_play_dead code.

Suggested-by: Gautham R. Shenoy <gautham.shenoy@amd.com>
Signed-off-by: Patryk Wlazlyn <patryk.wlazlyn@linux.intel.com>
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lore.kernel.org/all/20250205155211.329780-3-artem.bityutskiy%40linux.intel.com
---
 arch/x86/kernel/acpi/cstate.c | 10 ++++++++++
 drivers/acpi/processor_idle.c |  2 ++
 include/acpi/processor.h      |  5 +++++
 3 files changed, 17 insertions(+)

diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index 5854f0b8f0f19..5bdb65516969d 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -16,6 +16,7 @@
 #include <asm/cpuid.h>
 #include <asm/mwait.h>
 #include <asm/special_insns.h>
+#include <asm/smp.h>
 
 /*
  * Initialize bm_flags based on the CPU cache properties
@@ -205,6 +206,15 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu,
 }
 EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_probe);
 
+void acpi_processor_ffh_play_dead(struct acpi_processor_cx *cx)
+{
+	unsigned int cpu = smp_processor_id();
+	struct cstate_entry *percpu_entry;
+
+	percpu_entry = per_cpu_ptr(cpu_cstate_entry, cpu);
+	mwait_play_dead(percpu_entry->states[cx->index].eax);
+}
+
 void __cpuidle acpi_processor_ffh_cstate_enter(struct acpi_processor_cx *cx)
 {
 	unsigned int cpu = smp_processor_id();
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 698897b29de24..586cc7d1d8aa3 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -590,6 +590,8 @@ static void acpi_idle_play_dead(struct cpuidle_device *dev, int index)
 			raw_safe_halt();
 		else if (cx->entry_method == ACPI_CSTATE_SYSTEMIO) {
 			io_idle(cx->address);
+		} else if (cx->entry_method == ACPI_CSTATE_FFH) {
+			acpi_processor_ffh_play_dead(cx);
 		} else
 			return;
 	}
diff --git a/include/acpi/processor.h b/include/acpi/processor.h
index a17e97e634a68..63a37e72b7218 100644
--- a/include/acpi/processor.h
+++ b/include/acpi/processor.h
@@ -280,6 +280,7 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu,
 				    struct acpi_processor_cx *cx,
 				    struct acpi_power_register *reg);
 void acpi_processor_ffh_cstate_enter(struct acpi_processor_cx *cstate);
+void acpi_processor_ffh_play_dead(struct acpi_processor_cx *cx);
 #else
 static inline void acpi_processor_power_init_bm_check(struct
 						      acpi_processor_flags
@@ -300,6 +301,10 @@ static inline void acpi_processor_ffh_cstate_enter(struct acpi_processor_cx
 {
 	return;
 }
+static inline void acpi_processor_ffh_play_dead(struct acpi_processor_cx *cx)
+{
+	return;
+}
 #endif
 
 static inline int call_on_cpu(int cpu, long (*fn)(void *), void *arg,

From fc4ca9537bc4e3141ba7e058700369ea242703df Mon Sep 17 00:00:00 2001
From: Patryk Wlazlyn <patryk.wlazlyn@linux.intel.com>
Date: Wed, 5 Feb 2025 17:52:10 +0200
Subject: [PATCH 0057/1173] intel_idle: Provide the default enter_dead()
 handler

Recent Intel platforms require idle driver to provide information about
the MWAIT hint used to enter the deepest idle state in the play_dead
code.

Provide the default enter_dead() handler for all of the platforms and
allow overwriting with a custom handler for each platform if needed.

Signed-off-by: Patryk Wlazlyn <patryk.wlazlyn@linux.intel.com>
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lore.kernel.org/all/20250205155211.329780-4-artem.bityutskiy%40linux.intel.com
---
 drivers/idle/intel_idle.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 118fe1d37c226..e59073efb6fa4 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -57,6 +57,7 @@
 #include <asm/mwait.h>
 #include <asm/spec-ctrl.h>
 #include <asm/fpu/api.h>
+#include <asm/smp.h>
 
 #define INTEL_IDLE_VERSION "0.5.1"
 
@@ -228,6 +229,15 @@ static __cpuidle int intel_idle_s2idle(struct cpuidle_device *dev,
 	return 0;
 }
 
+static void intel_idle_enter_dead(struct cpuidle_device *dev, int index)
+{
+	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
+	struct cpuidle_state *state = &drv->states[index];
+	unsigned long eax = flg2MWAIT(state->flags);
+
+	mwait_play_dead(eax);
+}
+
 /*
  * States are indexed by the cstate number,
  * which is also the index into the MWAIT hint array.
@@ -1800,6 +1810,7 @@ static void __init intel_idle_init_cstates_acpi(struct cpuidle_driver *drv)
 			state->flags |= CPUIDLE_FLAG_TIMER_STOP;
 
 		state->enter = intel_idle;
+		state->enter_dead = intel_idle_enter_dead;
 		state->enter_s2idle = intel_idle_s2idle;
 	}
 }
@@ -2149,6 +2160,9 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv)
 		    !cpuidle_state_table[cstate].enter_s2idle)
 			break;
 
+		if (!cpuidle_state_table[cstate].enter_dead)
+			cpuidle_state_table[cstate].enter_dead = intel_idle_enter_dead;
+
 		/* If marked as unusable, skip this state. */
 		if (cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_UNUSABLE) {
 			pr_debug("state %s is disabled\n",

From 96040f7273e2bc0be1871ad9ed4da7b504da9410 Mon Sep 17 00:00:00 2001
From: Patryk Wlazlyn <patryk.wlazlyn@linux.intel.com>
Date: Wed, 5 Feb 2025 17:52:11 +0200
Subject: [PATCH 0058/1173] x86/smp: Eliminate mwait_play_dead_cpuid_hint()

Currently, mwait_play_dead_cpuid_hint() looks up the MWAIT hint of the
deepest idle state by inspecting CPUID leaf 0x5 with the assumption
that, if the number of sub-states for a given major C-state is nonzero,
those sub-states are always represented by consecutive numbers starting
from 0. This assumption is not based on the documented platform behavior
and in fact it is not met on recent Intel platforms.

For example, Intel's Sierra Forest report two C-states with two
substates each in cpuid leaf 0x5:

  Name*   target cstate    target subcstate (mwait hint)
  ===========================================================
  C1      0x00             0x00
  C1E     0x00             0x01

  --      0x10             ----

  C6S     0x20             0x22
  C6P     0x20             0x23

  --      0x30             ----

  /* No more (sub)states all the way down to the end. */
  ===========================================================

   * Names of the cstates are not included in the CPUID leaf 0x5,
     they are taken from the product specific documentation.

Notice that hints 0x20 and 0x21 are not defined for C-state 0x20
(C6), so the existing MWAIT hint lookup in
mwait_play_dead_cpuid_hint() based on the CPUID leaf 0x5 contents does
not work in this case.

Instead of using MWAIT hint lookup that is not guaranteed to work,
make native_play_dead() rely on the idle driver for the given platform
to put CPUs going offline into appropriate idle state and, if that
fails, fall back to hlt_play_dead().

Accordingly, drop mwait_play_dead_cpuid_hint() altogether and make
native_play_dead() call cpuidle_play_dead() instead of it
unconditionally with the assumption that it will not return if it is
successful. Still, in case cpuidle_play_dead() fails, call
hlt_play_dead() at the end.

Signed-off-by: Patryk Wlazlyn <patryk.wlazlyn@linux.intel.com>
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lore.kernel.org/all/20250205155211.329780-5-artem.bityutskiy%40linux.intel.com
---
 arch/x86/kernel/smpboot.c | 54 +++++----------------------------------
 1 file changed, 7 insertions(+), 47 deletions(-)

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 8aad14e43f549..5746084bafe44 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1258,6 +1258,10 @@ void play_dead_common(void)
 	local_irq_disable();
 }
 
+/*
+ * We need to flush the caches before going to sleep, lest we have
+ * dirty data in our caches when we come back up.
+ */
 void __noreturn mwait_play_dead(unsigned int eax_hint)
 {
 	struct mwait_cpu_dead *md = this_cpu_ptr(&mwait_cpu_dead);
@@ -1303,50 +1307,6 @@ void __noreturn mwait_play_dead(unsigned int eax_hint)
 	}
 }
 
-/*
- * We need to flush the caches before going to sleep, lest we have
- * dirty data in our caches when we come back up.
- */
-static inline void mwait_play_dead_cpuid_hint(void)
-{
-	unsigned int eax, ebx, ecx, edx;
-	unsigned int highest_cstate = 0;
-	unsigned int highest_subcstate = 0;
-	int i;
-
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
-	    boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
-		return;
-	if (!this_cpu_has(X86_FEATURE_MWAIT))
-		return;
-	if (!this_cpu_has(X86_FEATURE_CLFLUSH))
-		return;
-
-	eax = CPUID_LEAF_MWAIT;
-	ecx = 0;
-	native_cpuid(&eax, &ebx, &ecx, &edx);
-
-	/*
-	 * eax will be 0 if EDX enumeration is not valid.
-	 * Initialized below to cstate, sub_cstate value when EDX is valid.
-	 */
-	if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED)) {
-		eax = 0;
-	} else {
-		edx >>= MWAIT_SUBSTATE_SIZE;
-		for (i = 0; i < 7 && edx; i++, edx >>= MWAIT_SUBSTATE_SIZE) {
-			if (edx & MWAIT_SUBSTATE_MASK) {
-				highest_cstate = i;
-				highest_subcstate = edx & MWAIT_SUBSTATE_MASK;
-			}
-		}
-		eax = (highest_cstate << MWAIT_SUBSTATE_SIZE) |
-			(highest_subcstate - 1);
-	}
-
-	mwait_play_dead(eax);
-}
-
 /*
  * Kick all "offline" CPUs out of mwait on kexec(). See comment in
  * mwait_play_dead().
@@ -1397,9 +1357,9 @@ void native_play_dead(void)
 	play_dead_common();
 	tboot_shutdown(TB_SHUTDOWN_WFS);
 
-	mwait_play_dead_cpuid_hint();
-	if (cpuidle_play_dead())
-		hlt_play_dead();
+	/* Below returns only on error. */
+	cpuidle_play_dead();
+	hlt_play_dead();
 }
 
 #else /* ... !CONFIG_HOTPLUG_CPU */

From 63887c9f02030afd042c125052ad60680f7c21b2 Mon Sep 17 00:00:00 2001
From: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Date: Tue, 4 Feb 2025 18:33:50 +0100
Subject: [PATCH 0059/1173] x86: Compare physical instead of virtual PGD
 addresses

This is a preparatory patch for when pointers have tags in their
upper address bits. But it's a harmless change on its own.

The mm->pgd virtual address may be tagged because it came out of
the allocator at some point. The __va(read_cr3_pa()) address will
never be tagged (the tag bits are all 1's). A direct pointer value
comparison would fail if one is tagged and the other is not.

To fix this, just compare the physical addresses which are never
affected by tagging.

[ dhansen: subject and changelog munging ]

Signed-off-by: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/all/fde443d0e67f76a51e7ab4e96647705840f53ddb.1738686764.git.maciej.wieczor-retman%40intel.com
---
 arch/x86/mm/tlb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 6cf881a942bbe..ffc25b3480415 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -1325,7 +1325,7 @@ bool nmi_uaccess_okay(void)
 	if (loaded_mm != current_mm)
 		return false;
 
-	VM_WARN_ON_ONCE(current_mm->pgd != __va(read_cr3_pa()));
+	VM_WARN_ON_ONCE(__pa(current_mm->pgd) != read_cr3_pa());
 
 	return true;
 }

From c7691aec5e991cec9c5c5fdab08c24856a1fc56f Mon Sep 17 00:00:00 2001
From: Vaishnav Achath <vaishnav.a@ti.com>
Date: Wed, 5 Feb 2025 11:52:29 +0530
Subject: [PATCH 0060/1173] arm64: defconfig: Enable TISCI Interrupt Router and
 Aggregator

Enable TISCI Interrupt Router and Interrupt Aggregator drivers.
These IPs are found in all TI K3 SoCs like J721E, AM62X and is required
for core functionality like DMA, GPIO Interrupts which is necessary
during boot, thus make them built-in.

bloat-o-meter summary on vmlinux:
	add/remove: 460/1 grow/shrink: 4/0 up/down: 162483/-8 (162475)
	...
	Total: Before=31615984, After=31778459, chg +0.51%

These configs were previously selected for ARCH_K3 in respective Kconfigs
till commit b8b26ae398c4 ("irqchip/ti-sci-inta : Add module build support")
and commit 2d95ffaecbc2 ("irqchip/ti-sci-intr: Add module build support")
dropped them and few driver configs (TI_K3_UDMA, TI_K3_RINGACC)
dependent on these also got disabled due to this. While re-enabling the
TI_SCI_INT_*_IRQCHIP configs, these configs with missing dependencies
(which are already part of arm64 defconfig) also get re-enabled which
explains the slightly larger size increase from the bloat-o-meter summary.

Fixes: 2d95ffaecbc2 ("irqchip/ti-sci-intr: Add module build support")
Fixes: b8b26ae398c4 ("irqchip/ti-sci-inta : Add module build support")

Signed-off-by: Vaishnav Achath <vaishnav.a@ti.com>
Tested-by: Dhruva Gole <d-gole@ti.com>
Reviewed-by: Dhruva Gole <d-gole@ti.com>
Link: https://lore.kernel.org/r/20250205062229.3869081-1-vaishnav.a@ti.com
Signed-off-by: Nishanth Menon <nm@ti.com>
---
 arch/arm64/configs/defconfig | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index cb7da44155999..1f25423de3833 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -1551,6 +1551,8 @@ CONFIG_PWM_VISCONTI=m
 CONFIG_SL28CPLD_INTC=y
 CONFIG_QCOM_PDC=y
 CONFIG_QCOM_MPM=y
+CONFIG_TI_SCI_INTR_IRQCHIP=y
+CONFIG_TI_SCI_INTA_IRQCHIP=y
 CONFIG_RESET_GPIO=m
 CONFIG_RESET_IMX7=y
 CONFIG_RESET_QCOM_AOSS=y

From cc668a11e6ac8adb0e016711080d3f314722cc91 Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Mon, 3 Feb 2025 14:50:59 +0200
Subject: [PATCH 0061/1173] RDMA/mlx5: Fix a race for DMABUF MR which can lead
 to CQE with error

This patch addresses a potential race condition for a DMABUF MR that can
result in a CQE with an error on the UMR QP.

During the __mlx5_ib_dereg_mr() flow, the following sequence of calls
occurs:
mlx5_revoke_mr()
mlx5r_umr_revoke_mr()
mlx5r_umr_post_send_wait()
At this point, the lkey is freed from the hardware's perspective.

However, concurrently, mlx5_ib_dmabuf_invalidate_cb() might be triggered
by another task attempting to invalidate the MR having that freed lkey.

Since the lkey has already been freed, this can lead to a CQE error,
causing the UMR QP to enter an error state.

To resolve this race condition, the dma_resv_lock() which was hold as
part of the mlx5_ib_dmabuf_invalidate_cb() is now also acquired as part
of the mlx5_revoke_mr() scope.

Upon a successful revoke, we set umem_dmabuf->private which points to
that MR to NULL, preventing any further invalidation attempts on its
lkey.

Fixes: e6fb246ccafb ("RDMA/mlx5: Consolidate MR destruction to mlx5_ib_dereg_mr()")
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Reviewed-by: Artemy Kovalyov <artemyko@mnvidia.com>
Link: https://patch.msgid.link/70617067abbfaa0c816a2544c922e7f4346def58.1738587016.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/mlx5/mr.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index bb02b6adbf2c2..0a3cbb14e1839 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -1550,7 +1550,7 @@ static void mlx5_ib_dmabuf_invalidate_cb(struct dma_buf_attachment *attach)
 
 	dma_resv_assert_held(umem_dmabuf->attach->dmabuf->resv);
 
-	if (!umem_dmabuf->sgt)
+	if (!umem_dmabuf->sgt || !mr)
 		return;
 
 	mlx5r_umr_update_mr_pas(mr, MLX5_IB_UPD_XLT_ZAP);
@@ -2022,11 +2022,16 @@ static int mlx5_revoke_mr(struct mlx5_ib_mr *mr)
 	struct mlx5_ib_dev *dev = to_mdev(mr->ibmr.device);
 	struct mlx5_cache_ent *ent = mr->mmkey.cache_ent;
 	bool is_odp = is_odp_mr(mr);
+	bool is_odp_dma_buf = is_dmabuf_mr(mr) &&
+			!to_ib_umem_dmabuf(mr->umem)->pinned;
 	int ret = 0;
 
 	if (is_odp)
 		mutex_lock(&to_ib_umem_odp(mr->umem)->umem_mutex);
 
+	if (is_odp_dma_buf)
+		dma_resv_lock(to_ib_umem_dmabuf(mr->umem)->attach->dmabuf->resv, NULL);
+
 	if (mr->mmkey.cacheable && !mlx5r_umr_revoke_mr(mr) && !cache_ent_find_and_store(dev, mr)) {
 		ent = mr->mmkey.cache_ent;
 		/* upon storing to a clean temp entry - schedule its cleanup */
@@ -2054,6 +2059,12 @@ static int mlx5_revoke_mr(struct mlx5_ib_mr *mr)
 		mutex_unlock(&to_ib_umem_odp(mr->umem)->umem_mutex);
 	}
 
+	if (is_odp_dma_buf) {
+		if (!ret)
+			to_ib_umem_dmabuf(mr->umem)->private = NULL;
+		dma_resv_unlock(to_ib_umem_dmabuf(mr->umem)->attach->dmabuf->resv);
+	}
+
 	return ret;
 }
 

From abc7b3f1f056d69a8f11d6dceecc0c9549ace770 Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Mon, 3 Feb 2025 14:51:43 +0200
Subject: [PATCH 0062/1173] RDMA/mlx5: Fix a WARN during dereg_mr for DM type

Memory regions (MR) of type DM (device memory) do not have an associated
umem.

In the __mlx5_ib_dereg_mr() -> mlx5_free_priv_descs() flow, the code
incorrectly takes the wrong branch, attempting to call
dma_unmap_single() on a DMA address that is not mapped.

This results in a WARN [1], as shown below.

The issue is resolved by properly accounting for the DM type and
ensuring the correct branch is selected in mlx5_free_priv_descs().

[1]
WARNING: CPU: 12 PID: 1346 at drivers/iommu/dma-iommu.c:1230 iommu_dma_unmap_page+0x79/0x90
Modules linked in: ip6table_mangle ip6table_nat ip6table_filter ip6_tables iptable_mangle xt_conntrack xt_MASQUERADE nf_conntrack_netlink nfnetlink xt_addrtype iptable_nat nf_nat br_netfilter rpcsec_gss_krb5 auth_rpcgss oid_registry ovelay rpcrdma rdma_ucm ib_iser libiscsi scsi_transport_iscsi ib_umad rdma_cm ib_ipoib iw_cm ib_cm mlx5_ib ib_uverbs ib_core fuse mlx5_core
CPU: 12 UID: 0 PID: 1346 Comm: ibv_rc_pingpong Not tainted 6.12.0-rc7+ #1631
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
RIP: 0010:iommu_dma_unmap_page+0x79/0x90
Code: 2b 49 3b 29 72 26 49 3b 69 08 73 20 4d 89 f0 44 89 e9 4c 89 e2 48 89 ee 48 89 df 5b 5d 41 5c 41 5d 41 5e 41 5f e9 07 b8 88 ff <0f> 0b 5b 5d 41 5c 41 5d 41 5e 41 5f c3 cc cc cc cc 66 0f 1f 44 00
RSP: 0018:ffffc90001913a10 EFLAGS: 00010246
RAX: 0000000000000000 RBX: ffff88810194b0a8 RCX: 0000000000000000
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000001
RBP: ffff88810194b0a8 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000001 R11: 0000000000000000 R12: 0000000000000000
R13: 0000000000000001 R14: 0000000000000000 R15: 0000000000000000
FS:  00007f537abdd740(0000) GS:ffff88885fb00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f537aeb8000 CR3: 000000010c248001 CR4: 0000000000372eb0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
<TASK>
? __warn+0x84/0x190
? iommu_dma_unmap_page+0x79/0x90
? report_bug+0xf8/0x1c0
? handle_bug+0x55/0x90
? exc_invalid_op+0x13/0x60
? asm_exc_invalid_op+0x16/0x20
? iommu_dma_unmap_page+0x79/0x90
dma_unmap_page_attrs+0xe6/0x290
mlx5_free_priv_descs+0xb0/0xe0 [mlx5_ib]
__mlx5_ib_dereg_mr+0x37e/0x520 [mlx5_ib]
? _raw_spin_unlock_irq+0x24/0x40
? wait_for_completion+0xfe/0x130
? rdma_restrack_put+0x63/0xe0 [ib_core]
ib_dereg_mr_user+0x5f/0x120 [ib_core]
? lock_release+0xc6/0x280
destroy_hw_idr_uobject+0x1d/0x60 [ib_uverbs]
uverbs_destroy_uobject+0x58/0x1d0 [ib_uverbs]
uobj_destroy+0x3f/0x70 [ib_uverbs]
ib_uverbs_cmd_verbs+0x3e4/0xbb0 [ib_uverbs]
? __pfx_uverbs_destroy_def_handler+0x10/0x10 [ib_uverbs]
? lock_acquire+0xc1/0x2f0
? ib_uverbs_ioctl+0xcb/0x170 [ib_uverbs]
? ib_uverbs_ioctl+0x116/0x170 [ib_uverbs]
? lock_release+0xc6/0x280
ib_uverbs_ioctl+0xe7/0x170 [ib_uverbs]
? ib_uverbs_ioctl+0xcb/0x170 [ib_uverbs]
__x64_sys_ioctl+0x1b0/0xa70
do_syscall_64+0x6b/0x140
entry_SYSCALL_64_after_hwframe+0x76/0x7e
RIP: 0033:0x7f537adaf17b
Code: 0f 1e fa 48 8b 05 1d ad 0c 00 64 c7 00 26 00 00 00 48 c7 c0 ff ff ff ff c3 66 0f 1f 44 00 00 f3 0f 1e fa b8 10 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d ed ac 0c 00 f7 d8 64 89 01 48
RSP: 002b:00007ffff218f0b8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 00007ffff218f1d8 RCX: 00007f537adaf17b
RDX: 00007ffff218f1c0 RSI: 00000000c0181b01 RDI: 0000000000000003
RBP: 00007ffff218f1a0 R08: 00007f537aa8d010 R09: 0000561ee2e4f270
R10: 00007f537aace3a8 R11: 0000000000000246 R12: 00007ffff218f190
R13: 000000000000001c R14: 0000561ee2e4d7c0 R15: 00007ffff218f450
</TASK>

Fixes: f18ec4223117 ("RDMA/mlx5: Use a union inside mlx5_ib_mr")
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Link: https://patch.msgid.link/2039c22cfc3df02378747ba4d623a558b53fc263.1738587076.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/mlx5/mr.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 0a3cbb14e1839..753faa9ad06a8 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -1935,7 +1935,8 @@ mlx5_alloc_priv_descs(struct ib_device *device,
 static void
 mlx5_free_priv_descs(struct mlx5_ib_mr *mr)
 {
-	if (!mr->umem && !mr->data_direct && mr->descs) {
+	if (!mr->umem && !mr->data_direct &&
+	    mr->ibmr.type != IB_MR_TYPE_DM && mr->descs) {
 		struct ib_device *device = mr->ibmr.device;
 		int size = mr->max_descs * mr->desc_size;
 		struct mlx5_ib_dev *dev = to_mdev(device);

From 29b7bb98234cc287cebef9bccf638c2e3f39be71 Mon Sep 17 00:00:00 2001
From: Konstantin Taranov <kotaranov@microsoft.com>
Date: Wed, 5 Feb 2025 02:30:05 -0800
Subject: [PATCH 0063/1173] RDMA/mana_ib: Allocate PAGE aligned doorbell index

Allocate a PAGE aligned doorbell index to ensure each process gets a
separate PAGE sized doorbell area space remapped to it in mana_ib_mmap

Fixes: 0266a177631d ("RDMA/mana_ib: Add a driver for Microsoft Azure Network Adapter")
Signed-off-by: Shiraz Saleem <shirazsaleem@microsoft.com>
Signed-off-by: Konstantin Taranov <kotaranov@microsoft.com>
Link: https://patch.msgid.link/1738751405-15041-1-git-send-email-kotaranov@linux.microsoft.com
Reviewed-by: Long Li <longli@microsoft.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/mana/main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/mana/main.c b/drivers/infiniband/hw/mana/main.c
index 67c2d43135a8a..457cea6d99095 100644
--- a/drivers/infiniband/hw/mana/main.c
+++ b/drivers/infiniband/hw/mana/main.c
@@ -174,7 +174,7 @@ static int mana_gd_allocate_doorbell_page(struct gdma_context *gc,
 
 	req.resource_type = GDMA_RESOURCE_DOORBELL_PAGE;
 	req.num_resources = 1;
-	req.alignment = 1;
+	req.alignment = PAGE_SIZE / MANA_PAGE_SIZE;
 
 	/* Have GDMA start searching from 0 */
 	req.allocated_resources = 0;

From cc2c3540d9477a9931fb0fd851fcaeba524a5b35 Mon Sep 17 00:00:00 2001
From: Sam Winchenbach <swinchenbach@arka.org>
Date: Mon, 3 Feb 2025 13:34:34 +0000
Subject: [PATCH 0064/1173] iio: filter: admv8818: Force initialization of SDO

When a weak pull-up is present on the SDO line, regmap_update_bits fails
to write both the SOFTRESET and SDOACTIVE bits because it incorrectly
reads them as already set.

Since the soft reset disables the SDO line, performing a
read-modify-write operation on ADI_SPI_CONFIG_A to enable the SDO line
doesn't make sense. This change directly writes to the register instead
of using regmap_update_bits.

Fixes: f34fe888ad05 ("iio:filter:admv8818: add support for ADMV8818")
Signed-off-by: Sam Winchenbach <swinchenbach@arka.org>
Link: https://patch.msgid.link/SA1P110MB106904C961B0F3FAFFED74C0BCF5A@SA1P110MB1069.NAMP110.PROD.OUTLOOK.COM
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/filter/admv8818.c | 14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

diff --git a/drivers/iio/filter/admv8818.c b/drivers/iio/filter/admv8818.c
index 848baa6e3bbf5..d85b7d3de8660 100644
--- a/drivers/iio/filter/admv8818.c
+++ b/drivers/iio/filter/admv8818.c
@@ -574,21 +574,15 @@ static int admv8818_init(struct admv8818_state *st)
 	struct spi_device *spi = st->spi;
 	unsigned int chip_id;
 
-	ret = regmap_update_bits(st->regmap, ADMV8818_REG_SPI_CONFIG_A,
-				 ADMV8818_SOFTRESET_N_MSK |
-				 ADMV8818_SOFTRESET_MSK,
-				 FIELD_PREP(ADMV8818_SOFTRESET_N_MSK, 1) |
-				 FIELD_PREP(ADMV8818_SOFTRESET_MSK, 1));
+	ret = regmap_write(st->regmap, ADMV8818_REG_SPI_CONFIG_A,
+			   ADMV8818_SOFTRESET_N_MSK | ADMV8818_SOFTRESET_MSK);
 	if (ret) {
 		dev_err(&spi->dev, "ADMV8818 Soft Reset failed.\n");
 		return ret;
 	}
 
-	ret = regmap_update_bits(st->regmap, ADMV8818_REG_SPI_CONFIG_A,
-				 ADMV8818_SDOACTIVE_N_MSK |
-				 ADMV8818_SDOACTIVE_MSK,
-				 FIELD_PREP(ADMV8818_SDOACTIVE_N_MSK, 1) |
-				 FIELD_PREP(ADMV8818_SDOACTIVE_MSK, 1));
+	ret = regmap_write(st->regmap, ADMV8818_REG_SPI_CONFIG_A,
+			   ADMV8818_SDOACTIVE_N_MSK | ADMV8818_SDOACTIVE_MSK);
 	if (ret) {
 		dev_err(&spi->dev, "ADMV8818 SDO Enable failed.\n");
 		return ret;

From ee9d1619ef6e4a3412a13788256cb8c3e5efbe3d Mon Sep 17 00:00:00 2001
From: Long Li <longli@microsoft.com>
Date: Fri, 7 Feb 2025 13:46:28 -0800
Subject: [PATCH 0065/1173] MAINTAINERS: update maintainer for Microsoft MANA
 RDMA driver

Ajay is no longer working on the MANA RDMA driver.

Konstantin Taranov has made significant contributions to implementing RC
QP in both kernel and user-mode.

He will take the responsibility of fixing bugs, reviewing patches and
developing new features for MANA RDMA driver.

Signed-off-by: Long Li <longli@microsoft.com>
Link: https://patch.msgid.link/1738964792-21140-1-git-send-email-longli@linuxonhyperv.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 896a307fa0654..c51503268a026 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15689,7 +15689,7 @@ F:	include/uapi/linux/cciss*.h
 
 MICROSOFT MANA RDMA DRIVER
 M:	Long Li <longli@microsoft.com>
-M:	Ajay Sharma <sharmaajay@microsoft.com>
+M:	Konstantin Taranov <kotaranov@microsoft.com>
 L:	linux-rdma@vger.kernel.org
 S:	Supported
 F:	drivers/infiniband/hw/mana/

From 9747c0c7791d4a5a62018a0c9c563dd2e6f6c1c0 Mon Sep 17 00:00:00 2001
From: Junxian Huang <huangjunxian6@hisilicon.com>
Date: Sat, 8 Feb 2025 18:59:30 +0800
Subject: [PATCH 0066/1173] RDMA/hns: Fix mbox timing out by adding retry
 mechanism

If a QP is modified to error state and a flush CQE process is triggered,
the subsequent QP destruction mbox can still be successfully posted but
will be blocked in HW until the flush CQE process finishes. This causes
further mbox posting timeouts in driver. The blocking time is related
to QP depth. Considering an extreme case where SQ depth and RQ depth
are both 32K, the blocking time can reach about 135ms.

This patch adds a retry mechanism for mbox posting. For each try, FW
waits 15ms for HW to complete the previous mbox, otherwise return a
timeout error code to driver. Counting other time consumption in FW,
set 8 tries for mbox posting and a 5ms time gap before each retry to
increase to a sufficient timeout limit.

Fixes: 0425e3e6e0c7 ("RDMA/hns: Support flush cqe for hip08 in kernel space")
Signed-off-by: Junxian Huang <huangjunxian6@hisilicon.com>
Link: https://patch.msgid.link/20250208105930.522796-1-huangjunxian6@hisilicon.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 64 ++++++++++++++++------
 drivers/infiniband/hw/hns/hns_roce_hw_v2.h |  2 +
 2 files changed, 50 insertions(+), 16 deletions(-)

diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
index dded339802b33..160e8927d364e 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
@@ -1286,10 +1286,8 @@ static u32 hns_roce_cmdq_tx_timeout(u16 opcode, u32 tx_timeout)
 	return tx_timeout;
 }
 
-static void hns_roce_wait_csq_done(struct hns_roce_dev *hr_dev, u16 opcode)
+static void hns_roce_wait_csq_done(struct hns_roce_dev *hr_dev, u32 tx_timeout)
 {
-	struct hns_roce_v2_priv *priv = hr_dev->priv;
-	u32 tx_timeout = hns_roce_cmdq_tx_timeout(opcode, priv->cmq.tx_timeout);
 	u32 timeout = 0;
 
 	do {
@@ -1299,8 +1297,9 @@ static void hns_roce_wait_csq_done(struct hns_roce_dev *hr_dev, u16 opcode)
 	} while (++timeout < tx_timeout);
 }
 
-static int __hns_roce_cmq_send(struct hns_roce_dev *hr_dev,
-			       struct hns_roce_cmq_desc *desc, int num)
+static int __hns_roce_cmq_send_one(struct hns_roce_dev *hr_dev,
+				   struct hns_roce_cmq_desc *desc,
+				   int num, u32 tx_timeout)
 {
 	struct hns_roce_v2_priv *priv = hr_dev->priv;
 	struct hns_roce_v2_cmq_ring *csq = &priv->cmq.csq;
@@ -1309,8 +1308,6 @@ static int __hns_roce_cmq_send(struct hns_roce_dev *hr_dev,
 	int ret;
 	int i;
 
-	spin_lock_bh(&csq->lock);
-
 	tail = csq->head;
 
 	for (i = 0; i < num; i++) {
@@ -1324,22 +1321,17 @@ static int __hns_roce_cmq_send(struct hns_roce_dev *hr_dev,
 
 	atomic64_inc(&hr_dev->dfx_cnt[HNS_ROCE_DFX_CMDS_CNT]);
 
-	hns_roce_wait_csq_done(hr_dev, le16_to_cpu(desc->opcode));
+	hns_roce_wait_csq_done(hr_dev, tx_timeout);
 	if (hns_roce_cmq_csq_done(hr_dev)) {
 		ret = 0;
 		for (i = 0; i < num; i++) {
 			/* check the result of hardware write back */
-			desc[i] = csq->desc[tail++];
+			desc_ret = le16_to_cpu(csq->desc[tail++].retval);
 			if (tail == csq->desc_num)
 				tail = 0;
-
-			desc_ret = le16_to_cpu(desc[i].retval);
 			if (likely(desc_ret == CMD_EXEC_SUCCESS))
 				continue;
 
-			dev_err_ratelimited(hr_dev->dev,
-					    "Cmdq IO error, opcode = 0x%x, return = 0x%x.\n",
-					    desc->opcode, desc_ret);
 			ret = hns_roce_cmd_err_convert_errno(desc_ret);
 		}
 	} else {
@@ -1354,14 +1346,54 @@ static int __hns_roce_cmq_send(struct hns_roce_dev *hr_dev,
 		ret = -EAGAIN;
 	}
 
-	spin_unlock_bh(&csq->lock);
-
 	if (ret)
 		atomic64_inc(&hr_dev->dfx_cnt[HNS_ROCE_DFX_CMDS_ERR_CNT]);
 
 	return ret;
 }
 
+static int __hns_roce_cmq_send(struct hns_roce_dev *hr_dev,
+			       struct hns_roce_cmq_desc *desc, int num)
+{
+	struct hns_roce_v2_priv *priv = hr_dev->priv;
+	struct hns_roce_v2_cmq_ring *csq = &priv->cmq.csq;
+	u16 opcode = le16_to_cpu(desc->opcode);
+	u32 tx_timeout = hns_roce_cmdq_tx_timeout(opcode, priv->cmq.tx_timeout);
+	u8 try_cnt = HNS_ROCE_OPC_POST_MB_TRY_CNT;
+	u32 rsv_tail;
+	int ret;
+	int i;
+
+	while (try_cnt) {
+		try_cnt--;
+
+		spin_lock_bh(&csq->lock);
+		rsv_tail = csq->head;
+		ret = __hns_roce_cmq_send_one(hr_dev, desc, num, tx_timeout);
+		if (opcode == HNS_ROCE_OPC_POST_MB && ret == -ETIME &&
+		    try_cnt) {
+			spin_unlock_bh(&csq->lock);
+			mdelay(HNS_ROCE_OPC_POST_MB_RETRY_GAP_MSEC);
+			continue;
+		}
+
+		for (i = 0; i < num; i++) {
+			desc[i] = csq->desc[rsv_tail++];
+			if (rsv_tail == csq->desc_num)
+				rsv_tail = 0;
+		}
+		spin_unlock_bh(&csq->lock);
+		break;
+	}
+
+	if (ret)
+		dev_err_ratelimited(hr_dev->dev,
+				    "Cmdq IO error, opcode = 0x%x, return = %d.\n",
+				    opcode, ret);
+
+	return ret;
+}
+
 static int hns_roce_cmq_send(struct hns_roce_dev *hr_dev,
 			     struct hns_roce_cmq_desc *desc, int num)
 {
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
index cbdbc9edbce6e..91a5665465ffb 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
@@ -230,6 +230,8 @@ enum hns_roce_opcode_type {
 };
 
 #define HNS_ROCE_OPC_POST_MB_TIMEOUT 35000
+#define HNS_ROCE_OPC_POST_MB_TRY_CNT 8
+#define HNS_ROCE_OPC_POST_MB_RETRY_GAP_MSEC 5
 struct hns_roce_cmdq_tx_timeout_map {
 	u16 opcode;
 	u32 tx_timeout;

From a27c6f46dcec8f697cbf15c8a10f8534c7b8a2c3 Mon Sep 17 00:00:00 2001
From: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Date: Tue, 4 Feb 2025 00:21:22 -0800
Subject: [PATCH 0067/1173] RDMA/bnxt_re: Fix an issue in
 bnxt_re_async_notifier

In the bnxt_re_async_notifier() callback, the way driver retrieves
rdev pointer is wrong. The rdev pointer should be parsed from
adev pointer as while registering with the L2 for ULP, driver uses
the aux device pointer for the handle.

Fixes: 7fea32784068 ("RDMA/bnxt_re: Add Async event handling support")
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://patch.msgid.link/1738657285-23968-2-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/bnxt_re/main.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index e9e4da4dd576b..c4c3d67c42cc6 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -396,11 +396,16 @@ static void bnxt_re_dcb_wq_task(struct work_struct *work)
 
 static void bnxt_re_async_notifier(void *handle, struct hwrm_async_event_cmpl *cmpl)
 {
-	struct bnxt_re_dev *rdev = (struct bnxt_re_dev *)handle;
+	struct bnxt_re_en_dev_info *en_info = auxiliary_get_drvdata(handle);
 	struct bnxt_re_dcb_work *dcb_work;
+	struct bnxt_re_dev *rdev;
 	u32 data1, data2;
 	u16 event_id;
 
+	rdev = en_info->rdev;
+	if (!rdev)
+		return;
+
 	event_id = le16_to_cpu(cmpl->event_id);
 	data1 = le32_to_cpu(cmpl->event_data1);
 	data2 = le32_to_cpu(cmpl->event_data2);

From f0df225d12fcb049429fb5bf5122afe143c2dd15 Mon Sep 17 00:00:00 2001
From: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Date: Tue, 4 Feb 2025 00:21:23 -0800
Subject: [PATCH 0068/1173] RDMA/bnxt_re: Add sanity checks on rdev validity

There is a possibility that ulp_irq_stop and ulp_irq_start
callbacks will be called when the device is in detached state.
This can cause a crash due to NULL pointer dereference as
the rdev is already freed.

Fixes: cc5b9b48d447 ("RDMA/bnxt_re: Recover the device when FW error is detected")
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://patch.msgid.link/1738657285-23968-3-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/bnxt_re/main.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index c4c3d67c42cc6..89ac5c21ca7ad 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -438,6 +438,8 @@ static void bnxt_re_stop_irq(void *handle, bool reset)
 	int indx;
 
 	rdev = en_info->rdev;
+	if (!rdev)
+		return;
 	rcfw = &rdev->rcfw;
 
 	if (reset) {
@@ -466,6 +468,8 @@ static void bnxt_re_start_irq(void *handle, struct bnxt_msix_entry *ent)
 	int indx, rc;
 
 	rdev = en_info->rdev;
+	if (!rdev)
+		return;
 	msix_ent = rdev->nqr->msix_entries;
 	rcfw = &rdev->rcfw;
 	if (!ent) {
@@ -2438,6 +2442,7 @@ static int bnxt_re_suspend(struct auxiliary_device *adev, pm_message_t state)
 	ibdev_info(&rdev->ibdev, "%s: L2 driver notified to stop en_state 0x%lx",
 		   __func__, en_dev->en_state);
 	bnxt_re_remove_device(rdev, BNXT_RE_PRE_RECOVERY_REMOVE, adev);
+	bnxt_re_update_en_info_rdev(NULL, en_info, adev);
 	mutex_unlock(&bnxt_re_mutex);
 
 	return 0;

From e2f105277411c4ebacd00d4ae1a57f693ba7d22d Mon Sep 17 00:00:00 2001
From: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Date: Tue, 4 Feb 2025 00:21:24 -0800
Subject: [PATCH 0069/1173] RDMA/bnxt_re: Fix issue in the unload path

The cited comment removed the netdev notifier register call
from the driver. But, it did not remove the cleanup code from
the unload path. As a result, driver unload is not clean and
resulted in undesired behaviour.

Fixes: d3b15fcc4201 ("RDMA/bnxt_re: Remove deliver net device event")
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://patch.msgid.link/1738657285-23968-4-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/bnxt_re/bnxt_re.h |  1 -
 drivers/infiniband/hw/bnxt_re/main.c    | 10 ----------
 2 files changed, 11 deletions(-)

diff --git a/drivers/infiniband/hw/bnxt_re/bnxt_re.h b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
index b91a85a491d05..3721446c6ba4b 100644
--- a/drivers/infiniband/hw/bnxt_re/bnxt_re.h
+++ b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
@@ -187,7 +187,6 @@ struct bnxt_re_dev {
 #define BNXT_RE_FLAG_ISSUE_ROCE_STATS          29
 	struct net_device		*netdev;
 	struct auxiliary_device         *adev;
-	struct notifier_block		nb;
 	unsigned int			version, major, minor;
 	struct bnxt_qplib_chip_ctx	*chip_ctx;
 	struct bnxt_en_dev		*en_dev;
diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index 89ac5c21ca7ad..a94c8c5387d9e 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -1359,7 +1359,6 @@ static struct bnxt_re_dev *bnxt_re_dev_add(struct auxiliary_device *adev,
 		return NULL;
 	}
 	/* Default values */
-	rdev->nb.notifier_call = NULL;
 	rdev->netdev = en_dev->net;
 	rdev->en_dev = en_dev;
 	rdev->adev = adev;
@@ -2354,15 +2353,6 @@ static int bnxt_re_add_device(struct auxiliary_device *adev, u8 op_type)
 static void bnxt_re_remove_device(struct bnxt_re_dev *rdev, u8 op_type,
 				  struct auxiliary_device *aux_dev)
 {
-	if (rdev->nb.notifier_call) {
-		unregister_netdevice_notifier(&rdev->nb);
-		rdev->nb.notifier_call = NULL;
-	} else {
-		/* If notifier is null, we should have already done a
-		 * clean up before coming here.
-		 */
-		return;
-	}
 	bnxt_re_setup_cc(rdev, false);
 	ib_unregister_device(&rdev->ibdev);
 	bnxt_re_dev_uninit(rdev, op_type);

From 8238c7bd84209c8216b1381ab0dbe6db9e203769 Mon Sep 17 00:00:00 2001
From: Selvin Xavier <selvin.xavier@broadcom.com>
Date: Tue, 4 Feb 2025 00:21:25 -0800
Subject: [PATCH 0070/1173] RDMA/bnxt_re: Fix the statistics for Gen P7 VF

Gen P7 VF support the extended stats and is prevented
by a VF check. Fix the check to issue the FW command
for GenP7 VFs also.

Fixes: 1801d87b3598 ("RDMA/bnxt_re: Support new 5760X P7 devices")
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://patch.msgid.link/1738657285-23968-5-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/bnxt_re/hw_counters.c | 4 ++--
 drivers/infiniband/hw/bnxt_re/qplib_res.h   | 8 ++++++++
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/hw/bnxt_re/hw_counters.c b/drivers/infiniband/hw/bnxt_re/hw_counters.c
index 3ac47f4e61229..f039aefcaf675 100644
--- a/drivers/infiniband/hw/bnxt_re/hw_counters.c
+++ b/drivers/infiniband/hw/bnxt_re/hw_counters.c
@@ -348,8 +348,8 @@ int bnxt_re_ib_get_hw_stats(struct ib_device *ibdev,
 			goto done;
 		}
 		bnxt_re_copy_err_stats(rdev, stats, err_s);
-		if (_is_ext_stats_supported(rdev->dev_attr->dev_cap_flags) &&
-		    !rdev->is_virtfn) {
+		if (bnxt_ext_stats_supported(rdev->chip_ctx, rdev->dev_attr->dev_cap_flags,
+					     rdev->is_virtfn)) {
 			rc = bnxt_re_get_ext_stat(rdev, stats);
 			if (rc) {
 				clear_bit(BNXT_RE_FLAG_ISSUE_ROCE_STATS,
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.h b/drivers/infiniband/hw/bnxt_re/qplib_res.h
index be5d907a036b6..711990232de1c 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_res.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.h
@@ -547,6 +547,14 @@ static inline bool _is_ext_stats_supported(u16 dev_cap_flags)
 		CREQ_QUERY_FUNC_RESP_SB_EXT_STATS;
 }
 
+static inline int bnxt_ext_stats_supported(struct bnxt_qplib_chip_ctx *ctx,
+					   u16 flags, bool virtfn)
+{
+	/* ext stats supported if cap flag is set AND is a PF OR a Thor2 VF */
+	return (_is_ext_stats_supported(flags) &&
+		((virtfn && bnxt_qplib_is_chip_gen_p7(ctx)) || (!virtfn)));
+}
+
 static inline bool _is_hw_retx_supported(u16 dev_cap_flags)
 {
 	return dev_cap_flags &

From b921f66ccf5e8cf1b8a5052b35ceda454f19f5dd Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Mon, 3 Feb 2025 15:30:56 -0600
Subject: [PATCH 0071/1173] dt-bindings: rockchip: pmu: Ensure all properties
 are defined

Device specific schemas should not allow undefined properties which is
what 'additionalProperties: true' allows. Add the missing child nodes
and fix this constraint.

Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://lore.kernel.org/r/20250203213056.13827-1-robh@kernel.org
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 Documentation/devicetree/bindings/arm/rockchip/pmu.yaml | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/arm/rockchip/pmu.yaml b/Documentation/devicetree/bindings/arm/rockchip/pmu.yaml
index 932f981265ccb..52016a141227b 100644
--- a/Documentation/devicetree/bindings/arm/rockchip/pmu.yaml
+++ b/Documentation/devicetree/bindings/arm/rockchip/pmu.yaml
@@ -53,11 +53,17 @@ properties:
   reg:
     maxItems: 1
 
+  power-controller:
+    type: object
+
+  reboot-mode:
+    type: object
+
 required:
   - compatible
   - reg
 
-additionalProperties: true
+additionalProperties: false
 
 examples:
   - |

From 2c202e6c4f4dd19d2e8c1dfac9df05170aa3934f Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Sat, 8 Feb 2025 08:29:15 +0900
Subject: [PATCH 0072/1173] ata: libahci_platform: Do not set mask_port_map
 when not needed

Commit 8c87215dd3a2 ("ata: libahci_platform: support non-consecutive
port numbers") modified ahci_platform_get_resources() to allow
identifying the ports of a controller that are defined as child nodes of
the controller node in order to support non-consecutive port numbers (as
defined by the platform device tree).

However, this commit also erroneously sets bit 0 of
hpriv->mask_port_map when the platform devices tree does not define port
child nodes, to match the fact that the temporary default number of
ports used in that case is 1 (which is also consistent with the fact
that only index 0 of hpriv->phys[] is initialized with the call to
ahci_platform_get_phy(). But doing so causes ahci_platform_init_host()
to initialize and probe only the first port, even if this function
determines that the controller has in fact multiple ports using the
capability register of the controller (through a call to
ahci_nr_ports()). This can be seen with the ahci_mvebu driver (Armada
385 SoC) with the second port declared as "dummy":

ahci-mvebu f10a8000.sata: masking port_map 0x3 -> 0x1
ahci-mvebu f10a8000.sata: AHCI vers 0001.0000, 32 command slots, 6 Gbps, platform mode
ahci-mvebu f10a8000.sata: 1/2 ports implemented (port mask 0x1)
ahci-mvebu f10a8000.sata: flags: 64bit ncq sntf led only pmp fbs pio slum part sxs
scsi host0: ahci-mvebu
scsi host1: ahci-mvebu
ata1: SATA max UDMA/133 mmio [mem 0xf10a8000-0xf10a9fff] port 0x100 irq 40 lpm-pol 0
ata2: DUMMY

Fix this issue by removing setting bit 0 of hpriv->mask_port_map when
the platform device tree does not define port child nodes.

Reported-by: Klaus Kudielka <klaus.kudielka@gmail.com>
Fixes: 8c87215dd3a2 ("ata: libahci_platform: support non-consecutive port numbers")
Tested-by: Klaus Kudielka <klaus.kudielka@gmail.com>
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Acked-by: Josua Mayer <josua@solid-run.com>
Link: https://lore.kernel.org/r/20250207232915.1439174-1-dlemoal@kernel.org
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/libahci_platform.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c
index 53b2c7719dc51..91d44302eac92 100644
--- a/drivers/ata/libahci_platform.c
+++ b/drivers/ata/libahci_platform.c
@@ -651,8 +651,6 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev,
 		 * If no sub-node was found, keep this for device tree
 		 * compatibility
 		 */
-		hpriv->mask_port_map |= BIT(0);
-
 		rc = ahci_platform_get_phy(hpriv, 0, dev, dev->of_node);
 		if (rc)
 			goto err_out;

From 17987453a9d997c4d0749abc52f047bfa275427a Mon Sep 17 00:00:00 2001
From: Mohan Kumar D <mkumard@nvidia.com>
Date: Mon, 10 Feb 2025 19:24:12 +0530
Subject: [PATCH 0073/1173] dmaengine: tegra210-adma: Use div_u64 for 64 bit
 division

The ADMA base and page address are represented using a 64-bit variable.
To accurately derive the exact ADMA page number provided from the DT
properties, use the div_u64() to divide the address difference between
adma page and base address by the page offset.

This change fixes the below error
   "ERROR: modpost: "__udivdi3" [drivers/dma/tegra210-adma.ko] undefined!
    ld: drivers/dma/tegra210-adma.o: in function `tegra_adma_probe':
    tegra210-adma.c:(.text+0x12cf): undefined reference to `__udivdi3'"

Fixes: 68811c928f88 ("dmaengine: tegra210-adma: Support channel page")
Cc: stable@vger.kernel.org
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202412250204.GCQhdKe3-lkp@intel.com/
Signed-off-by: Mohan Kumar D <mkumard@nvidia.com>
Reviewed-by: Jon Hunter <jonathanh@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
Link: https://lore.kernel.org/r/20250210135413.2504272-2-mkumard@nvidia.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/tegra210-adma.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c
index 6896da8ac7ef6..a0bd4822ed808 100644
--- a/drivers/dma/tegra210-adma.c
+++ b/drivers/dma/tegra210-adma.c
@@ -887,7 +887,8 @@ static int tegra_adma_probe(struct platform_device *pdev)
 	const struct tegra_adma_chip_data *cdata;
 	struct tegra_adma *tdma;
 	struct resource *res_page, *res_base;
-	int ret, i, page_no;
+	u64 page_no, page_offset;
+	int ret, i;
 
 	cdata = of_device_get_match_data(&pdev->dev);
 	if (!cdata) {
@@ -914,10 +915,16 @@ static int tegra_adma_probe(struct platform_device *pdev)
 
 		res_base = platform_get_resource_byname(pdev, IORESOURCE_MEM, "global");
 		if (res_base) {
-			page_no = (res_page->start - res_base->start) / cdata->ch_base_offset;
-			if (page_no <= 0)
+			if (WARN_ON(res_page->start <= res_base->start))
 				return -EINVAL;
-			tdma->ch_page_no = page_no - 1;
+
+			page_offset = res_page->start - res_base->start;
+			page_no = div_u64(page_offset, cdata->ch_base_offset);
+
+			if (WARN_ON(page_no == 0))
+				return -EINVAL;
+
+			tdma->ch_page_no = lower_32_bits(page_no) - 1;
 			tdma->base_addr = devm_ioremap_resource(&pdev->dev, res_base);
 			if (IS_ERR(tdma->base_addr))
 				return PTR_ERR(tdma->base_addr);

From 76ed9b7d177ed5aa161a824ea857619b88542de1 Mon Sep 17 00:00:00 2001
From: Mohan Kumar D <mkumard@nvidia.com>
Date: Mon, 10 Feb 2025 19:24:13 +0530
Subject: [PATCH 0074/1173] dmaengine: tegra210-adma: check for adma max page

Have additional check for max channel page during the probe
to cover if any offset overshoot happens due to wrong DT
configuration.

Fixes: 68811c928f88 ("dmaengine: tegra210-adma: Support channel page")
Cc: stable@vger.kernel.org
Signed-off-by: Mohan Kumar D <mkumard@nvidia.com>
Reviewed-by: Jon Hunter <jonathanh@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
Link: https://lore.kernel.org/r/20250210135413.2504272-3-mkumard@nvidia.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/tegra210-adma.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c
index a0bd4822ed808..801740ad8e0d9 100644
--- a/drivers/dma/tegra210-adma.c
+++ b/drivers/dma/tegra210-adma.c
@@ -83,7 +83,9 @@ struct tegra_adma;
  * @nr_channels: Number of DMA channels available.
  * @ch_fifo_size_mask: Mask for FIFO size field.
  * @sreq_index_offset: Slave channel index offset.
+ * @max_page: Maximum ADMA Channel Page.
  * @has_outstanding_reqs: If DMA channel can have outstanding requests.
+ * @set_global_pg_config: Global page programming.
  */
 struct tegra_adma_chip_data {
 	unsigned int (*adma_get_burst_config)(unsigned int burst_size);
@@ -99,6 +101,7 @@ struct tegra_adma_chip_data {
 	unsigned int nr_channels;
 	unsigned int ch_fifo_size_mask;
 	unsigned int sreq_index_offset;
+	unsigned int max_page;
 	bool has_outstanding_reqs;
 	void (*set_global_pg_config)(struct tegra_adma *tdma);
 };
@@ -854,6 +857,7 @@ static const struct tegra_adma_chip_data tegra210_chip_data = {
 	.nr_channels		= 22,
 	.ch_fifo_size_mask	= 0xf,
 	.sreq_index_offset	= 2,
+	.max_page		= 0,
 	.has_outstanding_reqs	= false,
 	.set_global_pg_config	= NULL,
 };
@@ -871,6 +875,7 @@ static const struct tegra_adma_chip_data tegra186_chip_data = {
 	.nr_channels		= 32,
 	.ch_fifo_size_mask	= 0x1f,
 	.sreq_index_offset	= 4,
+	.max_page		= 4,
 	.has_outstanding_reqs	= true,
 	.set_global_pg_config	= tegra186_adma_global_page_config,
 };
@@ -921,7 +926,7 @@ static int tegra_adma_probe(struct platform_device *pdev)
 			page_offset = res_page->start - res_base->start;
 			page_no = div_u64(page_offset, cdata->ch_base_offset);
 
-			if (WARN_ON(page_no == 0))
+			if (WARN_ON(page_no == 0 || page_no > cdata->max_page))
 				return -EINVAL;
 
 			tdma->ch_page_no = lower_32_bits(page_no) - 1;

From 2b9df00cded911e2ca2cfae5c45082166b24f8aa Mon Sep 17 00:00:00 2001
From: Niravkumar L Rabara <niravkumar.l.rabara@intel.com>
Date: Mon, 10 Feb 2025 13:35:49 +0800
Subject: [PATCH 0075/1173] mtd: rawnand: cadence: fix error code in
 cadence_nand_init()

Replace dma_request_channel() with dma_request_chan_by_mask() and use
helper functions to return proper error code instead of fixed -EBUSY.

Fixes: ec4ba01e894d ("mtd: rawnand: Add new Cadence NAND driver to MTD subsystem")
Cc: stable@vger.kernel.org
Signed-off-by: Niravkumar L Rabara <niravkumar.l.rabara@intel.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/cadence-nand-controller.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/mtd/nand/raw/cadence-nand-controller.c b/drivers/mtd/nand/raw/cadence-nand-controller.c
index 8d1d710e439dd..fb5f671bdb7bb 100644
--- a/drivers/mtd/nand/raw/cadence-nand-controller.c
+++ b/drivers/mtd/nand/raw/cadence-nand-controller.c
@@ -2904,11 +2904,10 @@ static int cadence_nand_init(struct cdns_nand_ctrl *cdns_ctrl)
 	dma_cap_set(DMA_MEMCPY, mask);
 
 	if (cdns_ctrl->caps1->has_dma) {
-		cdns_ctrl->dmac = dma_request_channel(mask, NULL, NULL);
-		if (!cdns_ctrl->dmac) {
-			dev_err(cdns_ctrl->dev,
-				"Unable to get a DMA channel\n");
-			ret = -EBUSY;
+		cdns_ctrl->dmac = dma_request_chan_by_mask(&mask);
+		if (IS_ERR(cdns_ctrl->dmac)) {
+			ret = dev_err_probe(cdns_ctrl->dev, PTR_ERR(cdns_ctrl->dmac),
+					    "%d: Failed to get a DMA channel\n", ret);
 			goto disable_irq;
 		}
 	}

From d76d22b5096c5b05208fd982b153b3f182350b19 Mon Sep 17 00:00:00 2001
From: Niravkumar L Rabara <niravkumar.l.rabara@intel.com>
Date: Mon, 10 Feb 2025 13:35:50 +0800
Subject: [PATCH 0076/1173] mtd: rawnand: cadence: use dma_map_resource for
 sdma address

Remap the slave DMA I/O resources to enhance driver portability.
Using a physical address causes DMA translation failure when the
ARM SMMU is enabled.

Fixes: ec4ba01e894d ("mtd: rawnand: Add new Cadence NAND driver to MTD subsystem")
Cc: stable@vger.kernel.org
Signed-off-by: Niravkumar L Rabara <niravkumar.l.rabara@intel.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 .../mtd/nand/raw/cadence-nand-controller.c    | 29 ++++++++++++++++---
 1 file changed, 25 insertions(+), 4 deletions(-)

diff --git a/drivers/mtd/nand/raw/cadence-nand-controller.c b/drivers/mtd/nand/raw/cadence-nand-controller.c
index fb5f671bdb7bb..47950a0ac6d28 100644
--- a/drivers/mtd/nand/raw/cadence-nand-controller.c
+++ b/drivers/mtd/nand/raw/cadence-nand-controller.c
@@ -471,6 +471,8 @@ struct cdns_nand_ctrl {
 	struct {
 		void __iomem *virt;
 		dma_addr_t dma;
+		dma_addr_t iova_dma;
+		u32 size;
 	} io;
 
 	int irq;
@@ -1835,11 +1837,11 @@ static int cadence_nand_slave_dma_transfer(struct cdns_nand_ctrl *cdns_ctrl,
 	}
 
 	if (dir == DMA_FROM_DEVICE) {
-		src_dma = cdns_ctrl->io.dma;
+		src_dma = cdns_ctrl->io.iova_dma;
 		dst_dma = buf_dma;
 	} else {
 		src_dma = buf_dma;
-		dst_dma = cdns_ctrl->io.dma;
+		dst_dma = cdns_ctrl->io.iova_dma;
 	}
 
 	tx = dmaengine_prep_dma_memcpy(cdns_ctrl->dmac, dst_dma, src_dma, len,
@@ -2869,6 +2871,7 @@ cadence_nand_irq_cleanup(int irqnum, struct cdns_nand_ctrl *cdns_ctrl)
 static int cadence_nand_init(struct cdns_nand_ctrl *cdns_ctrl)
 {
 	dma_cap_mask_t mask;
+	struct dma_device *dma_dev = cdns_ctrl->dmac->device;
 	int ret;
 
 	cdns_ctrl->cdma_desc = dma_alloc_coherent(cdns_ctrl->dev,
@@ -2912,6 +2915,16 @@ static int cadence_nand_init(struct cdns_nand_ctrl *cdns_ctrl)
 		}
 	}
 
+	cdns_ctrl->io.iova_dma = dma_map_resource(dma_dev->dev, cdns_ctrl->io.dma,
+						  cdns_ctrl->io.size,
+						  DMA_BIDIRECTIONAL, 0);
+
+	ret = dma_mapping_error(dma_dev->dev, cdns_ctrl->io.iova_dma);
+	if (ret) {
+		dev_err(cdns_ctrl->dev, "Failed to map I/O resource to DMA\n");
+		goto dma_release_chnl;
+	}
+
 	nand_controller_init(&cdns_ctrl->controller);
 	INIT_LIST_HEAD(&cdns_ctrl->chips);
 
@@ -2922,18 +2935,22 @@ static int cadence_nand_init(struct cdns_nand_ctrl *cdns_ctrl)
 	if (ret) {
 		dev_err(cdns_ctrl->dev, "Failed to register MTD: %d\n",
 			ret);
-		goto dma_release_chnl;
+		goto unmap_dma_resource;
 	}
 
 	kfree(cdns_ctrl->buf);
 	cdns_ctrl->buf = kzalloc(cdns_ctrl->buf_size, GFP_KERNEL);
 	if (!cdns_ctrl->buf) {
 		ret = -ENOMEM;
-		goto dma_release_chnl;
+		goto unmap_dma_resource;
 	}
 
 	return 0;
 
+unmap_dma_resource:
+	dma_unmap_resource(dma_dev->dev, cdns_ctrl->io.iova_dma,
+			   cdns_ctrl->io.size, DMA_BIDIRECTIONAL, 0);
+
 dma_release_chnl:
 	if (cdns_ctrl->dmac)
 		dma_release_channel(cdns_ctrl->dmac);
@@ -2955,6 +2972,8 @@ static int cadence_nand_init(struct cdns_nand_ctrl *cdns_ctrl)
 static void cadence_nand_remove(struct cdns_nand_ctrl *cdns_ctrl)
 {
 	cadence_nand_chips_cleanup(cdns_ctrl);
+	dma_unmap_resource(cdns_ctrl->dmac->device->dev, cdns_ctrl->io.iova_dma,
+			   cdns_ctrl->io.size, DMA_BIDIRECTIONAL, 0);
 	cadence_nand_irq_cleanup(cdns_ctrl->irq, cdns_ctrl);
 	kfree(cdns_ctrl->buf);
 	dma_free_coherent(cdns_ctrl->dev, sizeof(struct cadence_nand_cdma_desc),
@@ -3019,7 +3038,9 @@ static int cadence_nand_dt_probe(struct platform_device *ofdev)
 	cdns_ctrl->io.virt = devm_platform_get_and_ioremap_resource(ofdev, 1, &res);
 	if (IS_ERR(cdns_ctrl->io.virt))
 		return PTR_ERR(cdns_ctrl->io.virt);
+
 	cdns_ctrl->io.dma = res->start;
+	cdns_ctrl->io.size = resource_size(res);
 
 	dt->clk = devm_clk_get(cdns_ctrl->dev, "nf_clk");
 	if (IS_ERR(dt->clk))

From f37d135b42cb484bdecee93f56b9f483214ede78 Mon Sep 17 00:00:00 2001
From: Niravkumar L Rabara <niravkumar.l.rabara@intel.com>
Date: Mon, 10 Feb 2025 13:35:51 +0800
Subject: [PATCH 0077/1173] mtd: rawnand: cadence: fix incorrect device in
 dma_unmap_single

dma_map_single is using physical/bus device (DMA) but dma_unmap_single
is using framework device(NAND controller), which is incorrect.
Fixed dma_unmap_single to use correct physical/bus device.

Fixes: ec4ba01e894d ("mtd: rawnand: Add new Cadence NAND driver to MTD subsystem")
Cc: stable@vger.kernel.org
Signed-off-by: Niravkumar L Rabara <niravkumar.l.rabara@intel.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/cadence-nand-controller.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/mtd/nand/raw/cadence-nand-controller.c b/drivers/mtd/nand/raw/cadence-nand-controller.c
index 47950a0ac6d28..0b2db4173e723 100644
--- a/drivers/mtd/nand/raw/cadence-nand-controller.c
+++ b/drivers/mtd/nand/raw/cadence-nand-controller.c
@@ -1863,12 +1863,12 @@ static int cadence_nand_slave_dma_transfer(struct cdns_nand_ctrl *cdns_ctrl,
 	dma_async_issue_pending(cdns_ctrl->dmac);
 	wait_for_completion(&finished);
 
-	dma_unmap_single(cdns_ctrl->dev, buf_dma, len, dir);
+	dma_unmap_single(dma_dev->dev, buf_dma, len, dir);
 
 	return 0;
 
 err_unmap:
-	dma_unmap_single(cdns_ctrl->dev, buf_dma, len, dir);
+	dma_unmap_single(dma_dev->dev, buf_dma, len, dir);
 
 err:
 	dev_dbg(cdns_ctrl->dev, "Fall back to CPU I/O\n");

From fd75f371f3a1b04a33d2e750363d6ad76abf734e Mon Sep 17 00:00:00 2001
From: Christian Bruel <christian.bruel@foss.st.com>
Date: Mon, 10 Feb 2025 11:35:15 +0100
Subject: [PATCH 0078/1173] phy: stm32: Fix constant-value overflow assertion

Rework the workaround as the lookup tables always fits into the bitfield,
and the default values are defined by the hardware and cannot be 0:

Guard against false positive with a WARN_ON check to make the compiler
happy: The offset range is pre-checked against the sorted imp_lookup_table
values and overflow should not happen and would be caught by a warning and
return in error.

Also guard against a true positive found during the max_vswing lookup, as a
max vswing value can be 802000 or 803000 microvolt depending on the current
impedance. Therefore set the default impedence index.

Fixes: 2de679ecd724 ("phy: stm32: work around constant-value overflow assertion")
Signed-off-by: Christian Bruel <christian.bruel@foss.st.com>
Link: https://lore.kernel.org/r/20250210103515.2598377-1-christian.bruel@foss.st.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/st/phy-stm32-combophy.c | 38 ++++++++++++++---------------
 1 file changed, 18 insertions(+), 20 deletions(-)

diff --git a/drivers/phy/st/phy-stm32-combophy.c b/drivers/phy/st/phy-stm32-combophy.c
index 49e9fa90a6819..607b4d607eb5e 100644
--- a/drivers/phy/st/phy-stm32-combophy.c
+++ b/drivers/phy/st/phy-stm32-combophy.c
@@ -111,6 +111,7 @@ static const struct clk_impedance imp_lookup[] = {
 	{ 4204000, { 511000, 609000, 706000, 802000 } },
 	{ 3999000, { 571000, 648000, 726000, 803000 } }
 };
+#define DEFAULT_IMP_INDEX 3 /* Default impedance is 50 Ohm */
 
 static int stm32_impedance_tune(struct stm32_combophy *combophy)
 {
@@ -119,10 +120,9 @@ static int stm32_impedance_tune(struct stm32_combophy *combophy)
 	u8 imp_of, vswing_of;
 	u32 max_imp = imp_lookup[0].microohm;
 	u32 min_imp = imp_lookup[imp_size - 1].microohm;
-	u32 max_vswing = imp_lookup[imp_size - 1].vswing[vswing_size - 1];
+	u32 max_vswing;
 	u32 min_vswing = imp_lookup[0].vswing[0];
 	u32 val;
-	u32 regval;
 
 	if (!of_property_read_u32(combophy->dev->of_node, "st,output-micro-ohms", &val)) {
 		if (val < min_imp || val > max_imp) {
@@ -130,45 +130,43 @@ static int stm32_impedance_tune(struct stm32_combophy *combophy)
 			return -EINVAL;
 		}
 
-		regval = 0;
-		for (imp_of = 0; imp_of < ARRAY_SIZE(imp_lookup); imp_of++) {
-			if (imp_lookup[imp_of].microohm <= val) {
-				regval = FIELD_PREP(STM32MP25_PCIEPRG_IMPCTRL_OHM, imp_of);
+		for (imp_of = 0; imp_of < ARRAY_SIZE(imp_lookup); imp_of++)
+			if (imp_lookup[imp_of].microohm <= val)
 				break;
-			}
-		}
+
+		if (WARN_ON(imp_of == ARRAY_SIZE(imp_lookup)))
+			return -EINVAL;
 
 		dev_dbg(combophy->dev, "Set %u micro-ohms output impedance\n",
 			imp_lookup[imp_of].microohm);
 
 		regmap_update_bits(combophy->regmap, SYSCFG_PCIEPRGCR,
 				   STM32MP25_PCIEPRG_IMPCTRL_OHM,
-				   regval);
-	} else {
-		regmap_read(combophy->regmap, SYSCFG_PCIEPRGCR, &val);
-		imp_of = FIELD_GET(STM32MP25_PCIEPRG_IMPCTRL_OHM, val);
-	}
+				   FIELD_PREP(STM32MP25_PCIEPRG_IMPCTRL_OHM, imp_of));
+	} else
+		imp_of = DEFAULT_IMP_INDEX;
 
 	if (!of_property_read_u32(combophy->dev->of_node, "st,output-vswing-microvolt", &val)) {
+		max_vswing = imp_lookup[imp_of].vswing[vswing_size - 1];
+
 		if (val < min_vswing || val > max_vswing) {
 			dev_err(combophy->dev, "Invalid value %u for output vswing\n", val);
 			return -EINVAL;
 		}
 
-		regval = 0;
-		for (vswing_of = 0; vswing_of < ARRAY_SIZE(imp_lookup[imp_of].vswing); vswing_of++) {
-			if (imp_lookup[imp_of].vswing[vswing_of] >= val) {
-				regval = FIELD_PREP(STM32MP25_PCIEPRG_IMPCTRL_VSWING, vswing_of);
+		for (vswing_of = 0; vswing_of < ARRAY_SIZE(imp_lookup[imp_of].vswing); vswing_of++)
+			if (imp_lookup[imp_of].vswing[vswing_of] >= val)
 				break;
-			}
-		}
+
+		if (WARN_ON(vswing_of == ARRAY_SIZE(imp_lookup[imp_of].vswing)))
+			return -EINVAL;
 
 		dev_dbg(combophy->dev, "Set %u microvolt swing\n",
 			 imp_lookup[imp_of].vswing[vswing_of]);
 
 		regmap_update_bits(combophy->regmap, SYSCFG_PCIEPRGCR,
 				   STM32MP25_PCIEPRG_IMPCTRL_VSWING,
-				   regval);
+				   FIELD_PREP(STM32MP25_PCIEPRG_IMPCTRL_VSWING, vswing_of));
 	}
 
 	return 0;

From e2158c953c973adb49383ddea2504faf08d375b7 Mon Sep 17 00:00:00 2001
From: Kaustabh Chakraborty <kauschluss@disroot.org>
Date: Sun, 9 Feb 2025 00:29:30 +0530
Subject: [PATCH 0079/1173] phy: exynos5-usbdrd: fix MPLL_MULTIPLIER and
 SSC_REFCLKSEL masks in refclk

In exynos5_usbdrd_{pipe3,utmi}_set_refclk(), the masks
PHYCLKRST_MPLL_MULTIPLIER_MASK and PHYCLKRST_SSC_REFCLKSEL_MASK are not
inverted when applied to the register values. Fix it.

Cc: stable@vger.kernel.org
Fixes: 59025887fb08 ("phy: Add new Exynos5 USB 3.0 PHY driver")
Signed-off-by: Kaustabh Chakraborty <kauschluss@disroot.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Anand Moon <linux.amoon@gmail.com>
Link: https://lore.kernel.org/r/20250209-exynos5-usbdrd-masks-v1-1-4f7f83f323d7@disroot.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/samsung/phy-exynos5-usbdrd.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/phy/samsung/phy-exynos5-usbdrd.c b/drivers/phy/samsung/phy-exynos5-usbdrd.c
index c421b495eb0fe..4a108fdab118c 100644
--- a/drivers/phy/samsung/phy-exynos5-usbdrd.c
+++ b/drivers/phy/samsung/phy-exynos5-usbdrd.c
@@ -488,9 +488,9 @@ exynos5_usbdrd_pipe3_set_refclk(struct phy_usb_instance *inst)
 	reg |=	PHYCLKRST_REFCLKSEL_EXT_REFCLK;
 
 	/* FSEL settings corresponding to reference clock */
-	reg &= ~PHYCLKRST_FSEL_PIPE_MASK |
-		PHYCLKRST_MPLL_MULTIPLIER_MASK |
-		PHYCLKRST_SSC_REFCLKSEL_MASK;
+	reg &= ~(PHYCLKRST_FSEL_PIPE_MASK |
+		 PHYCLKRST_MPLL_MULTIPLIER_MASK |
+		 PHYCLKRST_SSC_REFCLKSEL_MASK);
 	switch (phy_drd->extrefclk) {
 	case EXYNOS5_FSEL_50MHZ:
 		reg |= (PHYCLKRST_MPLL_MULTIPLIER_50M_REF |
@@ -532,9 +532,9 @@ exynos5_usbdrd_utmi_set_refclk(struct phy_usb_instance *inst)
 	reg &= ~PHYCLKRST_REFCLKSEL_MASK;
 	reg |=	PHYCLKRST_REFCLKSEL_EXT_REFCLK;
 
-	reg &= ~PHYCLKRST_FSEL_UTMI_MASK |
-		PHYCLKRST_MPLL_MULTIPLIER_MASK |
-		PHYCLKRST_SSC_REFCLKSEL_MASK;
+	reg &= ~(PHYCLKRST_FSEL_UTMI_MASK |
+		 PHYCLKRST_MPLL_MULTIPLIER_MASK |
+		 PHYCLKRST_SSC_REFCLKSEL_MASK);
 	reg |= PHYCLKRST_FSEL(phy_drd->extrefclk);
 
 	return reg;

From 2ea97b76d6712bfb0408e5b81ffd7bc4551d3153 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 7 Feb 2025 22:16:09 +0100
Subject: [PATCH 0080/1173] hrtimers: Make hrtimer_update_function() less
 expensive

The sanity checks in hrtimer_update_function() are expensive for high
frequency usage like in the io/uring code due to locking.

Hide the sanity checks behind CONFIG_PROVE_LOCKING, which has a decent
chance to be enabled on a regular basis for testing.

Fixes: 8f02e3563bb5 ("hrtimers: Introduce hrtimer_update_function()")
Reported-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/87ikpllali.ffs@tglx
---
 include/linux/hrtimer.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index f7bfdcf0dda3f..bdd55c1f0d73e 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -333,6 +333,7 @@ static inline int hrtimer_callback_running(struct hrtimer *timer)
 static inline void hrtimer_update_function(struct hrtimer *timer,
 					   enum hrtimer_restart (*function)(struct hrtimer *))
 {
+#ifdef CONFIG_PROVE_LOCKING
 	guard(raw_spinlock_irqsave)(&timer->base->cpu_base->lock);
 
 	if (WARN_ON_ONCE(hrtimer_is_queued(timer)))
@@ -340,7 +341,7 @@ static inline void hrtimer_update_function(struct hrtimer *timer,
 
 	if (WARN_ON_ONCE(!function))
 		return;
-
+#endif
 	timer->function = function;
 }
 

From ccb7735a1ea22621f21c3133e4f5f3da5fe5f5b7 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Mon, 27 Jan 2025 14:45:23 -0800
Subject: [PATCH 0081/1173] x86/fpu: Fully optimize out WARN_ON_FPU()

Currently WARN_ON_FPU evaluates its argument even if
CONFIG_X86_DEBUG_FPU is disabled, which adds unnecessary instructions to
several functions, for example kernel_fpu_begin().  Fix this by using
BUILD_BUG_ON_INVALID(x) in the no-debug case rather than (void)(x).

Fixes: 83242c515881 ("x86/fpu: Make WARN_ON_FPU() more robust in the !CONFIG_X86_DEBUG_FPU case")
Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/all/20250127224523.94300-1-ebiggers%40kernel.org
---
 arch/x86/kernel/fpu/internal.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/fpu/internal.h b/arch/x86/kernel/fpu/internal.h
index dbdb31f55fc7f..975de070c9c98 100644
--- a/arch/x86/kernel/fpu/internal.h
+++ b/arch/x86/kernel/fpu/internal.h
@@ -18,7 +18,7 @@ static __always_inline __pure bool use_fxsr(void)
 #ifdef CONFIG_X86_DEBUG_FPU
 # define WARN_ON_FPU(x) WARN_ON_ONCE(x)
 #else
-# define WARN_ON_FPU(x) ({ (void)(x); 0; })
+# define WARN_ON_FPU(x) ({ BUILD_BUG_ON_INVALID(x); 0; })
 #endif
 
 /* Used in init.c */

From 49f27f29446a5bfe633dd2cc0cfebd48a1a5e77f Mon Sep 17 00:00:00 2001
From: Vitaliy Shevtsov <v.shevtsov@mt-integration.ru>
Date: Fri, 31 Jan 2025 20:26:55 +0500
Subject: [PATCH 0082/1173] wifi: nl80211: reject cooked mode if it is set
 along with other flags

It is possible to set both MONITOR_FLAG_COOK_FRAMES and MONITOR_FLAG_ACTIVE
flags simultaneously on the same monitor interface from the userspace. This
causes a sub-interface to be created with no IEEE80211_SDATA_IN_DRIVER bit
set because the monitor interface is in the cooked state and it takes
precedence over all other states. When the interface is then being deleted
the kernel calls WARN_ONCE() from check_sdata_in_driver() because of missing
that bit.

Fix this by rejecting MONITOR_FLAG_COOK_FRAMES if it is set along with
other flags.

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

Fixes: 66f7ac50ed7c ("nl80211: Add monitor interface configuration flags")
Cc: stable@vger.kernel.org
Reported-by: syzbot+2e5c1e55b9e5c28a3da7@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=2e5c1e55b9e5c28a3da7
Signed-off-by: Vitaliy Shevtsov <v.shevtsov@mt-integration.ru>
Link: https://patch.msgid.link/20250131152657.5606-1-v.shevtsov@mt-integration.ru
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/nl80211.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index d7d3da0f6833d..fdb2aac951d18 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -4220,6 +4220,11 @@ static int parse_monitor_flags(struct nlattr *nla, u32 *mntrflags)
 		if (flags[flag])
 			*mntrflags |= (1<<flag);
 
+	/* cooked monitor mode is incompatible with other modes */
+	if (*mntrflags & MONITOR_FLAG_COOK_FRAMES &&
+	    *mntrflags != MONITOR_FLAG_COOK_FRAMES)
+		return -EOPNOTSUPP;
+
 	*mntrflags |= MONITOR_FLAG_CHANGED;
 
 	return 0;

From 5b999006e35ea9c11116ddff7e375b256421d0af Mon Sep 17 00:00:00 2001
From: Alexander Wetzel <Alexander@wetzel-home.de>
Date: Tue, 4 Feb 2025 13:31:29 +0100
Subject: [PATCH 0083/1173] wifi: mac80211: Cleanup sta TXQs on flush

Drop the sta TXQs on flush when the drivers is not supporting
flush.

ieee80211_set_disassoc() tries to clean up everything for the sta.
But it ignored queued frames in the sta TX queues when the driver
isn't supporting the flush driver ops.

Signed-off-by: Alexander Wetzel <Alexander@wetzel-home.de>
Link: https://patch.msgid.link/20250204123129.9162-1-Alexander@wetzel-home.de
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/util.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index f6b631faf4f7f..7f02bd5891eb9 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -687,7 +687,7 @@ void __ieee80211_flush_queues(struct ieee80211_local *local,
 			      struct ieee80211_sub_if_data *sdata,
 			      unsigned int queues, bool drop)
 {
-	if (!local->ops->flush)
+	if (!local->ops->flush && !drop)
 		return;
 
 	/*
@@ -714,7 +714,8 @@ void __ieee80211_flush_queues(struct ieee80211_local *local,
 		}
 	}
 
-	drv_flush(local, sdata, queues, drop);
+	if (local->ops->flush)
+		drv_flush(local, sdata, queues, drop);
 
 	ieee80211_wake_queues_by_reason(&local->hw, queues,
 					IEEE80211_QUEUE_STOP_REASON_FLUSH,

From 646262c71aca87bb66945933abe4e620796d6c5a Mon Sep 17 00:00:00 2001
From: Alexander Wetzel <Alexander@wetzel-home.de>
Date: Tue, 4 Feb 2025 17:42:40 +0100
Subject: [PATCH 0084/1173] wifi: mac80211: remove debugfs dir for virtual
 monitor

Don't call ieee80211_debugfs_recreate_netdev() for virtual monitor
interface when deleting it.

The virtual monitor interface shouldn't have debugfs entries and trying
to update them will *create* them on deletion.

And when the virtual monitor interface is created/destroyed multiple
times we'll get warnings about debugfs name conflicts.

Signed-off-by: Alexander Wetzel <Alexander@wetzel-home.de>
Link: https://patch.msgid.link/20250204164240.370153-1-Alexander@wetzel-home.de
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/driver-ops.c | 10 ++++++++--
 net/mac80211/iface.c      | 11 ++++++-----
 2 files changed, 14 insertions(+), 7 deletions(-)

diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c
index 299d38e9e8630..2fc60e1e77a55 100644
--- a/net/mac80211/driver-ops.c
+++ b/net/mac80211/driver-ops.c
@@ -116,8 +116,14 @@ void drv_remove_interface(struct ieee80211_local *local,
 
 	sdata->flags &= ~IEEE80211_SDATA_IN_DRIVER;
 
-	/* Remove driver debugfs entries */
-	ieee80211_debugfs_recreate_netdev(sdata, sdata->vif.valid_links);
+	/*
+	 * Remove driver debugfs entries.
+	 * The virtual monitor interface doesn't get a debugfs
+	 * entry, so it's exempt here.
+	 */
+	if (sdata != local->monitor_sdata)
+		ieee80211_debugfs_recreate_netdev(sdata,
+						  sdata->vif.valid_links);
 
 	trace_drv_remove_interface(local, sdata);
 	local->ops->remove_interface(&local->hw, &sdata->vif);
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 0ea7e77860b73..738de269e13f0 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1206,16 +1206,17 @@ void ieee80211_del_virtual_monitor(struct ieee80211_local *local)
 		return;
 	}
 
-	RCU_INIT_POINTER(local->monitor_sdata, NULL);
-	mutex_unlock(&local->iflist_mtx);
-
-	synchronize_net();
-
+	clear_bit(SDATA_STATE_RUNNING, &sdata->state);
 	ieee80211_link_release_channel(&sdata->deflink);
 
 	if (ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF))
 		drv_remove_interface(local, sdata);
 
+	RCU_INIT_POINTER(local->monitor_sdata, NULL);
+	mutex_unlock(&local->iflist_mtx);
+
+	synchronize_net();
+
 	kfree(sdata);
 }
 

From 7774e3920029398ad49dc848b23840593f14d515 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sun, 9 Feb 2025 14:34:45 +0200
Subject: [PATCH 0085/1173] wifi: iwlwifi: fw: allocate chained SG tables for
 dump

The firmware dumps can be pretty big, and since we use single
pages for each SG table entry, even the table itself may end
up being an order-5 allocation. Build chained tables so that
we need not allocate a higher-order table here.

This could be improved and cleaned up, e.g. by using the SG
pool code or simply kvmalloc(), but all of that would require
also updating the devcoredump first since that frees it all,
so we need to be more careful. SG pool might also run against
the CONFIG_ARCH_NO_SG_CHAIN limitation, which is irrelevant
here.

Also use _devcd_free_sgtable() for the error paths now, much
simpler especially since it's in two places now.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250209143303.697c7a465ac9.Iea982df46b5c075bfb77ade36f187d99a70c63db@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/dbg.c | 86 ++++++++++++++-------
 1 file changed, 58 insertions(+), 28 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index fb2ea38e89aca..6594216f873c4 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -558,41 +558,71 @@ static void iwl_dump_prph(struct iwl_fw_runtime *fwrt,
 }
 
 /*
- * alloc_sgtable - allocates scallerlist table in the given size,
- * fills it with pages and returns it
+ * alloc_sgtable - allocates (chained) scatterlist in the given size,
+ *	fills it with pages and returns it
  * @size: the size (in bytes) of the table
-*/
-static struct scatterlist *alloc_sgtable(int size)
+ */
+static struct scatterlist *alloc_sgtable(ssize_t size)
 {
-	int alloc_size, nents, i;
-	struct page *new_page;
-	struct scatterlist *iter;
-	struct scatterlist *table;
+	struct scatterlist *result = NULL, *prev;
+	int nents, i, n_prev;
 
 	nents = DIV_ROUND_UP(size, PAGE_SIZE);
-	table = kcalloc(nents, sizeof(*table), GFP_KERNEL);
-	if (!table)
-		return NULL;
-	sg_init_table(table, nents);
-	iter = table;
-	for_each_sg(table, iter, sg_nents(table), i) {
-		new_page = alloc_page(GFP_KERNEL);
-		if (!new_page) {
-			/* release all previous allocated pages in the table */
-			iter = table;
-			for_each_sg(table, iter, sg_nents(table), i) {
-				new_page = sg_page(iter);
-				if (new_page)
-					__free_page(new_page);
-			}
-			kfree(table);
+
+#define N_ENTRIES_PER_PAGE (PAGE_SIZE / sizeof(*result))
+	/*
+	 * We need an additional entry for table chaining,
+	 * this ensures the loop can finish i.e. we can
+	 * fit at least two entries per page (obviously,
+	 * many more really fit.)
+	 */
+	BUILD_BUG_ON(N_ENTRIES_PER_PAGE < 2);
+
+	while (nents > 0) {
+		struct scatterlist *new, *iter;
+		int n_fill, n_alloc;
+
+		if (nents <= N_ENTRIES_PER_PAGE) {
+			/* last needed table */
+			n_fill = nents;
+			n_alloc = nents;
+			nents = 0;
+		} else {
+			/* fill a page with entries */
+			n_alloc = N_ENTRIES_PER_PAGE;
+			/* reserve one for chaining */
+			n_fill = n_alloc - 1;
+			nents -= n_fill;
+		}
+
+		new = kcalloc(n_alloc, sizeof(*new), GFP_KERNEL);
+		if (!new) {
+			if (result)
+				_devcd_free_sgtable(result);
 			return NULL;
 		}
-		alloc_size = min_t(int, size, PAGE_SIZE);
-		size -= PAGE_SIZE;
-		sg_set_page(iter, new_page, alloc_size, 0);
+		sg_init_table(new, n_alloc);
+
+		if (!result)
+			result = new;
+		else
+			sg_chain(prev, n_prev, new);
+		prev = new;
+		n_prev = n_alloc;
+
+		for_each_sg(new, iter, n_fill, i) {
+			struct page *new_page = alloc_page(GFP_KERNEL);
+
+			if (!new_page) {
+				_devcd_free_sgtable(result);
+				return NULL;
+			}
+
+			sg_set_page(iter, new_page, PAGE_SIZE, 0);
+		}
 	}
-	return table;
+
+	return result;
 }
 
 static void iwl_fw_get_prph_len(struct iwl_fw_runtime *fwrt,

From 3f8aa0b8a53df2247a84eaf3b3aa38b6ef86cb1c Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Sun, 9 Feb 2025 14:34:46 +0200
Subject: [PATCH 0086/1173] wifi: iwlwifi: fw: avoid using an uninitialized
 variable

iwl_fwrt_read_err_table can return true also when it failed to read
the memory. In this case, err_id argument is not initialized,
but the callers are still using it.

Simply initialize it to 0. If the error table was read successfully it'll
be overridden.

Fixes: 43e0b2ada519 ("wifi: iwlwifi: fw: add an error table status getter")
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Link: https://patch.msgid.link/20250209143303.37cdbba4eb56.I95fe9bd95303b8179f946766558a9f15f4fe254c@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/dump.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dump.c b/drivers/net/wireless/intel/iwlwifi/fw/dump.c
index 8e0c85a1240d7..c7b261c8ec969 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dump.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dump.c
@@ -540,6 +540,9 @@ bool iwl_fwrt_read_err_table(struct iwl_trans *trans, u32 base, u32 *err_id)
 	} err_info = {};
 	int ret;
 
+	if (err_id)
+		*err_id = 0;
+
 	if (!base)
 		return false;
 

From f9751163bffd3fe60794929829f810968c6de73d Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sun, 9 Feb 2025 14:34:47 +0200
Subject: [PATCH 0087/1173] wifi: iwlwifi: mvm: clean up ROC on failure

If the firmware fails to start the session protection, then we
do call iwl_mvm_roc_finished() here, but that won't do anything
at all because IWL_MVM_STATUS_ROC_P2P_RUNNING was never set.
Set IWL_MVM_STATUS_ROC_P2P_RUNNING in the failure/stop path.
If it started successfully before, it's already set, so that
doesn't matter, and if it didn't start it needs to be set to
clean up.

Not doing so will lead to a WARN_ON() later on a fresh remain-
on-channel, since the link is already active when activated as
it was never deactivated.

Fixes: 35c1bbd93c4e ("wifi: iwlwifi: mvm: remove IWL_MVM_STATUS_NEED_FLUSH_P2P")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250209143303.0fe36c291068.I67f5dac742170dd937f11e4d4f937f45f71b7cb4@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/time-event.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
index 9216c43a35c4d..ebfa88b38b71b 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
@@ -1030,6 +1030,8 @@ void iwl_mvm_rx_session_protect_notif(struct iwl_mvm *mvm,
 		/* End TE, notify mac80211 */
 		mvmvif->time_event_data.id = SESSION_PROTECT_CONF_MAX_ID;
 		mvmvif->time_event_data.link_id = -1;
+		/* set the bit so the ROC cleanup will actually clean up */
+		set_bit(IWL_MVM_STATUS_ROC_P2P_RUNNING, &mvm->status);
 		iwl_mvm_roc_finished(mvm);
 		ieee80211_remain_on_channel_expired(mvm->hw);
 	} else if (le32_to_cpu(notif->start)) {

From d48ff3ce92259bae7e77732c7cfd7cbc7992c021 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Sun, 9 Feb 2025 14:34:48 +0200
Subject: [PATCH 0088/1173] wifi: iwlwifi: mvm: don't dump the firmware state
 upon RFKILL while suspend

This is not really a firmware error. We need to reload the firmware, but
this doesn't mean that we should consider this as a firmware error.
When the firmware was restarted upon resume, this wasn't felt by the
driver. Now that we keep the firmware running during suspend even if we
don't have wowlan, this started to pop-up.

Fixes: e8bb19c1d590 ("wifi: iwlwifi: support fast resume")
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250209143303.a10463a40318.I14131781c3124b58e60e1f5e9d793a2bc88b464c@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/d3.c | 77 ++++++++++++++-------
 1 file changed, 51 insertions(+), 26 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
index 129b6bdf9ef90..82ca7f8b1bb27 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
@@ -3092,8 +3092,14 @@ static void iwl_mvm_d3_disconnect_iter(void *data, u8 *mac,
 		ieee80211_resume_disconnect(vif);
 }
 
-static bool iwl_mvm_check_rt_status(struct iwl_mvm *mvm,
-				   struct ieee80211_vif *vif)
+enum rt_status {
+	FW_ALIVE,
+	FW_NEEDS_RESET,
+	FW_ERROR,
+};
+
+static enum rt_status iwl_mvm_check_rt_status(struct iwl_mvm *mvm,
+					      struct ieee80211_vif *vif)
 {
 	u32 err_id;
 
@@ -3101,29 +3107,35 @@ static bool iwl_mvm_check_rt_status(struct iwl_mvm *mvm,
 	if (iwl_fwrt_read_err_table(mvm->trans,
 				    mvm->trans->dbg.lmac_error_event_table[0],
 				    &err_id)) {
-		if (err_id == RF_KILL_INDICATOR_FOR_WOWLAN && vif) {
-			struct cfg80211_wowlan_wakeup wakeup = {
-				.rfkill_release = true,
-			};
-			ieee80211_report_wowlan_wakeup(vif, &wakeup,
-						       GFP_KERNEL);
+		if (err_id == RF_KILL_INDICATOR_FOR_WOWLAN) {
+			IWL_WARN(mvm, "Rfkill was toggled during suspend\n");
+			if (vif) {
+				struct cfg80211_wowlan_wakeup wakeup = {
+					.rfkill_release = true,
+				};
+
+				ieee80211_report_wowlan_wakeup(vif, &wakeup,
+							       GFP_KERNEL);
+			}
+
+			return FW_NEEDS_RESET;
 		}
-		return true;
+		return FW_ERROR;
 	}
 
 	/* check if we have lmac2 set and check for error */
 	if (iwl_fwrt_read_err_table(mvm->trans,
 				    mvm->trans->dbg.lmac_error_event_table[1],
 				    NULL))
-		return true;
+		return FW_ERROR;
 
 	/* check for umac error */
 	if (iwl_fwrt_read_err_table(mvm->trans,
 				    mvm->trans->dbg.umac_error_event_table,
 				    NULL))
-		return true;
+		return FW_ERROR;
 
-	return false;
+	return FW_ALIVE;
 }
 
 /*
@@ -3492,6 +3504,7 @@ static int __iwl_mvm_resume(struct iwl_mvm *mvm, bool test)
 	bool d0i3_first = fw_has_capa(&mvm->fw->ucode_capa,
 				      IWL_UCODE_TLV_CAPA_D0I3_END_FIRST);
 	bool resume_notif_based = iwl_mvm_d3_resume_notif_based(mvm);
+	enum rt_status rt_status;
 	bool keep = false;
 
 	mutex_lock(&mvm->mutex);
@@ -3515,14 +3528,19 @@ static int __iwl_mvm_resume(struct iwl_mvm *mvm, bool test)
 
 	iwl_fw_dbg_read_d3_debug_data(&mvm->fwrt);
 
-	if (iwl_mvm_check_rt_status(mvm, vif)) {
-		IWL_ERR(mvm, "FW Error occurred during suspend. Restarting.\n");
+	rt_status = iwl_mvm_check_rt_status(mvm, vif);
+	if (rt_status != FW_ALIVE) {
 		set_bit(STATUS_FW_ERROR, &mvm->trans->status);
-		iwl_mvm_dump_nic_error_log(mvm);
-		iwl_dbg_tlv_time_point(&mvm->fwrt,
-				       IWL_FW_INI_TIME_POINT_FW_ASSERT, NULL);
-		iwl_fw_dbg_collect_desc(&mvm->fwrt, &iwl_dump_desc_assert,
-					false, 0);
+		if (rt_status == FW_ERROR) {
+			IWL_ERR(mvm, "FW Error occurred during suspend. Restarting.\n");
+			iwl_mvm_dump_nic_error_log(mvm);
+			iwl_dbg_tlv_time_point(&mvm->fwrt,
+					       IWL_FW_INI_TIME_POINT_FW_ASSERT,
+					       NULL);
+			iwl_fw_dbg_collect_desc(&mvm->fwrt,
+						&iwl_dump_desc_assert,
+						false, 0);
+		}
 		ret = 1;
 		goto err;
 	}
@@ -3679,6 +3697,7 @@ int iwl_mvm_fast_resume(struct iwl_mvm *mvm)
 		.notif_expected =
 			IWL_D3_NOTIF_D3_END_NOTIF,
 	};
+	enum rt_status rt_status;
 	int ret;
 
 	lockdep_assert_held(&mvm->mutex);
@@ -3688,14 +3707,20 @@ int iwl_mvm_fast_resume(struct iwl_mvm *mvm)
 	mvm->last_reset_or_resume_time_jiffies = jiffies;
 	iwl_fw_dbg_read_d3_debug_data(&mvm->fwrt);
 
-	if (iwl_mvm_check_rt_status(mvm, NULL)) {
-		IWL_ERR(mvm, "FW Error occurred during suspend. Restarting.\n");
+	rt_status = iwl_mvm_check_rt_status(mvm, NULL);
+	if (rt_status != FW_ALIVE) {
 		set_bit(STATUS_FW_ERROR, &mvm->trans->status);
-		iwl_mvm_dump_nic_error_log(mvm);
-		iwl_dbg_tlv_time_point(&mvm->fwrt,
-				       IWL_FW_INI_TIME_POINT_FW_ASSERT, NULL);
-		iwl_fw_dbg_collect_desc(&mvm->fwrt, &iwl_dump_desc_assert,
-					false, 0);
+		if (rt_status == FW_ERROR) {
+			IWL_ERR(mvm,
+				"iwl_mvm_check_rt_status failed, device is gone during suspend\n");
+			iwl_mvm_dump_nic_error_log(mvm);
+			iwl_dbg_tlv_time_point(&mvm->fwrt,
+					       IWL_FW_INI_TIME_POINT_FW_ASSERT,
+					       NULL);
+			iwl_fw_dbg_collect_desc(&mvm->fwrt,
+						&iwl_dump_desc_assert,
+						false, 0);
+		}
 		mvm->trans->state = IWL_TRANS_NO_FW;
 		ret = -ENODEV;
 

From d73d2c6e3313f0ba60711ab4f4b9044eddca9ca5 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Sun, 9 Feb 2025 14:34:49 +0200
Subject: [PATCH 0089/1173] wifi: iwlwifi: mvm: don't try to talk to a dead
 firmware

This fixes:

 bad state = 0
 WARNING: CPU: 10 PID: 702 at drivers/net/wireless/inel/iwlwifi/iwl-trans.c:178 iwl_trans_send_cmd+0xba/0xe0 [iwlwifi]
 Call Trace:
  <TASK>
  ? __warn+0xca/0x1c0
  ? iwl_trans_send_cmd+0xba/0xe0 [iwlwifi 64fa9ad799a0e0d2ba53d4af93a53ad9a531f8d4]
  iwl_fw_dbg_clear_monitor_buf+0xd7/0x110 [iwlwifi 64fa9ad799a0e0d2ba53d4af93a53ad9a531f8d4]
  _iwl_dbgfs_fw_dbg_clear_write+0xe2/0x120 [iwlmvm 0e8adb18cea92d2c341766bcc10b18699290068a]

Ask whether the firmware is alive before sending a command.

Fixes: 268712dc3b34 ("wifi: iwlwifi: mvm: add a debugfs hook to clear the monitor data")
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250209143303.8e1597b62c70.I12ea71dd9b805b095c9fc12a10c9f34a4e801b61@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
index 83e3c11603622..55d035b896e91 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
@@ -1479,6 +1479,13 @@ static ssize_t iwl_dbgfs_fw_dbg_clear_write(struct iwl_mvm *mvm,
 	if (mvm->trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_9000)
 		return -EOPNOTSUPP;
 
+	/*
+	 * If the firmware is not running, silently succeed since there is
+	 * no data to clear.
+	 */
+	if (!iwl_mvm_firmware_running(mvm))
+		return count;
+
 	mutex_lock(&mvm->mutex);
 	iwl_fw_dbg_clear_monitor_buf(&mvm->fwrt);
 	mutex_unlock(&mvm->mutex);

From a03e2082e678ea10d0d8bdf3ed933eb05a8ddbb0 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Sun, 9 Feb 2025 14:34:50 +0200
Subject: [PATCH 0090/1173] wifi: iwlwifi: mvm: use the right version of the
 rate API

The firmware uses the newer version of the API in recent devices. For
older devices, we translate the rate to the new format.
Don't parse the rate with old parsing macros.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250209143303.13d70cdcbb4e.Ic92193bce4013b70a823cfef250ee79c16cf7c17@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index 09fd8752046ee..14ea89f931bbf 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -995,7 +995,7 @@ iwl_mvm_decode_he_phy_ru_alloc(struct iwl_mvm_rx_phy_data *phy_data,
 	 */
 	u8 ru = le32_get_bits(phy_data->d1, IWL_RX_PHY_DATA1_HE_RU_ALLOC_MASK);
 	u32 rate_n_flags = phy_data->rate_n_flags;
-	u32 he_type = rate_n_flags & RATE_MCS_HE_TYPE_MSK_V1;
+	u32 he_type = rate_n_flags & RATE_MCS_HE_TYPE_MSK;
 	u8 offs = 0;
 
 	rx_status->bw = RATE_INFO_BW_HE_RU;
@@ -1050,13 +1050,13 @@ iwl_mvm_decode_he_phy_ru_alloc(struct iwl_mvm_rx_phy_data *phy_data,
 
 	if (he_mu)
 		he_mu->flags2 |=
-			le16_encode_bits(FIELD_GET(RATE_MCS_CHAN_WIDTH_MSK_V1,
+			le16_encode_bits(FIELD_GET(RATE_MCS_CHAN_WIDTH_MSK,
 						   rate_n_flags),
 					 IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW);
-	else if (he_type == RATE_MCS_HE_TYPE_TRIG_V1)
+	else if (he_type == RATE_MCS_HE_TYPE_TRIG)
 		he->data6 |=
 			cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA6_TB_PPDU_BW_KNOWN) |
-			le16_encode_bits(FIELD_GET(RATE_MCS_CHAN_WIDTH_MSK_V1,
+			le16_encode_bits(FIELD_GET(RATE_MCS_CHAN_WIDTH_MSK,
 						   rate_n_flags),
 					 IEEE80211_RADIOTAP_HE_DATA6_TB_PPDU_BW);
 }

From e0dc2c1bef722cbf16ae557690861e5f91208129 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sun, 9 Feb 2025 14:34:51 +0200
Subject: [PATCH 0091/1173] wifi: iwlwifi: limit printed string from FW file

There's no guarantee here that the file is always with a
NUL-termination, so reading the string may read beyond the
end of the TLV. If that's the last TLV in the file, it can
perhaps even read beyond the end of the file buffer.

Fix that by limiting the print format to the size of the
buffer we have.

Fixes: aee1b6385e29 ("iwlwifi: support fseq tlv and print fseq version")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250209143303.cb5f9d0c2f5d.Idec695d53c6c2234aade306f7647b576c7e3d928@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-drv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
index d3a65f33097cb..352b6e73e08f3 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
@@ -1181,7 +1181,7 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv,
 
 			if (tlv_len != sizeof(*fseq_ver))
 				goto invalid_tlv_len;
-			IWL_INFO(drv, "TLV_FW_FSEQ_VERSION: %s\n",
+			IWL_INFO(drv, "TLV_FW_FSEQ_VERSION: %.32s\n",
 				 fseq_ver->version);
 			}
 			break;

From 3b08e608d50c44ca1135beed179f266aa0461da7 Mon Sep 17 00:00:00 2001
From: Ilan Peer <ilan.peer@intel.com>
Date: Sun, 9 Feb 2025 14:34:52 +0200
Subject: [PATCH 0092/1173] wifi: iwlwifi: Free pages allocated when failing to
 build A-MSDU

When failing to prepare the data needed for A-MSDU transmission, the memory
allocated for the TSO management was not freed. Fix it.

Fixes: 7f5e3038f029 ("wifi: iwlwifi: map entire SKB when sending AMSDUs")
Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250209143303.bc27fad9b3d5.Ibf43dd18fb652b1a59061204e081f11c9fa34a3f@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
index 1f483f15c2383..dce5096db82b6 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
@@ -347,6 +347,7 @@ iwl_tfh_tfd *iwl_txq_gen2_build_tx_amsdu(struct iwl_trans *trans,
 	return tfd;
 
 out_err:
+	iwl_pcie_free_tso_pages(trans, skb, out_meta);
 	iwl_txq_gen2_tfd_unmap(trans, out_meta, tfd);
 	return NULL;
 }

From 3640dbc1f75ce15d128ea4af44226960d894f3fd Mon Sep 17 00:00:00 2001
From: Ilan Peer <ilan.peer@intel.com>
Date: Sun, 9 Feb 2025 14:34:53 +0200
Subject: [PATCH 0093/1173] wifi: iwlwifi: Fix A-MSDU TSO preparation

The TSO preparation assumed that the skb head contained the headers
while the rest of the data was in the fragments. Since this is not
always true, e.g., it is possible that the data was linearised, modify
the TSO preparation to start the data processing after the network
headers.

Fixes: 7f5e3038f029 ("wifi: iwlwifi: map entire SKB when sending AMSDUs")
Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Reviewed-by: Benjamin Berg <benjamin.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250209143303.75769a4769bf.Iaf79e8538093cdf8c446c292cc96164ad6498f61@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../wireless/intel/iwlwifi/pcie/internal.h    |  5 +++--
 .../net/wireless/intel/iwlwifi/pcie/tx-gen2.c |  5 +++--
 drivers/net/wireless/intel/iwlwifi/pcie/tx.c  | 20 +++++++++++--------
 3 files changed, 18 insertions(+), 12 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
index 856b7e9f717d5..45460f93d24ad 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2003-2015, 2018-2024 Intel Corporation
+ * Copyright (C) 2003-2015, 2018-2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -646,7 +646,8 @@ dma_addr_t iwl_pcie_get_sgt_tb_phys(struct sg_table *sgt, unsigned int offset,
 				    unsigned int len);
 struct sg_table *iwl_pcie_prep_tso(struct iwl_trans *trans, struct sk_buff *skb,
 				   struct iwl_cmd_meta *cmd_meta,
-				   u8 **hdr, unsigned int hdr_room);
+				   u8 **hdr, unsigned int hdr_room,
+				   unsigned int offset);
 
 void iwl_pcie_free_tso_pages(struct iwl_trans *trans, struct sk_buff *skb,
 			     struct iwl_cmd_meta *cmd_meta);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
index dce5096db82b6..401919f9fe88e 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
  * Copyright (C) 2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2020, 2023-2024 Intel Corporation
+ * Copyright (C) 2018-2020, 2023-2025 Intel Corporation
  */
 #include <net/tso.h>
 #include <linux/tcp.h>
@@ -188,7 +188,8 @@ static int iwl_txq_gen2_build_amsdu(struct iwl_trans *trans,
 		(3 + snap_ip_tcp_hdrlen + sizeof(struct ethhdr));
 
 	/* Our device supports 9 segments at most, it will fit in 1 page */
-	sgt = iwl_pcie_prep_tso(trans, skb, out_meta, &start_hdr, hdr_room);
+	sgt = iwl_pcie_prep_tso(trans, skb, out_meta, &start_hdr, hdr_room,
+				snap_ip_tcp_hdrlen + hdr_len);
 	if (!sgt)
 		return -ENOMEM;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
index 334ebd4c12fa7..7b6071a59b694 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2003-2014, 2018-2021, 2023-2024 Intel Corporation
+ * Copyright (C) 2003-2014, 2018-2021, 2023-2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -1855,6 +1855,7 @@ dma_addr_t iwl_pcie_get_sgt_tb_phys(struct sg_table *sgt, unsigned int offset,
  * @cmd_meta: command meta to store the scatter list information for unmapping
  * @hdr: output argument for TSO headers
  * @hdr_room: requested length for TSO headers
+ * @offset: offset into the data from which mapping should start
  *
  * Allocate space for a scatter gather list and TSO headers and map the SKB
  * using the scatter gather list. The SKB is unmapped again when the page is
@@ -1864,18 +1865,20 @@ dma_addr_t iwl_pcie_get_sgt_tb_phys(struct sg_table *sgt, unsigned int offset,
  */
 struct sg_table *iwl_pcie_prep_tso(struct iwl_trans *trans, struct sk_buff *skb,
 				   struct iwl_cmd_meta *cmd_meta,
-				   u8 **hdr, unsigned int hdr_room)
+				   u8 **hdr, unsigned int hdr_room,
+				   unsigned int offset)
 {
 	struct sg_table *sgt;
+	unsigned int n_segments;
 
 	if (WARN_ON_ONCE(skb_has_frag_list(skb)))
 		return NULL;
 
+	n_segments = DIV_ROUND_UP(skb->len - offset, skb_shinfo(skb)->gso_size);
 	*hdr = iwl_pcie_get_page_hdr(trans,
 				     hdr_room + __alignof__(struct sg_table) +
 				     sizeof(struct sg_table) +
-				     (skb_shinfo(skb)->nr_frags + 1) *
-				     sizeof(struct scatterlist),
+				     n_segments * sizeof(struct scatterlist),
 				     skb);
 	if (!*hdr)
 		return NULL;
@@ -1883,11 +1886,11 @@ struct sg_table *iwl_pcie_prep_tso(struct iwl_trans *trans, struct sk_buff *skb,
 	sgt = (void *)PTR_ALIGN(*hdr + hdr_room, __alignof__(struct sg_table));
 	sgt->sgl = (void *)(sgt + 1);
 
-	sg_init_table(sgt->sgl, skb_shinfo(skb)->nr_frags + 1);
+	sg_init_table(sgt->sgl, n_segments);
 
 	/* Only map the data, not the header (it is copied to the TSO page) */
-	sgt->orig_nents = skb_to_sgvec(skb, sgt->sgl, skb_headlen(skb),
-				       skb->data_len);
+	sgt->orig_nents = skb_to_sgvec(skb, sgt->sgl, offset,
+				       skb->len - offset);
 	if (WARN_ON_ONCE(sgt->orig_nents <= 0))
 		return NULL;
 
@@ -1939,7 +1942,8 @@ static int iwl_fill_data_tbs_amsdu(struct iwl_trans *trans, struct sk_buff *skb,
 		(3 + snap_ip_tcp_hdrlen + sizeof(struct ethhdr)) + iv_len;
 
 	/* Our device supports 9 segments at most, it will fit in 1 page */
-	sgt = iwl_pcie_prep_tso(trans, skb, out_meta, &start_hdr, hdr_room);
+	sgt = iwl_pcie_prep_tso(trans, skb, out_meta, &start_hdr, hdr_room,
+				snap_ip_tcp_hdrlen + hdr_len + iv_len);
 	if (!sgt)
 		return -ENOMEM;
 

From 86ede0a61f8576a84bb0a93c5d9861d2ec1cdf9a Mon Sep 17 00:00:00 2001
From: Christian Marangi <ansuelsmth@gmail.com>
Date: Sun, 9 Feb 2025 15:09:38 +0100
Subject: [PATCH 0094/1173] mtd: rawnand: qcom: fix broken config in
 qcom_param_page_type_exec

Fix broken config in qcom_param_page_type_exec caused by copy-paste error
from commit 0c08080fd71c ("mtd: rawnand: qcom: use FIELD_PREP and GENMASK")

In qcom_param_page_type_exec the value needs to be set to
nandc->regs->cfg0 instead of host->cfg0. This wrong configuration caused
the Qcom NANDC driver to malfunction on any device that makes use of it
(IPQ806x, IPQ40xx, IPQ807x, IPQ60xx) with the following error:

[    0.885369] nand: device found, Manufacturer ID: 0x2c, Chip ID: 0xaa
[    0.885909] nand: Micron NAND 256MiB 1,8V 8-bit
[    0.892499] nand: 256 MiB, SLC, erase size: 128 KiB, page size: 2048, OOB size: 64
[    0.896823] nand: ECC (step, strength) = (512, 8) does not fit in OOB
[    0.896836] qcom-nandc 79b0000.nand-controller: No valid ECC settings possible
[    0.910996] bam-dma-engine 7984000.dma-controller: Cannot free busy channel
[    0.918070] qcom-nandc: probe of 79b0000.nand-controller failed with error -28

Restore original configuration fix the problem and makes the driver work
again.

Also restore the wrongly dropped cpu_to_le32 to correctly support BE
systems.

Cc: stable@vger.kernel.org
Fixes: 0c08080fd71c ("mtd: rawnand: qcom: use FIELD_PREP and GENMASK")
Tested-by: Robert Marko <robimarko@gmail.com> # IPQ8074 and IPQ6018
Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/qcom_nandc.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c
index d2d2aeee42a7e..6720b547892ba 100644
--- a/drivers/mtd/nand/raw/qcom_nandc.c
+++ b/drivers/mtd/nand/raw/qcom_nandc.c
@@ -1881,18 +1881,18 @@ static int qcom_param_page_type_exec(struct nand_chip *chip,  const struct nand_
 	nandc->regs->addr0 = 0;
 	nandc->regs->addr1 = 0;
 
-	host->cfg0 = FIELD_PREP(CW_PER_PAGE_MASK, 0) |
-		     FIELD_PREP(UD_SIZE_BYTES_MASK, 512) |
-		     FIELD_PREP(NUM_ADDR_CYCLES_MASK, 5) |
-		     FIELD_PREP(SPARE_SIZE_BYTES_MASK, 0);
-
-	host->cfg1 = FIELD_PREP(NAND_RECOVERY_CYCLES_MASK, 7) |
-		     FIELD_PREP(BAD_BLOCK_BYTE_NUM_MASK, 17) |
-		     FIELD_PREP(CS_ACTIVE_BSY, 0) |
-		     FIELD_PREP(BAD_BLOCK_IN_SPARE_AREA, 1) |
-		     FIELD_PREP(WR_RD_BSY_GAP_MASK, 2) |
-		     FIELD_PREP(WIDE_FLASH, 0) |
-		     FIELD_PREP(DEV0_CFG1_ECC_DISABLE, 1);
+	nandc->regs->cfg0 = cpu_to_le32(FIELD_PREP(CW_PER_PAGE_MASK, 0) |
+					FIELD_PREP(UD_SIZE_BYTES_MASK, 512) |
+					FIELD_PREP(NUM_ADDR_CYCLES_MASK, 5) |
+					FIELD_PREP(SPARE_SIZE_BYTES_MASK, 0));
+
+	nandc->regs->cfg1 = cpu_to_le32(FIELD_PREP(NAND_RECOVERY_CYCLES_MASK, 7) |
+					FIELD_PREP(BAD_BLOCK_BYTE_NUM_MASK, 17) |
+					FIELD_PREP(CS_ACTIVE_BSY, 0) |
+					FIELD_PREP(BAD_BLOCK_IN_SPARE_AREA, 1) |
+					FIELD_PREP(WR_RD_BSY_GAP_MASK, 2) |
+					FIELD_PREP(WIDE_FLASH, 0) |
+					FIELD_PREP(DEV0_CFG1_ECC_DISABLE, 1));
 
 	if (!nandc->props->qpic_version2)
 		nandc->regs->ecc_buf_cfg = cpu_to_le32(ECC_CFG_ECC_DISABLE);

From 7d1163fc08936fcb5cf5d9daf366c322c3b4e882 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <cassel@kernel.org>
Date: Fri, 7 Feb 2025 15:39:01 +0100
Subject: [PATCH 0095/1173] arm64: dts: rockchip: disable IOMMU when running
 rk3588 in PCIe endpoint mode

Commit da92d3dfc871 ("arm64: dts: rockchip: enable the mmu600_pcie IOMMU
on the rk3588 SoC") enabled the mmu600_pcie IOMMU, both in the normal case
(when all PCIe controllers are running in Root Complex mode) and in the
case when running the pcie3x4 PCIe controller in Endpoint mode.

There have been no issues detected when running the PCIe controllers in
Root Complex mode. During PCI probe time, we will add a SID to the IOMMU
for each PCI device enumerated on the bus, including the root port itself.

However, when running the pcie3x4 PCIe controller in Endpoint mode, we
will only add a single SID to the IOMMU (the SID specified in the iommus
DT property).

The enablement of IOMMU in endpoint mode was verified on setup with two
Rock 5b:s, where the BDF of the Root Complex has BDF (00:00.0).

A Root Complex sending a TLP to the Endpoint will have Requester ID set
to the BDF of the initiator. On the EP side, the Requester ID will then
be used as the SID. This works fine if the Root Complex has a BDF that
matches the iommus DT property, however, if the Root Complex has any other
BDF, we will see something like:
arm-smmu-v3 fc900000.iommu: event: C_BAD_STREAMID client: (unassigned sid) sid: 0x1600 ssid: 0x0
on the endpoint side.

For PCIe controllers running in endpoint mode that always uses the
incoming Requester ID as the SID, the iommus DT property simply isn't
a viable solution. (Neither is iommu-map a viable solution, as there is
no enumeration done on the endpoint side.)

Thus, partly revert commit da92d3dfc871 ("arm64: dts: rockchip: enable the
mmu600_pcie IOMMU on the rk3588 SoC") by disabling the PCI IOMMU when
running the pcie3x4 PCIe controller in Endpoint mode.

Since the PCI IOMMU is working as expected in the normal case, keep it
enabled when running all PCIe controllers in Root Complex mode.

Fixes: da92d3dfc871 ("arm64: dts: rockchip: enable the mmu600_pcie IOMMU on the rk3588 SoC")
Signed-off-by: Niklas Cassel <cassel@kernel.org>
Acked-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/20250207143900.2047949-2-cassel@kernel.org
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 arch/arm64/boot/dts/rockchip/rk3588-extra.dtsi           | 1 -
 arch/arm64/boot/dts/rockchip/rk3588-rock-5b-pcie-ep.dtso | 4 ++++
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/boot/dts/rockchip/rk3588-extra.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-extra.dtsi
index 4a950907ea6f5..840b638af1c24 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-extra.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-extra.dtsi
@@ -213,7 +213,6 @@
 		interrupt-names = "sys", "pmc", "msg", "legacy", "err",
 				  "dma0", "dma1", "dma2", "dma3";
 		max-link-speed = <3>;
-		iommus = <&mmu600_pcie 0x0000>;
 		num-lanes = <4>;
 		phys = <&pcie30phy>;
 		phy-names = "pcie-phy";
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b-pcie-ep.dtso b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b-pcie-ep.dtso
index 672d748fcc67c..f229cb49da680 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b-pcie-ep.dtso
+++ b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b-pcie-ep.dtso
@@ -23,3 +23,7 @@
 	vpcie3v3-supply = <&vcc3v3_pcie30>;
 	status = "okay";
 };
+
+&mmu600_pcie {
+	status = "disabled";
+};

From 8546cfd08aa4b982acd2357403a1f15495d622ec Mon Sep 17 00:00:00 2001
From: Patrick Wildt <patrick@blueri.se>
Date: Mon, 10 Feb 2025 22:37:29 +0100
Subject: [PATCH 0096/1173] arm64: dts: rockchip: adjust SMMU interrupt type on
 rk3588

The SMMU architecture requires wired interrupts to be edge triggered,
which does not align with the DT description for the RK3588.  This leads
to interrupt storms, as the SMMU continues to hold the pin high and only
pulls it down for a short amount when issuing an IRQ.  Update the DT
description to be in line with the spec and perceived reality.

Signed-off-by: Patrick Wildt <patrick@blueri.se>
Fixes: cd81d3a0695c ("arm64: dts: rockchip: add rk3588 pcie and php IOMMUs")
Reviewed-by: Niklas Cassel <cassel@kernel.org>
Link: https://lore.kernel.org/r/Z6pxme2Chmf3d3uK@windev.fritz.box
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 arch/arm64/boot/dts/rockchip/rk3588-base.dtsi | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi
index 978de506d4348..c3abdfb04f8f4 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi
@@ -549,10 +549,10 @@
 	mmu600_pcie: iommu@fc900000 {
 		compatible = "arm,smmu-v3";
 		reg = <0x0 0xfc900000 0x0 0x200000>;
-		interrupts = <GIC_SPI 369 IRQ_TYPE_LEVEL_HIGH 0>,
-			     <GIC_SPI 371 IRQ_TYPE_LEVEL_HIGH 0>,
-			     <GIC_SPI 374 IRQ_TYPE_LEVEL_HIGH 0>,
-			     <GIC_SPI 367 IRQ_TYPE_LEVEL_HIGH 0>;
+		interrupts = <GIC_SPI 369 IRQ_TYPE_EDGE_RISING 0>,
+			     <GIC_SPI 371 IRQ_TYPE_EDGE_RISING 0>,
+			     <GIC_SPI 374 IRQ_TYPE_EDGE_RISING 0>,
+			     <GIC_SPI 367 IRQ_TYPE_EDGE_RISING 0>;
 		interrupt-names = "eventq", "gerror", "priq", "cmdq-sync";
 		#iommu-cells = <1>;
 	};
@@ -560,10 +560,10 @@
 	mmu600_php: iommu@fcb00000 {
 		compatible = "arm,smmu-v3";
 		reg = <0x0 0xfcb00000 0x0 0x200000>;
-		interrupts = <GIC_SPI 381 IRQ_TYPE_LEVEL_HIGH 0>,
-			     <GIC_SPI 383 IRQ_TYPE_LEVEL_HIGH 0>,
-			     <GIC_SPI 386 IRQ_TYPE_LEVEL_HIGH 0>,
-			     <GIC_SPI 379 IRQ_TYPE_LEVEL_HIGH 0>;
+		interrupts = <GIC_SPI 381 IRQ_TYPE_EDGE_RISING 0>,
+			     <GIC_SPI 383 IRQ_TYPE_EDGE_RISING 0>,
+			     <GIC_SPI 386 IRQ_TYPE_EDGE_RISING 0>,
+			     <GIC_SPI 379 IRQ_TYPE_EDGE_RISING 0>;
 		interrupt-names = "eventq", "gerror", "priq", "cmdq-sync";
 		#iommu-cells = <1>;
 		status = "disabled";

From ab027c488fc4a1fff0a5b712d4bdb2d2d324e8f8 Mon Sep 17 00:00:00 2001
From: Peng Fan <peng.fan@nxp.com>
Date: Thu, 23 Jan 2025 14:34:41 +0800
Subject: [PATCH 0097/1173] firmware: arm_scmi: imx: Correct tx size of
 scmi_imx_misc_ctrl_set

'struct scmi_imx_misc_ctrl_set_in' has a zero length array in the end,
The sizeof will not count 'value[]', and hence Tx size will be smaller
than actual size for Tx,and SCMI firmware will flag this as protocol
error.

Fix this by enlarge the Tx size with 'num * sizeof(__le32)' to count in
the size of data.

Fixes: 61c9f03e22fc ("firmware: arm_scmi: Add initial support for i.MX MISC protocol")
Reviewed-by: Jacky Bai <ping.bai@nxp.com>
Tested-by: Shengjiu Wang <shengjiu.wang@nxp.com>
Acked-by: Jason Liu <jason.hui.liu@nxp.com>
Signed-off-by: Peng Fan <peng.fan@nxp.com>
Message-Id: <20250123063441.392555-1-peng.fan@oss.nxp.com>
(sudeep.holla: Commit rewording and replace hardcoded sizeof(__le32) value)
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_scmi/vendors/imx/imx-sm-misc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/firmware/arm_scmi/vendors/imx/imx-sm-misc.c b/drivers/firmware/arm_scmi/vendors/imx/imx-sm-misc.c
index 83b69fc4fba5b..a8915d3b4df51 100644
--- a/drivers/firmware/arm_scmi/vendors/imx/imx-sm-misc.c
+++ b/drivers/firmware/arm_scmi/vendors/imx/imx-sm-misc.c
@@ -254,8 +254,8 @@ static int scmi_imx_misc_ctrl_set(const struct scmi_protocol_handle *ph,
 	if (num > max_num)
 		return -EINVAL;
 
-	ret = ph->xops->xfer_get_init(ph, SCMI_IMX_MISC_CTRL_SET, sizeof(*in),
-				      0, &t);
+	ret = ph->xops->xfer_get_init(ph, SCMI_IMX_MISC_CTRL_SET,
+				      sizeof(*in) + num * sizeof(__le32), 0, &t);
 	if (ret)
 		return ret;
 

From a8972d5a49b408248294b5ecbdd0a085e4726349 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Fri, 27 Sep 2024 09:53:05 -0400
Subject: [PATCH 0098/1173] drm: panel: jd9365da-h3: fix reset signal polarity

In jadard_prepare() a reset pulse is generated with the following
statements (delays ommited for clarity):

    gpiod_set_value(jadard->reset, 1); --> Deassert reset
    gpiod_set_value(jadard->reset, 0); --> Assert reset for 10ms
    gpiod_set_value(jadard->reset, 1); --> Deassert reset

However, specifying second argument of "0" to gpiod_set_value() means to
deassert the GPIO, and "1" means to assert it. If the reset signal is
defined as GPIO_ACTIVE_LOW in the DTS, the above statements will
incorrectly generate the reset pulse (inverted) and leave it asserted
(LOW) at the end of jadard_prepare().

Fix reset behavior by inverting gpiod_set_value() second argument
in jadard_prepare(). Also modify second argument to devm_gpiod_get()
in jadard_dsi_probe() to assert the reset when probing.

Do not modify it in jadard_unprepare() as it is already properly
asserted with "1", which seems to be the intended behavior.

Fixes: 6b818c533dd8 ("drm: panel: Add Jadard JD9365DA-H3 DSI panel")
Cc: stable@vger.kernel.org
Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20240927135306.857617-1-hugo@hugovil.com
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20240927135306.857617-1-hugo@hugovil.com
---
 drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c b/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c
index 45d09e6fa667f..7d68a8acfe2ea 100644
--- a/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c
+++ b/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c
@@ -109,13 +109,13 @@ static int jadard_prepare(struct drm_panel *panel)
 	if (jadard->desc->lp11_to_reset_delay_ms)
 		msleep(jadard->desc->lp11_to_reset_delay_ms);
 
-	gpiod_set_value(jadard->reset, 1);
+	gpiod_set_value(jadard->reset, 0);
 	msleep(5);
 
-	gpiod_set_value(jadard->reset, 0);
+	gpiod_set_value(jadard->reset, 1);
 	msleep(10);
 
-	gpiod_set_value(jadard->reset, 1);
+	gpiod_set_value(jadard->reset, 0);
 	msleep(130);
 
 	ret = jadard->desc->init(jadard);
@@ -1130,7 +1130,7 @@ static int jadard_dsi_probe(struct mipi_dsi_device *dsi)
 	dsi->format = desc->format;
 	dsi->lanes = desc->lanes;
 
-	jadard->reset = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW);
+	jadard->reset = devm_gpiod_get(dev, "reset", GPIOD_OUT_HIGH);
 	if (IS_ERR(jadard->reset)) {
 		DRM_DEV_ERROR(&dsi->dev, "failed to get our reset GPIO\n");
 		return PTR_ERR(jadard->reset);

From fbe8f2fa971c537571994a0df532c511c4fb5537 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Wed, 12 Feb 2025 09:11:07 -0800
Subject: [PATCH 0099/1173] md/raid*: Fix the set_queue_limits implementations

queue_limits_cancel_update() must only be called if
queue_limits_start_update() is called first. Remove the
queue_limits_cancel_update() calls from the raid*_set_limits() functions
because there is no corresponding queue_limits_start_update() call.

Cc: Christoph Hellwig <hch@lst.de>
Fixes: c6e56cf6b2e7 ("block: move integrity information into queue_limits")
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/linux-raid/20250212171108.3483150-1-bvanassche@acm.org/
Signed-off-by: Yu Kuai <yukuai@kernel.org>
---
 drivers/md/raid0.c  | 4 +---
 drivers/md/raid1.c  | 4 +---
 drivers/md/raid10.c | 4 +---
 3 files changed, 3 insertions(+), 9 deletions(-)

diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 8fc9339b00c72..70bcc3cdf2cd1 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -386,10 +386,8 @@ static int raid0_set_limits(struct mddev *mddev)
 	lim.io_opt = lim.io_min * mddev->raid_disks;
 	lim.features |= BLK_FEAT_ATOMIC_WRITES;
 	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
-	if (err) {
-		queue_limits_cancel_update(mddev->gendisk->queue);
+	if (err)
 		return err;
-	}
 	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
 
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 9d57a88dbd261..10ea3af40991d 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -3219,10 +3219,8 @@ static int raid1_set_limits(struct mddev *mddev)
 	lim.max_write_zeroes_sectors = 0;
 	lim.features |= BLK_FEAT_ATOMIC_WRITES;
 	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
-	if (err) {
-		queue_limits_cancel_update(mddev->gendisk->queue);
+	if (err)
 		return err;
-	}
 	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
 
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index efe93b9791677..15b9ae5bf84d8 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -4020,10 +4020,8 @@ static int raid10_set_queue_limits(struct mddev *mddev)
 	lim.io_opt = lim.io_min * raid10_nr_stripes(conf);
 	lim.features |= BLK_FEAT_ATOMIC_WRITES;
 	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
-	if (err) {
-		queue_limits_cancel_update(mddev->gendisk->queue);
+	if (err)
 		return err;
-	}
 	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
 

From cd57e4327707126dca3f9517b84274c001d4c184 Mon Sep 17 00:00:00 2001
From: Pei Xiao <xiaopei01@kylinos.cn>
Date: Tue, 11 Feb 2025 10:29:48 +0800
Subject: [PATCH 0100/1173] phy: freescale: fsl-samsung-hdmi: Limit PLL lock
 detection clock divider to valid range
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

FIELD_PREP() checks that a value fits into the available bitfield,
but the index div equals to 4,is out of range.

which gcc complains about:
In function ‘fsl_samsung_hdmi_phy_configure_pll_lock_det’,
inlined from ‘fsl_samsung_hdmi_phy_configure’ at
drivers/phy/freescale/phy-fsl-samsung-hdmi.c :470:2:
././include/linux/compiler_types.h:542:38: error: call to ‘__compiletime_assert_538’
declared with attribute error: FIELD_PREP: value too large for the field
  542 |  _compiletime_assert(condition, msg, __compiletime_assert_,
__COUNTER__)
      |                                      ^
././include/linux/compiler_types.h:523:4: note: in definition of
macro ‘__compiletime_assert’ 523 |    prefix ## suffix();
      |    ^~~~~~
././include/linux/compiler_types.h:542:2: note: in expansion of macro
‘_compiletime_assert’
  542 |  _compiletime_assert(condition, msg, __compiletime_assert_,
 __COUNTER__)

REG12_CK_DIV_MASK only two bit, limit div to range 0~3,
so build error will fix.

Fixes: d567679f2b6a ("phy: freescale: fsl-samsung-hdmi: Clean up fld_tg_code calculation")
Signed-off-by: Pei Xiao <xiaopei01@kylinos.cn>

Changlog:

Reviewed-by: Adam Ford <aford173@gmail.com>
Link: https://lore.kernel.org/r/tencent_6F503D43467AA99DD8CC59B8F645F0725B0A@qq.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/freescale/phy-fsl-samsung-hdmi.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/phy/freescale/phy-fsl-samsung-hdmi.c b/drivers/phy/freescale/phy-fsl-samsung-hdmi.c
index 45004f598e4dc..e4c0a82d16d9e 100644
--- a/drivers/phy/freescale/phy-fsl-samsung-hdmi.c
+++ b/drivers/phy/freescale/phy-fsl-samsung-hdmi.c
@@ -325,7 +325,7 @@ to_fsl_samsung_hdmi_phy(struct clk_hw *hw)
 	return container_of(hw, struct fsl_samsung_hdmi_phy, hw);
 }
 
-static void
+static int
 fsl_samsung_hdmi_phy_configure_pll_lock_det(struct fsl_samsung_hdmi_phy *phy,
 					    const struct phy_config *cfg)
 {
@@ -341,6 +341,9 @@ fsl_samsung_hdmi_phy_configure_pll_lock_det(struct fsl_samsung_hdmi_phy *phy,
 			break;
 	}
 
+	if (unlikely(div == 4))
+		return -EINVAL;
+
 	writeb(FIELD_PREP(REG12_CK_DIV_MASK, div), phy->regs + PHY_REG(12));
 
 	/*
@@ -364,6 +367,8 @@ fsl_samsung_hdmi_phy_configure_pll_lock_det(struct fsl_samsung_hdmi_phy *phy,
 	       FIELD_PREP(REG14_RP_CODE_MASK, 2) |
 	       FIELD_PREP(REG14_TG_CODE_HIGH_MASK, fld_tg_code >> 8),
 	       phy->regs + PHY_REG(14));
+
+	return 0;
 }
 
 static unsigned long fsl_samsung_hdmi_phy_find_pms(unsigned long fout, u8 *p, u16 *m, u8 *s)
@@ -466,7 +471,11 @@ static int fsl_samsung_hdmi_phy_configure(struct fsl_samsung_hdmi_phy *phy,
 	writeb(REG21_SEL_TX_CK_INV | FIELD_PREP(REG21_PMS_S_MASK,
 	       cfg->pll_div_regs[2] >> 4), phy->regs + PHY_REG(21));
 
-	fsl_samsung_hdmi_phy_configure_pll_lock_det(phy, cfg);
+	ret = fsl_samsung_hdmi_phy_configure_pll_lock_det(phy, cfg);
+	if (ret) {
+		dev_err(phy->dev, "pixclock too large\n");
+		return ret;
+	}
 
 	writeb(REG33_FIX_DA | REG33_MODE_SET_DONE, phy->regs + PHY_REG(33));
 

From 89cb121e94612cd3bb3c74b0e772ead5b40b7a5d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Micka=C3=ABl=20Sala=C3=BCn?= <mic@digikod.net>
Date: Tue, 11 Feb 2025 14:25:28 +0100
Subject: [PATCH 0101/1173] selftests/landlock: Enable the new
 CONFIG_AF_UNIX_OOB
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since commit 5155cbcdbf03 ("af_unix: Add a prompt to
CONFIG_AF_UNIX_OOB"), the Landlock selftests's configuration is not
enough to build a minimal kernel.  Because scoped_signal_test checks
with the MSG_OOB flag, we need to enable CONFIG_AF_UNIX_OOB for tests:

 #  RUN           fown.no_sandbox.sigurg_socket ...
 # scoped_signal_test.c:420:sigurg_socket:Expected 1 (1) == send(client_socket, ".", 1, MSG_OOB) (-1)
 # sigurg_socket: Test terminated by assertion
 #          FAIL  fown.no_sandbox.sigurg_socket
 ...

Cc: Günther Noack <gnoack@google.com>
Acked-by: Florent Revest <revest@chromium.org>
Link: https://lore.kernel.org/r/20250211132531.1625566-1-mic@digikod.net
Signed-off-by: Mickaël Salaün <mic@digikod.net>
---
 tools/testing/selftests/landlock/config | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/landlock/config b/tools/testing/selftests/landlock/config
index 29af19c4e9f98..361f94f8cb0d4 100644
--- a/tools/testing/selftests/landlock/config
+++ b/tools/testing/selftests/landlock/config
@@ -1,3 +1,4 @@
+CONFIG_AF_UNIX_OOB=y
 CONFIG_CGROUPS=y
 CONFIG_CGROUP_SCHED=y
 CONFIG_INET=y

From 143c9aae043a1dc174a75be52521192a0caa224b Mon Sep 17 00:00:00 2001
From: Tanya Agarwal <tanyaagarwal25699@gmail.com>
Date: Fri, 24 Jan 2025 01:12:10 +0530
Subject: [PATCH 0102/1173] landlock: Fix grammar error
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix grammar error in comments that were identified using the codespell
tool.

Signed-off-by: Tanya Agarwal <tanyaagarwal25699@gmail.com>
Reviewed-by: Günther Noack <gnoack@google.com>
Link: https://lore.kernel.org/r/20250123194208.2660-1-tanyaagarwal25699@gmail.com
[mic: Simplify commit message]
Signed-off-by: Mickaël Salaün <mic@digikod.net>
---
 security/landlock/ruleset.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/security/landlock/ruleset.c b/security/landlock/ruleset.c
index 241ce44375b6a..bff4e40a3093c 100644
--- a/security/landlock/ruleset.c
+++ b/security/landlock/ruleset.c
@@ -124,7 +124,7 @@ create_rule(const struct landlock_id id,
 		return ERR_PTR(-ENOMEM);
 	RB_CLEAR_NODE(&new_rule->node);
 	if (is_object_pointer(id.type)) {
-		/* This should be catched by insert_rule(). */
+		/* This should have been caught by insert_rule(). */
 		WARN_ON_ONCE(!id.key.object);
 		landlock_get_object(id.key.object);
 	}

From 192b7ff29b1fb0335a9b9107991e6286f462f361 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?G=C3=BCnther=20Noack?= <gnoack@google.com>
Date: Fri, 24 Jan 2025 15:44:44 +0000
Subject: [PATCH 0103/1173] landlock: Minor typo and grammar fixes in IPC
 scoping documentation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

* Fix some whitespace, punctuation and minor grammar.
* Add a missing sentence about the minimum ABI version,
  to stay in line with the section next to it.

Cc: Tahera Fahimi <fahimitahera@gmail.com>
Cc: Tanya Agarwal <tanyaagarwal25699@gmail.com>
Signed-off-by: Günther Noack <gnoack@google.com>
Link: https://lore.kernel.org/r/20250124154445.162841-1-gnoack@google.com
[mic: Add newlines, update doc date]
Signed-off-by: Mickaël Salaün <mic@digikod.net>
---
 Documentation/userspace-api/landlock.rst | 6 +++---
 include/uapi/linux/landlock.h            | 8 ++++++--
 2 files changed, 9 insertions(+), 5 deletions(-)

diff --git a/Documentation/userspace-api/landlock.rst b/Documentation/userspace-api/landlock.rst
index d639c61cb472a..ad587f53fe417 100644
--- a/Documentation/userspace-api/landlock.rst
+++ b/Documentation/userspace-api/landlock.rst
@@ -8,7 +8,7 @@ Landlock: unprivileged access control
 =====================================
 
 :Author: Mickaël Salaün
-:Date: October 2024
+:Date: January 2025
 
 The goal of Landlock is to enable restriction of ambient rights (e.g. global
 filesystem or network access) for a set of processes.  Because Landlock
@@ -329,11 +329,11 @@ non-sandboxed process, we can specify this restriction with
 A sandboxed process can connect to a non-sandboxed process when its domain is
 not scoped. If a process's domain is scoped, it can only connect to sockets
 created by processes in the same scope.
-Moreover, If a process is scoped to send signal to a non-scoped process, it can
+Moreover, if a process is scoped to send signal to a non-scoped process, it can
 only send signals to processes in the same scope.
 
 A connected datagram socket behaves like a stream socket when its domain is
-scoped, meaning if the domain is scoped after the socket is connected , it can
+scoped, meaning if the domain is scoped after the socket is connected, it can
 still :manpage:`send(2)` data just like a stream socket.  However, in the same
 scenario, a non-connected datagram socket cannot send data (with
 :manpage:`sendto(2)`) outside its scope.
diff --git a/include/uapi/linux/landlock.h b/include/uapi/linux/landlock.h
index 33745642f7875..e1d2c27533b49 100644
--- a/include/uapi/linux/landlock.h
+++ b/include/uapi/linux/landlock.h
@@ -268,7 +268,9 @@ struct landlock_net_port_attr {
  * ~~~~~~~~~~~~~~~~
  *
  * These flags enable to restrict a sandboxed process to a set of network
- * actions. This is supported since the Landlock ABI version 4.
+ * actions.
+ *
+ * This is supported since Landlock ABI version 4.
  *
  * The following access rights apply to TCP port numbers:
  *
@@ -291,11 +293,13 @@ struct landlock_net_port_attr {
  * Setting a flag for a ruleset will isolate the Landlock domain to forbid
  * connections to resources outside the domain.
  *
+ * This is supported since Landlock ABI version 6.
+ *
  * Scopes:
  *
  * - %LANDLOCK_SCOPE_ABSTRACT_UNIX_SOCKET: Restrict a sandboxed process from
  *   connecting to an abstract UNIX socket created by a process outside the
- *   related Landlock domain (e.g. a parent domain or a non-sandboxed process).
+ *   related Landlock domain (e.g., a parent domain or a non-sandboxed process).
  * - %LANDLOCK_SCOPE_SIGNAL: Restrict a sandboxed process from sending a signal
  *   to another process outside the domain.
  */

From 854277e2cc8c75dc3c216c82e72523258fcf65b9 Mon Sep 17 00:00:00 2001
From: Mikhail Ivanov <ivanov.mikhail1@huawei-partners.com>
Date: Wed, 5 Feb 2025 17:36:49 +0800
Subject: [PATCH 0104/1173] landlock: Fix non-TCP sockets restriction
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use sk_is_tcp() to check if socket is TCP in bind(2) and connect(2)
hooks.

SMC, MPTCP, SCTP protocols are currently restricted by TCP access
rights.  The purpose of TCP access rights is to provide control over
ports that can be used by userland to establish a TCP connection.
Therefore, it is incorrect to deny bind(2) and connect(2) requests for a
socket of another protocol.

However, SMC, MPTCP and RDS implementations use TCP internal sockets to
establish communication or even to exchange packets over a TCP
connection [1]. Landlock rules that configure bind(2) and connect(2)
usage for TCP sockets should not cover requests for sockets of such
protocols. These protocols have different set of security issues and
security properties, therefore, it is necessary to provide the userland
with the ability to distinguish between them (eg. [2]).

Control over TCP connection used by other protocols can be achieved with
upcoming support of socket creation control [3].

[1] https://lore.kernel.org/all/62336067-18c2-3493-d0ec-6dd6a6d3a1b5@huawei-partners.com/
[2] https://lore.kernel.org/all/20241204.fahVio7eicim@digikod.net/
[3] https://lore.kernel.org/all/20240904104824.1844082-1-ivanov.mikhail1@huawei-partners.com/

Closes: https://github.com/landlock-lsm/linux/issues/40
Fixes: fff69fb03dde ("landlock: Support network rules with TCP bind and connect")
Signed-off-by: Mikhail Ivanov <ivanov.mikhail1@huawei-partners.com>
Link: https://lore.kernel.org/r/20250205093651.1424339-2-ivanov.mikhail1@huawei-partners.com
[mic: Format commit message to 72 columns]
Signed-off-by: Mickaël Salaün <mic@digikod.net>
---
 security/landlock/net.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/security/landlock/net.c b/security/landlock/net.c
index d5dcc4407a197..104b6c01fe503 100644
--- a/security/landlock/net.c
+++ b/security/landlock/net.c
@@ -63,8 +63,7 @@ static int current_check_access_socket(struct socket *const sock,
 	if (WARN_ON_ONCE(dom->num_layers < 1))
 		return -EACCES;
 
-	/* Checks if it's a (potential) TCP socket. */
-	if (sock->type != SOCK_STREAM)
+	if (!sk_is_tcp(sock->sk))
 		return 0;
 
 	/* Checks for minimal header length to safely read sa_family. */

From f5534d511bcd273720f168386de74af76e148a9b Mon Sep 17 00:00:00 2001
From: Mikhail Ivanov <ivanov.mikhail1@huawei-partners.com>
Date: Wed, 5 Feb 2025 17:36:50 +0800
Subject: [PATCH 0105/1173] selftests/landlock: Test TCP accesses with
 protocol=IPPROTO_TCP
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Extend protocol_variant structure with protocol field (Cf. socket(2)).

Extend protocol fixture with TCP test suits with protocol=IPPROTO_TCP
which can be used as an alias for IPPROTO_IP (=0) in socket(2).

Signed-off-by: Mikhail Ivanov <ivanov.mikhail1@huawei-partners.com>
Link: https://lore.kernel.org/r/20250205093651.1424339-3-ivanov.mikhail1@huawei-partners.com
Cc: <stable@vger.kernel.org> # 6.7.x
Signed-off-by: Mickaël Salaün <mic@digikod.net>
---
 tools/testing/selftests/landlock/common.h   |  1 +
 tools/testing/selftests/landlock/net_test.c | 80 +++++++++++++++++----
 2 files changed, 67 insertions(+), 14 deletions(-)

diff --git a/tools/testing/selftests/landlock/common.h b/tools/testing/selftests/landlock/common.h
index a604ea5d8297c..6064c9ac05329 100644
--- a/tools/testing/selftests/landlock/common.h
+++ b/tools/testing/selftests/landlock/common.h
@@ -207,6 +207,7 @@ enforce_ruleset(struct __test_metadata *const _metadata, const int ruleset_fd)
 struct protocol_variant {
 	int domain;
 	int type;
+	int protocol;
 };
 
 struct service_fixture {
diff --git a/tools/testing/selftests/landlock/net_test.c b/tools/testing/selftests/landlock/net_test.c
index 4e0aeb53b225a..333263780fae4 100644
--- a/tools/testing/selftests/landlock/net_test.c
+++ b/tools/testing/selftests/landlock/net_test.c
@@ -85,18 +85,18 @@ static void setup_loopback(struct __test_metadata *const _metadata)
 	clear_ambient_cap(_metadata, CAP_NET_ADMIN);
 }
 
+static bool prot_is_tcp(const struct protocol_variant *const prot)
+{
+	return (prot->domain == AF_INET || prot->domain == AF_INET6) &&
+	       prot->type == SOCK_STREAM &&
+	       (prot->protocol == IPPROTO_TCP || prot->protocol == IPPROTO_IP);
+}
+
 static bool is_restricted(const struct protocol_variant *const prot,
 			  const enum sandbox_type sandbox)
 {
-	switch (prot->domain) {
-	case AF_INET:
-	case AF_INET6:
-		switch (prot->type) {
-		case SOCK_STREAM:
-			return sandbox == TCP_SANDBOX;
-		}
-		break;
-	}
+	if (sandbox == TCP_SANDBOX)
+		return prot_is_tcp(prot);
 	return false;
 }
 
@@ -105,7 +105,7 @@ static int socket_variant(const struct service_fixture *const srv)
 	int ret;
 
 	ret = socket(srv->protocol.domain, srv->protocol.type | SOCK_CLOEXEC,
-		     0);
+		     srv->protocol.protocol);
 	if (ret < 0)
 		return -errno;
 	return ret;
@@ -290,22 +290,48 @@ FIXTURE_TEARDOWN(protocol)
 }
 
 /* clang-format off */
-FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_ipv4_tcp) {
+FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_ipv4_tcp1) {
 	/* clang-format on */
 	.sandbox = NO_SANDBOX,
 	.prot = {
 		.domain = AF_INET,
 		.type = SOCK_STREAM,
+		/* IPPROTO_IP == 0 */
+		.protocol = IPPROTO_IP,
 	},
 };
 
 /* clang-format off */
-FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_ipv6_tcp) {
+FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_ipv4_tcp2) {
+	/* clang-format on */
+	.sandbox = NO_SANDBOX,
+	.prot = {
+		.domain = AF_INET,
+		.type = SOCK_STREAM,
+		.protocol = IPPROTO_TCP,
+	},
+};
+
+/* clang-format off */
+FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_ipv6_tcp1) {
 	/* clang-format on */
 	.sandbox = NO_SANDBOX,
 	.prot = {
 		.domain = AF_INET6,
 		.type = SOCK_STREAM,
+		/* IPPROTO_IP == 0 */
+		.protocol = IPPROTO_IP,
+	},
+};
+
+/* clang-format off */
+FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_ipv6_tcp2) {
+	/* clang-format on */
+	.sandbox = NO_SANDBOX,
+	.prot = {
+		.domain = AF_INET6,
+		.type = SOCK_STREAM,
+		.protocol = IPPROTO_TCP,
 	},
 };
 
@@ -350,22 +376,48 @@ FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_unix_datagram) {
 };
 
 /* clang-format off */
-FIXTURE_VARIANT_ADD(protocol, tcp_sandbox_with_ipv4_tcp) {
+FIXTURE_VARIANT_ADD(protocol, tcp_sandbox_with_ipv4_tcp1) {
+	/* clang-format on */
+	.sandbox = TCP_SANDBOX,
+	.prot = {
+		.domain = AF_INET,
+		.type = SOCK_STREAM,
+		/* IPPROTO_IP == 0 */
+		.protocol = IPPROTO_IP,
+	},
+};
+
+/* clang-format off */
+FIXTURE_VARIANT_ADD(protocol, tcp_sandbox_with_ipv4_tcp2) {
 	/* clang-format on */
 	.sandbox = TCP_SANDBOX,
 	.prot = {
 		.domain = AF_INET,
 		.type = SOCK_STREAM,
+		.protocol = IPPROTO_TCP,
+	},
+};
+
+/* clang-format off */
+FIXTURE_VARIANT_ADD(protocol, tcp_sandbox_with_ipv6_tcp1) {
+	/* clang-format on */
+	.sandbox = TCP_SANDBOX,
+	.prot = {
+		.domain = AF_INET6,
+		.type = SOCK_STREAM,
+		/* IPPROTO_IP == 0 */
+		.protocol = IPPROTO_IP,
 	},
 };
 
 /* clang-format off */
-FIXTURE_VARIANT_ADD(protocol, tcp_sandbox_with_ipv6_tcp) {
+FIXTURE_VARIANT_ADD(protocol, tcp_sandbox_with_ipv6_tcp2) {
 	/* clang-format on */
 	.sandbox = TCP_SANDBOX,
 	.prot = {
 		.domain = AF_INET6,
 		.type = SOCK_STREAM,
+		.protocol = IPPROTO_TCP,
 	},
 };
 

From 3d4033985ff508ef587ca11f1c8361ba57c7e09f Mon Sep 17 00:00:00 2001
From: Mikhail Ivanov <ivanov.mikhail1@huawei-partners.com>
Date: Wed, 5 Feb 2025 17:36:51 +0800
Subject: [PATCH 0106/1173] selftests/landlock: Test that MPTCP actions are not
 restricted
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Extend protocol fixture with test suits for MPTCP protocol.
Add CONFIG_MPTCP and CONFIG_MPTCP_IPV6 options in config.

Signed-off-by: Mikhail Ivanov <ivanov.mikhail1@huawei-partners.com>
Link: https://lore.kernel.org/r/20250205093651.1424339-4-ivanov.mikhail1@huawei-partners.com
Cc: <stable@vger.kernel.org> # 6.7.x
Signed-off-by: Mickaël Salaün <mic@digikod.net>
---
 tools/testing/selftests/landlock/config     |  2 +
 tools/testing/selftests/landlock/net_test.c | 44 +++++++++++++++++++++
 2 files changed, 46 insertions(+)

diff --git a/tools/testing/selftests/landlock/config b/tools/testing/selftests/landlock/config
index 361f94f8cb0d4..425de4c20271c 100644
--- a/tools/testing/selftests/landlock/config
+++ b/tools/testing/selftests/landlock/config
@@ -4,6 +4,8 @@ CONFIG_CGROUP_SCHED=y
 CONFIG_INET=y
 CONFIG_IPV6=y
 CONFIG_KEYS=y
+CONFIG_MPTCP=y
+CONFIG_MPTCP_IPV6=y
 CONFIG_NET=y
 CONFIG_NET_NS=y
 CONFIG_OVERLAY_FS=y
diff --git a/tools/testing/selftests/landlock/net_test.c b/tools/testing/selftests/landlock/net_test.c
index 333263780fae4..d9de0ee49ebc2 100644
--- a/tools/testing/selftests/landlock/net_test.c
+++ b/tools/testing/selftests/landlock/net_test.c
@@ -312,6 +312,17 @@ FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_ipv4_tcp2) {
 	},
 };
 
+/* clang-format off */
+FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_ipv4_mptcp) {
+	/* clang-format on */
+	.sandbox = NO_SANDBOX,
+	.prot = {
+		.domain = AF_INET,
+		.type = SOCK_STREAM,
+		.protocol = IPPROTO_MPTCP,
+	},
+};
+
 /* clang-format off */
 FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_ipv6_tcp1) {
 	/* clang-format on */
@@ -335,6 +346,17 @@ FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_ipv6_tcp2) {
 	},
 };
 
+/* clang-format off */
+FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_ipv6_mptcp) {
+	/* clang-format on */
+	.sandbox = NO_SANDBOX,
+	.prot = {
+		.domain = AF_INET6,
+		.type = SOCK_STREAM,
+		.protocol = IPPROTO_MPTCP,
+	},
+};
+
 /* clang-format off */
 FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_ipv4_udp) {
 	/* clang-format on */
@@ -398,6 +420,17 @@ FIXTURE_VARIANT_ADD(protocol, tcp_sandbox_with_ipv4_tcp2) {
 	},
 };
 
+/* clang-format off */
+FIXTURE_VARIANT_ADD(protocol, tcp_sandbox_with_ipv4_mptcp) {
+	/* clang-format on */
+	.sandbox = TCP_SANDBOX,
+	.prot = {
+		.domain = AF_INET,
+		.type = SOCK_STREAM,
+		.protocol = IPPROTO_MPTCP,
+	},
+};
+
 /* clang-format off */
 FIXTURE_VARIANT_ADD(protocol, tcp_sandbox_with_ipv6_tcp1) {
 	/* clang-format on */
@@ -421,6 +454,17 @@ FIXTURE_VARIANT_ADD(protocol, tcp_sandbox_with_ipv6_tcp2) {
 	},
 };
 
+/* clang-format off */
+FIXTURE_VARIANT_ADD(protocol, tcp_sandbox_with_ipv6_mptcp) {
+	/* clang-format on */
+	.sandbox = TCP_SANDBOX,
+	.prot = {
+		.domain = AF_INET6,
+		.type = SOCK_STREAM,
+		.protocol = IPPROTO_MPTCP,
+	},
+};
+
 /* clang-format off */
 FIXTURE_VARIANT_ADD(protocol, tcp_sandbox_with_ipv4_udp) {
 	/* clang-format on */

From 78332fdb956f18accfbca5993b10c5ed69f00a2c Mon Sep 17 00:00:00 2001
From: Bharadwaj Raju <bharadwaj.raju777@gmail.com>
Date: Mon, 10 Feb 2025 21:40:57 +0530
Subject: [PATCH 0107/1173] selftests/landlock: Add binaries to .gitignore
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Building the test creates binaries 'wait-pipe' and
'sandbox-and-launch' which need to be gitignore'd.

Signed-off-by: Bharadwaj Raju <bharadwaj.raju777@gmail.com>
Link: https://lore.kernel.org/r/20250210161101.6024-1-bharadwaj.raju777@gmail.com
[mic: Sort entries]
Signed-off-by: Mickaël Salaün <mic@digikod.net>
---
 tools/testing/selftests/landlock/.gitignore | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/testing/selftests/landlock/.gitignore b/tools/testing/selftests/landlock/.gitignore
index 470203a7cd737..335b2b1a3463a 100644
--- a/tools/testing/selftests/landlock/.gitignore
+++ b/tools/testing/selftests/landlock/.gitignore
@@ -1,2 +1,4 @@
 /*_test
+/sandbox-and-launch
 /true
+/wait-pipe

From f553741ac8c0e467a3b873e305f34b902e50b86d Mon Sep 17 00:00:00 2001
From: zihan zhou <15645113830zzh@gmail.com>
Date: Sat, 8 Feb 2025 16:08:52 +0800
Subject: [PATCH 0108/1173] sched: Cancel the slice protection of the idle
 entity

A wakeup non-idle entity should preempt idle entity at any time,
but because of the slice protection of the idle entity, the non-idle
entity has to wait, so just cancel it.

This patch is aimed at minimizing the impact of SCHED_IDLE on
SCHED_NORMAL. For example, a task with SCHED_IDLE policy that sleeps for
1s and then runs for 3 ms, running cyclictest on the same cpu, has a
maximum latency of 3 ms, which is caused by the slice protection of the
idle entity. It is unreasonable. With this patch, the cyclictest latency
under the same conditions is basically the same on the cpu with idle
processes and on empty cpu.

[peterz: add helpers]
Fixes: 63304558ba5d ("sched/eevdf: Curb wakeup-preemption")
Signed-off-by: zihan zhou <15645113830zzh@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Tested-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20250208080850.16300-1-15645113830zzh@gmail.com
---
 kernel/sched/fair.c | 46 ++++++++++++++++++++++++++++++++-------------
 1 file changed, 33 insertions(+), 13 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1c0ef435a7aae..61b826fa06805 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -883,6 +883,26 @@ struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
 	return __node_2_se(left);
 }
 
+/*
+ * HACK, stash a copy of deadline at the point of pick in vlag,
+ * which isn't used until dequeue.
+ */
+static inline void set_protect_slice(struct sched_entity *se)
+{
+	se->vlag = se->deadline;
+}
+
+static inline bool protect_slice(struct sched_entity *se)
+{
+	return se->vlag == se->deadline;
+}
+
+static inline void cancel_protect_slice(struct sched_entity *se)
+{
+	if (protect_slice(se))
+		se->vlag = se->deadline + 1;
+}
+
 /*
  * Earliest Eligible Virtual Deadline First
  *
@@ -919,11 +939,7 @@ static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
 	if (curr && (!curr->on_rq || !entity_eligible(cfs_rq, curr)))
 		curr = NULL;
 
-	/*
-	 * Once selected, run a task until it either becomes non-eligible or
-	 * until it gets a new slice. See the HACK in set_next_entity().
-	 */
-	if (sched_feat(RUN_TO_PARITY) && curr && curr->vlag == curr->deadline)
+	if (sched_feat(RUN_TO_PARITY) && curr && protect_slice(curr))
 		return curr;
 
 	/* Pick the leftmost entity if it's eligible */
@@ -5528,11 +5544,8 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		update_stats_wait_end_fair(cfs_rq, se);
 		__dequeue_entity(cfs_rq, se);
 		update_load_avg(cfs_rq, se, UPDATE_TG);
-		/*
-		 * HACK, stash a copy of deadline at the point of pick in vlag,
-		 * which isn't used until dequeue.
-		 */
-		se->vlag = se->deadline;
+
+		set_protect_slice(se);
 	}
 
 	update_stats_curr_start(cfs_rq, se);
@@ -8781,8 +8794,15 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int
 	 * Preempt an idle entity in favor of a non-idle entity (and don't preempt
 	 * in the inverse case).
 	 */
-	if (cse_is_idle && !pse_is_idle)
+	if (cse_is_idle && !pse_is_idle) {
+		/*
+		 * When non-idle entity preempt an idle entity,
+		 * don't give idle entity slice protection.
+		 */
+		cancel_protect_slice(se);
 		goto preempt;
+	}
+
 	if (cse_is_idle != pse_is_idle)
 		return;
 
@@ -8801,8 +8821,8 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int
 	 * Note that even if @p does not turn out to be the most eligible
 	 * task at this moment, current's slice protection will be lost.
 	 */
-	if (do_preempt_short(cfs_rq, pse, se) && se->vlag == se->deadline)
-		se->vlag = se->deadline + 1;
+	if (do_preempt_short(cfs_rq, pse, se))
+		cancel_protect_slice(se);
 
 	/*
 	 * If @p has become the most eligible task, force preemption.

From 2ae891b826958b60919ea21c727f77bcd6ffcc2c Mon Sep 17 00:00:00 2001
From: zihan zhou <15645113830zzh@gmail.com>
Date: Sat, 8 Feb 2025 15:53:23 +0800
Subject: [PATCH 0109/1173] sched: Reduce the default slice to avoid tasks
 getting an extra tick

The old default value for slice is 0.75 msec * (1 + ilog(ncpus)) which
means that we have a default slice of:

  0.75 for 1 cpu
  1.50 up to 3 cpus
  2.25 up to 7 cpus
  3.00 for 8 cpus and above.

For HZ=250 and HZ=100, because of the tick accuracy, the runtime of
tasks is far higher than their slice.

For HZ=1000 with 8 cpus or more, the accuracy of tick is already
satisfactory, but there is still an issue that tasks will get an extra
tick because the tick often arrives a little faster than expected. In
this case, the task can only wait until the next tick to consider that it
has reached its deadline, and will run 1ms longer.

vruntime + sysctl_sched_base_slice =     deadline
        |-----------|-----------|-----------|-----------|
             1ms          1ms         1ms         1ms
                   ^           ^           ^           ^
                 tick1       tick2       tick3       tick4(nearly 4ms)

There are two reasons for tick error: clockevent precision and the
CONFIG_IRQ_TIME_ACCOUNTING/CONFIG_PARAVIRT_TIME_ACCOUNTING. with
CONFIG_IRQ_TIME_ACCOUNTING every tick will be less than 1ms, but even
without it, because of clockevent precision, tick still often less than
1ms.

In order to make scheduling more precise, we changed 0.75 to 0.70,
Using 0.70 instead of 0.75 should not change much for other configs
and would fix this issue:

  0.70 for 1 cpu
  1.40 up to 3 cpus
  2.10 up to 7 cpus
  2.8 for 8 cpus and above.

This does not guarantee that tasks can run the slice time accurately
every time, but occasionally running an extra tick has little impact.

Signed-off-by: zihan zhou <15645113830zzh@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20250208075322.13139-1-15645113830zzh@gmail.com
---
 kernel/sched/fair.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 61b826fa06805..17847527aa202 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -74,10 +74,10 @@ unsigned int sysctl_sched_tunable_scaling = SCHED_TUNABLESCALING_LOG;
 /*
  * Minimal preemption granularity for CPU-bound tasks:
  *
- * (default: 0.75 msec * (1 + ilog(ncpus)), units: nanoseconds)
+ * (default: 0.70 msec * (1 + ilog(ncpus)), units: nanoseconds)
  */
-unsigned int sysctl_sched_base_slice			= 750000ULL;
-static unsigned int normalized_sysctl_sched_base_slice	= 750000ULL;
+unsigned int sysctl_sched_base_slice			= 700000ULL;
+static unsigned int normalized_sysctl_sched_base_slice	= 700000ULL;
 
 const_debug unsigned int sysctl_sched_migration_cost	= 500000UL;
 

From b9f2b29b94943b08157e3dfc970baabc7944dbc3 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Wed, 5 Feb 2025 11:24:38 +0800
Subject: [PATCH 0110/1173] sched: Don't define sched_clock_irqtime as static
 key
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The sched_clock_irqtime was defined as a static key in commit 8722903cbb8f
('sched: Define sched_clock_irqtime as static key'). However, this change
introduces a 'sleeping in atomic context' warning, as shown below:

	arch/x86/kernel/tsc.c:1214 mark_tsc_unstable()
	warn: sleeping in atomic context

As analyzed by Dan, the affected code path is as follows:

vcpu_load() <- disables preempt
-> kvm_arch_vcpu_load()
   -> mark_tsc_unstable() <- sleeps

virt/kvm/kvm_main.c
   166  void vcpu_load(struct kvm_vcpu *vcpu)
   167  {
   168          int cpu = get_cpu();
                          ^^^^^^^^^^
This get_cpu() disables preemption.

   169
   170          __this_cpu_write(kvm_running_vcpu, vcpu);
   171          preempt_notifier_register(&vcpu->preempt_notifier);
   172          kvm_arch_vcpu_load(vcpu, cpu);
   173          put_cpu();
   174  }

arch/x86/kvm/x86.c
  4979          if (unlikely(vcpu->cpu != cpu) || kvm_check_tsc_unstable()) {
  4980                  s64 tsc_delta = !vcpu->arch.last_host_tsc ? 0 :
  4981                                  rdtsc() - vcpu->arch.last_host_tsc;
  4982                  if (tsc_delta < 0)
  4983                          mark_tsc_unstable("KVM discovered backwards TSC");

arch/x86/kernel/tsc.c
    1206 void mark_tsc_unstable(char *reason)
    1207 {
    1208         if (tsc_unstable)
    1209                 return;
    1210
    1211         tsc_unstable = 1;
    1212         if (using_native_sched_clock())
    1213                 clear_sched_clock_stable();
--> 1214         disable_sched_clock_irqtime();
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
kernel/jump_label.c
   245  void static_key_disable(struct static_key *key)
   246  {
   247          cpus_read_lock();
                ^^^^^^^^^^^^^^^^
This lock has a might_sleep() in it which triggers the static checker
warning.

   248          static_key_disable_cpuslocked(key);
   249          cpus_read_unlock();
   250  }

Let revert this change for now as {disable,enable}_sched_clock_irqtime
are used in many places, as pointed out by Sean, including the following:

The code path in clocksource_watchdog():

  clocksource_watchdog()
  |
  -> spin_lock(&watchdog_lock);
     |
     -> __clocksource_unstable()
        |
        -> clocksource.mark_unstable() == tsc_cs_mark_unstable()
           |
           -> disable_sched_clock_irqtime()

And the code path in sched_clock_register():

	/* Cannot register a sched_clock with interrupts on */
	local_irq_save(flags);

	...

	/* Enable IRQ time accounting if we have a fast enough sched_clock() */
	if (irqtime > 0 || (irqtime == -1 && rate >= 1000000))
		enable_sched_clock_irqtime();

	local_irq_restore(flags);

[lkp@intel.com: reported a build error in the prev version]

Closes: https://lore.kernel.org/kvm/37a79ba3-9ce0-479c-a5b0-2bd75d573ed3@stanley.mountain/
Fixes: 8722903cbb8f ("sched: Define sched_clock_irqtime as static key")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Debugged-by: Dan Carpenter <dan.carpenter@linaro.org>
Debugged-by: Sean Christopherson <seanjc@google.com>
Debugged-by: Michal Koutný <mkoutny@suse.com>
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20250205032438.14668-1-laoar.shao@gmail.com
---
 kernel/sched/cputime.c | 8 ++++----
 kernel/sched/sched.h   | 4 ++--
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 5d9143dd08791..6dab4854c6c08 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -9,8 +9,6 @@
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
 
-DEFINE_STATIC_KEY_FALSE(sched_clock_irqtime);
-
 /*
  * There are no locks covering percpu hardirq/softirq time.
  * They are only modified in vtime_account, on corresponding CPU
@@ -24,14 +22,16 @@ DEFINE_STATIC_KEY_FALSE(sched_clock_irqtime);
  */
 DEFINE_PER_CPU(struct irqtime, cpu_irqtime);
 
+int sched_clock_irqtime;
+
 void enable_sched_clock_irqtime(void)
 {
-	static_branch_enable(&sched_clock_irqtime);
+	sched_clock_irqtime = 1;
 }
 
 void disable_sched_clock_irqtime(void)
 {
-	static_branch_disable(&sched_clock_irqtime);
+	sched_clock_irqtime = 0;
 }
 
 static void irqtime_account_delta(struct irqtime *irqtime, u64 delta,
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 38e0e323dda26..ab16d3d0e51cd 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -3259,11 +3259,11 @@ struct irqtime {
 };
 
 DECLARE_PER_CPU(struct irqtime, cpu_irqtime);
-DECLARE_STATIC_KEY_FALSE(sched_clock_irqtime);
+extern int sched_clock_irqtime;
 
 static inline int irqtime_enabled(void)
 {
-	return static_branch_likely(&sched_clock_irqtime);
+	return sched_clock_irqtime;
 }
 
 /*

From 563bc2161b94571ea425bbe2cf69fd38e24cdedf Mon Sep 17 00:00:00 2001
From: Tianchen Ding <dtcccc@linux.alibaba.com>
Date: Tue, 11 Feb 2025 14:36:59 +0800
Subject: [PATCH 0111/1173] sched/eevdf: Force propagating min_slice of cfs_rq
 when {en,de}queue tasks

When a task is enqueued and its parent cgroup se is already on_rq, this
parent cgroup se will not be enqueued again, and hence the root->min_slice
leaves unchanged. The same issue happens when a task is dequeued and its
parent cgroup se has other runnable entities, and the parent cgroup se
will not be dequeued.

Force propagating min_slice when se doesn't need to be enqueued or
dequeued. Ensure the se hierarchy always get the latest min_slice.

Fixes: aef6987d8954 ("sched/eevdf: Propagate min_slice up the cgroup hierarchy")
Signed-off-by: Tianchen Ding <dtcccc@linux.alibaba.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250211063659.7180-1-dtcccc@linux.alibaba.com
---
 kernel/sched/fair.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 17847527aa202..9279bfb740406 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7002,6 +7002,8 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		update_cfs_group(se);
 
 		se->slice = slice;
+		if (se != cfs_rq->curr)
+			min_vruntime_cb_propagate(&se->run_node, NULL);
 		slice = cfs_rq_min_slice(cfs_rq);
 
 		cfs_rq->h_nr_runnable += h_nr_runnable;
@@ -7131,6 +7133,8 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 		update_cfs_group(se);
 
 		se->slice = slice;
+		if (se != cfs_rq->curr)
+			min_vruntime_cb_propagate(&se->run_node, NULL);
 		slice = cfs_rq_min_slice(cfs_rq);
 
 		cfs_rq->h_nr_runnable -= h_nr_runnable;

From d34e798094ca7be935b629a42f8b237d4d5b7f1d Mon Sep 17 00:00:00 2001
From: I Hsin Cheng <richard120310@gmail.com>
Date: Mon, 10 Feb 2025 18:30:18 +0800
Subject: [PATCH 0112/1173] sched/fair: Refactor can_migrate_task() to elimate
 looping

The function "can_migrate_task()" utilize "for_each_cpu_and" with a
"if" statement inside to find the destination cpu. It's the same logic
to find the first set bit of the result of the bitwise-AND of
"env->dst_grpmask", "env->cpus" and "p->cpus_ptr".

Refactor it by using "cpumask_first_and_and()" to perform bitwise-AND
for "env->dst_grpmask", "env->cpus" and "p->cpus_ptr" and pick the
first cpu within the intersection as the destination cpu, so we can
elimate the need of looping and multiple times of branch.

After the refactoring this part of the code can speed up from ~115ns
to ~54ns, according to the test below.

Ran the test for 5 times and the result is showned in the following
table, and the test script is paste in next section.

  -------------------------------------------------------
  |Old method|  130|  118|  115|  109|  106|  avg ~115ns|
  -------------------------------------------------------
  |New method|   58|   55|   54|   48|   55|  avg  ~54ns|
  -------------------------------------------------------

Signed-off-by: I Hsin Cheng <richard120310@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250210103019.283824-1-richard120310@gmail.com
---
 kernel/sched/fair.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 9279bfb740406..857808da23d84 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -9439,12 +9439,11 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 			return 0;
 
 		/* Prevent to re-select dst_cpu via env's CPUs: */
-		for_each_cpu_and(cpu, env->dst_grpmask, env->cpus) {
-			if (cpumask_test_cpu(cpu, p->cpus_ptr)) {
-				env->flags |= LBF_DST_PINNED;
-				env->new_dst_cpu = cpu;
-				break;
-			}
+		cpu = cpumask_first_and_and(env->dst_grpmask, env->cpus, p->cpus_ptr);
+
+		if (cpu < nr_cpu_ids) {
+			env->flags |= LBF_DST_PINNED;
+			env->new_dst_cpu = cpu;
 		}
 
 		return 0;

From 1623ced247f7cb1b48a27cca6b0f17fe5ab5942b Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 10 Feb 2025 21:34:12 +0200
Subject: [PATCH 0113/1173] x86/events/amd/iommu: Increase IOMMU_NAME_SIZE
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The init_one_iommu() takes an unsigned int argument that can't be checked for
the boundaries at compile time and GCC complains about that when build with
`make W=1`:

arch/x86/events/amd/iommu.c:441:53: note: directive argument in the range [0, 4294967294]
arch/x86/events/amd/iommu.c:441:9: note: ‘snprintf’ output between 12 and 21 bytes into a destination of size 16

Increase the size to cover all possible cases.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250210193412.483233-1-andriy.shevchenko@linux.intel.com
---
 arch/x86/events/amd/iommu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/events/amd/iommu.c b/arch/x86/events/amd/iommu.c
index b15f7b950d2e0..f8228d8243f7d 100644
--- a/arch/x86/events/amd/iommu.c
+++ b/arch/x86/events/amd/iommu.c
@@ -30,7 +30,7 @@
 #define GET_DOMID_MASK(x)  (((x)->conf1 >> 16) & 0xFFFFULL)
 #define GET_PASID_MASK(x)  (((x)->conf1 >> 32) & 0xFFFFFULL)
 
-#define IOMMU_NAME_SIZE 16
+#define IOMMU_NAME_SIZE 24
 
 struct perf_amd_iommu {
 	struct list_head list;

From 675204778c69c2b3e0f6a4e2dbfeb4f3e89194ba Mon Sep 17 00:00:00 2001
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Date: Fri, 14 Feb 2025 10:45:31 +0200
Subject: [PATCH 0114/1173] module: don't annotate ROX memory as
 kmemleak_not_leak()

The ROX memory allocations are part of a larger vmalloc allocation and
annotating them with kmemleak_not_leak() confuses kmemleak.

Skip kmemleak_not_leak() annotations for the ROX areas.

Fixes: c287c0723329 ("module: switch to execmem API for remapping as RW and restoring ROX")
Fixes: 64f6a4e10c05 ("x86: re-enable EXECMEM_ROX support")
Reported-by: "Borah, Chaitanya Kumar" <chaitanya.kumar.borah@intel.com>
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250214084531.3299390-1-rppt@kernel.org
---
 kernel/module/main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/module/main.c b/kernel/module/main.c
index 5c127bedd3f07..a256cc919ad74 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -1260,7 +1260,8 @@ static int module_memory_alloc(struct module *mod, enum mod_mem_type type)
 	 * *do* eventually get freed, but let's just keep things simple
 	 * and avoid *any* false positives.
 	 */
-	kmemleak_not_leak(ptr);
+	if (!mod->mem[type].is_rox)
+		kmemleak_not_leak(ptr);
 
 	memset(ptr, 0, size);
 	mod->mem[type].base = ptr;

From 72e213a7ccf9dc78a85eecee8dc8170762ed876c Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 7 Feb 2025 13:15:31 +0100
Subject: [PATCH 0115/1173] x86/ibt: Clean up is_endbr()

Pretty much every caller of is_endbr() actually wants to test something at an
address and ends up doing get_kernel_nofault(). Fold the lot into a more
convenient helper.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Link: https://lore.kernel.org/r/20250207122546.181367417@infradead.org
---
 arch/x86/events/core.c         |  2 +-
 arch/x86/include/asm/ftrace.h  | 16 ++--------------
 arch/x86/include/asm/ibt.h     |  5 +++--
 arch/x86/kernel/alternative.c  | 20 ++++++++++++++------
 arch/x86/kernel/kprobes/core.c | 11 +----------
 arch/x86/net/bpf_jit_comp.c    |  4 ++--
 kernel/trace/bpf_trace.c       | 21 ++++-----------------
 7 files changed, 27 insertions(+), 52 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 8f218ac0d445c..ff4e84a514c64 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2844,7 +2844,7 @@ static bool is_uprobe_at_func_entry(struct pt_regs *regs)
 		return true;
 
 	/* endbr64 (64-bit only) */
-	if (user_64bit_mode(regs) && is_endbr(*(u32 *)auprobe->insn))
+	if (user_64bit_mode(regs) && is_endbr((u32 *)auprobe->insn))
 		return true;
 
 	return false;
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index f9cb4d07df58f..f2265246249ad 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -36,21 +36,9 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
 
 static inline unsigned long arch_ftrace_get_symaddr(unsigned long fentry_ip)
 {
-#ifdef CONFIG_X86_KERNEL_IBT
-	u32 instr;
-
-	/* We want to be extra safe in case entry ip is on the page edge,
-	 * but otherwise we need to avoid get_kernel_nofault()'s overhead.
-	 */
-	if ((fentry_ip & ~PAGE_MASK) < ENDBR_INSN_SIZE) {
-		if (get_kernel_nofault(instr, (u32 *)(fentry_ip - ENDBR_INSN_SIZE)))
-			return fentry_ip;
-	} else {
-		instr = *(u32 *)(fentry_ip - ENDBR_INSN_SIZE);
-	}
-	if (is_endbr(instr))
+	if (is_endbr((void*)(fentry_ip - ENDBR_INSN_SIZE)))
 		fentry_ip -= ENDBR_INSN_SIZE;
-#endif
+
 	return fentry_ip;
 }
 #define ftrace_get_symaddr(fentry_ip)	arch_ftrace_get_symaddr(fentry_ip)
diff --git a/arch/x86/include/asm/ibt.h b/arch/x86/include/asm/ibt.h
index 1e59581d500ca..d955e0d1cbf15 100644
--- a/arch/x86/include/asm/ibt.h
+++ b/arch/x86/include/asm/ibt.h
@@ -65,7 +65,7 @@ static inline __attribute_const__ u32 gen_endbr_poison(void)
 	return 0x001f0f66; /* osp nopl (%rax) */
 }
 
-static inline bool is_endbr(u32 val)
+static inline bool __is_endbr(u32 val)
 {
 	if (val == gen_endbr_poison())
 		return true;
@@ -74,6 +74,7 @@ static inline bool is_endbr(u32 val)
 	return val == gen_endbr();
 }
 
+extern __noendbr bool is_endbr(u32 *val);
 extern __noendbr u64 ibt_save(bool disable);
 extern __noendbr void ibt_restore(u64 save);
 
@@ -98,7 +99,7 @@ extern __noendbr void ibt_restore(u64 save);
 
 #define __noendbr
 
-static inline bool is_endbr(u32 val) { return false; }
+static inline bool is_endbr(u32 *val) { return false; }
 
 static inline u64 ibt_save(bool disable) { return 0; }
 static inline void ibt_restore(u64 save) { }
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 8b66a555d2f03..9a252bb0d34b8 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -852,16 +852,24 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end) { }
 
 #ifdef CONFIG_X86_KERNEL_IBT
 
+__noendbr bool is_endbr(u32 *val)
+{
+	u32 endbr;
+
+	__get_kernel_nofault(&endbr, val, u32, Efault);
+	return __is_endbr(endbr);
+
+Efault:
+	return false;
+}
+
 static void poison_cfi(void *addr);
 
 static void __init_or_module poison_endbr(void *addr, bool warn)
 {
-	u32 endbr, poison = gen_endbr_poison();
-
-	if (WARN_ON_ONCE(get_kernel_nofault(endbr, addr)))
-		return;
+	u32 poison = gen_endbr_poison();
 
-	if (!is_endbr(endbr)) {
+	if (!is_endbr(addr)) {
 		WARN_ON_ONCE(warn);
 		return;
 	}
@@ -988,7 +996,7 @@ static u32  cfi_seed __ro_after_init;
 static u32 cfi_rehash(u32 hash)
 {
 	hash ^= cfi_seed;
-	while (unlikely(is_endbr(hash) || is_endbr(-hash))) {
+	while (unlikely(__is_endbr(hash) || __is_endbr(-hash))) {
 		bool lsb = hash & 1;
 		hash >>= 1;
 		if (lsb)
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 72e6a45e7ec24..09608fd936876 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -373,16 +373,7 @@ static bool can_probe(unsigned long paddr)
 kprobe_opcode_t *arch_adjust_kprobe_addr(unsigned long addr, unsigned long offset,
 					 bool *on_func_entry)
 {
-	u32 insn;
-
-	/*
-	 * Since 'addr' is not guaranteed to be safe to access, use
-	 * copy_from_kernel_nofault() to read the instruction:
-	 */
-	if (copy_from_kernel_nofault(&insn, (void *)addr, sizeof(u32)))
-		return NULL;
-
-	if (is_endbr(insn)) {
+	if (is_endbr((u32 *)addr)) {
 		*on_func_entry = !offset || offset == 4;
 		if (*on_func_entry)
 			offset = 4;
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index a43fc5af973d2..f36508b67278a 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -641,7 +641,7 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 	 * See emit_prologue(), for IBT builds the trampoline hook is preceded
 	 * with an ENDBR instruction.
 	 */
-	if (is_endbr(*(u32 *)ip))
+	if (is_endbr(ip))
 		ip += ENDBR_INSN_SIZE;
 
 	return __bpf_arch_text_poke(ip, t, old_addr, new_addr);
@@ -3036,7 +3036,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 		/* skip patched call instruction and point orig_call to actual
 		 * body of the kernel function.
 		 */
-		if (is_endbr(*(u32 *)orig_call))
+		if (is_endbr(orig_call))
 			orig_call += ENDBR_INSN_SIZE;
 		orig_call += X86_PATCH_SIZE;
 	}
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index adc947587eb81..997fb2a47c921 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1038,27 +1038,14 @@ static const struct bpf_func_proto bpf_get_func_ip_proto_tracing = {
 	.arg1_type	= ARG_PTR_TO_CTX,
 };
 
-#ifdef CONFIG_X86_KERNEL_IBT
-static unsigned long get_entry_ip(unsigned long fentry_ip)
+static inline unsigned long get_entry_ip(unsigned long fentry_ip)
 {
-	u32 instr;
-
-	/* We want to be extra safe in case entry ip is on the page edge,
-	 * but otherwise we need to avoid get_kernel_nofault()'s overhead.
-	 */
-	if ((fentry_ip & ~PAGE_MASK) < ENDBR_INSN_SIZE) {
-		if (get_kernel_nofault(instr, (u32 *)(fentry_ip - ENDBR_INSN_SIZE)))
-			return fentry_ip;
-	} else {
-		instr = *(u32 *)(fentry_ip - ENDBR_INSN_SIZE);
-	}
-	if (is_endbr(instr))
+#ifdef CONFIG_X86_KERNEL_IBT
+	if (is_endbr((void *)(fentry_ip - ENDBR_INSN_SIZE)))
 		fentry_ip -= ENDBR_INSN_SIZE;
+#endif
 	return fentry_ip;
 }
-#else
-#define get_entry_ip(fentry_ip) fentry_ip
-#endif
 
 BPF_CALL_1(bpf_get_func_ip_kprobe, struct pt_regs *, regs)
 {

From 2981557cb0408e142480bc1eea30558cf5a2382f Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 7 Feb 2025 13:15:32 +0100
Subject: [PATCH 0116/1173] x86,kcfi: Fix EXPORT_SYMBOL vs kCFI

The expectation is that all EXPORT'ed symbols are free to have their
address taken and called indirectly. The majority of the assembly
defined functions currently violate this expectation.

Make then all use SYM_TYPED_FUNC_START() in order to emit the proper
kCFI preamble.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Link: https://lore.kernel.org/r/20250207122546.302679189@infradead.org
---
 arch/x86/crypto/camellia-aesni-avx-asm_64.S  | 7 ++++---
 arch/x86/crypto/camellia-aesni-avx2-asm_64.S | 1 +
 arch/x86/crypto/camellia-x86_64-asm_64.S     | 9 +++++----
 arch/x86/crypto/serpent-avx-x86_64-asm_64.S  | 7 ++++---
 arch/x86/crypto/twofish-x86_64-asm_64-3way.S | 5 +++--
 arch/x86/crypto/twofish-x86_64-asm_64.S      | 5 +++--
 arch/x86/lib/clear_page_64.S                 | 7 ++++---
 arch/x86/lib/copy_page_64.S                  | 3 ++-
 arch/x86/lib/memmove_64.S                    | 3 ++-
 arch/x86/lib/memset_64.S                     | 3 ++-
 arch/x86/lib/msr-reg.S                       | 3 ++-
 11 files changed, 32 insertions(+), 21 deletions(-)

diff --git a/arch/x86/crypto/camellia-aesni-avx-asm_64.S b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
index 646477a13e110..1dfef28c12663 100644
--- a/arch/x86/crypto/camellia-aesni-avx-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
@@ -16,6 +16,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/frame.h>
 
 #define CAMELLIA_TABLE_BYTE_LEN 272
@@ -882,7 +883,7 @@ SYM_FUNC_START_LOCAL(__camellia_dec_blk16)
 	jmp .Ldec_max24;
 SYM_FUNC_END(__camellia_dec_blk16)
 
-SYM_FUNC_START(camellia_ecb_enc_16way)
+SYM_TYPED_FUNC_START(camellia_ecb_enc_16way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst (16 blocks)
@@ -907,7 +908,7 @@ SYM_FUNC_START(camellia_ecb_enc_16way)
 	RET;
 SYM_FUNC_END(camellia_ecb_enc_16way)
 
-SYM_FUNC_START(camellia_ecb_dec_16way)
+SYM_TYPED_FUNC_START(camellia_ecb_dec_16way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst (16 blocks)
@@ -937,7 +938,7 @@ SYM_FUNC_START(camellia_ecb_dec_16way)
 	RET;
 SYM_FUNC_END(camellia_ecb_dec_16way)
 
-SYM_FUNC_START(camellia_cbc_dec_16way)
+SYM_TYPED_FUNC_START(camellia_cbc_dec_16way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst (16 blocks)
diff --git a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
index a0eb94e53b1bb..b1c9b94505557 100644
--- a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
@@ -6,6 +6,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/frame.h>
 
 #define CAMELLIA_TABLE_BYTE_LEN 272
diff --git a/arch/x86/crypto/camellia-x86_64-asm_64.S b/arch/x86/crypto/camellia-x86_64-asm_64.S
index 816b6bb8bded7..824cb94de6c25 100644
--- a/arch/x86/crypto/camellia-x86_64-asm_64.S
+++ b/arch/x86/crypto/camellia-x86_64-asm_64.S
@@ -6,6 +6,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 
 .file "camellia-x86_64-asm_64.S"
 .text
@@ -177,7 +178,7 @@
 	bswapq				RAB0; \
 	movq RAB0,			4*2(RIO);
 
-SYM_FUNC_START(__camellia_enc_blk)
+SYM_TYPED_FUNC_START(__camellia_enc_blk)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -224,7 +225,7 @@ SYM_FUNC_START(__camellia_enc_blk)
 	RET;
 SYM_FUNC_END(__camellia_enc_blk)
 
-SYM_FUNC_START(camellia_dec_blk)
+SYM_TYPED_FUNC_START(camellia_dec_blk)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -411,7 +412,7 @@ SYM_FUNC_END(camellia_dec_blk)
 		bswapq				RAB1; \
 		movq RAB1,			12*2(RIO);
 
-SYM_FUNC_START(__camellia_enc_blk_2way)
+SYM_TYPED_FUNC_START(__camellia_enc_blk_2way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -460,7 +461,7 @@ SYM_FUNC_START(__camellia_enc_blk_2way)
 	RET;
 SYM_FUNC_END(__camellia_enc_blk_2way)
 
-SYM_FUNC_START(camellia_dec_blk_2way)
+SYM_TYPED_FUNC_START(camellia_dec_blk_2way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
diff --git a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
index 97e2836218518..84e47f7f6188c 100644
--- a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
@@ -9,6 +9,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/frame.h>
 #include "glue_helper-asm-avx.S"
 
@@ -656,7 +657,7 @@ SYM_FUNC_START_LOCAL(__serpent_dec_blk8_avx)
 	RET;
 SYM_FUNC_END(__serpent_dec_blk8_avx)
 
-SYM_FUNC_START(serpent_ecb_enc_8way_avx)
+SYM_TYPED_FUNC_START(serpent_ecb_enc_8way_avx)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -674,7 +675,7 @@ SYM_FUNC_START(serpent_ecb_enc_8way_avx)
 	RET;
 SYM_FUNC_END(serpent_ecb_enc_8way_avx)
 
-SYM_FUNC_START(serpent_ecb_dec_8way_avx)
+SYM_TYPED_FUNC_START(serpent_ecb_dec_8way_avx)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -692,7 +693,7 @@ SYM_FUNC_START(serpent_ecb_dec_8way_avx)
 	RET;
 SYM_FUNC_END(serpent_ecb_dec_8way_avx)
 
-SYM_FUNC_START(serpent_cbc_dec_8way_avx)
+SYM_TYPED_FUNC_START(serpent_cbc_dec_8way_avx)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
diff --git a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
index d2288bf38a8a5..071e90e7f0d8f 100644
--- a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
+++ b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
@@ -6,6 +6,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 
 .file "twofish-x86_64-asm-3way.S"
 .text
@@ -220,7 +221,7 @@
 	rorq $32,			RAB2; \
 	outunpack3(mov, RIO, 2, RAB, 2);
 
-SYM_FUNC_START(__twofish_enc_blk_3way)
+SYM_TYPED_FUNC_START(__twofish_enc_blk_3way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -269,7 +270,7 @@ SYM_FUNC_START(__twofish_enc_blk_3way)
 	RET;
 SYM_FUNC_END(__twofish_enc_blk_3way)
 
-SYM_FUNC_START(twofish_dec_blk_3way)
+SYM_TYPED_FUNC_START(twofish_dec_blk_3way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
diff --git a/arch/x86/crypto/twofish-x86_64-asm_64.S b/arch/x86/crypto/twofish-x86_64-asm_64.S
index 775af290cd196..e08b4ba07b934 100644
--- a/arch/x86/crypto/twofish-x86_64-asm_64.S
+++ b/arch/x86/crypto/twofish-x86_64-asm_64.S
@@ -8,6 +8,7 @@
 .text
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/asm-offsets.h>
 
 #define a_offset	0
@@ -202,7 +203,7 @@
 	xor	%r8d,		d ## D;\
 	ror	$1,		d ## D;
 
-SYM_FUNC_START(twofish_enc_blk)
+SYM_TYPED_FUNC_START(twofish_enc_blk)
 	pushq    R1
 
 	/* %rdi contains the ctx address */
@@ -255,7 +256,7 @@ SYM_FUNC_START(twofish_enc_blk)
 	RET
 SYM_FUNC_END(twofish_enc_blk)
 
-SYM_FUNC_START(twofish_dec_blk)
+SYM_TYPED_FUNC_START(twofish_dec_blk)
 	pushq    R1
 
 	/* %rdi contains the ctx address */
diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S
index 2760a15fbc002..cc5077b122d6e 100644
--- a/arch/x86/lib/clear_page_64.S
+++ b/arch/x86/lib/clear_page_64.S
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 #include <linux/export.h>
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/asm.h>
 
 /*
@@ -14,7 +15,7 @@
  * Zero a page.
  * %rdi	- page
  */
-SYM_FUNC_START(clear_page_rep)
+SYM_TYPED_FUNC_START(clear_page_rep)
 	movl $4096/8,%ecx
 	xorl %eax,%eax
 	rep stosq
@@ -22,7 +23,7 @@ SYM_FUNC_START(clear_page_rep)
 SYM_FUNC_END(clear_page_rep)
 EXPORT_SYMBOL_GPL(clear_page_rep)
 
-SYM_FUNC_START(clear_page_orig)
+SYM_TYPED_FUNC_START(clear_page_orig)
 	xorl   %eax,%eax
 	movl   $4096/64,%ecx
 	.p2align 4
@@ -44,7 +45,7 @@ SYM_FUNC_START(clear_page_orig)
 SYM_FUNC_END(clear_page_orig)
 EXPORT_SYMBOL_GPL(clear_page_orig)
 
-SYM_FUNC_START(clear_page_erms)
+SYM_TYPED_FUNC_START(clear_page_erms)
 	movl $4096,%ecx
 	xorl %eax,%eax
 	rep stosb
diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S
index d6ae793d08faf..d8e87fedc20dc 100644
--- a/arch/x86/lib/copy_page_64.S
+++ b/arch/x86/lib/copy_page_64.S
@@ -3,6 +3,7 @@
 
 #include <linux/export.h>
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
 
@@ -13,7 +14,7 @@
  * prefetch distance based on SMP/UP.
  */
 	ALIGN
-SYM_FUNC_START(copy_page)
+SYM_TYPED_FUNC_START(copy_page)
 	ALTERNATIVE "jmp copy_page_regs", "", X86_FEATURE_REP_GOOD
 	movl	$4096/8, %ecx
 	rep	movsq
diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
index 1b60ae81ecd88..aa1f92ee6b2e7 100644
--- a/arch/x86/lib/memmove_64.S
+++ b/arch/x86/lib/memmove_64.S
@@ -8,6 +8,7 @@
  */
 #include <linux/export.h>
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
 
@@ -26,7 +27,7 @@
  * Output:
  * rax: dest
  */
-SYM_FUNC_START(__memmove)
+SYM_TYPED_FUNC_START(__memmove)
 
 	mov %rdi, %rax
 
diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
index 0199d56cb479d..d66b710d628f8 100644
--- a/arch/x86/lib/memset_64.S
+++ b/arch/x86/lib/memset_64.S
@@ -3,6 +3,7 @@
 
 #include <linux/export.h>
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
 
@@ -28,7 +29,7 @@
  * only for the return value that is the same as the source input,
  * which the compiler could/should do much better anyway.
  */
-SYM_FUNC_START(__memset)
+SYM_TYPED_FUNC_START(__memset)
 	ALTERNATIVE "jmp memset_orig", "", X86_FEATURE_FSRS
 
 	movq %rdi,%r9
diff --git a/arch/x86/lib/msr-reg.S b/arch/x86/lib/msr-reg.S
index ebd259f314963..5ef8494896e82 100644
--- a/arch/x86/lib/msr-reg.S
+++ b/arch/x86/lib/msr-reg.S
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/linkage.h>
 #include <linux/errno.h>
+#include <linux/cfi_types.h>
 #include <asm/asm.h>
 #include <asm/msr.h>
 
@@ -12,7 +13,7 @@
  *
  */
 .macro op_safe_regs op
-SYM_FUNC_START(\op\()_safe_regs)
+SYM_TYPED_FUNC_START(\op\()_safe_regs)
 	pushq %rbx
 	pushq %r12
 	movq	%rdi, %r10	/* Save pointer */

From 582077c94052bd69a544b3f9d7619c9c6a67c34b Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 7 Feb 2025 13:15:33 +0100
Subject: [PATCH 0117/1173] x86/cfi: Clean up linkage

With the introduction of kCFI the addition of ENDBR to
SYM_FUNC_START* no longer suffices to make the function indirectly
callable. This now requires the use of SYM_TYPED_FUNC_START.

As such, remove the implicit ENDBR from SYM_FUNC_START* and add some
explicit annotations to fix things up again.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Link: https://lore.kernel.org/r/20250207122546.409116003@infradead.org
---
 arch/x86/crypto/aesni-intel_asm.S     |  2 ++
 arch/x86/entry/calling.h              |  1 +
 arch/x86/entry/entry.S                |  2 ++
 arch/x86/entry/entry_64.S             |  3 +++
 arch/x86/entry/entry_64_fred.S        |  1 +
 arch/x86/entry/vdso/Makefile          |  1 +
 arch/x86/include/asm/linkage.h        | 18 ++++++------------
 arch/x86/include/asm/page_64.h        |  1 +
 arch/x86/include/asm/paravirt_types.h | 12 +++++++++++-
 arch/x86/include/asm/special_insns.h  |  4 ++--
 arch/x86/include/asm/string_64.h      |  2 ++
 arch/x86/kernel/acpi/madt_playdead.S  |  1 +
 arch/x86/kernel/acpi/wakeup_64.S      |  1 +
 arch/x86/kernel/alternative.c         |  8 ++------
 arch/x86/kernel/ftrace_64.S           |  5 +++++
 arch/x86/kernel/irqflags.S            |  1 +
 arch/x86/kernel/paravirt.c            | 14 ++++++++++++--
 arch/x86/lib/clear_page_64.S          |  2 ++
 arch/x86/lib/copy_user_64.S           |  3 +++
 arch/x86/lib/copy_user_uncached_64.S  |  2 ++
 arch/x86/lib/getuser.S                |  9 +++++++++
 arch/x86/lib/hweight.S                |  3 +++
 arch/x86/lib/putuser.S                |  9 +++++++++
 arch/x86/lib/retpoline.S              |  1 +
 arch/x86/mm/mem_encrypt_boot.S        |  1 +
 arch/x86/power/hibernate_asm_64.S     |  2 ++
 arch/x86/xen/xen-asm.S                |  5 +++++
 arch/x86/xen/xen-head.S               |  2 ++
 include/linux/compiler.h              | 10 ++++++++++
 29 files changed, 103 insertions(+), 23 deletions(-)

diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index eb153eff9331a..b37881bb9f157 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -17,6 +17,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/objtool.h>
 #include <asm/frame.h>
 
 #define STATE1	%xmm0
@@ -1071,6 +1072,7 @@ SYM_FUNC_END(_aesni_inc)
  *		      size_t len, u8 *iv)
  */
 SYM_FUNC_START(aesni_ctr_enc)
+	ANNOTATE_NOENDBR
 	FRAME_BEGIN
 	cmp $16, LEN
 	jb .Lctr_enc_just_ret
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index ea81770629eea..cb0911c5dc5dd 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -431,6 +431,7 @@ For 32-bit we have the following conventions - kernel is built with
 /* rdi:	arg1 ... normal C conventions. rax is saved/restored. */
 .macro THUNK name, func
 SYM_FUNC_START(\name)
+	ANNOTATE_NOENDBR
 	pushq %rbp
 	movq %rsp, %rbp
 
diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S
index b7ea3e8e9eccd..e6d52c2fd0887 100644
--- a/arch/x86/entry/entry.S
+++ b/arch/x86/entry/entry.S
@@ -5,6 +5,7 @@
 
 #include <linux/export.h>
 #include <linux/linkage.h>
+#include <linux/objtool.h>
 #include <asm/msr-index.h>
 #include <asm/unwind_hints.h>
 #include <asm/segment.h>
@@ -17,6 +18,7 @@
 .pushsection .noinstr.text, "ax"
 
 SYM_FUNC_START(entry_ibpb)
+	ANNOTATE_NOENDBR
 	movl	$MSR_IA32_PRED_CMD, %ecx
 	movl	$PRED_CMD_IBPB, %eax
 	xorl	%edx, %edx
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index f52dbe0ad93cd..4e5260cdeb816 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -175,6 +175,7 @@ SYM_CODE_END(entry_SYSCALL_64)
  */
 .pushsection .text, "ax"
 SYM_FUNC_START(__switch_to_asm)
+	ANNOTATE_NOENDBR
 	/*
 	 * Save callee-saved registers
 	 * This must match the order in inactive_task_frame
@@ -742,6 +743,7 @@ _ASM_NOKPROBE(common_interrupt_return)
  * Is in entry.text as it shouldn't be instrumented.
  */
 SYM_FUNC_START(asm_load_gs_index)
+	ANNOTATE_NOENDBR
 	FRAME_BEGIN
 	swapgs
 .Lgs_change:
@@ -1526,6 +1528,7 @@ SYM_CODE_END(rewind_stack_and_make_dead)
  * refactored in the future if needed.
  */
 SYM_FUNC_START(clear_bhb_loop)
+	ANNOTATE_NOENDBR
 	push	%rbp
 	mov	%rsp, %rbp
 	movl	$5, %ecx
diff --git a/arch/x86/entry/entry_64_fred.S b/arch/x86/entry/entry_64_fred.S
index a02bc6f3d2e6a..29c5c32c16c36 100644
--- a/arch/x86/entry/entry_64_fred.S
+++ b/arch/x86/entry/entry_64_fred.S
@@ -58,6 +58,7 @@ SYM_CODE_END(asm_fred_entrypoint_kernel)
 
 #if IS_ENABLED(CONFIG_KVM_INTEL)
 SYM_FUNC_START(asm_fred_entry_from_kvm)
+	ANNOTATE_NOENDBR
 	push %rbp
 	mov %rsp, %rbp
 
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index c9216ac4fb1eb..bf9f4f63e1b41 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -133,6 +133,7 @@ KBUILD_CFLAGS_32 += -fno-stack-protector
 KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls)
 KBUILD_CFLAGS_32 += -fno-omit-frame-pointer
 KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING
+KBUILD_CFLAGS_32 += -DBUILD_VDSO
 
 ifdef CONFIG_MITIGATION_RETPOLINE
 ifneq ($(RETPOLINE_VDSO_CFLAGS),)
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index dc31b13b87a0d..4835c67bb5ddb 100644
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -119,33 +119,27 @@
 
 /* SYM_FUNC_START -- use for global functions */
 #define SYM_FUNC_START(name)				\
-	SYM_START(name, SYM_L_GLOBAL, SYM_F_ALIGN)	\
-	ENDBR
+	SYM_START(name, SYM_L_GLOBAL, SYM_F_ALIGN)
 
 /* SYM_FUNC_START_NOALIGN -- use for global functions, w/o alignment */
 #define SYM_FUNC_START_NOALIGN(name)			\
-	SYM_START(name, SYM_L_GLOBAL, SYM_A_NONE)	\
-	ENDBR
+	SYM_START(name, SYM_L_GLOBAL, SYM_A_NONE)
 
 /* SYM_FUNC_START_LOCAL -- use for local functions */
 #define SYM_FUNC_START_LOCAL(name)			\
-	SYM_START(name, SYM_L_LOCAL, SYM_F_ALIGN)	\
-	ENDBR
+	SYM_START(name, SYM_L_LOCAL, SYM_F_ALIGN)
 
 /* SYM_FUNC_START_LOCAL_NOALIGN -- use for local functions, w/o alignment */
 #define SYM_FUNC_START_LOCAL_NOALIGN(name)		\
-	SYM_START(name, SYM_L_LOCAL, SYM_A_NONE)	\
-	ENDBR
+	SYM_START(name, SYM_L_LOCAL, SYM_A_NONE)
 
 /* SYM_FUNC_START_WEAK -- use for weak functions */
 #define SYM_FUNC_START_WEAK(name)			\
-	SYM_START(name, SYM_L_WEAK, SYM_F_ALIGN)	\
-	ENDBR
+	SYM_START(name, SYM_L_WEAK, SYM_F_ALIGN)
 
 /* SYM_FUNC_START_WEAK_NOALIGN -- use for weak functions, w/o alignment */
 #define SYM_FUNC_START_WEAK_NOALIGN(name)		\
-	SYM_START(name, SYM_L_WEAK, SYM_A_NONE)		\
-	ENDBR
+	SYM_START(name, SYM_L_WEAK, SYM_A_NONE)
 
 #endif /* _ASM_X86_LINKAGE_H */
 
diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h
index d63576608ce76..5c5cfa076a27e 100644
--- a/arch/x86/include/asm/page_64.h
+++ b/arch/x86/include/asm/page_64.h
@@ -60,6 +60,7 @@ static inline void clear_page(void *page)
 }
 
 void copy_page(void *to, void *from);
+KCFI_REFERENCE(copy_page);
 
 #ifdef CONFIG_X86_5LEVEL
 /*
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index fea56b04f4365..8b36a9562191c 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -244,7 +244,17 @@ extern struct paravirt_patch_template pv_ops;
 
 int paravirt_disable_iospace(void);
 
-/* This generates an indirect call based on the operation type number. */
+/*
+ * This generates an indirect call based on the operation type number.
+ *
+ * Since alternatives run after enabling CET/IBT -- the latter setting/clearing
+ * capabilities and the former requiring all capabilities being finalized --
+ * these indirect calls are subject to IBT and the paravirt stubs should have
+ * ENDBR on.
+ *
+ * OTOH since this is effectively a __nocfi indirect call, the paravirt stubs
+ * don't need to bother with CFI prefixes.
+ */
 #define PARAVIRT_CALL					\
 	ANNOTATE_RETPOLINE_SAFE				\
 	"call *%[paravirt_opptr];"
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 03e7c2d495597..21ce480658b14 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -42,14 +42,14 @@ static __always_inline void native_write_cr2(unsigned long val)
 	asm volatile("mov %0,%%cr2": : "r" (val) : "memory");
 }
 
-static inline unsigned long __native_read_cr3(void)
+static __always_inline unsigned long __native_read_cr3(void)
 {
 	unsigned long val;
 	asm volatile("mov %%cr3,%0\n\t" : "=r" (val) : __FORCE_ORDER);
 	return val;
 }
 
-static inline void native_write_cr3(unsigned long val)
+static __always_inline void native_write_cr3(unsigned long val)
 {
 	asm volatile("mov %0,%%cr3": : "r" (val) : "memory");
 }
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index 9d0b324eab213..79e9695dc13e4 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -21,6 +21,7 @@ extern void *__memcpy(void *to, const void *from, size_t len);
 #define __HAVE_ARCH_MEMSET
 void *memset(void *s, int c, size_t n);
 void *__memset(void *s, int c, size_t n);
+KCFI_REFERENCE(__memset);
 
 /*
  * KMSAN needs to instrument as much code as possible. Use C versions of
@@ -70,6 +71,7 @@ static inline void *memset64(uint64_t *s, uint64_t v, size_t n)
 #define __HAVE_ARCH_MEMMOVE
 void *memmove(void *dest, const void *src, size_t count);
 void *__memmove(void *dest, const void *src, size_t count);
+KCFI_REFERENCE(__memmove);
 
 int memcmp(const void *cs, const void *ct, size_t count);
 size_t strlen(const char *s);
diff --git a/arch/x86/kernel/acpi/madt_playdead.S b/arch/x86/kernel/acpi/madt_playdead.S
index 4e498d28cdc85..aefb9cb583add 100644
--- a/arch/x86/kernel/acpi/madt_playdead.S
+++ b/arch/x86/kernel/acpi/madt_playdead.S
@@ -14,6 +14,7 @@
  * rsi: PGD of the identity mapping
  */
 SYM_FUNC_START(asm_acpi_mp_play_dead)
+	ANNOTATE_NOENDBR
 	/* Turn off global entries. Following CR3 write will flush them. */
 	movq	%cr4, %rdx
 	andq	$~(X86_CR4_PGE), %rdx
diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index b200a193beeb3..04f561f75e990 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -17,6 +17,7 @@
 	 * Hooray, we are in Long 64-bit mode (but still running in low memory)
 	 */
 SYM_FUNC_START(wakeup_long64)
+	ANNOTATE_NOENDBR
 	movq	saved_magic(%rip), %rax
 	movq	$0x123456789abcdef0, %rdx
 	cmpq	%rdx, %rax
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 9a252bb0d34b8..e914a65ff1541 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -926,11 +926,7 @@ struct bpf_insn;
 extern unsigned int __bpf_prog_runX(const void *ctx,
 				    const struct bpf_insn *insn);
 
-/*
- * Force a reference to the external symbol so the compiler generates
- * __kcfi_typid.
- */
-__ADDRESSABLE(__bpf_prog_runX);
+KCFI_REFERENCE(__bpf_prog_runX);
 
 /* u32 __ro_after_init cfi_bpf_hash = __kcfi_typeid___bpf_prog_runX; */
 asm (
@@ -947,7 +943,7 @@ asm (
 /* Must match bpf_callback_t */
 extern u64 __bpf_callback_fn(u64, u64, u64, u64, u64);
 
-__ADDRESSABLE(__bpf_callback_fn);
+KCFI_REFERENCE(__bpf_callback_fn);
 
 /* u32 __ro_after_init cfi_bpf_subprog_hash = __kcfi_typeid___bpf_callback_fn; */
 asm (
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index d516472285967..367da36381678 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -146,12 +146,14 @@ SYM_FUNC_END(ftrace_stub_graph)
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 SYM_FUNC_START(__fentry__)
+	ANNOTATE_NOENDBR
 	CALL_DEPTH_ACCOUNT
 	RET
 SYM_FUNC_END(__fentry__)
 EXPORT_SYMBOL(__fentry__)
 
 SYM_FUNC_START(ftrace_caller)
+	ANNOTATE_NOENDBR
 	/* save_mcount_regs fills in first two parameters */
 	save_mcount_regs
 
@@ -197,6 +199,7 @@ SYM_FUNC_END(ftrace_caller);
 STACK_FRAME_NON_STANDARD_FP(ftrace_caller)
 
 SYM_FUNC_START(ftrace_regs_caller)
+	ANNOTATE_NOENDBR
 	/* Save the current flags before any operations that can change them */
 	pushfq
 
@@ -310,6 +313,7 @@ SYM_FUNC_END(ftrace_regs_caller)
 STACK_FRAME_NON_STANDARD_FP(ftrace_regs_caller)
 
 SYM_FUNC_START(ftrace_stub_direct_tramp)
+	ANNOTATE_NOENDBR
 	CALL_DEPTH_ACCOUNT
 	RET
 SYM_FUNC_END(ftrace_stub_direct_tramp)
@@ -317,6 +321,7 @@ SYM_FUNC_END(ftrace_stub_direct_tramp)
 #else /* ! CONFIG_DYNAMIC_FTRACE */
 
 SYM_FUNC_START(__fentry__)
+	ANNOTATE_NOENDBR
 	CALL_DEPTH_ACCOUNT
 
 	cmpq $ftrace_stub, ftrace_trace_function
diff --git a/arch/x86/kernel/irqflags.S b/arch/x86/kernel/irqflags.S
index 7f542a7799cb7..fdabd5dda154a 100644
--- a/arch/x86/kernel/irqflags.S
+++ b/arch/x86/kernel/irqflags.S
@@ -9,6 +9,7 @@
  */
 .pushsection .noinstr.text, "ax"
 SYM_FUNC_START(native_save_fl)
+	ENDBR
 	pushf
 	pop %_ASM_AX
 	RET
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 1ccaa3397a670..1dc114c810ac9 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -116,6 +116,16 @@ static noinstr void pv_native_write_cr2(unsigned long val)
 	native_write_cr2(val);
 }
 
+static noinstr unsigned long pv_native_read_cr3(void)
+{
+	return __native_read_cr3();
+}
+
+static noinstr void pv_native_write_cr3(unsigned long cr3)
+{
+	native_write_cr3(cr3);
+}
+
 static noinstr unsigned long pv_native_get_debugreg(int regno)
 {
 	return native_get_debugreg(regno);
@@ -203,8 +213,8 @@ struct paravirt_patch_template pv_ops = {
 #ifdef CONFIG_PARAVIRT_XXL
 	.mmu.read_cr2		= __PV_IS_CALLEE_SAVE(pv_native_read_cr2),
 	.mmu.write_cr2		= pv_native_write_cr2,
-	.mmu.read_cr3		= __native_read_cr3,
-	.mmu.write_cr3		= native_write_cr3,
+	.mmu.read_cr3		= pv_native_read_cr3,
+	.mmu.write_cr3		= pv_native_write_cr3,
 
 	.mmu.pgd_alloc		= __paravirt_pgd_alloc,
 	.mmu.pgd_free		= paravirt_nop,
diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S
index cc5077b122d6e..a508e4a8c66a2 100644
--- a/arch/x86/lib/clear_page_64.S
+++ b/arch/x86/lib/clear_page_64.S
@@ -2,6 +2,7 @@
 #include <linux/export.h>
 #include <linux/linkage.h>
 #include <linux/cfi_types.h>
+#include <linux/objtool.h>
 #include <asm/asm.h>
 
 /*
@@ -64,6 +65,7 @@ EXPORT_SYMBOL_GPL(clear_page_erms)
  * rcx: uncleared bytes or 0 if successful.
  */
 SYM_FUNC_START(rep_stos_alternative)
+	ANNOTATE_NOENDBR
 	cmpq $64,%rcx
 	jae .Lunrolled
 
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index fc9fb5d061744..aa8c341b24419 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -8,6 +8,8 @@
 
 #include <linux/export.h>
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
+#include <linux/objtool.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
 #include <asm/asm.h>
@@ -30,6 +32,7 @@
  * it simpler for us, we can clobber rsi/rdi and rax freely.
  */
 SYM_FUNC_START(rep_movs_alternative)
+	ANNOTATE_NOENDBR
 	cmpq $64,%rcx
 	jae .Llarge
 
diff --git a/arch/x86/lib/copy_user_uncached_64.S b/arch/x86/lib/copy_user_uncached_64.S
index 2918e36eece22..18350b343c2ab 100644
--- a/arch/x86/lib/copy_user_uncached_64.S
+++ b/arch/x86/lib/copy_user_uncached_64.S
@@ -5,6 +5,7 @@
 
 #include <linux/export.h>
 #include <linux/linkage.h>
+#include <linux/objtool.h>
 #include <asm/asm.h>
 
 /*
@@ -27,6 +28,7 @@
  * rax uncopied bytes or 0 if successful.
  */
 SYM_FUNC_START(__copy_user_nocache)
+	ANNOTATE_NOENDBR
 	/* If destination is not 7-byte aligned, we'll have to align it */
 	testb $7,%dil
 	jne .Lalign
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index 89ecd57c9d423..71d8e7da4fc55 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -28,6 +28,7 @@
 
 #include <linux/export.h>
 #include <linux/linkage.h>
+#include <linux/objtool.h>
 #include <asm/page_types.h>
 #include <asm/errno.h>
 #include <asm/asm-offsets.h>
@@ -62,6 +63,7 @@
 
 	.text
 SYM_FUNC_START(__get_user_1)
+	ANNOTATE_NOENDBR
 	check_range size=1
 	ASM_STAC
 	UACCESS movzbl (%_ASM_AX),%edx
@@ -72,6 +74,7 @@ SYM_FUNC_END(__get_user_1)
 EXPORT_SYMBOL(__get_user_1)
 
 SYM_FUNC_START(__get_user_2)
+	ANNOTATE_NOENDBR
 	check_range size=2
 	ASM_STAC
 	UACCESS movzwl (%_ASM_AX),%edx
@@ -82,6 +85,7 @@ SYM_FUNC_END(__get_user_2)
 EXPORT_SYMBOL(__get_user_2)
 
 SYM_FUNC_START(__get_user_4)
+	ANNOTATE_NOENDBR
 	check_range size=4
 	ASM_STAC
 	UACCESS movl (%_ASM_AX),%edx
@@ -92,6 +96,7 @@ SYM_FUNC_END(__get_user_4)
 EXPORT_SYMBOL(__get_user_4)
 
 SYM_FUNC_START(__get_user_8)
+	ANNOTATE_NOENDBR
 #ifndef CONFIG_X86_64
 	xor %ecx,%ecx
 #endif
@@ -111,6 +116,7 @@ EXPORT_SYMBOL(__get_user_8)
 
 /* .. and the same for __get_user, just without the range checks */
 SYM_FUNC_START(__get_user_nocheck_1)
+	ANNOTATE_NOENDBR
 	ASM_STAC
 	ASM_BARRIER_NOSPEC
 	UACCESS movzbl (%_ASM_AX),%edx
@@ -121,6 +127,7 @@ SYM_FUNC_END(__get_user_nocheck_1)
 EXPORT_SYMBOL(__get_user_nocheck_1)
 
 SYM_FUNC_START(__get_user_nocheck_2)
+	ANNOTATE_NOENDBR
 	ASM_STAC
 	ASM_BARRIER_NOSPEC
 	UACCESS movzwl (%_ASM_AX),%edx
@@ -131,6 +138,7 @@ SYM_FUNC_END(__get_user_nocheck_2)
 EXPORT_SYMBOL(__get_user_nocheck_2)
 
 SYM_FUNC_START(__get_user_nocheck_4)
+	ANNOTATE_NOENDBR
 	ASM_STAC
 	ASM_BARRIER_NOSPEC
 	UACCESS movl (%_ASM_AX),%edx
@@ -141,6 +149,7 @@ SYM_FUNC_END(__get_user_nocheck_4)
 EXPORT_SYMBOL(__get_user_nocheck_4)
 
 SYM_FUNC_START(__get_user_nocheck_8)
+	ANNOTATE_NOENDBR
 	ASM_STAC
 	ASM_BARRIER_NOSPEC
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/lib/hweight.S b/arch/x86/lib/hweight.S
index 774bdf3e6f0a9..edbeb3ecad38c 100644
--- a/arch/x86/lib/hweight.S
+++ b/arch/x86/lib/hweight.S
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/export.h>
 #include <linux/linkage.h>
+#include <linux/objtool.h>
 
 #include <asm/asm.h>
 
@@ -9,6 +10,7 @@
  * %rdi: w
  */
 SYM_FUNC_START(__sw_hweight32)
+	ANNOTATE_NOENDBR
 
 #ifdef CONFIG_X86_64
 	movl %edi, %eax				# w
@@ -42,6 +44,7 @@ EXPORT_SYMBOL(__sw_hweight32)
  */
 #ifdef CONFIG_X86_64
 SYM_FUNC_START(__sw_hweight64)
+	ANNOTATE_NOENDBR
 	pushq   %rdi
 	pushq   %rdx
 
diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S
index 975c9c18263d2..46d9e9b98a618 100644
--- a/arch/x86/lib/putuser.S
+++ b/arch/x86/lib/putuser.S
@@ -13,6 +13,7 @@
  */
 #include <linux/export.h>
 #include <linux/linkage.h>
+#include <linux/objtool.h>
 #include <asm/thread_info.h>
 #include <asm/errno.h>
 #include <asm/asm.h>
@@ -45,6 +46,7 @@
 
 .text
 SYM_FUNC_START(__put_user_1)
+	ANNOTATE_NOENDBR
 	check_range size=1
 	ASM_STAC
 1:	movb %al,(%_ASM_CX)
@@ -55,6 +57,7 @@ SYM_FUNC_END(__put_user_1)
 EXPORT_SYMBOL(__put_user_1)
 
 SYM_FUNC_START(__put_user_nocheck_1)
+	ANNOTATE_NOENDBR
 	ASM_STAC
 2:	movb %al,(%_ASM_CX)
 	xor %ecx,%ecx
@@ -64,6 +67,7 @@ SYM_FUNC_END(__put_user_nocheck_1)
 EXPORT_SYMBOL(__put_user_nocheck_1)
 
 SYM_FUNC_START(__put_user_2)
+	ANNOTATE_NOENDBR
 	check_range size=2
 	ASM_STAC
 3:	movw %ax,(%_ASM_CX)
@@ -74,6 +78,7 @@ SYM_FUNC_END(__put_user_2)
 EXPORT_SYMBOL(__put_user_2)
 
 SYM_FUNC_START(__put_user_nocheck_2)
+	ANNOTATE_NOENDBR
 	ASM_STAC
 4:	movw %ax,(%_ASM_CX)
 	xor %ecx,%ecx
@@ -83,6 +88,7 @@ SYM_FUNC_END(__put_user_nocheck_2)
 EXPORT_SYMBOL(__put_user_nocheck_2)
 
 SYM_FUNC_START(__put_user_4)
+	ANNOTATE_NOENDBR
 	check_range size=4
 	ASM_STAC
 5:	movl %eax,(%_ASM_CX)
@@ -93,6 +99,7 @@ SYM_FUNC_END(__put_user_4)
 EXPORT_SYMBOL(__put_user_4)
 
 SYM_FUNC_START(__put_user_nocheck_4)
+	ANNOTATE_NOENDBR
 	ASM_STAC
 6:	movl %eax,(%_ASM_CX)
 	xor %ecx,%ecx
@@ -102,6 +109,7 @@ SYM_FUNC_END(__put_user_nocheck_4)
 EXPORT_SYMBOL(__put_user_nocheck_4)
 
 SYM_FUNC_START(__put_user_8)
+	ANNOTATE_NOENDBR
 	check_range size=8
 	ASM_STAC
 7:	mov %_ASM_AX,(%_ASM_CX)
@@ -115,6 +123,7 @@ SYM_FUNC_END(__put_user_8)
 EXPORT_SYMBOL(__put_user_8)
 
 SYM_FUNC_START(__put_user_nocheck_8)
+	ANNOTATE_NOENDBR
 	ASM_STAC
 9:	mov %_ASM_AX,(%_ASM_CX)
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index 391059b2c6fbc..038f49a43ab43 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -326,6 +326,7 @@ SYM_FUNC_END(retbleed_untrain_ret)
 #if defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO)
 
 SYM_FUNC_START(entry_untrain_ret)
+	ANNOTATE_NOENDBR
 	ALTERNATIVE JMP_RETBLEED_UNTRAIN_RET, JMP_SRSO_UNTRAIN_RET, X86_FEATURE_SRSO
 SYM_FUNC_END(entry_untrain_ret)
 __EXPORT_THUNK(entry_untrain_ret)
diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S
index e25288ee33c2d..f8a33b25ae869 100644
--- a/arch/x86/mm/mem_encrypt_boot.S
+++ b/arch/x86/mm/mem_encrypt_boot.S
@@ -72,6 +72,7 @@ SYM_FUNC_START(sme_encrypt_execute)
 SYM_FUNC_END(sme_encrypt_execute)
 
 SYM_FUNC_START(__enc_copy)
+	ANNOTATE_NOENDBR
 /*
  * Routine used to encrypt memory in place.
  *   This routine must be run outside of the kernel proper since
diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S
index 0a0539e1cc814..8c534c36adfa2 100644
--- a/arch/x86/power/hibernate_asm_64.S
+++ b/arch/x86/power/hibernate_asm_64.S
@@ -26,6 +26,7 @@
 	 /* code below belongs to the image kernel */
 	.align PAGE_SIZE
 SYM_FUNC_START(restore_registers)
+	ANNOTATE_NOENDBR
 	/* go back to the original page tables */
 	movq    %r9, %cr3
 
@@ -119,6 +120,7 @@ SYM_FUNC_END(restore_image)
 
 	/* code below has been relocated to a safe page */
 SYM_FUNC_START(core_restore_code)
+	ANNOTATE_NOENDBR
 	/* switch to temporary page tables */
 	movq	%rax, %cr3
 	/* flush TLB */
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index b518f36d1ca2e..109af12f76472 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -51,6 +51,7 @@ SYM_FUNC_END(xen_hypercall_pv)
  * non-zero.
  */
 SYM_FUNC_START(xen_irq_disable_direct)
+	ENDBR
 	movb $1, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask)
 	RET
 SYM_FUNC_END(xen_irq_disable_direct)
@@ -90,6 +91,7 @@ SYM_FUNC_END(check_events)
  * then enter the hypervisor to get them handled.
  */
 SYM_FUNC_START(xen_irq_enable_direct)
+	ENDBR
 	FRAME_BEGIN
 	/* Unmask events */
 	movb $0, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask)
@@ -120,6 +122,7 @@ SYM_FUNC_END(xen_irq_enable_direct)
  * x86 use opposite senses (mask vs enable).
  */
 SYM_FUNC_START(xen_save_fl_direct)
+	ENDBR
 	testb $0xff, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask)
 	setz %ah
 	addb %ah, %ah
@@ -127,6 +130,7 @@ SYM_FUNC_START(xen_save_fl_direct)
 SYM_FUNC_END(xen_save_fl_direct)
 
 SYM_FUNC_START(xen_read_cr2)
+	ENDBR
 	FRAME_BEGIN
 	_ASM_MOV PER_CPU_VAR(xen_vcpu), %_ASM_AX
 	_ASM_MOV XEN_vcpu_info_arch_cr2(%_ASM_AX), %_ASM_AX
@@ -135,6 +139,7 @@ SYM_FUNC_START(xen_read_cr2)
 SYM_FUNC_END(xen_read_cr2);
 
 SYM_FUNC_START(xen_read_cr2_direct)
+	ENDBR
 	FRAME_BEGIN
 	_ASM_MOV PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_arch_cr2), %_ASM_AX
 	FRAME_END
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 894edf8d6d62f..8d6873edff36e 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -133,11 +133,13 @@ SYM_FUNC_START(xen_hypercall_hvm)
 SYM_FUNC_END(xen_hypercall_hvm)
 
 SYM_FUNC_START(xen_hypercall_amd)
+	ANNOTATE_NOENDBR
 	vmmcall
 	RET
 SYM_FUNC_END(xen_hypercall_amd)
 
 SYM_FUNC_START(xen_hypercall_intel)
+	ANNOTATE_NOENDBR
 	vmcall
 	RET
 SYM_FUNC_END(xen_hypercall_intel)
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 200fd3c5bc70d..aa7f0a9f60852 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -212,6 +212,16 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 
 #endif /* __KERNEL__ */
 
+#if defined(CONFIG_CFI_CLANG) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO)
+/*
+ * Force a reference to the external symbol so the compiler generates
+ * __kcfi_typid.
+ */
+#define KCFI_REFERENCE(sym) __ADDRESSABLE(sym)
+#else
+#define KCFI_REFERENCE(sym)
+#endif
+
 /**
  * offset_to_ptr - convert a relative memory offset to an absolute pointer
  * @off:	the address of the 32-bit offset value

From 93f16a1ab78ca56e3cd997d1ea54c214774781ac Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 7 Feb 2025 13:15:34 +0100
Subject: [PATCH 0118/1173] x86/boot: Mark start_secondary() with __noendbr

The handoff between the boot stubs and start_secondary() are before IBT is
enabled and is definitely not subject to kCFI. As such, suppress all that for
this function.

Notably when the ENDBR poison would become fatal (ud1 instead of nop) this will
trigger a tripple fault because we haven't set up the IDT to handle #UD yet.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Link: https://lore.kernel.org/r/20250207122546.509520369@infradead.org
---
 arch/x86/kernel/smpboot.c | 3 ++-
 include/linux/objtool.h   | 4 +++-
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index c10850ae6f094..4be00831656c4 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -229,7 +229,7 @@ static void ap_calibrate_delay(void)
 /*
  * Activate a secondary processor.
  */
-static void notrace start_secondary(void *unused)
+static void notrace __noendbr start_secondary(void *unused)
 {
 	/*
 	 * Don't put *anything* except direct CPU state initialization
@@ -314,6 +314,7 @@ static void notrace start_secondary(void *unused)
 	wmb();
 	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
+ANNOTATE_NOENDBR_SYM(start_secondary);
 
 /*
  * The bootstrap kernel entry code has set these up. Save them for
diff --git a/include/linux/objtool.h b/include/linux/objtool.h
index c722a921165ba..3ca965a2ddc80 100644
--- a/include/linux/objtool.h
+++ b/include/linux/objtool.h
@@ -128,7 +128,7 @@
 #define UNWIND_HINT(type, sp_reg, sp_offset, signal) "\n\t"
 #define STACK_FRAME_NON_STANDARD(func)
 #define STACK_FRAME_NON_STANDARD_FP(func)
-#define __ASM_ANNOTATE(label, type)
+#define __ASM_ANNOTATE(label, type) ""
 #define ASM_ANNOTATE(type)
 #else
 .macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0
@@ -147,6 +147,8 @@
  * these relocations will never be used for indirect calls.
  */
 #define ANNOTATE_NOENDBR		ASM_ANNOTATE(ANNOTYPE_NOENDBR)
+#define ANNOTATE_NOENDBR_SYM(sym)	asm(__ASM_ANNOTATE(sym, ANNOTYPE_NOENDBR))
+
 /*
  * This should be used immediately before an indirect jump/call. It tells
  * objtool the subsequent indirect jump/call is vouched safe for retpoline

From ab9fea59487d8b5149a323e2092b7c0f53994dd5 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 7 Feb 2025 13:15:35 +0100
Subject: [PATCH 0119/1173] x86/alternative: Simplify callthunk patching

Now that paravirt call patching is implemented using alternatives, it
is possible to avoid having to patch the alternative sites by
including the altinstr_replacement calls in the call_sites list.

This means we're now stacking relative adjustments like so:

  callthunks_patch_builtin_calls():
    patches all function calls to target: func() -> func()-10
    since the CALL accounting lives in the CALL_PADDING.

    This explicitly includes .altinstr_replacement

  alt_replace_call():
    patches: x86_BUG() -> target()

    this patching is done in a relative manner, and will preserve
    the above adjustment, meaning that with calldepth patching it
    will do: x86_BUG()-10 -> target()-10

  apply_relocation():
    does code relocation, and adjusts all RIP-relative instructions
    to the new location, also in a relative manner.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Link: https://lore.kernel.org/r/20250207122546.617187089@infradead.org
---
 arch/x86/include/asm/alternative.h |  1 -
 arch/x86/kernel/alternative.c      |  8 ++++----
 arch/x86/kernel/callthunks.c       | 13 -------------
 arch/x86/kernel/module.c           | 17 ++++++-----------
 tools/objtool/arch/x86/decode.c    |  1 +
 tools/objtool/check.c              | 12 ++----------
 6 files changed, 13 insertions(+), 39 deletions(-)

diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index a2141665239b5..853fbcf68719b 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -100,7 +100,6 @@ struct module;
 
 struct callthunk_sites {
 	s32				*call_start, *call_end;
-	struct alt_instr		*alt_start, *alt_end;
 };
 
 #ifdef CONFIG_CALL_THUNKS
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index e914a65ff1541..fda11df1e6501 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -1705,14 +1705,14 @@ void __init alternative_instructions(void)
 	apply_retpolines(__retpoline_sites, __retpoline_sites_end);
 	apply_returns(__return_sites, __return_sites_end);
 
-	apply_alternatives(__alt_instructions, __alt_instructions_end);
-
 	/*
-	 * Now all calls are established. Apply the call thunks if
-	 * required.
+	 * Adjust all CALL instructions to point to func()-10, including
+	 * those in .altinstr_replacement.
 	 */
 	callthunks_patch_builtin_calls();
 
+	apply_alternatives(__alt_instructions, __alt_instructions_end);
+
 	/*
 	 * Seal all functions that do not have their address taken.
 	 */
diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c
index 8418a892d195a..25ae542501124 100644
--- a/arch/x86/kernel/callthunks.c
+++ b/arch/x86/kernel/callthunks.c
@@ -239,22 +239,11 @@ patch_call_sites(s32 *start, s32 *end, const struct core_text *ct)
 		patch_call((void *)s + *s, ct);
 }
 
-static __init_or_module void
-patch_alt_call_sites(struct alt_instr *start, struct alt_instr *end,
-		     const struct core_text *ct)
-{
-	struct alt_instr *a;
-
-	for (a = start; a < end; a++)
-		patch_call((void *)&a->instr_offset + a->instr_offset, ct);
-}
-
 static __init_or_module void
 callthunks_setup(struct callthunk_sites *cs, const struct core_text *ct)
 {
 	prdbg("Patching call sites %s\n", ct->name);
 	patch_call_sites(cs->call_start, cs->call_end, ct);
-	patch_alt_call_sites(cs->alt_start, cs->alt_end, ct);
 	prdbg("Patching call sites done%s\n", ct->name);
 }
 
@@ -263,8 +252,6 @@ void __init callthunks_patch_builtin_calls(void)
 	struct callthunk_sites cs = {
 		.call_start	= __call_sites,
 		.call_end	= __call_sites_end,
-		.alt_start	= __alt_instructions,
-		.alt_end	= __alt_instructions_end
 	};
 
 	if (!cpu_feature_enabled(X86_FEATURE_CALL_DEPTH))
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index 837450b6e882f..cb9d295e67cbf 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -275,12 +275,7 @@ int module_finalize(const Elf_Ehdr *hdr,
 		void *rseg = (void *)returns->sh_addr;
 		apply_returns(rseg, rseg + returns->sh_size);
 	}
-	if (alt) {
-		/* patch .altinstructions */
-		void *aseg = (void *)alt->sh_addr;
-		apply_alternatives(aseg, aseg + alt->sh_size);
-	}
-	if (calls || alt) {
+	if (calls) {
 		struct callthunk_sites cs = {};
 
 		if (calls) {
@@ -288,13 +283,13 @@ int module_finalize(const Elf_Ehdr *hdr,
 			cs.call_end = (void *)calls->sh_addr + calls->sh_size;
 		}
 
-		if (alt) {
-			cs.alt_start = (void *)alt->sh_addr;
-			cs.alt_end = (void *)alt->sh_addr + alt->sh_size;
-		}
-
 		callthunks_patch_module_calls(&cs, me);
 	}
+	if (alt) {
+		/* patch .altinstructions */
+		void *aseg = (void *)alt->sh_addr;
+		apply_alternatives(aseg, aseg + alt->sh_size);
+	}
 	if (ibt_endbr) {
 		void *iseg = (void *)ibt_endbr->sh_addr;
 		apply_seal_endbr(iseg, iseg + ibt_endbr->sh_size);
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index fe1362c345647..181aa604f8cdf 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -850,5 +850,6 @@ bool arch_is_rethunk(struct symbol *sym)
 bool arch_is_embedded_insn(struct symbol *sym)
 {
 	return !strcmp(sym->name, "retbleed_return_thunk") ||
+	       !strcmp(sym->name, "srso_alias_safe_ret") ||
 	       !strcmp(sym->name, "srso_safe_ret");
 }
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 753dbc4f81985..26f2c1b8e099c 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -1283,15 +1283,6 @@ static void annotate_call_site(struct objtool_file *file,
 	if (!sym)
 		sym = reloc->sym;
 
-	/*
-	 * Alternative replacement code is just template code which is
-	 * sometimes copied to the original instruction. For now, don't
-	 * annotate it. (In the future we might consider annotating the
-	 * original instruction if/when it ever makes sense to do so.)
-	 */
-	if (!strcmp(insn->sec->name, ".altinstr_replacement"))
-		return;
-
 	if (sym->static_call_tramp) {
 		list_add_tail(&insn->call_node, &file->static_call_list);
 		return;
@@ -1349,7 +1340,8 @@ static void annotate_call_site(struct objtool_file *file,
 		return;
 	}
 
-	if (insn->type == INSN_CALL && !insn->sec->init)
+	if (insn->type == INSN_CALL && !insn->sec->init &&
+	    !insn->_call_dest->embedded_insn)
 		list_add_tail(&insn->call_node, &file->call_list);
 
 	if (!sibling && dead_end_function(file, sym))

From c20ad96c9a8f0aeaf4e4057730a22de2657ad0c2 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 7 Feb 2025 13:15:36 +0100
Subject: [PATCH 0120/1173] x86/traps: Cleanup and robustify decode_bug()

Notably, don't attempt to decode an immediate when MOD == 3.

Additionally have it return the instruction length, such that WARN
like bugs can more reliably skip to the correct instruction.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Link: https://lore.kernel.org/r/20250207122546.721120726@infradead.org
---
 arch/x86/include/asm/bug.h |  5 ++-
 arch/x86/include/asm/ibt.h |  4 +-
 arch/x86/kernel/traps.c    | 82 ++++++++++++++++++++++++++++----------
 3 files changed, 65 insertions(+), 26 deletions(-)

diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index e85ac0c7c039e..1a5e4b3726940 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -22,8 +22,9 @@
 #define SECOND_BYTE_OPCODE_UD2	0x0b
 
 #define BUG_NONE		0xffff
-#define BUG_UD1			0xfffe
-#define BUG_UD2			0xfffd
+#define BUG_UD2			0xfffe
+#define BUG_UD1			0xfffd
+#define BUG_UD1_UBSAN		0xfffc
 
 #ifdef CONFIG_GENERIC_BUG
 
diff --git a/arch/x86/include/asm/ibt.h b/arch/x86/include/asm/ibt.h
index d955e0d1cbf15..f0ca5c0b1a6b2 100644
--- a/arch/x86/include/asm/ibt.h
+++ b/arch/x86/include/asm/ibt.h
@@ -41,7 +41,7 @@
 	_ASM_PTR fname "\n\t"				\
 	".popsection\n\t"
 
-static inline __attribute_const__ u32 gen_endbr(void)
+static __always_inline __attribute_const__ u32 gen_endbr(void)
 {
 	u32 endbr;
 
@@ -56,7 +56,7 @@ static inline __attribute_const__ u32 gen_endbr(void)
 	return endbr;
 }
 
-static inline __attribute_const__ u32 gen_endbr_poison(void)
+static __always_inline __attribute_const__ u32 gen_endbr_poison(void)
 {
 	/*
 	 * 4 byte NOP that isn't NOP4 (in fact it is OSP NOP3), such that it
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 2dbadf347b5f4..05b86c05e446c 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -94,10 +94,17 @@ __always_inline int is_valid_bugaddr(unsigned long addr)
 
 /*
  * Check for UD1 or UD2, accounting for Address Size Override Prefixes.
- * If it's a UD1, get the ModRM byte to pass along to UBSan.
+ * If it's a UD1, further decode to determine its use:
+ *
+ * UBSan{0}:     67 0f b9 00             ud1    (%eax),%eax
+ * UBSan{10}:    67 0f b9 40 10          ud1    0x10(%eax),%eax
+ * static_call:  0f b9 cc                ud1    %esp,%ecx
+ *
+ * Notably UBSAN uses EAX, static_call uses ECX.
  */
-__always_inline int decode_bug(unsigned long addr, u32 *imm)
+__always_inline int decode_bug(unsigned long addr, s32 *imm, int *len)
 {
+	unsigned long start = addr;
 	u8 v;
 
 	if (addr < TASK_SIZE_MAX)
@@ -110,24 +117,42 @@ __always_inline int decode_bug(unsigned long addr, u32 *imm)
 		return BUG_NONE;
 
 	v = *(u8 *)(addr++);
-	if (v == SECOND_BYTE_OPCODE_UD2)
+	if (v == SECOND_BYTE_OPCODE_UD2) {
+		*len = addr - start;
 		return BUG_UD2;
+	}
 
-	if (!IS_ENABLED(CONFIG_UBSAN_TRAP) || v != SECOND_BYTE_OPCODE_UD1)
+	if (v != SECOND_BYTE_OPCODE_UD1)
 		return BUG_NONE;
 
-	/* Retrieve the immediate (type value) for the UBSAN UD1 */
-	v = *(u8 *)(addr++);
-	if (X86_MODRM_RM(v) == 4)
-		addr++;
-
 	*imm = 0;
-	if (X86_MODRM_MOD(v) == 1)
-		*imm = *(u8 *)addr;
-	else if (X86_MODRM_MOD(v) == 2)
-		*imm = *(u32 *)addr;
-	else
-		WARN_ONCE(1, "Unexpected MODRM_MOD: %u\n", X86_MODRM_MOD(v));
+	v = *(u8 *)(addr++);		/* ModRM */
+
+	if (X86_MODRM_MOD(v) != 3 && X86_MODRM_RM(v) == 4)
+		addr++;			/* SIB */
+
+	/* Decode immediate, if present */
+	switch (X86_MODRM_MOD(v)) {
+	case 0: if (X86_MODRM_RM(v) == 5)
+			addr += 4; /* RIP + disp32 */
+		break;
+
+	case 1: *imm = *(s8 *)addr;
+		addr += 1;
+		break;
+
+	case 2: *imm = *(s32 *)addr;
+		addr += 4;
+		break;
+
+	case 3: break;
+	}
+
+	/* record instruction length */
+	*len = addr - start;
+
+	if (X86_MODRM_REG(v) == 0)	/* EAX */
+		return BUG_UD1_UBSAN;
 
 	return BUG_UD1;
 }
@@ -258,10 +283,10 @@ static inline void handle_invalid_op(struct pt_regs *regs)
 static noinstr bool handle_bug(struct pt_regs *regs)
 {
 	bool handled = false;
-	int ud_type;
-	u32 imm;
+	int ud_type, ud_len;
+	s32 ud_imm;
 
-	ud_type = decode_bug(regs->ip, &imm);
+	ud_type = decode_bug(regs->ip, &ud_imm, &ud_len);
 	if (ud_type == BUG_NONE)
 		return handled;
 
@@ -281,15 +306,28 @@ static noinstr bool handle_bug(struct pt_regs *regs)
 	 */
 	if (regs->flags & X86_EFLAGS_IF)
 		raw_local_irq_enable();
-	if (ud_type == BUG_UD2) {
+
+	switch (ud_type) {
+	case BUG_UD2:
 		if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN ||
 		    handle_cfi_failure(regs) == BUG_TRAP_TYPE_WARN) {
-			regs->ip += LEN_UD2;
+			regs->ip += ud_len;
 			handled = true;
 		}
-	} else if (IS_ENABLED(CONFIG_UBSAN_TRAP)) {
-		pr_crit("%s at %pS\n", report_ubsan_failure(regs, imm), (void *)regs->ip);
+		break;
+
+	case BUG_UD1_UBSAN:
+		if (IS_ENABLED(CONFIG_UBSAN_TRAP)) {
+			pr_crit("%s at %pS\n",
+				report_ubsan_failure(regs, ud_imm),
+				(void *)regs->ip);
+		}
+		break;
+
+	default:
+		break;
 	}
+
 	if (regs->flags & X86_EFLAGS_IF)
 		raw_local_irq_disable();
 	instrumentation_end();

From c4239a72a29d58a4377c2db8583c24f9e2b79d01 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 7 Feb 2025 13:15:37 +0100
Subject: [PATCH 0121/1173] x86/ibt: Clean up poison_endbr()

Basically, get rid of the .warn argument and explicitly don't call the
function when we know there isn't an endbr. This makes the calling
code clearer.

Note: perhaps don't add functions to .cfi_sites when the function
doesn't have endbr -- OTOH why would the compiler emit the prefix if
it has already determined there are no indirect callers and has
omitted the ENDBR instruction.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Link: https://lore.kernel.org/r/20250207122546.815505775@infradead.org
---
 arch/x86/kernel/alternative.c | 43 +++++++++++++++++++++++++++++------
 1 file changed, 36 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index fda11df1e6501..e285933506e99 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -865,14 +865,12 @@ __noendbr bool is_endbr(u32 *val)
 
 static void poison_cfi(void *addr);
 
-static void __init_or_module poison_endbr(void *addr, bool warn)
+static void __init_or_module poison_endbr(void *addr)
 {
 	u32 poison = gen_endbr_poison();
 
-	if (!is_endbr(addr)) {
-		WARN_ON_ONCE(warn);
+	if (WARN_ON_ONCE(!is_endbr(addr)))
 		return;
-	}
 
 	DPRINTK(ENDBR, "ENDBR at: %pS (%px)", addr, addr);
 
@@ -897,7 +895,7 @@ void __init_or_module noinline apply_seal_endbr(s32 *start, s32 *end)
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
 
-		poison_endbr(addr, true);
+		poison_endbr(addr);
 		if (IS_ENABLED(CONFIG_FINEIBT))
 			poison_cfi(addr - 16);
 	}
@@ -1200,6 +1198,14 @@ static int cfi_rewrite_preamble(s32 *start, s32 *end)
 		void *addr = (void *)s + *s;
 		u32 hash;
 
+		/*
+		 * When the function doesn't start with ENDBR the compiler will
+		 * have determined there are no indirect calls to it and we
+		 * don't need no CFI either.
+		 */
+		if (!is_endbr(addr + 16))
+			continue;
+
 		hash = decode_preamble_hash(addr);
 		if (WARN(!hash, "no CFI hash found at: %pS %px %*ph\n",
 			 addr, addr, 5, addr))
@@ -1220,7 +1226,10 @@ static void cfi_rewrite_endbr(s32 *start, s32 *end)
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
 
-		poison_endbr(addr+16, false);
+		if (!is_endbr(addr + 16))
+			continue;
+
+		poison_endbr(addr + 16);
 	}
 }
 
@@ -1353,8 +1362,22 @@ static inline void poison_hash(void *addr)
 
 static void poison_cfi(void *addr)
 {
+	/*
+	 * Compilers manage to be inconsistent with ENDBR vs __cfi prefixes,
+	 * some (static) functions for which they can determine the address
+	 * is never taken do not get a __cfi prefix, but *DO* get an ENDBR.
+	 *
+	 * As such, these functions will get sealed, but we need to be careful
+	 * to not unconditionally scribble the previous function.
+	 */
 	switch (cfi_mode) {
 	case CFI_FINEIBT:
+		/*
+		 * FineIBT prefix should start with an ENDBR.
+		 */
+		if (!is_endbr(addr))
+			break;
+
 		/*
 		 * __cfi_\func:
 		 *	osp nopl (%rax)
@@ -1363,11 +1386,17 @@ static void poison_cfi(void *addr)
 		 *	ud2
 		 * 1:	nop
 		 */
-		poison_endbr(addr, false);
+		poison_endbr(addr);
 		poison_hash(addr + fineibt_preamble_hash);
 		break;
 
 	case CFI_KCFI:
+		/*
+		 * kCFI prefix should start with a valid hash.
+		 */
+		if (!decode_preamble_hash(addr))
+			break;
+
 		/*
 		 * __cfi_\func:
 		 *	movl	$0, %eax

From 306859de59e59f88662b6b56ff2ce3bbb1e375bb Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 7 Feb 2025 13:15:38 +0100
Subject: [PATCH 0122/1173] x86/early_printk: Harden early_serial

Scott found that mem32_serial_in() is an ideal speculation gadget, an
indirectly callable function that takes an adddress and offset and
immediately does a load.

Use static_call() to take away the need for indirect calls and
explicitly seal the functions to ensure they're not callable on IBT
enabled parts.

Reported-by: Scott Constable <scott.d.constable@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Link: https://lore.kernel.org/r/20250207122546.919773202@infradead.org
---
 arch/x86/kernel/early_printk.c | 49 +++++++++++++++++-----------------
 1 file changed, 24 insertions(+), 25 deletions(-)

diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index 44f937015e1e2..fc1714bad0458 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -19,6 +19,7 @@
 #include <linux/usb/ehci_def.h>
 #include <linux/usb/xhci-dbgp.h>
 #include <asm/pci_x86.h>
+#include <linux/static_call.h>
 
 /* Simple VGA output */
 #define VGABASE		(__ISA_IO_base + 0xb8000)
@@ -94,26 +95,28 @@ static unsigned long early_serial_base = 0x3f8;  /* ttyS0 */
 #define DLL             0       /*  Divisor Latch Low         */
 #define DLH             1       /*  Divisor latch High        */
 
-static unsigned int io_serial_in(unsigned long addr, int offset)
+static __noendbr unsigned int io_serial_in(unsigned long addr, int offset)
 {
 	return inb(addr + offset);
 }
+ANNOTATE_NOENDBR_SYM(io_serial_in);
 
-static void io_serial_out(unsigned long addr, int offset, int value)
+static __noendbr void io_serial_out(unsigned long addr, int offset, int value)
 {
 	outb(value, addr + offset);
 }
+ANNOTATE_NOENDBR_SYM(io_serial_out);
 
-static unsigned int (*serial_in)(unsigned long addr, int offset) = io_serial_in;
-static void (*serial_out)(unsigned long addr, int offset, int value) = io_serial_out;
+DEFINE_STATIC_CALL(serial_in, io_serial_in);
+DEFINE_STATIC_CALL(serial_out, io_serial_out);
 
 static int early_serial_putc(unsigned char ch)
 {
 	unsigned timeout = 0xffff;
 
-	while ((serial_in(early_serial_base, LSR) & XMTRDY) == 0 && --timeout)
+	while ((static_call(serial_in)(early_serial_base, LSR) & XMTRDY) == 0 && --timeout)
 		cpu_relax();
-	serial_out(early_serial_base, TXR, ch);
+	static_call(serial_out)(early_serial_base, TXR, ch);
 	return timeout ? 0 : -1;
 }
 
@@ -131,16 +134,16 @@ static __init void early_serial_hw_init(unsigned divisor)
 {
 	unsigned char c;
 
-	serial_out(early_serial_base, LCR, 0x3);	/* 8n1 */
-	serial_out(early_serial_base, IER, 0);	/* no interrupt */
-	serial_out(early_serial_base, FCR, 0);	/* no fifo */
-	serial_out(early_serial_base, MCR, 0x3);	/* DTR + RTS */
+	static_call(serial_out)(early_serial_base, LCR, 0x3);	/* 8n1 */
+	static_call(serial_out)(early_serial_base, IER, 0);	/* no interrupt */
+	static_call(serial_out)(early_serial_base, FCR, 0);	/* no fifo */
+	static_call(serial_out)(early_serial_base, MCR, 0x3);	/* DTR + RTS */
 
-	c = serial_in(early_serial_base, LCR);
-	serial_out(early_serial_base, LCR, c | DLAB);
-	serial_out(early_serial_base, DLL, divisor & 0xff);
-	serial_out(early_serial_base, DLH, (divisor >> 8) & 0xff);
-	serial_out(early_serial_base, LCR, c & ~DLAB);
+	c = static_call(serial_in)(early_serial_base, LCR);
+	static_call(serial_out)(early_serial_base, LCR, c | DLAB);
+	static_call(serial_out)(early_serial_base, DLL, divisor & 0xff);
+	static_call(serial_out)(early_serial_base, DLH, (divisor >> 8) & 0xff);
+	static_call(serial_out)(early_serial_base, LCR, c & ~DLAB);
 }
 
 #define DEFAULT_BAUD 9600
@@ -183,28 +186,26 @@ static __init void early_serial_init(char *s)
 	/* Convert from baud to divisor value */
 	divisor = 115200 / baud;
 
-	/* These will always be IO based ports */
-	serial_in = io_serial_in;
-	serial_out = io_serial_out;
-
 	/* Set up the HW */
 	early_serial_hw_init(divisor);
 }
 
 #ifdef CONFIG_PCI
-static void mem32_serial_out(unsigned long addr, int offset, int value)
+static __noendbr void mem32_serial_out(unsigned long addr, int offset, int value)
 {
 	u32 __iomem *vaddr = (u32 __iomem *)addr;
 	/* shift implied by pointer type */
 	writel(value, vaddr + offset);
 }
+ANNOTATE_NOENDBR_SYM(mem32_serial_out);
 
-static unsigned int mem32_serial_in(unsigned long addr, int offset)
+static __noendbr unsigned int mem32_serial_in(unsigned long addr, int offset)
 {
 	u32 __iomem *vaddr = (u32 __iomem *)addr;
 	/* shift implied by pointer type */
 	return readl(vaddr + offset);
 }
+ANNOTATE_NOENDBR_SYM(mem32_serial_in);
 
 /*
  * early_pci_serial_init()
@@ -278,15 +279,13 @@ static __init void early_pci_serial_init(char *s)
 	 */
 	if ((bar0 & PCI_BASE_ADDRESS_SPACE) == PCI_BASE_ADDRESS_SPACE_IO) {
 		/* it is IO mapped */
-		serial_in = io_serial_in;
-		serial_out = io_serial_out;
 		early_serial_base = bar0 & PCI_BASE_ADDRESS_IO_MASK;
 		write_pci_config(bus, slot, func, PCI_COMMAND,
 				 cmdreg|PCI_COMMAND_IO);
 	} else {
 		/* It is memory mapped - assume 32-bit alignment */
-		serial_in = mem32_serial_in;
-		serial_out = mem32_serial_out;
+		static_call_update(serial_in, mem32_serial_in);
+		static_call_update(serial_out, mem32_serial_out);
 		/* WARNING! assuming the address is always in the first 4G */
 		early_serial_base =
 			(unsigned long)early_ioremap(bar0 & PCI_BASE_ADDRESS_MEM_MASK, 0x10);

From 882b86fd4e0d49bf91148dbadcdbece19ded40e6 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 13 Feb 2025 12:45:47 +0100
Subject: [PATCH 0123/1173] x86/ibt: Handle FineIBT in handle_cfi_failure()

Sami reminded me that FineIBT failure does not hook into the regular
CFI failure case, and as such CFI_PERMISSIVE does not work.

Reported-by: Sami Tolvanen <samitolvanen@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Link: https://lkml.kernel.org/r/20250214092619.GB21726@noisy.programming.kicks-ass.net
---
 arch/x86/include/asm/cfi.h    | 11 +++++++++++
 arch/x86/kernel/alternative.c | 30 ++++++++++++++++++++++++++++++
 arch/x86/kernel/cfi.c         | 22 ++++++++++++++++++----
 3 files changed, 59 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/cfi.h b/arch/x86/include/asm/cfi.h
index 31d19c815f992..7dd5ab239c87b 100644
--- a/arch/x86/include/asm/cfi.h
+++ b/arch/x86/include/asm/cfi.h
@@ -126,6 +126,17 @@ static inline int cfi_get_offset(void)
 
 extern u32 cfi_get_func_hash(void *func);
 
+#ifdef CONFIG_FINEIBT
+extern bool decode_fineibt_insn(struct pt_regs *regs, unsigned long *target, u32 *type);
+#else
+static inline bool
+decode_fineibt_insn(struct pt_regs *regs, unsigned long *target, u32 *type)
+{
+	return false;
+}
+
+#endif
+
 #else
 static inline enum bug_trap_type handle_cfi_failure(struct pt_regs *regs)
 {
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index e285933506e99..247ee5ffbff47 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -1065,6 +1065,7 @@ asm(	".pushsection .rodata			\n"
 	"	endbr64				\n"
 	"	subl	$0x12345678, %r10d	\n"
 	"	je	fineibt_preamble_end	\n"
+	"fineibt_preamble_ud2:			\n"
 	"	ud2				\n"
 	"	nop				\n"
 	"fineibt_preamble_end:			\n"
@@ -1072,9 +1073,11 @@ asm(	".pushsection .rodata			\n"
 );
 
 extern u8 fineibt_preamble_start[];
+extern u8 fineibt_preamble_ud2[];
 extern u8 fineibt_preamble_end[];
 
 #define fineibt_preamble_size (fineibt_preamble_end - fineibt_preamble_start)
+#define fineibt_preamble_ud2  (fineibt_preamble_ud2 - fineibt_preamble_start)
 #define fineibt_preamble_hash 7
 
 asm(	".pushsection .rodata			\n"
@@ -1410,6 +1413,33 @@ static void poison_cfi(void *addr)
 	}
 }
 
+/*
+ * regs->ip points to a UD2 instruction, return true and fill out target and
+ * type when this UD2 is from a FineIBT preamble.
+ *
+ * We check the preamble by checking for the ENDBR instruction relative to the
+ * UD2 instruction.
+ */
+bool decode_fineibt_insn(struct pt_regs *regs, unsigned long *target, u32 *type)
+{
+	unsigned long addr = regs->ip - fineibt_preamble_ud2;
+	u32 endbr, hash;
+
+	__get_kernel_nofault(&endbr, addr, u32, Efault);
+	if (endbr != gen_endbr())
+		return false;
+
+	*target = addr + fineibt_preamble_size;
+
+	__get_kernel_nofault(&hash, addr + fineibt_preamble_hash, u32, Efault);
+	*type = (u32)regs->r10 + hash;
+
+	return true;
+
+Efault:
+	return false;
+}
+
 #else
 
 static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
diff --git a/arch/x86/kernel/cfi.c b/arch/x86/kernel/cfi.c
index e6bf78fac1462..f6905bef0af84 100644
--- a/arch/x86/kernel/cfi.c
+++ b/arch/x86/kernel/cfi.c
@@ -70,11 +70,25 @@ enum bug_trap_type handle_cfi_failure(struct pt_regs *regs)
 	unsigned long target;
 	u32 type;
 
-	if (!is_cfi_trap(regs->ip))
-		return BUG_TRAP_TYPE_NONE;
+	switch (cfi_mode) {
+	case CFI_KCFI:
+		if (!is_cfi_trap(regs->ip))
+			return BUG_TRAP_TYPE_NONE;
+
+		if (!decode_cfi_insn(regs, &target, &type))
+			return report_cfi_failure_noaddr(regs, regs->ip);
+
+		break;
 
-	if (!decode_cfi_insn(regs, &target, &type))
-		return report_cfi_failure_noaddr(regs, regs->ip);
+	case CFI_FINEIBT:
+		if (!decode_fineibt_insn(regs, &target, &type))
+			return BUG_TRAP_TYPE_NONE;
+
+		break;
+
+	default:
+		return BUG_TRAP_TYPE_NONE;
+	}
 
 	return report_cfi_failure(regs, regs->ip, &target, type);
 }

From 0c67c37e1710b2a8f61c8a02db95a51fe577e2c1 Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannelkoong@gmail.com>
Date: Tue, 11 Feb 2025 13:47:50 -0800
Subject: [PATCH 0124/1173] fuse: revert back to __readahead_folio() for
 readahead
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In commit 3eab9d7bc2f4 ("fuse: convert readahead to use folios"), the
logic was converted to using the new folio readahead code, which drops
the reference on the folio once it is locked, using an inferred
reference on the folio. Previously we held a reference on the folio for
the entire duration of the readpages call.

This is fine, however for the case for splice pipe responses where we
will remove the old folio and splice in the new folio (see
fuse_try_move_page()), we assume that there is a reference held on the
folio for ap->folios, which is no longer the case.

To fix this, revert back to __readahead_folio() which allows us to hold
the reference on the folio for the duration of readpages until either we
drop the reference ourselves in fuse_readpages_end() or the reference is
dropped after it's replaced in the page cache in the splice case.
This will fix the UAF bug that was reported.

Link: https://lore.kernel.org/linux-fsdevel/2f681f48-00f5-4e09-8431-2b3dbfaa881e@heusel.eu/
Fixes: 3eab9d7bc2f4 ("fuse: convert readahead to use folios")
Reported-by: Christian Heusel <christian@heusel.eu>
Closes: https://lore.kernel.org/all/2f681f48-00f5-4e09-8431-2b3dbfaa881e@heusel.eu/
Closes: https://gitlab.archlinux.org/archlinux/packaging/packages/linux/-/issues/110
Reported-by: Mantas Mikulėnas <grawity@gmail.com>
Closes: https://lore.kernel.org/all/34feb867-09e2-46e4-aa31-d9660a806d1a@gmail.com/
Closes: https://bugzilla.opensuse.org/show_bug.cgi?id=1236660
Cc: <stable@vger.kernel.org> # v6.13
Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/dev.c  |  6 ++++++
 fs/fuse/file.c | 13 +++++++++++--
 2 files changed, 17 insertions(+), 2 deletions(-)

diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 5b5f789b37eb6..2b2d1b7555444 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -838,6 +838,12 @@ static int fuse_check_folio(struct folio *folio)
 	return 0;
 }
 
+/*
+ * Attempt to steal a page from the splice() pipe and move it into the
+ * pagecache. If successful, the pointer in @pagep will be updated. The
+ * folio that was originally in @pagep will lose a reference and the new
+ * folio returned in @pagep will carry a reference.
+ */
 static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
 {
 	int err;
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 7d92a54799985..d63e56fd3dd20 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -955,8 +955,10 @@ static void fuse_readpages_end(struct fuse_mount *fm, struct fuse_args *args,
 		fuse_invalidate_atime(inode);
 	}
 
-	for (i = 0; i < ap->num_folios; i++)
+	for (i = 0; i < ap->num_folios; i++) {
 		folio_end_read(ap->folios[i], !err);
+		folio_put(ap->folios[i]);
+	}
 	if (ia->ff)
 		fuse_file_put(ia->ff, false);
 
@@ -1048,7 +1050,14 @@ static void fuse_readahead(struct readahead_control *rac)
 		ap = &ia->ap;
 
 		while (ap->num_folios < cur_pages) {
-			folio = readahead_folio(rac);
+			/*
+			 * This returns a folio with a ref held on it.
+			 * The ref needs to be held until the request is
+			 * completed, since the splice case (see
+			 * fuse_try_move_page()) drops the ref after it's
+			 * replaced in the page cache.
+			 */
+			folio = __readahead_folio(rac);
 			ap->folios[ap->num_folios] = folio;
 			ap->descs[ap->num_folios].length = folio_size(folio);
 			ap->num_folios++;

From 8789b4296aa796f658a19cac7d27365012893de1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Andr=C3=A9=20Draszik?= <andre.draszik@linaro.org>
Date: Thu, 5 Dec 2024 10:22:00 +0000
Subject: [PATCH 0125/1173] phy: exynos5-usbdrd: gs101: ensure power is gated
 to SS phy in phy_exit()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We currently don't gate the power to the SS phy in phy_exit().

Shuffle the code slightly to ensure the power is gated to the SS phy as
well.

Fixes: 32267c29bc7d ("phy: exynos5-usbdrd: support Exynos USBDRD 3.1 combo phy (HS & SS)")
CC: stable@vger.kernel.org # 6.11+
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Peter Griffin <peter.griffin@linaro.org>
Signed-off-by: André Draszik <andre.draszik@linaro.org>
Link: https://lore.kernel.org/r/20241205-gs101-usb-phy-fix-v4-1-0278809fb810@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/samsung/phy-exynos5-usbdrd.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/phy/samsung/phy-exynos5-usbdrd.c b/drivers/phy/samsung/phy-exynos5-usbdrd.c
index 4a108fdab118c..46b8f6987c62c 100644
--- a/drivers/phy/samsung/phy-exynos5-usbdrd.c
+++ b/drivers/phy/samsung/phy-exynos5-usbdrd.c
@@ -1296,14 +1296,17 @@ static int exynos5_usbdrd_gs101_phy_exit(struct phy *phy)
 	struct exynos5_usbdrd_phy *phy_drd = to_usbdrd_phy(inst);
 	int ret;
 
+	if (inst->phy_cfg->id == EXYNOS5_DRDPHY_UTMI) {
+		ret = exynos850_usbdrd_phy_exit(phy);
+		if (ret)
+			return ret;
+	}
+
+	exynos5_usbdrd_phy_isol(inst, true);
+
 	if (inst->phy_cfg->id != EXYNOS5_DRDPHY_UTMI)
 		return 0;
 
-	ret = exynos850_usbdrd_phy_exit(phy);
-	if (ret)
-		return ret;
-
-	exynos5_usbdrd_phy_isol(inst, true);
 	return regulator_bulk_disable(phy_drd->drv_data->n_regulators,
 				      phy_drd->regulators);
 }

From 5ab90f40121a9f6a9b368274cd92d0f435dc7cfa Mon Sep 17 00:00:00 2001
From: Andrew Davis <afd@ti.com>
Date: Thu, 23 Jan 2025 12:22:34 -0600
Subject: [PATCH 0126/1173] phy: ti: gmii-sel: Do not use syscon helper to
 build regmap

The syscon helper device_node_to_regmap() is used to fetch a regmap
registered to a device node. It also currently creates this regmap
if the node did not already have a regmap associated with it. This
should only be used on "syscon" nodes. This driver is not such a
device and instead uses device_node_to_regmap() on its own node as
a hacky way to create a regmap for itself.

This will not work going forward and so we should create our regmap
the normal way by defining our regmap_config, fetching our memory
resource, then using the normal regmap_init_mmio() function.

Signed-off-by: Andrew Davis <afd@ti.com>
Tested-by: Nishanth Menon <nm@ti.com>
Link: https://lore.kernel.org/r/20250123182234.597665-1-afd@ti.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/ti/phy-gmii-sel.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/phy/ti/phy-gmii-sel.c b/drivers/phy/ti/phy-gmii-sel.c
index e0ca59ae31531..ff5d5e29629fa 100644
--- a/drivers/phy/ti/phy-gmii-sel.c
+++ b/drivers/phy/ti/phy-gmii-sel.c
@@ -424,6 +424,12 @@ static int phy_gmii_sel_init_ports(struct phy_gmii_sel_priv *priv)
 	return 0;
 }
 
+static const struct regmap_config phy_gmii_sel_regmap_cfg = {
+	.reg_bits = 32,
+	.val_bits = 32,
+	.reg_stride = 4,
+};
+
 static int phy_gmii_sel_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -468,7 +474,14 @@ static int phy_gmii_sel_probe(struct platform_device *pdev)
 
 	priv->regmap = syscon_node_to_regmap(node->parent);
 	if (IS_ERR(priv->regmap)) {
-		priv->regmap = device_node_to_regmap(node);
+		void __iomem *base;
+
+		base = devm_platform_ioremap_resource(pdev, 0);
+		if (IS_ERR(base))
+			return dev_err_probe(dev, PTR_ERR(base),
+					     "failed to get base memory resource\n");
+
+		priv->regmap = regmap_init_mmio(dev, base, &phy_gmii_sel_regmap_cfg);
 		if (IS_ERR(priv->regmap))
 			return dev_err_probe(dev, PTR_ERR(priv->regmap),
 					     "Failed to get syscon\n");

From 55f1a5f7c97c3c92ba469e16991a09274410ceb7 Mon Sep 17 00:00:00 2001
From: BH Hsieh <bhsieh@nvidia.com>
Date: Wed, 22 Jan 2025 18:59:43 +0800
Subject: [PATCH 0127/1173] phy: tegra: xusb: reset VBUS & ID OVERRIDE

Observed VBUS_OVERRIDE & ID_OVERRIDE might be programmed
with unexpected value prior to XUSB PADCTL driver, this
could also occur in virtualization scenario.

For example, UEFI firmware programs ID_OVERRIDE=GROUNDED to set
a type-c port to host mode and keeps the value to kernel.
If the type-c port is connected a usb host, below errors can be
observed right after usb host mode driver gets probed. The errors
would keep until usb role class driver detects the type-c port
as device mode and notifies usb device mode driver to set both
ID_OVERRIDE and VBUS_OVERRIDE to correct value by XUSB PADCTL
driver.

[  173.765814] usb usb3-port2: Cannot enable. Maybe the USB cable is bad?
[  173.765837] usb usb3-port2: config error

Taking virtualization into account, asserting XUSB PADCTL
reset would break XUSB functions used by other guest OS,
hence only reset VBUS & ID OVERRIDE of the port in
utmi_phy_init.

Fixes: bbf711682cd5 ("phy: tegra: xusb: Add Tegra186 support")
Cc: stable@vger.kernel.org
Change-Id: Ic63058d4d49b4a1f8f9ab313196e20ad131cc591
Signed-off-by: BH Hsieh <bhsieh@nvidia.com>
Signed-off-by: Henry Lin <henryl@nvidia.com>
Link: https://lore.kernel.org/r/20250122105943.8057-1-henryl@nvidia.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/tegra/xusb-tegra186.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/phy/tegra/xusb-tegra186.c b/drivers/phy/tegra/xusb-tegra186.c
index 0f60d5d1c1678..fae6242aa730e 100644
--- a/drivers/phy/tegra/xusb-tegra186.c
+++ b/drivers/phy/tegra/xusb-tegra186.c
@@ -928,6 +928,7 @@ static int tegra186_utmi_phy_init(struct phy *phy)
 	unsigned int index = lane->index;
 	struct device *dev = padctl->dev;
 	int err;
+	u32 reg;
 
 	port = tegra_xusb_find_usb2_port(padctl, index);
 	if (!port) {
@@ -935,6 +936,16 @@ static int tegra186_utmi_phy_init(struct phy *phy)
 		return -ENODEV;
 	}
 
+	if (port->mode == USB_DR_MODE_OTG ||
+	    port->mode == USB_DR_MODE_PERIPHERAL) {
+		/* reset VBUS&ID OVERRIDE */
+		reg = padctl_readl(padctl, USB2_VBUS_ID);
+		reg &= ~VBUS_OVERRIDE;
+		reg &= ~ID_OVERRIDE(~0);
+		reg |= ID_OVERRIDE_FLOATING;
+		padctl_writel(padctl, reg, USB2_VBUS_ID);
+	}
+
 	if (port->supply && port->mode == USB_DR_MODE_HOST) {
 		err = regulator_enable(port->supply);
 		if (err) {

From 5755eb0a8168493fddf63d72e0133de54b3a17dd Mon Sep 17 00:00:00 2001
From: Andrew Jeffery <andrew@codeconstruct.com.au>
Date: Mon, 3 Feb 2025 13:26:31 +1030
Subject: [PATCH 0128/1173] MAINTAINERS: Mark Andrew as M: for ASPEED MACHINE
 SUPPORT

From discussion in [1] and in-person with Joel, flip my entry from R:
to M:.

Link: https://lore.kernel.org/all/CACPK8Xe8yZLXzEQPp=1D2f0TsKA7hBZG=pHHW6U51FMpp_BiRQ@mail.gmail.com/ [1]
Cc: Joel Stanley <joel@jms.id.au>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: soc@lists.linux.dev
Cc: linux-aspeed@lists.ozlabs.org
Cc: linux-arm-kernel@lists.infradead.org
Signed-off-by: Andrew Jeffery <andrew@codeconstruct.com.au>
Acked-by: Joel Stanley <joel@jms.id.au>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 25c86f47353de..e3920abb7794f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2284,7 +2284,7 @@ F:	drivers/irqchip/irq-aspeed-i2c-ic.c
 
 ARM/ASPEED MACHINE SUPPORT
 M:	Joel Stanley <joel@jms.id.au>
-R:	Andrew Jeffery <andrew@codeconstruct.com.au>
+M:	Andrew Jeffery <andrew@codeconstruct.com.au>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 L:	linux-aspeed@lists.ozlabs.org (moderated for non-subscribers)
 S:	Supported

From f0570fdc8f72fb1a22bfd2bbf030b34a06da21ff Mon Sep 17 00:00:00 2001
From: Janne Grunau <j@jannau.net>
Date: Sat, 8 Feb 2025 10:22:01 +0100
Subject: [PATCH 0129/1173] MAINTAINERS: arm: apple: Add Janne as maintainer

Sven and I have agreed to share the maintainership for the ARM/APPLE
platform after Marcan's step down. I'm handling the downstream Asahi
Linux tree since April 2024 and worked on or wrote several drivers for
the platform.

Signed-off-by: Janne Grunau <j@jannau.net>
Acked-by: Sven Peter <sven@svenpeter.dev>
Acked-by: Hector Martin <marcan@marcan.st>
Acked-by: Neal Gompa <neal@gompa.dev>
Link: https://lore.kernel.org/r/20250208-maint-soc-apple-v1-1-a7f7337baec0@jannau.net
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index e3920abb7794f..04c90ecf616a2 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2210,6 +2210,7 @@ F:	sound/soc/codecs/ssm3515.c
 
 ARM/APPLE MACHINE SUPPORT
 M:	Sven Peter <sven@svenpeter.dev>
+M:	Janne Grunau <j@jannau.net>
 R:	Alyssa Rosenzweig <alyssa@rosenzweig.io>
 L:	asahi@lists.linux.dev
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)

From be6686b823b30a69b1f71bde228ce042c78a1941 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Wed, 5 Feb 2025 15:41:43 +0100
Subject: [PATCH 0130/1173] firmware: imx: IMX_SCMI_MISC_DRV should depend on
 ARCH_MXC

The i.MX System Controller Management Interface firmware is only present
on Freescale i.MX SoCs.  Hence add a dependency on ARCH_MXC, to prevent
asking the user about this driver when configuring a kernel without
Freescale i.MX platform support.

Fixes: 514b2262ade48a05 ("firmware: arm_scmi: Fix i.MX build dependency")
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Fabio Estevam <festevam@gmail.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 drivers/firmware/imx/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/firmware/imx/Kconfig b/drivers/firmware/imx/Kconfig
index 907cd149c40a8..c964f4924359f 100644
--- a/drivers/firmware/imx/Kconfig
+++ b/drivers/firmware/imx/Kconfig
@@ -25,6 +25,7 @@ config IMX_SCU
 
 config IMX_SCMI_MISC_DRV
 	tristate "IMX SCMI MISC Protocol driver"
+	depends on ARCH_MXC || COMPILE_TEST
 	default y if ARCH_MXC
 	help
 	  The System Controller Management Interface firmware (SCMI FW) is

From dd0f05b98925111f4530d7dab774398cdb32e9e3 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Fri, 14 Feb 2025 09:31:29 +0100
Subject: [PATCH 0131/1173] platform: cznic: CZNIC_PLATFORMS should depend on
 ARCH_MVEBU

CZ.NIC's Turris devices are based on Marvell EBU SoCs.  Hence add a
dependency on ARCH_MVEBU, to prevent asking the user about these drivers
when configuring a kernel that cannot run on an affected CZ.NIC Turris
system.

Fixes: 992f1a3d4e88498d ("platform: cznic: Add preliminary support for Turris Omnia MCU")
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 drivers/platform/cznic/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/platform/cznic/Kconfig b/drivers/platform/cznic/Kconfig
index 49c383eb67854..13e37b49d9d01 100644
--- a/drivers/platform/cznic/Kconfig
+++ b/drivers/platform/cznic/Kconfig
@@ -6,6 +6,7 @@
 
 menuconfig CZNIC_PLATFORMS
 	bool "Platform support for CZ.NIC's Turris hardware"
+	depends on ARCH_MVEBU || COMPILE_TEST
 	help
 	  Say Y here to be able to choose driver support for CZ.NIC's Turris
 	  devices. This option alone does not add any kernel code.

From 70b0d6b0a199c5a3ee6c72f5e61681ed6f759612 Mon Sep 17 00:00:00 2001
From: Sumit Garg <sumit.garg@linaro.org>
Date: Tue, 4 Feb 2025 13:04:18 +0530
Subject: [PATCH 0132/1173] tee: optee: Fix supplicant wait loop

OP-TEE supplicant is a user-space daemon and it's possible for it
be hung or crashed or killed in the middle of processing an OP-TEE
RPC call. It becomes more complicated when there is incorrect shutdown
ordering of the supplicant process vs the OP-TEE client application which
can eventually lead to system hang-up waiting for the closure of the
client application.

Allow the client process waiting in kernel for supplicant response to
be killed rather than indefinitely waiting in an unkillable state. Also,
a normal uninterruptible wait should not have resulted in the hung-task
watchdog getting triggered, but the endless loop would.

This fixes issues observed during system reboot/shutdown when supplicant
got hung for some reason or gets crashed/killed which lead to client
getting hung in an unkillable state. It in turn lead to system being in
hung up state requiring hard power off/on to recover.

Fixes: 4fb0a5eb364d ("tee: add OP-TEE driver")
Suggested-by: Arnd Bergmann <arnd@arndb.de>
Cc: stable@vger.kernel.org
Signed-off-by: Sumit Garg <sumit.garg@linaro.org>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Jens Wiklander <jens.wiklander@linaro.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 drivers/tee/optee/supp.c | 35 ++++++++---------------------------
 1 file changed, 8 insertions(+), 27 deletions(-)

diff --git a/drivers/tee/optee/supp.c b/drivers/tee/optee/supp.c
index 322a543b8c278..d0f397c902420 100644
--- a/drivers/tee/optee/supp.c
+++ b/drivers/tee/optee/supp.c
@@ -80,7 +80,6 @@ u32 optee_supp_thrd_req(struct tee_context *ctx, u32 func, size_t num_params,
 	struct optee *optee = tee_get_drvdata(ctx->teedev);
 	struct optee_supp *supp = &optee->supp;
 	struct optee_supp_req *req;
-	bool interruptable;
 	u32 ret;
 
 	/*
@@ -111,36 +110,18 @@ u32 optee_supp_thrd_req(struct tee_context *ctx, u32 func, size_t num_params,
 	/*
 	 * Wait for supplicant to process and return result, once we've
 	 * returned from wait_for_completion(&req->c) successfully we have
-	 * exclusive access again.
+	 * exclusive access again. Allow the wait to be killable such that
+	 * the wait doesn't turn into an indefinite state if the supplicant
+	 * gets hung for some reason.
 	 */
-	while (wait_for_completion_interruptible(&req->c)) {
+	if (wait_for_completion_killable(&req->c)) {
 		mutex_lock(&supp->mutex);
-		interruptable = !supp->ctx;
-		if (interruptable) {
-			/*
-			 * There's no supplicant available and since the
-			 * supp->mutex currently is held none can
-			 * become available until the mutex released
-			 * again.
-			 *
-			 * Interrupting an RPC to supplicant is only
-			 * allowed as a way of slightly improving the user
-			 * experience in case the supplicant hasn't been
-			 * started yet. During normal operation the supplicant
-			 * will serve all requests in a timely manner and
-			 * interrupting then wouldn't make sense.
-			 */
-			if (req->in_queue) {
-				list_del(&req->link);
-				req->in_queue = false;
-			}
+		if (req->in_queue) {
+			list_del(&req->link);
+			req->in_queue = false;
 		}
 		mutex_unlock(&supp->mutex);
-
-		if (interruptable) {
-			req->ret = TEEC_ERROR_COMMUNICATION;
-			break;
-		}
+		req->ret = TEEC_ERROR_COMMUNICATION;
 	}
 
 	ret = req->ret;

From b3fefbb30a1691533cb905006b69b2a474660744 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Fri, 24 Jan 2025 19:15:23 +0100
Subject: [PATCH 0133/1173] nouveau/svm: fix missing folio unlock + put after
 make_device_exclusive_range()

In case we have to retry the loop, we are missing to unlock+put the
folio. In that case, we will keep failing make_device_exclusive_range()
because we cannot grab the folio lock, and even return from the function
with the folio locked and referenced, effectively never succeeding the
make_device_exclusive_range().

While at it, convert the other unlock+put to use a folio as well.

This was found by code inspection.

Fixes: 8f187163eb89 ("nouveau/svm: implement atomic SVM access")
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Alistair Popple <apopple@nvidia.com>
Tested-by: Alistair Popple <apopple@nvidia.com>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20250124181524.3584236-2-david@redhat.com
---
 drivers/gpu/drm/nouveau/nouveau_svm.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c
index b4da82ddbb6b2..8ea98f06d39af 100644
--- a/drivers/gpu/drm/nouveau/nouveau_svm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_svm.c
@@ -590,6 +590,7 @@ static int nouveau_atomic_range_fault(struct nouveau_svmm *svmm,
 	unsigned long timeout =
 		jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT);
 	struct mm_struct *mm = svmm->notifier.mm;
+	struct folio *folio;
 	struct page *page;
 	unsigned long start = args->p.addr;
 	unsigned long notifier_seq;
@@ -616,12 +617,16 @@ static int nouveau_atomic_range_fault(struct nouveau_svmm *svmm,
 			ret = -EINVAL;
 			goto out;
 		}
+		folio = page_folio(page);
 
 		mutex_lock(&svmm->mutex);
 		if (!mmu_interval_read_retry(&notifier->notifier,
 					     notifier_seq))
 			break;
 		mutex_unlock(&svmm->mutex);
+
+		folio_unlock(folio);
+		folio_put(folio);
 	}
 
 	/* Map the page on the GPU. */
@@ -637,8 +642,8 @@ static int nouveau_atomic_range_fault(struct nouveau_svmm *svmm,
 	ret = nvif_object_ioctl(&svmm->vmm->vmm.object, args, size, NULL);
 	mutex_unlock(&svmm->mutex);
 
-	unlock_page(page);
-	put_page(page);
+	folio_unlock(folio);
+	folio_put(folio);
 
 out:
 	mmu_interval_notifier_remove(&notifier->notifier);

From 8221fd1a73044adef712a5c9346a23c2447f629c Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Fri, 14 Feb 2025 16:43:49 +0000
Subject: [PATCH 0134/1173] workqueue: Log additional details when rejecting
 work

Syzbot regularly runs into the following warning on arm64:

  | WARNING: CPU: 1 PID: 6023 at kernel/workqueue.c:2257 current_wq_worker kernel/workqueue_internal.h:69 [inline]
  | WARNING: CPU: 1 PID: 6023 at kernel/workqueue.c:2257 is_chained_work kernel/workqueue.c:2199 [inline]
  | WARNING: CPU: 1 PID: 6023 at kernel/workqueue.c:2257 __queue_work+0xe50/0x1308 kernel/workqueue.c:2256
  | Modules linked in:
  | CPU: 1 UID: 0 PID: 6023 Comm: klogd Not tainted 6.13.0-rc2-syzkaller-g2e7aff49b5da #0
  | Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/13/2024
  | pstate: 404000c5 (nZcv daIF +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
  | pc : __queue_work+0xe50/0x1308 kernel/workqueue_internal.h:69
  | lr : current_wq_worker kernel/workqueue_internal.h:69 [inline]
  | lr : is_chained_work kernel/workqueue.c:2199 [inline]
  | lr : __queue_work+0xe50/0x1308 kernel/workqueue.c:2256

  [...]

  |    __queue_work+0xe50/0x1308 kernel/workqueue.c:2256 (L)
  |  delayed_work_timer_fn+0x74/0x90 kernel/workqueue.c:2485
  |  call_timer_fn+0x1b4/0x8b8 kernel/time/timer.c:1793
  |  expire_timers kernel/time/timer.c:1839 [inline]
  |  __run_timers kernel/time/timer.c:2418 [inline]
  |  __run_timer_base+0x59c/0x7b4 kernel/time/timer.c:2430
  |  run_timer_base kernel/time/timer.c:2439 [inline]
  |  run_timer_softirq+0xcc/0x194 kernel/time/timer.c:2449

The warning is probably because we are trying to queue work into a
destroyed workqueue, but the softirq context makes it hard to pinpoint
the problematic caller.

Extend the warning diagnostics to print both the function we are trying
to queue as well as the name of the workqueue.

Cc: Tejun Heo <tj@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Link: https://syzkaller.appspot.com/bug?extid=e13e654d315d4da1277c
Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/workqueue.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index ccad33001c58c..902df3253598c 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -2254,8 +2254,10 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
 	 * queues a new work item to a wq after destroy_workqueue(wq).
 	 */
 	if (unlikely(wq->flags & (__WQ_DESTROYING | __WQ_DRAINING) &&
-		     WARN_ON_ONCE(!is_chained_work(wq))))
+		     WARN_ONCE(!is_chained_work(wq), "workqueue: cannot queue %ps on wq %s\n",
+			       work->func, wq->name))) {
 		return;
+	}
 	rcu_read_lock();
 retry:
 	/* pwq which will be used unless @work is executing elsewhere */

From 41758630dd7ea9dce3eb152168c979534b415ab0 Mon Sep 17 00:00:00 2001
From: Niravkumar L Rabara <niravkumar.l.rabara@intel.com>
Date: Wed, 12 Feb 2025 19:25:34 +0800
Subject: [PATCH 0135/1173] dt-bindings: mtd: cadence: document required
 clock-names

The clock-names property is required because the driver requests
the clock by name and not the index.
Update the example to use &clk instead of &nf_clk for the clocks
property to avoid confusion with the clock-names property "nf_clk".

Fixes: 1f05f823a16c (dt-bindings: mtd: cadence: convert cadence-nand-controller.txt to yaml)
Signed-off-by: Niravkumar L Rabara <niravkumar.l.rabara@intel.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 Documentation/devicetree/bindings/mtd/cdns,hp-nfc.yaml | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/mtd/cdns,hp-nfc.yaml b/Documentation/devicetree/bindings/mtd/cdns,hp-nfc.yaml
index 0bed37a994c38..e1f4d7c35a885 100644
--- a/Documentation/devicetree/bindings/mtd/cdns,hp-nfc.yaml
+++ b/Documentation/devicetree/bindings/mtd/cdns,hp-nfc.yaml
@@ -33,6 +33,10 @@ properties:
   clocks:
     maxItems: 1
 
+  clock-names:
+    items:
+      - const: nf_clk
+
   dmas:
     maxItems: 1
 
@@ -51,6 +55,7 @@ required:
   - reg-names
   - interrupts
   - clocks
+  - clock-names
 
 unevaluatedProperties: false
 
@@ -66,7 +71,8 @@ examples:
         #address-cells = <1>;
         #size-cells = <0>;
         interrupts = <GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>;
-        clocks = <&nf_clk>;
+        clocks = <&clk>;
+        clock-names = "nf_clk";
         cdns,board-delay-ps = <4830>;
 
         nand@0 {

From c158647c107358bf1be579f98e4bb705c1953292 Mon Sep 17 00:00:00 2001
From: Komal Bajaj <quic_kbajaj@quicinc.com>
Date: Tue, 19 Nov 2024 12:16:08 +0530
Subject: [PATCH 0136/1173] EDAC/qcom: Correct interrupt enable register
 configuration

The previous implementation incorrectly configured the cmn_interrupt_2_enable
register for interrupt handling. Using cmn_interrupt_2_enable to configure
Tag, Data RAM ECC interrupts would lead to issues like double handling of the
interrupts (EL1 and EL3) as cmn_interrupt_2_enable is meant to be configured
for interrupts which needs to be handled by EL3.

EL1 LLCC EDAC driver needs to use cmn_interrupt_0_enable register to configure
Tag, Data RAM ECC interrupts instead of cmn_interrupt_2_enable.

Fixes: 27450653f1db ("drivers: edac: Add EDAC driver support for QCOM SoCs")
Signed-off-by: Komal Bajaj <quic_kbajaj@quicinc.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Cc: <stable@kernel.org>
Link: https://lore.kernel.org/r/20241119064608.12326-1-quic_kbajaj@quicinc.com
---
 drivers/edac/qcom_edac.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/edac/qcom_edac.c b/drivers/edac/qcom_edac.c
index 04c42c83a2bad..f3da9385ca0d8 100644
--- a/drivers/edac/qcom_edac.c
+++ b/drivers/edac/qcom_edac.c
@@ -95,7 +95,7 @@ static int qcom_llcc_core_setup(struct llcc_drv_data *drv, struct regmap *llcc_b
 	 * Configure interrupt enable registers such that Tag, Data RAM related
 	 * interrupts are propagated to interrupt controller for servicing
 	 */
-	ret = regmap_update_bits(llcc_bcast_regmap, drv->edac_reg_offset->cmn_interrupt_2_enable,
+	ret = regmap_update_bits(llcc_bcast_regmap, drv->edac_reg_offset->cmn_interrupt_0_enable,
 				 TRP0_INTERRUPT_ENABLE,
 				 TRP0_INTERRUPT_ENABLE);
 	if (ret)
@@ -113,7 +113,7 @@ static int qcom_llcc_core_setup(struct llcc_drv_data *drv, struct regmap *llcc_b
 	if (ret)
 		return ret;
 
-	ret = regmap_update_bits(llcc_bcast_regmap, drv->edac_reg_offset->cmn_interrupt_2_enable,
+	ret = regmap_update_bits(llcc_bcast_regmap, drv->edac_reg_offset->cmn_interrupt_0_enable,
 				 DRP0_INTERRUPT_ENABLE,
 				 DRP0_INTERRUPT_ENABLE);
 	if (ret)

From fb8179ce2996bffaa36a04e2b6262843b01b7565 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Mon, 4 Nov 2024 13:03:13 -0600
Subject: [PATCH 0137/1173] riscv: cacheinfo: Use of_property_present() for
 non-boolean properties
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The use of of_property_read_bool() for non-boolean properties is
deprecated in favor of of_property_present() when testing for property
presence.

Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: Clément Léger <cleger@rivosinc.com>
Cc: stable@vger.kernel.org
Fixes: 76d2a0493a17 ("RISC-V: Init and Halt Code")
Link: https://lore.kernel.org/r/20241104190314.270095-1-robh@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/kernel/cacheinfo.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c
index 2d40736fc37ce..26b085dbdd073 100644
--- a/arch/riscv/kernel/cacheinfo.c
+++ b/arch/riscv/kernel/cacheinfo.c
@@ -108,11 +108,11 @@ int populate_cache_leaves(unsigned int cpu)
 	if (!np)
 		return -ENOENT;
 
-	if (of_property_read_bool(np, "cache-size"))
+	if (of_property_present(np, "cache-size"))
 		ci_leaf_init(this_leaf++, CACHE_TYPE_UNIFIED, level);
-	if (of_property_read_bool(np, "i-cache-size"))
+	if (of_property_present(np, "i-cache-size"))
 		ci_leaf_init(this_leaf++, CACHE_TYPE_INST, level);
-	if (of_property_read_bool(np, "d-cache-size"))
+	if (of_property_present(np, "d-cache-size"))
 		ci_leaf_init(this_leaf++, CACHE_TYPE_DATA, level);
 
 	prev = np;
@@ -125,11 +125,11 @@ int populate_cache_leaves(unsigned int cpu)
 			break;
 		if (level <= levels)
 			break;
-		if (of_property_read_bool(np, "cache-size"))
+		if (of_property_present(np, "cache-size"))
 			ci_leaf_init(this_leaf++, CACHE_TYPE_UNIFIED, level);
-		if (of_property_read_bool(np, "i-cache-size"))
+		if (of_property_present(np, "i-cache-size"))
 			ci_leaf_init(this_leaf++, CACHE_TYPE_INST, level);
-		if (of_property_read_bool(np, "d-cache-size"))
+		if (of_property_present(np, "d-cache-size"))
 			ci_leaf_init(this_leaf++, CACHE_TYPE_DATA, level);
 		levels = level;
 	}

From c6ec1e1b078d8e2ecd075e46db6197a14930a3fc Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= <cleger@rivosinc.com>
Date: Mon, 10 Feb 2025 16:56:14 +0100
Subject: [PATCH 0138/1173] riscv: cpufeature: use bitmap_equal() instead of
 memcmp()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Comparison of bitmaps should be done using bitmap_equal(), not memcmp(),
use the former one to compare isa bitmaps.

Signed-off-by: Clément Léger <cleger@rivosinc.com>
Fixes: 625034abd52a8c ("riscv: add ISA extensions validation callback")
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250210155615.1545738-1-cleger@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/kernel/cpufeature.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index c6ba750536c32..40ac72e407b68 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -479,7 +479,7 @@ static void __init riscv_resolve_isa(unsigned long *source_isa,
 			if (bit < RISCV_ISA_EXT_BASE)
 				*this_hwcap |= isa2hwcap[bit];
 		}
-	} while (loop && memcmp(prev_resolved_isa, resolved_isa, sizeof(prev_resolved_isa)));
+	} while (loop && !bitmap_equal(prev_resolved_isa, resolved_isa, RISCV_ISA_EXT_MAX));
 }
 
 static void __init match_isa_ext(const char *name, const char *name_end, unsigned long *bitmap)

From 1898300abf3508bca152e65b36cce5bf93d7e63e Mon Sep 17 00:00:00 2001
From: Andreas Schwab <schwab@suse.de>
Date: Thu, 30 Jan 2025 10:25:38 +0100
Subject: [PATCH 0139/1173] riscv/atomic: Do proper sign extension also for
 unsigned in arch_cmpxchg

Sign extend also an unsigned compare value to match what lr.w is doing.
Otherwise try_cmpxchg may spuriously return true when used on a u32 value
that has the sign bit set, as it happens often in inode_set_ctime_current.

Do this in three conversion steps.  The first conversion to long is needed
to avoid a -Wpointer-to-int-cast warning when arch_cmpxchg is used with a
pointer type.  Then convert to int and back to long to always sign extend
the 32-bit value to 64-bit.

Fixes: 6c58f25e6938 ("riscv/atomic: Fix sign extension for RV64I")
Signed-off-by: Andreas Schwab <schwab@suse.de>
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Tested-by: Xi Ruoyao <xry111@xry111.site>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/mvmed0k4prh.fsf@suse.de
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/cmpxchg.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index 4cadc56220fea..427c41dde6431 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -231,7 +231,7 @@
 		__arch_cmpxchg(".w", ".w" sc_sfx, ".w" cas_sfx,		\
 			       sc_prepend, sc_append,			\
 			       cas_prepend, cas_append,			\
-			       __ret, __ptr, (long), __old, __new);	\
+			       __ret, __ptr, (long)(int)(long), __old, __new);	\
 		break;							\
 	case 8:								\
 		__arch_cmpxchg(".d", ".d" sc_sfx, ".d" cas_sfx,		\

From 599c44cd21f4967774e0acf58f734009be4aea9a Mon Sep 17 00:00:00 2001
From: Andreas Schwab <schwab@suse.de>
Date: Mon, 3 Feb 2025 11:06:00 +0100
Subject: [PATCH 0140/1173] riscv/futex: sign extend compare value in atomic
 cmpxchg
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Make sure the compare value in the lr/sc loop is sign extended to match
what lr.w does.  Fortunately, due to the compiler keeping the register
contents sign extended anyway the lack of the explicit extension didn't
result in wrong code so far, but this cannot be relied upon.

Fixes: b90edb33010b ("RISC-V: Add futex support.")
Signed-off-by: Andreas Schwab <schwab@suse.de>
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Björn Töpel <bjorn@rivosinc.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/mvmfrkv2vhz.fsf@suse.de
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/futex.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/include/asm/futex.h b/arch/riscv/include/asm/futex.h
index 72be100afa236..90c86b115e008 100644
--- a/arch/riscv/include/asm/futex.h
+++ b/arch/riscv/include/asm/futex.h
@@ -93,7 +93,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		_ASM_EXTABLE_UACCESS_ERR(1b, 3b, %[r])	\
 		_ASM_EXTABLE_UACCESS_ERR(2b, 3b, %[r])	\
 	: [r] "+r" (ret), [v] "=&r" (val), [u] "+m" (*uaddr), [t] "=&r" (tmp)
-	: [ov] "Jr" (oldval), [nv] "Jr" (newval)
+	: [ov] "Jr" ((long)(int)oldval), [nv] "Jr" (newval)
 	: "memory");
 	__disable_user_access();
 

From 713e788c0e07e185fd44dd581f74855ef149722f Mon Sep 17 00:00:00 2001
From: Stafford Horne <shorne@gmail.com>
Date: Tue, 14 Jan 2025 17:07:21 +0000
Subject: [PATCH 0141/1173] rseq/selftests: Fix riscv rseq_offset_deref_addv
 inline asm

When working on OpenRISC support for restartable sequences I noticed
and fixed these two issues with the riscv support bits.

 1 The 'inc' argument to RSEQ_ASM_OP_R_DEREF_ADDV was being implicitly
   passed to the macro.  Fix this by adding 'inc' to the list of macro
   arguments.
 2 The inline asm input constraints for 'inc' and 'off' use "er",  The
   riscv gcc port does not have an "e" constraint, this looks to be
   copied from the x86 port.  Fix this by just using an "r" constraint.

I have compile tested this only for riscv.  However, the same fixes I
use in the OpenRISC rseq selftests and everything passes with no issues.

Fixes: 171586a6ab66 ("selftests/rseq: riscv: Template memory ordering and percpu access mode")
Signed-off-by: Stafford Horne <shorne@gmail.com>
Tested-by: Charlie Jenkins <charlie@rivosinc.com>
Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: Shuah Khan <skhan@linuxfoundation.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250114170721.3613280-1-shorne@gmail.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 tools/testing/selftests/rseq/rseq-riscv-bits.h | 6 +++---
 tools/testing/selftests/rseq/rseq-riscv.h      | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/rseq/rseq-riscv-bits.h b/tools/testing/selftests/rseq/rseq-riscv-bits.h
index de31a0143139b..f02f411d550d1 100644
--- a/tools/testing/selftests/rseq/rseq-riscv-bits.h
+++ b/tools/testing/selftests/rseq/rseq-riscv-bits.h
@@ -243,7 +243,7 @@ int RSEQ_TEMPLATE_IDENTIFIER(rseq_offset_deref_addv)(intptr_t *ptr, off_t off, i
 #ifdef RSEQ_COMPARE_TWICE
 				  RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, "%l[error1]")
 #endif
-				  RSEQ_ASM_OP_R_DEREF_ADDV(ptr, off, 3)
+				  RSEQ_ASM_OP_R_DEREF_ADDV(ptr, off, inc, 3)
 				  RSEQ_INJECT_ASM(4)
 				  RSEQ_ASM_DEFINE_ABORT(4, abort)
 				  : /* gcc asm goto does not allow outputs */
@@ -251,8 +251,8 @@ int RSEQ_TEMPLATE_IDENTIFIER(rseq_offset_deref_addv)(intptr_t *ptr, off_t off, i
 				    [current_cpu_id]		"m" (rseq_get_abi()->RSEQ_TEMPLATE_CPU_ID_FIELD),
 				    [rseq_cs]			"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 				    [ptr]			"r" (ptr),
-				    [off]			"er" (off),
-				    [inc]			"er" (inc)
+				    [off]			"r" (off),
+				    [inc]			"r" (inc)
 				    RSEQ_INJECT_INPUT
 				  : "memory", RSEQ_ASM_TMP_REG_1
 				    RSEQ_INJECT_CLOBBER
diff --git a/tools/testing/selftests/rseq/rseq-riscv.h b/tools/testing/selftests/rseq/rseq-riscv.h
index 37e598d0a365e..67d544aaa9a3b 100644
--- a/tools/testing/selftests/rseq/rseq-riscv.h
+++ b/tools/testing/selftests/rseq/rseq-riscv.h
@@ -158,7 +158,7 @@ do {									\
 	"bnez	" RSEQ_ASM_TMP_REG_1 ", 222b\n"				\
 	"333:\n"
 
-#define RSEQ_ASM_OP_R_DEREF_ADDV(ptr, off, post_commit_label)		\
+#define RSEQ_ASM_OP_R_DEREF_ADDV(ptr, off, inc, post_commit_label)	\
 	"mv	" RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(ptr) "]\n"	\
 	RSEQ_ASM_OP_R_ADD(off)						\
 	REG_L	  RSEQ_ASM_TMP_REG_1 ", 0(" RSEQ_ASM_TMP_REG_1 ")\n"	\

From aa49bc2ca8524186ceb0811c23a7f00c3dea6987 Mon Sep 17 00:00:00 2001
From: Yong-Xuan Wang <yongxuan.wang@sifive.com>
Date: Fri, 20 Dec 2024 16:39:23 +0800
Subject: [PATCH 0142/1173] riscv: signal: fix signal frame size

The signal context of certain RISC-V extensions will be appended after
struct __riscv_extra_ext_header, which already includes an empty context
header. Therefore, there is no need to preserve a separate hdr for the
END of signal context.

Fixes: 8ee0b41898fa ("riscv: signal: Add sigcontext save/restore for vector")
Signed-off-by: Yong-Xuan Wang <yongxuan.wang@sifive.com>
Reviewed-by: Zong Li <zong.li@sifive.com>
Reviewed-by: Andy Chiu <AndybnAC@gmail.com>
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20241220083926.19453-2-yongxuan.wang@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/kernel/signal.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index 94e905eea1dee..08378fea3a111 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -215,12 +215,6 @@ static size_t get_rt_frame_size(bool cal_all)
 		if (cal_all || riscv_v_vstate_query(task_pt_regs(current)))
 			total_context_size += riscv_v_sc_size;
 	}
-	/*
-	 * Preserved a __riscv_ctx_hdr for END signal context header if an
-	 * extension uses __riscv_extra_ext_header
-	 */
-	if (total_context_size)
-		total_context_size += sizeof(struct __riscv_ctx_hdr);
 
 	frame_size += total_context_size;
 

From 564fc8eb6f78e01292ff10801f318feae6153fdd Mon Sep 17 00:00:00 2001
From: Yong-Xuan Wang <yongxuan.wang@sifive.com>
Date: Fri, 20 Dec 2024 16:39:24 +0800
Subject: [PATCH 0143/1173] riscv: signal: fix signal_minsigstksz

The init_rt_signal_env() funciton is called before the alternative patch
is applied, so using the alternative-related API to check the availability
of an extension within this function doesn't have the intended effect.
This patch reorders the init_rt_signal_env() and apply_boot_alternatives()
to get the correct signal_minsigstksz.

Fixes: e92f469b0771 ("riscv: signal: Report signal frame size to userspace via auxv")
Signed-off-by: Yong-Xuan Wang <yongxuan.wang@sifive.com>
Reviewed-by: Zong Li <zong.li@sifive.com>
Reviewed-by: Andy Chiu <andybnac@gmail.com>
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20241220083926.19453-3-yongxuan.wang@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/kernel/setup.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index f1793630fc518..4fe45daa6281e 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -322,8 +322,8 @@ void __init setup_arch(char **cmdline_p)
 
 	riscv_init_cbo_blocksizes();
 	riscv_fill_hwcap();
-	init_rt_signal_env();
 	apply_boot_alternatives();
+	init_rt_signal_env();
 
 	if (IS_ENABLED(CONFIG_RISCV_ISA_ZICBOM) &&
 	    riscv_isa_extension_available(NULL, ZICBOM))

From 245aece3750d3692ae7a44516c1096936bded7ab Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Thu, 12 Dec 2024 14:11:34 +0100
Subject: [PATCH 0144/1173] MAINTAINERS: Add myself as a riscv reviewer
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The goal is for me to get a kernel.org account and then send pull requests
in order to relieve some pressure from Palmer and make our workflow
smoother.

Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Enthusiastically-Supported-by: Björn Töpel <bjorn@kernel.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20241212131134.288819-1-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 896a307fa0654..ebc3e39dbcaab 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -20280,6 +20280,7 @@ RISC-V ARCHITECTURE
 M:	Paul Walmsley <paul.walmsley@sifive.com>
 M:	Palmer Dabbelt <palmer@dabbelt.com>
 M:	Albert Ou <aou@eecs.berkeley.edu>
+R:	Alexandre Ghiti <alex@ghiti.fr>
 L:	linux-riscv@lists.infradead.org
 S:	Supported
 Q:	https://patchwork.kernel.org/project/linux-riscv/list/

From 13918315c5dc5a515926c8799042ea6885c2b734 Mon Sep 17 00:00:00 2001
From: Uday Shankar <ushankar@purestorage.com>
Date: Sat, 8 Feb 2025 13:42:13 -0700
Subject: [PATCH 0145/1173] io-wq: backoff when retrying worker creation

When io_uring submission goes async for the first time on a given task,
we'll try to create a worker thread to handle the submission. Creating
this worker thread can fail due to various transient conditions, such as
an outstanding signal in the forking thread, so we have retry logic with
a limit of 3 retries. However, this retry logic appears to be too
aggressive/fast - we've observed a thread blowing through the retry
limit while having the same outstanding signal the whole time. Here's an
excerpt of some tracing that demonstrates the issue:

First, signal 26 is generated for the process. It ends up getting routed
to thread 92942.

 0)   cbd-92284    /* signal_generate: sig=26 errno=0 code=-2 comm=psblkdASD pid=92934 grp=1 res=0 */

This causes create_io_thread in the signalled thread to fail with
ERESTARTNOINTR, and thus a retry is queued.

13) task_th-92942  /* io_uring_queue_async_work: ring 000000007325c9ae, request 0000000080c96d8e, user_data 0x0, opcode URING_CMD, flags 0x8240001, normal queue, work 000000006e96dd3f */
13) task_th-92942  io_wq_enqueue() {
13) task_th-92942    _raw_spin_lock();
13) task_th-92942    io_wq_activate_free_worker();
13) task_th-92942    _raw_spin_lock();
13) task_th-92942    create_io_worker() {
13) task_th-92942      __kmalloc_cache_noprof();
13) task_th-92942      __init_swait_queue_head();
13) task_th-92942      kprobe_ftrace_handler() {
13) task_th-92942        get_kprobe();
13) task_th-92942        aggr_pre_handler() {
13) task_th-92942          pre_handler_kretprobe();
13) task_th-92942          /* create_enter: (create_io_thread+0x0/0x50) fn=0xffffffff8172c0e0 arg=0xffff888996bb69c0 node=-1 */
13) task_th-92942        } /* aggr_pre_handler */
...
13) task_th-92942        } /* copy_process */
13) task_th-92942      } /* create_io_thread */
13) task_th-92942      kretprobe_rethook_handler() {
13) task_th-92942        /* create_exit: (create_io_worker+0x8a/0x1a0 <- create_io_thread) arg1=0xfffffffffffffdff */
13) task_th-92942      } /* kretprobe_rethook_handler */
13) task_th-92942    queue_work_on() {
...

The CPU is then handed to a kworker to process the queued retry:

------------------------------------------
 13) task_th-92942  => kworker-54154
------------------------------------------
13) kworker-54154  io_workqueue_create() {
13) kworker-54154    io_queue_worker_create() {
13) kworker-54154      task_work_add() {
13) kworker-54154        wake_up_state() {
13) kworker-54154          try_to_wake_up() {
13) kworker-54154            _raw_spin_lock_irqsave();
13) kworker-54154            _raw_spin_unlock_irqrestore();
13) kworker-54154          } /* try_to_wake_up */
13) kworker-54154        } /* wake_up_state */
13) kworker-54154        kick_process();
13) kworker-54154      } /* task_work_add */
13) kworker-54154    } /* io_queue_worker_create */
13) kworker-54154  } /* io_workqueue_create */

And then we immediately switch back to the original task to try creating
a worker again. This fails, because the original task still hasn't
handled its signal.

-----------------------------------------
 13) kworker-54154  => task_th-92942
------------------------------------------
13) task_th-92942  create_worker_cont() {
13) task_th-92942    kprobe_ftrace_handler() {
13) task_th-92942      get_kprobe();
13) task_th-92942      aggr_pre_handler() {
13) task_th-92942        pre_handler_kretprobe();
13) task_th-92942        /* create_enter: (create_io_thread+0x0/0x50) fn=0xffffffff8172c0e0 arg=0xffff888996bb69c0 node=-1 */
13) task_th-92942      } /* aggr_pre_handler */
13) task_th-92942    } /* kprobe_ftrace_handler */
13) task_th-92942    create_io_thread() {
13) task_th-92942      copy_process() {
13) task_th-92942        task_active_pid_ns();
13) task_th-92942        _raw_spin_lock_irq();
13) task_th-92942        recalc_sigpending();
13) task_th-92942        _raw_spin_lock_irq();
13) task_th-92942      } /* copy_process */
13) task_th-92942    } /* create_io_thread */
13) task_th-92942    kretprobe_rethook_handler() {
13) task_th-92942      /* create_exit: (create_worker_cont+0x35/0x1b0 <- create_io_thread) arg1=0xfffffffffffffdff */
13) task_th-92942    } /* kretprobe_rethook_handler */
13) task_th-92942    io_worker_release();
13) task_th-92942    queue_work_on() {
13) task_th-92942      clear_pending_if_disabled();
13) task_th-92942      __queue_work() {
13) task_th-92942      } /* __queue_work */
13) task_th-92942    } /* queue_work_on */
13) task_th-92942  } /* create_worker_cont */

The pattern repeats another couple times until we blow through the retry
counter, at which point we give up. All outstanding work is canceled,
and the io_uring command which triggered all this is failed with
ECANCELED:

13) task_th-92942  io_acct_cancel_pending_work() {
...
13) task_th-92942  /* io_uring_complete: ring 000000007325c9ae, req 0000000080c96d8e, user_data 0x0, result -125, cflags 0x0 extra1 0 extra2 0  */

Finally, the task gets around to processing its outstanding signal 26,
but it's too late.

13) task_th-92942  /* signal_deliver: sig=26 errno=0 code=-2 sa_handler=59566a0 sa_flags=14000000 */

Try to address this issue by adding a small scaling delay when retrying
worker creation. This should give the forking thread time to handle its
signal in the above case. This isn't a particularly satisfying solution,
as sufficiently paradoxical scheduling would still have us hitting the
same issue, and I'm open to suggestions for something better. But this
is likely to prevent this (already rare) issue from hitting in practice.

Signed-off-by: Uday Shankar <ushankar@purestorage.com>
Link: https://lore.kernel.org/r/20250208-wq_retry-v2-1-4f6f5041d303@purestorage.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/io-wq.c | 23 ++++++++++++++++++-----
 1 file changed, 18 insertions(+), 5 deletions(-)

diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c
index 5d0928f37471e..91019b4d03088 100644
--- a/io_uring/io-wq.c
+++ b/io_uring/io-wq.c
@@ -64,7 +64,7 @@ struct io_worker {
 
 	union {
 		struct rcu_head rcu;
-		struct work_struct work;
+		struct delayed_work work;
 	};
 };
 
@@ -770,6 +770,18 @@ static inline bool io_should_retry_thread(struct io_worker *worker, long err)
 	}
 }
 
+static void queue_create_worker_retry(struct io_worker *worker)
+{
+	/*
+	 * We only bother retrying because there's a chance that the
+	 * failure to create a worker is due to some temporary condition
+	 * in the forking task (e.g. outstanding signal); give the task
+	 * some time to clear that condition.
+	 */
+	schedule_delayed_work(&worker->work,
+			      msecs_to_jiffies(worker->init_retries * 5));
+}
+
 static void create_worker_cont(struct callback_head *cb)
 {
 	struct io_worker *worker;
@@ -809,12 +821,13 @@ static void create_worker_cont(struct callback_head *cb)
 
 	/* re-create attempts grab a new worker ref, drop the existing one */
 	io_worker_release(worker);
-	schedule_work(&worker->work);
+	queue_create_worker_retry(worker);
 }
 
 static void io_workqueue_create(struct work_struct *work)
 {
-	struct io_worker *worker = container_of(work, struct io_worker, work);
+	struct io_worker *worker = container_of(work, struct io_worker,
+						work.work);
 	struct io_wq_acct *acct = io_wq_get_acct(worker);
 
 	if (!io_queue_worker_create(worker, acct, create_worker_cont))
@@ -855,8 +868,8 @@ static bool create_io_worker(struct io_wq *wq, int index)
 		kfree(worker);
 		goto fail;
 	} else {
-		INIT_WORK(&worker->work, io_workqueue_create);
-		schedule_work(&worker->work);
+		INIT_DELAYED_WORK(&worker->work, io_workqueue_create);
+		queue_create_worker_retry(worker);
 	}
 
 	return true;

From 43c70b104093c324b1a000762ce943d16ce788f9 Mon Sep 17 00:00:00 2001
From: Caleb Sander Mateos <csander@purestorage.com>
Date: Fri, 14 Feb 2025 12:36:36 -0700
Subject: [PATCH 0146/1173] block/merge: remove unnecessary min() with UINT_MAX

In bvec_split_segs(), max_bytes is an unsigned, so it must be less than
or equal to UINT_MAX. Remove the unnecessary min().

Prior to commit 67927d220150 ("block/merge: count bytes instead of
sectors"), the min() was with UINT_MAX >> 9, so it did have an effect.

Signed-off-by: Caleb Sander Mateos <csander@purestorage.com>
Link: https://lore.kernel.org/r/20250214193637.234702-1-csander@purestorage.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-merge.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/block/blk-merge.c b/block/blk-merge.c
index 15cd231d560cb..39b738c0e4c9a 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -270,7 +270,7 @@ static bool bvec_split_segs(const struct queue_limits *lim,
 		const struct bio_vec *bv, unsigned *nsegs, unsigned *bytes,
 		unsigned max_segs, unsigned max_bytes)
 {
-	unsigned max_len = min(max_bytes, UINT_MAX) - *bytes;
+	unsigned max_len = max_bytes - *bytes;
 	unsigned len = min(bv->bv_len, max_len);
 	unsigned total_len = 0;
 	unsigned seg_size = 0;

From 1e988c3fe1264708f4f92109203ac5b1d65de50b Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Fri, 14 Feb 2025 22:48:15 +0000
Subject: [PATCH 0147/1173] io_uring: prevent opcode speculation

sqe->opcode is used for different tables, make sure we santitise it
against speculations.

Cc: stable@vger.kernel.org
Fixes: d3656344fea03 ("io_uring: add lookup table for various opcode needs")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Li Zetao <lizetao1@huawei.com>
Link: https://lore.kernel.org/r/7eddbf31c8ca0a3947f8ed98271acc2b4349c016.1739568408.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/io_uring.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 263e504be4a8b..29a42365a4816 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -2045,6 +2045,8 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 		req->opcode = 0;
 		return io_init_fail_req(req, -EINVAL);
 	}
+	opcode = array_index_nospec(opcode, IORING_OP_LAST);
+
 	def = &io_issue_defs[opcode];
 	if (unlikely(sqe_flags & ~SQE_COMMON_FLAGS)) {
 		/* enforce forwards compatibility on users */

From ef24989a62eefa6293a6c1c59dbb8b7e646e76dd Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Date: Thu, 13 Feb 2025 17:44:43 +0100
Subject: [PATCH 0148/1173] drm/msm/a6xx: Only print the GMU firmware version
 once

We only fetch it once from userland, so let's also only notify the
user once and not on every runtime resume.

As you can notice by the tags chain, more than one user found this
annoying.

Reported-by: Jens Glathe <jens.glathe@oldschoolsolutions.biz>
Suggested-by: Abel Vesa <abel.vesa@linaro.org>
Suggested-by: Rob Clark <robdclark@chromium.org>
Signed-off-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Patchwork: https://patchwork.freedesktop.org/patch/637062/
Signed-off-by: Rob Clark <robdclark@chromium.org>
---
 drivers/gpu/drm/msm/adreno/a6xx_gmu.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index 65d38b25c0707..699b0dd34b18f 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -813,10 +813,10 @@ static int a6xx_gmu_fw_load(struct a6xx_gmu *gmu)
 	}
 
 	ver = gmu_read(gmu, REG_A6XX_GMU_CORE_FW_VERSION);
-	DRM_INFO("Loaded GMU firmware v%u.%u.%u\n",
-		 FIELD_GET(A6XX_GMU_CORE_FW_VERSION_MAJOR__MASK, ver),
-		 FIELD_GET(A6XX_GMU_CORE_FW_VERSION_MINOR__MASK, ver),
-		 FIELD_GET(A6XX_GMU_CORE_FW_VERSION_STEP__MASK, ver));
+	DRM_INFO_ONCE("Loaded GMU firmware v%u.%u.%u\n",
+		      FIELD_GET(A6XX_GMU_CORE_FW_VERSION_MAJOR__MASK, ver),
+		      FIELD_GET(A6XX_GMU_CORE_FW_VERSION_MINOR__MASK, ver),
+		      FIELD_GET(A6XX_GMU_CORE_FW_VERSION_STEP__MASK, ver));
 
 	return 0;
 }

From 669c285620231786fffe9d87ab432e08a6ed922b Mon Sep 17 00:00:00 2001
From: Rob Clark <robdclark@chromium.org>
Date: Mon, 13 Jan 2025 07:48:41 -0800
Subject: [PATCH 0149/1173] drm/msm: Avoid rounding up to one jiffy

If userspace is trying to achieve a timeout of zero, let 'em have it.
Only round up if the timeout is greater than zero.

Fixes: 4969bccd5f4e ("drm/msm: Avoid rounding down to zero jiffies")
Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Akhil P Oommen <quic_akhilpo@quicinc.com>
Patchwork: https://patchwork.freedesktop.org/patch/632264/
---
 drivers/gpu/drm/msm/msm_drv.h | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index fee31680a6d54..a650778552017 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -537,15 +537,12 @@ static inline int align_pitch(int width, int bpp)
 static inline unsigned long timeout_to_jiffies(const ktime_t *timeout)
 {
 	ktime_t now = ktime_get();
-	s64 remaining_jiffies;
 
-	if (ktime_compare(*timeout, now) < 0) {
-		remaining_jiffies = 0;
-	} else {
-		ktime_t rem = ktime_sub(*timeout, now);
-		remaining_jiffies = ktime_divns(rem, NSEC_PER_SEC / HZ);
-	}
+	if (ktime_compare(*timeout, now) <= 0)
+		return 0;
 
+	ktime_t rem = ktime_sub(*timeout, now);
+	s64 remaining_jiffies = ktime_divns(rem, NSEC_PER_SEC / HZ);
 	return clamp(remaining_jiffies, 1LL, (s64)INT_MAX);
 }
 

From 2f69e54584475ac85ea0e3407c9198ac7c6ea8ad Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Sat, 14 Dec 2024 00:14:17 +0200
Subject: [PATCH 0150/1173] drm/msm/dpu: skip watchdog timer programming
 through TOP on >= SM8450

The SM8450 and later chips have DPU_MDP_PERIPH_0_REMOVED feature bit
set, which means that those platforms have dropped some of the
registers, including the WD TIMER-related ones. Stop providing the
callback to program WD timer on those platforms.

Fixes: 100d7ef6995d ("drm/msm/dpu: add support for SM8450")
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Patchwork: https://patchwork.freedesktop.org/patch/628874/
Link: https://lore.kernel.org/r/20241214-dpu-drop-features-v1-1-988f0662cb7e@linaro.org
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c
index ad19330de61ab..562a3f4c5238a 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c
@@ -272,7 +272,7 @@ static void _setup_mdp_ops(struct dpu_hw_mdp_ops *ops,
 
 	if (cap & BIT(DPU_MDP_VSYNC_SEL))
 		ops->setup_vsync_source = dpu_hw_setup_vsync_sel;
-	else
+	else if (!(cap & BIT(DPU_MDP_PERIPH_0_REMOVED)))
 		ops->setup_vsync_source = dpu_hw_setup_wd_timer;
 
 	ops->get_safe_status = dpu_hw_get_safe_status;

From af0a4a2090cce732c70ad6c5f4145b43f39e3fe9 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Sat, 14 Dec 2024 00:14:18 +0200
Subject: [PATCH 0151/1173] drm/msm/dpu: enable DPU_WB_INPUT_CTRL for DPU 5.x

Several DPU 5.x platforms are supposed to be using DPU_WB_INPUT_CTRL,
to bind WB and PINGPONG blocks, but they do not. Change those platforms
to use WB_SM8250_MASK, which includes that bit.

Fixes: 1f5bcc4316b3 ("drm/msm/dpu: enable writeback on SC8108X")
Fixes: ab2b03d73a66 ("drm/msm/dpu: enable writeback on SM6125")
Fixes: 47cebb740a83 ("drm/msm/dpu: enable writeback on SM8150")
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Patchwork: https://patchwork.freedesktop.org/patch/628876/
Link: https://lore.kernel.org/r/20241214-dpu-drop-features-v1-2-988f0662cb7e@linaro.org
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
 drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h  | 2 +-
 drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h | 2 +-
 drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_4_sm6125.h  | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h
index 421afacb72480..36cc9dbc00b5c 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h
@@ -297,7 +297,7 @@ static const struct dpu_wb_cfg sm8150_wb[] = {
 	{
 		.name = "wb_2", .id = WB_2,
 		.base = 0x65000, .len = 0x2c8,
-		.features = WB_SDM845_MASK,
+		.features = WB_SM8250_MASK,
 		.format_list = wb2_formats_rgb,
 		.num_formats = ARRAY_SIZE(wb2_formats_rgb),
 		.clk_ctrl = DPU_CLK_CTRL_WB2,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h
index 641023b102bf5..e8eacdb47967a 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h
@@ -304,7 +304,7 @@ static const struct dpu_wb_cfg sc8180x_wb[] = {
 	{
 		.name = "wb_2", .id = WB_2,
 		.base = 0x65000, .len = 0x2c8,
-		.features = WB_SDM845_MASK,
+		.features = WB_SM8250_MASK,
 		.format_list = wb2_formats_rgb,
 		.num_formats = ARRAY_SIZE(wb2_formats_rgb),
 		.clk_ctrl = DPU_CLK_CTRL_WB2,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_4_sm6125.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_4_sm6125.h
index d039b96beb97c..76f60a2df7a89 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_4_sm6125.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_4_sm6125.h
@@ -144,7 +144,7 @@ static const struct dpu_wb_cfg sm6125_wb[] = {
 	{
 		.name = "wb_2", .id = WB_2,
 		.base = 0x65000, .len = 0x2c8,
-		.features = WB_SDM845_MASK,
+		.features = WB_SM8250_MASK,
 		.format_list = wb2_formats_rgb,
 		.num_formats = ARRAY_SIZE(wb2_formats_rgb),
 		.clk_ctrl = DPU_CLK_CTRL_WB2,

From 24b50b7340ab7e7b004ee6db43d625caa68498b0 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Tue, 17 Dec 2024 14:35:40 +0200
Subject: [PATCH 0152/1173] drm/msm/dpu: correct LM pairing for SM6150

The SM6150 platform doesn't have 3DMux (MERGE_3D) block, so it can not
split the screen between two LMs. Drop lm_pair fields as they don't make
sense for this platform.

Suggested-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Fixes: cb2f9144693b ("drm/msm/dpu: Add SM6150 support")
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Patchwork: https://patchwork.freedesktop.org/patch/629377/
Link: https://lore.kernel.org/r/20241217-dpu-fix-sm6150-v2-1-9acc8f5addf3@linaro.org
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
 drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_3_sm6150.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_3_sm6150.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_3_sm6150.h
index 621a2140f675f..d761ed705bac3 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_3_sm6150.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_3_sm6150.h
@@ -116,14 +116,12 @@ static const struct dpu_lm_cfg sm6150_lm[] = {
 		.sblk = &sdm845_lm_sblk,
 		.pingpong = PINGPONG_0,
 		.dspp = DSPP_0,
-		.lm_pair = LM_1,
 	}, {
 		.name = "lm_1", .id = LM_1,
 		.base = 0x45000, .len = 0x320,
 		.features = MIXER_QCM2290_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.pingpong = PINGPONG_1,
-		.lm_pair = LM_0,
 	}, {
 		.name = "lm_2", .id = LM_2,
 		.base = 0x46000, .len = 0x320,

From df9cf852ca3099feb8fed781bdd5d3863af001c8 Mon Sep 17 00:00:00 2001
From: Abhinav Kumar <quic_abhinavk@quicinc.com>
Date: Thu, 6 Feb 2025 11:46:36 -0800
Subject: [PATCH 0153/1173] drm/msm/dp: account for widebus and yuv420 during
 mode validation

Widebus allows the DP controller to operate in 2 pixel per clock mode.
The mode validation logic validates the mode->clock against the max
DP pixel clock. However the max DP pixel clock limit assumes widebus
is already enabled. Adjust the mode validation logic to only compare
the adjusted pixel clock which accounts for widebus against the max DP
pixel clock. Also fix the mode validation logic for YUV420 modes as in
that case as well, only half the pixel clock is needed.

Cc: stable@vger.kernel.org
Fixes: 757a2f36ab09 ("drm/msm/dp: enable widebus feature for display port")
Fixes: 6db6e5606576 ("drm/msm/dp: change clock related programming for YUV420 over DP")
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Tested-by: Dale Whinham <daleyo@gmail.com>
Patchwork: https://patchwork.freedesktop.org/patch/635789/
Link: https://lore.kernel.org/r/20250206-dp-widebus-fix-v2-1-cb89a0313286@quicinc.com
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
 drivers/gpu/drm/msm/dp/dp_display.c | 11 ++++++-----
 drivers/gpu/drm/msm/dp/dp_drm.c     |  5 ++++-
 2 files changed, 10 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c
index d852e7a853348..a129e26c3ddb3 100644
--- a/drivers/gpu/drm/msm/dp/dp_display.c
+++ b/drivers/gpu/drm/msm/dp/dp_display.c
@@ -930,16 +930,17 @@ enum drm_mode_status msm_dp_bridge_mode_valid(struct drm_bridge *bridge,
 		return -EINVAL;
 	}
 
-	if (mode->clock > DP_MAX_PIXEL_CLK_KHZ)
-		return MODE_CLOCK_HIGH;
-
 	msm_dp_display = container_of(dp, struct msm_dp_display_private, msm_dp_display);
 	link_info = &msm_dp_display->panel->link_info;
 
-	if (drm_mode_is_420_only(&dp->connector->display_info, mode) &&
-	    msm_dp_display->panel->vsc_sdp_supported)
+	if ((drm_mode_is_420_only(&dp->connector->display_info, mode) &&
+	     msm_dp_display->panel->vsc_sdp_supported) ||
+	     msm_dp_wide_bus_available(dp))
 		mode_pclk_khz /= 2;
 
+	if (mode_pclk_khz > DP_MAX_PIXEL_CLK_KHZ)
+		return MODE_CLOCK_HIGH;
+
 	mode_bpp = dp->connector->display_info.bpc * num_components;
 	if (!mode_bpp)
 		mode_bpp = default_bpp;
diff --git a/drivers/gpu/drm/msm/dp/dp_drm.c b/drivers/gpu/drm/msm/dp/dp_drm.c
index d3e241ea69416..16b7913d1eefa 100644
--- a/drivers/gpu/drm/msm/dp/dp_drm.c
+++ b/drivers/gpu/drm/msm/dp/dp_drm.c
@@ -257,7 +257,10 @@ static enum drm_mode_status msm_edp_bridge_mode_valid(struct drm_bridge *bridge,
 		return -EINVAL;
 	}
 
-	if (mode->clock > DP_MAX_PIXEL_CLK_KHZ)
+	if (msm_dp_wide_bus_available(dp))
+		mode_pclk_khz /= 2;
+
+	if (mode_pclk_khz > DP_MAX_PIXEL_CLK_KHZ)
 		return MODE_CLOCK_HIGH;
 
 	/*

From 978ca99d6bd87b84ff7788eea4d2c328a70530f6 Mon Sep 17 00:00:00 2001
From: Ethan Carter Edwards <ethan@ethancedwards.com>
Date: Sun, 9 Feb 2025 22:51:54 -0500
Subject: [PATCH 0154/1173] drm/msm/dpu: Fix uninitialized variable

There is a possibility for an uninitialized *ret* variable to be
returned in some code paths.

Fix this by initializing *ret* to 0.

Addresses-Coverity-ID: 1642546 ("Uninitialized scalar variable")
Fixes: 774bcfb73176 ("drm/msm/dpu: add support for virtual planes")
Signed-off-by: Ethan Carter Edwards <ethan@ethancedwards.com>
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Patchwork: https://patchwork.freedesktop.org/patch/636201/
Link: https://lore.kernel.org/r/20250209-dpu-v2-1-114dfd4ebefd@ethancedwards.com
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
index 098abc2c0003c..af3e541f60c30 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
@@ -1164,7 +1164,6 @@ int dpu_assign_plane_resources(struct dpu_global_state *global_state,
 			       unsigned int num_planes)
 {
 	unsigned int i;
-	int ret;
 
 	for (i = 0; i < num_planes; i++) {
 		struct drm_plane_state *plane_state = states[i];
@@ -1173,13 +1172,13 @@ int dpu_assign_plane_resources(struct dpu_global_state *global_state,
 		    !plane_state->visible)
 			continue;
 
-		ret = dpu_plane_virtual_assign_resources(crtc, global_state,
+		int ret = dpu_plane_virtual_assign_resources(crtc, global_state,
 							 state, plane_state);
 		if (ret)
-			break;
+			return ret;
 	}
 
-	return ret;
+	return 0;
 }
 
 static void dpu_plane_flush_csc(struct dpu_plane *pdpu, struct dpu_sw_pipe *pipe)

From f063ac6b55df03ed25996bdc84d9e1c50147cfa1 Mon Sep 17 00:00:00 2001
From: Jessica Zhang <quic_jesszhan@quicinc.com>
Date: Tue, 11 Feb 2025 19:59:19 -0800
Subject: [PATCH 0155/1173] drm/msm/dpu: Disable dither in phys encoder cleanup

Disable pingpong dither in dpu_encoder_helper_phys_cleanup().

This avoids the issue where an encoder unknowingly uses dither after
reserving a pingpong block that was previously bound to an encoder that
had enabled dither.

Cc: stable@vger.kernel.org
Reported-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Closes: https://lore.kernel.org/all/jr7zbj5w7iq4apg3gofuvcwf4r2swzqjk7sshwcdjll4mn6ctt@l2n3qfpujg3q/
Signed-off-by: Jessica Zhang <quic_jesszhan@quicinc.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Fixes: 3c128638a07d ("drm/msm/dpu: add support for dither block in display")
Patchwork: https://patchwork.freedesktop.org/patch/636517/
Link: https://lore.kernel.org/r/20250211-dither-disable-v1-1-ac2cb455f6b9@quicinc.com
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index 5172ab4dea995..48e6e8d74c855 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -2281,6 +2281,9 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc)
 		}
 	}
 
+	if (phys_enc->hw_pp && phys_enc->hw_pp->ops.setup_dither)
+		phys_enc->hw_pp->ops.setup_dither(phys_enc->hw_pp, NULL);
+
 	/* reset the merge 3D HW block */
 	if (phys_enc->hw_pp && phys_enc->hw_pp->merge_3d) {
 		phys_enc->hw_pp->merge_3d->ops.setup_3d_mode(phys_enc->hw_pp->merge_3d,

From 144429831f447223253a0e4376489f84ff37d1a7 Mon Sep 17 00:00:00 2001
From: Marijn Suijten <marijn.suijten@somainline.org>
Date: Tue, 11 Feb 2025 00:19:32 +0100
Subject: [PATCH 0156/1173] drm/msm/dpu: Don't leak bits_per_component into
 random DSC_ENC fields

What used to be the input_10_bits boolean - feeding into the lowest
bit of DSC_ENC - on MSM downstream turned into an accidental OR with
the full bits_per_component number when it was ported to the upstream
kernel.

On typical bpc=8 setups we don't notice this because line_buf_depth is
always an odd value (it contains bpc+1) and will also set the 4th bit
after left-shifting by 3 (hence this |= bits_per_component is a no-op).

Now that guards are being removed to allow more bits_per_component
values besides 8 (possible since commit 49fd30a7153b ("drm/msm/dsi: use
DRM DSC helpers for DSC setup")), a bpc of 10 will instead clash with
the 5th bit which is convert_rgb.  This is "fortunately" also always set
to true by MSM's dsi_populate_dsc_params() already, but once a bpc of 12
starts being used it'll write into simple_422 which is normally false.

To solve all these overlaps, simply replicate downstream code and only
set this lowest bit if bits_per_component is equal to 10.  It is unclear
why DSC requires this only for bpc=10 but not bpc=12, and also notice
that this lowest bit wasn't set previously despite having a panel and
patch on the list using it without any mentioned issues.

Fixes: c110cfd1753e ("drm/msm/disp/dpu1: Add support for DSC")
Signed-off-by: Marijn Suijten <marijn.suijten@somainline.org>
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Patchwork: https://patchwork.freedesktop.org/patch/636311/
Link: https://lore.kernel.org/r/20250211-dsc-10-bit-v1-1-1c85a9430d9a@somainline.org
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.c
index 657200401f576..cec6d4e8baec4 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.c
@@ -52,6 +52,7 @@ static void dpu_hw_dsc_config(struct dpu_hw_dsc *hw_dsc,
 	u32 slice_last_group_size;
 	u32 det_thresh_flatness;
 	bool is_cmd_mode = !(mode & DSC_MODE_VIDEO);
+	bool input_10_bits = dsc->bits_per_component == 10;
 
 	DPU_REG_WRITE(c, DSC_COMMON_MODE, mode);
 
@@ -68,7 +69,7 @@ static void dpu_hw_dsc_config(struct dpu_hw_dsc *hw_dsc,
 	data |= (dsc->line_buf_depth << 3);
 	data |= (dsc->simple_422 << 2);
 	data |= (dsc->convert_rgb << 1);
-	data |= dsc->bits_per_component;
+	data |= input_10_bits;
 
 	DPU_REG_WRITE(c, DSC_ENC, data);
 

From 5e192eefebaab5bdcf716add8910d7f8a2e30e3c Mon Sep 17 00:00:00 2001
From: Jessica Zhang <quic_jesszhan@quicinc.com>
Date: Wed, 8 Jan 2025 14:40:48 -0800
Subject: [PATCH 0157/1173] drm/msm/dpu: Drop extraneous return in
 dpu_crtc_reassign_planes()

Drop extra return at the end of dpu_crtc_reassign_planes()

Fixes: 774bcfb73176 ("drm/msm/dpu: add support for virtual planes")
Signed-off-by: Jessica Zhang <quic_jesszhan@quicinc.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Patchwork: https://patchwork.freedesktop.org/patch/631565/
Link: https://lore.kernel.org/r/20250108-virtual-planes-fixes-v1-2-420cb36df94a@quicinc.com
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
index 7191b1a6d41b3..e5dcd41a361f4 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
@@ -1228,8 +1228,6 @@ static int dpu_crtc_reassign_planes(struct drm_crtc *crtc, struct drm_crtc_state
 done:
 	kfree(states);
 	return ret;
-
-	return 0;
 }
 
 static int dpu_crtc_atomic_check(struct drm_crtc *crtc,

From 588257897058a0b1aa47912db4fe93c6ff5e3887 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 14 Feb 2025 16:08:41 +0100
Subject: [PATCH 0158/1173] drm/msm/dsi/phy: Protect PHY_CMN_CLK_CFG0 updated
 from driver side

PHY_CMN_CLK_CFG0 register is updated by the PHY driver and by two
divider clocks from Common Clock Framework:
devm_clk_hw_register_divider_parent_hw().  Concurrent access by the
clocks side is protected with spinlock, however driver's side in
restoring state is not.  Restoring state is called from
msm_dsi_phy_enable(), so there could be a path leading to concurrent and
conflicting updates with clock framework.

Add missing lock usage on the PHY driver side, encapsulated in its own
function so the code will be still readable.

While shuffling the code, define and use PHY_CMN_CLK_CFG0 bitfields to
make the code more readable and obvious.

Fixes: 1ef7c99d145c ("drm/msm/dsi: add support for 7nm DSI PHY/PLL")
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Patchwork: https://patchwork.freedesktop.org/patch/637376/
Link: https://lore.kernel.org/r/20250214-drm-msm-phy-pll-cfg-reg-v3-1-0943b850722c@linaro.org
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
 drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c          | 14 ++++++++++++--
 .../gpu/drm/msm/registers/display/dsi_phy_7nm.xml  |  5 ++++-
 2 files changed, 16 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
index 031446c87daec..25ca649de717e 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
@@ -372,6 +372,15 @@ static void dsi_pll_enable_pll_bias(struct dsi_pll_7nm *pll)
 	ndelay(250);
 }
 
+static void dsi_pll_cmn_clk_cfg0_write(struct dsi_pll_7nm *pll, u32 val)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&pll->postdiv_lock, flags);
+	writel(val, pll->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG0);
+	spin_unlock_irqrestore(&pll->postdiv_lock, flags);
+}
+
 static void dsi_pll_disable_global_clk(struct dsi_pll_7nm *pll)
 {
 	u32 data;
@@ -574,8 +583,9 @@ static int dsi_7nm_pll_restore_state(struct msm_dsi_phy *phy)
 	val |= cached->pll_out_div;
 	writel(val, pll_7nm->phy->pll_base + REG_DSI_7nm_PHY_PLL_PLL_OUTDIV_RATE);
 
-	writel(cached->bit_clk_div | (cached->pix_clk_div << 4),
-	       phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG0);
+	dsi_pll_cmn_clk_cfg0_write(pll_7nm,
+				   DSI_7nm_PHY_CMN_CLK_CFG0_DIV_CTRL_3_0(cached->bit_clk_div) |
+				   DSI_7nm_PHY_CMN_CLK_CFG0_DIV_CTRL_7_4(cached->pix_clk_div));
 
 	val = readl(phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG1);
 	val &= ~0x3;
diff --git a/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml b/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml
index d54b72f924493..e0bf6e016b4ce 100644
--- a/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml
+++ b/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml
@@ -9,7 +9,10 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd">
 	<reg32 offset="0x00004" name="REVISION_ID1"/>
 	<reg32 offset="0x00008" name="REVISION_ID2"/>
 	<reg32 offset="0x0000c" name="REVISION_ID3"/>
-	<reg32 offset="0x00010" name="CLK_CFG0"/>
+	<reg32 offset="0x00010" name="CLK_CFG0">
+		<bitfield name="DIV_CTRL_3_0" low="0" high="3" type="uint"/>
+		<bitfield name="DIV_CTRL_7_4" low="4" high="7" type="uint"/>
+	</reg32>
 	<reg32 offset="0x00014" name="CLK_CFG1"/>
 	<reg32 offset="0x00018" name="GLBL_CTRL"/>
 	<reg32 offset="0x0001c" name="RBUF_CTRL"/>

From 5a97bc924ae0804b8dbf627e357acaa5ef761483 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 14 Feb 2025 16:08:42 +0100
Subject: [PATCH 0159/1173] drm/msm/dsi/phy: Protect PHY_CMN_CLK_CFG1 against
 clock driver

PHY_CMN_CLK_CFG1 register is updated by the PHY driver and by a mux
clock from Common Clock Framework:
devm_clk_hw_register_mux_parent_hws().  There could be a path leading to
concurrent and conflicting updates between PHY driver and clock
framework, e.g. changing the mux and enabling PLL clocks.

Add dedicated spinlock to be sure all PHY_CMN_CLK_CFG1 updates are
synchronized.

While shuffling the code, define and use PHY_CMN_CLK_CFG1 bitfields to
make the code more readable and obvious.

Fixes: 1ef7c99d145c ("drm/msm/dsi: add support for 7nm DSI PHY/PLL")
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Patchwork: https://patchwork.freedesktop.org/patch/637378/
Link: https://lore.kernel.org/r/20250214-drm-msm-phy-pll-cfg-reg-v3-2-0943b850722c@linaro.org
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
 drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c     | 35 ++++++++++++-------
 .../drm/msm/registers/display/dsi_phy_7nm.xml |  5 ++-
 2 files changed, 26 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
index 25ca649de717e..388017db45d80 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
@@ -83,6 +83,9 @@ struct dsi_pll_7nm {
 	/* protects REG_DSI_7nm_PHY_CMN_CLK_CFG0 register */
 	spinlock_t postdiv_lock;
 
+	/* protects REG_DSI_7nm_PHY_CMN_CLK_CFG1 register */
+	spinlock_t pclk_mux_lock;
+
 	struct pll_7nm_cached_state cached_state;
 
 	struct dsi_pll_7nm *slave;
@@ -381,22 +384,32 @@ static void dsi_pll_cmn_clk_cfg0_write(struct dsi_pll_7nm *pll, u32 val)
 	spin_unlock_irqrestore(&pll->postdiv_lock, flags);
 }
 
-static void dsi_pll_disable_global_clk(struct dsi_pll_7nm *pll)
+static void dsi_pll_cmn_clk_cfg1_update(struct dsi_pll_7nm *pll, u32 mask,
+					u32 val)
 {
+	unsigned long flags;
 	u32 data;
 
+	spin_lock_irqsave(&pll->pclk_mux_lock, flags);
 	data = readl(pll->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1);
-	writel(data & ~BIT(5), pll->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1);
+	data &= ~mask;
+	data |= val & mask;
+
+	writel(data, pll->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1);
+	spin_unlock_irqrestore(&pll->pclk_mux_lock, flags);
+}
+
+static void dsi_pll_disable_global_clk(struct dsi_pll_7nm *pll)
+{
+	dsi_pll_cmn_clk_cfg1_update(pll, DSI_7nm_PHY_CMN_CLK_CFG1_CLK_EN, 0);
 }
 
 static void dsi_pll_enable_global_clk(struct dsi_pll_7nm *pll)
 {
-	u32 data;
+	u32 cfg_1 = DSI_7nm_PHY_CMN_CLK_CFG1_CLK_EN | DSI_7nm_PHY_CMN_CLK_CFG1_CLK_EN_SEL;
 
 	writel(0x04, pll->phy->base + REG_DSI_7nm_PHY_CMN_CTRL_3);
-
-	data = readl(pll->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1);
-	writel(data | BIT(5) | BIT(4), pll->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1);
+	dsi_pll_cmn_clk_cfg1_update(pll, cfg_1, cfg_1);
 }
 
 static void dsi_pll_phy_dig_reset(struct dsi_pll_7nm *pll)
@@ -574,7 +587,6 @@ static int dsi_7nm_pll_restore_state(struct msm_dsi_phy *phy)
 {
 	struct dsi_pll_7nm *pll_7nm = to_pll_7nm(phy->vco_hw);
 	struct pll_7nm_cached_state *cached = &pll_7nm->cached_state;
-	void __iomem *phy_base = pll_7nm->phy->base;
 	u32 val;
 	int ret;
 
@@ -586,11 +598,7 @@ static int dsi_7nm_pll_restore_state(struct msm_dsi_phy *phy)
 	dsi_pll_cmn_clk_cfg0_write(pll_7nm,
 				   DSI_7nm_PHY_CMN_CLK_CFG0_DIV_CTRL_3_0(cached->bit_clk_div) |
 				   DSI_7nm_PHY_CMN_CLK_CFG0_DIV_CTRL_7_4(cached->pix_clk_div));
-
-	val = readl(phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG1);
-	val &= ~0x3;
-	val |= cached->pll_mux;
-	writel(val, phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG1);
+	dsi_pll_cmn_clk_cfg1_update(pll_7nm, 0x3, cached->pll_mux);
 
 	ret = dsi_pll_7nm_vco_set_rate(phy->vco_hw,
 			pll_7nm->vco_current_rate,
@@ -743,7 +751,7 @@ static int pll_7nm_register(struct dsi_pll_7nm *pll_7nm, struct clk_hw **provide
 					pll_by_2_bit,
 				}), 2, 0, pll_7nm->phy->base +
 					REG_DSI_7nm_PHY_CMN_CLK_CFG1,
-				0, 1, 0, NULL);
+				0, 1, 0, &pll_7nm->pclk_mux_lock);
 		if (IS_ERR(hw)) {
 			ret = PTR_ERR(hw);
 			goto fail;
@@ -788,6 +796,7 @@ static int dsi_pll_7nm_init(struct msm_dsi_phy *phy)
 	pll_7nm_list[phy->id] = pll_7nm;
 
 	spin_lock_init(&pll_7nm->postdiv_lock);
+	spin_lock_init(&pll_7nm->pclk_mux_lock);
 
 	pll_7nm->phy = phy;
 
diff --git a/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml b/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml
index e0bf6e016b4ce..cfaf78c028b13 100644
--- a/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml
+++ b/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml
@@ -13,7 +13,10 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd">
 		<bitfield name="DIV_CTRL_3_0" low="0" high="3" type="uint"/>
 		<bitfield name="DIV_CTRL_7_4" low="4" high="7" type="uint"/>
 	</reg32>
-	<reg32 offset="0x00014" name="CLK_CFG1"/>
+	<reg32 offset="0x00014" name="CLK_CFG1">
+		<bitfield name="CLK_EN" pos="5" type="boolean"/>
+		<bitfield name="CLK_EN_SEL" pos="4" type="boolean"/>
+	</reg32>
 	<reg32 offset="0x00018" name="GLBL_CTRL"/>
 	<reg32 offset="0x0001c" name="RBUF_CTRL"/>
 	<reg32 offset="0x00020" name="VREG_CTRL_0"/>

From 73f69c6be2a9f22c31c775ec03c6c286bfe12cfa Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 14 Feb 2025 16:08:43 +0100
Subject: [PATCH 0160/1173] drm/msm/dsi/phy: Do not overwite PHY_CMN_CLK_CFG1
 when choosing bitclk source

PHY_CMN_CLK_CFG1 register has four fields being used in the driver: DSI
clock divider, source of bitclk and two for enabling the DSI PHY PLL
clocks.

dsi_7nm_set_usecase() sets only the source of bitclk, so should leave
all other bits untouched.  Use newly introduced
dsi_pll_cmn_clk_cfg1_update() to update respective bits without
overwriting the rest.

While shuffling the code, define and use PHY_CMN_CLK_CFG1 bitfields to
make the code more readable and obvious.

Fixes: 1ef7c99d145c ("drm/msm/dsi: add support for 7nm DSI PHY/PLL")
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Patchwork: https://patchwork.freedesktop.org/patch/637380/
Link: https://lore.kernel.org/r/20250214-drm-msm-phy-pll-cfg-reg-v3-3-0943b850722c@linaro.org
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
 drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c             | 4 ++--
 drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml | 1 +
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
index 388017db45d80..798168180c1ab 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
@@ -617,7 +617,6 @@ static int dsi_7nm_pll_restore_state(struct msm_dsi_phy *phy)
 static int dsi_7nm_set_usecase(struct msm_dsi_phy *phy)
 {
 	struct dsi_pll_7nm *pll_7nm = to_pll_7nm(phy->vco_hw);
-	void __iomem *base = phy->base;
 	u32 data = 0x0;	/* internal PLL */
 
 	DBG("DSI PLL%d", pll_7nm->phy->id);
@@ -636,7 +635,8 @@ static int dsi_7nm_set_usecase(struct msm_dsi_phy *phy)
 	}
 
 	/* set PLL src */
-	writel(data << 2, base + REG_DSI_7nm_PHY_CMN_CLK_CFG1);
+	dsi_pll_cmn_clk_cfg1_update(pll_7nm, DSI_7nm_PHY_CMN_CLK_CFG1_BITCLK_SEL__MASK,
+				    DSI_7nm_PHY_CMN_CLK_CFG1_BITCLK_SEL(data));
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml b/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml
index cfaf78c028b13..35f7f40e405b7 100644
--- a/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml
+++ b/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml
@@ -16,6 +16,7 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd">
 	<reg32 offset="0x00014" name="CLK_CFG1">
 		<bitfield name="CLK_EN" pos="5" type="boolean"/>
 		<bitfield name="CLK_EN_SEL" pos="4" type="boolean"/>
+		<bitfield name="BITCLK_SEL" low="2" high="3" type="uint"/>
 	</reg32>
 	<reg32 offset="0x00018" name="GLBL_CTRL"/>
 	<reg32 offset="0x0001c" name="RBUF_CTRL"/>

From 579cd64b9df8a60284ec3422be919c362de40e41 Mon Sep 17 00:00:00 2001
From: Hector Martin <marcan@marcan.st>
Date: Sat, 8 Feb 2025 00:54:35 +0000
Subject: [PATCH 0161/1173] ASoC: tas2770: Fix volume scale

The scale starts at -100dB, not -128dB.

Signed-off-by: Hector Martin <marcan@marcan.st>
Signed-off-by: Mark Brown <broonie@kernel.org>
Link: https://patch.msgid.link/20250208-asoc-tas2770-v1-1-cf50ff1d59a3@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/tas2770.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/codecs/tas2770.c b/sound/soc/codecs/tas2770.c
index 9f93b230652a5..863c3f672ba98 100644
--- a/sound/soc/codecs/tas2770.c
+++ b/sound/soc/codecs/tas2770.c
@@ -506,7 +506,7 @@ static int tas2770_codec_probe(struct snd_soc_component *component)
 }
 
 static DECLARE_TLV_DB_SCALE(tas2770_digital_tlv, 1100, 50, 0);
-static DECLARE_TLV_DB_SCALE(tas2770_playback_volume, -12750, 50, 0);
+static DECLARE_TLV_DB_SCALE(tas2770_playback_volume, -10050, 50, 0);
 
 static const struct snd_kcontrol_new tas2770_snd_controls[] = {
 	SOC_SINGLE_TLV("Speaker Playback Volume", TAS2770_PLAY_CFG_REG2,

From 7103f0589ac220eac3d2b1e8411494b31b883d06 Mon Sep 17 00:00:00 2001
From: "Borislav Petkov (AMD)" <bp@alien8.de>
Date: Thu, 23 Jan 2025 13:14:34 +0100
Subject: [PATCH 0162/1173] x86/microcode/AMD: Remove ugly linebreak in
 __verify_patch_section() signature

No functional changes.

Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20250211163648.30531-2-bp@kernel.org
---
 arch/x86/kernel/cpu/microcode/amd.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index a5dac7f3c0a07..4a62625c311a6 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -246,8 +246,7 @@ static bool verify_equivalence_table(const u8 *buf, size_t buf_size)
  * On success, @sh_psize returns the patch size according to the section header,
  * to the caller.
  */
-static bool
-__verify_patch_section(const u8 *buf, size_t buf_size, u32 *sh_psize)
+static bool __verify_patch_section(const u8 *buf, size_t buf_size, u32 *sh_psize)
 {
 	u32 p_type, p_size;
 	const u32 *hdr;

From 3ef0740d10b005a45e8ae5b4b7b5d37bfddf63c0 Mon Sep 17 00:00:00 2001
From: "Borislav Petkov (AMD)" <bp@alien8.de>
Date: Thu, 23 Jan 2025 12:23:47 +0100
Subject: [PATCH 0163/1173] x86/microcode/AMD: Remove unused
 save_microcode_in_initrd_amd() declarations

Commit

  a7939f016720 ("x86/microcode/amd: Cache builtin/initrd microcode early")

renamed it to save_microcode_in_initrd() and made it static. Zap the
forgotten declarations.

No functional changes.

Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20250211163648.30531-3-bp@kernel.org
---
 arch/x86/kernel/cpu/microcode/amd.c      | 2 +-
 arch/x86/kernel/cpu/microcode/internal.h | 2 --
 2 files changed, 1 insertion(+), 3 deletions(-)

diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 4a62625c311a6..f831c06029948 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -517,7 +517,7 @@ static bool __apply_microcode_amd(struct microcode_amd *mc, unsigned int psize)
  * patch container file in initrd, traverse equivalent cpu table, look for a
  * matching microcode patch, and update, all in initrd memory in place.
  * When vmalloc() is available for use later -- on 64-bit during first AP load,
- * and on 32-bit during save_microcode_in_initrd_amd() -- we can call
+ * and on 32-bit during save_microcode_in_initrd() -- we can call
  * load_microcode_amd() to save equivalent cpu table and microcode patches in
  * kernel heap memory.
  *
diff --git a/arch/x86/kernel/cpu/microcode/internal.h b/arch/x86/kernel/cpu/microcode/internal.h
index 21776c529fa97..5df621752fefa 100644
--- a/arch/x86/kernel/cpu/microcode/internal.h
+++ b/arch/x86/kernel/cpu/microcode/internal.h
@@ -100,14 +100,12 @@ extern bool force_minrev;
 #ifdef CONFIG_CPU_SUP_AMD
 void load_ucode_amd_bsp(struct early_load_data *ed, unsigned int family);
 void load_ucode_amd_ap(unsigned int family);
-int save_microcode_in_initrd_amd(unsigned int family);
 void reload_ucode_amd(unsigned int cpu);
 struct microcode_ops *init_amd_microcode(void);
 void exit_amd_microcode(void);
 #else /* CONFIG_CPU_SUP_AMD */
 static inline void load_ucode_amd_bsp(struct early_load_data *ed, unsigned int family) { }
 static inline void load_ucode_amd_ap(unsigned int family) { }
-static inline int save_microcode_in_initrd_amd(unsigned int family) { return -EINVAL; }
 static inline void reload_ucode_amd(unsigned int cpu) { }
 static inline struct microcode_ops *init_amd_microcode(void) { return NULL; }
 static inline void exit_amd_microcode(void) { }

From dc15675074dcfd79a2f10a6e39f96b0244961a01 Mon Sep 17 00:00:00 2001
From: "Borislav Petkov (AMD)" <bp@alien8.de>
Date: Thu, 23 Jan 2025 12:46:45 +0100
Subject: [PATCH 0164/1173] x86/microcode/AMD: Merge early_apply_microcode()
 into its single callsite

No functional changes.

Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20250211163648.30531-4-bp@kernel.org
---
 arch/x86/kernel/cpu/microcode/amd.c | 60 +++++++++++++----------------
 1 file changed, 26 insertions(+), 34 deletions(-)

diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index f831c06029948..90f93b3ca9dbb 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -512,39 +512,6 @@ static bool __apply_microcode_amd(struct microcode_amd *mc, unsigned int psize)
 	return true;
 }
 
-/*
- * Early load occurs before we can vmalloc(). So we look for the microcode
- * patch container file in initrd, traverse equivalent cpu table, look for a
- * matching microcode patch, and update, all in initrd memory in place.
- * When vmalloc() is available for use later -- on 64-bit during first AP load,
- * and on 32-bit during save_microcode_in_initrd() -- we can call
- * load_microcode_amd() to save equivalent cpu table and microcode patches in
- * kernel heap memory.
- *
- * Returns true if container found (sets @desc), false otherwise.
- */
-static bool early_apply_microcode(u32 old_rev, void *ucode, size_t size)
-{
-	struct cont_desc desc = { 0 };
-	struct microcode_amd *mc;
-
-	scan_containers(ucode, size, &desc);
-
-	mc = desc.mc;
-	if (!mc)
-		return false;
-
-	/*
-	 * Allow application of the same revision to pick up SMT-specific
-	 * changes even if the revision of the other SMT thread is already
-	 * up-to-date.
-	 */
-	if (old_rev > mc->hdr.patch_id)
-		return false;
-
-	return __apply_microcode_amd(mc, desc.psize);
-}
-
 static bool get_builtin_microcode(struct cpio_data *cp)
 {
 	char fw_name[36] = "amd-ucode/microcode_amd.bin";
@@ -582,8 +549,19 @@ static bool __init find_blobs_in_containers(struct cpio_data *ret)
 	return found;
 }
 
+/*
+ * Early load occurs before we can vmalloc(). So we look for the microcode
+ * patch container file in initrd, traverse equivalent cpu table, look for a
+ * matching microcode patch, and update, all in initrd memory in place.
+ * When vmalloc() is available for use later -- on 64-bit during first AP load,
+ * and on 32-bit during save_microcode_in_initrd() -- we can call
+ * load_microcode_amd() to save equivalent cpu table and microcode patches in
+ * kernel heap memory.
+ */
 void __init load_ucode_amd_bsp(struct early_load_data *ed, unsigned int cpuid_1_eax)
 {
+	struct cont_desc desc = { };
+	struct microcode_amd *mc;
 	struct cpio_data cp = { };
 	u32 dummy;
 
@@ -597,7 +575,21 @@ void __init load_ucode_amd_bsp(struct early_load_data *ed, unsigned int cpuid_1_
 	if (!find_blobs_in_containers(&cp))
 		return;
 
-	if (early_apply_microcode(ed->old_rev, cp.data, cp.size))
+	scan_containers(cp.data, cp.size, &desc);
+
+	mc = desc.mc;
+	if (!mc)
+		return;
+
+	/*
+	 * Allow application of the same revision to pick up SMT-specific
+	 * changes even if the revision of the other SMT thread is already
+	 * up-to-date.
+	 */
+	if (ed->old_rev > mc->hdr.patch_id)
+		return;
+
+	if (__apply_microcode_amd(mc, desc.psize))
 		native_rdmsr(MSR_AMD64_PATCH_LEVEL, ed->new_rev, dummy);
 }
 

From b39c387164879eef71886fc93cee5ca7dd7bf500 Mon Sep 17 00:00:00 2001
From: "Borislav Petkov (AMD)" <bp@alien8.de>
Date: Thu, 23 Jan 2025 12:51:37 +0100
Subject: [PATCH 0165/1173] x86/microcode/AMD: Get rid of the
 _load_microcode_amd() forward declaration

Simply move save_microcode_in_initrd() down.

No functional changes.

Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20250211163648.30531-5-bp@kernel.org
---
 arch/x86/kernel/cpu/microcode/amd.c | 54 ++++++++++++++---------------
 1 file changed, 26 insertions(+), 28 deletions(-)

diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 90f93b3ca9dbb..adfea4d0d1297 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -593,34 +593,6 @@ void __init load_ucode_amd_bsp(struct early_load_data *ed, unsigned int cpuid_1_
 		native_rdmsr(MSR_AMD64_PATCH_LEVEL, ed->new_rev, dummy);
 }
 
-static enum ucode_state _load_microcode_amd(u8 family, const u8 *data, size_t size);
-
-static int __init save_microcode_in_initrd(void)
-{
-	unsigned int cpuid_1_eax = native_cpuid_eax(1);
-	struct cpuinfo_x86 *c = &boot_cpu_data;
-	struct cont_desc desc = { 0 };
-	enum ucode_state ret;
-	struct cpio_data cp;
-
-	if (dis_ucode_ldr || c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10)
-		return 0;
-
-	if (!find_blobs_in_containers(&cp))
-		return -EINVAL;
-
-	scan_containers(cp.data, cp.size, &desc);
-	if (!desc.mc)
-		return -EINVAL;
-
-	ret = _load_microcode_amd(x86_family(cpuid_1_eax), desc.data, desc.size);
-	if (ret > UCODE_UPDATED)
-		return -EINVAL;
-
-	return 0;
-}
-early_initcall(save_microcode_in_initrd);
-
 static inline bool patch_cpus_equivalent(struct ucode_patch *p,
 					 struct ucode_patch *n,
 					 bool ignore_stepping)
@@ -1004,6 +976,32 @@ static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t siz
 	return ret;
 }
 
+static int __init save_microcode_in_initrd(void)
+{
+	unsigned int cpuid_1_eax = native_cpuid_eax(1);
+	struct cpuinfo_x86 *c = &boot_cpu_data;
+	struct cont_desc desc = { 0 };
+	enum ucode_state ret;
+	struct cpio_data cp;
+
+	if (dis_ucode_ldr || c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10)
+		return 0;
+
+	if (!find_blobs_in_containers(&cp))
+		return -EINVAL;
+
+	scan_containers(cp.data, cp.size, &desc);
+	if (!desc.mc)
+		return -EINVAL;
+
+	ret = _load_microcode_amd(x86_family(cpuid_1_eax), desc.data, desc.size);
+	if (ret > UCODE_UPDATED)
+		return -EINVAL;
+
+	return 0;
+}
+early_initcall(save_microcode_in_initrd);
+
 /*
  * AMD microcode firmware naming convention, up to family 15h they are in
  * the legacy file:

From 037e81fb9d2dfe7b31fd97e5f578854e38f09887 Mon Sep 17 00:00:00 2001
From: "Borislav Petkov (AMD)" <bp@alien8.de>
Date: Thu, 23 Jan 2025 13:02:32 +0100
Subject: [PATCH 0166/1173] x86/microcode/AMD: Add get_patch_level()

Put the MSR_AMD64_PATCH_LEVEL reading of the current microcode revision
the hw has, into a separate function.

Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20250211163648.30531-6-bp@kernel.org
---
 arch/x86/kernel/cpu/microcode/amd.c | 46 +++++++++++++++--------------
 1 file changed, 24 insertions(+), 22 deletions(-)

diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index adfea4d0d1297..31f90e129b083 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -145,6 +145,15 @@ ucode_path[] __maybe_unused = "kernel/x86/microcode/AuthenticAMD.bin";
  */
 static u32 bsp_cpuid_1_eax __ro_after_init;
 
+static u32 get_patch_level(void)
+{
+	u32 rev, dummy __always_unused;
+
+	native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
+
+	return rev;
+}
+
 static union cpuid_1_eax ucode_rev_to_cpuid(unsigned int val)
 {
 	union zen_patch_rev p;
@@ -483,10 +492,10 @@ static void scan_containers(u8 *ucode, size_t size, struct cont_desc *desc)
 	}
 }
 
-static bool __apply_microcode_amd(struct microcode_amd *mc, unsigned int psize)
+static bool __apply_microcode_amd(struct microcode_amd *mc, u32 *cur_rev,
+				  unsigned int psize)
 {
 	unsigned long p_addr = (unsigned long)&mc->hdr.data_code;
-	u32 rev, dummy;
 
 	native_wrmsrl(MSR_AMD64_PATCH_LOADER, p_addr);
 
@@ -504,9 +513,8 @@ static bool __apply_microcode_amd(struct microcode_amd *mc, unsigned int psize)
 	}
 
 	/* verify patch application was successful */
-	native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
-
-	if (rev != mc->hdr.patch_id)
+	*cur_rev = get_patch_level();
+	if (*cur_rev != mc->hdr.patch_id)
 		return false;
 
 	return true;
@@ -563,11 +571,12 @@ void __init load_ucode_amd_bsp(struct early_load_data *ed, unsigned int cpuid_1_
 	struct cont_desc desc = { };
 	struct microcode_amd *mc;
 	struct cpio_data cp = { };
-	u32 dummy;
+	u32 rev;
 
 	bsp_cpuid_1_eax = cpuid_1_eax;
 
-	native_rdmsr(MSR_AMD64_PATCH_LEVEL, ed->old_rev, dummy);
+	rev = get_patch_level();
+	ed->old_rev = rev;
 
 	/* Needed in load_microcode_amd() */
 	ucode_cpu_info[0].cpu_sig.sig = cpuid_1_eax;
@@ -589,8 +598,8 @@ void __init load_ucode_amd_bsp(struct early_load_data *ed, unsigned int cpuid_1_
 	if (ed->old_rev > mc->hdr.patch_id)
 		return;
 
-	if (__apply_microcode_amd(mc, desc.psize))
-		native_rdmsr(MSR_AMD64_PATCH_LEVEL, ed->new_rev, dummy);
+	if (__apply_microcode_amd(mc, &rev, desc.psize))
+		ed->new_rev = rev;
 }
 
 static inline bool patch_cpus_equivalent(struct ucode_patch *p,
@@ -692,14 +701,9 @@ static void free_cache(void)
 static struct ucode_patch *find_patch(unsigned int cpu)
 {
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-	u32 rev, dummy __always_unused;
 	u16 equiv_id = 0;
 
-	/* fetch rev if not populated yet: */
-	if (!uci->cpu_sig.rev) {
-		rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
-		uci->cpu_sig.rev = rev;
-	}
+	uci->cpu_sig.rev = get_patch_level();
 
 	if (x86_family(bsp_cpuid_1_eax) < 0x17) {
 		equiv_id = find_equiv_id(&equiv_table, uci->cpu_sig.sig);
@@ -722,22 +726,20 @@ void reload_ucode_amd(unsigned int cpu)
 
 	mc = p->data;
 
-	rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
-
+	rev = get_patch_level();
 	if (rev < mc->hdr.patch_id) {
-		if (__apply_microcode_amd(mc, p->size))
-			pr_info_once("reload revision: 0x%08x\n", mc->hdr.patch_id);
+		if (__apply_microcode_amd(mc, &rev, p->size))
+			pr_info_once("reload revision: 0x%08x\n", rev);
 	}
 }
 
 static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig)
 {
-	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 	struct ucode_patch *p;
 
 	csig->sig = cpuid_eax(0x00000001);
-	csig->rev = c->microcode;
+	csig->rev = get_patch_level();
 
 	/*
 	 * a patch could have been loaded early, set uci->mc so that
@@ -778,7 +780,7 @@ static enum ucode_state apply_microcode_amd(int cpu)
 		goto out;
 	}
 
-	if (!__apply_microcode_amd(mc_amd, p->size)) {
+	if (!__apply_microcode_amd(mc_amd, &rev, p->size)) {
 		pr_err("CPU%d: update failed for patch_level=0x%08x\n",
 			cpu, mc_amd->hdr.patch_id);
 		return UCODE_ERROR;

From 735049b801cf3d597752017385cfc8768ce44303 Mon Sep 17 00:00:00 2001
From: Yazen Ghannam <yazen.ghannam@amd.com>
Date: Thu, 30 Jan 2025 19:48:55 +0000
Subject: [PATCH 0167/1173] x86/amd_node, platform/x86/amd/hsmp: Have HSMP use
 SMN through AMD_NODE
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The HSMP interface is just an SMN interface with different offsets.

Define an HSMP wrapper in the SMN code and have the HSMP platform driver
use that rather than a local solution.

Also, remove the "root" member from AMD_NB, since there are no more
users of it.

Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Carlos Bilbao <carlos.bilbao@kernel.org>
Acked-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://lore.kernel.org/r/20250130-wip-x86-amd-nb-cleanup-v4-1-b5cc997e471b@amd.com
---
 arch/x86/include/asm/amd_nb.h         |  1 -
 arch/x86/include/asm/amd_node.h       | 13 ++++++++++
 arch/x86/kernel/amd_nb.c              |  1 -
 arch/x86/kernel/amd_node.c            |  9 +++++++
 drivers/platform/x86/amd/hsmp/Kconfig |  2 +-
 drivers/platform/x86/amd/hsmp/acpi.c  |  7 +++---
 drivers/platform/x86/amd/hsmp/hsmp.c  |  1 -
 drivers/platform/x86/amd/hsmp/hsmp.h  |  3 ---
 drivers/platform/x86/amd/hsmp/plat.c  | 36 +++++++++------------------
 9 files changed, 39 insertions(+), 34 deletions(-)

diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
index 4c4efb93045ed..adfa0854cf2da 100644
--- a/arch/x86/include/asm/amd_nb.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -27,7 +27,6 @@ struct amd_l3_cache {
 };
 
 struct amd_northbridge {
-	struct pci_dev *root;
 	struct pci_dev *misc;
 	struct pci_dev *link;
 	struct amd_l3_cache l3_cache;
diff --git a/arch/x86/include/asm/amd_node.h b/arch/x86/include/asm/amd_node.h
index 113ad3e8ee40a..002c3afbd30f9 100644
--- a/arch/x86/include/asm/amd_node.h
+++ b/arch/x86/include/asm/amd_node.h
@@ -30,7 +30,20 @@ static inline u16 amd_num_nodes(void)
 	return topology_amd_nodes_per_pkg() * topology_max_packages();
 }
 
+#ifdef CONFIG_AMD_NODE
 int __must_check amd_smn_read(u16 node, u32 address, u32 *value);
 int __must_check amd_smn_write(u16 node, u32 address, u32 value);
 
+/* Should only be used by the HSMP driver. */
+int __must_check amd_smn_hsmp_rdwr(u16 node, u32 address, u32 *value, bool write);
+#else
+static inline int __must_check amd_smn_read(u16 node, u32 address, u32 *value) { return -ENODEV; }
+static inline int __must_check amd_smn_write(u16 node, u32 address, u32 value) { return -ENODEV; }
+
+static inline int __must_check amd_smn_hsmp_rdwr(u16 node, u32 address, u32 *value, bool write)
+{
+	return -ENODEV;
+}
+#endif /* CONFIG_AMD_NODE */
+
 #endif /*_ASM_X86_AMD_NODE_H_*/
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 11fac09e3a8cb..24d7a87edf9c0 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -73,7 +73,6 @@ static int amd_cache_northbridges(void)
 	amd_northbridges.nb = nb;
 
 	for (i = 0; i < amd_northbridges.num; i++) {
-		node_to_amd_nb(i)->root = amd_node_get_root(i);
 		node_to_amd_nb(i)->misc = amd_node_get_func(i, 3);
 
 		/*
diff --git a/arch/x86/kernel/amd_node.c b/arch/x86/kernel/amd_node.c
index d2ec7fd555c51..65045f223c10a 100644
--- a/arch/x86/kernel/amd_node.c
+++ b/arch/x86/kernel/amd_node.c
@@ -97,6 +97,9 @@ static DEFINE_MUTEX(smn_mutex);
 #define SMN_INDEX_OFFSET	0x60
 #define SMN_DATA_OFFSET		0x64
 
+#define HSMP_INDEX_OFFSET	0xc4
+#define HSMP_DATA_OFFSET	0xc8
+
 /*
  * SMN accesses may fail in ways that are difficult to detect here in the called
  * functions amd_smn_read() and amd_smn_write(). Therefore, callers must do
@@ -179,6 +182,12 @@ int __must_check amd_smn_write(u16 node, u32 address, u32 value)
 }
 EXPORT_SYMBOL_GPL(amd_smn_write);
 
+int __must_check amd_smn_hsmp_rdwr(u16 node, u32 address, u32 *value, bool write)
+{
+	return __amd_smn_rw(HSMP_INDEX_OFFSET, HSMP_DATA_OFFSET, node, address, value, write);
+}
+EXPORT_SYMBOL_GPL(amd_smn_hsmp_rdwr);
+
 static int amd_cache_roots(void)
 {
 	u16 node, num_nodes = amd_num_nodes();
diff --git a/drivers/platform/x86/amd/hsmp/Kconfig b/drivers/platform/x86/amd/hsmp/Kconfig
index 7d10d4462a453..d6f7a62d55b5e 100644
--- a/drivers/platform/x86/amd/hsmp/Kconfig
+++ b/drivers/platform/x86/amd/hsmp/Kconfig
@@ -7,7 +7,7 @@ config AMD_HSMP
 	tristate
 
 menu "AMD HSMP Driver"
-	depends on AMD_NB || COMPILE_TEST
+	depends on AMD_NODE || COMPILE_TEST
 
 config AMD_HSMP_ACPI
 	tristate "AMD HSMP ACPI device driver"
diff --git a/drivers/platform/x86/amd/hsmp/acpi.c b/drivers/platform/x86/amd/hsmp/acpi.c
index 444b43be35a25..c1eccb3c80c5c 100644
--- a/drivers/platform/x86/amd/hsmp/acpi.c
+++ b/drivers/platform/x86/amd/hsmp/acpi.c
@@ -10,7 +10,6 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <asm/amd_hsmp.h>
-#include <asm/amd_nb.h>
 
 #include <linux/acpi.h>
 #include <linux/device.h>
@@ -24,6 +23,8 @@
 
 #include <uapi/asm-generic/errno-base.h>
 
+#include <asm/amd_node.h>
+
 #include "hsmp.h"
 
 #define DRIVER_NAME		"amd_hsmp"
@@ -321,8 +322,8 @@ static int hsmp_acpi_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	if (!hsmp_pdev->is_probed) {
-		hsmp_pdev->num_sockets = amd_nb_num();
-		if (hsmp_pdev->num_sockets == 0 || hsmp_pdev->num_sockets > MAX_AMD_SOCKETS)
+		hsmp_pdev->num_sockets = amd_num_nodes();
+		if (hsmp_pdev->num_sockets == 0 || hsmp_pdev->num_sockets > MAX_AMD_NUM_NODES)
 			return -ENODEV;
 
 		hsmp_pdev->sock = devm_kcalloc(&pdev->dev, hsmp_pdev->num_sockets,
diff --git a/drivers/platform/x86/amd/hsmp/hsmp.c b/drivers/platform/x86/amd/hsmp/hsmp.c
index 03164e30b3a50..a3ac09a90de45 100644
--- a/drivers/platform/x86/amd/hsmp/hsmp.c
+++ b/drivers/platform/x86/amd/hsmp/hsmp.c
@@ -8,7 +8,6 @@
  */
 
 #include <asm/amd_hsmp.h>
-#include <asm/amd_nb.h>
 
 #include <linux/acpi.h>
 #include <linux/delay.h>
diff --git a/drivers/platform/x86/amd/hsmp/hsmp.h b/drivers/platform/x86/amd/hsmp/hsmp.h
index e852f0a947e4f..af8b21f821d66 100644
--- a/drivers/platform/x86/amd/hsmp/hsmp.h
+++ b/drivers/platform/x86/amd/hsmp/hsmp.h
@@ -21,8 +21,6 @@
 
 #define HSMP_ATTR_GRP_NAME_SIZE	10
 
-#define MAX_AMD_SOCKETS 8
-
 #define HSMP_CDEV_NAME		"hsmp_cdev"
 #define HSMP_DEVNODE_NAME	"hsmp"
 
@@ -41,7 +39,6 @@ struct hsmp_socket {
 	void __iomem *virt_base_addr;
 	struct semaphore hsmp_sem;
 	char name[HSMP_ATTR_GRP_NAME_SIZE];
-	struct pci_dev *root;
 	struct device *dev;
 	u16 sock_ind;
 	int (*amd_hsmp_rdwr)(struct hsmp_socket *sock, u32 off, u32 *val, bool rw);
diff --git a/drivers/platform/x86/amd/hsmp/plat.c b/drivers/platform/x86/amd/hsmp/plat.c
index 02ca85762b686..b9782a078dbd2 100644
--- a/drivers/platform/x86/amd/hsmp/plat.c
+++ b/drivers/platform/x86/amd/hsmp/plat.c
@@ -10,14 +10,16 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <asm/amd_hsmp.h>
-#include <asm/amd_nb.h>
 
+#include <linux/build_bug.h>
 #include <linux/device.h>
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/platform_device.h>
 #include <linux/sysfs.h>
 
+#include <asm/amd_node.h>
+
 #include "hsmp.h"
 
 #define DRIVER_NAME		"amd_hsmp"
@@ -34,28 +36,12 @@
 #define SMN_HSMP_MSG_RESP	0x0010980
 #define SMN_HSMP_MSG_DATA	0x00109E0
 
-#define HSMP_INDEX_REG		0xc4
-#define HSMP_DATA_REG		0xc8
-
 static struct hsmp_plat_device *hsmp_pdev;
 
 static int amd_hsmp_pci_rdwr(struct hsmp_socket *sock, u32 offset,
 			     u32 *value, bool write)
 {
-	int ret;
-
-	if (!sock->root)
-		return -ENODEV;
-
-	ret = pci_write_config_dword(sock->root, HSMP_INDEX_REG,
-				     sock->mbinfo.base_addr + offset);
-	if (ret)
-		return ret;
-
-	ret = (write ? pci_write_config_dword(sock->root, HSMP_DATA_REG, *value)
-		     : pci_read_config_dword(sock->root, HSMP_DATA_REG, value));
-
-	return ret;
+	return amd_smn_hsmp_rdwr(sock->sock_ind, sock->mbinfo.base_addr + offset, value, write);
 }
 
 static ssize_t hsmp_metric_tbl_plat_read(struct file *filp, struct kobject *kobj,
@@ -95,7 +81,12 @@ static umode_t hsmp_is_sock_attr_visible(struct kobject *kobj,
  * Static array of 8 + 1(for NULL) elements is created below
  * to create sysfs groups for sockets.
  * is_bin_visible function is used to show / hide the necessary groups.
+ *
+ * Validate the maximum number against MAX_AMD_NUM_NODES. If this changes,
+ * then the attributes and groups below must be adjusted.
  */
+static_assert(MAX_AMD_NUM_NODES == 8);
+
 #define HSMP_BIN_ATTR(index, _list)					\
 static const struct bin_attribute attr##index = {			\
 	.attr = { .name = HSMP_METRICS_TABLE_NAME, .mode = 0444},	\
@@ -159,10 +150,7 @@ static int init_platform_device(struct device *dev)
 	int ret, i;
 
 	for (i = 0; i < hsmp_pdev->num_sockets; i++) {
-		if (!node_to_amd_nb(i))
-			return -ENODEV;
 		sock = &hsmp_pdev->sock[i];
-		sock->root			= node_to_amd_nb(i)->root;
 		sock->sock_ind			= i;
 		sock->dev			= dev;
 		sock->mbinfo.base_addr		= SMN_HSMP_BASE;
@@ -305,11 +293,11 @@ static int __init hsmp_plt_init(void)
 		return -ENOMEM;
 
 	/*
-	 * amd_nb_num() returns number of SMN/DF interfaces present in the system
+	 * amd_num_nodes() returns number of SMN/DF interfaces present in the system
 	 * if we have N SMN/DF interfaces that ideally means N sockets
 	 */
-	hsmp_pdev->num_sockets = amd_nb_num();
-	if (hsmp_pdev->num_sockets == 0 || hsmp_pdev->num_sockets > MAX_AMD_SOCKETS)
+	hsmp_pdev->num_sockets = amd_num_nodes();
+	if (hsmp_pdev->num_sockets == 0 || hsmp_pdev->num_sockets > MAX_AMD_NUM_NODES)
 		return ret;
 
 	ret = platform_driver_register(&amd_hsmp_driver);

From bebe0afb74514ae51f4f348b28326c658b02209d Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Thu, 30 Jan 2025 19:48:56 +0000
Subject: [PATCH 0168/1173] x86/amd_node: Add SMN offsets to exclusive region
 access

Offsets 0x60 and 0x64 are used internally by kernel drivers that call
the amd_smn_read() and amd_smn_write() functions. If userspace accesses
the regions at the same time as the kernel it may cause malfunctions in
drivers using the offsets.

Add these offsets to the exclusions so that the kernel is tainted if a
non locked down userspace tries to access them.

Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20250130-wip-x86-amd-nb-cleanup-v4-2-b5cc997e471b@amd.com
---
 arch/x86/kernel/amd_node.c | 41 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 41 insertions(+)

diff --git a/arch/x86/kernel/amd_node.c b/arch/x86/kernel/amd_node.c
index 65045f223c10a..ac571948cb353 100644
--- a/arch/x86/kernel/amd_node.c
+++ b/arch/x86/kernel/amd_node.c
@@ -93,6 +93,7 @@ static struct pci_dev **amd_roots;
 
 /* Protect the PCI config register pairs used for SMN. */
 static DEFINE_MUTEX(smn_mutex);
+static bool smn_exclusive;
 
 #define SMN_INDEX_OFFSET	0x60
 #define SMN_DATA_OFFSET		0x64
@@ -149,6 +150,9 @@ static int __amd_smn_rw(u8 i_off, u8 d_off, u16 node, u32 address, u32 *value, b
 	if (!root)
 		return err;
 
+	if (!smn_exclusive)
+		return err;
+
 	guard(mutex)(&smn_mutex);
 
 	err = pci_write_config_dword(root, i_off, address);
@@ -202,6 +206,39 @@ static int amd_cache_roots(void)
 	return 0;
 }
 
+static int reserve_root_config_spaces(void)
+{
+	struct pci_dev *root = NULL;
+	struct pci_bus *bus = NULL;
+
+	while ((bus = pci_find_next_bus(bus))) {
+		/* Root device is Device 0 Function 0 on each Primary Bus. */
+		root = pci_get_slot(bus, 0);
+		if (!root)
+			continue;
+
+		if (root->vendor != PCI_VENDOR_ID_AMD &&
+		    root->vendor != PCI_VENDOR_ID_HYGON)
+			continue;
+
+		pci_dbg(root, "Reserving PCI config space\n");
+
+		/*
+		 * There are a few SMN index/data pairs and other registers
+		 * that shouldn't be accessed by user space.
+		 * So reserve the entire PCI config space for simplicity rather
+		 * than covering specific registers piecemeal.
+		 */
+		if (!pci_request_config_region_exclusive(root, 0, PCI_CFG_SPACE_SIZE, NULL)) {
+			pci_err(root, "Failed to reserve config space\n");
+			return -EEXIST;
+		}
+	}
+
+	smn_exclusive = true;
+	return 0;
+}
+
 static int __init amd_smn_init(void)
 {
 	int err;
@@ -218,6 +255,10 @@ static int __init amd_smn_init(void)
 	if (err)
 		return err;
 
+	err = reserve_root_config_spaces();
+	if (err)
+		return err;
+
 	return 0;
 }
 

From 6b06755af6679fd7c98ebc017ac31c8a74127538 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Thu, 30 Jan 2025 19:48:57 +0000
Subject: [PATCH 0169/1173] x86/amd_node: Add support for debugfs access to SMN
 registers

There are certain registers on AMD Zen systems that can only be accessed
through SMN.

Introduce a new interface that provides debugfs files for accessing SMN.  As
this introduces the capability for userspace to manipulate the hardware in
unpredictable ways, taint the kernel when writing.

Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20250130-wip-x86-amd-nb-cleanup-v4-3-b5cc997e471b@amd.com
---
 arch/x86/kernel/amd_node.c | 99 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 99 insertions(+)

diff --git a/arch/x86/kernel/amd_node.c b/arch/x86/kernel/amd_node.c
index ac571948cb353..b670fa85c61b4 100644
--- a/arch/x86/kernel/amd_node.c
+++ b/arch/x86/kernel/amd_node.c
@@ -8,6 +8,7 @@
  * Author: Yazen Ghannam <Yazen.Ghannam@amd.com>
  */
 
+#include <linux/debugfs.h>
 #include <asm/amd_node.h>
 
 /*
@@ -192,6 +193,87 @@ int __must_check amd_smn_hsmp_rdwr(u16 node, u32 address, u32 *value, bool write
 }
 EXPORT_SYMBOL_GPL(amd_smn_hsmp_rdwr);
 
+static struct dentry *debugfs_dir;
+static u16 debug_node;
+static u32 debug_address;
+
+static ssize_t smn_node_write(struct file *file, const char __user *userbuf,
+			      size_t count, loff_t *ppos)
+{
+	u16 node;
+	int ret;
+
+	ret = kstrtou16_from_user(userbuf, count, 0, &node);
+	if (ret)
+		return ret;
+
+	if (node >= amd_num_nodes())
+		return -ENODEV;
+
+	debug_node = node;
+	return count;
+}
+
+static int smn_node_show(struct seq_file *m, void *v)
+{
+	seq_printf(m, "0x%08x\n", debug_node);
+	return 0;
+}
+
+static ssize_t smn_address_write(struct file *file, const char __user *userbuf,
+				 size_t count, loff_t *ppos)
+{
+	int ret;
+
+	ret = kstrtouint_from_user(userbuf, count, 0, &debug_address);
+	if (ret)
+		return ret;
+
+	return count;
+}
+
+static int smn_address_show(struct seq_file *m, void *v)
+{
+	seq_printf(m, "0x%08x\n", debug_address);
+	return 0;
+}
+
+static int smn_value_show(struct seq_file *m, void *v)
+{
+	u32 val;
+	int ret;
+
+	ret = amd_smn_read(debug_node, debug_address, &val);
+	if (ret)
+		return ret;
+
+	seq_printf(m, "0x%08x\n", val);
+	return 0;
+}
+
+static ssize_t smn_value_write(struct file *file, const char __user *userbuf,
+			       size_t count, loff_t *ppos)
+{
+	u32 val;
+	int ret;
+
+	ret = kstrtouint_from_user(userbuf, count, 0, &val);
+	if (ret)
+		return ret;
+
+	add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK);
+
+	ret = amd_smn_write(debug_node, debug_address, val);
+	if (ret)
+		return ret;
+
+	return count;
+}
+
+DEFINE_SHOW_STORE_ATTRIBUTE(smn_node);
+DEFINE_SHOW_STORE_ATTRIBUTE(smn_address);
+DEFINE_SHOW_STORE_ATTRIBUTE(smn_value);
+
 static int amd_cache_roots(void)
 {
 	u16 node, num_nodes = amd_num_nodes();
@@ -239,6 +321,15 @@ static int reserve_root_config_spaces(void)
 	return 0;
 }
 
+static bool enable_dfs;
+
+static int __init amd_smn_enable_dfs(char *str)
+{
+	enable_dfs = true;
+	return 1;
+}
+__setup("amd_smn_debugfs_enable", amd_smn_enable_dfs);
+
 static int __init amd_smn_init(void)
 {
 	int err;
@@ -259,6 +350,14 @@ static int __init amd_smn_init(void)
 	if (err)
 		return err;
 
+	if (enable_dfs) {
+		debugfs_dir = debugfs_create_dir("amd_smn", arch_debugfs_dir);
+
+		debugfs_create_file("node",	0600, debugfs_dir, NULL, &smn_node_fops);
+		debugfs_create_file("address",	0600, debugfs_dir, NULL, &smn_address_fops);
+		debugfs_create_file("value",	0600, debugfs_dir, NULL, &smn_value_fops);
+	}
+
 	return 0;
 }
 

From 7fb39882b20c98a9a393c244c86b56ef6933cff8 Mon Sep 17 00:00:00 2001
From: Milan Broz <gmazyland@gmail.com>
Date: Sun, 16 Feb 2025 11:42:09 +0100
Subject: [PATCH 0170/1173] dm-integrity: Avoid divide by zero in table status
 in Inline mode

In Inline mode, the journal is unused, and journal_sectors is zero.

Calculating the journal watermark requires dividing by journal_sectors,
which should be done only if the journal is configured.

Otherwise, a simple table query (dmsetup table) can cause OOPS.

This bug did not show on some systems, perhaps only due to
compiler optimization.

On my 32-bit testing machine, this reliably crashes with the following:

 : Oops: divide error: 0000 [#1] PREEMPT SMP
 : CPU: 0 UID: 0 PID: 2450 Comm: dmsetup Not tainted 6.14.0-rc2+ #959
 : EIP: dm_integrity_status+0x2f8/0xab0 [dm_integrity]
 ...

Signed-off-by: Milan Broz <gmazyland@gmail.com>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Fixes: fb0987682c62 ("dm-integrity: introduce the Inline mode")
Cc: stable@vger.kernel.org # 6.11+
---
 drivers/md/dm-integrity.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index ee9f7cecd78e0..555dc06b94228 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -3790,10 +3790,6 @@ static void dm_integrity_status(struct dm_target *ti, status_type_t type,
 		break;
 
 	case STATUSTYPE_TABLE: {
-		__u64 watermark_percentage = (__u64)(ic->journal_entries - ic->free_sectors_threshold) * 100;
-
-		watermark_percentage += ic->journal_entries / 2;
-		do_div(watermark_percentage, ic->journal_entries);
 		arg_count = 3;
 		arg_count += !!ic->meta_dev;
 		arg_count += ic->sectors_per_block != 1;
@@ -3826,6 +3822,10 @@ static void dm_integrity_status(struct dm_target *ti, status_type_t type,
 		DMEMIT(" interleave_sectors:%u", 1U << ic->sb->log2_interleave_sectors);
 		DMEMIT(" buffer_sectors:%u", 1U << ic->log2_buffer_sectors);
 		if (ic->mode == 'J') {
+			__u64 watermark_percentage = (__u64)(ic->journal_entries - ic->free_sectors_threshold) * 100;
+
+			watermark_percentage += ic->journal_entries / 2;
+			do_div(watermark_percentage, ic->journal_entries);
 			DMEMIT(" journal_watermark:%u", (unsigned int)watermark_percentage);
 			DMEMIT(" commit_time:%u", ic->autocommit_msec);
 		}

From c19525b5fb71a355079063bb14adcddae60cf922 Mon Sep 17 00:00:00 2001
From: Milan Broz <gmazyland@gmail.com>
Date: Sun, 16 Feb 2025 11:42:10 +0100
Subject: [PATCH 0171/1173] dm-integrity: Do not emit journal configuration in
 DM table for Inline mode

The Inline mode does not use a journal; it makes no sense to print
journal information in DM table. Print it only if the journal is used.

The same applies to interleave_sectors (unused for Inline mode).

Also, add comments for arg_count, as the current calculation
is quite obscure.

Signed-off-by: Milan Broz <gmazyland@gmail.com>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
---
 drivers/md/dm-integrity.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 555dc06b94228..c45464b6576aa 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -3790,16 +3790,18 @@ static void dm_integrity_status(struct dm_target *ti, status_type_t type,
 		break;
 
 	case STATUSTYPE_TABLE: {
-		arg_count = 3;
+		arg_count = 1; /* buffer_sectors */
 		arg_count += !!ic->meta_dev;
 		arg_count += ic->sectors_per_block != 1;
 		arg_count += !!(ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING));
 		arg_count += ic->reset_recalculate_flag;
 		arg_count += ic->discard;
-		arg_count += ic->mode == 'J';
-		arg_count += ic->mode == 'J';
-		arg_count += ic->mode == 'B';
-		arg_count += ic->mode == 'B';
+		arg_count += ic->mode != 'I'; /* interleave_sectors */
+		arg_count += ic->mode == 'J'; /* journal_sectors */
+		arg_count += ic->mode == 'J'; /* journal_watermark */
+		arg_count += ic->mode == 'J'; /* commit_time */
+		arg_count += ic->mode == 'B'; /* sectors_per_bit */
+		arg_count += ic->mode == 'B'; /* bitmap_flush_interval */
 		arg_count += !!ic->internal_hash_alg.alg_string;
 		arg_count += !!ic->journal_crypt_alg.alg_string;
 		arg_count += !!ic->journal_mac_alg.alg_string;
@@ -3818,14 +3820,15 @@ static void dm_integrity_status(struct dm_target *ti, status_type_t type,
 			DMEMIT(" reset_recalculate");
 		if (ic->discard)
 			DMEMIT(" allow_discards");
-		DMEMIT(" journal_sectors:%u", ic->initial_sectors - SB_SECTORS);
-		DMEMIT(" interleave_sectors:%u", 1U << ic->sb->log2_interleave_sectors);
+		if (ic->mode != 'I')
+			DMEMIT(" interleave_sectors:%u", 1U << ic->sb->log2_interleave_sectors);
 		DMEMIT(" buffer_sectors:%u", 1U << ic->log2_buffer_sectors);
 		if (ic->mode == 'J') {
 			__u64 watermark_percentage = (__u64)(ic->journal_entries - ic->free_sectors_threshold) * 100;
 
 			watermark_percentage += ic->journal_entries / 2;
 			do_div(watermark_percentage, ic->journal_entries);
+			DMEMIT(" journal_sectors:%u", ic->initial_sectors - SB_SECTORS);
 			DMEMIT(" journal_watermark:%u", (unsigned int)watermark_percentage);
 			DMEMIT(" commit_time:%u", ic->autocommit_msec);
 		}

From 9d846b1aebbe488f245f1aa463802ff9c34cc078 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Mon, 10 Feb 2025 11:51:55 +0100
Subject: [PATCH 0172/1173] gpiolib: check the return value of
 gpio_chip::get_direction()

As per the API contract - gpio_chip::get_direction() may fail and return
a negative error number. However, we treat it as if it always returned 0
or 1. Check the return value of the callback and propagate the error
number up the stack.

Cc: stable@vger.kernel.org
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20250210-gpio-sanitize-retvals-v1-1-12ea88506cb2@linaro.org
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpiolib.c | 44 ++++++++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 15 deletions(-)

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index ca2f58a2cd45e..29110dc436f15 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1057,8 +1057,11 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data,
 		desc->gdev = gdev;
 
 		if (gc->get_direction && gpiochip_line_is_valid(gc, desc_index)) {
-			assign_bit(FLAG_IS_OUT,
-				   &desc->flags, !gc->get_direction(gc, desc_index));
+			ret = gc->get_direction(gc, desc_index);
+			if (ret < 0)
+				goto err_cleanup_desc_srcu;
+
+			assign_bit(FLAG_IS_OUT, &desc->flags, !ret);
 		} else {
 			assign_bit(FLAG_IS_OUT,
 				   &desc->flags, !gc->direction_input);
@@ -2728,13 +2731,18 @@ int gpiod_direction_input_nonotify(struct gpio_desc *desc)
 	if (guard.gc->direction_input) {
 		ret = guard.gc->direction_input(guard.gc,
 						gpio_chip_hwgpio(desc));
-	} else if (guard.gc->get_direction &&
-		  (guard.gc->get_direction(guard.gc,
-					   gpio_chip_hwgpio(desc)) != 1)) {
-		gpiod_warn(desc,
-			   "%s: missing direction_input() operation and line is output\n",
-			   __func__);
-		return -EIO;
+	} else if (guard.gc->get_direction) {
+		ret = guard.gc->get_direction(guard.gc,
+					      gpio_chip_hwgpio(desc));
+		if (ret < 0)
+			return ret;
+
+		if (ret != GPIO_LINE_DIRECTION_IN) {
+			gpiod_warn(desc,
+				   "%s: missing direction_input() operation and line is output\n",
+				    __func__);
+			return -EIO;
+		}
 	}
 	if (ret == 0) {
 		clear_bit(FLAG_IS_OUT, &desc->flags);
@@ -2771,12 +2779,18 @@ static int gpiod_direction_output_raw_commit(struct gpio_desc *desc, int value)
 						 gpio_chip_hwgpio(desc), val);
 	} else {
 		/* Check that we are in output mode if we can */
-		if (guard.gc->get_direction &&
-		    guard.gc->get_direction(guard.gc, gpio_chip_hwgpio(desc))) {
-			gpiod_warn(desc,
-				"%s: missing direction_output() operation\n",
-				__func__);
-			return -EIO;
+		if (guard.gc->get_direction) {
+			ret = guard.gc->get_direction(guard.gc,
+						      gpio_chip_hwgpio(desc));
+			if (ret < 0)
+				return ret;
+
+			if (ret != GPIO_LINE_DIRECTION_OUT) {
+				gpiod_warn(desc,
+					   "%s: missing direction_output() operation\n",
+					   __func__);
+				return -EIO;
+			}
 		}
 		/*
 		 * If we can't actively set the direction, we are some

From 4e667a1968099c6deadee2313ecd648f8f0a8956 Mon Sep 17 00:00:00 2001
From: Johan Korsnes <johan.korsnes@remarkable.no>
Date: Mon, 17 Feb 2025 10:16:43 +0100
Subject: [PATCH 0173/1173] gpio: vf610: add locking to gpio direction
 functions

Add locking to `vf610_gpio_direction_input|output()` functions. Without
this locking, a race condition exists between concurrent calls to these
functions, potentially leading to incorrect GPIO direction settings.

To verify the correctness of this fix, a `trylock` patch was applied,
where after a couple of reboots the race was confirmed. I.e., one user
had to wait before acquiring the lock. With this patch the race has not
been encountered. It's worth mentioning that any type of debugging
(printing, tracing, etc.) would "resolve"/hide the issue.

Fixes: 659d8a62311f ("gpio: vf610: add imx7ulp support")
Signed-off-by: Johan Korsnes <johan.korsnes@remarkable.no>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Haibo Chen <haibo.chen@nxp.com>
Cc: Bartosz Golaszewski <brgl@bgdev.pl>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250217091643.679644-1-johan.korsnes@remarkable.no
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpio-vf610.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpio/gpio-vf610.c b/drivers/gpio/gpio-vf610.c
index c4f34a347cb6e..c36a9dbccd4dd 100644
--- a/drivers/gpio/gpio-vf610.c
+++ b/drivers/gpio/gpio-vf610.c
@@ -36,6 +36,7 @@ struct vf610_gpio_port {
 	struct clk *clk_port;
 	struct clk *clk_gpio;
 	int irq;
+	spinlock_t lock; /* protect gpio direction registers */
 };
 
 #define GPIO_PDOR		0x00
@@ -124,6 +125,7 @@ static int vf610_gpio_direction_input(struct gpio_chip *chip, unsigned int gpio)
 	u32 val;
 
 	if (port->sdata->have_paddr) {
+		guard(spinlock_irqsave)(&port->lock);
 		val = vf610_gpio_readl(port->gpio_base + GPIO_PDDR);
 		val &= ~mask;
 		vf610_gpio_writel(val, port->gpio_base + GPIO_PDDR);
@@ -142,6 +144,7 @@ static int vf610_gpio_direction_output(struct gpio_chip *chip, unsigned int gpio
 	vf610_gpio_set(chip, gpio, value);
 
 	if (port->sdata->have_paddr) {
+		guard(spinlock_irqsave)(&port->lock);
 		val = vf610_gpio_readl(port->gpio_base + GPIO_PDDR);
 		val |= mask;
 		vf610_gpio_writel(val, port->gpio_base + GPIO_PDDR);
@@ -297,6 +300,7 @@ static int vf610_gpio_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	port->sdata = device_get_match_data(dev);
+	spin_lock_init(&port->lock);
 
 	dual_base = port->sdata->have_dual_base;
 

From c7db342e3b4744688be1e27e31254c1d31a35274 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Mon, 17 Feb 2025 09:45:08 +0100
Subject: [PATCH 0174/1173] riscv: KVM: Fix hart suspend status check

"Not stopped" means started or suspended so we need to check for
a single state in order to have a chance to check for each state.
Also, we need to use target_vcpu when checking for the suspend
state.

Fixes: 763c8bed8c05 ("RISC-V: KVM: Implement SBI HSM suspend call")
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Link: https://lore.kernel.org/r/20250217084506.18763-8-ajones@ventanamicro.com
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_sbi_hsm.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/riscv/kvm/vcpu_sbi_hsm.c b/arch/riscv/kvm/vcpu_sbi_hsm.c
index dce667f4b6ab0..13a35eb77e8e3 100644
--- a/arch/riscv/kvm/vcpu_sbi_hsm.c
+++ b/arch/riscv/kvm/vcpu_sbi_hsm.c
@@ -79,12 +79,12 @@ static int kvm_sbi_hsm_vcpu_get_status(struct kvm_vcpu *vcpu)
 	target_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, target_vcpuid);
 	if (!target_vcpu)
 		return SBI_ERR_INVALID_PARAM;
-	if (!kvm_riscv_vcpu_stopped(target_vcpu))
-		return SBI_HSM_STATE_STARTED;
-	else if (vcpu->stat.generic.blocking)
+	if (kvm_riscv_vcpu_stopped(target_vcpu))
+		return SBI_HSM_STATE_STOPPED;
+	else if (target_vcpu->stat.generic.blocking)
 		return SBI_HSM_STATE_SUSPENDED;
 	else
-		return SBI_HSM_STATE_STOPPED;
+		return SBI_HSM_STATE_STARTED;
 }
 
 static int kvm_sbi_ext_hsm_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,

From e3219b0c491f2aa0e0b200a39d3352ab05cdda96 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Mon, 17 Feb 2025 09:45:09 +0100
Subject: [PATCH 0175/1173] riscv: KVM: Fix hart suspend_type use

The spec says suspend_type is 32 bits wide and "In case the data is
defined as 32bit wide, higher privilege software must ensure that it
only uses 32 bit data." Mask off upper bits of suspend_type before
using it.

Fixes: 763c8bed8c05 ("RISC-V: KVM: Implement SBI HSM suspend call")
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Link: https://lore.kernel.org/r/20250217084506.18763-9-ajones@ventanamicro.com
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_sbi_hsm.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/kvm/vcpu_sbi_hsm.c b/arch/riscv/kvm/vcpu_sbi_hsm.c
index 13a35eb77e8e3..3070bb31745de 100644
--- a/arch/riscv/kvm/vcpu_sbi_hsm.c
+++ b/arch/riscv/kvm/vcpu_sbi_hsm.c
@@ -9,6 +9,7 @@
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/kvm_host.h>
+#include <linux/wordpart.h>
 #include <asm/sbi.h>
 #include <asm/kvm_vcpu_sbi.h>
 
@@ -109,7 +110,7 @@ static int kvm_sbi_ext_hsm_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		}
 		return 0;
 	case SBI_EXT_HSM_HART_SUSPEND:
-		switch (cp->a0) {
+		switch (lower_32_bits(cp->a0)) {
 		case SBI_HSM_SUSPEND_RET_DEFAULT:
 			kvm_riscv_vcpu_wfi(vcpu);
 			break;

From 0611f78f83c93c000029ab01daa28166d03590ed Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Mon, 17 Feb 2025 09:45:10 +0100
Subject: [PATCH 0176/1173] riscv: KVM: Fix SBI IPI error generation

When an invalid function ID of an SBI extension is used we should
return not-supported, not invalid-param. Also, when we see that at
least one hartid constructed from the base and mask parameters is
invalid, then we should return invalid-param. Finally, rather than
relying on overflowing a left shift to result in zero and then using
that zero in a condition which [correctly] skips sending an IPI (but
loops unnecessarily), explicitly check for overflow and exit the loop
immediately.

Fixes: 5f862df5585c ("RISC-V: KVM: Add v0.1 replacement SBI extensions defined in v0.2")
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Link: https://lore.kernel.org/r/20250217084506.18763-10-ajones@ventanamicro.com
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_sbi_replace.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/kvm/vcpu_sbi_replace.c b/arch/riscv/kvm/vcpu_sbi_replace.c
index 9c2ab3dfa93aa..74e3a38c6a29e 100644
--- a/arch/riscv/kvm/vcpu_sbi_replace.c
+++ b/arch/riscv/kvm/vcpu_sbi_replace.c
@@ -51,9 +51,10 @@ static int kvm_sbi_ext_ipi_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
 	unsigned long hmask = cp->a0;
 	unsigned long hbase = cp->a1;
+	unsigned long hart_bit = 0, sentmask = 0;
 
 	if (cp->a6 != SBI_EXT_IPI_SEND_IPI) {
-		retdata->err_val = SBI_ERR_INVALID_PARAM;
+		retdata->err_val = SBI_ERR_NOT_SUPPORTED;
 		return 0;
 	}
 
@@ -62,15 +63,23 @@ static int kvm_sbi_ext_ipi_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		if (hbase != -1UL) {
 			if (tmp->vcpu_id < hbase)
 				continue;
-			if (!(hmask & (1UL << (tmp->vcpu_id - hbase))))
+			hart_bit = tmp->vcpu_id - hbase;
+			if (hart_bit >= __riscv_xlen)
+				goto done;
+			if (!(hmask & (1UL << hart_bit)))
 				continue;
 		}
 		ret = kvm_riscv_vcpu_set_interrupt(tmp, IRQ_VS_SOFT);
 		if (ret < 0)
 			break;
+		sentmask |= 1UL << hart_bit;
 		kvm_riscv_vcpu_pmu_incr_fw(tmp, SBI_PMU_FW_IPI_RCVD);
 	}
 
+done:
+	if (hbase != -1UL && (hmask ^ sentmask))
+		retdata->err_val = SBI_ERR_INVALID_PARAM;
+
 	return ret;
 }
 

From b901484852992cf3d162a5eab72251cc813ca624 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Mon, 17 Feb 2025 09:45:11 +0100
Subject: [PATCH 0177/1173] riscv: KVM: Fix SBI TIME error generation

When an invalid function ID of an SBI extension is used we should
return not-supported, not invalid-param.

Fixes: 5f862df5585c ("RISC-V: KVM: Add v0.1 replacement SBI extensions defined in v0.2")
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Link: https://lore.kernel.org/r/20250217084506.18763-11-ajones@ventanamicro.com
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_sbi_replace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/kvm/vcpu_sbi_replace.c b/arch/riscv/kvm/vcpu_sbi_replace.c
index 74e3a38c6a29e..5fbf3f94f1e85 100644
--- a/arch/riscv/kvm/vcpu_sbi_replace.c
+++ b/arch/riscv/kvm/vcpu_sbi_replace.c
@@ -21,7 +21,7 @@ static int kvm_sbi_ext_time_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	u64 next_cycle;
 
 	if (cp->a6 != SBI_EXT_TIME_SET_TIMER) {
-		retdata->err_val = SBI_ERR_INVALID_PARAM;
+		retdata->err_val = SBI_ERR_NOT_SUPPORTED;
 		return 0;
 	}
 

From 351e02b1733b057e33fe13fc03ca93ec799e4f78 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Mon, 17 Feb 2025 09:45:12 +0100
Subject: [PATCH 0178/1173] riscv: KVM: Fix SBI sleep_type use

The spec says sleep_type is 32 bits wide and "In case the data is
defined as 32bit wide, higher privilege software must ensure that it
only uses 32 bit data." Mask off upper bits of sleep_type before
using it.

Fixes: 023c15151fbb ("RISC-V: KVM: Add SBI system suspend support")
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Link: https://lore.kernel.org/r/20250217084506.18763-12-ajones@ventanamicro.com
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_sbi_system.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/kvm/vcpu_sbi_system.c b/arch/riscv/kvm/vcpu_sbi_system.c
index 5d55e08791fa1..bc0ebba890037 100644
--- a/arch/riscv/kvm/vcpu_sbi_system.c
+++ b/arch/riscv/kvm/vcpu_sbi_system.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/kvm_host.h>
+#include <linux/wordpart.h>
 
 #include <asm/kvm_vcpu_sbi.h>
 #include <asm/sbi.h>
@@ -19,7 +20,7 @@ static int kvm_sbi_ext_susp_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
 
 	switch (funcid) {
 	case SBI_EXT_SUSP_SYSTEM_SUSPEND:
-		if (cp->a0 != SBI_SUSP_SLEEP_TYPE_SUSPEND_TO_RAM) {
+		if (lower_32_bits(cp->a0) != SBI_SUSP_SLEEP_TYPE_SUSPEND_TO_RAM) {
 			retdata->err_val = SBI_ERR_INVALID_PARAM;
 			return 0;
 		}

From 539bd20352832b9244238a055eb169ccf1c41ff6 Mon Sep 17 00:00:00 2001
From: Amit Kumar Mahapatra <amit.kumar-mahapatra@amd.com>
Date: Thu, 13 Feb 2025 11:15:46 +0530
Subject: [PATCH 0179/1173] mtd: spi-nor: sst: Fix SST write failure
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

'commit 18bcb4aa54ea ("mtd: spi-nor: sst: Factor out common write operation
to `sst_nor_write_data()`")' introduced a bug where only one byte of data
is written, regardless of the number of bytes passed to
sst_nor_write_data(), causing a kernel crash during the write operation.
Ensure the correct number of bytes are written as passed to
sst_nor_write_data().

Call trace:
[   57.400180] ------------[ cut here ]------------
[   57.404842] While writing 2 byte written 1 bytes
[   57.409493] WARNING: CPU: 0 PID: 737 at drivers/mtd/spi-nor/sst.c:187 sst_nor_write_data+0x6c/0x74
[   57.418464] Modules linked in:
[   57.421517] CPU: 0 UID: 0 PID: 737 Comm: mtd_debug Not tainted 6.12.0-g5ad04afd91f9 #30
[   57.429517] Hardware name: Xilinx Versal A2197 Processor board revA - x-prc-02 revA (DT)
[   57.437600] pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[   57.444557] pc : sst_nor_write_data+0x6c/0x74
[   57.448911] lr : sst_nor_write_data+0x6c/0x74
[   57.453264] sp : ffff80008232bb40
[   57.456570] x29: ffff80008232bb40 x28: 0000000000010000 x27: 0000000000000001
[   57.463708] x26: 000000000000ffff x25: 0000000000000000 x24: 0000000000000000
[   57.470843] x23: 0000000000010000 x22: ffff80008232bbf0 x21: ffff000816230000
[   57.477978] x20: ffff0008056c0080 x19: 0000000000000002 x18: 0000000000000006
[   57.485112] x17: 0000000000000000 x16: 0000000000000000 x15: ffff80008232b580
[   57.492246] x14: 0000000000000000 x13: ffff8000816d1530 x12: 00000000000004a4
[   57.499380] x11: 000000000000018c x10: ffff8000816fd530 x9 : ffff8000816d1530
[   57.506515] x8 : 00000000fffff7ff x7 : ffff8000816fd530 x6 : 0000000000000001
[   57.513649] x5 : 0000000000000000 x4 : 0000000000000000 x3 : 0000000000000000
[   57.520782] x2 : 0000000000000000 x1 : 0000000000000000 x0 : ffff0008049b0000
[   57.527916] Call trace:
[   57.530354]  sst_nor_write_data+0x6c/0x74
[   57.534361]  sst_nor_write+0xb4/0x18c
[   57.538019]  mtd_write_oob_std+0x7c/0x88
[   57.541941]  mtd_write_oob+0x70/0xbc
[   57.545511]  mtd_write+0x68/0xa8
[   57.548733]  mtdchar_write+0x10c/0x290
[   57.552477]  vfs_write+0xb4/0x3a8
[   57.555791]  ksys_write+0x74/0x10c
[   57.559189]  __arm64_sys_write+0x1c/0x28
[   57.563109]  invoke_syscall+0x54/0x11c
[   57.566856]  el0_svc_common.constprop.0+0xc0/0xe0
[   57.571557]  do_el0_svc+0x1c/0x28
[   57.574868]  el0_svc+0x30/0xcc
[   57.577921]  el0t_64_sync_handler+0x120/0x12c
[   57.582276]  el0t_64_sync+0x190/0x194
[   57.585933] ---[ end trace 0000000000000000 ]---

Cc: stable@vger.kernel.org
Fixes: 18bcb4aa54ea ("mtd: spi-nor: sst: Factor out common write operation to `sst_nor_write_data()`")
Signed-off-by: Amit Kumar Mahapatra <amit.kumar-mahapatra@amd.com>
Reviewed-by: Pratyush Yadav <pratyush@kernel.org>
Reviewed-by: Tudor Ambarus <tudor.ambarus@linaro.org>
Reviewed-by: Bence Csókás <csokas.bence@prolan.hu>
[pratyush@kernel.org: add Cc stable tag]
Signed-off-by: Pratyush Yadav <pratyush@kernel.org>
Link: https://lore.kernel.org/r/20250213054546.2078121-1-amit.kumar-mahapatra@amd.com
---
 drivers/mtd/spi-nor/sst.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mtd/spi-nor/sst.c b/drivers/mtd/spi-nor/sst.c
index b5ad7118c49a2..175211fe6a5ed 100644
--- a/drivers/mtd/spi-nor/sst.c
+++ b/drivers/mtd/spi-nor/sst.c
@@ -174,7 +174,7 @@ static int sst_nor_write_data(struct spi_nor *nor, loff_t to, size_t len,
 	int ret;
 
 	nor->program_opcode = op;
-	ret = spi_nor_write_data(nor, to, 1, buf);
+	ret = spi_nor_write_data(nor, to, len, buf);
 	if (ret < 0)
 		return ret;
 	WARN(ret != len, "While writing %zu byte written %i bytes\n", len, ret);

From d20610c19b4a22bc69085b7eb7a02741d51de30e Mon Sep 17 00:00:00 2001
From: Ravi Bangoria <ravi.bangoria@amd.com>
Date: Wed, 5 Feb 2025 06:05:41 +0000
Subject: [PATCH 0180/1173] perf/amd/ibs: Add support for OP Load Latency
 Filtering

IBS Op PMU on Zen5 uarch added new Load Latency filtering capability. It's
advertised by CPUID_Fn8000001B_EAX bit 12. When enabled, IBS HW will raise
interrupt only for sample that had an IbsDcMissLat value greater than N
cycles, where N is a programmable value defined as multiples of 128 (i.e.
128, 256, 384 etc.) from 128-2048 cycles. Similar to L3MissOnly, IBS HW
internally drops the sample and restarts if the sample does not meet the
filtering criteria.

Add support for LdLat filtering in IBS Op PMU. Since hardware supports
threshold in multiple of 128, add a software filter on top to support
latency threshold with the granularity of 1 cycle between [128-2048].

Example usage:
  # perf record -a -e ibs_op/ldlat=128/ -- sleep 5

Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250205060547.1337-2-ravi.bangoria@amd.com
---
 arch/x86/events/amd/ibs.c         | 93 ++++++++++++++++++++++++++++---
 arch/x86/include/asm/amd-ibs.h    |  3 +-
 arch/x86/include/asm/perf_event.h |  3 +
 3 files changed, 90 insertions(+), 9 deletions(-)

diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 7978d7910adc3..85b29b3f305b2 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -268,6 +268,14 @@ static int validate_group(struct perf_event *event)
 	return 0;
 }
 
+static bool perf_ibs_ldlat_event(struct perf_ibs *perf_ibs,
+				 struct perf_event *event)
+{
+	return perf_ibs == &perf_ibs_op &&
+	       (ibs_caps & IBS_CAPS_OPLDLAT) &&
+	       (event->attr.config1 & 0xFFF);
+}
+
 static int perf_ibs_init(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
@@ -339,6 +347,17 @@ static int perf_ibs_init(struct perf_event *event)
 			return -EINVAL;
 	}
 
+	if (perf_ibs_ldlat_event(perf_ibs, event)) {
+		u64 ldlat = event->attr.config1 & 0xFFF;
+
+		if (ldlat < 128 || ldlat > 2048)
+			return -EINVAL;
+		ldlat >>= 7;
+
+		config |= (ldlat - 1) << 59;
+		config |= IBS_OP_L3MISSONLY | IBS_OP_LDLAT_EN;
+	}
+
 	/*
 	 * If we modify hwc->sample_period, we also need to update
 	 * hwc->last_period and hwc->period_left.
@@ -607,7 +626,9 @@ PMU_FORMAT_ATTR(cnt_ctl,	"config:19");
 PMU_FORMAT_ATTR(swfilt,		"config2:0");
 PMU_EVENT_ATTR_STRING(l3missonly, fetch_l3missonly, "config:59");
 PMU_EVENT_ATTR_STRING(l3missonly, op_l3missonly, "config:16");
+PMU_EVENT_ATTR_STRING(ldlat, ibs_op_ldlat_format, "config1:0-11");
 PMU_EVENT_ATTR_STRING(zen4_ibs_extensions, zen4_ibs_extensions, "1");
+PMU_EVENT_ATTR_STRING(ldlat, ibs_op_ldlat_cap, "1");
 
 static umode_t
 zen4_ibs_extensions_is_visible(struct kobject *kobj, struct attribute *attr, int i)
@@ -615,6 +636,12 @@ zen4_ibs_extensions_is_visible(struct kobject *kobj, struct attribute *attr, int
 	return ibs_caps & IBS_CAPS_ZEN4 ? attr->mode : 0;
 }
 
+static umode_t
+ibs_op_ldlat_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+	return ibs_caps & IBS_CAPS_OPLDLAT ? attr->mode : 0;
+}
+
 static struct attribute *fetch_attrs[] = {
 	&format_attr_rand_en.attr,
 	&format_attr_swfilt.attr,
@@ -631,6 +658,11 @@ static struct attribute *zen4_ibs_extensions_attrs[] = {
 	NULL,
 };
 
+static struct attribute *ibs_op_ldlat_cap_attrs[] = {
+	&ibs_op_ldlat_cap.attr.attr,
+	NULL,
+};
+
 static struct attribute_group group_fetch_formats = {
 	.name = "format",
 	.attrs = fetch_attrs,
@@ -648,6 +680,12 @@ static struct attribute_group group_zen4_ibs_extensions = {
 	.is_visible = zen4_ibs_extensions_is_visible,
 };
 
+static struct attribute_group group_ibs_op_ldlat_cap = {
+	.name = "caps",
+	.attrs = ibs_op_ldlat_cap_attrs,
+	.is_visible = ibs_op_ldlat_is_visible,
+};
+
 static const struct attribute_group *fetch_attr_groups[] = {
 	&group_fetch_formats,
 	&empty_caps_group,
@@ -686,6 +724,11 @@ static struct attribute_group group_op_formats = {
 	.attrs = op_attrs,
 };
 
+static struct attribute *ibs_op_ldlat_format_attrs[] = {
+	&ibs_op_ldlat_format.attr.attr,
+	NULL,
+};
+
 static struct attribute_group group_cnt_ctl = {
 	.name = "format",
 	.attrs = cnt_ctl_attrs,
@@ -704,10 +747,18 @@ static const struct attribute_group *op_attr_groups[] = {
 	NULL,
 };
 
+static struct attribute_group group_ibs_op_ldlat_format = {
+	.name = "format",
+	.attrs = ibs_op_ldlat_format_attrs,
+	.is_visible = ibs_op_ldlat_is_visible,
+};
+
 static const struct attribute_group *op_attr_update[] = {
 	&group_cnt_ctl,
 	&group_op_l3missonly,
 	&group_zen4_ibs_extensions,
+	&group_ibs_op_ldlat_cap,
+	&group_ibs_op_ldlat_format,
 	NULL,
 };
 
@@ -1060,15 +1111,25 @@ static void perf_ibs_parse_ld_st_data(__u64 sample_type,
 	}
 }
 
-static int perf_ibs_get_offset_max(struct perf_ibs *perf_ibs, u64 sample_type,
+static bool perf_ibs_is_mem_sample_type(struct perf_ibs *perf_ibs,
+					struct perf_event *event)
+{
+	u64 sample_type = event->attr.sample_type;
+
+	return perf_ibs == &perf_ibs_op &&
+	       sample_type & (PERF_SAMPLE_DATA_SRC |
+			      PERF_SAMPLE_WEIGHT_TYPE |
+			      PERF_SAMPLE_ADDR |
+			      PERF_SAMPLE_PHYS_ADDR);
+}
+
+static int perf_ibs_get_offset_max(struct perf_ibs *perf_ibs,
+				   struct perf_event *event,
 				   int check_rip)
 {
-	if (sample_type & PERF_SAMPLE_RAW ||
-	    (perf_ibs == &perf_ibs_op &&
-	     (sample_type & PERF_SAMPLE_DATA_SRC ||
-	      sample_type & PERF_SAMPLE_WEIGHT_TYPE ||
-	      sample_type & PERF_SAMPLE_ADDR ||
-	      sample_type & PERF_SAMPLE_PHYS_ADDR)))
+	if (event->attr.sample_type & PERF_SAMPLE_RAW ||
+	    perf_ibs_is_mem_sample_type(perf_ibs, event) ||
+	    perf_ibs_ldlat_event(perf_ibs, event))
 		return perf_ibs->offset_max;
 	else if (check_rip)
 		return 3;
@@ -1123,7 +1184,7 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
 	offset = 1;
 	check_rip = (perf_ibs == &perf_ibs_op && (ibs_caps & IBS_CAPS_RIPINVALIDCHK));
 
-	offset_max = perf_ibs_get_offset_max(perf_ibs, event->attr.sample_type, check_rip);
+	offset_max = perf_ibs_get_offset_max(perf_ibs, event, check_rip);
 
 	do {
 		rdmsrl(msr + offset, *buf++);
@@ -1132,6 +1193,22 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
 				       perf_ibs->offset_max,
 				       offset + 1);
 	} while (offset < offset_max);
+
+	if (perf_ibs_ldlat_event(perf_ibs, event)) {
+		union ibs_op_data3 op_data3;
+
+		op_data3.val = ibs_data.regs[ibs_op_msr_idx(MSR_AMD64_IBSOPDATA3)];
+		/*
+		 * Opening event is errored out if load latency threshold is
+		 * outside of [128, 2048] range. Since the event has reached
+		 * interrupt handler, we can safely assume the threshold is
+		 * within [128, 2048] range.
+		 */
+		if (!op_data3.ld_op || !op_data3.dc_miss ||
+		    op_data3.dc_miss_lat <= (event->attr.config1 & 0xFFF))
+			goto out;
+	}
+
 	/*
 	 * Read IbsBrTarget, IbsOpData4, and IbsExtdCtl separately
 	 * depending on their availability.
diff --git a/arch/x86/include/asm/amd-ibs.h b/arch/x86/include/asm/amd-ibs.h
index cb2a5e113daa7..77f3a589a99ac 100644
--- a/arch/x86/include/asm/amd-ibs.h
+++ b/arch/x86/include/asm/amd-ibs.h
@@ -64,7 +64,8 @@ union ibs_op_ctl {
 			opmaxcnt_ext:7,	/* 20-26: upper 7 bits of periodic op maximum count */
 			reserved0:5,	/* 27-31: reserved */
 			opcurcnt:27,	/* 32-58: periodic op counter current count */
-			reserved1:5;	/* 59-63: reserved */
+			ldlat_thrsh:4,	/* 59-62: Load Latency threshold */
+			ldlat_en:1;	/* 63: Load Latency enabled */
 	};
 };
 
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 73b104049f8cf..a60efe47498de 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -502,6 +502,7 @@ struct pebs_cntr_header {
 #define IBS_CAPS_FETCHCTLEXTD		(1U<<9)
 #define IBS_CAPS_OPDATA4		(1U<<10)
 #define IBS_CAPS_ZEN4			(1U<<11)
+#define IBS_CAPS_OPLDLAT		(1U<<12)
 
 #define IBS_CAPS_DEFAULT		(IBS_CAPS_AVAIL		\
 					 | IBS_CAPS_FETCHSAM	\
@@ -527,6 +528,8 @@ struct pebs_cntr_header {
  * The lower 7 bits of the current count are random bits
  * preloaded by hardware and ignored in software
  */
+#define IBS_OP_LDLAT_EN		(1ULL<<63)
+#define IBS_OP_LDLAT_THRSH	(0xFULL<<59)
 #define IBS_OP_CUR_CNT		(0xFFF80ULL<<32)
 #define IBS_OP_CUR_CNT_RAND	(0x0007FULL<<32)
 #define IBS_OP_CUR_CNT_EXT_MASK	(0x7FULL<<52)

From 0b347a4218da08b1eb400c259d193bff463dae87 Mon Sep 17 00:00:00 2001
From: Ravi Bangoria <ravi.bangoria@amd.com>
Date: Wed, 5 Feb 2025 06:05:42 +0000
Subject: [PATCH 0181/1173] perf/amd/ibs: Update DTLB/PageSize decode logic

IBS Op PMU on Zen5 reports DTLB and page size information differently
compared to prior generation. The change is enumerated by
CPUID_Fn8000001B_EAX[19].

  IBS_OP_DATA3     Zen3/4                 Zen5
  ----------------------------------------------------------------
  19               IbsDcL2TlbHit1G        Reserved
  ----------------------------------------------------------------
   6               IbsDcL2tlbHit2M        Reserved
  ----------------------------------------------------------------
   5               IbsDcL1TlbHit1G        PageSize:
   4               IbsDcL1TlbHit2M          0 - 4K
                                            1 - 2M
                                            2 - 1G
                                            3 - Reserved
                                          Valid only if
                                            IbsDcPhyAddrValid = 1
  ----------------------------------------------------------------
   3               IbsDcL2TlbMiss         IbsDcL2TlbMiss
                                          Valid only if
                                            IbsDcPhyAddrValid = 1
  ----------------------------------------------------------------
   2               IbsDcL1tlbMiss         IbsDcL1tlbMiss
                                          Valid only if
                                            IbsDcPhyAddrValid = 1
  ----------------------------------------------------------------

o Currently, only bit 2 and 3 are interpreted by IBS NMI handler for
  PERF_SAMPLE_DATA_SRC. Add dependency on IbsDcPhyAddrValid for those
  bits.

o Introduce new IBS Op PMU capability and expose it to userspace via
  PMU's sysfs directory.

Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250205060547.1337-3-ravi.bangoria@amd.com
---
 arch/x86/events/amd/ibs.c         | 23 +++++++++++++++++++++++
 arch/x86/include/asm/perf_event.h |  1 +
 2 files changed, 24 insertions(+)

diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 85b29b3f305b2..7b52b8e3a1851 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -629,6 +629,7 @@ PMU_EVENT_ATTR_STRING(l3missonly, op_l3missonly, "config:16");
 PMU_EVENT_ATTR_STRING(ldlat, ibs_op_ldlat_format, "config1:0-11");
 PMU_EVENT_ATTR_STRING(zen4_ibs_extensions, zen4_ibs_extensions, "1");
 PMU_EVENT_ATTR_STRING(ldlat, ibs_op_ldlat_cap, "1");
+PMU_EVENT_ATTR_STRING(dtlb_pgsize, ibs_op_dtlb_pgsize_cap, "1");
 
 static umode_t
 zen4_ibs_extensions_is_visible(struct kobject *kobj, struct attribute *attr, int i)
@@ -642,6 +643,12 @@ ibs_op_ldlat_is_visible(struct kobject *kobj, struct attribute *attr, int i)
 	return ibs_caps & IBS_CAPS_OPLDLAT ? attr->mode : 0;
 }
 
+static umode_t
+ibs_op_dtlb_pgsize_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+	return ibs_caps & IBS_CAPS_OPDTLBPGSIZE ? attr->mode : 0;
+}
+
 static struct attribute *fetch_attrs[] = {
 	&format_attr_rand_en.attr,
 	&format_attr_swfilt.attr,
@@ -663,6 +670,11 @@ static struct attribute *ibs_op_ldlat_cap_attrs[] = {
 	NULL,
 };
 
+static struct attribute *ibs_op_dtlb_pgsize_cap_attrs[] = {
+	&ibs_op_dtlb_pgsize_cap.attr.attr,
+	NULL,
+};
+
 static struct attribute_group group_fetch_formats = {
 	.name = "format",
 	.attrs = fetch_attrs,
@@ -686,6 +698,12 @@ static struct attribute_group group_ibs_op_ldlat_cap = {
 	.is_visible = ibs_op_ldlat_is_visible,
 };
 
+static struct attribute_group group_ibs_op_dtlb_pgsize_cap = {
+	.name = "caps",
+	.attrs = ibs_op_dtlb_pgsize_cap_attrs,
+	.is_visible = ibs_op_dtlb_pgsize_is_visible,
+};
+
 static const struct attribute_group *fetch_attr_groups[] = {
 	&group_fetch_formats,
 	&empty_caps_group,
@@ -759,6 +777,7 @@ static const struct attribute_group *op_attr_update[] = {
 	&group_zen4_ibs_extensions,
 	&group_ibs_op_ldlat_cap,
 	&group_ibs_op_ldlat_format,
+	&group_ibs_op_dtlb_pgsize_cap,
 	NULL,
 };
 
@@ -1007,6 +1026,10 @@ static void perf_ibs_get_tlb_lvl(union ibs_op_data3 *op_data3,
 	if (!op_data3->dc_lin_addr_valid)
 		return;
 
+	if ((ibs_caps & IBS_CAPS_OPDTLBPGSIZE) &&
+	    !op_data3->dc_phy_addr_valid)
+		return;
+
 	if (!op_data3->dc_l1tlb_miss) {
 		data_src->mem_dtlb = PERF_MEM_TLB_L1 | PERF_MEM_TLB_HIT;
 		return;
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index a60efe47498de..43b17b7b6ac07 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -503,6 +503,7 @@ struct pebs_cntr_header {
 #define IBS_CAPS_OPDATA4		(1U<<10)
 #define IBS_CAPS_ZEN4			(1U<<11)
 #define IBS_CAPS_OPLDLAT		(1U<<12)
+#define IBS_CAPS_OPDTLBPGSIZE		(1U<<19)
 
 #define IBS_CAPS_DEFAULT		(IBS_CAPS_AVAIL		\
 					 | IBS_CAPS_FETCHSAM	\

From 3201bfa368fee5e70927e45222ff0b235352c01c Mon Sep 17 00:00:00 2001
From: Ravi Bangoria <ravi.bangoria@amd.com>
Date: Wed, 5 Feb 2025 06:05:43 +0000
Subject: [PATCH 0182/1173] perf amd ibs: Sync arch/x86/include/asm/amd-ibs.h
 header with the kernel

Sync load latency related bit fields into the tool's header copy

Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250205060547.1337-4-ravi.bangoria@amd.com
---
 tools/arch/x86/include/asm/amd-ibs.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/arch/x86/include/asm/amd-ibs.h b/tools/arch/x86/include/asm/amd-ibs.h
index 93807b437e4de..cb1740bc3da2d 100644
--- a/tools/arch/x86/include/asm/amd-ibs.h
+++ b/tools/arch/x86/include/asm/amd-ibs.h
@@ -64,7 +64,8 @@ union ibs_op_ctl {
 			opmaxcnt_ext:7,	/* 20-26: upper 7 bits of periodic op maximum count */
 			reserved0:5,	/* 27-31: reserved */
 			opcurcnt:27,	/* 32-58: periodic op counter current count */
-			reserved1:5;	/* 59-63: reserved */
+			ldlat_thrsh:4,	/* 59-62: Load Latency threshold */
+			ldlat_en:1;	/* 63: Load Latency enabled */
 	};
 };
 

From e49477f7f78598295551d486ecc7f020d796432e Mon Sep 17 00:00:00 2001
From: Krzysztof Karas <krzysztof.karas@intel.com>
Date: Thu, 16 Jan 2025 10:40:46 +0000
Subject: [PATCH 0183/1173] drm/i915/gt: Use spin_lock_irqsave() in
 interruptible context

spin_lock/unlock() functions used in interrupt contexts could
result in a deadlock, as seen in GitLab issue #13399,
which occurs when interrupt comes in while holding a lock.

Try to remedy the problem by saving irq state before spin lock
acquisition.

v2: add irqs' state save/restore calls to all locks/unlocks in
 signal_irq_work() execution (Maciej)

v3: use with spin_lock_irqsave() in guc_lrc_desc_unpin() instead
 of other lock/unlock calls and add Fixes and Cc tags (Tvrtko);
 change title and commit message

Fixes: 2f2cc53b5fe7 ("drm/i915/guc: Close deregister-context race against CT-loss")
Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/13399
Signed-off-by: Krzysztof Karas <krzysztof.karas@intel.com>
Cc: <stable@vger.kernel.org> # v6.9+
Reviewed-by: Maciej Patelczyk <maciej.patelczyk@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/pusppq5ybyszau2oocboj3mtj5x574gwij323jlclm5zxvimmu@mnfg6odxbpsv
(cherry picked from commit c088387ddd6482b40f21ccf23db1125e8fa4af7e)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index cc05bd9e43b49..3fce5c0001444 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -3449,10 +3449,10 @@ static inline int guc_lrc_desc_unpin(struct intel_context *ce)
 	 */
 	ret = deregister_context(ce, ce->guc_id.id);
 	if (ret) {
-		spin_lock(&ce->guc_state.lock);
+		spin_lock_irqsave(&ce->guc_state.lock, flags);
 		set_context_registered(ce);
 		clr_context_destroyed(ce);
-		spin_unlock(&ce->guc_state.lock);
+		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
 		/*
 		 * As gt-pm is awake at function entry, intel_wakeref_put_async merely decrements
 		 * the wakeref immediately but per function spec usage call this after unlock.

From 0c455f3a12298e9c89a78d2f3327e15e52c0adc5 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Thu, 13 Feb 2025 11:28:59 -0800
Subject: [PATCH 0184/1173] drm/xe: Fix error handling in xe_irq_install()

When devm_add_action_or_reset() fails, it already calls the function
passed as parameter and that function is already free'ing the irqs.
Drop the goto and just return.

The caller, xe_device_probe(), should also do the same thing instead of
wrongly doing `goto err` and calling the unrelated xe_display_fini()
function.

Fixes: 14d25d8d684d ("drm/xe: change old msi irq api to a new one")
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250213192909.996148-3-lucas.demarchi@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit 121b214cdf10d4129b64f2b1f31807154c74ae55)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_irq.c | 14 +-------------
 1 file changed, 1 insertion(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_irq.c b/drivers/gpu/drm/xe/xe_irq.c
index 32f5a67a917b5..08552ee3fb94b 100644
--- a/drivers/gpu/drm/xe/xe_irq.c
+++ b/drivers/gpu/drm/xe/xe_irq.c
@@ -757,19 +757,7 @@ int xe_irq_install(struct xe_device *xe)
 
 	xe_irq_postinstall(xe);
 
-	err = devm_add_action_or_reset(xe->drm.dev, irq_uninstall, xe);
-	if (err)
-		goto free_irq_handler;
-
-	return 0;
-
-free_irq_handler:
-	if (xe_device_has_msix(xe))
-		xe_irq_msix_free(xe);
-	else
-		xe_irq_msi_free(xe);
-
-	return err;
+	return devm_add_action_or_reset(xe->drm.dev, irq_uninstall, xe);
 }
 
 static void xe_irq_msi_synchronize_irq(struct xe_device *xe)

From 879f70382ff3e92fc854589ada3453e3f5f5b601 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Fri, 14 Feb 2025 16:19:51 +0200
Subject: [PATCH 0185/1173] drm/i915/dsi: Use TRANS_DDI_FUNC_CTL's own port
 width macro

The format of the port width field in the DDI_BUF_CTL and the
TRANS_DDI_FUNC_CTL registers are different starting with MTL, where the
x3 lane mode for HDMI FRL has a different encoding in the two registers.
To account for this use the TRANS_DDI_FUNC_CTL's own port width macro.

Cc: <stable@vger.kernel.org> # v6.5+
Fixes: b66a8abaa48a ("drm/i915/display/mtl: Fill port width in DDI_BUF_/TRANS_DDI_FUNC_/PORT_BUF_CTL for HDMI")
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250214142001.552916-2-imre.deak@intel.com
(cherry picked from commit 76120b3a304aec28fef4910204b81a12db8974da)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/display/icl_dsi.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c
index c977b74f82f0b..82bf6c654de25 100644
--- a/drivers/gpu/drm/i915/display/icl_dsi.c
+++ b/drivers/gpu/drm/i915/display/icl_dsi.c
@@ -809,8 +809,8 @@ gen11_dsi_configure_transcoder(struct intel_encoder *encoder,
 		/* select data lane width */
 		tmp = intel_de_read(display,
 				    TRANS_DDI_FUNC_CTL(display, dsi_trans));
-		tmp &= ~DDI_PORT_WIDTH_MASK;
-		tmp |= DDI_PORT_WIDTH(intel_dsi->lane_count);
+		tmp &= ~TRANS_DDI_PORT_WIDTH_MASK;
+		tmp |= TRANS_DDI_PORT_WIDTH(intel_dsi->lane_count);
 
 		/* select input pipe */
 		tmp &= ~TRANS_DDI_EDP_INPUT_MASK;

From 166ce267ae3f96e439d8ccc838e8ec4d8b4dab73 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Fri, 14 Feb 2025 16:19:52 +0200
Subject: [PATCH 0186/1173] drm/i915/ddi: Fix HDMI port width programming in
 DDI_BUF_CTL

Fix the port width programming in the DDI_BUF_CTL register on MTLP+,
where this had an off-by-one error.

Cc: <stable@vger.kernel.org> # v6.5+
Fixes: b66a8abaa48a ("drm/i915/display/mtl: Fill port width in DDI_BUF_/TRANS_DDI_FUNC_/PORT_BUF_CTL for HDMI")
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250214142001.552916-3-imre.deak@intel.com
(cherry picked from commit b2ecdabe46d23db275f94cd7c46ca414a144818b)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/display/intel_ddi.c | 2 +-
 drivers/gpu/drm/i915/i915_reg.h          | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index acb986bc1f33a..2b9240ab547d8 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -3487,7 +3487,7 @@ static void intel_ddi_enable_hdmi(struct intel_atomic_state *state,
 		intel_de_rmw(dev_priv, XELPDP_PORT_BUF_CTL1(dev_priv, port),
 			     XELPDP_PORT_WIDTH_MASK | XELPDP_PORT_REVERSAL, port_buf);
 
-		buf_ctl |= DDI_PORT_WIDTH(lane_count);
+		buf_ctl |= DDI_PORT_WIDTH(crtc_state->lane_count);
 
 		if (DISPLAY_VER(dev_priv) >= 20)
 			buf_ctl |= XE2LPD_DDI_BUF_D2D_LINK_ENABLE;
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 765e6c0528fb0..786c727aea454 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -3633,7 +3633,7 @@ enum skl_power_gate {
 #define  DDI_BUF_IS_IDLE			(1 << 7)
 #define  DDI_BUF_CTL_TC_PHY_OWNERSHIP		REG_BIT(6)
 #define  DDI_A_4_LANES				(1 << 4)
-#define  DDI_PORT_WIDTH(width)			(((width) - 1) << 1)
+#define  DDI_PORT_WIDTH(width)			(((width) == 3 ? 4 : ((width) - 1)) << 1)
 #define  DDI_PORT_WIDTH_MASK			(7 << 1)
 #define  DDI_PORT_WIDTH_SHIFT			1
 #define  DDI_INIT_DISPLAY_DETECTED		(1 << 0)

From 07fb70d82e0df085980246bf17bc12537588795f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Wed, 12 Feb 2025 18:43:21 +0200
Subject: [PATCH 0187/1173] drm/i915: Make sure all planes in use by the joiner
 have their crtc included
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Any active plane needs to have its crtc included in the atomic
state. For planes enabled via uapi that is all handler in the core.
But when we use a plane for joiner the uapi code things the plane
is disabled and therefore doesn't have a crtc. So we need to pull
those in by hand. We do it first thing in
intel_joiner_add_affected_crtcs() so that any newly added crtc will
subsequently pull in all of its joined crtcs as well.

The symptoms from failing to do this are:
- duct tape in the form of commit 1d5b09f8daf8 ("drm/i915: Fix NULL
  ptr deref by checking new_crtc_state")
- the plane's hw state will get overwritten by the disabled
  uapi state if it can't find the uapi counterpart plane in
  the atomic state from where it should copy the correct state

Cc: stable@vger.kernel.org
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250212164330.16891-2-ville.syrjala@linux.intel.com
(cherry picked from commit 91077d1deb5374eb8be00fb391710f00e751dc4b)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/display/intel_display.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 4271da219b410..41128469f12a2 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -6628,12 +6628,30 @@ static int intel_async_flip_check_hw(struct intel_atomic_state *state, struct in
 static int intel_joiner_add_affected_crtcs(struct intel_atomic_state *state)
 {
 	struct drm_i915_private *i915 = to_i915(state->base.dev);
+	const struct intel_plane_state *plane_state;
 	struct intel_crtc_state *crtc_state;
+	struct intel_plane *plane;
 	struct intel_crtc *crtc;
 	u8 affected_pipes = 0;
 	u8 modeset_pipes = 0;
 	int i;
 
+	/*
+	 * Any plane which is in use by the joiner needs its crtc.
+	 * Pull those in first as this will not have happened yet
+	 * if the plane remains disabled according to uapi.
+	 */
+	for_each_new_intel_plane_in_state(state, plane, plane_state, i) {
+		crtc = to_intel_crtc(plane_state->hw.crtc);
+		if (!crtc)
+			continue;
+
+		crtc_state = intel_atomic_get_crtc_state(&state->base, crtc);
+		if (IS_ERR(crtc_state))
+			return PTR_ERR(crtc_state);
+	}
+
+	/* Now pull in all joined crtcs */
 	for_each_new_intel_crtc_in_state(state, crtc, crtc_state, i) {
 		affected_pipes |= crtc_state->joiner_pipes;
 		if (intel_crtc_needs_modeset(crtc_state))

From dd8b0582e25e36bba483c60338741c0ba5bc426c Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Mon, 17 Feb 2025 11:16:26 +0800
Subject: [PATCH 0188/1173] block: fix NULL pointer dereferenced within
 __blk_rq_map_sg

The block layer internal flush request may not have bio attached, so the
request iterator has to be initialized from valid req->bio, otherwise NULL
pointer dereferenced is triggered.

Cc: Christoph Hellwig <hch@lst.de>
Reported-and-tested-by: Cheyenne Wills <cheyenne.wills@gmail.com>
Fixes: b7175e24d6ac ("block: add a dma mapping iterator")
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20250217031626.461977-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-merge.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/block/blk-merge.c b/block/blk-merge.c
index 39b738c0e4c9a..c7c85e10cf9cb 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -556,11 +556,14 @@ int __blk_rq_map_sg(struct request_queue *q, struct request *rq,
 {
 	struct req_iterator iter = {
 		.bio	= rq->bio,
-		.iter	= rq->bio->bi_iter,
 	};
 	struct phys_vec vec;
 	int nsegs = 0;
 
+	/* the internal flush request may not have bio attached */
+	if (iter.bio)
+		iter.iter = iter.bio->bi_iter;
+
 	while (blk_map_iter_next(rq, &iter, &vec)) {
 		*last_sg = blk_next_sg(last_sg, sglist);
 		sg_set_page(*last_sg, phys_to_page(vec.paddr), vec.len,

From 290237fde9491ca26cf4020bbf5a2b330452e7db Mon Sep 17 00:00:00 2001
From: David Disseldorp <ddiss@suse.de>
Date: Mon, 10 Feb 2025 22:17:29 +1100
Subject: [PATCH 0189/1173] btrfs: selftests: fix btrfs_test_delayed_refs()
 leak of transaction

The btrfs_transaction struct leaks, which can cause sporadic fstests
failures when kmemleak checking is enabled:

kmemleak: 5 new suspected memory leaks (see /sys/kernel/debug/kmemleak)
> cat /sys/kernel/debug/kmemleak
unreferenced object 0xffff88810fdc6c00 (size 512):
  comm "modprobe", pid 203, jiffies 4294892552
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace (crc 6736050f):
    __kmalloc_cache_noprof+0x133/0x2c0
    btrfs_test_delayed_refs+0x6f/0xbb0 [btrfs]
    btrfs_run_sanity_tests.cold+0x91/0xf9 [btrfs]
    0xffffffffa02fd055
    do_one_initcall+0x49/0x1c0
    do_init_module+0x5b/0x1f0
    init_module_from_file+0x70/0x90
    idempotent_init_module+0xe8/0x2c0
    __x64_sys_finit_module+0x6b/0xd0
    do_syscall_64+0x54/0x110
    entry_SYSCALL_64_after_hwframe+0x76/0x7e

The transaction struct was initially stack-allocated but switched to
heap following frame size compiler warnings.

Fixes: 2b34879d97e27 ("btrfs: selftests: add delayed ref self test cases")
Signed-off-by: David Disseldorp <ddiss@suse.de>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/tests/delayed-refs-tests.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/btrfs/tests/delayed-refs-tests.c b/fs/btrfs/tests/delayed-refs-tests.c
index 6558508c2ddf5..265370e79a546 100644
--- a/fs/btrfs/tests/delayed-refs-tests.c
+++ b/fs/btrfs/tests/delayed-refs-tests.c
@@ -1009,6 +1009,7 @@ int btrfs_test_delayed_refs(u32 sectorsize, u32 nodesize)
 	if (!ret)
 		ret = select_delayed_refs_test(&trans);
 
+	kfree(transaction);
 out_free_fs_info:
 	btrfs_free_dummy_fs_info(fs_info);
 	return ret;

From 4cb77793842a351b39a030f77caebace3524840e Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sat, 15 Feb 2025 18:52:41 +0000
Subject: [PATCH 0190/1173] irqchip/gic-v3: Fix rk3399 workaround when secure
 interrupts are enabled

Christoph reports that their rk3399 system dies since commit 773c05f417fa1
("irqchip/gic-v3: Work around insecure GIC integrations").

It appears that some rk3399 have secure payloads, and that the firmware
sets SCR_EL3.FIQ==1. Obivously, disabling security in that configuration
leads to even more problems.

Revisit the workaround by:

  - making it rk3399 specific
  - checking whether Group-0 is available, which is a good proxy
    for SCR_EL3.FIQ being 0
  - either apply the workaround if Group-0 is available, or disable
    pseudo-NMIs if not

Note that this doesn't mean that the secure side is able to receive
interrupts, as all interrupts are made non-secure anyway.

Clearly, nobody ever tested secure interrupts on this platform.

Fixes: 773c05f417fa1 ("irqchip/gic-v3: Work around insecure GIC integrations")
Reported-by: Christoph Fritz <chf.fritz@googlemail.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Christoph Fritz <chf.fritz@googlemail.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/all/20250215185241.3768218-1-maz@kernel.org
Closes: https://lore.kernel.org/r/b1266652fb64857246e8babdf268d0df8f0c36d9.camel@googlemail.com
---
 drivers/irqchip/irq-gic-v3.c | 53 +++++++++++++++++++++++++++---------
 1 file changed, 40 insertions(+), 13 deletions(-)

diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 76dce0aac2465..270d7a4d85a6d 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -44,6 +44,7 @@ static u8 dist_prio_nmi __ro_after_init = GICV3_PRIO_NMI;
 #define FLAGS_WORKAROUND_GICR_WAKER_MSM8996	(1ULL << 0)
 #define FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539	(1ULL << 1)
 #define FLAGS_WORKAROUND_ASR_ERRATUM_8601001	(1ULL << 2)
+#define FLAGS_WORKAROUND_INSECURE		(1ULL << 3)
 
 #define GIC_IRQ_TYPE_PARTITION	(GIC_IRQ_TYPE_LPI + 1)
 
@@ -83,6 +84,8 @@ static DEFINE_STATIC_KEY_TRUE(supports_deactivate_key);
 #define GIC_LINE_NR	min(GICD_TYPER_SPIS(gic_data.rdists.gicd_typer), 1020U)
 #define GIC_ESPI_NR	GICD_TYPER_ESPIS(gic_data.rdists.gicd_typer)
 
+static bool nmi_support_forbidden;
+
 /*
  * There are 16 SGIs, though we only actually use 8 in Linux. The other 8 SGIs
  * are potentially stolen by the secure side. Some code, especially code dealing
@@ -163,21 +166,27 @@ static void __init gic_prio_init(void)
 {
 	bool ds;
 
-	ds = gic_dist_security_disabled();
-	if (!ds) {
-		u32 val;
-
-		val = readl_relaxed(gic_data.dist_base + GICD_CTLR);
-		val |= GICD_CTLR_DS;
-		writel_relaxed(val, gic_data.dist_base + GICD_CTLR);
+	cpus_have_group0 = gic_has_group0();
 
-		ds = gic_dist_security_disabled();
-		if (ds)
-			pr_warn("Broken GIC integration, security disabled");
+	ds = gic_dist_security_disabled();
+	if ((gic_data.flags & FLAGS_WORKAROUND_INSECURE) && !ds) {
+		if (cpus_have_group0) {
+			u32 val;
+
+			val = readl_relaxed(gic_data.dist_base + GICD_CTLR);
+			val |= GICD_CTLR_DS;
+			writel_relaxed(val, gic_data.dist_base + GICD_CTLR);
+
+			ds = gic_dist_security_disabled();
+			if (ds)
+				pr_warn("Broken GIC integration, security disabled\n");
+		} else {
+			pr_warn("Broken GIC integration, pNMI forbidden\n");
+			nmi_support_forbidden = true;
+		}
 	}
 
 	cpus_have_security_disabled = ds;
-	cpus_have_group0 = gic_has_group0();
 
 	/*
 	 * How priority values are used by the GIC depends on two things:
@@ -209,7 +218,7 @@ static void __init gic_prio_init(void)
 	 * be in the non-secure range, we program the non-secure values into
 	 * the distributor to match the PMR values we want.
 	 */
-	if (cpus_have_group0 & !cpus_have_security_disabled) {
+	if (cpus_have_group0 && !cpus_have_security_disabled) {
 		dist_prio_irq = __gicv3_prio_to_ns(dist_prio_irq);
 		dist_prio_nmi = __gicv3_prio_to_ns(dist_prio_nmi);
 	}
@@ -1922,6 +1931,18 @@ static bool gic_enable_quirk_arm64_2941627(void *data)
 	return true;
 }
 
+static bool gic_enable_quirk_rk3399(void *data)
+{
+	struct gic_chip_data *d = data;
+
+	if (of_machine_is_compatible("rockchip,rk3399")) {
+		d->flags |= FLAGS_WORKAROUND_INSECURE;
+		return true;
+	}
+
+	return false;
+}
+
 static bool rd_set_non_coherent(void *data)
 {
 	struct gic_chip_data *d = data;
@@ -1996,6 +2017,12 @@ static const struct gic_quirk gic_quirks[] = {
 		.property = "dma-noncoherent",
 		.init   = rd_set_non_coherent,
 	},
+	{
+		.desc	= "GICv3: Insecure RK3399 integration",
+		.iidr	= 0x0000043b,
+		.mask	= 0xff000fff,
+		.init	= gic_enable_quirk_rk3399,
+	},
 	{
 	}
 };
@@ -2004,7 +2031,7 @@ static void gic_enable_nmi_support(void)
 {
 	int i;
 
-	if (!gic_prio_masking_enabled())
+	if (!gic_prio_masking_enabled() || nmi_support_forbidden)
 		return;
 
 	rdist_nmi_refs = kcalloc(gic_data.ppi_nr + SGI_NR,

From d7e3fd658248f257006227285095d190e70ee73a Mon Sep 17 00:00:00 2001
From: Artur Rojek <contact@artur-rojek.eu>
Date: Sun, 16 Feb 2025 18:55:45 +0100
Subject: [PATCH 0191/1173] irqchip/jcore-aic, clocksource/drivers/jcore: Fix
 jcore-pit interrupt request

The jcore-aic irqchip does not have separate interrupt numbers reserved for
cpu-local vs global interrupts. Therefore the device drivers need to
request the given interrupt as per CPU interrupt.

69a9dcbd2d65 ("clocksource/drivers/jcore: Use request_percpu_irq()")
converted the clocksource driver over to request_percpu_irq(), but failed
to do add all the required changes, resulting in a failure to register PIT
interrupts.

Fix this by:

 1) Explicitly mark the interrupt via irq_set_percpu_devid() in
    jcore_pit_init().

 2) Enable and disable the per CPU interrupt in the CPU hotplug callbacks.

 3) Pass the correct per-cpu cookie to the irq handler by using
    handle_percpu_devid_irq() instead of handle_percpu_irq() in
    handle_jcore_irq().

[ tglx: Massage change log ]

Fixes: 69a9dcbd2d65 ("clocksource/drivers/jcore: Use request_percpu_irq()")
Signed-off-by: Artur Rojek <contact@artur-rojek.eu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Uros Bizjak <ubizjak@gmail.com>
Link: https://lore.kernel.org/all/20250216175545.35079-3-contact@artur-rojek.eu
---
 drivers/clocksource/jcore-pit.c | 15 ++++++++++++++-
 drivers/irqchip/irq-jcore-aic.c |  2 +-
 2 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/drivers/clocksource/jcore-pit.c b/drivers/clocksource/jcore-pit.c
index a3fe98cd38382..82815428f8f92 100644
--- a/drivers/clocksource/jcore-pit.c
+++ b/drivers/clocksource/jcore-pit.c
@@ -114,6 +114,18 @@ static int jcore_pit_local_init(unsigned cpu)
 	pit->periodic_delta = DIV_ROUND_CLOSEST(NSEC_PER_SEC, HZ * buspd);
 
 	clockevents_config_and_register(&pit->ced, freq, 1, ULONG_MAX);
+	enable_percpu_irq(pit->ced.irq, IRQ_TYPE_NONE);
+
+	return 0;
+}
+
+static int jcore_pit_local_teardown(unsigned cpu)
+{
+	struct jcore_pit *pit = this_cpu_ptr(jcore_pit_percpu);
+
+	pr_info("Local J-Core PIT teardown on cpu %u\n", cpu);
+
+	disable_percpu_irq(pit->ced.irq);
 
 	return 0;
 }
@@ -168,6 +180,7 @@ static int __init jcore_pit_init(struct device_node *node)
 		return -ENOMEM;
 	}
 
+	irq_set_percpu_devid(pit_irq);
 	err = request_percpu_irq(pit_irq, jcore_timer_interrupt,
 				 "jcore_pit", jcore_pit_percpu);
 	if (err) {
@@ -237,7 +250,7 @@ static int __init jcore_pit_init(struct device_node *node)
 
 	cpuhp_setup_state(CPUHP_AP_JCORE_TIMER_STARTING,
 			  "clockevents/jcore:starting",
-			  jcore_pit_local_init, NULL);
+			  jcore_pit_local_init, jcore_pit_local_teardown);
 
 	return 0;
 }
diff --git a/drivers/irqchip/irq-jcore-aic.c b/drivers/irqchip/irq-jcore-aic.c
index b9dcc8e78c750..1f613eb7b7f03 100644
--- a/drivers/irqchip/irq-jcore-aic.c
+++ b/drivers/irqchip/irq-jcore-aic.c
@@ -38,7 +38,7 @@ static struct irq_chip jcore_aic;
 static void handle_jcore_irq(struct irq_desc *desc)
 {
 	if (irqd_is_per_cpu(irq_desc_get_irq_data(desc)))
-		handle_percpu_irq(desc);
+		handle_percpu_devid_irq(desc);
 	else
 		handle_simple_irq(desc);
 }

From 02d954c0fdf91845169cdacc7405b120f90afe01 Mon Sep 17 00:00:00 2001
From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Date: Mon, 10 Feb 2025 16:32:50 +0100
Subject: [PATCH 0192/1173] sched: Compact RSEQ concurrency IDs with reduced
 threads and affinity

When a process reduces its number of threads or clears bits in its CPU
affinity mask, the mm_cid allocation should eventually converge towards
smaller values.

However, the change introduced by:

commit 7e019dcc470f ("sched: Improve cache locality of RSEQ concurrency
IDs for intermittent workloads")

adds a per-mm/CPU recent_cid which is never unset unless a thread
migrates.

This is a tradeoff between:

A) Preserving cache locality after a transition from many threads to few
   threads, or after reducing the hamming weight of the allowed CPU mask.

B) Making the mm_cid upper bounds wrt nr threads and allowed CPU mask
   easy to document and understand.

C) Allowing applications to eventually react to mm_cid compaction after
   reduction of the nr threads or allowed CPU mask, making the tracking
   of mm_cid compaction easier by shrinking it back towards 0 or not.

D) Making sure applications that periodically reduce and then increase
   again the nr threads or allowed CPU mask still benefit from good
   cache locality with mm_cid.

Introduce the following changes:

* After shrinking the number of threads or reducing the number of
  allowed CPUs, reduce the value of max_nr_cid so expansion of CID
  allocation will preserve cache locality if the number of threads or
  allowed CPUs increase again.

* Only re-use a recent_cid if it is within the max_nr_cid upper bound,
  else find the first available CID.

Fixes: 7e019dcc470f ("sched: Improve cache locality of RSEQ concurrency IDs for intermittent workloads")
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Gabriele Monaco <gmonaco@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Gabriele Monaco <gmonaco@redhat.com>
Link: https://lkml.kernel.org/r/20250210153253.460471-2-gmonaco@redhat.com
---
 include/linux/mm_types.h |  7 ++++---
 kernel/sched/sched.h     | 25 ++++++++++++++++++++++---
 2 files changed, 26 insertions(+), 6 deletions(-)

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 6b27db7f94963..0234f14f2aa6b 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -875,10 +875,11 @@ struct mm_struct {
 		 */
 		unsigned int nr_cpus_allowed;
 		/**
-		 * @max_nr_cid: Maximum number of concurrency IDs allocated.
+		 * @max_nr_cid: Maximum number of allowed concurrency
+		 *              IDs allocated.
 		 *
-		 * Track the highest number of concurrency IDs allocated for the
-		 * mm.
+		 * Track the highest number of allowed concurrency IDs
+		 * allocated for the mm.
 		 */
 		atomic_t max_nr_cid;
 		/**
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b93c8c3dc05a5..c8512a9fb0229 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -3698,10 +3698,28 @@ static inline int __mm_cid_try_get(struct task_struct *t, struct mm_struct *mm)
 {
 	struct cpumask *cidmask = mm_cidmask(mm);
 	struct mm_cid __percpu *pcpu_cid = mm->pcpu_cid;
-	int cid = __this_cpu_read(pcpu_cid->recent_cid);
+	int cid, max_nr_cid, allowed_max_nr_cid;
 
+	/*
+	 * After shrinking the number of threads or reducing the number
+	 * of allowed cpus, reduce the value of max_nr_cid so expansion
+	 * of cid allocation will preserve cache locality if the number
+	 * of threads or allowed cpus increase again.
+	 */
+	max_nr_cid = atomic_read(&mm->max_nr_cid);
+	while ((allowed_max_nr_cid = min_t(int, READ_ONCE(mm->nr_cpus_allowed),
+					   atomic_read(&mm->mm_users))),
+	       max_nr_cid > allowed_max_nr_cid) {
+		/* atomic_try_cmpxchg loads previous mm->max_nr_cid into max_nr_cid. */
+		if (atomic_try_cmpxchg(&mm->max_nr_cid, &max_nr_cid, allowed_max_nr_cid)) {
+			max_nr_cid = allowed_max_nr_cid;
+			break;
+		}
+	}
 	/* Try to re-use recent cid. This improves cache locality. */
-	if (!mm_cid_is_unset(cid) && !cpumask_test_and_set_cpu(cid, cidmask))
+	cid = __this_cpu_read(pcpu_cid->recent_cid);
+	if (!mm_cid_is_unset(cid) && cid < max_nr_cid &&
+	    !cpumask_test_and_set_cpu(cid, cidmask))
 		return cid;
 	/*
 	 * Expand cid allocation if the maximum number of concurrency
@@ -3709,8 +3727,9 @@ static inline int __mm_cid_try_get(struct task_struct *t, struct mm_struct *mm)
 	 * and number of threads. Expanding cid allocation as much as
 	 * possible improves cache locality.
 	 */
-	cid = atomic_read(&mm->max_nr_cid);
+	cid = max_nr_cid;
 	while (cid < READ_ONCE(mm->nr_cpus_allowed) && cid < atomic_read(&mm->mm_users)) {
+		/* atomic_try_cmpxchg loads previous mm->max_nr_cid into cid. */
 		if (!atomic_try_cmpxchg(&mm->max_nr_cid, &cid, cid + 1))
 			continue;
 		if (!cpumask_test_and_set_cpu(cid, cidmask))

From dd4e17c309445eeecb8e0252ef9a519505035c27 Mon Sep 17 00:00:00 2001
From: Fabrizio Castro <fabrizio.castro.jz@renesas.com>
Date: Wed, 12 Feb 2025 18:20:29 +0000
Subject: [PATCH 0193/1173] irqchip/renesas-rzg2l: Use local dev pointer in
 rzg2l_irqc_common_init()

Replace direct references to `&pdev->dev` with the local `dev` pointer
in rzg2l_irqc_common_init() to avoid redundant dereferencing.

Suggested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Fabrizio Castro <fabrizio.castro.jz@renesas.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Link: https://lore.kernel.org/all/20250212182034.366167-2-fabrizio.castro.jz@renesas.com
---
 drivers/irqchip/irq-renesas-rzg2l.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/irqchip/irq-renesas-rzg2l.c b/drivers/irqchip/irq-renesas-rzg2l.c
index 99e27e01b0b19..a7c3a3cc6b9f7 100644
--- a/drivers/irqchip/irq-renesas-rzg2l.c
+++ b/drivers/irqchip/irq-renesas-rzg2l.c
@@ -542,40 +542,40 @@ static int rzg2l_irqc_common_init(struct device_node *node, struct device_node *
 
 	parent_domain = irq_find_host(parent);
 	if (!parent_domain) {
-		dev_err(&pdev->dev, "cannot find parent domain\n");
+		dev_err(dev, "cannot find parent domain\n");
 		return -ENODEV;
 	}
 
-	rzg2l_irqc_data = devm_kzalloc(&pdev->dev, sizeof(*rzg2l_irqc_data), GFP_KERNEL);
+	rzg2l_irqc_data = devm_kzalloc(dev, sizeof(*rzg2l_irqc_data), GFP_KERNEL);
 	if (!rzg2l_irqc_data)
 		return -ENOMEM;
 
 	rzg2l_irqc_data->irqchip = irq_chip;
 
-	rzg2l_irqc_data->base = devm_of_iomap(&pdev->dev, pdev->dev.of_node, 0, NULL);
+	rzg2l_irqc_data->base = devm_of_iomap(dev, dev->of_node, 0, NULL);
 	if (IS_ERR(rzg2l_irqc_data->base))
 		return PTR_ERR(rzg2l_irqc_data->base);
 
 	ret = rzg2l_irqc_parse_interrupts(rzg2l_irqc_data, node);
 	if (ret) {
-		dev_err(&pdev->dev, "cannot parse interrupts: %d\n", ret);
+		dev_err(dev, "cannot parse interrupts: %d\n", ret);
 		return ret;
 	}
 
-	resetn = devm_reset_control_get_exclusive(&pdev->dev, NULL);
+	resetn = devm_reset_control_get_exclusive(dev, NULL);
 	if (IS_ERR(resetn))
 		return PTR_ERR(resetn);
 
 	ret = reset_control_deassert(resetn);
 	if (ret) {
-		dev_err(&pdev->dev, "failed to deassert resetn pin, %d\n", ret);
+		dev_err(dev, "failed to deassert resetn pin, %d\n", ret);
 		return ret;
 	}
 
-	pm_runtime_enable(&pdev->dev);
-	ret = pm_runtime_resume_and_get(&pdev->dev);
+	pm_runtime_enable(dev);
+	ret = pm_runtime_resume_and_get(dev);
 	if (ret < 0) {
-		dev_err(&pdev->dev, "pm_runtime_resume_and_get failed: %d\n", ret);
+		dev_err(dev, "pm_runtime_resume_and_get failed: %d\n", ret);
 		goto pm_disable;
 	}
 
@@ -585,7 +585,7 @@ static int rzg2l_irqc_common_init(struct device_node *node, struct device_node *
 					      node, &rzg2l_irqc_domain_ops,
 					      rzg2l_irqc_data);
 	if (!irq_domain) {
-		dev_err(&pdev->dev, "failed to add irq domain\n");
+		dev_err(dev, "failed to add irq domain\n");
 		ret = -ENOMEM;
 		goto pm_put;
 	}
@@ -606,9 +606,9 @@ static int rzg2l_irqc_common_init(struct device_node *node, struct device_node *
 	return 0;
 
 pm_put:
-	pm_runtime_put(&pdev->dev);
+	pm_runtime_put(dev);
 pm_disable:
-	pm_runtime_disable(&pdev->dev);
+	pm_runtime_disable(dev);
 	reset_control_assert(resetn);
 	return ret;
 }

From 78f384dad082af13a9399b14ff23c5ea02b0a407 Mon Sep 17 00:00:00 2001
From: Fabrizio Castro <fabrizio.castro.jz@renesas.com>
Date: Wed, 12 Feb 2025 18:20:30 +0000
Subject: [PATCH 0194/1173] irqchip/renesas-rzg2l: Use
 devm_reset_control_get_exclusive_deasserted()

Use devm_reset_control_get_exclusive_deasserted() to simplify
rzg2l_irqc_common_init().

Signed-off-by: Fabrizio Castro <fabrizio.castro.jz@renesas.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de>
Reviewed-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Link: https://lore.kernel.org/all/20250212182034.366167-3-fabrizio.castro.jz@renesas.com
---
 drivers/irqchip/irq-renesas-rzg2l.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/drivers/irqchip/irq-renesas-rzg2l.c b/drivers/irqchip/irq-renesas-rzg2l.c
index a7c3a3cc6b9f7..a29c404661372 100644
--- a/drivers/irqchip/irq-renesas-rzg2l.c
+++ b/drivers/irqchip/irq-renesas-rzg2l.c
@@ -562,14 +562,10 @@ static int rzg2l_irqc_common_init(struct device_node *node, struct device_node *
 		return ret;
 	}
 
-	resetn = devm_reset_control_get_exclusive(dev, NULL);
-	if (IS_ERR(resetn))
+	resetn = devm_reset_control_get_exclusive_deasserted(dev, NULL);
+	if (IS_ERR(resetn)) {
+		dev_err(dev, "failed to acquire deasserted reset: %d\n", ret);
 		return PTR_ERR(resetn);
-
-	ret = reset_control_deassert(resetn);
-	if (ret) {
-		dev_err(dev, "failed to deassert resetn pin, %d\n", ret);
-		return ret;
 	}
 
 	pm_runtime_enable(dev);
@@ -609,7 +605,6 @@ static int rzg2l_irqc_common_init(struct device_node *node, struct device_node *
 	pm_runtime_put(dev);
 pm_disable:
 	pm_runtime_disable(dev);
-	reset_control_assert(resetn);
 	return ret;
 }
 

From 7de11369ef3037feb8365a3b5e8c433652f5fdeb Mon Sep 17 00:00:00 2001
From: Fabrizio Castro <fabrizio.castro.jz@renesas.com>
Date: Wed, 12 Feb 2025 18:20:31 +0000
Subject: [PATCH 0195/1173] irqchip/renesas-rzg2l: Use devm_pm_runtime_enable()

Simplify rzg2l_irqc_common_init() by using devm_pm_runtime_enable().

Signed-off-by: Fabrizio Castro <fabrizio.castro.jz@renesas.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250212182034.366167-4-fabrizio.castro.jz@renesas.com
---
 drivers/irqchip/irq-renesas-rzg2l.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/irqchip/irq-renesas-rzg2l.c b/drivers/irqchip/irq-renesas-rzg2l.c
index a29c404661372..c024023a1832d 100644
--- a/drivers/irqchip/irq-renesas-rzg2l.c
+++ b/drivers/irqchip/irq-renesas-rzg2l.c
@@ -568,11 +568,16 @@ static int rzg2l_irqc_common_init(struct device_node *node, struct device_node *
 		return PTR_ERR(resetn);
 	}
 
-	pm_runtime_enable(dev);
+	ret = devm_pm_runtime_enable(dev);
+	if (ret < 0) {
+		dev_err(dev, "devm_pm_runtime_enable failed: %d\n", ret);
+		return ret;
+	}
+
 	ret = pm_runtime_resume_and_get(dev);
 	if (ret < 0) {
 		dev_err(dev, "pm_runtime_resume_and_get failed: %d\n", ret);
-		goto pm_disable;
+		return ret;
 	}
 
 	raw_spin_lock_init(&rzg2l_irqc_data->lock);
@@ -603,8 +608,7 @@ static int rzg2l_irqc_common_init(struct device_node *node, struct device_node *
 
 pm_put:
 	pm_runtime_put(dev);
-pm_disable:
-	pm_runtime_disable(dev);
+
 	return ret;
 }
 

From bec8a3712943282fcac10647905c021335e27c2b Mon Sep 17 00:00:00 2001
From: Fabrizio Castro <fabrizio.castro.jz@renesas.com>
Date: Wed, 12 Feb 2025 18:20:32 +0000
Subject: [PATCH 0196/1173] irqchip/renesas-rzg2l: Remove pm_put label

No need to keep label `pm_put`, as it's only used once.
Call pm_runtime_put() directly from the error path.

Signed-off-by: Fabrizio Castro <fabrizio.castro.jz@renesas.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Link: https://lore.kernel.org/all/20250212182034.366167-5-fabrizio.castro.jz@renesas.com
---
 drivers/irqchip/irq-renesas-rzg2l.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/drivers/irqchip/irq-renesas-rzg2l.c b/drivers/irqchip/irq-renesas-rzg2l.c
index c024023a1832d..0f325ceb0f53f 100644
--- a/drivers/irqchip/irq-renesas-rzg2l.c
+++ b/drivers/irqchip/irq-renesas-rzg2l.c
@@ -586,9 +586,9 @@ static int rzg2l_irqc_common_init(struct device_node *node, struct device_node *
 					      node, &rzg2l_irqc_domain_ops,
 					      rzg2l_irqc_data);
 	if (!irq_domain) {
+		pm_runtime_put(dev);
 		dev_err(dev, "failed to add irq domain\n");
-		ret = -ENOMEM;
-		goto pm_put;
+		return -ENOMEM;
 	}
 
 	register_syscore_ops(&rzg2l_irqc_syscore_ops);
@@ -605,11 +605,6 @@ static int rzg2l_irqc_common_init(struct device_node *node, struct device_node *
 	dev = NULL;
 
 	return 0;
-
-pm_put:
-	pm_runtime_put(dev);
-
-	return ret;
 }
 
 static int __init rzg2l_irqc_init(struct device_node *node,

From 4bd0317ce63c26c8a1b6e96c9be0badac749c6f7 Mon Sep 17 00:00:00 2001
From: Fabrizio Castro <fabrizio.castro.jz@renesas.com>
Date: Wed, 12 Feb 2025 18:20:33 +0000
Subject: [PATCH 0197/1173] irqchip/renesas-rzg2l: Switch to using
 dev_err_probe()

Make use of dev_err_probe() to simplify rzg2l_irqc_common_init().

Signed-off-by: Fabrizio Castro <fabrizio.castro.jz@renesas.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Link: https://lore.kernel.org/all/20250212182034.366167-6-fabrizio.castro.jz@renesas.com
---
 drivers/irqchip/irq-renesas-rzg2l.c | 31 ++++++++++-------------------
 1 file changed, 11 insertions(+), 20 deletions(-)

diff --git a/drivers/irqchip/irq-renesas-rzg2l.c b/drivers/irqchip/irq-renesas-rzg2l.c
index 0f325ceb0f53f..8714e7fdbbda1 100644
--- a/drivers/irqchip/irq-renesas-rzg2l.c
+++ b/drivers/irqchip/irq-renesas-rzg2l.c
@@ -541,10 +541,8 @@ static int rzg2l_irqc_common_init(struct device_node *node, struct device_node *
 		return -ENODEV;
 
 	parent_domain = irq_find_host(parent);
-	if (!parent_domain) {
-		dev_err(dev, "cannot find parent domain\n");
-		return -ENODEV;
-	}
+	if (!parent_domain)
+		return dev_err_probe(dev, -ENODEV, "cannot find parent domain\n");
 
 	rzg2l_irqc_data = devm_kzalloc(dev, sizeof(*rzg2l_irqc_data), GFP_KERNEL);
 	if (!rzg2l_irqc_data)
@@ -557,28 +555,22 @@ static int rzg2l_irqc_common_init(struct device_node *node, struct device_node *
 		return PTR_ERR(rzg2l_irqc_data->base);
 
 	ret = rzg2l_irqc_parse_interrupts(rzg2l_irqc_data, node);
-	if (ret) {
-		dev_err(dev, "cannot parse interrupts: %d\n", ret);
-		return ret;
-	}
+	if (ret)
+		return dev_err_probe(dev, ret, "cannot parse interrupts: %d\n", ret);
 
 	resetn = devm_reset_control_get_exclusive_deasserted(dev, NULL);
 	if (IS_ERR(resetn)) {
-		dev_err(dev, "failed to acquire deasserted reset: %d\n", ret);
-		return PTR_ERR(resetn);
+		return dev_err_probe(dev, PTR_ERR(resetn),
+				     "failed to acquire deasserted reset: %d\n", ret);
 	}
 
 	ret = devm_pm_runtime_enable(dev);
-	if (ret < 0) {
-		dev_err(dev, "devm_pm_runtime_enable failed: %d\n", ret);
-		return ret;
-	}
+	if (ret < 0)
+		return dev_err_probe(dev, ret, "devm_pm_runtime_enable failed: %d\n", ret);
 
 	ret = pm_runtime_resume_and_get(dev);
-	if (ret < 0) {
-		dev_err(dev, "pm_runtime_resume_and_get failed: %d\n", ret);
-		return ret;
-	}
+	if (ret < 0)
+		return dev_err_probe(dev, ret, "pm_runtime_resume_and_get failed: %d\n", ret);
 
 	raw_spin_lock_init(&rzg2l_irqc_data->lock);
 
@@ -587,8 +579,7 @@ static int rzg2l_irqc_common_init(struct device_node *node, struct device_node *
 					      rzg2l_irqc_data);
 	if (!irq_domain) {
 		pm_runtime_put(dev);
-		dev_err(dev, "failed to add irq domain\n");
-		return -ENOMEM;
+		return dev_err_probe(dev, -ENOMEM, "failed to add irq domain\n");
 	}
 
 	register_syscore_ops(&rzg2l_irqc_syscore_ops);

From 0699e578e27910224ee09a55b824e5d494ce280f Mon Sep 17 00:00:00 2001
From: Fabrizio Castro <fabrizio.castro.jz@renesas.com>
Date: Wed, 12 Feb 2025 18:20:34 +0000
Subject: [PATCH 0198/1173] irqchip/renesas-rzg2l: Simplify checks in
 rzg2l_irqc_common_init()

Both devm_pm_runtime_enable() and pm_runtime_resume_and_get()
return 0 or a negative error code.

Simplify the checks done with their respective return values
accordingly.

Signed-off-by: Fabrizio Castro <fabrizio.castro.jz@renesas.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250212182034.366167-7-fabrizio.castro.jz@renesas.com
---
 drivers/irqchip/irq-renesas-rzg2l.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/irqchip/irq-renesas-rzg2l.c b/drivers/irqchip/irq-renesas-rzg2l.c
index 8714e7fdbbda1..6a2e41f024464 100644
--- a/drivers/irqchip/irq-renesas-rzg2l.c
+++ b/drivers/irqchip/irq-renesas-rzg2l.c
@@ -565,11 +565,11 @@ static int rzg2l_irqc_common_init(struct device_node *node, struct device_node *
 	}
 
 	ret = devm_pm_runtime_enable(dev);
-	if (ret < 0)
+	if (ret)
 		return dev_err_probe(dev, ret, "devm_pm_runtime_enable failed: %d\n", ret);
 
 	ret = pm_runtime_resume_and_get(dev);
-	if (ret < 0)
+	if (ret)
 		return dev_err_probe(dev, ret, "pm_runtime_resume_and_get failed: %d\n", ret);
 
 	raw_spin_lock_init(&rzg2l_irqc_data->lock);

From ec5fd50aeff9c9156304853c6d75eda852d4a2c8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Mon, 17 Feb 2025 08:43:35 +0100
Subject: [PATCH 0199/1173] uprobes: Don't use %pK through printk
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Restricted pointers ("%pK") are not meant to be used through printk().
It can unintentionally expose security sensitive, raw pointer values.

Use regular pointer formatting instead.

For more background, see:

  https://lore.kernel.org/lkml/20250113171731-dc10e3c1-da64-4af0-b767-7c7070468023@linutronix.de/

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250217-restricted-pointers-uprobes-v1-1-e8cbe5bb22a7@linutronix.de
---
 kernel/events/uprobes.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 2ca797cbe465f..bf2a87a0a3787 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -417,7 +417,7 @@ static void update_ref_ctr_warn(struct uprobe *uprobe,
 				struct mm_struct *mm, short d)
 {
 	pr_warn("ref_ctr %s failed for inode: 0x%lx offset: "
-		"0x%llx ref_ctr_offset: 0x%llx of mm: 0x%pK\n",
+		"0x%llx ref_ctr_offset: 0x%llx of mm: 0x%p\n",
 		d > 0 ? "increment" : "decrement", uprobe->inode->i_ino,
 		(unsigned long long) uprobe->offset,
 		(unsigned long long) uprobe->ref_ctr_offset, mm);

From 999f458c1771354371ba367dd84f55f9a62a4233 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Mon, 17 Feb 2025 14:26:47 +0530
Subject: [PATCH 0200/1173] irqchip/riscv-imsic: Set irq_set_affinity() for
 IMSIC base

The IMSIC driver assigns the IMSIC domain specific imsic_irq_set_affinity()
callback to the per device leaf MSI domain. That's a layering violation as
it is called with the leaf domain data and not with the IMSIC domain
data. This prevents moving the IMSIC driver to the common MSI library which
uses the generic msi_domain_set_affinity() callback for device MSI domains.

Instead of using imsic_irq_set_affinity() for leaf MSI domains, use
imsic_irq_set_affinity() for the non-leaf IMSIC base domain and use
irq_chip_set_affinity_parent() for leaf MSI domains.

[ tglx: Massaged change log ]

Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250217085657.789309-2-apatel@ventanamicro.com
---
 drivers/irqchip/irq-riscv-imsic-platform.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/drivers/irqchip/irq-riscv-imsic-platform.c b/drivers/irqchip/irq-riscv-imsic-platform.c
index c708780e8760f..5d7c30ad8855b 100644
--- a/drivers/irqchip/irq-riscv-imsic-platform.c
+++ b/drivers/irqchip/irq-riscv-imsic-platform.c
@@ -96,9 +96,8 @@ static int imsic_irq_set_affinity(struct irq_data *d, const struct cpumask *mask
 				  bool force)
 {
 	struct imsic_vector *old_vec, *new_vec;
-	struct irq_data *pd = d->parent_data;
 
-	old_vec = irq_data_get_irq_chip_data(pd);
+	old_vec = irq_data_get_irq_chip_data(d);
 	if (WARN_ON(!old_vec))
 		return -ENOENT;
 
@@ -116,13 +115,13 @@ static int imsic_irq_set_affinity(struct irq_data *d, const struct cpumask *mask
 		return -ENOSPC;
 
 	/* Point device to the new vector */
-	imsic_msi_update_msg(d, new_vec);
+	imsic_msi_update_msg(irq_get_irq_data(d->irq), new_vec);
 
 	/* Update irq descriptors with the new vector */
-	pd->chip_data = new_vec;
+	d->chip_data = new_vec;
 
-	/* Update effective affinity of parent irq data */
-	irq_data_update_effective_affinity(pd, cpumask_of(new_vec->cpu));
+	/* Update effective affinity */
+	irq_data_update_effective_affinity(d, cpumask_of(new_vec->cpu));
 
 	/* Move state of the old vector to the new vector */
 	imsic_vector_move(old_vec, new_vec);
@@ -135,6 +134,9 @@ static struct irq_chip imsic_irq_base_chip = {
 	.name			= "IMSIC",
 	.irq_mask		= imsic_irq_mask,
 	.irq_unmask		= imsic_irq_unmask,
+#ifdef CONFIG_SMP
+	.irq_set_affinity	= imsic_irq_set_affinity,
+#endif
 	.irq_retrigger		= imsic_irq_retrigger,
 	.irq_compose_msi_msg	= imsic_irq_compose_msg,
 	.flags			= IRQCHIP_SKIP_SET_WAKE |
@@ -245,7 +247,7 @@ static bool imsic_init_dev_msi_info(struct device *dev,
 		if (WARN_ON_ONCE(domain != real_parent))
 			return false;
 #ifdef CONFIG_SMP
-		info->chip->irq_set_affinity = imsic_irq_set_affinity;
+		info->chip->irq_set_affinity = irq_chip_set_affinity_parent;
 #endif
 		break;
 	default:

From 4441b976dfeff0d3579e8da3c0283300c618a553 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 14 Feb 2025 15:43:33 +0200
Subject: [PATCH 0201/1173] hrtimers: Replace hrtimer_clock_to_base_table with
 switch-case

Clang and GCC complain about overlapped initialisers in the
hrtimer_clock_to_base_table definition. With `make W=1` and CONFIG_WERROR=y
(which is default nowadays) this breaks the build:

  CC      kernel/time/hrtimer.o
kernel/time/hrtimer.c:124:21: error: initializer overrides prior initialization of this subobject [-Werror,-Winitializer-overrides]
  124 |         [CLOCK_REALTIME]        = HRTIMER_BASE_REALTIME,

kernel/time/hrtimer.c:122:27: note: previous initialization is here
  122 |         [0 ... MAX_CLOCKS - 1]  = HRTIMER_MAX_CLOCK_BASES,

(and similar for CLOCK_MONOTONIC, CLOCK_BOOTTIME, and CLOCK_TAI).

hrtimer_clockid_to_base(), which uses the table, is only used in
__hrtimer_init(), which is not a hotpath.

Therefore replace the table lookup with a switch case in
hrtimer_clockid_to_base() to avoid this warning.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250214134424.3367619-1-andriy.shevchenko@linux.intel.com
---
 kernel/time/hrtimer.c | 29 ++++++++++++-----------------
 1 file changed, 12 insertions(+), 17 deletions(-)

diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index deb1aa32814e3..453dc76c93484 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -117,16 +117,6 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 	.csd = CSD_INIT(retrigger_next_event, NULL)
 };
 
-static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
-	/* Make sure we catch unsupported clockids */
-	[0 ... MAX_CLOCKS - 1]	= HRTIMER_MAX_CLOCK_BASES,
-
-	[CLOCK_REALTIME]	= HRTIMER_BASE_REALTIME,
-	[CLOCK_MONOTONIC]	= HRTIMER_BASE_MONOTONIC,
-	[CLOCK_BOOTTIME]	= HRTIMER_BASE_BOOTTIME,
-	[CLOCK_TAI]		= HRTIMER_BASE_TAI,
-};
-
 static inline bool hrtimer_base_is_online(struct hrtimer_cpu_base *base)
 {
 	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
@@ -1587,14 +1577,19 @@ u64 hrtimer_next_event_without(const struct hrtimer *exclude)
 
 static inline int hrtimer_clockid_to_base(clockid_t clock_id)
 {
-	if (likely(clock_id < MAX_CLOCKS)) {
-		int base = hrtimer_clock_to_base_table[clock_id];
-
-		if (likely(base != HRTIMER_MAX_CLOCK_BASES))
-			return base;
+	switch (clock_id) {
+	case CLOCK_REALTIME:
+		return HRTIMER_BASE_REALTIME;
+	case CLOCK_MONOTONIC:
+		return HRTIMER_BASE_MONOTONIC;
+	case CLOCK_BOOTTIME:
+		return HRTIMER_BASE_BOOTTIME;
+	case CLOCK_TAI:
+		return HRTIMER_BASE_TAI;
+	default:
+		WARN(1, "Invalid clockid %d. Using MONOTONIC\n", clock_id);
+		return HRTIMER_BASE_MONOTONIC;
 	}
-	WARN(1, "Invalid clockid %d. Using MONOTONIC\n", clock_id);
-	return HRTIMER_BASE_MONOTONIC;
 }
 
 static enum hrtimer_restart hrtimer_dummy_timeout(struct hrtimer *unused)

From f99c5bb396b8d1424ed229d1ffa6f596e3b9c36b Mon Sep 17 00:00:00 2001
From: Benjamin Segall <bsegall@google.com>
Date: Fri, 14 Feb 2025 14:12:20 -0800
Subject: [PATCH 0202/1173] posix-timers: Invoke cond_resched() during
 exit_itimers()

exit_itimers() loops through every timer in the process to delete it.  This
requires taking the system-wide hash_lock for each of these timers, and
contends with other processes trying to create or delete timers.

When a process creates hundreds of thousands of timers, and then exits
while other processes contend with it, this can trigger softlockups on
CONFIG_PREEMPT=n.

Add a cond_resched() invocation into the loop to allow the system to make
progress.

Signed-off-by: Ben Segall <bsegall@google.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/xm2634gg2n23.fsf@google.com
---
 kernel/time/posix-timers.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 1b675aee99a98..44ba7db07e900 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -1099,8 +1099,10 @@ void exit_itimers(struct task_struct *tsk)
 	spin_unlock_irq(&tsk->sighand->siglock);
 
 	/* The timers are not longer accessible via tsk::signal */
-	while (!hlist_empty(&timers))
+	while (!hlist_empty(&timers)) {
 		itimer_delete(hlist_entry(timers.first, struct k_itimer, list));
+		cond_resched();
+	}
 
 	/*
 	 * There should be no timers on the ignored list. itimer_delete() has

From a3e8fe814ad15c16735cdf394454a8bd96eb4d56 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Thu, 23 Jan 2025 14:07:33 -0500
Subject: [PATCH 0203/1173] x86/build: Raise the minimum GCC version to 8.1

Stack protector support on 64-bit currently requires that the percpu
section is linked at absolute address 0, because older compilers fixed
the location of the canary value relative to the GS segment base.

GCC 8.1 introduced options to change where the canary value is located,
allowing it to be configured as a standard per-CPU variable.  This has
already been done for 32-bit.  Doing the same for 64-bit will enable
removing the code needed to support zero-based percpu.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250123190747.745588-2-brgerst@gmail.com
---
 scripts/min-tool-version.sh | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/scripts/min-tool-version.sh b/scripts/min-tool-version.sh
index 91c91201212c4..06c4e410ecaba 100755
--- a/scripts/min-tool-version.sh
+++ b/scripts/min-tool-version.sh
@@ -19,6 +19,8 @@ binutils)
 gcc)
 	if [ "$ARCH" = parisc64 ]; then
 		echo 12.0.0
+	elif [ "$SRCARCH" = x86 ]; then
+		echo 8.1.0
 	else
 		echo 5.1.0
 	fi

From 0ee2689b9374d6fd5f43b703713a532278654749 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Thu, 23 Jan 2025 14:07:34 -0500
Subject: [PATCH 0204/1173] x86/stackprotector: Remove stack protector test
 scripts

With GCC 8.1 now the minimum supported compiler for x86, these scripts
are no longer needed.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250123190747.745588-3-brgerst@gmail.com
---
 arch/x86/Kconfig                          | 11 +----------
 scripts/gcc-x86_32-has-stack-protector.sh |  8 --------
 scripts/gcc-x86_64-has-stack-protector.sh |  4 ----
 3 files changed, 1 insertion(+), 22 deletions(-)
 delete mode 100755 scripts/gcc-x86_32-has-stack-protector.sh
 delete mode 100755 scripts/gcc-x86_64-has-stack-protector.sh

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index be2c311f5118d..6595b35dd52da 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -285,7 +285,7 @@ config X86
 	select HAVE_FUNCTION_ARG_ACCESS_API
 	select HAVE_SETUP_PER_CPU_AREA
 	select HAVE_SOFTIRQ_ON_OWN_STACK
-	select HAVE_STACKPROTECTOR		if CC_HAS_SANE_STACKPROTECTOR
+	select HAVE_STACKPROTECTOR
 	select HAVE_STACK_VALIDATION		if HAVE_OBJTOOL
 	select HAVE_STATIC_CALL
 	select HAVE_STATIC_CALL_INLINE		if HAVE_OBJTOOL
@@ -426,15 +426,6 @@ config PGTABLE_LEVELS
 	default 3 if X86_PAE
 	default 2
 
-config CC_HAS_SANE_STACKPROTECTOR
-	bool
-	default $(success,$(srctree)/scripts/gcc-x86_64-has-stack-protector.sh $(CC) $(CLANG_FLAGS)) if 64BIT
-	default $(success,$(srctree)/scripts/gcc-x86_32-has-stack-protector.sh $(CC) $(CLANG_FLAGS))
-	help
-	  We have to make sure stack protector is unconditionally disabled if
-	  the compiler produces broken code or if it does not let us control
-	  the segment on 32-bit kernels.
-
 menu "Processor type and features"
 
 config SMP
diff --git a/scripts/gcc-x86_32-has-stack-protector.sh b/scripts/gcc-x86_32-has-stack-protector.sh
deleted file mode 100755
index 9459ca4f0f11f..0000000000000
--- a/scripts/gcc-x86_32-has-stack-protector.sh
+++ /dev/null
@@ -1,8 +0,0 @@
-#!/bin/sh
-# SPDX-License-Identifier: GPL-2.0
-
-# This requires GCC 8.1 or better.  Specifically, we require
-# -mstack-protector-guard-reg, added by
-# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81708
-
-echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -m32 -O0 -fstack-protector -mstack-protector-guard-reg=fs -mstack-protector-guard-symbol=__stack_chk_guard - -o - 2> /dev/null | grep -q "%fs"
diff --git a/scripts/gcc-x86_64-has-stack-protector.sh b/scripts/gcc-x86_64-has-stack-protector.sh
deleted file mode 100755
index f680bb01aeeb3..0000000000000
--- a/scripts/gcc-x86_64-has-stack-protector.sh
+++ /dev/null
@@ -1,4 +0,0 @@
-#!/bin/sh
-# SPDX-License-Identifier: GPL-2.0
-
-echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -m64 -O0 -mcmodel=kernel -fno-PIE -fstack-protector - -o - 2> /dev/null | grep -q "%gs"

From a9a76b38aaf577887103e3ebb41d70e6aa5a4b19 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Thu, 23 Jan 2025 14:07:35 -0500
Subject: [PATCH 0205/1173] x86/boot: Disable stack protector for early boot
 code

On 64-bit, this will prevent crashes when the canary access is changed
from %gs:40 to %gs:__stack_chk_guard(%rip).  RIP-relative addresses from
the identity-mapped early boot code will target the wrong address with
zero-based percpu.  KASLR could then shift that address to an unmapped
page causing a crash on boot.

This early boot code runs well before user-space is active and does not
need stack protector enabled.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250123190747.745588-4-brgerst@gmail.com
---
 arch/x86/kernel/Makefile | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index b43eb7e384eba..84cfa179802c3 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -44,6 +44,8 @@ KCOV_INSTRUMENT_unwind_orc.o				:= n
 KCOV_INSTRUMENT_unwind_frame.o				:= n
 KCOV_INSTRUMENT_unwind_guess.o				:= n
 
+CFLAGS_head32.o := -fno-stack-protector
+CFLAGS_head64.o := -fno-stack-protector
 CFLAGS_irq.o := -I $(src)/../include/asm/trace
 
 obj-y			+= head_$(BITS).o

From f58b63857ae38b4484185b799a2759274b930c92 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Thu, 23 Jan 2025 14:07:36 -0500
Subject: [PATCH 0206/1173] x86/pvh: Use fixed_percpu_data for early boot
 GSBASE

Instead of having a private area for the stack canary, use
fixed_percpu_data for GSBASE like the native kernel.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250123190747.745588-5-brgerst@gmail.com
---
 arch/x86/platform/pvh/head.S | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/arch/x86/platform/pvh/head.S b/arch/x86/platform/pvh/head.S
index 4733a5f467b81..723f181b222ab 100644
--- a/arch/x86/platform/pvh/head.S
+++ b/arch/x86/platform/pvh/head.S
@@ -173,10 +173,15 @@ SYM_CODE_START(pvh_start_xen)
 1:
 	UNWIND_HINT_END_OF_STACK
 
-	/* Set base address in stack canary descriptor. */
-	mov $MSR_GS_BASE,%ecx
-	leal canary(%rip), %eax
-	xor %edx, %edx
+	/*
+	 * Set up GSBASE.
+	 * Note that on SMP the boot CPU uses the init data section until
+	 * the per-CPU areas are set up.
+	 */
+	movl $MSR_GS_BASE,%ecx
+	leaq INIT_PER_CPU_VAR(fixed_percpu_data)(%rip), %rdx
+	movq %edx, %eax
+	shrq $32, %rdx
 	wrmsr
 
 	/* Call xen_prepare_pvh() via the kernel virtual mapping */
@@ -238,8 +243,6 @@ SYM_DATA_START_LOCAL(gdt_start)
 SYM_DATA_END_LABEL(gdt_start, SYM_L_LOCAL, gdt_end)
 
 	.balign 16
-SYM_DATA_LOCAL(canary, .fill 48, 1, 0)
-
 SYM_DATA_START_LOCAL(early_stack)
 	.fill BOOT_STACK_SIZE, 1, 0
 SYM_DATA_END_LABEL(early_stack, SYM_L_LOCAL, early_stack_end)

From cb7927fda002ca49ae62e2782c1692acc7b80c67 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Thu, 23 Jan 2025 14:07:37 -0500
Subject: [PATCH 0207/1173] x86/relocs: Handle R_X86_64_REX_GOTPCRELX
 relocations

Clang may produce R_X86_64_REX_GOTPCRELX relocations when redefining the
stack protector location.  Treat them as another type of PC-relative
relocation.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250123190747.745588-6-brgerst@gmail.com
---
 arch/x86/tools/relocs.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index e937be979ec86..92a1e503305ef 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -32,6 +32,11 @@ static struct relocs		relocs32;
 static struct relocs		relocs32neg;
 static struct relocs		relocs64;
 # define FMT PRIu64
+
+#ifndef R_X86_64_REX_GOTPCRELX
+# define R_X86_64_REX_GOTPCRELX 42
+#endif
+
 #else
 # define FMT PRIu32
 #endif
@@ -227,6 +232,7 @@ static const char *rel_type(unsigned type)
 		REL_TYPE(R_X86_64_PC16),
 		REL_TYPE(R_X86_64_8),
 		REL_TYPE(R_X86_64_PC8),
+		REL_TYPE(R_X86_64_REX_GOTPCRELX),
 #else
 		REL_TYPE(R_386_NONE),
 		REL_TYPE(R_386_32),
@@ -861,6 +867,7 @@ static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym,
 
 	case R_X86_64_PC32:
 	case R_X86_64_PLT32:
+	case R_X86_64_REX_GOTPCRELX:
 		/*
 		 * PC relative relocations don't need to be adjusted unless
 		 * referencing a percpu symbol.

From 78c4374ef8b842c6abf195d6f963853c7ec464d2 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Thu, 23 Jan 2025 14:07:38 -0500
Subject: [PATCH 0208/1173] x86/module: Deal with GOT based stack cookie load
 on Clang < 17

Clang versions before 17 will not honour -fdirect-access-external-data
for the load of the stack cookie emitted into each function's prologue
and epilogue.

This is not an issue for the core kernel, as the linker will relax these
loads into LEA instructions that take the address of __stack_chk_guard
directly. For modules, however, we need to work around this, by dealing
with R_X86_64_REX_GOTPCRELX relocations that refer to __stack_chk_guard.

In this case, given that this is a GOT load, the reference should not
refer to __stack_chk_guard directly, but to a memory location that holds
its address. So take the address of __stack_chk_guard into a static
variable, and fix up the relocations to refer to that.

[ mingo: Fix broken R_X86_64_GOTPCRELX definition. ]

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250123190747.745588-7-brgerst@gmail.com
---
 arch/x86/include/asm/elf.h |  5 +++--
 arch/x86/kernel/module.c   | 15 +++++++++++++++
 2 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 1fb83d47711f9..128602612ecaa 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -54,8 +54,9 @@ typedef struct user_i387_struct elf_fpregset_t;
 #define R_X86_64_GLOB_DAT	6	/* Create GOT entry */
 #define R_X86_64_JUMP_SLOT	7	/* Create PLT entry */
 #define R_X86_64_RELATIVE	8	/* Adjust by program base */
-#define R_X86_64_GOTPCREL	9	/* 32 bit signed pc relative
-					   offset to GOT */
+#define R_X86_64_GOTPCREL	9	/* 32 bit signed pc relative offset to GOT */
+#define R_X86_64_GOTPCRELX	41
+#define R_X86_64_REX_GOTPCRELX	42
 #define R_X86_64_32		10	/* Direct 32 bit zero extended */
 #define R_X86_64_32S		11	/* Direct 32 bit sign extended */
 #define R_X86_64_16		12	/* Direct 16 bit zero extended */
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index 8984abd91c001..a286f32c55036 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -19,6 +19,7 @@
 #include <linux/jump_label.h>
 #include <linux/random.h>
 #include <linux/memory.h>
+#include <linux/stackprotector.h>
 
 #include <asm/text-patching.h>
 #include <asm/page.h>
@@ -130,6 +131,20 @@ static int __write_relocate_add(Elf64_Shdr *sechdrs,
 				goto overflow;
 			size = 4;
 			break;
+#if defined(CONFIG_STACKPROTECTOR) && \
+    defined(CONFIG_CC_IS_CLANG) && CONFIG_CLANG_VERSION < 170000
+		case R_X86_64_REX_GOTPCRELX: {
+			static unsigned long __percpu *const addr = &__stack_chk_guard;
+
+			if (sym->st_value != (u64)addr) {
+				pr_err("%s: Unsupported GOTPCREL relocation\n", me->name);
+				return -ENOEXEC;
+			}
+
+			val = (u64)&addr + rel[i].r_addend;
+			fallthrough;
+		}
+#endif
 		case R_X86_64_PC32:
 		case R_X86_64_PLT32:
 			val -= (u64)loc;

From 80d47defddc000271502057ebd7efa4fd6481542 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Thu, 23 Jan 2025 14:07:39 -0500
Subject: [PATCH 0209/1173] x86/stackprotector/64: Convert to normal per-CPU
 variable

Older versions of GCC fixed the location of the stack protector canary
at %gs:40.  This constraint forced the percpu section to be linked at
absolute address 0 so that the canary could be the first data object in
the percpu section.  Supporting the zero-based percpu section requires
additional code to handle relocations for RIP-relative references to
percpu data, extra complexity to kallsyms, and workarounds for linker
bugs due to the use of absolute symbols.

GCC 8.1 supports redefining where the canary is located, allowing it to
become a normal percpu variable instead of at a fixed location.  This
removes the constraint that the percpu section must be zero-based.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250123190747.745588-8-brgerst@gmail.com
---
 arch/x86/Makefile                     | 20 +++++++++------
 arch/x86/entry/entry.S                |  2 --
 arch/x86/entry/entry_64.S             |  2 +-
 arch/x86/include/asm/processor.h      | 16 ++----------
 arch/x86/include/asm/stackprotector.h | 36 ++++-----------------------
 arch/x86/kernel/asm-offsets_64.c      |  6 -----
 arch/x86/kernel/cpu/common.c          |  5 +---
 arch/x86/kernel/head_64.S             |  3 +--
 arch/x86/xen/xen-head.S               |  3 +--
 9 files changed, 23 insertions(+), 70 deletions(-)

diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 5b773b34768d1..88a1705366f91 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -140,14 +140,7 @@ ifeq ($(CONFIG_X86_32),y)
         # temporary until string.h is fixed
         KBUILD_CFLAGS += -ffreestanding
 
-    ifeq ($(CONFIG_STACKPROTECTOR),y)
-        ifeq ($(CONFIG_SMP),y)
-            KBUILD_CFLAGS += -mstack-protector-guard-reg=fs \
-                             -mstack-protector-guard-symbol=__ref_stack_chk_guard
-        else
-            KBUILD_CFLAGS += -mstack-protector-guard=global
-        endif
-    endif
+        percpu_seg := fs
 else
         BITS := 64
         UTS_MACHINE := x86_64
@@ -197,6 +190,17 @@ else
         KBUILD_CFLAGS += -mcmodel=kernel
         KBUILD_RUSTFLAGS += -Cno-redzone=y
         KBUILD_RUSTFLAGS += -Ccode-model=kernel
+
+        percpu_seg := gs
+endif
+
+ifeq ($(CONFIG_STACKPROTECTOR),y)
+    ifeq ($(CONFIG_SMP),y)
+	KBUILD_CFLAGS += -mstack-protector-guard-reg=$(percpu_seg)
+	KBUILD_CFLAGS += -mstack-protector-guard-symbol=__ref_stack_chk_guard
+    else
+	KBUILD_CFLAGS += -mstack-protector-guard=global
+    endif
 endif
 
 #
diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S
index b7ea3e8e9eccd..fe5344a249a1b 100644
--- a/arch/x86/entry/entry.S
+++ b/arch/x86/entry/entry.S
@@ -52,7 +52,6 @@ EXPORT_SYMBOL_GPL(mds_verw_sel);
 
 THUNK warn_thunk_thunk, __warn_thunk
 
-#ifndef CONFIG_X86_64
 /*
  * Clang's implementation of TLS stack cookies requires the variable in
  * question to be a TLS variable. If the variable happens to be defined as an
@@ -66,4 +65,3 @@ THUNK warn_thunk_thunk, __warn_thunk
 #ifdef CONFIG_STACKPROTECTOR
 EXPORT_SYMBOL(__ref_stack_chk_guard);
 #endif
-#endif
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index f52dbe0ad93cd..33a955aa01d89 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -192,7 +192,7 @@ SYM_FUNC_START(__switch_to_asm)
 
 #ifdef CONFIG_STACKPROTECTOR
 	movq	TASK_stack_canary(%rsi), %rbx
-	movq	%rbx, PER_CPU_VAR(fixed_percpu_data + FIXED_stack_canary)
+	movq	%rbx, PER_CPU_VAR(__stack_chk_guard)
 #endif
 
 	/*
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index c0cd10182e90c..a4687122951f7 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -422,16 +422,8 @@ struct irq_stack {
 
 #ifdef CONFIG_X86_64
 struct fixed_percpu_data {
-	/*
-	 * GCC hardcodes the stack canary as %gs:40.  Since the
-	 * irq_stack is the object at %gs:0, we reserve the bottom
-	 * 48 bytes of the irq stack for the canary.
-	 *
-	 * Once we are willing to require -mstack-protector-guard-symbol=
-	 * support for x86_64 stackprotector, we can get rid of this.
-	 */
 	char		gs_base[40];
-	unsigned long	stack_canary;
+	unsigned long	reserved;
 };
 
 DECLARE_PER_CPU_FIRST(struct fixed_percpu_data, fixed_percpu_data) __visible;
@@ -446,11 +438,7 @@ extern asmlinkage void entry_SYSCALL32_ignore(void);
 
 /* Save actual FS/GS selectors and bases to current->thread */
 void current_save_fsgs(void);
-#else	/* X86_64 */
-#ifdef CONFIG_STACKPROTECTOR
-DECLARE_PER_CPU(unsigned long, __stack_chk_guard);
-#endif
-#endif	/* !X86_64 */
+#endif	/* X86_64 */
 
 struct perf_event;
 
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index 00473a650f512..d43fb589fcf66 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/arch/x86/include/asm/stackprotector.h
@@ -2,26 +2,10 @@
 /*
  * GCC stack protector support.
  *
- * Stack protector works by putting predefined pattern at the start of
+ * Stack protector works by putting a predefined pattern at the start of
  * the stack frame and verifying that it hasn't been overwritten when
- * returning from the function.  The pattern is called stack canary
- * and unfortunately gcc historically required it to be at a fixed offset
- * from the percpu segment base.  On x86_64, the offset is 40 bytes.
- *
- * The same segment is shared by percpu area and stack canary.  On
- * x86_64, percpu symbols are zero based and %gs (64-bit) points to the
- * base of percpu area.  The first occupant of the percpu area is always
- * fixed_percpu_data which contains stack_canary at the appropriate
- * offset.  On x86_32, the stack canary is just a regular percpu
- * variable.
- *
- * Putting percpu data in %fs on 32-bit is a minor optimization compared to
- * using %gs.  Since 32-bit userspace normally has %fs == 0, we are likely
- * to load 0 into %fs on exit to usermode, whereas with percpu data in
- * %gs, we are likely to load a non-null %gs on return to user mode.
- *
- * Once we are willing to require GCC 8.1 or better for 64-bit stackprotector
- * support, we can remove some of this complexity.
+ * returning from the function.  The pattern is called the stack canary
+ * and is a unique value for each task.
  */
 
 #ifndef _ASM_STACKPROTECTOR_H
@@ -36,6 +20,8 @@
 
 #include <linux/sched.h>
 
+DECLARE_PER_CPU(unsigned long, __stack_chk_guard);
+
 /*
  * Initialize the stackprotector canary value.
  *
@@ -51,25 +37,13 @@ static __always_inline void boot_init_stack_canary(void)
 {
 	unsigned long canary = get_random_canary();
 
-#ifdef CONFIG_X86_64
-	BUILD_BUG_ON(offsetof(struct fixed_percpu_data, stack_canary) != 40);
-#endif
-
 	current->stack_canary = canary;
-#ifdef CONFIG_X86_64
-	this_cpu_write(fixed_percpu_data.stack_canary, canary);
-#else
 	this_cpu_write(__stack_chk_guard, canary);
-#endif
 }
 
 static inline void cpu_init_stack_canary(int cpu, struct task_struct *idle)
 {
-#ifdef CONFIG_X86_64
-	per_cpu(fixed_percpu_data.stack_canary, cpu) = idle->stack_canary;
-#else
 	per_cpu(__stack_chk_guard, cpu) = idle->stack_canary;
-#endif
 }
 
 #else	/* STACKPROTECTOR */
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index bb65371ea9df5..590b6cd0eac0e 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -54,11 +54,5 @@ int main(void)
 	BLANK();
 #undef ENTRY
 
-	BLANK();
-
-#ifdef CONFIG_STACKPROTECTOR
-	OFFSET(FIXED_stack_canary, fixed_percpu_data, stack_canary);
-	BLANK();
-#endif
 	return 0;
 }
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 7cce91b19fb2c..b71178f0ed6c6 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -2089,8 +2089,7 @@ void syscall_init(void)
 	if (!cpu_feature_enabled(X86_FEATURE_FRED))
 		idt_syscall_init();
 }
-
-#else	/* CONFIG_X86_64 */
+#endif /* CONFIG_X86_64 */
 
 #ifdef CONFIG_STACKPROTECTOR
 DEFINE_PER_CPU(unsigned long, __stack_chk_guard);
@@ -2099,8 +2098,6 @@ EXPORT_PER_CPU_SYMBOL(__stack_chk_guard);
 #endif
 #endif
 
-#endif	/* CONFIG_X86_64 */
-
 /*
  * Clear all 6 debug registers:
  */
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 31345e0ba0064..c3d73c04603f4 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -361,8 +361,7 @@ SYM_INNER_LABEL(common_startup_64, SYM_L_LOCAL)
 
 	/* Set up %gs.
 	 *
-	 * The base of %gs always points to fixed_percpu_data. If the
-	 * stack protector canary is enabled, it is located at %gs:40.
+	 * The base of %gs always points to fixed_percpu_data.
 	 * Note that, on SMP, the boot cpu uses init data section until
 	 * the per cpu areas are set up.
 	 */
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 894edf8d6d62f..a31b057e641e4 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -33,8 +33,7 @@ SYM_CODE_START(startup_xen)
 
 	/* Set up %gs.
 	 *
-	 * The base of %gs always points to fixed_percpu_data.  If the
-	 * stack protector canary is enabled, it is located at %gs:40.
+	 * The base of %gs always points to fixed_percpu_data.
 	 * Note that, on SMP, the boot cpu uses init data section until
 	 * the per cpu areas are set up.
 	 */

From 9d7de2aa8b41407bc96d89a80dc1fd637d389d42 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Thu, 23 Jan 2025 14:07:40 -0500
Subject: [PATCH 0210/1173] x86/percpu/64: Use relative percpu offsets

The percpu section is currently linked at absolute address 0, because
older compilers hard-coded the stack protector canary value at a fixed
offset from the start of the GS segment.  Now that the canary is a
normal percpu variable, the percpu section does not need to be linked
at a specific address.

x86-64 will now calculate the percpu offsets as the delta between the
initial percpu address and the dynamically allocated memory, like other
architectures.  Note that GSBASE is limited to the canonical address
width (48 or 57 bits, sign-extended).  As long as the kernel text,
modules, and the dynamically allocated percpu memory are all in the
negative address space, the delta will not overflow this limit.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250123190747.745588-9-brgerst@gmail.com
---
 arch/x86/include/asm/processor.h |  6 +++++-
 arch/x86/kernel/head_64.S        | 19 +++++++++----------
 arch/x86/kernel/setup_percpu.c   | 12 ++----------
 arch/x86/kernel/vmlinux.lds.S    | 29 +----------------------------
 arch/x86/platform/pvh/head.S     |  5 ++---
 arch/x86/tools/relocs.c          | 10 +++-------
 arch/x86/xen/xen-head.S          |  9 ++++-----
 init/Kconfig                     |  2 +-
 8 files changed, 27 insertions(+), 65 deletions(-)

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index a4687122951f7..b8fee88dac3d5 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -431,7 +431,11 @@ DECLARE_INIT_PER_CPU(fixed_percpu_data);
 
 static inline unsigned long cpu_kernelmode_gs_base(int cpu)
 {
-	return (unsigned long)per_cpu(fixed_percpu_data.gs_base, cpu);
+#ifdef CONFIG_SMP
+	return per_cpu_offset(cpu);
+#else
+	return 0;
+#endif
 }
 
 extern asmlinkage void entry_SYSCALL32_ignore(void);
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index c3d73c04603f4..2843b0a56198d 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -61,11 +61,14 @@ SYM_CODE_START_NOALIGN(startup_64)
 	/* Set up the stack for verify_cpu() */
 	leaq	__top_init_kernel_stack(%rip), %rsp
 
-	/* Setup GSBASE to allow stack canary access for C code */
+	/*
+	 * Set up GSBASE.
+	 * Note that on SMP the boot CPU uses the init data section until
+	 * the per-CPU areas are set up.
+	 */
 	movl	$MSR_GS_BASE, %ecx
-	leaq	INIT_PER_CPU_VAR(fixed_percpu_data)(%rip), %rdx
-	movl	%edx, %eax
-	shrq	$32,  %rdx
+	xorl	%eax, %eax
+	xorl	%edx, %edx
 	wrmsr
 
 	call	startup_64_setup_gdt_idt
@@ -359,16 +362,12 @@ SYM_INNER_LABEL(common_startup_64, SYM_L_LOCAL)
 	movl %eax,%fs
 	movl %eax,%gs
 
-	/* Set up %gs.
-	 *
-	 * The base of %gs always points to fixed_percpu_data.
+	/*
+	 * Set up GSBASE.
 	 * Note that, on SMP, the boot cpu uses init data section until
 	 * the per cpu areas are set up.
 	 */
 	movl	$MSR_GS_BASE,%ecx
-#ifndef CONFIG_SMP
-	leaq	INIT_PER_CPU_VAR(fixed_percpu_data)(%rip), %rdx
-#endif
 	movl	%edx, %eax
 	shrq	$32, %rdx
 	wrmsr
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index b30d6e180df7c..1e7be9409aa26 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -23,18 +23,10 @@
 #include <asm/cpumask.h>
 #include <asm/cpu.h>
 
-#ifdef CONFIG_X86_64
-#define BOOT_PERCPU_OFFSET ((unsigned long)__per_cpu_load)
-#else
-#define BOOT_PERCPU_OFFSET 0
-#endif
-
-DEFINE_PER_CPU_READ_MOSTLY(unsigned long, this_cpu_off) = BOOT_PERCPU_OFFSET;
+DEFINE_PER_CPU_READ_MOSTLY(unsigned long, this_cpu_off);
 EXPORT_PER_CPU_SYMBOL(this_cpu_off);
 
-unsigned long __per_cpu_offset[NR_CPUS] __ro_after_init = {
-	[0 ... NR_CPUS-1] = BOOT_PERCPU_OFFSET,
-};
+unsigned long __per_cpu_offset[NR_CPUS] __ro_after_init;
 EXPORT_SYMBOL(__per_cpu_offset);
 
 /*
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 0deb4887d6e96..8a598515239a5 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -112,12 +112,6 @@ ASSERT(__relocate_kernel_end - __relocate_kernel_start <= KEXEC_CONTROL_CODE_MAX
 PHDRS {
 	text PT_LOAD FLAGS(5);          /* R_E */
 	data PT_LOAD FLAGS(6);          /* RW_ */
-#ifdef CONFIG_X86_64
-#ifdef CONFIG_SMP
-	percpu PT_LOAD FLAGS(6);        /* RW_ */
-#endif
-	init PT_LOAD FLAGS(7);          /* RWE */
-#endif
 	note PT_NOTE FLAGS(0);          /* ___ */
 }
 
@@ -216,21 +210,7 @@ SECTIONS
 		__init_begin = .; /* paired with __init_end */
 	}
 
-#if defined(CONFIG_X86_64) && defined(CONFIG_SMP)
-	/*
-	 * percpu offsets are zero-based on SMP.  PERCPU_VADDR() changes the
-	 * output PHDR, so the next output section - .init.text - should
-	 * start another segment - init.
-	 */
-	PERCPU_VADDR(INTERNODE_CACHE_BYTES, 0, :percpu)
-	ASSERT(SIZEOF(.data..percpu) < CONFIG_PHYSICAL_START,
-	       "per-CPU data too large - increase CONFIG_PHYSICAL_START")
-#endif
-
 	INIT_TEXT_SECTION(PAGE_SIZE)
-#ifdef CONFIG_X86_64
-	:init
-#endif
 
 	/*
 	 * Section for code used exclusively before alternatives are run. All
@@ -347,9 +327,7 @@ SECTIONS
 		EXIT_DATA
 	}
 
-#if !defined(CONFIG_X86_64) || !defined(CONFIG_SMP)
 	PERCPU_SECTION(INTERNODE_CACHE_BYTES)
-#endif
 
 	RUNTIME_CONST_VARIABLES
 	RUNTIME_CONST(ptr, USER_PTR_MAX)
@@ -497,16 +475,11 @@ PROVIDE(__ref_stack_chk_guard = __stack_chk_guard);
  * Per-cpu symbols which need to be offset from __per_cpu_load
  * for the boot processor.
  */
-#define INIT_PER_CPU(x) init_per_cpu__##x = ABSOLUTE(x) + __per_cpu_load
+#define INIT_PER_CPU(x) init_per_cpu__##x = ABSOLUTE(x)
 INIT_PER_CPU(gdt_page);
 INIT_PER_CPU(fixed_percpu_data);
 INIT_PER_CPU(irq_stack_backing_store);
 
-#ifdef CONFIG_SMP
-. = ASSERT((fixed_percpu_data == 0),
-           "fixed_percpu_data is not at start of per-cpu area");
-#endif
-
 #ifdef CONFIG_MITIGATION_UNRET_ENTRY
 . = ASSERT((retbleed_return_thunk & 0x3f) == 0, "retbleed_return_thunk not cacheline-aligned");
 #endif
diff --git a/arch/x86/platform/pvh/head.S b/arch/x86/platform/pvh/head.S
index 723f181b222ab..cfa18ec7d55f1 100644
--- a/arch/x86/platform/pvh/head.S
+++ b/arch/x86/platform/pvh/head.S
@@ -179,9 +179,8 @@ SYM_CODE_START(pvh_start_xen)
 	 * the per-CPU areas are set up.
 	 */
 	movl $MSR_GS_BASE,%ecx
-	leaq INIT_PER_CPU_VAR(fixed_percpu_data)(%rip), %rdx
-	movq %edx, %eax
-	shrq $32, %rdx
+	xorl %eax, %eax
+	xorl %edx, %edx
 	wrmsr
 
 	/* Call xen_prepare_pvh() via the kernel virtual mapping */
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index 92a1e503305ef..3cb3b30b67061 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -835,12 +835,7 @@ static void percpu_init(void)
  */
 static int is_percpu_sym(ElfW(Sym) *sym, const char *symname)
 {
-	int shndx = sym_index(sym);
-
-	return (shndx == per_cpu_shndx) &&
-		strcmp(symname, "__init_begin") &&
-		strcmp(symname, "__per_cpu_load") &&
-		strncmp(symname, "init_per_cpu_", 13);
+	return 0;
 }
 
 
@@ -1062,7 +1057,8 @@ static int cmp_relocs(const void *va, const void *vb)
 
 static void sort_relocs(struct relocs *r)
 {
-	qsort(r->offset, r->count, sizeof(r->offset[0]), cmp_relocs);
+	if (r->count)
+		qsort(r->offset, r->count, sizeof(r->offset[0]), cmp_relocs);
 }
 
 static int write32(uint32_t v, FILE *f)
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index a31b057e641e4..5ccb4c54e2415 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -31,15 +31,14 @@ SYM_CODE_START(startup_xen)
 
 	leaq	__top_init_kernel_stack(%rip), %rsp
 
-	/* Set up %gs.
-	 *
-	 * The base of %gs always points to fixed_percpu_data.
+	/*
+	 * Set up GSBASE.
 	 * Note that, on SMP, the boot cpu uses init data section until
 	 * the per cpu areas are set up.
 	 */
 	movl	$MSR_GS_BASE,%ecx
-	movq	$INIT_PER_CPU_VAR(fixed_percpu_data),%rax
-	cdq
+	xorl	%eax, %eax
+	xorl	%edx, %edx
 	wrmsr
 
 	mov	%rsi, %rdi
diff --git a/init/Kconfig b/init/Kconfig
index d0d021b3fa3b3..b5d9c0fa69f67 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1872,7 +1872,7 @@ config KALLSYMS_ALL
 config KALLSYMS_ABSOLUTE_PERCPU
 	bool
 	depends on KALLSYMS
-	default X86_64 && SMP
+	default n
 
 # end of the "standard kernel features (expert users)" menu
 

From b5c4f95351a097a635c1a7fc8d9efa18308491b5 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Thu, 23 Jan 2025 14:07:41 -0500
Subject: [PATCH 0211/1173] x86/percpu/64: Remove fixed_percpu_data

Now that the stack protector canary value is a normal percpu variable,
fixed_percpu_data is unused and can be removed.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250123190747.745588-10-brgerst@gmail.com
---
 arch/x86/include/asm/processor.h | 8 --------
 arch/x86/kernel/cpu/common.c     | 4 ----
 arch/x86/kernel/vmlinux.lds.S    | 1 -
 arch/x86/tools/relocs.c          | 1 -
 4 files changed, 14 deletions(-)

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index b8fee88dac3d5..b3d153730f63b 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -421,14 +421,6 @@ struct irq_stack {
 } __aligned(IRQ_STACK_SIZE);
 
 #ifdef CONFIG_X86_64
-struct fixed_percpu_data {
-	char		gs_base[40];
-	unsigned long	reserved;
-};
-
-DECLARE_PER_CPU_FIRST(struct fixed_percpu_data, fixed_percpu_data) __visible;
-DECLARE_INIT_PER_CPU(fixed_percpu_data);
-
 static inline unsigned long cpu_kernelmode_gs_base(int cpu)
 {
 #ifdef CONFIG_SMP
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index b71178f0ed6c6..8b49b1338f762 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -2023,10 +2023,6 @@ EXPORT_PER_CPU_SYMBOL(pcpu_hot);
 EXPORT_PER_CPU_SYMBOL(const_pcpu_hot);
 
 #ifdef CONFIG_X86_64
-DEFINE_PER_CPU_FIRST(struct fixed_percpu_data,
-		     fixed_percpu_data) __aligned(PAGE_SIZE) __visible;
-EXPORT_PER_CPU_SYMBOL_GPL(fixed_percpu_data);
-
 static void wrmsrl_cstar(unsigned long val)
 {
 	/*
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 8a598515239a5..93c2fa8a7522e 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -477,7 +477,6 @@ PROVIDE(__ref_stack_chk_guard = __stack_chk_guard);
  */
 #define INIT_PER_CPU(x) init_per_cpu__##x = ABSOLUTE(x)
 INIT_PER_CPU(gdt_page);
-INIT_PER_CPU(fixed_percpu_data);
 INIT_PER_CPU(irq_stack_backing_store);
 
 #ifdef CONFIG_MITIGATION_UNRET_ENTRY
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index 3cb3b30b67061..b5e3695a06158 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -830,7 +830,6 @@ static void percpu_init(void)
  *	__per_cpu_load
  *
  * The "gold" linker incorrectly associates:
- *	init_per_cpu__fixed_percpu_data
  *	init_per_cpu__gdt_page
  */
 static int is_percpu_sym(ElfW(Sym) *sym, const char *symname)

From a8327be7b2aa067ff2b11551732d5bd8b49ef7d1 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Thu, 23 Jan 2025 14:07:42 -0500
Subject: [PATCH 0212/1173] x86/boot/64: Remove inverse relocations

Inverse relocations were needed to offset the effects of relocation for
RIP-relative accesses to zero-based percpu data.  Now that the percpu
section is linked normally as part of the kernel image, they are no
longer needed.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250123190747.745588-11-brgerst@gmail.com
---
 arch/x86/boot/compressed/misc.c |  14 +---
 arch/x86/tools/relocs.c         | 130 +-------------------------------
 2 files changed, 2 insertions(+), 142 deletions(-)

diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 0d37420cad025..1cdcd4aaf3955 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -235,7 +235,7 @@ static void handle_relocations(void *output, unsigned long output_len,
 
 	/*
 	 * Process relocations: 32 bit relocations first then 64 bit after.
-	 * Three sets of binary relocations are added to the end of the kernel
+	 * Two sets of binary relocations are added to the end of the kernel
 	 * before compression. Each relocation table entry is the kernel
 	 * address of the location which needs to be updated stored as a
 	 * 32-bit value which is sign extended to 64 bits.
@@ -245,8 +245,6 @@ static void handle_relocations(void *output, unsigned long output_len,
 	 * kernel bits...
 	 * 0 - zero terminator for 64 bit relocations
 	 * 64 bit relocation repeated
-	 * 0 - zero terminator for inverse 32 bit relocations
-	 * 32 bit inverse relocation repeated
 	 * 0 - zero terminator for 32 bit relocations
 	 * 32 bit relocation repeated
 	 *
@@ -263,16 +261,6 @@ static void handle_relocations(void *output, unsigned long output_len,
 		*(uint32_t *)ptr += delta;
 	}
 #ifdef CONFIG_X86_64
-	while (*--reloc) {
-		long extended = *reloc;
-		extended += map;
-
-		ptr = (unsigned long)extended;
-		if (ptr < min_addr || ptr > max_addr)
-			error("inverse 32-bit relocation outside of kernel!\n");
-
-		*(int32_t *)ptr -= delta;
-	}
 	for (reloc--; *reloc; reloc--) {
 		long extended = *reloc;
 		extended += map;
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index b5e3695a06158..ae6962665b351 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -29,7 +29,6 @@ static struct relocs		relocs16;
 static struct relocs		relocs32;
 
 #if ELF_BITS == 64
-static struct relocs		relocs32neg;
 static struct relocs		relocs64;
 # define FMT PRIu64
 
@@ -91,7 +90,6 @@ static const char * const	sym_regex_kernel[S_NSYMTYPES] = {
 	"__initramfs_start|"
 	"(jiffies|jiffies_64)|"
 #if ELF_BITS == 64
-	"__per_cpu_load|"
 	"init_per_cpu__.*|"
 	"__end_rodata_hpage_align|"
 #endif
@@ -290,34 +288,6 @@ static const char *sym_name(const char *sym_strtab, Elf_Sym *sym)
 	return name;
 }
 
-static Elf_Sym *sym_lookup(const char *symname)
-{
-	int i;
-
-	for (i = 0; i < shnum; i++) {
-		struct section *sec = &secs[i];
-		long nsyms;
-		char *strtab;
-		Elf_Sym *symtab;
-		Elf_Sym *sym;
-
-		if (sec->shdr.sh_type != SHT_SYMTAB)
-			continue;
-
-		nsyms = sec->shdr.sh_size/sizeof(Elf_Sym);
-		symtab = sec->symtab;
-		strtab = sec->link->strtab;
-
-		for (sym = symtab; --nsyms >= 0; sym++) {
-			if (!sym->st_name)
-				continue;
-			if (strcmp(symname, strtab + sym->st_name) == 0)
-				return sym;
-		}
-	}
-	return 0;
-}
-
 #if BYTE_ORDER == LITTLE_ENDIAN
 # define le16_to_cpu(val)	(val)
 # define le32_to_cpu(val)	(val)
@@ -766,78 +736,8 @@ static void walk_relocs(int (*process)(struct section *sec, Elf_Rel *rel,
 	}
 }
 
-/*
- * The .data..percpu section is a special case for x86_64 SMP kernels.
- * It is used to initialize the actual per_cpu areas and to provide
- * definitions for the per_cpu variables that correspond to their offsets
- * within the percpu area. Since the values of all of the symbols need
- * to be offsets from the start of the per_cpu area the virtual address
- * (sh_addr) of .data..percpu is 0 in SMP kernels.
- *
- * This means that:
- *
- *	Relocations that reference symbols in the per_cpu area do not
- *	need further relocation (since the value is an offset relative
- *	to the start of the per_cpu area that does not change).
- *
- *	Relocations that apply to the per_cpu area need to have their
- *	offset adjusted by by the value of __per_cpu_load to make them
- *	point to the correct place in the loaded image (because the
- *	virtual address of .data..percpu is 0).
- *
- * For non SMP kernels .data..percpu is linked as part of the normal
- * kernel data and does not require special treatment.
- *
- */
-static int per_cpu_shndx = -1;
-static Elf_Addr per_cpu_load_addr;
-
-static void percpu_init(void)
-{
-	int i;
-
-	for (i = 0; i < shnum; i++) {
-		ElfW(Sym) *sym;
-
-		if (strcmp(sec_name(i), ".data..percpu"))
-			continue;
-
-		if (secs[i].shdr.sh_addr != 0)	/* non SMP kernel */
-			return;
-
-		sym = sym_lookup("__per_cpu_load");
-		if (!sym)
-			die("can't find __per_cpu_load\n");
-
-		per_cpu_shndx = i;
-		per_cpu_load_addr = sym->st_value;
-
-		return;
-	}
-}
-
 #if ELF_BITS == 64
 
-/*
- * Check to see if a symbol lies in the .data..percpu section.
- *
- * The linker incorrectly associates some symbols with the
- * .data..percpu section so we also need to check the symbol
- * name to make sure that we classify the symbol correctly.
- *
- * The GNU linker incorrectly associates:
- *	__init_begin
- *	__per_cpu_load
- *
- * The "gold" linker incorrectly associates:
- *	init_per_cpu__gdt_page
- */
-static int is_percpu_sym(ElfW(Sym) *sym, const char *symname)
-{
-	return 0;
-}
-
-
 static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym,
 		      const char *symname)
 {
@@ -848,12 +748,6 @@ static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym,
 	if (sym->st_shndx == SHN_UNDEF)
 		return 0;
 
-	/*
-	 * Adjust the offset if this reloc applies to the percpu section.
-	 */
-	if (sec->shdr.sh_info == per_cpu_shndx)
-		offset += per_cpu_load_addr;
-
 	switch (r_type) {
 	case R_X86_64_NONE:
 		/* NONE can be ignored. */
@@ -863,32 +757,21 @@ static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym,
 	case R_X86_64_PLT32:
 	case R_X86_64_REX_GOTPCRELX:
 		/*
-		 * PC relative relocations don't need to be adjusted unless
-		 * referencing a percpu symbol.
+		 * PC relative relocations don't need to be adjusted.
 		 *
 		 * NB: R_X86_64_PLT32 can be treated as R_X86_64_PC32.
 		 */
-		if (is_percpu_sym(sym, symname))
-			add_reloc(&relocs32neg, offset);
 		break;
 
 	case R_X86_64_PC64:
 		/*
 		 * Only used by jump labels
 		 */
-		if (is_percpu_sym(sym, symname))
-			die("Invalid R_X86_64_PC64 relocation against per-CPU symbol %s\n", symname);
 		break;
 
 	case R_X86_64_32:
 	case R_X86_64_32S:
 	case R_X86_64_64:
-		/*
-		 * References to the percpu area don't need to be adjusted.
-		 */
-		if (is_percpu_sym(sym, symname))
-			break;
-
 		if (shn_abs) {
 			/*
 			 * Whitelisted absolute symbols do not require
@@ -1101,7 +984,6 @@ static void emit_relocs(int as_text, int use_real_mode)
 	/* Order the relocations for more efficient processing */
 	sort_relocs(&relocs32);
 #if ELF_BITS == 64
-	sort_relocs(&relocs32neg);
 	sort_relocs(&relocs64);
 #else
 	sort_relocs(&relocs16);
@@ -1133,13 +1015,6 @@ static void emit_relocs(int as_text, int use_real_mode)
 		/* Now print each relocation */
 		for (i = 0; i < relocs64.count; i++)
 			write_reloc(relocs64.offset[i], stdout);
-
-		/* Print a stop */
-		write_reloc(0, stdout);
-
-		/* Now print each inverse 32-bit relocation */
-		for (i = 0; i < relocs32neg.count; i++)
-			write_reloc(relocs32neg.offset[i], stdout);
 #endif
 
 		/* Print a stop */
@@ -1192,9 +1067,6 @@ void process(FILE *fp, int use_real_mode, int as_text,
 	read_symtabs(fp);
 	read_relocs(fp);
 
-	if (ELF_BITS == 64)
-		percpu_init();
-
 	if (show_absolute_syms) {
 		print_absolute_symbols();
 		return;

From 38a4968b3190f873a8a60e953287278eddf037f1 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Thu, 23 Jan 2025 14:07:43 -0500
Subject: [PATCH 0213/1173] x86/percpu/64: Remove INIT_PER_CPU macros

Now that the load and link addresses of percpu variables are the same,
these macros are no longer necessary.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250123190747.745588-12-brgerst@gmail.com
---
 arch/x86/include/asm/desc.h   |  1 -
 arch/x86/include/asm/percpu.h | 22 ----------------------
 arch/x86/kernel/head64.c      |  2 +-
 arch/x86/kernel/irq_64.c      |  1 -
 arch/x86/kernel/vmlinux.lds.S |  7 -------
 arch/x86/tools/relocs.c       |  1 -
 6 files changed, 1 insertion(+), 33 deletions(-)

diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index 62dc9f59ea768..ec95fe44fa3a0 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -46,7 +46,6 @@ struct gdt_page {
 } __attribute__((aligned(PAGE_SIZE)));
 
 DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page);
-DECLARE_INIT_PER_CPU(gdt_page);
 
 /* Provide the original GDT */
 static inline struct desc_struct *get_cpu_gdt_rw(unsigned int cpu)
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index e525cd85f999f..1a76eb87c5d86 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -20,12 +20,6 @@
 
 #define PER_CPU_VAR(var)	__percpu(var)__percpu_rel
 
-#ifdef CONFIG_X86_64_SMP
-# define INIT_PER_CPU_VAR(var)  init_per_cpu__##var
-#else
-# define INIT_PER_CPU_VAR(var)  var
-#endif
-
 #else /* !__ASSEMBLY__: */
 
 #include <linux/build_bug.h>
@@ -97,22 +91,6 @@
 #define __percpu_arg(x)		__percpu_prefix "%" #x
 #define __force_percpu_arg(x)	__force_percpu_prefix "%" #x
 
-/*
- * Initialized pointers to per-CPU variables needed for the boot
- * processor need to use these macros to get the proper address
- * offset from __per_cpu_load on SMP.
- *
- * There also must be an entry in vmlinux_64.lds.S
- */
-#define DECLARE_INIT_PER_CPU(var) \
-       extern typeof(var) init_per_cpu_var(var)
-
-#ifdef CONFIG_X86_64_SMP
-# define init_per_cpu_var(var)  init_per_cpu__##var
-#else
-# define init_per_cpu_var(var)  var
-#endif
-
 /*
  * For arch-specific code, we can use direct single-insn ops (they
  * don't give an lvalue though).
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 22c9ba305ac17..05f8b8acf7845 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -567,7 +567,7 @@ void early_setup_idt(void)
  */
 void __head startup_64_setup_gdt_idt(void)
 {
-	struct desc_struct *gdt = (void *)(__force unsigned long)init_per_cpu_var(gdt_page.gdt);
+	struct desc_struct *gdt = (void *)(__force unsigned long)gdt_page.gdt;
 	void *handler = NULL;
 
 	struct desc_ptr startup_gdt_descr = {
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index ade0043ce56ef..56bdeecd8ee02 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -27,7 +27,6 @@
 #include <asm/apic.h>
 
 DEFINE_PER_CPU_PAGE_ALIGNED(struct irq_stack, irq_stack_backing_store) __visible;
-DECLARE_INIT_PER_CPU(irq_stack_backing_store);
 
 #ifdef CONFIG_VMAP_STACK
 /*
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 93c2fa8a7522e..1769a7126224c 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -471,13 +471,6 @@ SECTIONS
 PROVIDE(__ref_stack_chk_guard = __stack_chk_guard);
 
 #ifdef CONFIG_X86_64
-/*
- * Per-cpu symbols which need to be offset from __per_cpu_load
- * for the boot processor.
- */
-#define INIT_PER_CPU(x) init_per_cpu__##x = ABSOLUTE(x)
-INIT_PER_CPU(gdt_page);
-INIT_PER_CPU(irq_stack_backing_store);
 
 #ifdef CONFIG_MITIGATION_UNRET_ENTRY
 . = ASSERT((retbleed_return_thunk & 0x3f) == 0, "retbleed_return_thunk not cacheline-aligned");
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index ae6962665b351..5778bc4984153 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -90,7 +90,6 @@ static const char * const	sym_regex_kernel[S_NSYMTYPES] = {
 	"__initramfs_start|"
 	"(jiffies|jiffies_64)|"
 #if ELF_BITS == 64
-	"init_per_cpu__.*|"
 	"__end_rodata_hpage_align|"
 #endif
 	"_end)$"

From 95b0916118106054e1f3d5d7f8628ef3dc0b3c02 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Thu, 23 Jan 2025 14:07:44 -0500
Subject: [PATCH 0214/1173] percpu: Remove PER_CPU_FIRST_SECTION

x86-64 was the last user.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250123190747.745588-13-brgerst@gmail.com
---
 include/asm-generic/vmlinux.lds.h |  1 -
 include/linux/percpu-defs.h       | 12 ------------
 2 files changed, 13 deletions(-)

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 02a4adb4a9999..a3c77a1065658 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -1062,7 +1062,6 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
  */
 #define PERCPU_INPUT(cacheline)						\
 	__per_cpu_start = .;						\
-	*(.data..percpu..first)						\
 	. = ALIGN(PAGE_SIZE);						\
 	*(.data..percpu..page_aligned)					\
 	. = ALIGN(cacheline);						\
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index 5b520fe86b609..40d34e032d5b8 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -26,13 +26,11 @@
 #define PER_CPU_SHARED_ALIGNED_SECTION "..shared_aligned"
 #define PER_CPU_ALIGNED_SECTION "..shared_aligned"
 #endif
-#define PER_CPU_FIRST_SECTION "..first"
 
 #else
 
 #define PER_CPU_SHARED_ALIGNED_SECTION ""
 #define PER_CPU_ALIGNED_SECTION "..shared_aligned"
-#define PER_CPU_FIRST_SECTION ""
 
 #endif
 
@@ -114,16 +112,6 @@
 #define DEFINE_PER_CPU(type, name)					\
 	DEFINE_PER_CPU_SECTION(type, name, "")
 
-/*
- * Declaration/definition used for per-CPU variables that must come first in
- * the set of variables.
- */
-#define DECLARE_PER_CPU_FIRST(type, name)				\
-	DECLARE_PER_CPU_SECTION(type, name, PER_CPU_FIRST_SECTION)
-
-#define DEFINE_PER_CPU_FIRST(type, name)				\
-	DEFINE_PER_CPU_SECTION(type, name, PER_CPU_FIRST_SECTION)
-
 /*
  * Declaration/definition used for per-CPU variables that must be cacheline
  * aligned under SMP conditions so that, whilst a particular instance of the

From e23cff6861781ac4e15de6c7bf2d2a0b79cb52ef Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Thu, 23 Jan 2025 14:07:45 -0500
Subject: [PATCH 0215/1173] percpu: Remove PERCPU_VADDR()

x86-64 was the last user.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250123190747.745588-14-brgerst@gmail.com
---
 include/asm-generic/vmlinux.lds.h | 36 +------------------------------
 1 file changed, 1 insertion(+), 35 deletions(-)

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index a3c77a1065658..e25a8aeee29c4 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -1073,47 +1073,13 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
 	__per_cpu_end = .;
 
 /**
- * PERCPU_VADDR - define output section for percpu area
+ * PERCPU_SECTION - define output section for percpu area
  * @cacheline: cacheline size
- * @vaddr: explicit base address (optional)
- * @phdr: destination PHDR (optional)
  *
  * Macro which expands to output section for percpu area.
  *
  * @cacheline is used to align subsections to avoid false cacheline
  * sharing between subsections for different purposes.
- *
- * If @vaddr is not blank, it specifies explicit base address and all
- * percpu symbols will be offset from the given address.  If blank,
- * @vaddr always equals @laddr + LOAD_OFFSET.
- *
- * @phdr defines the output PHDR to use if not blank.  Be warned that
- * output PHDR is sticky.  If @phdr is specified, the next output
- * section in the linker script will go there too.  @phdr should have
- * a leading colon.
- *
- * Note that this macros defines __per_cpu_load as an absolute symbol.
- * If there is no need to put the percpu section at a predetermined
- * address, use PERCPU_SECTION.
- */
-#define PERCPU_VADDR(cacheline, vaddr, phdr)				\
-	__per_cpu_load = .;						\
-	.data..percpu vaddr : AT(__per_cpu_load - LOAD_OFFSET) {	\
-		PERCPU_INPUT(cacheline)					\
-	} phdr								\
-	. = __per_cpu_load + SIZEOF(.data..percpu);
-
-/**
- * PERCPU_SECTION - define output section for percpu area, simple version
- * @cacheline: cacheline size
- *
- * Align to PAGE_SIZE and outputs output section for percpu area.  This
- * macro doesn't manipulate @vaddr or @phdr and __per_cpu_load and
- * __per_cpu_start will be identical.
- *
- * This macro is equivalent to ALIGN(PAGE_SIZE); PERCPU_VADDR(@cacheline,,)
- * except that __per_cpu_load is defined as a relative symbol against
- * .data..percpu which is required for relocatable x86_32 configuration.
  */
 #define PERCPU_SECTION(cacheline)					\
 	. = ALIGN(PAGE_SIZE);						\

From 4b00c1160a13d8bf7297ebf49ec07a84e1f41132 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Thu, 23 Jan 2025 14:07:46 -0500
Subject: [PATCH 0216/1173] percpu: Remove __per_cpu_load

__per_cpu_load is now always equal to __per_cpu_start.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250123190747.745588-15-brgerst@gmail.com
---
 include/asm-generic/sections.h    | 2 +-
 include/asm-generic/vmlinux.lds.h | 1 -
 mm/percpu.c                       | 4 ++--
 3 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
index c768de6f19a9a..0755bc39b0d80 100644
--- a/include/asm-generic/sections.h
+++ b/include/asm-generic/sections.h
@@ -39,7 +39,7 @@ extern char __init_begin[], __init_end[];
 extern char _sinittext[], _einittext[];
 extern char __start_ro_after_init[], __end_ro_after_init[];
 extern char _end[];
-extern char __per_cpu_load[], __per_cpu_start[], __per_cpu_end[];
+extern char __per_cpu_start[], __per_cpu_end[];
 extern char __kprobes_text_start[], __kprobes_text_end[];
 extern char __entry_text_start[], __entry_text_end[];
 extern char __start_rodata[], __end_rodata[];
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index e25a8aeee29c4..92fc06f7da742 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -1084,7 +1084,6 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
 #define PERCPU_SECTION(cacheline)					\
 	. = ALIGN(PAGE_SIZE);						\
 	.data..percpu	: AT(ADDR(.data..percpu) - LOAD_OFFSET) {	\
-		__per_cpu_load = .;					\
 		PERCPU_INPUT(cacheline)					\
 	}
 
diff --git a/mm/percpu.c b/mm/percpu.c
index ac61e3fc5f151..7b5835356d1e1 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -3071,7 +3071,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
 				continue;
 			}
 			/* copy and return the unused part */
-			memcpy(ptr, __per_cpu_load, ai->static_size);
+			memcpy(ptr, __per_cpu_start, ai->static_size);
 			pcpu_fc_free(ptr + size_sum, ai->unit_size - size_sum);
 		}
 	}
@@ -3240,7 +3240,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_cpu_to_node_fn_t
 		flush_cache_vmap_early(unit_addr, unit_addr + ai->unit_size);
 
 		/* copy static data */
-		memcpy((void *)unit_addr, __per_cpu_load, ai->static_size);
+		memcpy((void *)unit_addr, __per_cpu_start, ai->static_size);
 	}
 
 	/* we're ready, commit */

From 01157ddc58dc2fe428ec17dd5a18cc13f134639f Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Thu, 23 Jan 2025 14:07:47 -0500
Subject: [PATCH 0217/1173] kallsyms: Remove KALLSYMS_ABSOLUTE_PERCPU

x86-64 was the only user.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250123190747.745588-16-brgerst@gmail.com
---
 init/Kconfig            |  5 ---
 kernel/kallsyms.c       | 12 ++-----
 scripts/kallsyms.c      | 72 +++++++----------------------------------
 scripts/link-vmlinux.sh |  4 ---
 4 files changed, 14 insertions(+), 79 deletions(-)

diff --git a/init/Kconfig b/init/Kconfig
index b5d9c0fa69f67..a0ea04c177842 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1869,11 +1869,6 @@ config KALLSYMS_ALL
 
 	  Say N unless you really need all symbols, or kernel live patching.
 
-config KALLSYMS_ABSOLUTE_PERCPU
-	bool
-	depends on KALLSYMS
-	default n
-
 # end of the "standard kernel features (expert users)" menu
 
 config ARCH_HAS_MEMBARRIER_CALLBACKS
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index a9a0ca605d4a8..4198f30aac3ca 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -148,16 +148,8 @@ static unsigned int get_symbol_offset(unsigned long pos)
 
 unsigned long kallsyms_sym_address(int idx)
 {
-	/* values are unsigned offsets if --absolute-percpu is not in effect */
-	if (!IS_ENABLED(CONFIG_KALLSYMS_ABSOLUTE_PERCPU))
-		return kallsyms_relative_base + (u32)kallsyms_offsets[idx];
-
-	/* ...otherwise, positive offsets are absolute values */
-	if (kallsyms_offsets[idx] >= 0)
-		return kallsyms_offsets[idx];
-
-	/* ...and negative offsets are relative to kallsyms_relative_base - 1 */
-	return kallsyms_relative_base - 1 - kallsyms_offsets[idx];
+	/* values are unsigned offsets */
+	return kallsyms_relative_base + (u32)kallsyms_offsets[idx];
 }
 
 static unsigned int get_symbol_seq(int index)
diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c
index 03852da3d2490..4b0234e4b12f3 100644
--- a/scripts/kallsyms.c
+++ b/scripts/kallsyms.c
@@ -5,7 +5,7 @@
  * This software may be used and distributed according to the terms
  * of the GNU General Public License, incorporated herein by reference.
  *
- * Usage: kallsyms [--all-symbols] [--absolute-percpu]  in.map > out.S
+ * Usage: kallsyms [--all-symbols] in.map > out.S
  *
  *      Table compression uses all the unused char codes on the symbols and
  *  maps these to the most used substrings (tokens). For instance, it might
@@ -37,7 +37,6 @@ struct sym_entry {
 	unsigned long long addr;
 	unsigned int len;
 	unsigned int seq;
-	bool percpu_absolute;
 	unsigned char sym[];
 };
 
@@ -55,14 +54,9 @@ static struct addr_range text_ranges[] = {
 #define text_range_text     (&text_ranges[0])
 #define text_range_inittext (&text_ranges[1])
 
-static struct addr_range percpu_range = {
-	"__per_cpu_start", "__per_cpu_end", -1ULL, 0
-};
-
 static struct sym_entry **table;
 static unsigned int table_size, table_cnt;
 static int all_symbols;
-static int absolute_percpu;
 
 static int token_profit[0x10000];
 
@@ -73,7 +67,7 @@ static unsigned char best_table_len[256];
 
 static void usage(void)
 {
-	fprintf(stderr, "Usage: kallsyms [--all-symbols] [--absolute-percpu] in.map > out.S\n");
+	fprintf(stderr, "Usage: kallsyms [--all-symbols] in.map > out.S\n");
 	exit(1);
 }
 
@@ -164,7 +158,6 @@ static struct sym_entry *read_symbol(FILE *in, char **buf, size_t *buf_len)
 		return NULL;
 
 	check_symbol_range(name, addr, text_ranges, ARRAY_SIZE(text_ranges));
-	check_symbol_range(name, addr, &percpu_range, 1);
 
 	/* include the type field in the symbol name, so that it gets
 	 * compressed together */
@@ -175,7 +168,6 @@ static struct sym_entry *read_symbol(FILE *in, char **buf, size_t *buf_len)
 	sym->len = len;
 	sym->sym[0] = type;
 	strcpy(sym_name(sym), name);
-	sym->percpu_absolute = false;
 
 	return sym;
 }
@@ -319,11 +311,6 @@ static int expand_symbol(const unsigned char *data, int len, char *result)
 	return total;
 }
 
-static bool symbol_absolute(const struct sym_entry *s)
-{
-	return s->percpu_absolute;
-}
-
 static int compare_names(const void *a, const void *b)
 {
 	int ret;
@@ -455,22 +442,11 @@ static void write_src(void)
 		 */
 
 		long long offset;
-		bool overflow;
-
-		if (!absolute_percpu) {
-			offset = table[i]->addr - relative_base;
-			overflow = offset < 0 || offset > UINT_MAX;
-		} else if (symbol_absolute(table[i])) {
-			offset = table[i]->addr;
-			overflow = offset < 0 || offset > INT_MAX;
-		} else {
-			offset = relative_base - table[i]->addr - 1;
-			overflow = offset < INT_MIN || offset >= 0;
-		}
-		if (overflow) {
+
+		offset = table[i]->addr - relative_base;
+		if (offset < 0 || offset > UINT_MAX) {
 			fprintf(stderr, "kallsyms failure: "
-				"%s symbol value %#llx out of range in relative mode\n",
-				symbol_absolute(table[i]) ? "absolute" : "relative",
+				"relative symbol value %#llx out of range\n",
 				table[i]->addr);
 			exit(EXIT_FAILURE);
 		}
@@ -725,36 +701,15 @@ static void sort_symbols(void)
 	qsort(table, table_cnt, sizeof(table[0]), compare_symbols);
 }
 
-static void make_percpus_absolute(void)
-{
-	unsigned int i;
-
-	for (i = 0; i < table_cnt; i++)
-		if (symbol_in_range(table[i], &percpu_range, 1)) {
-			/*
-			 * Keep the 'A' override for percpu symbols to
-			 * ensure consistent behavior compared to older
-			 * versions of this tool.
-			 */
-			table[i]->sym[0] = 'A';
-			table[i]->percpu_absolute = true;
-		}
-}
-
 /* find the minimum non-absolute symbol address */
 static void record_relative_base(void)
 {
-	unsigned int i;
-
-	for (i = 0; i < table_cnt; i++)
-		if (!symbol_absolute(table[i])) {
-			/*
-			 * The table is sorted by address.
-			 * Take the first non-absolute symbol value.
-			 */
-			relative_base = table[i]->addr;
-			return;
-		}
+	/*
+	 * The table is sorted by address.
+	 * Take the first symbol value.
+	 */
+	if (table_cnt)
+		relative_base = table[0]->addr;
 }
 
 int main(int argc, char **argv)
@@ -762,7 +717,6 @@ int main(int argc, char **argv)
 	while (1) {
 		static const struct option long_options[] = {
 			{"all-symbols",     no_argument, &all_symbols,     1},
-			{"absolute-percpu", no_argument, &absolute_percpu, 1},
 			{},
 		};
 
@@ -779,8 +733,6 @@ int main(int argc, char **argv)
 
 	read_map(argv[optind]);
 	shrink_table();
-	if (absolute_percpu)
-		make_percpus_absolute();
 	sort_symbols();
 	record_relative_base();
 	optimize_token_table();
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index 56a077d204cfa..67e66333bd2a3 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -144,10 +144,6 @@ kallsyms()
 		kallsymopt="${kallsymopt} --all-symbols"
 	fi
 
-	if is_enabled CONFIG_KALLSYMS_ABSOLUTE_PERCPU; then
-		kallsymopt="${kallsymopt} --absolute-percpu"
-	fi
-
 	info KSYMS "${2}.S"
 	scripts/kallsyms ${kallsymopt} "${1}" > "${2}.S"
 

From c97f85ddd60a5a87058ddc1054f0396c3524ae0f Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:38:45 +0100
Subject: [PATCH 0218/1173] KVM: MIPS: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/34004267eba24388fb50ef6de1b8dd7addba6475.1738746821.git.namcao@linutronix.de
---
 arch/mips/kvm/mips.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 60b43ea85c125..cef3c423a41ae 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -288,9 +288,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	if (err)
 		return err;
 
-	hrtimer_init(&vcpu->arch.comparecount_timer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_REL);
-	vcpu->arch.comparecount_timer.function = kvm_mips_comparecount_wakeup;
+	hrtimer_setup(&vcpu->arch.comparecount_timer, kvm_mips_comparecount_wakeup, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 
 	/*
 	 * Allocate space for host mode exception handlers that handle

From a0241210a3f3950bf4a28b5077108c8a126d47ec Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:38:46 +0100
Subject: [PATCH 0219/1173] KVM: PPC: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/a58c4f16b1cfba13f96201fda355553850a97562.1738746821.git.namcao@linutronix.de
---
 arch/powerpc/kvm/powerpc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index ce1d91eed231b..61f2b7e007fad 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -766,8 +766,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 {
 	int err;
 
-	hrtimer_init(&vcpu->arch.dec_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
-	vcpu->arch.dec_timer.function = kvmppc_decrementer_wakeup;
+	hrtimer_setup(&vcpu->arch.dec_timer, kvmppc_decrementer_wakeup, CLOCK_REALTIME,
+		      HRTIMER_MODE_ABS);
 
 #ifdef CONFIG_KVM_EXIT_TIMING
 	mutex_init(&vcpu->arch.exit_timing_lock);

From 7ff22753d894250aed6048f6d4a5680142b4083f Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:38:47 +0100
Subject: [PATCH 0220/1173] KVM: s390: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Link: https://lore.kernel.org/all/637865c62963fb8cddf6c4368ca12434988a8c27.1738746821.git.namcao@linutronix.de
---
 arch/s390/kvm/interrupt.c | 3 +--
 arch/s390/kvm/kvm-s390.c  | 4 ++--
 2 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 07ff0e10cb7f5..0f00f8e85feec 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -3174,8 +3174,7 @@ void kvm_s390_gisa_init(struct kvm *kvm)
 	gi->alert.mask = 0;
 	spin_lock_init(&gi->alert.ref_lock);
 	gi->expires = 50 * 1000; /* 50 usec */
-	hrtimer_init(&gi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	gi->timer.function = gisa_vcpu_kicker;
+	hrtimer_setup(&gi->timer, gisa_vcpu_kicker, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	memset(gi->origin, 0, sizeof(struct kvm_s390_gisa));
 	gi->origin->next_alert = (u32)virt_to_phys(gi->origin);
 	VM_EVENT(kvm, 3, "gisa 0x%pK initialized", gi->origin);
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index ebecb96bacce7..1066c6ac59014 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -3943,8 +3943,8 @@ static int kvm_s390_vcpu_setup(struct kvm_vcpu *vcpu)
 		if (rc)
 			return rc;
 	}
-	hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	vcpu->arch.ckc_timer.function = kvm_s390_idle_wakeup;
+	hrtimer_setup(&vcpu->arch.ckc_timer, kvm_s390_idle_wakeup, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 
 	vcpu->arch.sie_block->hpid = HPID_KVM;
 

From 7764b9dd174c3e529e4445f0100e49a0d981a39b Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:38:48 +0100
Subject: [PATCH 0221/1173] KVM: x86: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/all/5051cfe7ed48ef9913bf2583eeca6795cb53d6ae.1738746821.git.namcao@linutronix.de
---
 arch/x86/kvm/hyperv.c     | 3 +--
 arch/x86/kvm/i8254.c      | 3 +--
 arch/x86/kvm/lapic.c      | 5 ++---
 arch/x86/kvm/vmx/nested.c | 5 ++---
 arch/x86/kvm/xen.c        | 4 ++--
 5 files changed, 8 insertions(+), 12 deletions(-)

diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 6ebeb6cea6c0d..24f0318c50d79 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -952,8 +952,7 @@ static void stimer_init(struct kvm_vcpu_hv_stimer *stimer, int timer_index)
 {
 	memset(stimer, 0, sizeof(*stimer));
 	stimer->index = timer_index;
-	hrtimer_init(&stimer->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
-	stimer->timer.function = stimer_timer_callback;
+	hrtimer_setup(&stimer->timer, stimer_timer_callback, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
 	stimer_prepare_msg(stimer);
 }
 
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index d7ab8780ab9e1..739aa6c0d0c36 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -690,8 +690,7 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
 	pit->kvm = kvm;
 
 	pit_state = &pit->pit_state;
-	hrtimer_init(&pit_state->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
-	pit_state->timer.function = pit_timer_fn;
+	hrtimer_setup(&pit_state->timer, pit_timer_fn, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
 
 	pit_state->irq_ack_notifier.gsi = 0;
 	pit_state->irq_ack_notifier.irq_acked = kvm_pit_ack_irq;
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index a009c94c26c2a..eb56cd9895748 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2921,9 +2921,8 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu)
 
 	apic->nr_lvt_entries = kvm_apic_calc_nr_lvt_entries(vcpu);
 
-	hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_ABS_HARD);
-	apic->lapic_timer.timer.function = apic_timer_fn;
+	hrtimer_setup(&apic->lapic_timer.timer, apic_timer_fn, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_ABS_HARD);
 	if (lapic_timer_advance)
 		apic->lapic_timer.timer_advance_ns = LAPIC_TIMER_ADVANCE_NS_INIT;
 
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 8a7af02d466e9..ca18c3eec76d8 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -5316,9 +5316,8 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu)
 	if (enable_shadow_vmcs && !alloc_shadow_vmcs(vcpu))
 		goto out_shadow_vmcs;
 
-	hrtimer_init(&vmx->nested.preemption_timer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_ABS_PINNED);
-	vmx->nested.preemption_timer.function = vmx_preemption_timer_fn;
+	hrtimer_setup(&vmx->nested.preemption_timer, vmx_preemption_timer_fn, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_ABS_PINNED);
 
 	vmx->nested.vpid02 = allocate_vpid();
 
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index a909b817b9c0d..1ac738dcf7a26 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -2225,8 +2225,8 @@ void kvm_xen_init_vcpu(struct kvm_vcpu *vcpu)
 	vcpu->arch.xen.poll_evtchn = 0;
 
 	timer_setup(&vcpu->arch.xen.poll_timer, cancel_evtchn_poll, 0);
-	hrtimer_init(&vcpu->arch.xen.timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
-	vcpu->arch.xen.timer.function = xen_timer_callback;
+	hrtimer_setup(&vcpu->arch.xen.timer, xen_timer_callback, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_ABS_HARD);
 
 	kvm_gpc_init(&vcpu->arch.xen.runstate_cache, vcpu->kvm);
 	kvm_gpc_init(&vcpu->arch.xen.runstate2_cache, vcpu->kvm);

From 7e5fd922c1464bd0678491f470844884af56f810 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:38:49 +0100
Subject: [PATCH 0222/1173] KVM: arm64: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/all/59f527713562ad491df7c216eeee0378e0eb2402.1738746821.git.namcao@linutronix.de
---
 arch/arm64/kvm/arch_timer.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c
index 70802e4c91cf5..5133dcbfe9f76 100644
--- a/arch/arm64/kvm/arch_timer.c
+++ b/arch/arm64/kvm/arch_timer.c
@@ -1070,8 +1070,7 @@ static void timer_context_init(struct kvm_vcpu *vcpu, int timerid)
 	else
 		ctxt->offset.vm_offset = &kvm->arch.timer_data.poffset;
 
-	hrtimer_init(&ctxt->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
-	ctxt->hrtimer.function = kvm_hrtimer_expire;
+	hrtimer_setup(&ctxt->hrtimer, kvm_hrtimer_expire, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
 
 	switch (timerid) {
 	case TIMER_PTIMER:
@@ -1098,8 +1097,8 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu)
 		timer_set_offset(vcpu_ptimer(vcpu), 0);
 	}
 
-	hrtimer_init(&timer->bg_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
-	timer->bg_timer.function = kvm_bg_timer_expire;
+	hrtimer_setup(&timer->bg_timer, kvm_bg_timer_expire, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_ABS_HARD);
 }
 
 void kvm_timer_init_vm(struct kvm *kvm)

From 7d6f12520bd40f6e88e79de29808c7ae98185324 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:38:50 +0100
Subject: [PATCH 0223/1173] LoongArch: KVM: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/a5b1b53813a15a73afdfff6fbb4c9064fa582be1.1738746821.git.namcao@linutronix.de
---
 arch/loongarch/kvm/vcpu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c
index 20f941af3e9ea..6230458d579a3 100644
--- a/arch/loongarch/kvm/vcpu.c
+++ b/arch/loongarch/kvm/vcpu.c
@@ -1459,8 +1459,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	vcpu->arch.vpid = 0;
 	vcpu->arch.flush_gpa = INVALID_GPA;
 
-	hrtimer_init(&vcpu->arch.swtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD);
-	vcpu->arch.swtimer.function = kvm_swtimer_wakeup;
+	hrtimer_setup(&vcpu->arch.swtimer, kvm_swtimer_wakeup, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_ABS_PINNED_HARD);
 
 	vcpu->arch.handle_exit = kvm_handle_exit;
 	vcpu->arch.guest_eentry = (unsigned long)kvm_loongarch_ops->exc_entry;

From 92051cb9d3e115533ff7c36ddae4e6888ac12869 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:38:51 +0100
Subject: [PATCH 0224/1173] riscv: kvm: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/d5ededf778f59f2fc38ff4276fb7f4c893e4142c.1738746821.git.namcao@linutronix.de
---
 arch/riscv/kvm/vcpu_timer.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/arch/riscv/kvm/vcpu_timer.c b/arch/riscv/kvm/vcpu_timer.c
index 96e7a4e463f7f..ff672fa71fccf 100644
--- a/arch/riscv/kvm/vcpu_timer.c
+++ b/arch/riscv/kvm/vcpu_timer.c
@@ -248,18 +248,19 @@ int kvm_riscv_vcpu_timer_init(struct kvm_vcpu *vcpu)
 	if (t->init_done)
 		return -EINVAL;
 
-	hrtimer_init(&t->hrt, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	t->init_done = true;
 	t->next_set = false;
 
 	/* Enable sstc for every vcpu if available in hardware */
 	if (riscv_isa_extension_available(NULL, SSTC)) {
 		t->sstc_enabled = true;
-		t->hrt.function = kvm_riscv_vcpu_vstimer_expired;
+		hrtimer_setup(&t->hrt, kvm_riscv_vcpu_vstimer_expired, CLOCK_MONOTONIC,
+			      HRTIMER_MODE_REL);
 		t->timer_next_event = kvm_riscv_vcpu_update_vstimecmp;
 	} else {
 		t->sstc_enabled = false;
-		t->hrt.function = kvm_riscv_vcpu_hrtimer_expired;
+		hrtimer_setup(&t->hrt, kvm_riscv_vcpu_hrtimer_expired, CLOCK_MONOTONIC,
+			      HRTIMER_MODE_REL);
 		t->timer_next_event = kvm_riscv_vcpu_update_hrtimer;
 	}
 

From 2f33de836402acc80c494ae56a5d74f5df5f4409 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:38:52 +0100
Subject: [PATCH 0225/1173] ARM: imx: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/aff915511ee629b461fee98688b8e859075386ac.1738746821.git.namcao@linutronix.de
---
 arch/arm/mach-imx/mmdc.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/arch/arm/mach-imx/mmdc.c b/arch/arm/mach-imx/mmdc.c
index e898f7c2733ef..94e4f4a2f73fc 100644
--- a/arch/arm/mach-imx/mmdc.c
+++ b/arch/arm/mach-imx/mmdc.c
@@ -509,9 +509,8 @@ static int imx_mmdc_perf_init(struct platform_device *pdev, void __iomem *mmdc_b
 	pmu_mmdc->mmdc_ipg_clk = mmdc_ipg_clk;
 	pmu_mmdc->devtype_data = device_get_match_data(&pdev->dev);
 
-	hrtimer_init(&pmu_mmdc->hrtimer, CLOCK_MONOTONIC,
-			HRTIMER_MODE_REL);
-	pmu_mmdc->hrtimer.function = mmdc_pmu_timer_handler;
+	hrtimer_setup(&pmu_mmdc->hrtimer, mmdc_pmu_timer_handler, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 
 	cpumask_set_cpu(raw_smp_processor_id(), &pmu_mmdc->cpu);
 

From 878a388866a67cb8f2d12df24f256b4e6159dcb8 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:38:53 +0100
Subject: [PATCH 0226/1173] ARM: 8611/1: l2x0: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/5ca584b1e32c34630bb15ccc84467c1e05059e66.1738746821.git.namcao@linutronix.de
---
 arch/arm/mm/cache-l2x0-pmu.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/arm/mm/cache-l2x0-pmu.c b/arch/arm/mm/cache-l2x0-pmu.c
index 993fefdc167a8..93ef0502b7ff2 100644
--- a/arch/arm/mm/cache-l2x0-pmu.c
+++ b/arch/arm/mm/cache-l2x0-pmu.c
@@ -539,8 +539,7 @@ static __init int l2x0_pmu_init(void)
 	 * at higher frequencies.
 	 */
 	l2x0_pmu_poll_period = ms_to_ktime(1000);
-	hrtimer_init(&l2x0_pmu_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	l2x0_pmu_hrtimer.function = l2x0_pmu_poll;
+	hrtimer_setup(&l2x0_pmu_hrtimer, l2x0_pmu_poll, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 
 	cpumask_set_cpu(0, &pmu_cpu);
 	ret = cpuhp_setup_state_nocalls(CPUHP_AP_PERF_ARM_L2X0_ONLINE,

From d1f0d81b3604506cdd128578f778b899bd142b94 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:38:54 +0100
Subject: [PATCH 0227/1173] powerpc/watchdog: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/099ebf6d352094a56e22fdfe76582b50f8fd6029.1738746821.git.namcao@linutronix.de
---
 arch/powerpc/kernel/watchdog.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c
index 8c464a5d82469..2429cb1c7baa7 100644
--- a/arch/powerpc/kernel/watchdog.c
+++ b/arch/powerpc/kernel/watchdog.c
@@ -495,8 +495,7 @@ static void start_watchdog(void *arg)
 
 	*this_cpu_ptr(&wd_timer_tb) = get_tb();
 
-	hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	hrtimer->function = watchdog_timer_fn;
+	hrtimer_setup(hrtimer, watchdog_timer_fn, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	hrtimer_start(hrtimer, ms_to_ktime(wd_timer_period_ms),
 		      HRTIMER_MODE_REL_PINNED);
 }

From c56c98e5af6d912c07b4e1e7be8ee97b0ff6ab27 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:38:55 +0100
Subject: [PATCH 0228/1173] perf/x86: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/e84ad5a660b8e10867e547db8e64f7e99c48ebba.1738746821.git.namcao@linutronix.de
---
 arch/x86/events/intel/uncore.c | 3 +--
 arch/x86/events/rapl.c         | 3 +--
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 60b3078b7502f..a34e50fc4a8fc 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -347,8 +347,7 @@ void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box)
 
 static void uncore_pmu_init_hrtimer(struct intel_uncore_box *box)
 {
-	hrtimer_init(&box->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	box->hrtimer.function = uncore_pmu_hrtimer;
+	hrtimer_setup(&box->hrtimer, uncore_pmu_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 }
 
 static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type,
diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index 4952faf03e82d..6a0d957d9d7e1 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -274,8 +274,7 @@ static void rapl_hrtimer_init(struct rapl_pmu *rapl_pmu)
 {
 	struct hrtimer *hr = &rapl_pmu->hrtimer;
 
-	hrtimer_init(hr, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	hr->function = rapl_hrtimer_handle;
+	hrtimer_setup(hr, rapl_hrtimer_handle, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 }
 
 static void __rapl_pmu_event_start(struct rapl_pmu *rapl_pmu,

From 99fb79f6d6de533d92dc11d53b0a058ac3de8cbc Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:38:56 +0100
Subject: [PATCH 0229/1173] s390/ap_bus: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/d8a3919c09caa671e64d9f9bbf726aa8a885a844.1738746821.git.namcao@linutronix.de
---
 drivers/s390/crypto/ap_bus.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index 26e1ea1940ecb..62feb2c639d56 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -2326,8 +2326,7 @@ static inline int __init ap_async_init(void)
 	 */
 	if (MACHINE_IS_VM)
 		poll_high_timeout = 1500000;
-	hrtimer_init(&ap_poll_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
-	ap_poll_timer.function = ap_poll_timeout;
+	hrtimer_setup(&ap_poll_timer, ap_poll_timeout, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
 
 	queue_work(system_long_wq, &ap_scan_bus_work);
 

From ee13da875b8a4636198538dbe2e8037574e7a98e Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:38:57 +0100
Subject: [PATCH 0230/1173] sched: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/a55e849cba3c41b4c5708be6ea6be6f337d1a8fb.1738746821.git.namcao@linutronix.de
---
 kernel/sched/core.c     | 3 +--
 kernel/sched/deadline.c | 6 ++----
 kernel/sched/fair.c     | 8 ++++----
 kernel/sched/rt.c       | 5 ++---
 4 files changed, 9 insertions(+), 13 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9aecd914ac691..6469755ea6adf 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -916,8 +916,7 @@ static void hrtick_rq_init(struct rq *rq)
 #ifdef CONFIG_SMP
 	INIT_CSD(&rq->hrtick_csd, __hrtick_start, rq);
 #endif
-	hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
-	rq->hrtick_timer.function = hrtick;
+	hrtimer_setup(&rq->hrtick_timer, hrtick, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
 }
 #else	/* CONFIG_SCHED_HRTICK */
 static inline void hrtick_clear(struct rq *rq)
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 38e4537790af7..2d0f571f95e98 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1382,8 +1382,7 @@ static void init_dl_task_timer(struct sched_dl_entity *dl_se)
 {
 	struct hrtimer *timer = &dl_se->dl_timer;
 
-	hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
-	timer->function = dl_task_timer;
+	hrtimer_setup(timer, dl_task_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
 }
 
 /*
@@ -1839,8 +1838,7 @@ static void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se)
 {
 	struct hrtimer *timer = &dl_se->inactive_timer;
 
-	hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
-	timer->function = inactive_task_timer;
+	hrtimer_setup(timer, inactive_task_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
 }
 
 #define __node_2_dle(node) \
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1c0ef435a7aae..88923f1873f6e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6539,14 +6539,14 @@ void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b, struct cfs_bandwidth *paren
 	cfs_b->hierarchical_quota = parent ? parent->hierarchical_quota : RUNTIME_INF;
 
 	INIT_LIST_HEAD(&cfs_b->throttled_cfs_rq);
-	hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
-	cfs_b->period_timer.function = sched_cfs_period_timer;
+	hrtimer_setup(&cfs_b->period_timer, sched_cfs_period_timer, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_ABS_PINNED);
 
 	/* Add a random offset so that timers interleave */
 	hrtimer_set_expires(&cfs_b->period_timer,
 			    get_random_u32_below(cfs_b->period));
-	hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	cfs_b->slack_timer.function = sched_cfs_slack_timer;
+	hrtimer_setup(&cfs_b->slack_timer, sched_cfs_slack_timer, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 	cfs_b->slack_started = false;
 }
 
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 4b8e33c615b12..7a9ed4d933977 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -127,9 +127,8 @@ void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime)
 
 	raw_spin_lock_init(&rt_b->rt_runtime_lock);
 
-	hrtimer_init(&rt_b->rt_period_timer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_REL_HARD);
-	rt_b->rt_period_timer.function = sched_rt_period_timer;
+	hrtimer_setup(&rt_b->rt_period_timer, sched_rt_period_timer, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL_HARD);
 }
 
 static inline void do_start_rt_bandwidth(struct rt_bandwidth *rt_b)

From 53867760f50c2b5b6b16f1350135553dda88c461 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:38:58 +0100
Subject: [PATCH 0231/1173] mm/slab: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Paul E. McKenney <paulmck@kernel.org>
Link: https://lore.kernel.org/all/030065d66630068f788caf9df15756fad404e754.1738746821.git.namcao@linutronix.de
---
 mm/slab_common.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/mm/slab_common.c b/mm/slab_common.c
index 4030907b6b7d8..59578dafbf378 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -1887,8 +1887,8 @@ run_page_cache_worker(struct kfree_rcu_cpu *krcp)
 				&krcp->page_cache_work,
 					msecs_to_jiffies(rcu_delay_page_cache_fill_msec));
 		} else {
-			hrtimer_init(&krcp->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-			krcp->hrtimer.function = schedule_page_work_fn;
+			hrtimer_setup(&krcp->hrtimer, schedule_page_work_fn, CLOCK_MONOTONIC,
+				      HRTIMER_MODE_REL);
 			hrtimer_start(&krcp->hrtimer, 0, HRTIMER_MODE_REL);
 		}
 	}

From b09dffdeb3691483fc8fbe58ff7787c964b56d5c Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:38:59 +0100
Subject: [PATCH 0232/1173] lib: test_objpool: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/edc46fbf290b280ebe67bb0d21599c4c30716b68.1738746821.git.namcao@linutronix.de
---
 lib/test_objpool.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/lib/test_objpool.c b/lib/test_objpool.c
index 896c0131c9a8c..8f688187fa872 100644
--- a/lib/test_objpool.c
+++ b/lib/test_objpool.c
@@ -190,8 +190,7 @@ static int ot_init_hrtimer(struct ot_item *item, unsigned long hrtimer)
 		return -ENOENT;
 
 	item->hrtcycle = ktime_set(0, hrtimer * 1000000UL);
-	hrtimer_init(hrt, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	hrt->function = ot_hrtimer_handler;
+	hrtimer_setup(hrt, ot_hrtimer_handler, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	return 0;
 }
 

From 4248fd6f37c1995fbc62cd563ab451094dadb412 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:39:00 +0100
Subject: [PATCH 0233/1173] io_uring/timeout: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/80ca8d959f2cc67c75f6d61008e3bebfe7fbc30a.1738746821.git.namcao@linutronix.de
---
 io_uring/timeout.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/io_uring/timeout.c b/io_uring/timeout.c
index 48fc8cf707843..c5fb817b1e28e 100644
--- a/io_uring/timeout.c
+++ b/io_uring/timeout.c
@@ -407,8 +407,7 @@ static int io_linked_timeout_update(struct io_ring_ctx *ctx, __u64 user_data,
 	io = req->async_data;
 	if (hrtimer_try_to_cancel(&io->timer) == -1)
 		return -EALREADY;
-	hrtimer_init(&io->timer, io_timeout_get_clock(io), mode);
-	io->timer.function = io_link_timeout_fn;
+	hrtimer_setup(&io->timer, io_link_timeout_fn, io_timeout_get_clock(io), mode);
 	hrtimer_start(&io->timer, timespec64_to_ktime(*ts), mode);
 	return 0;
 }
@@ -430,8 +429,7 @@ static int io_timeout_update(struct io_ring_ctx *ctx, __u64 user_data,
 	data->ts = *ts;
 
 	list_add_tail(&timeout->list, &ctx->timeout_list);
-	hrtimer_init(&data->timer, io_timeout_get_clock(data), mode);
-	data->timer.function = io_timeout_fn;
+	hrtimer_setup(&data->timer, io_timeout_fn, io_timeout_get_clock(data), mode);
 	hrtimer_start(&data->timer, timespec64_to_ktime(data->ts), mode);
 	return 0;
 }
@@ -557,7 +555,6 @@ static int __io_timeout_prep(struct io_kiocb *req,
 		return -EINVAL;
 
 	data->mode = io_translate_timeout_mode(flags);
-	hrtimer_init(&data->timer, io_timeout_get_clock(data), data->mode);
 
 	if (is_timeout_link) {
 		struct io_submit_link *link = &req->ctx->submit_state.link;
@@ -568,6 +565,10 @@ static int __io_timeout_prep(struct io_kiocb *req,
 			return -EINVAL;
 		timeout->head = link->last;
 		link->last->flags |= REQ_F_ARM_LTIMEOUT;
+		hrtimer_setup(&data->timer, io_link_timeout_fn, io_timeout_get_clock(data),
+			      data->mode);
+	} else {
+		hrtimer_setup(&data->timer, io_timeout_fn, io_timeout_get_clock(data), data->mode);
 	}
 	return 0;
 }
@@ -627,7 +628,6 @@ int io_timeout(struct io_kiocb *req, unsigned int issue_flags)
 	}
 add:
 	list_add(&timeout->list, entry);
-	data->timer.function = io_timeout_fn;
 	hrtimer_start(&data->timer, timespec64_to_ktime(data->ts), data->mode);
 	raw_spin_unlock_irq(&ctx->timeout_lock);
 	return IOU_ISSUE_SKIP_COMPLETE;
@@ -646,7 +646,6 @@ void io_queue_linked_timeout(struct io_kiocb *req)
 	if (timeout->head) {
 		struct io_timeout_data *data = req->async_data;
 
-		data->timer.function = io_link_timeout_fn;
 		hrtimer_start(&data->timer, timespec64_to_ktime(data->ts),
 				data->mode);
 		list_add_tail(&timeout->list, &ctx->ltimeout_list);

From 91b7be704dd4991bb6ec8bb67480993e82a673bb Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:39:01 +0100
Subject: [PATCH 0234/1173] fork: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/174111145b945391e48936d6debcd43caec3e406.1738746821.git.namcao@linutronix.de
---
 kernel/fork.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/kernel/fork.c b/kernel/fork.c
index 735405a9c5f32..e27fe5d5a15c9 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1891,8 +1891,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 #ifdef CONFIG_POSIX_TIMERS
 	INIT_HLIST_HEAD(&sig->posix_timers);
 	INIT_HLIST_HEAD(&sig->ignored_posix_timers);
-	hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	sig->real_timer.function = it_real_fn;
+	hrtimer_setup(&sig->real_timer, it_real_fn, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 #endif
 
 	task_lock(current->group_leader);

From 022a223546e4fa03bde18fea4562d29b4e1a432a Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:39:02 +0100
Subject: [PATCH 0235/1173] perf: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/f611e6d3fc6996bbcf0e19fe234f75edebe4332f.1738746821.git.namcao@linutronix.de
---
 kernel/events/core.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index bcb09e011e9e1..db5792d79b7f1 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1147,8 +1147,8 @@ static void __perf_mux_hrtimer_init(struct perf_cpu_pmu_context *cpc, int cpu)
 	cpc->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * interval);
 
 	raw_spin_lock_init(&cpc->hrtimer_lock);
-	hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD);
-	timer->function = perf_mux_hrtimer_handler;
+	hrtimer_setup(timer, perf_mux_hrtimer_handler, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_ABS_PINNED_HARD);
 }
 
 static int perf_mux_hrtimer_restart(struct perf_cpu_pmu_context *cpc)
@@ -11367,8 +11367,7 @@ static void perf_swevent_init_hrtimer(struct perf_event *event)
 	if (!is_sampling_event(event))
 		return;
 
-	hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
-	hwc->hrtimer.function = perf_swevent_hrtimer;
+	hrtimer_setup(&hwc->hrtimer, perf_swevent_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
 
 	/*
 	 * Since hrtimers have a fixed rate, we can do a static freq->period

From 9eeb54b47541d2ea51315af324e236bb6e6942ea Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:39:03 +0100
Subject: [PATCH 0236/1173] timerfd: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/2d1f26c2c2f3ad15f1ca1a09ecb9d760cafef4a6.1738746821.git.namcao@linutronix.de
---
 fs/timerfd.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/fs/timerfd.c b/fs/timerfd.c
index 9f7eb451a60f6..cee007e0d9780 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -205,9 +205,8 @@ static int timerfd_setup(struct timerfd_ctx *ctx, int flags,
 			   ALARM_REALTIME : ALARM_BOOTTIME,
 			   timerfd_alarmproc);
 	} else {
-		hrtimer_init(&ctx->t.tmr, clockid, htmode);
+		hrtimer_setup(&ctx->t.tmr, timerfd_tmrproc, clockid, htmode);
 		hrtimer_set_expires(&ctx->t.tmr, texp);
-		ctx->t.tmr.function = timerfd_tmrproc;
 	}
 
 	if (texp != 0) {
@@ -429,7 +428,7 @@ SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags)
 			   ALARM_REALTIME : ALARM_BOOTTIME,
 			   timerfd_alarmproc);
 	else
-		hrtimer_init(&ctx->t.tmr, clockid, HRTIMER_MODE_ABS);
+		hrtimer_setup(&ctx->t.tmr, timerfd_tmrproc, clockid, HRTIMER_MODE_ABS);
 
 	ctx->moffs = ktime_mono_to_real(0);
 

From f66b0acf394b8558f79c03336b579a47876a6940 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:39:04 +0100
Subject: [PATCH 0237/1173] time: Switch to hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/170bb691a0d59917c8268a98c80b607128fc9f7f.1738746821.git.namcao@linutronix.de
---
 kernel/time/ntp.c                    | 3 +--
 kernel/time/posix-timers.c           | 7 +++----
 kernel/time/sched_clock.c            | 3 +--
 kernel/time/tick-broadcast-hrtimer.c | 3 +--
 kernel/time/tick-sched.c             | 6 ++----
 5 files changed, 8 insertions(+), 14 deletions(-)

diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 163e7a2033b62..b837d3d9d3253 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -678,8 +678,7 @@ void ntp_notify_cmos_timer(bool offset_set)
 
 static void __init ntp_init_cmos_sync(void)
 {
-	hrtimer_init(&sync_hrtimer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
-	sync_hrtimer.function = sync_timer_callback;
+	hrtimer_setup(&sync_hrtimer, sync_timer_callback, CLOCK_REALTIME, HRTIMER_MODE_ABS);
 }
 #else /* CONFIG_GENERIC_CMOS_UPDATE) || defined(CONFIG_RTC_SYSTOHC) */
 static inline void __init ntp_init_cmos_sync(void) { }
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 1b675aee99a98..58351f537a047 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -381,7 +381,7 @@ static void posix_timer_unhash_and_free(struct k_itimer *tmr)
 
 static int common_timer_create(struct k_itimer *new_timer)
 {
-	hrtimer_init(&new_timer->it.real.timer, new_timer->it_clock, 0);
+	hrtimer_setup(&new_timer->it.real.timer, posix_timer_fn, new_timer->it_clock, 0);
 	return 0;
 }
 
@@ -747,7 +747,7 @@ static void common_hrtimer_arm(struct k_itimer *timr, ktime_t expires,
 	/*
 	 * Posix magic: Relative CLOCK_REALTIME timers are not affected by
 	 * clock modifications, so they become CLOCK_MONOTONIC based under the
-	 * hood. See hrtimer_init(). Update timr->kclock, so the generic
+	 * hood. See hrtimer_setup(). Update timr->kclock, so the generic
 	 * functions which use timr->kclock->clock_get_*() work.
 	 *
 	 * Note: it_clock stays unmodified, because the next timer_set() might
@@ -756,8 +756,7 @@ static void common_hrtimer_arm(struct k_itimer *timr, ktime_t expires,
 	if (timr->it_clock == CLOCK_REALTIME)
 		timr->kclock = absolute ? &clock_realtime : &clock_monotonic;
 
-	hrtimer_init(&timr->it.real.timer, timr->it_clock, mode);
-	timr->it.real.timer.function = posix_timer_fn;
+	hrtimer_setup(&timr->it.real.timer, posix_timer_fn, timr->it_clock, mode);
 
 	if (!absolute)
 		expires = ktime_add_safe(expires, timer->base->get_time());
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index fcca4e72f1efa..cc15fe293719f 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -263,8 +263,7 @@ void __init generic_sched_clock_init(void)
 	 * Start the timer to keep sched_clock() properly updated and
 	 * sets the initial epoch.
 	 */
-	hrtimer_init(&sched_clock_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
-	sched_clock_timer.function = sched_clock_poll;
+	hrtimer_setup(&sched_clock_timer, sched_clock_poll, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
 	hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL_HARD);
 }
 
diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
index e28f9210f8a15..a88b72b0f35ee 100644
--- a/kernel/time/tick-broadcast-hrtimer.c
+++ b/kernel/time/tick-broadcast-hrtimer.c
@@ -100,7 +100,6 @@ static enum hrtimer_restart bc_handler(struct hrtimer *t)
 
 void tick_setup_hrtimer_broadcast(void)
 {
-	hrtimer_init(&bctimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
-	bctimer.function = bc_handler;
+	hrtimer_setup(&bctimer, bc_handler, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
 	clockevents_register_device(&ce_broadcast_hrtimer);
 }
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index fa058510af9c1..c527b421c8652 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -1573,12 +1573,10 @@ void tick_setup_sched_timer(bool hrtimer)
 	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 
 	/* Emulate tick processing via per-CPU hrtimers: */
-	hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
+	hrtimer_setup(&ts->sched_timer, tick_nohz_handler, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
 
-	if (IS_ENABLED(CONFIG_HIGH_RES_TIMERS) && hrtimer) {
+	if (IS_ENABLED(CONFIG_HIGH_RES_TIMERS) && hrtimer)
 		tick_sched_flag_set(ts, TS_FLAG_HIGHRES);
-		ts->sched_timer.function = tick_nohz_handler;
-	}
 
 	/* Get the next period (per-CPU) */
 	hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update());

From deacdc871b48a6a75b03837e8faf3e0cd7c198ea Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:39:05 +0100
Subject: [PATCH 0238/1173] bpf: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/e4be2486f02a8e0ef5aa42624f1708d23e88ad57.1738746821.git.namcao@linutronix.de
---
 kernel/bpf/helpers.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index f27ce162427ab..672abe1112824 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1284,8 +1284,7 @@ static int __bpf_async_init(struct bpf_async_kern *async, struct bpf_map *map, u
 
 		atomic_set(&t->cancelling, 0);
 		INIT_WORK(&t->cb.delete_work, bpf_timer_delete_work);
-		hrtimer_init(&t->timer, clockid, HRTIMER_MODE_REL_SOFT);
-		t->timer.function = bpf_timer_cb;
+		hrtimer_setup(&t->timer, bpf_timer_cb, clockid, HRTIMER_MODE_REL_SOFT);
 		cb->value = (void *)async - map->record->timer_off;
 		break;
 	case BPF_ASYNC_TYPE_WQ:

From 1654eba8f74d1fcb95dd63e549c621722adc2689 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:39:06 +0100
Subject: [PATCH 0239/1173] ubifs: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Richard Weinberger <richard@nod.at>
Link: https://lore.kernel.org/all/f5767e50aaa2935b3e4a0e9cf1bc4365d6b0c1a0.1738746821.git.namcao@linutronix.de
---
 fs/ubifs/io.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/ubifs/io.c b/fs/ubifs/io.c
index 01d8eb1703820..a79f229df4754 100644
--- a/fs/ubifs/io.c
+++ b/fs/ubifs/io.c
@@ -1179,8 +1179,7 @@ int ubifs_wbuf_init(struct ubifs_info *c, struct ubifs_wbuf *wbuf)
 	wbuf->c = c;
 	wbuf->next_ino = 0;
 
-	hrtimer_init(&wbuf->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	wbuf->timer.function = wbuf_timer_callback_nolock;
+	hrtimer_setup(&wbuf->timer, wbuf_timer_callback_nolock, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	return 0;
 }
 

From d2254b0643222ffa7e4e7ac0ae8aa0e4cbf6d09a Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:39:07 +0100
Subject: [PATCH 0240/1173] watchdog: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/a5c62f2b5e1ea1cf4d32f37bc2d21a8eeab2f875.1738746821.git.namcao@linutronix.de
---
 drivers/watchdog/softdog.c                     | 8 +++-----
 drivers/watchdog/watchdog_dev.c                | 4 ++--
 drivers/watchdog/watchdog_hrtimer_pretimeout.c | 4 ++--
 kernel/watchdog.c                              | 3 +--
 4 files changed, 8 insertions(+), 11 deletions(-)

diff --git a/drivers/watchdog/softdog.c b/drivers/watchdog/softdog.c
index 7a1096265f180..0820e35ad2e3c 100644
--- a/drivers/watchdog/softdog.c
+++ b/drivers/watchdog/softdog.c
@@ -187,14 +187,12 @@ static int __init softdog_init(void)
 	watchdog_set_nowayout(&softdog_dev, nowayout);
 	watchdog_stop_on_reboot(&softdog_dev);
 
-	hrtimer_init(&softdog_ticktock, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	softdog_ticktock.function = softdog_fire;
+	hrtimer_setup(&softdog_ticktock, softdog_fire, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 
 	if (IS_ENABLED(CONFIG_SOFT_WATCHDOG_PRETIMEOUT)) {
 		softdog_info.options |= WDIOF_PRETIMEOUT;
-		hrtimer_init(&softdog_preticktock, CLOCK_MONOTONIC,
-			     HRTIMER_MODE_REL);
-		softdog_preticktock.function = softdog_pretimeout;
+		hrtimer_setup(&softdog_preticktock, softdog_pretimeout, CLOCK_MONOTONIC,
+			      HRTIMER_MODE_REL);
 	}
 
 	if (soft_active_on_boot)
diff --git a/drivers/watchdog/watchdog_dev.c b/drivers/watchdog/watchdog_dev.c
index 19698d87dc572..8369fd94fc1a6 100644
--- a/drivers/watchdog/watchdog_dev.c
+++ b/drivers/watchdog/watchdog_dev.c
@@ -1051,8 +1051,8 @@ static int watchdog_cdev_register(struct watchdog_device *wdd)
 	}
 
 	kthread_init_work(&wd_data->work, watchdog_ping_work);
-	hrtimer_init(&wd_data->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
-	wd_data->timer.function = watchdog_timer_expired;
+	hrtimer_setup(&wd_data->timer, watchdog_timer_expired, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL_HARD);
 	watchdog_hrtimer_pretimeout_init(wdd);
 
 	if (wdd->id == 0) {
diff --git a/drivers/watchdog/watchdog_hrtimer_pretimeout.c b/drivers/watchdog/watchdog_hrtimer_pretimeout.c
index 940b53718a91e..fbc7eecd8b203 100644
--- a/drivers/watchdog/watchdog_hrtimer_pretimeout.c
+++ b/drivers/watchdog/watchdog_hrtimer_pretimeout.c
@@ -23,8 +23,8 @@ void watchdog_hrtimer_pretimeout_init(struct watchdog_device *wdd)
 {
 	struct watchdog_core_data *wd_data = wdd->wd_data;
 
-	hrtimer_init(&wd_data->pretimeout_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	wd_data->pretimeout_timer.function = watchdog_hrtimer_pretimeout;
+	hrtimer_setup(&wd_data->pretimeout_timer, watchdog_hrtimer_pretimeout, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 }
 
 void watchdog_hrtimer_pretimeout_start(struct watchdog_device *wdd)
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index b2da7de39d06d..6a98dbc931ac6 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -797,8 +797,7 @@ static void watchdog_enable(unsigned int cpu)
 	 * Start the timer first to prevent the hardlockup watchdog triggering
 	 * before the timer has a chance to fire.
 	 */
-	hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
-	hrtimer->function = watchdog_timer_fn;
+	hrtimer_setup(hrtimer, watchdog_timer_fn, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
 	hrtimer_start(hrtimer, ns_to_ktime(sample_period),
 		      HRTIMER_MODE_REL_PINNED_HARD);
 

From 19fec9c4434f86bce6b7227ee70b8d9a2b3c9035 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:39:08 +0100
Subject: [PATCH 0241/1173] tracing/osnoise: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Link: https://lore.kernel.org/all/ff8e6e11df5f928b2b97619ac847b4fa045376a1.1738746821.git.namcao@linutronix.de
---
 kernel/trace/trace_osnoise.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index f3a2722ee4c07..15999532956ab 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -1901,8 +1901,7 @@ static int timerlat_main(void *data)
 	tlat->count = 0;
 	tlat->tracing_thread = false;
 
-	hrtimer_init(&tlat->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD);
-	tlat->timer.function = timerlat_irq;
+	hrtimer_setup(&tlat->timer, timerlat_irq, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD);
 	tlat->kthread = current;
 	osn_var->pid = current->pid;
 	/*
@@ -2456,8 +2455,7 @@ static int timerlat_fd_open(struct inode *inode, struct file *file)
 	tlat = this_cpu_tmr_var();
 	tlat->count = 0;
 
-	hrtimer_init(&tlat->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD);
-	tlat->timer.function = timerlat_irq;
+	hrtimer_setup(&tlat->timer, timerlat_irq, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD);
 
 	migrate_enable();
 	return 0;

From 2414f15910c50a714a4f9aa5aa874f0682648536 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:39:09 +0100
Subject: [PATCH 0242/1173] block, bfq: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/d0d57e1dab46b617856dfb93c721d221cc31ab0b.1738746821.git.namcao@linutronix.de
---
 block/bfq-iosched.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 1675422016038..abd80dc135623 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -7315,9 +7315,8 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
 
 	INIT_LIST_HEAD(&bfqd->dispatch);
 
-	hrtimer_init(&bfqd->idle_slice_timer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_REL);
-	bfqd->idle_slice_timer.function = bfq_idle_slice_timer;
+	hrtimer_setup(&bfqd->idle_slice_timer, bfq_idle_slice_timer, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 
 	bfqd->queue_weights_tree = RB_ROOT_CACHED;
 #ifdef CONFIG_BFQ_GROUP_IOSCHED

From 32539b780c4fc3641a37ad9cb6134d72b5c8cae9 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:39:10 +0100
Subject: [PATCH 0243/1173] ata: pata_octeon_cf: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Damien Le Moal <dlemoal@kernel.org>
Link: https://lore.kernel.org/all/a36ae1e4be26f8359bf2777b1813bbf4d7a7983f.1738746821.git.namcao@linutronix.de
---
 drivers/ata/pata_octeon_cf.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/ata/pata_octeon_cf.c b/drivers/ata/pata_octeon_cf.c
index dce24806a0529..2d32125c16fd4 100644
--- a/drivers/ata/pata_octeon_cf.c
+++ b/drivers/ata/pata_octeon_cf.c
@@ -935,9 +935,8 @@ static int octeon_cf_probe(struct platform_device *pdev)
 		ap->mwdma_mask	= enable_dma ? ATA_MWDMA4 : 0;
 
 		/* True IDE mode needs a timer to poll for not-busy.  */
-		hrtimer_init(&cf_port->delayed_finish, CLOCK_MONOTONIC,
-			     HRTIMER_MODE_REL);
-		cf_port->delayed_finish.function = octeon_cf_delayed_finish;
+		hrtimer_setup(&cf_port->delayed_finish, octeon_cf_delayed_finish, CLOCK_MONOTONIC,
+			      HRTIMER_MODE_REL);
 	} else {
 		/* 16 bit but not True IDE */
 		base = cs0 + 0x800;

From cab0e0a05627f7e661aa644a3a5f0eb88881872f Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:39:11 +0100
Subject: [PATCH 0244/1173] blk_iocost: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/196d487c925411923a2d59d4bf5e366b9dac2747.1738746821.git.namcao@linutronix.de
---
 block/blk-iocost.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index 65a1d4427ccf4..ed11438eb4be3 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -3004,8 +3004,7 @@ static void ioc_pd_init(struct blkg_policy_data *pd)
 	iocg->hweight_inuse = WEIGHT_ONE;
 
 	init_waitqueue_head(&iocg->waitq);
-	hrtimer_init(&iocg->waitq_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
-	iocg->waitq_timer.function = iocg_waitq_timer_fn;
+	hrtimer_setup(&iocg->waitq_timer, iocg_waitq_timer_fn, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
 
 	iocg->level = blkg->blkcg->css.cgroup->level;
 

From efad91a9836e3c26194a18947e0af7f575c254fb Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:39:12 +0100
Subject: [PATCH 0245/1173] PM: runtime: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Rafael J. Wysocki <rafael@kernel.org>
Link: https://lore.kernel.org/all/8d1ce108b043896733ce08d3deea6e84941d499b.1738746821.git.namcao@linutronix.de
---
 drivers/base/power/runtime.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 2ee45841486bc..425c43b2d478a 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -1764,8 +1764,8 @@ void pm_runtime_init(struct device *dev)
 	INIT_WORK(&dev->power.work, pm_runtime_work);
 
 	dev->power.timer_expires = 0;
-	hrtimer_init(&dev->power.suspend_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
-	dev->power.suspend_timer.function = pm_suspend_timer_fn;
+	hrtimer_setup(&dev->power.suspend_timer, pm_suspend_timer_fn, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_ABS);
 
 	init_waitqueue_head(&dev->power.wait_queue);
 }

From 4279d7054c871ed5e3d5de2b5948b24abba76c55 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:39:13 +0100
Subject: [PATCH 0246/1173] PM / devfreq: rockchip-dfi: Switch to use
 hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Chanwoo Choi <cw00.choi@samsung.com>
Link: https://lore.kernel.org/all/dfb35fb45eacdba7b8767052aa8c29ca157ac1b0.1738746821.git.namcao@linutronix.de
---
 drivers/devfreq/event/rockchip-dfi.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/devfreq/event/rockchip-dfi.c b/drivers/devfreq/event/rockchip-dfi.c
index e2a1e4463b6f5..0470d7c175f4f 100644
--- a/drivers/devfreq/event/rockchip-dfi.c
+++ b/drivers/devfreq/event/rockchip-dfi.c
@@ -642,8 +642,7 @@ static int rockchip_ddr_perf_init(struct rockchip_dfi *dfi)
 	if (ret)
 		return ret;
 
-	hrtimer_init(&dfi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	dfi->timer.function = rockchip_dfi_timer;
+	hrtimer_setup(&dfi->timer, rockchip_dfi_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 
 	switch (dfi->ddr_type) {
 	case ROCKCHIP_DDRTYPE_LPDDR2:

From 68d3de7fc49c326205811a23d0a146feed0d4fee Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:39:14 +0100
Subject: [PATCH 0247/1173] null_blk: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/076cd30acb4b2d6b699f3c80463a8983530d4f06.1738746821.git.namcao@linutronix.de
---
 drivers/block/null_blk/main.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index d94ef37480bd4..16457330c1bc7 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -1426,8 +1426,7 @@ static void nullb_setup_bwtimer(struct nullb *nullb)
 {
 	ktime_t timer_interval = ktime_set(0, TIMER_INTERVAL);
 
-	hrtimer_init(&nullb->bw_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	nullb->bw_timer.function = nullb_bwtimer_fn;
+	hrtimer_setup(&nullb->bw_timer, nullb_bwtimer_fn, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	atomic_long_set(&nullb->cur_bytes, mb_per_tick(nullb->dev->mbps));
 	hrtimer_start(&nullb->bw_timer, timer_interval, HRTIMER_MODE_REL);
 }
@@ -1604,8 +1603,8 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx,
 	might_sleep_if(hctx->flags & BLK_MQ_F_BLOCKING);
 
 	if (!is_poll && nq->dev->irqmode == NULL_IRQ_TIMER) {
-		hrtimer_init(&cmd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-		cmd->timer.function = null_cmd_timer_expired;
+		hrtimer_setup(&cmd->timer, null_cmd_timer_expired, CLOCK_MONOTONIC,
+			      HRTIMER_MODE_REL);
 	}
 	cmd->error = BLK_STS_OK;
 	cmd->nq = nq;

From 8030d4673e9957df30a8a0fa4228917b954f71c0 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:39:15 +0100
Subject: [PATCH 0248/1173] hwrng: timeriomem: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/010640f1668d40894a1721037c56f7a684dbcc5f.1738746821.git.namcao@linutronix.de
---
 drivers/char/hw_random/timeriomem-rng.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/char/hw_random/timeriomem-rng.c b/drivers/char/hw_random/timeriomem-rng.c
index 7174bfccc7b32..b95f6d0f17ede 100644
--- a/drivers/char/hw_random/timeriomem-rng.c
+++ b/drivers/char/hw_random/timeriomem-rng.c
@@ -152,8 +152,7 @@ static int timeriomem_rng_probe(struct platform_device *pdev)
 
 	priv->period = ns_to_ktime(period * NSEC_PER_USEC);
 	init_completion(&priv->completion);
-	hrtimer_init(&priv->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
-	priv->timer.function = timeriomem_rng_trigger;
+	hrtimer_setup(&priv->timer, timeriomem_rng_trigger, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
 
 	priv->rng_ops.name = dev_name(&pdev->dev);
 	priv->rng_ops.read = timeriomem_rng_read;

From fe0b776543e986249f48611387c847e5564a3647 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:43:21 +0100
Subject: [PATCH 0249/1173] netdev: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/861d9b287f2b5206b853dbcc0f302127f2a7f8ac.1738746872.git.namcao@linutronix.de
---
 net/core/dev.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index b91658e8aedb4..1ad2ca4d21169 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6931,8 +6931,7 @@ void netif_napi_add_weight_locked(struct net_device *dev,
 
 	INIT_LIST_HEAD(&napi->poll_list);
 	INIT_HLIST_NODE(&napi->napi_hash_node);
-	hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
-	napi->timer.function = napi_watchdog;
+	hrtimer_setup(&napi->timer, napi_watchdog, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
 	init_gro_hash(napi);
 	napi->skb = NULL;
 	INIT_LIST_HEAD(&napi->rx_list);

From efcb2d32a8f5afb4173a868a7616db1718641420 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:43:22 +0100
Subject: [PATCH 0250/1173] net/sched: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/f1d4843589dd924743b35de1f0920c4a4c43be01.1738746872.git.namcao@linutronix.de
---
 net/sched/act_gate.c   | 3 +--
 net/sched/sch_api.c    | 3 +--
 net/sched/sch_taprio.c | 6 ++----
 3 files changed, 4 insertions(+), 8 deletions(-)

diff --git a/net/sched/act_gate.c b/net/sched/act_gate.c
index 91c0ec729823b..c1f75f2727576 100644
--- a/net/sched/act_gate.c
+++ b/net/sched/act_gate.c
@@ -287,8 +287,7 @@ static void gate_setup_timer(struct tcf_gate *gact, u64 basetime,
 	gact->param.tcfg_basetime = basetime;
 	gact->param.tcfg_clockid = clockid;
 	gact->tk_offset = tko;
-	hrtimer_init(&gact->hitimer, clockid, HRTIMER_MODE_ABS_SOFT);
-	gact->hitimer.function = gate_timer_func;
+	hrtimer_setup(&gact->hitimer, gate_timer_func, clockid, HRTIMER_MODE_ABS_SOFT);
 }
 
 static int tcf_gate_init(struct net *net, struct nlattr *nla,
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index e3e91cf867eb9..6d85b342a8576 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -619,8 +619,7 @@ static enum hrtimer_restart qdisc_watchdog(struct hrtimer *timer)
 void qdisc_watchdog_init_clockid(struct qdisc_watchdog *wd, struct Qdisc *qdisc,
 				 clockid_t clockid)
 {
-	hrtimer_init(&wd->timer, clockid, HRTIMER_MODE_ABS_PINNED);
-	wd->timer.function = qdisc_watchdog;
+	hrtimer_setup(&wd->timer, qdisc_watchdog, clockid, HRTIMER_MODE_ABS_PINNED);
 	wd->qdisc = qdisc;
 }
 EXPORT_SYMBOL(qdisc_watchdog_init_clockid);
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index a68e17891b0b5..14021b8123290 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -1932,8 +1932,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 	if (!TXTIME_ASSIST_IS_ENABLED(q->flags) &&
 	    !FULL_OFFLOAD_IS_ENABLED(q->flags) &&
 	    !hrtimer_active(&q->advance_timer)) {
-		hrtimer_init(&q->advance_timer, q->clockid, HRTIMER_MODE_ABS);
-		q->advance_timer.function = advance_sched;
+		hrtimer_setup(&q->advance_timer, advance_sched, q->clockid, HRTIMER_MODE_ABS);
 	}
 
 	err = taprio_get_start_time(sch, new_admin, &start);
@@ -2056,8 +2055,7 @@ static int taprio_init(struct Qdisc *sch, struct nlattr *opt,
 
 	spin_lock_init(&q->current_entry_lock);
 
-	hrtimer_init(&q->advance_timer, CLOCK_TAI, HRTIMER_MODE_ABS);
-	q->advance_timer.function = advance_sched;
+	hrtimer_setup(&q->advance_timer, advance_sched, CLOCK_TAI, HRTIMER_MODE_ABS);
 
 	q->root = sch;
 

From 96b2fb3e6d146ab0b286101ddea6ad0cca8335c8 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:43:23 +0100
Subject: [PATCH 0251/1173] mac802154: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/5a89d86092d11a1d0cdfdfaa33990aaf7f1eec87.1738746872.git.namcao@linutronix.de
---
 net/mac802154/main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/mac802154/main.c b/net/mac802154/main.c
index 21b7c3b280b45..ea1efef3572ae 100644
--- a/net/mac802154/main.c
+++ b/net/mac802154/main.c
@@ -213,8 +213,8 @@ int ieee802154_register_hw(struct ieee802154_hw *hw)
 		goto out_wq;
 	}
 
-	hrtimer_init(&local->ifs_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	local->ifs_timer.function = ieee802154_xmit_ifs_timer;
+	hrtimer_setup(&local->ifs_timer, ieee802154_xmit_ifs_timer, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 
 	wpan_phy_set_dev(local->phy, local->hw.parent);
 

From 553f9a8be728cdf884985b2d9a057d3af09f60f3 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:43:24 +0100
Subject: [PATCH 0252/1173] tcp: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/a16c227cc6882d8aecf658e6a7e38b74e7fd7573.1738746872.git.namcao@linutronix.de
---
 net/ipv4/tcp_timer.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index b412ed88ccd9a..e7a75afa995d4 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -884,11 +884,9 @@ void tcp_init_xmit_timers(struct sock *sk)
 {
 	inet_csk_init_xmit_timers(sk, &tcp_write_timer, &tcp_delack_timer,
 				  &tcp_keepalive_timer);
-	hrtimer_init(&tcp_sk(sk)->pacing_timer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_ABS_PINNED_SOFT);
-	tcp_sk(sk)->pacing_timer.function = tcp_pace_kick;
+	hrtimer_setup(&tcp_sk(sk)->pacing_timer, tcp_pace_kick, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_ABS_PINNED_SOFT);
 
-	hrtimer_init(&tcp_sk(sk)->compressed_ack_timer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_REL_PINNED_SOFT);
-	tcp_sk(sk)->compressed_ack_timer.function = tcp_compressed_ack_kick;
+	hrtimer_setup(&tcp_sk(sk)->compressed_ack_timer, tcp_compressed_ack_kick, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL_PINNED_SOFT);
 }

From e0eaefcd7e4449a444b557578b60a988636b4a71 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:43:25 +0100
Subject: [PATCH 0253/1173] can: m_can: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Marc Kleine-Budde <mkl@pengutronix.de>
Link: https://lore.kernel.org/all/f1a87fcba211f6ce262a2d23fd152185f452c32d.1738746872.git.namcao@linutronix.de
---
 drivers/net/can/m_can/m_can.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index d025d4163fd12..884a6352c42b7 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -2420,12 +2420,11 @@ int m_can_class_register(struct m_can_classdev *cdev)
 
 	if (!cdev->net->irq) {
 		dev_dbg(cdev->dev, "Polling enabled, initialize hrtimer");
-		hrtimer_init(&cdev->hrtimer, CLOCK_MONOTONIC,
-			     HRTIMER_MODE_REL_PINNED);
-		cdev->hrtimer.function = &hrtimer_callback;
+		hrtimer_setup(&cdev->hrtimer, &hrtimer_callback, CLOCK_MONOTONIC,
+			      HRTIMER_MODE_REL_PINNED);
 	} else {
-		hrtimer_init(&cdev->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-		cdev->hrtimer.function = m_can_coalescing_timer;
+		hrtimer_setup(&cdev->hrtimer, m_can_coalescing_timer, CLOCK_MONOTONIC,
+			      HRTIMER_MODE_REL);
 	}
 
 	ret = m_can_dev_setup(cdev);

From 881ec0c6db17ec6bacd968d6899508be3cf00ff4 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:43:26 +0100
Subject: [PATCH 0254/1173] can: mcp251xfd: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Marc Kleine-Budde <mkl@pengutronix.de>
Link: https://lore.kernel.org/all/af32e1b1814263485be17bca9707d555f857c53f.1738746872.git.namcao@linutronix.de
---
 drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c
index 7209a831f0f20..c34f2067a989c 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c
@@ -541,11 +541,11 @@ int mcp251xfd_ring_alloc(struct mcp251xfd_priv *priv)
 	}
 	priv->rx_ring_num = i;
 
-	hrtimer_init(&priv->rx_irq_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	priv->rx_irq_timer.function = mcp251xfd_rx_irq_timer;
+	hrtimer_setup(&priv->rx_irq_timer, mcp251xfd_rx_irq_timer, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 
-	hrtimer_init(&priv->tx_irq_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	priv->tx_irq_timer.function = mcp251xfd_tx_irq_timer;
+	hrtimer_setup(&priv->tx_irq_timer, mcp251xfd_tx_irq_timer, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 
 	return 0;
 }

From 806e32248e22582715dbbb7664567b81b9d6928a Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:43:27 +0100
Subject: [PATCH 0255/1173] can: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Most of this patch is generated by Coccinelle. Except for the TX thrtimer
in bcm_tx_setup() because this timer is not used and the callback function
is never set. For this particular case, set the callback to
hrtimer_dummy_timeout()

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Marc Kleine-Budde <mkl@pengutronix.de>
Link: https://lore.kernel.org/all/a3a6be42c818722ad41758457408a32163bfd9a0.1738746872.git.namcao@linutronix.de
---
 include/linux/hrtimer.h   |  5 +++++
 kernel/time/hrtimer.c     |  5 -----
 net/can/bcm.c             | 20 ++++++++------------
 net/can/isotp.c           | 10 ++++------
 net/can/j1939/bus.c       |  4 ++--
 net/can/j1939/transport.c |  8 ++------
 6 files changed, 21 insertions(+), 31 deletions(-)

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index f7bfdcf0dda3f..acae379541c52 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -223,6 +223,11 @@ static inline void hrtimer_cancel_wait_running(struct hrtimer *timer)
 }
 #endif
 
+static inline enum hrtimer_restart hrtimer_dummy_timeout(struct hrtimer *unused)
+{
+	return HRTIMER_NORESTART;
+}
+
 /* Exported timer functions: */
 
 /* Initialize timers: */
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index deb1aa32814e3..47df6f50e12cf 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -1597,11 +1597,6 @@ static inline int hrtimer_clockid_to_base(clockid_t clock_id)
 	return HRTIMER_BASE_MONOTONIC;
 }
 
-static enum hrtimer_restart hrtimer_dummy_timeout(struct hrtimer *unused)
-{
-	return HRTIMER_NORESTART;
-}
-
 static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 			   enum hrtimer_mode mode)
 {
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 217049fa496e9..526cb6cd901fb 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -1011,13 +1011,12 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		op->ifindex = ifindex;
 
 		/* initialize uninitialized (kzalloc) structure */
-		hrtimer_init(&op->timer, CLOCK_MONOTONIC,
-			     HRTIMER_MODE_REL_SOFT);
-		op->timer.function = bcm_tx_timeout_handler;
+		hrtimer_setup(&op->timer, bcm_tx_timeout_handler, CLOCK_MONOTONIC,
+			      HRTIMER_MODE_REL_SOFT);
 
 		/* currently unused in tx_ops */
-		hrtimer_init(&op->thrtimer, CLOCK_MONOTONIC,
-			     HRTIMER_MODE_REL_SOFT);
+		hrtimer_setup(&op->thrtimer, hrtimer_dummy_timeout, CLOCK_MONOTONIC,
+			      HRTIMER_MODE_REL_SOFT);
 
 		/* add this bcm_op to the list of the tx_ops */
 		list_add(&op->list, &bo->tx_ops);
@@ -1192,13 +1191,10 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		op->rx_ifindex = ifindex;
 
 		/* initialize uninitialized (kzalloc) structure */
-		hrtimer_init(&op->timer, CLOCK_MONOTONIC,
-			     HRTIMER_MODE_REL_SOFT);
-		op->timer.function = bcm_rx_timeout_handler;
-
-		hrtimer_init(&op->thrtimer, CLOCK_MONOTONIC,
-			     HRTIMER_MODE_REL_SOFT);
-		op->thrtimer.function = bcm_rx_thr_handler;
+		hrtimer_setup(&op->timer, bcm_rx_timeout_handler, CLOCK_MONOTONIC,
+			      HRTIMER_MODE_REL_SOFT);
+		hrtimer_setup(&op->thrtimer, bcm_rx_thr_handler, CLOCK_MONOTONIC,
+			      HRTIMER_MODE_REL_SOFT);
 
 		/* add this bcm_op to the list of the rx_ops */
 		list_add(&op->list, &bo->rx_ops);
diff --git a/net/can/isotp.c b/net/can/isotp.c
index 16046931542a5..442c343afe1f7 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -1634,12 +1634,10 @@ static int isotp_init(struct sock *sk)
 	so->rx.buflen = ARRAY_SIZE(so->rx.sbuf);
 	so->tx.buflen = ARRAY_SIZE(so->tx.sbuf);
 
-	hrtimer_init(&so->rxtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
-	so->rxtimer.function = isotp_rx_timer_handler;
-	hrtimer_init(&so->txtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
-	so->txtimer.function = isotp_tx_timer_handler;
-	hrtimer_init(&so->txfrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
-	so->txfrtimer.function = isotp_txfr_timer_handler;
+	hrtimer_setup(&so->rxtimer, isotp_rx_timer_handler, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
+	hrtimer_setup(&so->txtimer, isotp_tx_timer_handler, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
+	hrtimer_setup(&so->txfrtimer, isotp_txfr_timer_handler, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL_SOFT);
 
 	init_waitqueue_head(&so->wait);
 	spin_lock_init(&so->rx_lock);
diff --git a/net/can/j1939/bus.c b/net/can/j1939/bus.c
index 4866879016021..39844f14eed86 100644
--- a/net/can/j1939/bus.c
+++ b/net/can/j1939/bus.c
@@ -158,8 +158,8 @@ struct j1939_ecu *j1939_ecu_create_locked(struct j1939_priv *priv, name_t name)
 	ecu->addr = J1939_IDLE_ADDR;
 	ecu->name = name;
 
-	hrtimer_init(&ecu->ac_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
-	ecu->ac_timer.function = j1939_ecu_timer_handler;
+	hrtimer_setup(&ecu->ac_timer, j1939_ecu_timer_handler, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL_SOFT);
 	INIT_LIST_HEAD(&ecu->list);
 
 	j1939_priv_get(priv);
diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c
index 9b72d118d756d..fbf5c8001c9df 100644
--- a/net/can/j1939/transport.c
+++ b/net/can/j1939/transport.c
@@ -1511,12 +1511,8 @@ static struct j1939_session *j1939_session_new(struct j1939_priv *priv,
 	skcb = j1939_skb_to_cb(skb);
 	memcpy(&session->skcb, skcb, sizeof(session->skcb));
 
-	hrtimer_init(&session->txtimer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_REL_SOFT);
-	session->txtimer.function = j1939_tp_txtimer;
-	hrtimer_init(&session->rxtimer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_REL_SOFT);
-	session->rxtimer.function = j1939_tp_rxtimer;
+	hrtimer_setup(&session->txtimer, j1939_tp_txtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
+	hrtimer_setup(&session->rxtimer, j1939_tp_rxtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
 
 	netdev_dbg(priv->ndev, "%s: 0x%p: sa: %02x, da: %02x\n",
 		   __func__, session, skcb->addr.sa, skcb->addr.da);

From e9cc3a8936ee7740b59547b369d60febbbbd1be0 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:43:28 +0100
Subject: [PATCH 0256/1173] net: ethernet: ti: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/bd34d3d0dba9a47b6ec5d14776941e9aa118c7d2.1738746872.git.namcao@linutronix.de
---
 drivers/net/ethernet/ti/am65-cpsw-nuss.c     | 9 ++++-----
 drivers/net/ethernet/ti/icssg/icssg_common.c | 5 ++---
 drivers/net/ethernet/ti/icssg/icssg_prueth.c | 5 ++---
 3 files changed, 8 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index 2806238629f82..361169db4befb 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -2311,8 +2311,8 @@ static int am65_cpsw_nuss_ndev_add_tx_napi(struct am65_cpsw_common *common)
 	for (i = 0; i < common->tx_ch_num; i++) {
 		struct am65_cpsw_tx_chn *tx_chn = &common->tx_chns[i];
 
-		hrtimer_init(&tx_chn->tx_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
-		tx_chn->tx_hrtimer.function = &am65_cpsw_nuss_tx_timer_callback;
+		hrtimer_setup(&tx_chn->tx_hrtimer, &am65_cpsw_nuss_tx_timer_callback,
+			      CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
 
 		ret = devm_request_irq(dev, tx_chn->irq,
 				       am65_cpsw_nuss_tx_irq,
@@ -2565,9 +2565,8 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common)
 		snprintf(flow->name,
 			 sizeof(flow->name), "%s-rx%d",
 			 dev_name(dev), i);
-		hrtimer_init(&flow->rx_hrtimer, CLOCK_MONOTONIC,
-			     HRTIMER_MODE_REL_PINNED);
-		flow->rx_hrtimer.function = &am65_cpsw_nuss_rx_timer_callback;
+		hrtimer_setup(&flow->rx_hrtimer, &am65_cpsw_nuss_rx_timer_callback, CLOCK_MONOTONIC,
+			      HRTIMER_MODE_REL_PINNED);
 
 		ret = devm_request_irq(dev, flow->irq,
 				       am65_cpsw_nuss_rx_irq,
diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c
index 74f0f200a89d4..6c1b8ff563e06 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_common.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_common.c
@@ -249,9 +249,8 @@ int prueth_ndev_add_tx_napi(struct prueth_emac *emac)
 		struct prueth_tx_chn *tx_chn = &emac->tx_chns[i];
 
 		netif_napi_add_tx(emac->ndev, &tx_chn->napi_tx, emac_napi_tx_poll);
-		hrtimer_init(&tx_chn->tx_hrtimer, CLOCK_MONOTONIC,
-			     HRTIMER_MODE_REL_PINNED);
-		tx_chn->tx_hrtimer.function = &emac_tx_timer_callback;
+		hrtimer_setup(&tx_chn->tx_hrtimer, &emac_tx_timer_callback, CLOCK_MONOTONIC,
+			      HRTIMER_MODE_REL_PINNED);
 		ret = request_irq(tx_chn->irq, prueth_tx_irq,
 				  IRQF_TRIGGER_HIGH, tx_chn->name,
 				  tx_chn);
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index 00ed978605478..d3bdde6bd3aac 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -1169,9 +1169,8 @@ static int prueth_netdev_init(struct prueth *prueth,
 	ndev->hw_features |= NETIF_PRUETH_HSR_OFFLOAD_FEATURES;
 
 	netif_napi_add(ndev, &emac->napi_rx, icssg_napi_rx_poll);
-	hrtimer_init(&emac->rx_hrtimer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_REL_PINNED);
-	emac->rx_hrtimer.function = &emac_rx_timer_callback;
+	hrtimer_setup(&emac->rx_hrtimer, &emac_rx_timer_callback, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL_PINNED);
 	prueth->emac[mac] = emac;
 
 	return 0;

From f12185af60cb4b81a22e600cbbf33fc91ba662f1 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:43:29 +0100
Subject: [PATCH 0257/1173] net: ethernet: cortina: Switch to use
 hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/ddbeac1e5d81df33e9cccb099f520111cb8ce9c4.1738746872.git.namcao@linutronix.de
---
 drivers/net/ethernet/cortina/gemini.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index 991e3839858b5..2b4bb74f21bf2 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -1833,9 +1833,8 @@ static int gmac_open(struct net_device *netdev)
 	gmac_enable_tx_rx(netdev);
 	netif_tx_start_all_queues(netdev);
 
-	hrtimer_init(&port->rx_coalesce_timer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_REL);
-	port->rx_coalesce_timer.function = &gmac_coalesce_delay_expired;
+	hrtimer_setup(&port->rx_coalesce_timer, &gmac_coalesce_delay_expired, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 
 	netdev_dbg(netdev, "opened\n");
 

From 66a3898a203d7a62967812d97629ee402a6f2221 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:43:30 +0100
Subject: [PATCH 0258/1173] net: ethernet: ec_bhf: Switch to use
 hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/2d8fcf9bf83af507f1ca25cb068af2ac32cdcb2c.1738746872.git.namcao@linutronix.de
---
 drivers/net/ethernet/ec_bhf.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/ec_bhf.c b/drivers/net/ethernet/ec_bhf.c
index 44af1d13d9317..67275aa4f65b2 100644
--- a/drivers/net/ethernet/ec_bhf.c
+++ b/drivers/net/ethernet/ec_bhf.c
@@ -416,8 +416,7 @@ static int ec_bhf_open(struct net_device *net_dev)
 
 	netif_start_queue(net_dev);
 
-	hrtimer_init(&priv->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	priv->hrtimer.function = ec_bhf_timer_fun;
+	hrtimer_setup(&priv->hrtimer, ec_bhf_timer_fun, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	hrtimer_start(&priv->hrtimer, polling_frequency, HRTIMER_MODE_REL);
 
 	return 0;

From 964177da435cc466c4ff4774f18e37aa03fafe4a Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:43:31 +0100
Subject: [PATCH 0259/1173] net: ethernet: hisilicon: Switch to use
 hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/11f5140e157cc0cd02a715f531217b021743aa71.1738746872.git.namcao@linutronix.de
---
 drivers/net/ethernet/hisilicon/hip04_eth.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c
index a376d4bdf2819..18376bcc718a2 100644
--- a/drivers/net/ethernet/hisilicon/hip04_eth.c
+++ b/drivers/net/ethernet/hisilicon/hip04_eth.c
@@ -934,8 +934,6 @@ static int hip04_mac_probe(struct platform_device *pdev)
 	priv->chan = arg.args[1] * RX_DESC_NUM;
 	priv->group = arg.args[2];
 
-	hrtimer_init(&priv->tx_coalesce_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-
 	/* BQL will try to keep the TX queue as short as possible, but it can't
 	 * be faster than tx_coalesce_usecs, so we need a fast timeout here,
 	 * but also long enough to gather up enough frames to ensure we don't
@@ -944,7 +942,7 @@ static int hip04_mac_probe(struct platform_device *pdev)
 	 */
 	priv->tx_coalesce_frames = TX_DESC_NUM * 3 / 4;
 	priv->tx_coalesce_usecs = 200;
-	priv->tx_coalesce_timer.function = tx_done;
+	hrtimer_setup(&priv->tx_coalesce_timer, tx_done, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 
 	priv->map = syscon_node_to_regmap(arg.np);
 	of_node_put(arg.np);

From 7b63b1dc473e5ad3c4c0f404d198e0c18dcbfa64 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:43:32 +0100
Subject: [PATCH 0260/1173] net: sparx5: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/d8f0e09bfa4bd4850e363645cc634afeb5779b88.1738746872.git.namcao@linutronix.de
---
 drivers/net/ethernet/microchip/sparx5/sparx5_packet.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c
index 138ac58fae51a..f713656f1fae1 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c
@@ -375,6 +375,6 @@ irqreturn_t sparx5_xtr_handler(int irq, void *_sparx5)
 
 void sparx5_port_inj_timer_setup(struct sparx5_port *port)
 {
-	hrtimer_init(&port->inj_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	port->inj_timer.function = sparx5_injection_timeout;
+	hrtimer_setup(&port->inj_timer, sparx5_injection_timeout, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 }

From dbf13c4278a5673d8fb6ba87ea81c92b886b3aca Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:43:33 +0100
Subject: [PATCH 0261/1173] net: ieee802154: at86rf230: Switch to use
 hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/9f701c1b64e248539772aee62e130a7e50bbf1b0.1738746872.git.namcao@linutronix.de
---
 drivers/net/ieee802154/at86rf230.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c
index f632b0cfd5ae0..fd91f8a45bce8 100644
--- a/drivers/net/ieee802154/at86rf230.c
+++ b/drivers/net/ieee802154/at86rf230.c
@@ -776,8 +776,8 @@ at86rf230_setup_spi_messages(struct at86rf230_local *lp,
 	state->trx.tx_buf = state->buf;
 	state->trx.rx_buf = state->buf;
 	spi_message_add_tail(&state->trx, &state->msg);
-	hrtimer_init(&state->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	state->timer.function = at86rf230_async_state_timer;
+	hrtimer_setup(&state->timer, at86rf230_async_state_timer, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 }
 
 static irqreturn_t at86rf230_isr(int irq, void *data)

From 4781599491bd62d88c34bb1dd6ac17d5f452fa31 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:43:34 +0100
Subject: [PATCH 0262/1173] net: mvpp2: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/44e2ebca1a3c1b90213cdb79f7a19ebe0ae70510.1738746872.git.namcao@linutronix.de
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index dd76c1b7ed3a1..3c7b43712d25f 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -6985,9 +6985,8 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 		for (thread = 0; thread < priv->nthreads; thread++) {
 			port_pcpu = per_cpu_ptr(port->pcpu, thread);
 
-			hrtimer_init(&port_pcpu->tx_done_timer, CLOCK_MONOTONIC,
-				     HRTIMER_MODE_REL_PINNED_SOFT);
-			port_pcpu->tx_done_timer.function = mvpp2_hr_timer_cb;
+			hrtimer_setup(&port_pcpu->tx_done_timer, mvpp2_hr_timer_cb, CLOCK_MONOTONIC,
+				      HRTIMER_MODE_REL_PINNED_SOFT);
 			port_pcpu->timer_scheduled = false;
 			port_pcpu->dev = dev;
 		}

From 3c85516612f8861cdfeefc300b7631f0d4797fbd Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:43:35 +0100
Subject: [PATCH 0263/1173] net: qualcomm: rmnet: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/4312885d95fc99053b2c285f74cc83a852c03f4a.1738746872.git.namcao@linutronix.de
---
 drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c
index a5e3d1a88305e..8b4640c5d61eb 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c
@@ -686,8 +686,8 @@ void rmnet_map_update_ul_agg_config(struct rmnet_port *port, u32 size,
 
 void rmnet_map_tx_aggregate_init(struct rmnet_port *port)
 {
-	hrtimer_init(&port->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	port->hrtimer.function = rmnet_map_flush_tx_packet_queue;
+	hrtimer_setup(&port->hrtimer, rmnet_map_flush_tx_packet_queue, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 	spin_lock_init(&port->agg_lock);
 	rmnet_map_update_ul_agg_config(port, 4096, 1, 800);
 	INIT_WORK(&port->agg_wq, rmnet_map_flush_tx_packet_work);

From 78afb7fa96ed9742c09a033782f50908c3d8e3cf Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:43:36 +0100
Subject: [PATCH 0264/1173] net: stmmac: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/73598e0c22ca99ce7a0e863298a0e0902f4d6e1d.1738746872.git.namcao@linutronix.de
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index c0ae7db96f46f..554d2c0a8fde0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3199,8 +3199,7 @@ static void stmmac_init_coalesce(struct stmmac_priv *priv)
 		priv->tx_coal_frames[chan] = STMMAC_TX_FRAMES;
 		priv->tx_coal_timer[chan] = STMMAC_COAL_TX_TIMER;
 
-		hrtimer_init(&tx_q->txtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-		tx_q->txtimer.function = stmmac_tx_timer;
+		hrtimer_setup(&tx_q->txtimer, stmmac_tx_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	}
 
 	for (chan = 0; chan < rx_channel_count; chan++)
@@ -6970,8 +6969,7 @@ int stmmac_xdp_open(struct net_device *dev)
 		stmmac_set_tx_tail_ptr(priv, priv->ioaddr,
 				       tx_q->tx_tail_addr, chan);
 
-		hrtimer_init(&tx_q->txtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-		tx_q->txtimer.function = stmmac_tx_timer;
+		hrtimer_setup(&tx_q->txtimer, stmmac_tx_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	}
 
 	/* Enable the MAC Rx/Tx */

From e193660f5e7feabc461142a96c3237d7618dfeb3 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:43:37 +0100
Subject: [PATCH 0265/1173] net: fec: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/c68759ce7879a41d33d1d435c721f156cb1683c2.1738746872.git.namcao@linutronix.de
---
 drivers/net/ethernet/freescale/fec_ptp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
index 7f6b574320716..fe4e7f99b6a3a 100644
--- a/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/drivers/net/ethernet/freescale/fec_ptp.c
@@ -739,8 +739,8 @@ void fec_ptp_init(struct platform_device *pdev, int irq_idx)
 
 	INIT_DELAYED_WORK(&fep->time_keep, fec_time_keep);
 
-	hrtimer_init(&fep->perout_timer, CLOCK_REALTIME, HRTIMER_MODE_REL);
-	fep->perout_timer.function = fec_ptp_pps_perout_handler;
+	hrtimer_setup(&fep->perout_timer, fec_ptp_pps_perout_handler, CLOCK_REALTIME,
+		      HRTIMER_MODE_REL);
 
 	irq = platform_get_irq_byname_optional(pdev, "pps");
 	if (irq < 0)

From d4bcc73352e467533b077e9253cbe68892adf6a1 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:43:38 +0100
Subject: [PATCH 0266/1173] net: wwan: iosm: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/e42d7d29879017d4b5ca9555f806e782658e3f21.1738746872.git.namcao@linutronix.de
---
 drivers/net/wwan/iosm/iosm_ipc_imem.c | 24 ++++++++++--------------
 1 file changed, 10 insertions(+), 14 deletions(-)

diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem.c b/drivers/net/wwan/iosm/iosm_ipc_imem.c
index 829515a601b37..530a3ea47a1a7 100644
--- a/drivers/net/wwan/iosm/iosm_ipc_imem.c
+++ b/drivers/net/wwan/iosm/iosm_ipc_imem.c
@@ -1381,24 +1381,20 @@ struct iosm_imem *ipc_imem_init(struct iosm_pcie *pcie, unsigned int device_id,
 	/* The phase is set to power off. */
 	ipc_imem->phase = IPC_P_OFF;
 
-	hrtimer_init(&ipc_imem->startup_timer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_REL);
-	ipc_imem->startup_timer.function = ipc_imem_startup_timer_cb;
+	hrtimer_setup(&ipc_imem->startup_timer, ipc_imem_startup_timer_cb, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 
-	hrtimer_init(&ipc_imem->tdupdate_timer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_REL);
-	ipc_imem->tdupdate_timer.function = ipc_imem_td_update_timer_cb;
+	hrtimer_setup(&ipc_imem->tdupdate_timer, ipc_imem_td_update_timer_cb, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 
-	hrtimer_init(&ipc_imem->fast_update_timer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_REL);
-	ipc_imem->fast_update_timer.function = ipc_imem_fast_update_timer_cb;
+	hrtimer_setup(&ipc_imem->fast_update_timer, ipc_imem_fast_update_timer_cb, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 
-	hrtimer_init(&ipc_imem->td_alloc_timer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_REL);
-	ipc_imem->td_alloc_timer.function = ipc_imem_td_alloc_timer_cb;
+	hrtimer_setup(&ipc_imem->td_alloc_timer, ipc_imem_td_alloc_timer_cb, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 
-	hrtimer_init(&ipc_imem->adb_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	ipc_imem->adb_timer.function = ipc_imem_adb_timer_cb;
+	hrtimer_setup(&ipc_imem->adb_timer, ipc_imem_adb_timer_cb, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 
 	if (ipc_imem_config(ipc_imem)) {
 		dev_err(ipc_imem->dev, "failed to initialize the imem");

From d1ba57528f44b3d3b270c9ecbf256fc6c88c748e Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:43:39 +0100
Subject: [PATCH 0267/1173] net/cdc_ncm: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/219735f98754fb30dcfd892fbaa5766f9d78c1f1.1738746872.git.namcao@linutronix.de
---
 drivers/net/usb/cdc_ncm.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index d5c47a2a62dcc..34e82f1e37d96 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -833,8 +833,7 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_
 
 	ctx->dev = dev;
 
-	hrtimer_init(&ctx->tx_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	ctx->tx_timer.function = &cdc_ncm_tx_timer_cb;
+	hrtimer_setup(&ctx->tx_timer, &cdc_ncm_tx_timer_cb, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	tasklet_setup(&ctx->bh, cdc_ncm_txpath_bh);
 	atomic_set(&ctx->stop, 0);
 	spin_lock_init(&ctx->mtx);

From cbe2691bee4e54024b9985ef78e740d9655d92f3 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:43:40 +0100
Subject: [PATCH 0268/1173] wifi: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/71fbc442aee9a9e892e475f3bbf8f368c6692a55.1738746872.git.namcao@linutronix.de
---
 drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c | 4 ++--
 drivers/net/wireless/virtual/mac80211_hwsim.c         | 6 ++----
 2 files changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c b/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c
index 0e1ede9314d8f..4840d0b500b30 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c
@@ -264,8 +264,8 @@ void mt76x02u_init_beacon_config(struct mt76x02_dev *dev)
 	};
 	dev->beacon_ops = &beacon_ops;
 
-	hrtimer_init(&dev->pre_tbtt_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	dev->pre_tbtt_timer.function = mt76x02u_pre_tbtt_interrupt;
+	hrtimer_setup(&dev->pre_tbtt_timer, mt76x02u_pre_tbtt_interrupt, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 	INIT_WORK(&dev->pre_tbtt_work, mt76x02u_pre_tbtt_work);
 
 	mt76x02_init_beacon_config(dev);
diff --git a/drivers/net/wireless/virtual/mac80211_hwsim.c b/drivers/net/wireless/virtual/mac80211_hwsim.c
index cf6a331d40427..fb187a9e984ed 100644
--- a/drivers/net/wireless/virtual/mac80211_hwsim.c
+++ b/drivers/net/wireless/virtual/mac80211_hwsim.c
@@ -5548,10 +5548,8 @@ static int mac80211_hwsim_new_radio(struct genl_info *info,
 	wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST);
 
 	for (i = 0; i < ARRAY_SIZE(data->link_data); i++) {
-		hrtimer_init(&data->link_data[i].beacon_timer, CLOCK_MONOTONIC,
-			     HRTIMER_MODE_ABS_SOFT);
-		data->link_data[i].beacon_timer.function =
-			mac80211_hwsim_beacon;
+		hrtimer_setup(&data->link_data[i].beacon_timer, mac80211_hwsim_beacon,
+			      CLOCK_MONOTONIC, HRTIMER_MODE_ABS_SOFT);
 		data->link_data[i].link_id = i;
 	}
 

From 1528fd734e7b8fabea014234fc3f35d811f2f6f7 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:43:41 +0100
Subject: [PATCH 0269/1173] wifi: rt2x00: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely. This new function replaces
hrtimer_init().

However, converting this driver is not obvious: the driver calls
hrtimer_init() in rt2x00dev.c, then set the hrtimer's callback function in
rt2800mmio.c and rt2800usb.c. Therefore, switching to the new function is
not a simple one-for-one replacement.

With the lack of hardware to verify any non-trivial changes, keep it simple
and calls hrtimer_setup() with hrtimer_dummy_timeout() as callback function
pointer.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/f086be77528edf0dfb455af4cb984b863084a455.1738746872.git.namcao@linutronix.de
---
 drivers/net/wireless/ralink/rt2x00/rt2x00dev.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c b/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c
index 9e7d9dbe954cf..432ddfac2c33e 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c
@@ -1391,8 +1391,8 @@ int rt2x00lib_probe_dev(struct rt2x00_dev *rt2x00dev)
 	mutex_init(&rt2x00dev->conf_mutex);
 	INIT_LIST_HEAD(&rt2x00dev->bar_list);
 	spin_lock_init(&rt2x00dev->bar_list_lock);
-	hrtimer_init(&rt2x00dev->txstatus_timer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_REL);
+	hrtimer_setup(&rt2x00dev->txstatus_timer, hrtimer_dummy_timeout, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 
 	set_bit(DEVICE_STATE_PRESENT, &rt2x00dev->flags);
 

From e26ad10db84bf60b56dfe738ded119a5ae1ca2f2 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:43:42 +0100
Subject: [PATCH 0270/1173] igc: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/baeaabb84aef1803dfae385f6e9614d6fc547667.1738746872.git.namcao@linutronix.de
---
 drivers/net/ethernet/intel/igc/igc_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 84307bb7313e0..733820a0c3508 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -7090,8 +7090,8 @@ static int igc_probe(struct pci_dev *pdev,
 	INIT_WORK(&adapter->reset_task, igc_reset_task);
 	INIT_WORK(&adapter->watchdog_task, igc_watchdog_task);
 
-	hrtimer_init(&adapter->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	adapter->hrtimer.function = &igc_qbv_scheduling_timer;
+	hrtimer_setup(&adapter->hrtimer, &igc_qbv_scheduling_timer, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 
 	/* Initialize link properties that are user-changeable */
 	adapter->fc_autoneg = true;

From 7b449279f56ac9679b4e5a14ce484953b8deddf0 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:43:43 +0100
Subject: [PATCH 0271/1173] octeontx2-pf: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/a935bc6ca7933053f9e349578da4a8fb477b7c2d.1738746872.git.namcao@linutronix.de
---
 drivers/net/ethernet/marvell/octeontx2/af/ptp.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/ptp.c b/drivers/net/ethernet/marvell/octeontx2/af/ptp.c
index bcc96eed24813..66749b3649c1f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/ptp.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/ptp.c
@@ -545,8 +545,7 @@ static int ptp_probe(struct pci_dev *pdev,
 	spin_lock_init(&ptp->ptp_lock);
 	if (cn10k_ptp_errata(ptp)) {
 		ptp->read_ptp_tstmp = &read_ptp_tstmp_sec_nsec;
-		hrtimer_init(&ptp->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-		ptp->hrtimer.function = ptp_reset_thresh;
+		hrtimer_setup(&ptp->hrtimer, ptp_reset_thresh, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	} else {
 		ptp->read_ptp_tstmp = &read_ptp_tstmp_nsec;
 	}

From 1417c85d16257f4cc581acca218f4f9fb17ef952 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:43:44 +0100
Subject: [PATCH 0272/1173] xfrm: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/d338b246f087ee2b2a305348c896449e107a7ff4.1738746872.git.namcao@linutronix.de
---
 net/xfrm/xfrm_iptfs.c | 6 ++----
 net/xfrm/xfrm_state.c | 4 ++--
 2 files changed, 4 insertions(+), 6 deletions(-)

diff --git a/net/xfrm/xfrm_iptfs.c b/net/xfrm/xfrm_iptfs.c
index 755f1eea8bfa1..3b6d7284fc70a 100644
--- a/net/xfrm/xfrm_iptfs.c
+++ b/net/xfrm/xfrm_iptfs.c
@@ -2625,12 +2625,10 @@ static void __iptfs_init_state(struct xfrm_state *x,
 			       struct xfrm_iptfs_data *xtfs)
 {
 	__skb_queue_head_init(&xtfs->queue);
-	hrtimer_init(&xtfs->iptfs_timer, CLOCK_MONOTONIC, IPTFS_HRTIMER_MODE);
-	xtfs->iptfs_timer.function = iptfs_delay_timer;
+	hrtimer_setup(&xtfs->iptfs_timer, iptfs_delay_timer, CLOCK_MONOTONIC, IPTFS_HRTIMER_MODE);
 
 	spin_lock_init(&xtfs->drop_lock);
-	hrtimer_init(&xtfs->drop_timer, CLOCK_MONOTONIC, IPTFS_HRTIMER_MODE);
-	xtfs->drop_timer.function = iptfs_drop_timer;
+	hrtimer_setup(&xtfs->drop_timer, iptfs_drop_timer, CLOCK_MONOTONIC, IPTFS_HRTIMER_MODE);
 
 	/* Modify type (esp) adjustment values */
 
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index ad2202fa82f34..9bd14fdb67a57 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -746,8 +746,8 @@ struct xfrm_state *xfrm_state_alloc(struct net *net)
 		INIT_HLIST_NODE(&x->bysrc);
 		INIT_HLIST_NODE(&x->byspi);
 		INIT_HLIST_NODE(&x->byseq);
-		hrtimer_init(&x->mtimer, CLOCK_BOOTTIME, HRTIMER_MODE_ABS_SOFT);
-		x->mtimer.function = xfrm_timer_handler;
+		hrtimer_setup(&x->mtimer, xfrm_timer_handler, CLOCK_BOOTTIME,
+			      HRTIMER_MODE_ABS_SOFT);
 		timer_setup(&x->rtimer, xfrm_replay_timer_handler, 0);
 		x->curlft.add_time = ktime_get_real_seconds();
 		x->lft.soft_byte_limit = XFRM_INF;

From c305a4e98378903da5322c598381ad1ce643f4b4 Mon Sep 17 00:00:00 2001
From: Joel Granados <joel.granados@kernel.org>
Date: Tue, 18 Feb 2025 10:56:24 +0100
Subject: [PATCH 0273/1173] x86: Move sysctls into arch/x86

Move the following sysctl tables into arch/x86/kernel/setup.c:

  panic_on_{unrecoverable_nmi,io_nmi}
  bootloader_{type,version}
  io_delay_type
  unknown_nmi_panic
  acpi_realmode_flags

Variables moved from include/linux/ to arch/x86/include/asm/ because there
is no longer need for them outside arch/x86/kernel:

  acpi_realmode_flags
  panic_on_{unrecoverable_nmi,io_nmi}

Include <asm/nmi.h> in arch/s86/kernel/setup.h in order to bring in
panic_on_{io_nmi,unrecovered_nmi}.

This is part of a greater effort to move ctl tables into their
respective subsystems which will reduce the merge conflicts in
kerenel/sysctl.c.

Signed-off-by: Joel Granados <joel.granados@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250218-jag-mv_ctltables-v1-8-cd3698ab8d29@kernel.org
---
 arch/x86/include/asm/setup.h |  1 +
 arch/x86/include/asm/traps.h |  2 --
 arch/x86/kernel/setup.c      | 66 ++++++++++++++++++++++++++++++++++++
 include/linux/acpi.h         |  1 -
 kernel/sysctl.c              | 56 ------------------------------
 5 files changed, 67 insertions(+), 59 deletions(-)

diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index 85f4fde3515c4..a8d676bba5def 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -46,6 +46,7 @@ void setup_bios_corruption_check(void);
 void early_platform_quirks(void);
 
 extern unsigned long saved_video_mode;
+extern unsigned long acpi_realmode_flags;
 
 extern void reserve_standard_io_resources(void);
 extern void i386_reserve_resources(void);
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 1f1deaecd364b..869b880618018 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -35,8 +35,6 @@ static inline int get_si_code(unsigned long condition)
 		return TRAP_BRKPT;
 }
 
-extern int panic_on_unrecovered_nmi;
-
 void math_emulate(struct math_emu_info *);
 
 bool fault_in_kernel_space(unsigned long address);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index cebee310e2009..9f8ff3aad4f4e 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -56,6 +56,9 @@
 #include <asm/unwind.h>
 #include <asm/vsyscall.h>
 #include <linux/vmalloc.h>
+#if defined(CONFIG_X86_LOCAL_APIC)
+#include <asm/nmi.h>
+#endif
 
 /*
  * max_low_pfn_mapped: highest directly mapped pfn < 4 GB
@@ -146,6 +149,69 @@ static size_t ima_kexec_buffer_size;
 /* Boot loader ID and version as integers, for the benefit of proc_dointvec */
 int bootloader_type, bootloader_version;
 
+static const struct ctl_table x86_sysctl_table[] = {
+	{
+		.procname	= "panic_on_unrecovered_nmi",
+		.data		= &panic_on_unrecovered_nmi,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "panic_on_io_nmi",
+		.data		= &panic_on_io_nmi,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "bootloader_type",
+		.data		= &bootloader_type,
+		.maxlen		= sizeof(int),
+		.mode		= 0444,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "bootloader_version",
+		.data		= &bootloader_version,
+		.maxlen		= sizeof(int),
+		.mode		= 0444,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "io_delay_type",
+		.data		= &io_delay_type,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+#if defined(CONFIG_X86_LOCAL_APIC)
+	{
+		.procname       = "unknown_nmi_panic",
+		.data           = &unknown_nmi_panic,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec,
+	},
+#endif
+#if defined(CONFIG_ACPI_SLEEP)
+	{
+		.procname	= "acpi_video_flags",
+		.data		= &acpi_realmode_flags,
+		.maxlen		= sizeof(unsigned long),
+		.mode		= 0644,
+		.proc_handler	= proc_doulongvec_minmax,
+	},
+#endif
+};
+
+static int __init init_x86_sysctl(void)
+{
+	register_sysctl_init("kernel", x86_sysctl_table);
+	return 0;
+}
+arch_initcall(init_x86_sysctl);
+
 /*
  * Setup options
  */
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 4e495b29c640f..a70e62d69dc79 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -330,7 +330,6 @@ static inline bool acpi_sci_irq_valid(void)
 }
 
 extern int sbf_port;
-extern unsigned long acpi_realmode_flags;
 
 int acpi_register_gsi (struct device *dev, u32 gsi, int triggering, int polarity);
 int acpi_gsi_to_irq (u32 gsi, unsigned int *irq);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index cb57da499ebb1..8a37d30f2aa60 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1831,16 +1831,6 @@ static const struct ctl_table kern_table[] = {
 		.mode		= 0444,
 		.proc_handler	= proc_dointvec,
 	},
-#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86)
-	{
-		.procname       = "unknown_nmi_panic",
-		.data           = &unknown_nmi_panic,
-		.maxlen         = sizeof (int),
-		.mode           = 0644,
-		.proc_handler   = proc_dointvec,
-	},
-#endif
-
 #if (defined(CONFIG_X86_32) || defined(CONFIG_PARISC)) && \
 	defined(CONFIG_DEBUG_STACKOVERFLOW)
 	{
@@ -1851,43 +1841,6 @@ static const struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 #endif
-#if defined(CONFIG_X86)
-	{
-		.procname	= "panic_on_unrecovered_nmi",
-		.data		= &panic_on_unrecovered_nmi,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "panic_on_io_nmi",
-		.data		= &panic_on_io_nmi,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "bootloader_type",
-		.data		= &bootloader_type,
-		.maxlen		= sizeof (int),
-		.mode		= 0444,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "bootloader_version",
-		.data		= &bootloader_version,
-		.maxlen		= sizeof (int),
-		.mode		= 0444,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "io_delay_type",
-		.data		= &io_delay_type,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-#endif
 #if defined(CONFIG_MMU)
 	{
 		.procname	= "randomize_va_space",
@@ -1906,15 +1859,6 @@ static const struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 #endif
-#if	defined(CONFIG_ACPI_SLEEP) && defined(CONFIG_X86)
-	{
-		.procname	= "acpi_video_flags",
-		.data		= &acpi_realmode_flags,
-		.maxlen		= sizeof (unsigned long),
-		.mode		= 0644,
-		.proc_handler	= proc_doulongvec_minmax,
-	},
-#endif
 #ifdef CONFIG_SYSCTL_ARCH_UNALIGN_NO_WARN
 	{
 		.procname	= "ignore-unaligned-usertrap",

From a63cb05bd553d93e43bfac4a899cd356082d307c Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:45:49 +0100
Subject: [PATCH 0274/1173] USB: chipidea: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://lore.kernel.org/all/a6e43ac5a90f975343e1cef2d8346b4697ec0473.1738746904.git.namcao@linutronix.de
---
 drivers/usb/chipidea/otg_fsm.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/usb/chipidea/otg_fsm.c b/drivers/usb/chipidea/otg_fsm.c
index c17516c29b63b..a093544482d5c 100644
--- a/drivers/usb/chipidea/otg_fsm.c
+++ b/drivers/usb/chipidea/otg_fsm.c
@@ -424,8 +424,7 @@ static enum hrtimer_restart ci_otg_hrtimer_func(struct hrtimer *t)
 /* Initialize timers */
 static int ci_otg_init_timers(struct ci_hdrc *ci)
 {
-	hrtimer_init(&ci->otg_fsm_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
-	ci->otg_fsm_hrtimer.function = ci_otg_hrtimer_func;
+	hrtimer_setup(&ci->otg_fsm_hrtimer, ci_otg_hrtimer_func, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
 
 	return 0;
 }

From 4cf533bbdfab30011da84074f1c2fce71fcdfe28 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:45:50 +0100
Subject: [PATCH 0275/1173] usb: dwc2: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://lore.kernel.org/all/ab5762d4fd512ac318e7962109d80547d38419cd.1738746904.git.namcao@linutronix.de
---
 drivers/usb/dwc2/hcd_queue.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/usb/dwc2/hcd_queue.c b/drivers/usb/dwc2/hcd_queue.c
index 238c6fd50e75a..2a542a99ec447 100644
--- a/drivers/usb/dwc2/hcd_queue.c
+++ b/drivers/usb/dwc2/hcd_queue.c
@@ -1459,8 +1459,7 @@ static void dwc2_qh_init(struct dwc2_hsotg *hsotg, struct dwc2_qh *qh,
 	/* Initialize QH */
 	qh->hsotg = hsotg;
 	timer_setup(&qh->unreserve_timer, dwc2_unreserve_timer_fn, 0);
-	hrtimer_init(&qh->wait_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	qh->wait_timer.function = &dwc2_wait_timer_fn;
+	hrtimer_setup(&qh->wait_timer, &dwc2_wait_timer_fn, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	qh->ep_type = ep_type;
 	qh->ep_is_in = ep_is_in;
 

From e0e59e95eb388c16e9fbe796a253fd4b58478d36 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:45:51 +0100
Subject: [PATCH 0276/1173] usb: fotg210-hcd: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://lore.kernel.org/all/eeabb788995d7566017ebcff6cc2daa8da35432d.1738746904.git.namcao@linutronix.de
---
 drivers/usb/fotg210/fotg210-hcd.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/usb/fotg210/fotg210-hcd.c b/drivers/usb/fotg210/fotg210-hcd.c
index 3d404d19a205e..64c4965a160f4 100644
--- a/drivers/usb/fotg210/fotg210-hcd.c
+++ b/drivers/usb/fotg210/fotg210-hcd.c
@@ -4901,8 +4901,7 @@ static int hcd_fotg210_init(struct usb_hcd *hcd)
 	 */
 	fotg210->need_io_watchdog = 1;
 
-	hrtimer_init(&fotg210->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
-	fotg210->hrtimer.function = fotg210_hrtimer_func;
+	hrtimer_setup(&fotg210->hrtimer, fotg210_hrtimer_func, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
 	fotg210->next_hrtimer_event = FOTG210_HRTIMER_NO_EVENT;
 
 	hcc_params = fotg210_readl(fotg210, &fotg210->caps->hcc_params);

From 060baec57cfea34b380618e68144c1605afdb500 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:45:52 +0100
Subject: [PATCH 0277/1173] usb: gadget: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://lore.kernel.org/all/7239d6211ffb0dff6351d0549d065277f2562793.1738746904.git.namcao@linutronix.de
---
 drivers/usb/gadget/function/f_ncm.c | 3 +--
 drivers/usb/gadget/udc/dummy_hcd.c  | 6 ++----
 2 files changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c
index f60576a65ca67..58b0dd575af32 100644
--- a/drivers/usb/gadget/function/f_ncm.c
+++ b/drivers/usb/gadget/function/f_ncm.c
@@ -1559,8 +1559,7 @@ static int ncm_bind(struct usb_configuration *c, struct usb_function *f)
 	ncm->port.open = ncm_open;
 	ncm->port.close = ncm_close;
 
-	hrtimer_init(&ncm->task_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
-	ncm->task_timer.function = ncm_tx_timeout;
+	hrtimer_setup(&ncm->task_timer, ncm_tx_timeout, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
 
 	DBG(cdev, "CDC Network: IN/%s OUT/%s NOTIFY/%s\n",
 			ncm->port.in_ep->name, ncm->port.out_ep->name,
diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c
index bda08c5ba7c01..4f1b5db51ddae 100644
--- a/drivers/usb/gadget/udc/dummy_hcd.c
+++ b/drivers/usb/gadget/udc/dummy_hcd.c
@@ -2479,8 +2479,7 @@ static DEVICE_ATTR_RO(urbs);
 
 static int dummy_start_ss(struct dummy_hcd *dum_hcd)
 {
-	hrtimer_init(&dum_hcd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
-	dum_hcd->timer.function = dummy_timer;
+	hrtimer_setup(&dum_hcd->timer, dummy_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
 	dum_hcd->rh_state = DUMMY_RH_RUNNING;
 	dum_hcd->stream_en_ep = 0;
 	INIT_LIST_HEAD(&dum_hcd->urbp_list);
@@ -2509,8 +2508,7 @@ static int dummy_start(struct usb_hcd *hcd)
 		return dummy_start_ss(dum_hcd);
 
 	spin_lock_init(&dum_hcd->dum->lock);
-	hrtimer_init(&dum_hcd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
-	dum_hcd->timer.function = dummy_timer;
+	hrtimer_setup(&dum_hcd->timer, dummy_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
 	dum_hcd->rh_state = DUMMY_RH_RUNNING;
 
 	INIT_LIST_HEAD(&dum_hcd->urbp_list);

From da4f28741b905ad1aded9e699b5db6223245d3c4 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:45:53 +0100
Subject: [PATCH 0278/1173] usb: ehci: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://lore.kernel.org/all/d703731ba61d1901c97758a60ccc3c209d21de0e.1738746904.git.namcao@linutronix.de
---
 drivers/usb/host/ehci-hcd.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c
index 6de79ac5e6a44..6d1d190c914d4 100644
--- a/drivers/usb/host/ehci-hcd.c
+++ b/drivers/usb/host/ehci-hcd.c
@@ -466,8 +466,7 @@ static int ehci_init(struct usb_hcd *hcd)
 	 */
 	ehci->need_io_watchdog = 1;
 
-	hrtimer_init(&ehci->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
-	ehci->hrtimer.function = ehci_hrtimer_func;
+	hrtimer_setup(&ehci->hrtimer, ehci_hrtimer_func, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
 	ehci->next_hrtimer_event = EHCI_HRTIMER_NO_EVENT;
 
 	hcc_params = ehci_readl(ehci, &ehci->caps->hcc_params);

From 8073d9dfe2ef1a8b1959cc3ae7ef1db6239e53e5 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:45:54 +0100
Subject: [PATCH 0279/1173] usb: musb: cppi41: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://lore.kernel.org/all/80d59a56c76c76ace982417e4dc8ddd37a5441d7.1738746904.git.namcao@linutronix.de
---
 drivers/usb/musb/musb_cppi41.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/musb/musb_cppi41.c b/drivers/usb/musb/musb_cppi41.c
index 9589243e89518..4cde3abb7006f 100644
--- a/drivers/usb/musb/musb_cppi41.c
+++ b/drivers/usb/musb/musb_cppi41.c
@@ -760,8 +760,8 @@ cppi41_dma_controller_create(struct musb *musb, void __iomem *base)
 	if (!controller)
 		goto kzalloc_fail;
 
-	hrtimer_init(&controller->early_tx, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	controller->early_tx.function = cppi41_recheck_tx_req;
+	hrtimer_setup(&controller->early_tx, cppi41_recheck_tx_req, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 	INIT_LIST_HEAD(&controller->early_tx_list);
 
 	controller->controller.channel_alloc = cppi41_dma_channel_allocate;

From 9fdf17c5aa2ccd9f7e6cf23c01f79a1541a9f932 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:45:55 +0100
Subject: [PATCH 0280/1173] usb: typec: tcpm: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://lore.kernel.org/all/7fd2a1f72b3833e1fb36f56f2b28a08c1e64f47e.1738746904.git.namcao@linutronix.de
---
 drivers/usb/typec/tcpm/tcpm.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 6bf1a22c785af..9c455f0732330 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -7721,14 +7721,14 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc)
 	kthread_init_work(&port->event_work, tcpm_pd_event_handler);
 	kthread_init_work(&port->enable_frs, tcpm_enable_frs_work);
 	kthread_init_work(&port->send_discover_work, tcpm_send_discover_work);
-	hrtimer_init(&port->state_machine_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	port->state_machine_timer.function = state_machine_timer_handler;
-	hrtimer_init(&port->vdm_state_machine_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	port->vdm_state_machine_timer.function = vdm_state_machine_timer_handler;
-	hrtimer_init(&port->enable_frs_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	port->enable_frs_timer.function = enable_frs_timer_handler;
-	hrtimer_init(&port->send_discover_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	port->send_discover_timer.function = send_discover_timer_handler;
+	hrtimer_setup(&port->state_machine_timer, state_machine_timer_handler, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
+	hrtimer_setup(&port->vdm_state_machine_timer, vdm_state_machine_timer_handler,
+		      CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hrtimer_setup(&port->enable_frs_timer, enable_frs_timer_handler, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
+	hrtimer_setup(&port->send_discover_timer, send_discover_timer_handler, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 
 	spin_lock_init(&port->pd_event_lock);
 

From 6bf9bb76b3af17f1fbfe76e8d70528e939511801 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:45:56 +0100
Subject: [PATCH 0281/1173] serial: 8250: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://lore.kernel.org/all/991926d130cc272df30d226760d5d74187991669.1738746904.git.namcao@linutronix.de
---
 drivers/tty/serial/8250/8250_bcm7271.c |  3 +--
 drivers/tty/serial/8250/8250_port.c    | 10 ++++------
 2 files changed, 5 insertions(+), 8 deletions(-)

diff --git a/drivers/tty/serial/8250/8250_bcm7271.c b/drivers/tty/serial/8250/8250_bcm7271.c
index d0b18358859e1..742004d63c6f0 100644
--- a/drivers/tty/serial/8250/8250_bcm7271.c
+++ b/drivers/tty/serial/8250/8250_bcm7271.c
@@ -1056,8 +1056,7 @@ static int brcmuart_probe(struct platform_device *pdev)
 	}
 
 	/* setup HR timer */
-	hrtimer_init(&priv->hrt, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
-	priv->hrt.function = brcmuart_hrtimer_func;
+	hrtimer_setup(&priv->hrt, brcmuart_hrtimer_func, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
 
 	up.port.shutdown = brcmuart_shutdown;
 	up.port.startup = brcmuart_startup;
diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index 442967a6cd52d..c57f44882abbf 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -566,12 +566,10 @@ static int serial8250_em485_init(struct uart_8250_port *p)
 	if (!p->em485)
 		return -ENOMEM;
 
-	hrtimer_init(&p->em485->stop_tx_timer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_REL);
-	hrtimer_init(&p->em485->start_tx_timer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_REL);
-	p->em485->stop_tx_timer.function = &serial8250_em485_handle_stop_tx;
-	p->em485->start_tx_timer.function = &serial8250_em485_handle_start_tx;
+	hrtimer_setup(&p->em485->stop_tx_timer, &serial8250_em485_handle_stop_tx, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
+	hrtimer_setup(&p->em485->start_tx_timer, &serial8250_em485_handle_start_tx, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 	p->em485->port = p;
 	p->em485->active_timer = NULL;
 	p->em485->tx_stopped = true;

From c5f0fa1622f6fec7c461f2fe5b5d62229b4ae785 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:45:57 +0100
Subject: [PATCH 0282/1173] serial: amba-pl011: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/78e8c0d1b38998eab983fad265751ed13c2b9009.1738746904.git.namcao@linutronix.de
---
 drivers/tty/serial/amba-pl011.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index 04212c823a91d..98f178bdbcbec 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -2867,11 +2867,10 @@ static int pl011_probe(struct amba_device *dev, const struct amba_id *id)
 			return -EINVAL;
 		}
 	}
-
-	hrtimer_init(&uap->trigger_start_tx, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	hrtimer_init(&uap->trigger_stop_tx, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	uap->trigger_start_tx.function = pl011_trigger_start_tx;
-	uap->trigger_stop_tx.function = pl011_trigger_stop_tx;
+	hrtimer_setup(&uap->trigger_start_tx, pl011_trigger_start_tx, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
+	hrtimer_setup(&uap->trigger_stop_tx, pl011_trigger_stop_tx, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 
 	ret = pl011_setup_port(&dev->dev, uap, &dev->res, portnr);
 	if (ret)

From 721c5bf65a1d19d2958a83c6eb7ddd8002b9026f Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:45:58 +0100
Subject: [PATCH 0283/1173] serial: imx: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://lore.kernel.org/all/ad27070bc67c13f8a9acbd5cbf4cbae72797e3e1.1738746904.git.namcao@linutronix.de
---
 drivers/tty/serial/imx.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c
index 9c59ec128bb4f..9a1afe409b989 100644
--- a/drivers/tty/serial/imx.c
+++ b/drivers/tty/serial/imx.c
@@ -2582,10 +2582,10 @@ static int imx_uart_probe(struct platform_device *pdev)
 		imx_uart_writel(sport, ucr3, UCR3);
 	}
 
-	hrtimer_init(&sport->trigger_start_tx, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	hrtimer_init(&sport->trigger_stop_tx, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	sport->trigger_start_tx.function = imx_trigger_start_tx;
-	sport->trigger_stop_tx.function = imx_trigger_stop_tx;
+	hrtimer_setup(&sport->trigger_start_tx, imx_trigger_start_tx, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
+	hrtimer_setup(&sport->trigger_stop_tx, imx_trigger_stop_tx, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 
 	/*
 	 * Allocate the IRQ(s) i.MX1 has three interrupts whereas later

From 4e121496960342f3f2c2c563d65a3c08821ef7d7 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:45:59 +0100
Subject: [PATCH 0284/1173] serial: sh-sci: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://lore.kernel.org/all/c21664d013015584aebbb6bb8cedd748182cb551.1738746904.git.namcao@linutronix.de
---
 drivers/tty/serial/sh-sci.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c
index b1ea48f38248e..b72c3bc19bfa1 100644
--- a/drivers/tty/serial/sh-sci.c
+++ b/drivers/tty/serial/sh-sci.c
@@ -1702,8 +1702,7 @@ static void sci_request_dma(struct uart_port *port)
 			dma += s->buf_len_rx;
 		}
 
-		hrtimer_init(&s->rx_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-		s->rx_timer.function = sci_dma_rx_timer_fn;
+		hrtimer_setup(&s->rx_timer, sci_dma_rx_timer_fn, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 
 		s->chan_rx_saved = s->chan_rx = chan;
 

From 0852ca41ce1cf1559764cdc7bf17c68e8042daaa Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:46:00 +0100
Subject: [PATCH 0285/1173] serial: xilinx_uartps: Switch to use
 hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://lore.kernel.org/all/4a028a23126b3350a5e243dcb49e1ef1b2a4b740.1738746904.git.namcao@linutronix.de
---
 drivers/tty/serial/xilinx_uartps.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c
index 92ec51870d1da..efb124a19c015 100644
--- a/drivers/tty/serial/xilinx_uartps.c
+++ b/drivers/tty/serial/xilinx_uartps.c
@@ -1626,8 +1626,8 @@ static int cdns_rs485_config(struct uart_port *port, struct ktermios *termios,
 		writel(val, port->membase + CDNS_UART_MODEMCR);
 
 		/* Timer setup */
-		hrtimer_init(&cdns_uart->tx_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-		cdns_uart->tx_timer.function = &cdns_rs485_tx_callback;
+		hrtimer_setup(&cdns_uart->tx_timer, &cdns_rs485_tx_callback, CLOCK_MONOTONIC,
+			      HRTIMER_MODE_REL);
 
 		/* Disable transmitter and make Rx setup*/
 		cdns_uart_stop_tx(port);

From b7011929380d2fce41e9fa7050a1f7f1eb254c2d Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:46:01 +0100
Subject: [PATCH 0286/1173] scsi: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://lore.kernel.org/all/c951a5966e134307b8e50afb08e4b742e3f6ad06.1738746904.git.namcao@linutronix.de
---
 drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c | 4 +---
 drivers/scsi/lpfc/lpfc_init.c            | 7 +++----
 drivers/scsi/scsi_debug.c                | 4 ++--
 3 files changed, 6 insertions(+), 9 deletions(-)

diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
index 16d085d56e9d7..9e42230e42b86 100644
--- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
+++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
@@ -2922,9 +2922,7 @@ static long ibmvscsis_alloctimer(struct scsi_info *vscsi)
 	struct timer_cb *p_timer;
 
 	p_timer = &vscsi->rsp_q_timer;
-	hrtimer_init(&p_timer->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-
-	p_timer->timer.function = ibmvscsis_service_wait_q;
+	hrtimer_setup(&p_timer->timer, ibmvscsis_service_wait_q, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	p_timer->started = false;
 	p_timer->timer_pops = 0;
 
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index bcadf11414c8a..d1ac1d1cec3c6 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -7952,11 +7952,10 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 	timer_setup(&phba->fcf.redisc_wait, lpfc_sli4_fcf_redisc_wait_tmo, 0);
 
 	/* CMF congestion timer */
-	hrtimer_init(&phba->cmf_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	phba->cmf_timer.function = lpfc_cmf_timer;
+	hrtimer_setup(&phba->cmf_timer, lpfc_cmf_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	/* CMF 1 minute stats collection timer */
-	hrtimer_init(&phba->cmf_stats_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	phba->cmf_stats_timer.function = lpfc_cmf_stats_timer;
+	hrtimer_setup(&phba->cmf_stats_timer, lpfc_cmf_stats_timer, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 
 	/*
 	 * Control structure for handling external multi-buffer mailbox
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 5ceaa4665e5df..fe5c30bb26398 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -6384,8 +6384,8 @@ static struct sdebug_queued_cmd *sdebug_alloc_queued_cmd(struct scsi_cmnd *scmd)
 
 	sd_dp = &sqcp->sd_dp;
 
-	hrtimer_init(&sd_dp->hrt, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
-	sd_dp->hrt.function = sdebug_q_cmd_hrt_complete;
+	hrtimer_setup(&sd_dp->hrt, sdebug_q_cmd_hrt_complete, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL_PINNED);
 	INIT_WORK(&sd_dp->ew.work, sdebug_q_cmd_wq_complete);
 
 	sqcp->scmd = scmd;

From c92697913fdc5fe0e16ec8e9cfa29c4300069918 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:46:02 +0100
Subject: [PATCH 0287/1173] rtc: class: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Acked-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Link: https://lore.kernel.org/all/22f3f087ddbab1708583033c07c3b7fb17810110.1738746904.git.namcao@linutronix.de
---
 drivers/rtc/class.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c
index e31fa0ad127e9..b88cd4fb295bc 100644
--- a/drivers/rtc/class.c
+++ b/drivers/rtc/class.c
@@ -240,8 +240,7 @@ static struct rtc_device *rtc_allocate_device(void)
 	/* Init uie timer */
 	rtc_timer_init(&rtc->uie_rtctimer, rtc_uie_update_irq, rtc);
 	/* Init pie timer */
-	hrtimer_init(&rtc->pie_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	rtc->pie_timer.function = rtc_pie_update_irq;
+	hrtimer_setup(&rtc->pie_timer, rtc_pie_update_irq, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	rtc->pie_enabled = 0;
 
 	set_bit(RTC_FEATURE_ALARM, rtc->features);

From 5e55888e340a5209f8b3dba4d937c48c143719d1 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:46:03 +0100
Subject: [PATCH 0288/1173] pps: generators: pps_gen_parport: Switch to use
 hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://lore.kernel.org/all/4bf3bb22e21f27c58bb28690d856df913431e693.1738746904.git.namcao@linutronix.de
---
 drivers/pps/generators/pps_gen_parport.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/pps/generators/pps_gen_parport.c b/drivers/pps/generators/pps_gen_parport.c
index d46eed1594951..f5eeb4dd01ad0 100644
--- a/drivers/pps/generators/pps_gen_parport.c
+++ b/drivers/pps/generators/pps_gen_parport.c
@@ -208,8 +208,7 @@ static void parport_attach(struct parport *port)
 
 	calibrate_port(&device);
 
-	hrtimer_init(&device.timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
-	device.timer.function = hrtimer_event;
+	hrtimer_setup(&device.timer, hrtimer_event, CLOCK_REALTIME, HRTIMER_MODE_ABS);
 	hrtimer_start(&device.timer, next_intr_time(&device), HRTIMER_MODE_ABS);
 
 	return;

From d9a67240729dbfb097a1258484d8c8ae100769b1 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:46:04 +0100
Subject: [PATCH 0289/1173] powercap: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Rafael J. Wysocki <rafael@kernel.org>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://lore.kernel.org/all/fffc5ecc232069d91817b519dcafd8985120e51c.1738746904.git.namcao@linutronix.de
---
 drivers/powercap/idle_inject.c       | 3 +--
 drivers/powercap/intel_rapl_common.c | 3 +--
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/powercap/idle_inject.c b/drivers/powercap/idle_inject.c
index 04c212953ded6..5ad7cc438068e 100644
--- a/drivers/powercap/idle_inject.c
+++ b/drivers/powercap/idle_inject.c
@@ -339,8 +339,7 @@ struct idle_inject_device *idle_inject_register_full(struct cpumask *cpumask,
 		return NULL;
 
 	cpumask_copy(to_cpumask(ii_dev->cpumask), cpumask);
-	hrtimer_init(&ii_dev->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	ii_dev->timer.function = idle_inject_timer_fn;
+	hrtimer_setup(&ii_dev->timer, idle_inject_timer_fn, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	ii_dev->latency_us = UINT_MAX;
 	ii_dev->update = update;
 
diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c
index 77d75e1f14a9f..cf3d806284c44 100644
--- a/drivers/powercap/intel_rapl_common.c
+++ b/drivers/powercap/intel_rapl_common.c
@@ -2064,8 +2064,7 @@ int rapl_package_add_pmu(struct rapl_package *rp)
 	raw_spin_lock_init(&data->lock);
 	INIT_LIST_HEAD(&data->active_list);
 	data->timer_interval = ms_to_ktime(rapl_pmu.timer_ms);
-	hrtimer_init(&data->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	data->hrtimer.function = rapl_hrtimer_handle;
+	hrtimer_setup(&data->hrtimer, rapl_hrtimer_handle, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 
 	return rapl_pmu_update(rp);
 }

From 1b73fd14cfb47710e99f2119ec19c770e5881928 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:46:05 +0100
Subject: [PATCH 0290/1173] power: supply: ab8500_chargalg: Switch to use
 hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Acked-by: Sebastian Reichel <sebastian.reichel@collabora.com>
Link: https://lore.kernel.org/all/fa0bf7376ce8f124c8285a52d9f55d0ab4c42988.1738746904.git.namcao@linutronix.de
---
 drivers/power/supply/ab8500_chargalg.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/power/supply/ab8500_chargalg.c b/drivers/power/supply/ab8500_chargalg.c
index 7a8d1feb8e905..dc6c8b0dd1cfd 100644
--- a/drivers/power/supply/ab8500_chargalg.c
+++ b/drivers/power/supply/ab8500_chargalg.c
@@ -1787,13 +1787,12 @@ static int ab8500_chargalg_probe(struct platform_device *pdev)
 	psy_cfg.drv_data = di;
 
 	/* Initilialize safety timer */
-	hrtimer_init(&di->safety_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	di->safety_timer.function = ab8500_chargalg_safety_timer_expired;
+	hrtimer_setup(&di->safety_timer, ab8500_chargalg_safety_timer_expired, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 
 	/* Initilialize maintenance timer */
-	hrtimer_init(&di->maintenance_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	di->maintenance_timer.function =
-		ab8500_chargalg_maintenance_timer_expired;
+	hrtimer_setup(&di->maintenance_timer, ab8500_chargalg_maintenance_timer_expired,
+		      CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 
 	/* Init work for chargalg */
 	INIT_DEFERRABLE_WORK(&di->chargalg_periodic_work,

From 563608c20403ebee8a5d4d4bda7c0ba75485acba Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:46:06 +0100
Subject: [PATCH 0291/1173] power: reset: ltc2952-poweroff: Switch to use
 hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Acked-by: Sebastian Reichel <sebastian.reichel@collabora.com>
Link: https://lore.kernel.org/all/75ef5206f52f194b9c51653628cd2d0b083a482f.1738746904.git.namcao@linutronix.de
---
 drivers/power/reset/ltc2952-poweroff.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/power/reset/ltc2952-poweroff.c b/drivers/power/reset/ltc2952-poweroff.c
index 1a6fc8d38e206..90c664d344d0f 100644
--- a/drivers/power/reset/ltc2952-poweroff.c
+++ b/drivers/power/reset/ltc2952-poweroff.c
@@ -162,11 +162,11 @@ static void ltc2952_poweroff_default(struct ltc2952_poweroff *data)
 	data->wde_interval = 300L * NSEC_PER_MSEC;
 	data->trigger_delay = ktime_set(2, 500L * NSEC_PER_MSEC);
 
-	hrtimer_init(&data->timer_trigger, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	data->timer_trigger.function = ltc2952_poweroff_timer_trigger;
+	hrtimer_setup(&data->timer_trigger, ltc2952_poweroff_timer_trigger, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 
-	hrtimer_init(&data->timer_wde, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	data->timer_wde.function = ltc2952_poweroff_timer_wde;
+	hrtimer_setup(&data->timer_wde, ltc2952_poweroff_timer_wde, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 }
 
 static int ltc2952_poweroff_init(struct platform_device *pdev)

From 5f8401cf7b3af468b29770d31cc993c2b6e5f027 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:46:07 +0100
Subject: [PATCH 0292/1173] drivers: perf: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://lore.kernel.org/all/471ea3b829d14a4b4c3c7814dbe1ed13b15d47b8.1738746904.git.namcao@linutronix.de
---
 drivers/perf/arm-ccn.c               | 5 ++---
 drivers/perf/marvell_cn10k_ddr_pmu.c | 4 ++--
 drivers/perf/thunderx2_pmu.c         | 5 ++---
 3 files changed, 6 insertions(+), 8 deletions(-)

diff --git a/drivers/perf/arm-ccn.c b/drivers/perf/arm-ccn.c
index d5fcea3d4328b..1a0d0e1a22633 100644
--- a/drivers/perf/arm-ccn.c
+++ b/drivers/perf/arm-ccn.c
@@ -1273,9 +1273,8 @@ static int arm_ccn_pmu_init(struct arm_ccn *ccn)
 	/* No overflow interrupt? Have to use a timer instead. */
 	if (!ccn->irq) {
 		dev_info(ccn->dev, "No access to interrupts, using timer.\n");
-		hrtimer_init(&ccn->dt.hrtimer, CLOCK_MONOTONIC,
-				HRTIMER_MODE_REL);
-		ccn->dt.hrtimer.function = arm_ccn_pmu_timer_handler;
+		hrtimer_setup(&ccn->dt.hrtimer, arm_ccn_pmu_timer_handler, CLOCK_MONOTONIC,
+			      HRTIMER_MODE_REL);
 	}
 
 	/* Pick one CPU which we will use to collect data from CCN... */
diff --git a/drivers/perf/marvell_cn10k_ddr_pmu.c b/drivers/perf/marvell_cn10k_ddr_pmu.c
index 039feded91527..72ac17efd846a 100644
--- a/drivers/perf/marvell_cn10k_ddr_pmu.c
+++ b/drivers/perf/marvell_cn10k_ddr_pmu.c
@@ -1064,8 +1064,8 @@ static int cn10k_ddr_perf_probe(struct platform_device *pdev)
 	if (!name)
 		return -ENOMEM;
 
-	hrtimer_init(&ddr_pmu->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	ddr_pmu->hrtimer.function = cn10k_ddr_pmu_timer_handler;
+	hrtimer_setup(&ddr_pmu->hrtimer, cn10k_ddr_pmu_timer_handler, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 
 	cpuhp_state_add_instance_nocalls(
 				CPUHP_AP_PERF_ARM_MARVELL_CN10K_DDR_ONLINE,
diff --git a/drivers/perf/thunderx2_pmu.c b/drivers/perf/thunderx2_pmu.c
index cadd60221b8f7..6ed4707bd6bb5 100644
--- a/drivers/perf/thunderx2_pmu.c
+++ b/drivers/perf/thunderx2_pmu.c
@@ -752,9 +752,8 @@ static int tx2_uncore_pmu_add_dev(struct tx2_uncore_pmu *tx2_pmu)
 	tx2_pmu->cpu = cpu;
 
 	if (tx2_pmu->hrtimer_callback) {
-		hrtimer_init(&tx2_pmu->hrtimer,
-				CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-		tx2_pmu->hrtimer.function = tx2_pmu->hrtimer_callback;
+		hrtimer_setup(&tx2_pmu->hrtimer, tx2_pmu->hrtimer_callback, CLOCK_MONOTONIC,
+			      HRTIMER_MODE_REL);
 	}
 
 	ret = tx2_uncore_pmu_register(tx2_pmu);

From abeebe8889b732b2de3c5c098350f51bc5204069 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:46:08 +0100
Subject: [PATCH 0293/1173] ntb: ntb_pingpong: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://lore.kernel.org/all/2b179e16ab830611fdcb09a33a5a531c9800679b.1738746904.git.namcao@linutronix.de
---
 drivers/ntb/test/ntb_pingpong.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/ntb/test/ntb_pingpong.c b/drivers/ntb/test/ntb_pingpong.c
index 8aeca79140509..1c1c74f4ff2d3 100644
--- a/drivers/ntb/test/ntb_pingpong.c
+++ b/drivers/ntb/test/ntb_pingpong.c
@@ -284,8 +284,7 @@ static struct pp_ctx *pp_create_data(struct ntb_dev *ntb)
 	pp->ntb = ntb;
 	atomic_set(&pp->count, 0);
 	spin_lock_init(&pp->lock);
-	hrtimer_init(&pp->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	pp->timer.function = pp_timer_func;
+	hrtimer_setup(&pp->timer, pp_timer_func, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 
 	return pp;
 }

From 3a1ed018e9950f49232600fd0d96d460e07874f9 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:46:09 +0100
Subject: [PATCH 0294/1173] mmc: dw_mmc: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://lore.kernel.org/all/4dec579387ced5e97bb25739fad2ac852e5a689c.1738746904.git.namcao@linutronix.de
---
 drivers/mmc/host/dw_mmc.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index 3cbda98d08d28..31f40c04afda5 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -1875,8 +1875,7 @@ static void dw_mci_init_fault(struct dw_mci *host)
 {
 	host->fail_data_crc = (struct fault_attr) FAULT_ATTR_INITIALIZER;
 
-	hrtimer_init(&host->fault_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	host->fault_timer.function = dw_mci_fault_timer;
+	hrtimer_setup(&host->fault_timer, dw_mci_fault_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 }
 #else
 static void dw_mci_init_fault(struct dw_mci *host)

From 7f657ad0948257d131bca6953b3b553fe9f238d6 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:46:10 +0100
Subject: [PATCH 0295/1173] misc: vcpu_stall_detector: Switch to use
 hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://lore.kernel.org/all/a1c984288c6e47d956c07339ced486a8ec95f8d5.1738746904.git.namcao@linutronix.de
---
 drivers/misc/vcpu_stall_detector.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/misc/vcpu_stall_detector.c b/drivers/misc/vcpu_stall_detector.c
index f0b1fc87490ec..26166357b255e 100644
--- a/drivers/misc/vcpu_stall_detector.c
+++ b/drivers/misc/vcpu_stall_detector.c
@@ -111,8 +111,7 @@ static int start_stall_detector_cpu(unsigned int cpu)
 	ping_timeout_ms = vcpu_stall_config.stall_timeout_sec *
 			  MSEC_PER_SEC / 2;
 
-	hrtimer_init(vcpu_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	vcpu_hrtimer->function = vcpu_stall_detect_timer_fn;
+	hrtimer_setup(vcpu_hrtimer, vcpu_stall_detect_timer_fn, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	vcpu_stall_detector->is_initialized = true;
 
 	hrtimer_start(vcpu_hrtimer, ms_to_ktime(ping_timeout_ms),

From 0ebb5e74db095156c392e96479846b4b46df7829 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:46:11 +0100
Subject: [PATCH 0296/1173] media: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://lore.kernel.org/all/c725ad8d0ecac3cf6bbc532af567e56d47a6b75c.1738746904.git.namcao@linutronix.de
---
 drivers/media/cec/core/cec-pin.c                     | 3 +--
 drivers/media/pci/cx88/cx88-input.c                  | 3 +--
 drivers/media/platform/chips-media/wave5/wave5-vpu.c | 4 ++--
 drivers/media/rc/pwm-ir-tx.c                         | 3 +--
 4 files changed, 5 insertions(+), 8 deletions(-)

diff --git a/drivers/media/cec/core/cec-pin.c b/drivers/media/cec/core/cec-pin.c
index a70451d99ebc9..bebaa40e0eb51 100644
--- a/drivers/media/cec/core/cec-pin.c
+++ b/drivers/media/cec/core/cec-pin.c
@@ -1346,9 +1346,8 @@ struct cec_adapter *cec_pin_allocate_adapter(const struct cec_pin_ops *pin_ops,
 	if (pin == NULL)
 		return ERR_PTR(-ENOMEM);
 	pin->ops = pin_ops;
-	hrtimer_init(&pin->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	atomic_set(&pin->work_pin_num_events, 0);
-	pin->timer.function = cec_pin_timer;
+	hrtimer_setup(&pin->timer, cec_pin_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	init_waitqueue_head(&pin->kthread_waitq);
 	pin->tx_custom_low_usecs = CEC_TIM_CUSTOM_DEFAULT;
 	pin->tx_custom_high_usecs = CEC_TIM_CUSTOM_DEFAULT;
diff --git a/drivers/media/pci/cx88/cx88-input.c b/drivers/media/pci/cx88/cx88-input.c
index a04a1d33fadb1..b9f2c14d62b40 100644
--- a/drivers/media/pci/cx88/cx88-input.c
+++ b/drivers/media/pci/cx88/cx88-input.c
@@ -190,8 +190,7 @@ static int __cx88_ir_start(void *priv)
 	ir = core->ir;
 
 	if (ir->polling) {
-		hrtimer_init(&ir->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-		ir->timer.function = cx88_ir_work;
+		hrtimer_setup(&ir->timer, cx88_ir_work, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 		hrtimer_start(&ir->timer,
 			      ktime_set(0, ir->polling * 1000000),
 			      HRTIMER_MODE_REL);
diff --git a/drivers/media/platform/chips-media/wave5/wave5-vpu.c b/drivers/media/platform/chips-media/wave5/wave5-vpu.c
index d1320298a0f76..8479dc9c9a8fb 100644
--- a/drivers/media/platform/chips-media/wave5/wave5-vpu.c
+++ b/drivers/media/platform/chips-media/wave5/wave5-vpu.c
@@ -269,8 +269,8 @@ static int wave5_vpu_probe(struct platform_device *pdev)
 	dev->irq = platform_get_irq(pdev, 0);
 	if (dev->irq < 0) {
 		dev_err(&pdev->dev, "failed to get irq resource, falling back to polling\n");
-		hrtimer_init(&dev->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
-		dev->hrtimer.function = &wave5_vpu_timer_callback;
+		hrtimer_setup(&dev->hrtimer, &wave5_vpu_timer_callback, CLOCK_MONOTONIC,
+			      HRTIMER_MODE_REL_PINNED);
 		dev->worker = kthread_run_worker(0, "vpu_irq_thread");
 		if (IS_ERR(dev->worker)) {
 			dev_err(&pdev->dev, "failed to create vpu irq worker\n");
diff --git a/drivers/media/rc/pwm-ir-tx.c b/drivers/media/rc/pwm-ir-tx.c
index fe368aebbc139..84533fdd61aa6 100644
--- a/drivers/media/rc/pwm-ir-tx.c
+++ b/drivers/media/rc/pwm-ir-tx.c
@@ -172,8 +172,7 @@ static int pwm_ir_probe(struct platform_device *pdev)
 		rcdev->tx_ir = pwm_ir_tx_sleep;
 	} else {
 		init_completion(&pwm_ir->tx_done);
-		hrtimer_init(&pwm_ir->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-		pwm_ir->timer.function = pwm_ir_timer;
+		hrtimer_setup(&pwm_ir->timer, pwm_ir_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 		rcdev->tx_ir = pwm_ir_tx_atomic;
 	}
 

From c158a29c5c5ba97c0549d3390f50d441950bbce7 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:46:12 +0100
Subject: [PATCH 0297/1173] mailbox: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://lore.kernel.org/all/b742f81b6acdaa604511834a06a8aac3e6e63ca3.1738746904.git.namcao@linutronix.de
---
 drivers/mailbox/mailbox.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/mailbox/mailbox.c b/drivers/mailbox/mailbox.c
index d3d26a2c98956..118beaf447aa9 100644
--- a/drivers/mailbox/mailbox.c
+++ b/drivers/mailbox/mailbox.c
@@ -534,9 +534,7 @@ int mbox_controller_register(struct mbox_controller *mbox)
 			return -EINVAL;
 		}
 
-		hrtimer_init(&mbox->poll_hrt, CLOCK_MONOTONIC,
-			     HRTIMER_MODE_REL);
-		mbox->poll_hrt.function = txdone_hrtimer;
+		hrtimer_setup(&mbox->poll_hrt, txdone_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 		spin_lock_init(&mbox->poll_hrt_lock);
 	}
 

From a9d0ac739658f9a7c27d3430475aa3a00948ab1f Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:46:13 +0100
Subject: [PATCH 0298/1173] leds: trigger: pattern: Switch to use
 hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://lore.kernel.org/all/76fa1cc9777a99a48f49f949abadc1c10af1bc64.1738746904.git.namcao@linutronix.de
---
 drivers/leds/trigger/ledtrig-pattern.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/leds/trigger/ledtrig-pattern.c b/drivers/leds/trigger/ledtrig-pattern.c
index aad48c2540fc8..a594bd5e22333 100644
--- a/drivers/leds/trigger/ledtrig-pattern.c
+++ b/drivers/leds/trigger/ledtrig-pattern.c
@@ -483,8 +483,8 @@ static int pattern_trig_activate(struct led_classdev *led_cdev)
 	data->led_cdev = led_cdev;
 	led_set_trigger_data(led_cdev, data);
 	timer_setup(&data->timer, pattern_trig_timer_function, 0);
-	hrtimer_init(&data->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	data->hrtimer.function = pattern_trig_hrtimer_function;
+	hrtimer_setup(&data->hrtimer, pattern_trig_hrtimer_function, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 	led_cdev->activated = true;
 
 	if (led_cdev->flags & LED_INIT_DEFAULT_TRIGGER) {

From c69da1735f19d93c63fef5d38d9ff3b1c56587da Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:46:15 +0100
Subject: [PATCH 0299/1173] iio: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://lore.kernel.org/all/570792e31b28a94a511c19c6789f2171a6745685.1738746904.git.namcao@linutronix.de
---
 drivers/iio/adc/ti-tsc2046.c           | 4 +---
 drivers/iio/trigger/iio-trig-hrtimer.c | 4 ++--
 2 files changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/iio/adc/ti-tsc2046.c b/drivers/iio/adc/ti-tsc2046.c
index 7dde5713973f9..49560059f4b7b 100644
--- a/drivers/iio/adc/ti-tsc2046.c
+++ b/drivers/iio/adc/ti-tsc2046.c
@@ -812,9 +812,7 @@ static int tsc2046_adc_probe(struct spi_device *spi)
 
 	spin_lock_init(&priv->state_lock);
 	priv->state = TSC2046_STATE_SHUTDOWN;
-	hrtimer_init(&priv->trig_timer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_REL_SOFT);
-	priv->trig_timer.function = tsc2046_adc_timer;
+	hrtimer_setup(&priv->trig_timer, tsc2046_adc_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
 
 	ret = devm_iio_trigger_register(dev, trig);
 	if (ret) {
diff --git a/drivers/iio/trigger/iio-trig-hrtimer.c b/drivers/iio/trigger/iio-trig-hrtimer.c
index 716c795d08fb9..82c72baccb623 100644
--- a/drivers/iio/trigger/iio-trig-hrtimer.c
+++ b/drivers/iio/trigger/iio-trig-hrtimer.c
@@ -145,8 +145,8 @@ static struct iio_sw_trigger *iio_trig_hrtimer_probe(const char *name)
 	trig_info->swt.trigger->ops = &iio_hrtimer_trigger_ops;
 	trig_info->swt.trigger->dev.groups = iio_hrtimer_attr_groups;
 
-	hrtimer_init(&trig_info->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
-	trig_info->timer.function = iio_hrtimer_trig_handler;
+	hrtimer_setup(&trig_info->timer, iio_hrtimer_trig_handler, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL_HARD);
 
 	trig_info->sampling_frequency[0] = HRTIMER_DEFAULT_SAMPLING_FREQUENCY;
 	trig_info->period = NSEC_PER_SEC / trig_info->sampling_frequency[0];

From f1061c1442c1eddd71a25fe86516ee346ff4b7aa Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:46:16 +0100
Subject: [PATCH 0300/1173] i2c: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://lore.kernel.org/all/6a0d31244560b76cc7e76954bf68dbe14a4761e3.1738746904.git.namcao@linutronix.de
---
 drivers/i2c/busses/i2c-imx.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c
index ee0d25b498cb2..9e5d454d8318e 100644
--- a/drivers/i2c/busses/i2c-imx.c
+++ b/drivers/i2c/busses/i2c-imx.c
@@ -1723,8 +1723,8 @@ static int i2c_imx_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	spin_lock_init(&i2c_imx->slave_lock);
-	hrtimer_init(&i2c_imx->slave_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
-	i2c_imx->slave_timer.function = i2c_imx_slave_timeout;
+	hrtimer_setup(&i2c_imx->slave_timer, i2c_imx_slave_timeout, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_ABS);
 
 	match = device_get_match_data(&pdev->dev);
 	if (match)

From c6be6eafd6200327d6c7952275c042785dccbb96 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:46:17 +0100
Subject: [PATCH 0301/1173] stm class: heartbeat: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://lore.kernel.org/all/c822671342e6ca0437b25f8e24935f09821e389f.1738746904.git.namcao@linutronix.de
---
 drivers/hwtracing/stm/heartbeat.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/hwtracing/stm/heartbeat.c b/drivers/hwtracing/stm/heartbeat.c
index e9496fe97baa1..495eb1dc8ac58 100644
--- a/drivers/hwtracing/stm/heartbeat.c
+++ b/drivers/hwtracing/stm/heartbeat.c
@@ -81,10 +81,8 @@ static int stm_heartbeat_init(void)
 		stm_heartbeat[i].data.type	= STM_USER;
 		stm_heartbeat[i].data.link	= stm_heartbeat_link;
 		stm_heartbeat[i].data.unlink	= stm_heartbeat_unlink;
-		hrtimer_init(&stm_heartbeat[i].hrtimer, CLOCK_MONOTONIC,
-			     HRTIMER_MODE_ABS);
-		stm_heartbeat[i].hrtimer.function =
-			stm_heartbeat_hrtimer_handler;
+		hrtimer_setup(&stm_heartbeat[i].hrtimer, stm_heartbeat_hrtimer_handler,
+			      CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
 
 		ret = stm_source_register_device(NULL, &stm_heartbeat[i].data);
 		if (ret)

From 690d59fee83cb0f45fae21ce3aed2b335c87c1c2 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:46:18 +0100
Subject: [PATCH 0302/1173] drm/amdgpu: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Link: https://lore.kernel.org/all/2e3664eebb00d3a8c786ee7cc1fba8096bababc9.1738746904.git.namcao@linutronix.de
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
index 03308261f8943..7507d94430287 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
@@ -188,8 +188,8 @@ static int amdgpu_vkms_crtc_init(struct drm_device *dev, struct drm_crtc *crtc,
 	amdgpu_crtc->connector = NULL;
 	amdgpu_crtc->vsync_timer_enabled = AMDGPU_IRQ_STATE_DISABLE;
 
-	hrtimer_init(&amdgpu_crtc->vblank_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	amdgpu_crtc->vblank_timer.function = &amdgpu_vkms_vblank_simulate;
+	hrtimer_setup(&amdgpu_crtc->vblank_timer, &amdgpu_vkms_vblank_simulate, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 
 	return ret;
 }

From 0592bb39e3a33ebcc956c1730fb2c756ebc71fdb Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:46:19 +0100
Subject: [PATCH 0303/1173] drm/i915/huc: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Acked-by: Jani Nikula <jani.nikula@intel.com>
Link: https://lore.kernel.org/all/d293dd4dd9cb6a9bb9e99f3fc11ea174c6525bf8.1738746904.git.namcao@linutronix.de
---
 drivers/gpu/drm/i915/gt/uc/intel_huc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
index b3cbf85c00cbd..00d00c480cc58 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_huc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
@@ -231,8 +231,8 @@ static void delayed_huc_load_init(struct intel_huc *huc)
 			   sw_fence_dummy_notify);
 	i915_sw_fence_commit(&huc->delayed_load.fence);
 
-	hrtimer_init(&huc->delayed_load.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	huc->delayed_load.timer.function = huc_delayed_load_timer_callback;
+	hrtimer_setup(&huc->delayed_load.timer, huc_delayed_load_timer_callback, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 }
 
 static void delayed_huc_load_fini(struct intel_huc *huc)

From 9892287897ca0c267a3071f7f6fa5d82126e29e9 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:46:20 +0100
Subject: [PATCH 0304/1173] drm/i915/gvt: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Acked-by: Jani Nikula <jani.nikula@intel.com>
Link: https://lore.kernel.org/all/9af55b7d0918bb3642c6392fbb4800d8ea7c9c50.1738746904.git.namcao@linutronix.de
---
 drivers/gpu/drm/i915/gvt/display.c      | 3 +--
 drivers/gpu/drm/i915/gvt/sched_policy.c | 3 +--
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c
index 95570cabdf276..f668cd9487f1e 100644
--- a/drivers/gpu/drm/i915/gvt/display.c
+++ b/drivers/gpu/drm/i915/gvt/display.c
@@ -581,8 +581,7 @@ static int setup_virtual_dp_monitor(struct intel_vgpu *vgpu, int port_num,
 	vgpu->display.port_num = port_num;
 
 	/* Init hrtimer based on default refresh rate */
-	hrtimer_init(&vblank_timer->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
-	vblank_timer->timer.function = vblank_timer_fn;
+	hrtimer_setup(&vblank_timer->timer, vblank_timer_fn, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
 	vblank_timer->vrefresh_k = port->vrefresh_k;
 	vblank_timer->period = DIV64_U64_ROUND_CLOSEST(NSEC_PER_SEC * MSEC_PER_SEC, vblank_timer->vrefresh_k);
 
diff --git a/drivers/gpu/drm/i915/gvt/sched_policy.c b/drivers/gpu/drm/i915/gvt/sched_policy.c
index c077fb4674f0f..9f97f743aa71a 100644
--- a/drivers/gpu/drm/i915/gvt/sched_policy.c
+++ b/drivers/gpu/drm/i915/gvt/sched_policy.c
@@ -286,8 +286,7 @@ static int tbs_sched_init(struct intel_gvt *gvt)
 		return -ENOMEM;
 
 	INIT_LIST_HEAD(&data->lru_runq_head);
-	hrtimer_init(&data->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
-	data->timer.function = tbs_timer_fn;
+	hrtimer_setup(&data->timer, tbs_timer_fn, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
 	data->period = GVT_DEFAULT_TIME_SLICE;
 	data->gvt = gvt;
 

From 7358f053c4d6ef2692e4860b6d46b8f33c9aa1d3 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:46:21 +0100
Subject: [PATCH 0305/1173] drm/i915/perf: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Acked-by: Jani Nikula <jani.nikula@intel.com>
Link: https://lore.kernel.org/all/b712673a02c7132ea85eff57b0e7e59f6d5d0da0.1738746904.git.namcao@linutronix.de
---
 drivers/gpu/drm/i915/i915_perf.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 5384d1bb49233..279e266b4b06c 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -3359,9 +3359,8 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 		"opening stream oa config uuid=%s\n",
 		  stream->oa_config->uuid);
 
-	hrtimer_init(&stream->poll_check_timer,
-		     CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	stream->poll_check_timer.function = oa_poll_check_timer_cb;
+	hrtimer_setup(&stream->poll_check_timer, oa_poll_check_timer_cb, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 	init_waitqueue_head(&stream->poll_wq);
 	spin_lock_init(&stream->oa_buffer.ptr_lock);
 	mutex_init(&stream->lock);

From 82ad584eed8baa5b1988580b3785649e7a1c07e5 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:46:22 +0100
Subject: [PATCH 0306/1173] drm/i915/pmu: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Acked-by: Jani Nikula <jani.nikula@intel.com>
Link: https://lore.kernel.org/all/71198b93c438866fe2be7323e59cdbf21aa0d493.1738746904.git.namcao@linutronix.de
---
 drivers/gpu/drm/i915/i915_pmu.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index e55db036be1bb..0ce87f188d116 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -1264,8 +1264,7 @@ void i915_pmu_register(struct drm_i915_private *i915)
 	int ret = -ENOMEM;
 
 	spin_lock_init(&pmu->lock);
-	hrtimer_init(&pmu->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	pmu->timer.function = i915_sample;
+	hrtimer_setup(&pmu->timer, i915_sample, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	pmu->cpuhp.cpu = -1;
 	init_rc6(pmu);
 

From f97e1d787f9f57fc78227bad348d092c1d7a1ee9 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:46:23 +0100
Subject: [PATCH 0307/1173] drm/i915/uncore: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Acked-by: Jani Nikula <jani.nikula@intel.com>
Link: https://lore.kernel.org/all/1d0ad9ab31040d9c3478b77626cdb0a04c0a7bad.1738746904.git.namcao@linutronix.de
---
 drivers/gpu/drm/i915/intel_uncore.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index eed4937c3ff30..bdcfcae83b52b 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -2103,8 +2103,7 @@ static int __fw_domain_init(struct intel_uncore *uncore,
 
 	d->mask = BIT(domain_id);
 
-	hrtimer_init(&d->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	d->timer.function = intel_uncore_fw_release_timer;
+	hrtimer_setup(&d->timer, intel_uncore_fw_release_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 
 	uncore->fw_domains |= BIT(domain_id);
 

From 1a2ff5c3058d3811b092736cbbd3ae09ea308dd2 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:46:24 +0100
Subject: [PATCH 0308/1173] drm/i915/request: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Acked-by: Jani Nikula <jani.nikula@intel.com>
Link: https://lore.kernel.org/all/4fe658e6d8483e44d4fff579bc426e627487f6ca.1738746904.git.namcao@linutronix.de
---
 drivers/gpu/drm/i915/i915_request.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 8f62cfa23fb76..ea0b8e7e4828a 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -293,8 +293,7 @@ static void __rq_init_watchdog(struct i915_request *rq)
 {
 	struct i915_request_watchdog *wdg = &rq->watchdog;
 
-	hrtimer_init(&wdg->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	wdg->timer.function = __rq_watchdog_expired;
+	hrtimer_setup(&wdg->timer, __rq_watchdog_expired, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 }
 
 static void __rq_arm_watchdog(struct i915_request *rq)

From 58ac3c93306ec588a6dbb8d3e02ac1109b32df6b Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:46:25 +0100
Subject: [PATCH 0309/1173] drm/msm: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://lore.kernel.org/all/2689e1ad4105f415ce8cd9e426873d9ac479dc36.1738746904.git.namcao@linutronix.de
---
 drivers/gpu/drm/msm/msm_fence.c    | 3 +--
 drivers/gpu/drm/msm/msm_io_utils.c | 3 +--
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_fence.c b/drivers/gpu/drm/msm/msm_fence.c
index 1a5d4f1c8b422..d41e5a6bbee09 100644
--- a/drivers/gpu/drm/msm/msm_fence.c
+++ b/drivers/gpu/drm/msm/msm_fence.c
@@ -65,8 +65,7 @@ msm_fence_context_alloc(struct drm_device *dev, volatile uint32_t *fenceptr,
 	fctx->completed_fence = fctx->last_fence;
 	*fctx->fenceptr = fctx->last_fence;
 
-	hrtimer_init(&fctx->deadline_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
-	fctx->deadline_timer.function = deadline_timer;
+	hrtimer_setup(&fctx->deadline_timer, deadline_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
 
 	kthread_init_work(&fctx->deadline_work, deadline_work);
 
diff --git a/drivers/gpu/drm/msm/msm_io_utils.c b/drivers/gpu/drm/msm/msm_io_utils.c
index afedd61c3e288..a6efe1eac2712 100644
--- a/drivers/gpu/drm/msm/msm_io_utils.c
+++ b/drivers/gpu/drm/msm/msm_io_utils.c
@@ -135,8 +135,7 @@ void msm_hrtimer_work_init(struct msm_hrtimer_work *work,
 			   clockid_t clock_id,
 			   enum hrtimer_mode mode)
 {
-	hrtimer_init(&work->timer, clock_id, mode);
-	work->timer.function = msm_hrtimer_worktimer;
+	hrtimer_setup(&work->timer, msm_hrtimer_worktimer, clock_id, mode);
 	work->worker = worker;
 	kthread_init_work(&work->work, fn);
 }

From c38e753abee274318a52ba53f99446a1b912ceea Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:46:26 +0100
Subject: [PATCH 0310/1173] drm/vkms: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://lore.kernel.org/all/866841803c850c38819f98fdf6bd992ee4a4d012.1738746904.git.namcao@linutronix.de
---
 drivers/gpu/drm/vkms/vkms_crtc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/vkms/vkms_crtc.c b/drivers/gpu/drm/vkms/vkms_crtc.c
index 28a57ae109fcc..ae4e36bc337c4 100644
--- a/drivers/gpu/drm/vkms/vkms_crtc.c
+++ b/drivers/gpu/drm/vkms/vkms_crtc.c
@@ -64,8 +64,8 @@ static int vkms_enable_vblank(struct drm_crtc *crtc)
 	struct drm_vblank_crtc *vblank = drm_crtc_vblank_crtc(crtc);
 	struct vkms_output *out = drm_crtc_to_vkms_output(crtc);
 
-	hrtimer_init(&out->vblank_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	out->vblank_hrtimer.function = &vkms_vblank_simulate;
+	hrtimer_setup(&out->vblank_hrtimer, &vkms_vblank_simulate, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 	out->period_ns = ktime_set(0, vblank->framedur_ns);
 	hrtimer_start(&out->vblank_hrtimer, out->period_ns, HRTIMER_MODE_REL);
 

From 397c07a3c90b18f09caa6ec4e00597f47319fbee Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:46:27 +0100
Subject: [PATCH 0311/1173] drm/xe/oa: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Lucas De Marchi <lucas.demarchi@intel.com>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://lore.kernel.org/all/08238e193b1f63ae7d5d607fa975420735a869a5.1738746904.git.namcao@linutronix.de
---
 drivers/gpu/drm/xe/xe_oa.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c
index fa873f3d0a9d1..f03b3a99ae430 100644
--- a/drivers/gpu/drm/xe/xe_oa.c
+++ b/drivers/gpu/drm/xe/xe_oa.c
@@ -1766,8 +1766,8 @@ static int xe_oa_stream_init(struct xe_oa_stream *stream,
 
 	WRITE_ONCE(u->exclusive_stream, stream);
 
-	hrtimer_init(&stream->poll_check_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	stream->poll_check_timer.function = xe_oa_poll_check_timer_cb;
+	hrtimer_setup(&stream->poll_check_timer, xe_oa_poll_check_timer_cb, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 	init_waitqueue_head(&stream->poll_wq);
 
 	spin_lock_init(&stream->oa_buffer.ptr_lock);

From ff533f73d5c038e9be359fbc587dc229a8299e13 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:46:28 +0100
Subject: [PATCH 0312/1173] drm/vmwgfx: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://lore.kernel.org/all/6f6664cf2fea2f782e37f64a77fc9f8699794f58.1738746904.git.namcao@linutronix.de
---
 drivers/gpu/drm/vmwgfx/vmwgfx_vkms.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_vkms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_vkms.c
index 8651b788e98bc..aec774fa4d7bf 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_vkms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_vkms.c
@@ -290,8 +290,8 @@ vmw_vkms_enable_vblank(struct drm_crtc *crtc)
 
 	drm_calc_timestamping_constants(crtc, &crtc->mode);
 
-	hrtimer_init(&du->vkms.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	du->vkms.timer.function = &vmw_vkms_vblank_simulate;
+	hrtimer_setup(&du->vkms.timer, &vmw_vkms_vblank_simulate, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 	du->vkms.period_ns = ktime_set(0, vblank->framedur_ns);
 	hrtimer_start(&du->vkms.timer, du->vkms.period_ns, HRTIMER_MODE_REL);
 

From 7b5edfd278b04bd158c14554dd494ec00aa9e275 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:46:29 +0100
Subject: [PATCH 0313/1173] virtio: mem: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://lore.kernel.org/all/4a911503d16684592b59a16d8ade97e42df64a54.1738746904.git.namcao@linutronix.de
---
 drivers/virtio/virtio_mem.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c
index 8a294b9cbcf68..56d0dbe621637 100644
--- a/drivers/virtio/virtio_mem.c
+++ b/drivers/virtio/virtio_mem.c
@@ -2950,8 +2950,8 @@ static int virtio_mem_probe(struct virtio_device *vdev)
 	mutex_init(&vm->hotplug_mutex);
 	INIT_LIST_HEAD(&vm->next);
 	spin_lock_init(&vm->removal_lock);
-	hrtimer_init(&vm->retry_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	vm->retry_timer.function = virtio_mem_timer_expired;
+	hrtimer_setup(&vm->retry_timer, virtio_mem_timer_expired, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 	vm->retry_timer_ms = VIRTIO_MEM_RETRY_TIMER_MIN_MS;
 	vm->in_kdump = is_kdump_kernel();
 

From bbdafde7c22018a4a84db98b11eb8f8ab26d7731 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:46:30 +0100
Subject: [PATCH 0314/1173] RDMA: Switch to use hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://lore.kernel.org/all/37bd6895bb946f6d785ab5fe32f1a6f4b9e77c26.1738746904.git.namcao@linutronix.de
---
 drivers/infiniband/hw/hfi1/init.c | 5 ++---
 drivers/infiniband/sw/rdmavt/qp.c | 5 ++---
 2 files changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index cbac4a442d9ec..d6fbd9c2b8b49 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -635,12 +635,11 @@ void hfi1_init_pportdata(struct pci_dev *pdev, struct hfi1_pportdata *ppd,
 	spin_lock_init(&ppd->cca_timer_lock);
 
 	for (i = 0; i < OPA_MAX_SLS; i++) {
-		hrtimer_init(&ppd->cca_timer[i].hrtimer, CLOCK_MONOTONIC,
-			     HRTIMER_MODE_REL);
 		ppd->cca_timer[i].ppd = ppd;
 		ppd->cca_timer[i].sl = i;
 		ppd->cca_timer[i].ccti = 0;
-		ppd->cca_timer[i].hrtimer.function = cca_timer_fn;
+		hrtimer_setup(&ppd->cca_timer[i].hrtimer, cca_timer_fn, CLOCK_MONOTONIC,
+			      HRTIMER_MODE_REL);
 	}
 
 	ppd->cc_max_table_entries = IB_CC_TABLE_CAP_DEFAULT;
diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c
index e6203e26cc064..614009fb96329 100644
--- a/drivers/infiniband/sw/rdmavt/qp.c
+++ b/drivers/infiniband/sw/rdmavt/qp.c
@@ -1107,9 +1107,8 @@ int rvt_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *init_attr,
 		}
 		/* initialize timers needed for rc qp */
 		timer_setup(&qp->s_timer, rvt_rc_timeout, 0);
-		hrtimer_init(&qp->s_rnr_timer, CLOCK_MONOTONIC,
-			     HRTIMER_MODE_REL);
-		qp->s_rnr_timer.function = rvt_rc_rnr_retry;
+		hrtimer_setup(&qp->s_rnr_timer, rvt_rc_rnr_retry, CLOCK_MONOTONIC,
+			      HRTIMER_MODE_REL);
 
 		/*
 		 * Driver needs to set up it's private QP structure and do any

From ce68de08a2cc95dc2cb6018a22673beed52f25c3 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:46:32 +0100
Subject: [PATCH 0315/1173] ASoC: fsl: imx-pcm-fiq: Switch to use
 hrtimer_setup()

hrtimer_setup() takes the callback function pointer as argument and
initializes the timer completely.

Replace hrtimer_init() and the open coded initialization of
hrtimer::function with the new setup mechanism.

Patch was created by using Coccinelle.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://lore.kernel.org/all/ed4be9ec380a688291e3fc9b24f8c38a3f07a143.1738746904.git.namcao@linutronix.de
---
 sound/soc/fsl/imx-pcm-fiq.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/sound/soc/fsl/imx-pcm-fiq.c b/sound/soc/fsl/imx-pcm-fiq.c
index 3391430e42532..83de3ae336910 100644
--- a/sound/soc/fsl/imx-pcm-fiq.c
+++ b/sound/soc/fsl/imx-pcm-fiq.c
@@ -185,8 +185,7 @@ static int snd_imx_open(struct snd_soc_component *component,
 
 	atomic_set(&iprtd->playing, 0);
 	atomic_set(&iprtd->capturing, 0);
-	hrtimer_init(&iprtd->hrt, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	iprtd->hrt.function = snd_hrtimer_callback;
+	hrtimer_setup(&iprtd->hrt, snd_hrtimer_callback, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 
 	ret = snd_pcm_hw_constraint_integer(substream->runtime,
 			SNDRV_PCM_HW_PARAM_PERIODS);

From 81570d6a7ad37033c7895811551a5a9023706eda Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Sat, 15 Feb 2025 10:56:55 +0100
Subject: [PATCH 0316/1173] gpiolib: protect gpio_chip with SRCU in array_info
 paths in multi get/set

During the locking rework in GPIOLIB, we omitted one important use-case,
namely: setting and getting values for GPIO descriptor arrays with
array_info present.

This patch does two things: first it makes struct gpio_array store the
address of the underlying GPIO device and not chip. Next: it protects
the chip with SRCU from removal in gpiod_get_array_value_complex() and
gpiod_set_array_value_complex().

Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250215095655.23152-1-brgl@bgdev.pl
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpiolib.c | 48 +++++++++++++++++++++++++++++-------------
 drivers/gpio/gpiolib.h |  4 ++--
 2 files changed, 35 insertions(+), 17 deletions(-)

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 29110dc436f15..5529d8b65f6fb 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -3143,6 +3143,8 @@ static int gpiod_get_raw_value_commit(const struct gpio_desc *desc)
 static int gpio_chip_get_multiple(struct gpio_chip *gc,
 				  unsigned long *mask, unsigned long *bits)
 {
+	lockdep_assert_held(&gc->gpiodev->srcu);
+
 	if (gc->get_multiple)
 		return gc->get_multiple(gc, mask, bits);
 	if (gc->get) {
@@ -3173,6 +3175,7 @@ int gpiod_get_array_value_complex(bool raw, bool can_sleep,
 				  struct gpio_array *array_info,
 				  unsigned long *value_bitmap)
 {
+	struct gpio_chip *gc;
 	int ret, i = 0;
 
 	/*
@@ -3184,10 +3187,15 @@ int gpiod_get_array_value_complex(bool raw, bool can_sleep,
 	    array_size <= array_info->size &&
 	    (void *)array_info == desc_array + array_info->size) {
 		if (!can_sleep)
-			WARN_ON(array_info->chip->can_sleep);
+			WARN_ON(array_info->gdev->can_sleep);
+
+		guard(srcu)(&array_info->gdev->srcu);
+		gc = srcu_dereference(array_info->gdev->chip,
+				      &array_info->gdev->srcu);
+		if (!gc)
+			return -ENODEV;
 
-		ret = gpio_chip_get_multiple(array_info->chip,
-					     array_info->get_mask,
+		ret = gpio_chip_get_multiple(gc, array_info->get_mask,
 					     value_bitmap);
 		if (ret)
 			return ret;
@@ -3468,6 +3476,8 @@ static void gpiod_set_raw_value_commit(struct gpio_desc *desc, bool value)
 static void gpio_chip_set_multiple(struct gpio_chip *gc,
 				   unsigned long *mask, unsigned long *bits)
 {
+	lockdep_assert_held(&gc->gpiodev->srcu);
+
 	if (gc->set_multiple) {
 		gc->set_multiple(gc, mask, bits);
 	} else {
@@ -3485,6 +3495,7 @@ int gpiod_set_array_value_complex(bool raw, bool can_sleep,
 				  struct gpio_array *array_info,
 				  unsigned long *value_bitmap)
 {
+	struct gpio_chip *gc;
 	int i = 0;
 
 	/*
@@ -3496,14 +3507,19 @@ int gpiod_set_array_value_complex(bool raw, bool can_sleep,
 	    array_size <= array_info->size &&
 	    (void *)array_info == desc_array + array_info->size) {
 		if (!can_sleep)
-			WARN_ON(array_info->chip->can_sleep);
+			WARN_ON(array_info->gdev->can_sleep);
+
+		guard(srcu)(&array_info->gdev->srcu);
+		gc = srcu_dereference(array_info->gdev->chip,
+				      &array_info->gdev->srcu);
+		if (!gc)
+			return -ENODEV;
 
 		if (!raw && !bitmap_empty(array_info->invert_mask, array_size))
 			bitmap_xor(value_bitmap, value_bitmap,
 				   array_info->invert_mask, array_size);
 
-		gpio_chip_set_multiple(array_info->chip, array_info->set_mask,
-				       value_bitmap);
+		gpio_chip_set_multiple(gc, array_info->set_mask, value_bitmap);
 
 		i = find_first_zero_bit(array_info->set_mask, array_size);
 		if (i == array_size)
@@ -4765,9 +4781,10 @@ struct gpio_descs *__must_check gpiod_get_array(struct device *dev,
 {
 	struct gpio_desc *desc;
 	struct gpio_descs *descs;
+	struct gpio_device *gdev;
 	struct gpio_array *array_info = NULL;
-	struct gpio_chip *gc;
 	int count, bitmap_size;
+	unsigned long dflags;
 	size_t descs_size;
 
 	count = gpiod_count(dev, con_id);
@@ -4788,7 +4805,7 @@ struct gpio_descs *__must_check gpiod_get_array(struct device *dev,
 
 		descs->desc[descs->ndescs] = desc;
 
-		gc = gpiod_to_chip(desc);
+		gdev = gpiod_to_gpio_device(desc);
 		/*
 		 * If pin hardware number of array member 0 is also 0, select
 		 * its chip as a candidate for fast bitmap processing path.
@@ -4796,8 +4813,8 @@ struct gpio_descs *__must_check gpiod_get_array(struct device *dev,
 		if (descs->ndescs == 0 && gpio_chip_hwgpio(desc) == 0) {
 			struct gpio_descs *array;
 
-			bitmap_size = BITS_TO_LONGS(gc->ngpio > count ?
-						    gc->ngpio : count);
+			bitmap_size = BITS_TO_LONGS(gdev->ngpio > count ?
+						    gdev->ngpio : count);
 
 			array = krealloc(descs, descs_size +
 					 struct_size(array_info, invert_mask, 3 * bitmap_size),
@@ -4817,7 +4834,7 @@ struct gpio_descs *__must_check gpiod_get_array(struct device *dev,
 
 			array_info->desc = descs->desc;
 			array_info->size = count;
-			array_info->chip = gc;
+			array_info->gdev = gdev;
 			bitmap_set(array_info->get_mask, descs->ndescs,
 				   count - descs->ndescs);
 			bitmap_set(array_info->set_mask, descs->ndescs,
@@ -4830,7 +4847,7 @@ struct gpio_descs *__must_check gpiod_get_array(struct device *dev,
 			continue;
 
 		/* Unmark array members which don't belong to the 'fast' chip */
-		if (array_info->chip != gc) {
+		if (array_info->gdev != gdev) {
 			__clear_bit(descs->ndescs, array_info->get_mask);
 			__clear_bit(descs->ndescs, array_info->set_mask);
 		}
@@ -4853,9 +4870,10 @@ struct gpio_descs *__must_check gpiod_get_array(struct device *dev,
 					    array_info->set_mask);
 			}
 		} else {
+			dflags = READ_ONCE(desc->flags);
 			/* Exclude open drain or open source from fast output */
-			if (gpiochip_line_is_open_drain(gc, descs->ndescs) ||
-			    gpiochip_line_is_open_source(gc, descs->ndescs))
+			if (test_bit(FLAG_OPEN_DRAIN, &dflags) ||
+			    test_bit(FLAG_OPEN_SOURCE, &dflags))
 				__clear_bit(descs->ndescs,
 					    array_info->set_mask);
 			/* Identify 'fast' pins which require invertion */
@@ -4867,7 +4885,7 @@ struct gpio_descs *__must_check gpiod_get_array(struct device *dev,
 	if (array_info)
 		dev_dbg(dev,
 			"GPIO array info: chip=%s, size=%d, get_mask=%lx, set_mask=%lx, invert_mask=%lx\n",
-			array_info->chip->label, array_info->size,
+			array_info->gdev->label, array_info->size,
 			*array_info->get_mask, *array_info->set_mask,
 			*array_info->invert_mask);
 	return descs;
diff --git a/drivers/gpio/gpiolib.h b/drivers/gpio/gpiolib.h
index 83690f72f7e5c..147156ec502b2 100644
--- a/drivers/gpio/gpiolib.h
+++ b/drivers/gpio/gpiolib.h
@@ -114,7 +114,7 @@ extern const char *const gpio_suffixes[];
  *
  * @desc:		Array of pointers to the GPIO descriptors
  * @size:		Number of elements in desc
- * @chip:		Parent GPIO chip
+ * @gdev:		Parent GPIO device
  * @get_mask:		Get mask used in fastpath
  * @set_mask:		Set mask used in fastpath
  * @invert_mask:	Invert mask used in fastpath
@@ -126,7 +126,7 @@ extern const char *const gpio_suffixes[];
 struct gpio_array {
 	struct gpio_desc	**desc;
 	unsigned int		size;
-	struct gpio_chip	*chip;
+	struct gpio_device	*gdev;
 	unsigned long		*get_mask;
 	unsigned long		*set_mask;
 	unsigned long		invert_mask[];

From a3bdd8f5c2217e1cb35db02c2eed36ea20fb50f5 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 18 Feb 2025 12:40:24 +0100
Subject: [PATCH 0317/1173] ALSA: usb-audio: Avoid dropping MIDI events at
 closing multiple ports

We fixed the UAF issue in USB MIDI code by canceling the pending work
at closing each MIDI output device in the commit below.  However, this
assumed that it's the only one that is tied with the endpoint, and it
resulted in unexpected data truncations when multiple devices are
assigned to a single endpoint and opened simultaneously.

For addressing the unexpected MIDI message drops, simply replace
cancel_work_sync() with flush_work().  The drain callback should have
been already invoked before the close callback, hence the port->active
flag must be already cleared.  So this just assures that the pending
work is finished before freeing the resources.

Fixes: 0125de38122f ("ALSA: usb-audio: Cancel pending work at closing a MIDI substream")
Reported-and-tested-by: John Keeping <jkeeping@inmusicbrands.com>
Closes: https://lore.kernel.org/20250217111647.3368132-1-jkeeping@inmusicbrands.com
Link: https://patch.msgid.link/20250218114024.23125-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/midi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/usb/midi.c b/sound/usb/midi.c
index 737dd00e97b14..779d97d31f170 100644
--- a/sound/usb/midi.c
+++ b/sound/usb/midi.c
@@ -1145,7 +1145,7 @@ static int snd_usbmidi_output_close(struct snd_rawmidi_substream *substream)
 {
 	struct usbmidi_out_port *port = substream->runtime->private_data;
 
-	cancel_work_sync(&port->ep->work);
+	flush_work(&port->ep->work);
 	return substream_open(substream, 0, 0);
 }
 

From fcd875445866a5219cf2be3101e276b21fc843f3 Mon Sep 17 00:00:00 2001
From: Christopher Lentocha <christopherericlentocha@gmail.com>
Date: Tue, 18 Feb 2025 08:59:29 -0500
Subject: [PATCH 0318/1173] nvme-pci: quirk Acer FA100 for non-uniqueue
 identifiers

In order for two Acer FA100 SSDs to work in one PC (in the case of
myself, a Lenovo Legion T5 28IMB05), and not show one drive and not
the other, and sometimes mix up what drive shows up (randomly), these
two lines of code need to be added, and then both of the SSDs will
show up and not conflict when booting off of one of them. If you boot
up your computer with both SSDs installed without this patch, you may
also randomly get into a kernel panic (if the initrd is not set up) or
stuck in the initrd "/init" process, it is set up, however, if you do
apply this patch, there should not be problems with booting or seeing
both contents of the drive. Tested with the btrfs filesystem with a
RAID configuration of having the root drive '/' combined to make two
256GB Acer FA100 SSDs become 512GB in total storage.

Kernel Logs with patch applied (`dmesg -t | grep -i nvm`):

```
...
nvme 0000:04:00.0: platform quirk: setting simple suspend
nvme nvme0: pci function 0000:04:00.0
nvme 0000:05:00.0: platform quirk: setting simple suspend
nvme nvme1: pci function 0000:05:00.0
nvme nvme1: missing or invalid SUBNQN field.
nvme nvme1: allocated 64 MiB host memory buffer.
nvme nvme0: missing or invalid SUBNQN field.
nvme nvme0: allocated 64 MiB host memory buffer.
nvme nvme1: 8/0/0 default/read/poll queues
nvme nvme1: Ignoring bogus Namespace Identifiers
nvme nvme0: 8/0/0 default/read/poll queues
nvme nvme0: Ignoring bogus Namespace Identifiers
nvme0n1: p1 p2
...
```

Kernel Logs with patch not applied (`dmesg -t | grep -i nvm`):

```
...
nvme 0000:04:00.0: platform quirk: setting simple suspend
nvme nvme0: pci function 0000:04:00.0
nvme 0000:05:00.0: platform quirk: setting simple suspend
nvme nvme1: pci function 0000:05:00.0
nvme nvme0: missing or invalid SUBNQN field.
nvme nvme1: missing or invalid SUBNQN field.
nvme nvme0: allocated 64 MiB host memory buffer.
nvme nvme1: allocated 64 MiB host memory buffer.
nvme nvme0: 8/0/0 default/read/poll queues
nvme nvme1: 8/0/0 default/read/poll queues
nvme nvme1: globally duplicate IDs for nsid 1
nvme nvme1: VID:DID 1dbe:5216 model:Acer SSD FA100 256GB firmware:1.Z.J.2X
nvme0n1: p1 p2
...
```

Signed-off-by: Christopher Lentocha <christopherericlentocha@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/pci.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 9197a5b173fdf..950289405ef28 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -3706,6 +3706,8 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(0x1cc1, 0x5350),   /* ADATA XPG GAMMIX S50 */
 		.driver_data = NVME_QUIRK_BOGUS_NID, },
+	{ PCI_DEVICE(0x1dbe, 0x5216),   /* Acer/INNOGRIT FA100/5216 NVMe SSD */
+		.driver_data = NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(0x1dbe, 0x5236),   /* ADATA XPG GAMMIX S70 */
 		.driver_data = NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(0x1e49, 0x0021),   /* ZHITAI TiPro5000 NVMe SSD */

From 84e009042d0f3dfe91bec60bcd208ee3f866cbcd Mon Sep 17 00:00:00 2001
From: Maurizio Lombardi <mlombard@redhat.com>
Date: Mon, 17 Feb 2025 17:08:27 +0100
Subject: [PATCH 0319/1173] nvme-tcp: add basic support for the C2HTermReq PDU

Previously, the NVMe/TCP host driver did not handle the C2HTermReq PDU,
instead printing "unsupported pdu type (3)" when received. This patch adds
support for processing the C2HTermReq PDU, allowing the driver
to print the Fatal Error Status field.

Example of output:
nvme nvme4: Received C2HTermReq (FES = Invalid PDU Header Field)

Signed-off-by: Maurizio Lombardi <mlombard@redhat.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/tcp.c  | 43 ++++++++++++++++++++++++++++++++++++++++
 include/linux/nvme-tcp.h |  2 ++
 2 files changed, 45 insertions(+)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 841238f38fdda..038b35238c26d 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -763,6 +763,40 @@ static int nvme_tcp_handle_r2t(struct nvme_tcp_queue *queue,
 	return 0;
 }
 
+static void nvme_tcp_handle_c2h_term(struct nvme_tcp_queue *queue,
+		struct nvme_tcp_term_pdu *pdu)
+{
+	u16 fes;
+	const char *msg;
+	u32 plen = le32_to_cpu(pdu->hdr.plen);
+
+	static const char * const msg_table[] = {
+		[NVME_TCP_FES_INVALID_PDU_HDR] = "Invalid PDU Header Field",
+		[NVME_TCP_FES_PDU_SEQ_ERR] = "PDU Sequence Error",
+		[NVME_TCP_FES_HDR_DIGEST_ERR] = "Header Digest Error",
+		[NVME_TCP_FES_DATA_OUT_OF_RANGE] = "Data Transfer Out Of Range",
+		[NVME_TCP_FES_R2T_LIMIT_EXCEEDED] = "R2T Limit Exceeded",
+		[NVME_TCP_FES_UNSUPPORTED_PARAM] = "Unsupported Parameter",
+	};
+
+	if (plen < NVME_TCP_MIN_C2HTERM_PLEN ||
+	    plen > NVME_TCP_MAX_C2HTERM_PLEN) {
+		dev_err(queue->ctrl->ctrl.device,
+			"Received a malformed C2HTermReq PDU (plen = %u)\n",
+			plen);
+		return;
+	}
+
+	fes = le16_to_cpu(pdu->fes);
+	if (fes && fes < ARRAY_SIZE(msg_table))
+		msg = msg_table[fes];
+	else
+		msg = "Unknown";
+
+	dev_err(queue->ctrl->ctrl.device,
+		"Received C2HTermReq (FES = %s)\n", msg);
+}
+
 static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb,
 		unsigned int *offset, size_t *len)
 {
@@ -784,6 +818,15 @@ static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb,
 		return 0;
 
 	hdr = queue->pdu;
+	if (unlikely(hdr->type == nvme_tcp_c2h_term)) {
+		/*
+		 * C2HTermReq never includes Header or Data digests.
+		 * Skip the checks.
+		 */
+		nvme_tcp_handle_c2h_term(queue, (void *)queue->pdu);
+		return -EINVAL;
+	}
+
 	if (queue->hdr_digest) {
 		ret = nvme_tcp_verify_hdgst(queue, queue->pdu, hdr->hlen);
 		if (unlikely(ret))
diff --git a/include/linux/nvme-tcp.h b/include/linux/nvme-tcp.h
index e07e8978d691b..e435250fcb4d0 100644
--- a/include/linux/nvme-tcp.h
+++ b/include/linux/nvme-tcp.h
@@ -13,6 +13,8 @@
 #define NVME_TCP_ADMIN_CCSZ	SZ_8K
 #define NVME_TCP_DIGEST_LENGTH	4
 #define NVME_TCP_MIN_MAXH2CDATA 4096
+#define NVME_TCP_MIN_C2HTERM_PLEN	24
+#define NVME_TCP_MAX_C2HTERM_PLEN	152
 
 enum nvme_tcp_pfv {
 	NVME_TCP_PFV_1_0 = 0x0,

From 4082326807072b71496501b6a0c55ffe8d5092a5 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@kernel.org>
Date: Fri, 7 Feb 2025 13:41:34 +0100
Subject: [PATCH 0320/1173] nvmet: Fix crash when a namespace is disabled

The namespace percpu counter protects pending I/O, and we can
only safely diable the namespace once the counter drop to zero.
Otherwise we end up with a crash when running blktests/nvme/058
(eg for loop transport):

[ 2352.930426] [  T53909] Oops: general protection fault, probably for non-canonical address 0xdffffc0000000005: 0000 [#1] PREEMPT SMP KASAN PTI
[ 2352.930431] [  T53909] KASAN: null-ptr-deref in range [0x0000000000000028-0x000000000000002f]
[ 2352.930434] [  T53909] CPU: 3 UID: 0 PID: 53909 Comm: kworker/u16:5 Tainted: G        W          6.13.0-rc6 #232
[ 2352.930438] [  T53909] Tainted: [W]=WARN
[ 2352.930440] [  T53909] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.3-3.fc41 04/01/2014
[ 2352.930443] [  T53909] Workqueue: nvmet-wq nvme_loop_execute_work [nvme_loop]
[ 2352.930449] [  T53909] RIP: 0010:blkcg_set_ioprio+0x44/0x180

as the queue is already torn down when calling submit_bio();

So we need to init the percpu counter in nvmet_ns_enable(), and
wait for it to drop to zero in nvmet_ns_disable() to avoid having
I/O pending after the namespace has been disabled.

Fixes: 74d16965d7ac ("nvmet-loop: avoid using mutex in IO hotpath")

Signed-off-by: Hannes Reinecke <hare@kernel.org>
Reviewed-by: Nilay Shroff <nilay@linux.ibm.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Tested-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/core.c | 40 ++++++++++++++++++--------------------
 1 file changed, 19 insertions(+), 21 deletions(-)

diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index cdc4a09a6e8a4..2e741696f3712 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -606,6 +606,9 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
 			goto out_dev_put;
 	}
 
+	if (percpu_ref_init(&ns->ref, nvmet_destroy_namespace, 0, GFP_KERNEL))
+		goto out_pr_exit;
+
 	nvmet_ns_changed(subsys, ns->nsid);
 	ns->enabled = true;
 	xa_set_mark(&subsys->namespaces, ns->nsid, NVMET_NS_ENABLED);
@@ -613,6 +616,9 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
 out_unlock:
 	mutex_unlock(&subsys->lock);
 	return ret;
+out_pr_exit:
+	if (ns->pr.enable)
+		nvmet_pr_exit_ns(ns);
 out_dev_put:
 	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry)
 		pci_dev_put(radix_tree_delete(&ctrl->p2p_ns_map, ns->nsid));
@@ -638,6 +644,19 @@ void nvmet_ns_disable(struct nvmet_ns *ns)
 
 	mutex_unlock(&subsys->lock);
 
+	/*
+	 * Now that we removed the namespaces from the lookup list, we
+	 * can kill the per_cpu ref and wait for any remaining references
+	 * to be dropped, as well as a RCU grace period for anyone only
+	 * using the namepace under rcu_read_lock().  Note that we can't
+	 * use call_rcu here as we need to ensure the namespaces have
+	 * been fully destroyed before unloading the module.
+	 */
+	percpu_ref_kill(&ns->ref);
+	synchronize_rcu();
+	wait_for_completion(&ns->disable_done);
+	percpu_ref_exit(&ns->ref);
+
 	if (ns->pr.enable)
 		nvmet_pr_exit_ns(ns);
 
@@ -660,22 +679,6 @@ void nvmet_ns_free(struct nvmet_ns *ns)
 	if (ns->nsid == subsys->max_nsid)
 		subsys->max_nsid = nvmet_max_nsid(subsys);
 
-	mutex_unlock(&subsys->lock);
-
-	/*
-	 * Now that we removed the namespaces from the lookup list, we
-	 * can kill the per_cpu ref and wait for any remaining references
-	 * to be dropped, as well as a RCU grace period for anyone only
-	 * using the namepace under rcu_read_lock().  Note that we can't
-	 * use call_rcu here as we need to ensure the namespaces have
-	 * been fully destroyed before unloading the module.
-	 */
-	percpu_ref_kill(&ns->ref);
-	synchronize_rcu();
-	wait_for_completion(&ns->disable_done);
-	percpu_ref_exit(&ns->ref);
-
-	mutex_lock(&subsys->lock);
 	subsys->nr_namespaces--;
 	mutex_unlock(&subsys->lock);
 
@@ -705,9 +708,6 @@ struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid)
 	ns->nsid = nsid;
 	ns->subsys = subsys;
 
-	if (percpu_ref_init(&ns->ref, nvmet_destroy_namespace, 0, GFP_KERNEL))
-		goto out_free;
-
 	if (ns->nsid > subsys->max_nsid)
 		subsys->max_nsid = nsid;
 
@@ -730,8 +730,6 @@ struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid)
 	return ns;
 out_exit:
 	subsys->max_nsid = nvmet_max_nsid(subsys);
-	percpu_ref_exit(&ns->ref);
-out_free:
 	kfree(ns);
 out_unlock:
 	mutex_unlock(&subsys->lock);

From 3988ac1c67e6e84d2feb987d7b36d5791174b3da Mon Sep 17 00:00:00 2001
From: Ruozhu Li <david.li@jaguarmicro.com>
Date: Sun, 16 Feb 2025 20:49:56 +0800
Subject: [PATCH 0321/1173] nvmet-rdma: recheck queue state is LIVE in state
 lock in recv done

The queue state checking in nvmet_rdma_recv_done is not in queue state
lock.Queue state can transfer to LIVE in cm establish handler between
state checking and state lock here, cause a silent drop of nvme connect
cmd.
Recheck queue state whether in LIVE state in state lock to prevent this
issue.

Signed-off-by: Ruozhu Li <david.li@jaguarmicro.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/rdma.c | 33 +++++++++++++++++++++++----------
 1 file changed, 23 insertions(+), 10 deletions(-)

diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 1afd93026f9bf..2a4536ef61848 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -996,6 +996,27 @@ static void nvmet_rdma_handle_command(struct nvmet_rdma_queue *queue,
 	nvmet_req_complete(&cmd->req, status);
 }
 
+static bool nvmet_rdma_recv_not_live(struct nvmet_rdma_queue *queue,
+		struct nvmet_rdma_rsp *rsp)
+{
+	unsigned long flags;
+	bool ret = true;
+
+	spin_lock_irqsave(&queue->state_lock, flags);
+	/*
+	 * recheck queue state is not live to prevent a race condition
+	 * with RDMA_CM_EVENT_ESTABLISHED handler.
+	 */
+	if (queue->state == NVMET_RDMA_Q_LIVE)
+		ret = false;
+	else if (queue->state == NVMET_RDMA_Q_CONNECTING)
+		list_add_tail(&rsp->wait_list, &queue->rsp_wait_list);
+	else
+		nvmet_rdma_put_rsp(rsp);
+	spin_unlock_irqrestore(&queue->state_lock, flags);
+	return ret;
+}
+
 static void nvmet_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc)
 {
 	struct nvmet_rdma_cmd *cmd =
@@ -1038,17 +1059,9 @@ static void nvmet_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc)
 	rsp->n_rdma = 0;
 	rsp->invalidate_rkey = 0;
 
-	if (unlikely(queue->state != NVMET_RDMA_Q_LIVE)) {
-		unsigned long flags;
-
-		spin_lock_irqsave(&queue->state_lock, flags);
-		if (queue->state == NVMET_RDMA_Q_CONNECTING)
-			list_add_tail(&rsp->wait_list, &queue->rsp_wait_list);
-		else
-			nvmet_rdma_put_rsp(rsp);
-		spin_unlock_irqrestore(&queue->state_lock, flags);
+	if (unlikely(queue->state != NVMET_RDMA_Q_LIVE) &&
+	    nvmet_rdma_recv_not_live(queue, rsp))
 		return;
-	}
 
 	nvmet_rdma_handle_command(queue, rsp);
 }

From 68a5c91f01fc9f086567b260cced003ed9fdff3f Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 13 Feb 2025 15:52:28 +0900
Subject: [PATCH 0322/1173] nvmet: pci-epf: Correctly initialize CSTS when
 enabling the controller

The function nvmet_pci_epf_poll_cc_work() sets the NVME_CSTS_RDY bit of
the controller status register (CSTS) when nvmet_pci_epf_enable_ctrl()
returns success. However, since this function can be called several
times (e.g. if the host reboots), instead of setting the bit in
ctrl->csts, initialize this field to only have NVME_CSTS_RDY set.
Conversely, if nvmet_pci_epf_enable_ctrl() fails, make sure to clear all
bits from ctrl->csts.

To simplify nvmet_pci_epf_poll_cc_work(), initialize ctrl->csts to
NVME_CSTS_RDY directly inside nvmet_pci_epf_enable_ctrl() and clear this
field in that function as well in case of a failure. To be consistent,
move clearing the NVME_CSTS_RDY bit from ctrl->csts when the controller
is being disabled from nvmet_pci_epf_poll_cc_work() into
nvmet_pci_epf_disable_ctrl().

Fixes: 0faa0fe6f90e ("nvmet: New NVMe PCI endpoint function target driver")
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/pci-epf.c | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/drivers/nvme/target/pci-epf.c b/drivers/nvme/target/pci-epf.c
index ac30b42cc6221..efd4623fb0022 100644
--- a/drivers/nvme/target/pci-epf.c
+++ b/drivers/nvme/target/pci-epf.c
@@ -1822,14 +1822,14 @@ static int nvmet_pci_epf_enable_ctrl(struct nvmet_pci_epf_ctrl *ctrl)
 	if (ctrl->io_sqes < sizeof(struct nvme_command)) {
 		dev_err(ctrl->dev, "Unsupported I/O SQES %zu (need %zu)\n",
 			ctrl->io_sqes, sizeof(struct nvme_command));
-		return -EINVAL;
+		goto err;
 	}
 
 	ctrl->io_cqes = 1UL << nvmet_cc_iocqes(ctrl->cc);
 	if (ctrl->io_cqes < sizeof(struct nvme_completion)) {
 		dev_err(ctrl->dev, "Unsupported I/O CQES %zu (need %zu)\n",
 			ctrl->io_sqes, sizeof(struct nvme_completion));
-		return -EINVAL;
+		goto err;
 	}
 
 	/* Create the admin queue. */
@@ -1844,7 +1844,7 @@ static int nvmet_pci_epf_enable_ctrl(struct nvmet_pci_epf_ctrl *ctrl)
 				qsize, pci_addr, 0);
 	if (status != NVME_SC_SUCCESS) {
 		dev_err(ctrl->dev, "Failed to create admin completion queue\n");
-		return -EINVAL;
+		goto err;
 	}
 
 	qsize = aqa & 0x00000fff;
@@ -1854,17 +1854,22 @@ static int nvmet_pci_epf_enable_ctrl(struct nvmet_pci_epf_ctrl *ctrl)
 	if (status != NVME_SC_SUCCESS) {
 		dev_err(ctrl->dev, "Failed to create admin submission queue\n");
 		nvmet_pci_epf_delete_cq(ctrl->tctrl, 0);
-		return -EINVAL;
+		goto err;
 	}
 
 	ctrl->sq_ab = NVMET_PCI_EPF_SQ_AB;
 	ctrl->irq_vector_threshold = NVMET_PCI_EPF_IV_THRESHOLD;
 	ctrl->enabled = true;
+	ctrl->csts = NVME_CSTS_RDY;
 
 	/* Start polling the controller SQs. */
 	schedule_delayed_work(&ctrl->poll_sqs, 0);
 
 	return 0;
+
+err:
+	ctrl->csts = 0;
+	return -EINVAL;
 }
 
 static void nvmet_pci_epf_disable_ctrl(struct nvmet_pci_epf_ctrl *ctrl)
@@ -1889,6 +1894,8 @@ static void nvmet_pci_epf_disable_ctrl(struct nvmet_pci_epf_ctrl *ctrl)
 	/* Delete the admin queue last. */
 	nvmet_pci_epf_delete_sq(ctrl->tctrl, 0);
 	nvmet_pci_epf_delete_cq(ctrl->tctrl, 0);
+
+	ctrl->csts &= ~NVME_CSTS_RDY;
 }
 
 static void nvmet_pci_epf_poll_cc_work(struct work_struct *work)
@@ -1909,13 +1916,10 @@ static void nvmet_pci_epf_poll_cc_work(struct work_struct *work)
 		ret = nvmet_pci_epf_enable_ctrl(ctrl);
 		if (ret)
 			return;
-		ctrl->csts |= NVME_CSTS_RDY;
 	}
 
-	if (!nvmet_cc_en(new_cc) && nvmet_cc_en(old_cc)) {
+	if (!nvmet_cc_en(new_cc) && nvmet_cc_en(old_cc))
 		nvmet_pci_epf_disable_ctrl(ctrl);
-		ctrl->csts &= ~NVME_CSTS_RDY;
-	}
 
 	if (nvmet_cc_shn(new_cc) && !nvmet_cc_shn(old_cc)) {
 		nvmet_pci_epf_disable_ctrl(ctrl);

From ffa35567632c0059e7f380ed155e26a07ec4153f Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 13 Feb 2025 15:52:29 +0900
Subject: [PATCH 0323/1173] nvmet: pci-epf: Do not uselessly write the CSTS
 register

The function nvmet_pci_epf_poll_cc_work() will do nothing if there are
no changes to the controller configuration (CC) register. However, even
for such case, this function still calls nvmet_update_cc() and uselessly
writes the CSTS register. Avoid this by simply rescheduling the poll_cc
work if the CC register has not changed.

Also reschedule the poll_cc work if the function
nvmet_pci_epf_enable_ctrl() fails to allow the host the chance to try
again enabling the controller.

While at it, since there is no point in trying to handle the CC register
as quickly as possible, change the poll_cc work scheduling interval to
10 ms (from 5ms), to avoid excessive read accesses to that register.

Fixes: 0faa0fe6f90e ("nvmet: New NVMe PCI endpoint function target driver")
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/pci-epf.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/target/pci-epf.c b/drivers/nvme/target/pci-epf.c
index efd4623fb0022..b646a8f468ea9 100644
--- a/drivers/nvme/target/pci-epf.c
+++ b/drivers/nvme/target/pci-epf.c
@@ -46,7 +46,7 @@ static DEFINE_MUTEX(nvmet_pci_epf_ports_mutex);
 /*
  * BAR CC register and SQ polling intervals.
  */
-#define NVMET_PCI_EPF_CC_POLL_INTERVAL	msecs_to_jiffies(5)
+#define NVMET_PCI_EPF_CC_POLL_INTERVAL	msecs_to_jiffies(10)
 #define NVMET_PCI_EPF_SQ_POLL_INTERVAL	msecs_to_jiffies(5)
 #define NVMET_PCI_EPF_SQ_POLL_IDLE	msecs_to_jiffies(5000)
 
@@ -1910,12 +1910,15 @@ static void nvmet_pci_epf_poll_cc_work(struct work_struct *work)
 
 	old_cc = ctrl->cc;
 	new_cc = nvmet_pci_epf_bar_read32(ctrl, NVME_REG_CC);
+	if (new_cc == old_cc)
+		goto reschedule_work;
+
 	ctrl->cc = new_cc;
 
 	if (nvmet_cc_en(new_cc) && !nvmet_cc_en(old_cc)) {
 		ret = nvmet_pci_epf_enable_ctrl(ctrl);
 		if (ret)
-			return;
+			goto reschedule_work;
 	}
 
 	if (!nvmet_cc_en(new_cc) && nvmet_cc_en(old_cc))
@@ -1932,6 +1935,7 @@ static void nvmet_pci_epf_poll_cc_work(struct work_struct *work)
 	nvmet_update_cc(ctrl->tctrl, ctrl->cc);
 	nvmet_pci_epf_bar_write32(ctrl, NVME_REG_CSTS, ctrl->csts);
 
+reschedule_work:
 	schedule_delayed_work(&ctrl->poll_cc, NVMET_PCI_EPF_CC_POLL_INTERVAL);
 }
 

From 01ef7ff7dd3cd8cc71af8d1d1496be853281a948 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 13 Feb 2025 15:52:30 +0900
Subject: [PATCH 0324/1173] nvmet: pci-epf: Avoid RCU stalls under heavy
 workload

The delayed work item function nvmet_pci_epf_poll_sqs_work() polls all
submission queues and keeps running in a loop as long as commands are
being submitted by the host. Depending on the preemption configuration
of the kernel, under heavy command workload, this function can thus run
for more than RCU_CPU_STALL_TIMEOUT seconds, leading to a RCU stall:

 rcu: INFO: rcu_sched self-detected stall on CPU
 rcu:   5-....: (20998 ticks this GP) idle=4244/1/0x4000000000000000 softirq=301/301 fqs=5132
 rcu:   (t=21000 jiffies g=-443 q=12 ncpus=8)
 CPU: 5 UID: 0 PID: 82 Comm: kworker/5:1 Not tainted 6.14.0-rc2 #1
 Hardware name: Radxa ROCK 5B (DT)
 Workqueue: events nvmet_pci_epf_poll_sqs_work [nvmet_pci_epf]
 pstate: 60400009 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
 pc : dw_edma_device_tx_status+0xb8/0x130
 lr : dw_edma_device_tx_status+0x9c/0x130
 sp : ffff800080b5bbb0
 x29: ffff800080b5bbb0 x28: ffff0331c5c78400 x27: ffff0331c1cd1960
 x26: ffff0331c0e39010 x25: ffff0331c20e4000 x24: ffff0331c20e4a90
 x23: 0000000000000000 x22: 0000000000000001 x21: 00000000005aca33
 x20: ffff800080b5bc30 x19: ffff0331c123e370 x18: 000000000ab29e62
 x17: ffffb2a878c9c118 x16: ffff0335bde82040 x15: 0000000000000000
 x14: 000000000000017b x13: 00000000ee601780 x12: 0000000000000018
 x11: 0000000000000000 x10: 0000000000000001 x9 : 0000000000000040
 x8 : 00000000ee601780 x7 : 0000000105c785c0 x6 : ffff0331c1027d80
 x5 : 0000000001ee7ad6 x4 : ffff0335bdea16c0 x3 : ffff0331c123e438
 x2 : 00000000005aca33 x1 : 0000000000000000 x0 : ffff0331c123e410
 Call trace:
  dw_edma_device_tx_status+0xb8/0x130 (P)
  dma_sync_wait+0x60/0xbc
  nvmet_pci_epf_dma_transfer+0x128/0x264 [nvmet_pci_epf]
  nvmet_pci_epf_poll_sqs_work+0x2a0/0x2e0 [nvmet_pci_epf]
  process_one_work+0x144/0x390
  worker_thread+0x27c/0x458
  kthread+0xe8/0x19c
  ret_from_fork+0x10/0x20

The solution for this is simply to explicitly allow rescheduling using
cond_resched(). However, since doing so for every loop of
nvmet_pci_epf_poll_sqs_work() significantly degrades performance
(for 4K random reads using 4 I/O queues, the maximum IOPS goes down from
137 KIOPS to 110 KIOPS), call cond_resched() every second to avoid the
RCU stalls.

Fixes: 0faa0fe6f90e ("nvmet: New NVMe PCI endpoint function target driver")
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/pci-epf.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/nvme/target/pci-epf.c b/drivers/nvme/target/pci-epf.c
index b646a8f468ea9..565d2bd36dcde 100644
--- a/drivers/nvme/target/pci-epf.c
+++ b/drivers/nvme/target/pci-epf.c
@@ -1694,6 +1694,7 @@ static void nvmet_pci_epf_poll_sqs_work(struct work_struct *work)
 	struct nvmet_pci_epf_ctrl *ctrl =
 		container_of(work, struct nvmet_pci_epf_ctrl, poll_sqs.work);
 	struct nvmet_pci_epf_queue *sq;
+	unsigned long limit = jiffies;
 	unsigned long last = 0;
 	int i, nr_sqs;
 
@@ -1708,6 +1709,16 @@ static void nvmet_pci_epf_poll_sqs_work(struct work_struct *work)
 				nr_sqs++;
 		}
 
+		/*
+		 * If we have been running for a while, reschedule to let other
+		 * tasks run and to avoid RCU stalls.
+		 */
+		if (time_is_before_jiffies(limit + secs_to_jiffies(1))) {
+			cond_resched();
+			limit = jiffies;
+			continue;
+		}
+
 		if (nr_sqs) {
 			last = jiffies;
 			continue;

From cd513e0434c3e736c549bc99bf7982658b25114d Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 13 Feb 2025 15:52:31 +0900
Subject: [PATCH 0325/1173] nvme: tcp: Fix compilation warning with W=1

When compiling with W=1, a warning result for the function
nvme_tcp_set_queue_io_cpu():

host/tcp.c:1578: warning: Function parameter or struct member 'queue'
not described in 'nvme_tcp_set_queue_io_cpu'
host/tcp.c:1578: warning: expecting prototype for Track the number of
queues assigned to each cpu using a global per(). Prototype was for
nvme_tcp_set_queue_io_cpu() instead

Avoid this warning by using the regular comment format for the function
nvme_tcp_set_queue_io_cpu() instead of the kdoc comment format.

Fixes: 32193789878c ("nvme-tcp: Fix I/O queue cpu spreading for multiple controllers")
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/tcp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 038b35238c26d..a7398e9e5f71c 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1608,7 +1608,7 @@ static bool nvme_tcp_poll_queue(struct nvme_tcp_queue *queue)
 			  ctrl->io_queues[HCTX_TYPE_POLL];
 }
 
-/**
+/*
  * Track the number of queues assigned to each cpu using a global per-cpu
  * counter and select the least used cpu from the mq_map. Our goal is to spread
  * different controllers I/O threads across different cpu cores.

From 578539e0969028f711c34d9a4565931edfe1d730 Mon Sep 17 00:00:00 2001
From: Caleb Sander Mateos <csander@purestorage.com>
Date: Fri, 24 Jan 2025 11:43:10 -0700
Subject: [PATCH 0326/1173] nvme-tcp: fix connect failure on receiving partial
 ICResp PDU

nvme_tcp_init_connection() attempts to receive an ICResp PDU but only
checks that the return value from recvmsg() is non-negative. If the
sender closes the TCP connection or sends fewer than 128 bytes, this
check will pass even though the full PDU wasn't received.

Ensure the full ICResp PDU is received by checking that recvmsg()
returns the expected 128 bytes.

Additionally set the MSG_WAITALL flag for recvmsg(), as a sender could
split the ICResp over multiple TCP frames. Without MSG_WAITALL,
recvmsg() could return prematurely with only part of the PDU.

Fixes: 3f2304f8c6d6 ("nvme-tcp: add NVMe over TCP host driver")
Signed-off-by: Caleb Sander Mateos <csander@purestorage.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/tcp.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index a7398e9e5f71c..8a9131c95a3da 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1492,11 +1492,14 @@ static int nvme_tcp_init_connection(struct nvme_tcp_queue *queue)
 		msg.msg_control = cbuf;
 		msg.msg_controllen = sizeof(cbuf);
 	}
+	msg.msg_flags = MSG_WAITALL;
 	ret = kernel_recvmsg(queue->sock, &msg, &iov, 1,
 			iov.iov_len, msg.msg_flags);
-	if (ret < 0) {
+	if (ret < sizeof(*icresp)) {
 		pr_warn("queue %d: failed to receive icresp, error %d\n",
 			nvme_tcp_queue_id(queue), ret);
+		if (ret >= 0)
+			ret = -ECONNRESET;
 		goto free_icresp;
 	}
 	ret = -ENOTCONN;

From 487a3ea7b1b8ba2ca7d2c2bb3c3594dc360d6261 Mon Sep 17 00:00:00 2001
From: Caleb Sander Mateos <csander@purestorage.com>
Date: Thu, 13 Feb 2025 10:05:14 -0700
Subject: [PATCH 0327/1173] nvme/ioctl: add missing space in err message

nvme_validate_passthru_nsid() logs an err message whose format string is
split over 2 lines. There is a missing space between the two pieces,
resulting in log lines like "... does not match nsid (1)of namespace".
Add the missing space between ")" and "of". Also combine the format
string pieces onto a single line to make the err message easier to grep.

Fixes: e7d4b5493a2d ("nvme: factor out a nvme_validate_passthru_nsid helper")
Signed-off-by: Caleb Sander Mateos <csander@purestorage.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/ioctl.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index e8930146847af..b1b46c2713e1c 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -283,8 +283,7 @@ static bool nvme_validate_passthru_nsid(struct nvme_ctrl *ctrl,
 {
 	if (ns && nsid != ns->head->ns_id) {
 		dev_err(ctrl->device,
-			"%s: nsid (%u) in cmd does not match nsid (%u)"
-			"of namespace\n",
+			"%s: nsid (%u) in cmd does not match nsid (%u) of namespace\n",
 			current->comm, nsid, ns->head->ns_id);
 		return false;
 	}

From d422247d14a53fe825b1778edf104167d8fd8f3f Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 13 Feb 2025 15:49:59 +0900
Subject: [PATCH 0328/1173] nvme: Cleanup the definition of the controller
 config register fields

Reorganized the enum used to define the fields of the contrller
configuration (CC) register in include/linux/nvme.h to:
1) Group together all the values defined for each field.
2) Add the missing field masks definitions.
3) Add comments to describe the enum and each field.

Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 include/linux/nvme.h | 40 +++++++++++++++++++++++++++++++++-------
 1 file changed, 33 insertions(+), 7 deletions(-)

diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index fe3b60818fdcf..2dc05b1c3283d 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -199,28 +199,54 @@ enum {
 #define NVME_NVM_IOSQES		6
 #define NVME_NVM_IOCQES		4
 
+/*
+ * Controller Configuration (CC) register (Offset 14h)
+ */
 enum {
+	/* Enable (EN): bit 0 */
 	NVME_CC_ENABLE		= 1 << 0,
 	NVME_CC_EN_SHIFT	= 0,
+
+	/* Bits 03:01 are reserved (NVMe Base Specification rev 2.1) */
+
+	/* I/O Command Set Selected (CSS): bits 06:04 */
 	NVME_CC_CSS_SHIFT	= 4,
-	NVME_CC_MPS_SHIFT	= 7,
-	NVME_CC_AMS_SHIFT	= 11,
-	NVME_CC_SHN_SHIFT	= 14,
-	NVME_CC_IOSQES_SHIFT	= 16,
-	NVME_CC_IOCQES_SHIFT	= 20,
+	NVME_CC_CSS_MASK	= 7 << NVME_CC_CSS_SHIFT,
 	NVME_CC_CSS_NVM		= 0 << NVME_CC_CSS_SHIFT,
 	NVME_CC_CSS_CSI		= 6 << NVME_CC_CSS_SHIFT,
-	NVME_CC_CSS_MASK	= 7 << NVME_CC_CSS_SHIFT,
+
+	/* Memory Page Size (MPS): bits 10:07 */
+	NVME_CC_MPS_SHIFT	= 7,
+	NVME_CC_MPS_MASK	= 0xf << NVME_CC_MPS_SHIFT,
+
+	/* Arbitration Mechanism Selected (AMS): bits 13:11 */
+	NVME_CC_AMS_SHIFT	= 11,
+	NVME_CC_AMS_MASK	= 7 << NVME_CC_AMS_SHIFT,
 	NVME_CC_AMS_RR		= 0 << NVME_CC_AMS_SHIFT,
 	NVME_CC_AMS_WRRU	= 1 << NVME_CC_AMS_SHIFT,
 	NVME_CC_AMS_VS		= 7 << NVME_CC_AMS_SHIFT,
+
+	/* Shutdown Notification (SHN): bits 15:14 */
+	NVME_CC_SHN_SHIFT	= 14,
+	NVME_CC_SHN_MASK	= 3 << NVME_CC_SHN_SHIFT,
 	NVME_CC_SHN_NONE	= 0 << NVME_CC_SHN_SHIFT,
 	NVME_CC_SHN_NORMAL	= 1 << NVME_CC_SHN_SHIFT,
 	NVME_CC_SHN_ABRUPT	= 2 << NVME_CC_SHN_SHIFT,
-	NVME_CC_SHN_MASK	= 3 << NVME_CC_SHN_SHIFT,
+
+	/* I/O Submission Queue Entry Size (IOSQES): bits 19:16 */
+	NVME_CC_IOSQES_SHIFT	= 16,
+	NVME_CC_IOSQES_MASK	= 0xf << NVME_CC_IOSQES_SHIFT,
 	NVME_CC_IOSQES		= NVME_NVM_IOSQES << NVME_CC_IOSQES_SHIFT,
+
+	/* I/O Completion Queue Entry Size (IOCQES): bits 23:20 */
+	NVME_CC_IOCQES_SHIFT	= 20,
+	NVME_CC_IOCQES_MASK	= 0xf << NVME_CC_IOCQES_SHIFT,
 	NVME_CC_IOCQES		= NVME_NVM_IOCQES << NVME_CC_IOCQES_SHIFT,
+
+	/* Controller Ready Independent of Media Enable (CRIME): bit 24 */
 	NVME_CC_CRIME		= 1 << 24,
+
+	/* Bits 25:31 are reserved (NVMe Base Specification rev 2.1) */
 };
 
 enum {

From 2ba8cf918f0d1873cd5430ae2cc3c41711a144d7 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 13 Feb 2025 15:50:00 +0900
Subject: [PATCH 0329/1173] nvmet: Use enum definitions instead of hardcoded
 values

Change the definition of the inline functions nvmet_cc_en(),
nvmet_cc_css(), nvmet_cc_mps(), nvmet_cc_ams(), nvmet_cc_shn(),
nvmet_cc_iosqes(), and nvmet_cc_iocqes() to use the enum difinitions in
include/linux/nvme.h instead of hardcoded values.

Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/nvmet.h | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 4be8d22d2d8d4..d2c1233981e1a 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -784,37 +784,37 @@ u16 nvmet_report_invalid_opcode(struct nvmet_req *req);
 
 static inline bool nvmet_cc_en(u32 cc)
 {
-	return (cc >> NVME_CC_EN_SHIFT) & 0x1;
+	return (cc & NVME_CC_ENABLE) >> NVME_CC_EN_SHIFT;
 }
 
 static inline u8 nvmet_cc_css(u32 cc)
 {
-	return (cc >> NVME_CC_CSS_SHIFT) & 0x7;
+	return (cc & NVME_CC_CSS_MASK) >> NVME_CC_CSS_SHIFT;
 }
 
 static inline u8 nvmet_cc_mps(u32 cc)
 {
-	return (cc >> NVME_CC_MPS_SHIFT) & 0xf;
+	return (cc & NVME_CC_MPS_MASK) >> NVME_CC_MPS_SHIFT;
 }
 
 static inline u8 nvmet_cc_ams(u32 cc)
 {
-	return (cc >> NVME_CC_AMS_SHIFT) & 0x7;
+	return (cc & NVME_CC_AMS_MASK) >> NVME_CC_AMS_SHIFT;
 }
 
 static inline u8 nvmet_cc_shn(u32 cc)
 {
-	return (cc >> NVME_CC_SHN_SHIFT) & 0x3;
+	return (cc & NVME_CC_SHN_MASK) >> NVME_CC_SHN_SHIFT;
 }
 
 static inline u8 nvmet_cc_iosqes(u32 cc)
 {
-	return (cc >> NVME_CC_IOSQES_SHIFT) & 0xf;
+	return (cc & NVME_CC_IOSQES_MASK) >> NVME_CC_IOSQES_SHIFT;
 }
 
 static inline u8 nvmet_cc_iocqes(u32 cc)
 {
-	return (cc >> NVME_CC_IOCQES_SHIFT) & 0xf;
+	return (cc & NVME_CC_IOCQES_MASK) >> NVME_CC_IOCQES_SHIFT;
 }
 
 /* Convert a 32-bit number to a 16-bit 0's based number */

From eefa72a15ea03fd009333aaa9f0e360b2578e434 Mon Sep 17 00:00:00 2001
From: Hector Martin <marcan@marcan.st>
Date: Thu, 13 Feb 2025 11:12:59 -0500
Subject: [PATCH 0330/1173] apple-nvme: Release power domains when probe fails

Signed-off-by: Hector Martin <marcan@marcan.st>
Reviewed-by: Neal Gompa <neal@gompa.dev>
Reviewed-by: Sven Peter <sven@svenpeter.dev>
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/apple.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c
index 1de11b722f049..7995f0776bc06 100644
--- a/drivers/nvme/host/apple.c
+++ b/drivers/nvme/host/apple.c
@@ -1516,6 +1516,7 @@ static struct apple_nvme *apple_nvme_alloc(struct platform_device *pdev)
 
 	return anv;
 put_dev:
+	apple_nvme_detach_genpd(anv);
 	put_device(anv->dev);
 	return ERR_PTR(ret);
 }
@@ -1549,6 +1550,7 @@ static int apple_nvme_probe(struct platform_device *pdev)
 	nvme_uninit_ctrl(&anv->ctrl);
 out_put_ctrl:
 	nvme_put_ctrl(&anv->ctrl);
+	apple_nvme_detach_genpd(anv);
 	return ret;
 }
 

From 3f22421f6a240b33ab8ffbf662bf0a8f336f405b Mon Sep 17 00:00:00 2001
From: Hector Martin <marcan@marcan.st>
Date: Thu, 13 Feb 2025 11:12:58 -0500
Subject: [PATCH 0331/1173] apple-nvme: Support coprocessors left idle

iBoot on at least some firmwares/machines leaves ANS2 running, requiring
a wake command instead of a CPU boot (and if we reset ANS2 in that
state, everything breaks).

Only stop the CPU if RTKit was running, and only do the reset dance if
the CPU is stopped.

Normal shutdown handoff:
- RTKit not yet running
- CPU detected not running
- Reset
- CPU powerup
- RTKit boot wait

ANS2 left running/idle:
- RTKit not yet running
- CPU detected running
- RTKit wake message

Sleep/resume cycle:
- RTKit shutdown
- CPU stopped
- (sleep here)
- CPU detected not running
- Reset
- CPU powerup
- RTKit boot wait

Shutdown or device removal:
- RTKit shutdown
- CPU stopped

Therefore, the CPU running bit serves as a consistent flag of whether
the coprocessor is fully stopped or just idle.

Signed-off-by: Hector Martin <marcan@marcan.st>
Reviewed-by: Neal Gompa <neal@gompa.dev>
Reviewed-by: Sven Peter <sven@svenpeter.dev>
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/apple.c | 53 ++++++++++++++++++++++++++-------------
 1 file changed, 36 insertions(+), 17 deletions(-)

diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c
index 7995f0776bc06..a060f69558e76 100644
--- a/drivers/nvme/host/apple.c
+++ b/drivers/nvme/host/apple.c
@@ -1011,25 +1011,37 @@ static void apple_nvme_reset_work(struct work_struct *work)
 		ret = apple_rtkit_shutdown(anv->rtk);
 		if (ret)
 			goto out;
+
+		writel(0, anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL);
 	}
 
-	writel(0, anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL);
+	/*
+	 * Only do the soft-reset if the CPU is not running, which means either we
+	 * or the previous stage shut it down cleanly.
+	 */
+	if (!(readl(anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL) &
+		APPLE_ANS_COPROC_CPU_CONTROL_RUN)) {
 
-	ret = reset_control_assert(anv->reset);
-	if (ret)
-		goto out;
+		ret = reset_control_assert(anv->reset);
+		if (ret)
+			goto out;
 
-	ret = apple_rtkit_reinit(anv->rtk);
-	if (ret)
-		goto out;
+		ret = apple_rtkit_reinit(anv->rtk);
+		if (ret)
+			goto out;
 
-	ret = reset_control_deassert(anv->reset);
-	if (ret)
-		goto out;
+		ret = reset_control_deassert(anv->reset);
+		if (ret)
+			goto out;
+
+		writel(APPLE_ANS_COPROC_CPU_CONTROL_RUN,
+		       anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL);
+
+		ret = apple_rtkit_boot(anv->rtk);
+	} else {
+		ret = apple_rtkit_wake(anv->rtk);
+	}
 
-	writel(APPLE_ANS_COPROC_CPU_CONTROL_RUN,
-	       anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL);
-	ret = apple_rtkit_boot(anv->rtk);
 	if (ret) {
 		dev_err(anv->dev, "ANS did not boot");
 		goto out;
@@ -1565,9 +1577,12 @@ static void apple_nvme_remove(struct platform_device *pdev)
 	apple_nvme_disable(anv, true);
 	nvme_uninit_ctrl(&anv->ctrl);
 
-	if (apple_rtkit_is_running(anv->rtk))
+	if (apple_rtkit_is_running(anv->rtk)) {
 		apple_rtkit_shutdown(anv->rtk);
 
+		writel(0, anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL);
+	}
+
 	apple_nvme_detach_genpd(anv);
 }
 
@@ -1576,8 +1591,11 @@ static void apple_nvme_shutdown(struct platform_device *pdev)
 	struct apple_nvme *anv = platform_get_drvdata(pdev);
 
 	apple_nvme_disable(anv, true);
-	if (apple_rtkit_is_running(anv->rtk))
+	if (apple_rtkit_is_running(anv->rtk)) {
 		apple_rtkit_shutdown(anv->rtk);
+
+		writel(0, anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL);
+	}
 }
 
 static int apple_nvme_resume(struct device *dev)
@@ -1594,10 +1612,11 @@ static int apple_nvme_suspend(struct device *dev)
 
 	apple_nvme_disable(anv, true);
 
-	if (apple_rtkit_is_running(anv->rtk))
+	if (apple_rtkit_is_running(anv->rtk)) {
 		ret = apple_rtkit_shutdown(anv->rtk);
 
-	writel(0, anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL);
+		writel(0, anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL);
+	}
 
 	return ret;
 }

From eee00df8e1f1f5648ed8f9e40e2bb54c2877344a Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:55:13 +0100
Subject: [PATCH 0332/1173] serial: xilinx_uartps: Use helper function
 hrtimer_update_function()

The field 'function' of struct hrtimer should not be changed directly, as
the write is lockless and a concurrent timer expiry might end up using the
wrong function pointer.

Switch to use hrtimer_update_function() which also performs runtime checks
that it is safe to modify the callback.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/af7823518fb060c6c97105a2513cfc61adbdf38f.1738746927.git.namcao@linutronix.de
---
 drivers/tty/serial/xilinx_uartps.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c
index efb124a19c015..fe457bf1e15bb 100644
--- a/drivers/tty/serial/xilinx_uartps.c
+++ b/drivers/tty/serial/xilinx_uartps.c
@@ -454,7 +454,7 @@ static void cdns_uart_handle_tx(void *dev_id)
 
 	if (cdns_uart->port->rs485.flags & SER_RS485_ENABLED &&
 	    (kfifo_is_empty(&tport->xmit_fifo) || uart_tx_stopped(port))) {
-		cdns_uart->tx_timer.function = &cdns_rs485_rx_callback;
+		hrtimer_update_function(&cdns_uart->tx_timer, cdns_rs485_rx_callback);
 		hrtimer_start(&cdns_uart->tx_timer,
 			      ns_to_ktime(cdns_calc_after_tx_delay(cdns_uart)), HRTIMER_MODE_REL);
 	}
@@ -734,7 +734,7 @@ static void cdns_uart_start_tx(struct uart_port *port)
 
 	if (cdns_uart->port->rs485.flags & SER_RS485_ENABLED) {
 		if (!cdns_uart->rs485_tx_started) {
-			cdns_uart->tx_timer.function = &cdns_rs485_tx_callback;
+			hrtimer_update_function(&cdns_uart->tx_timer, cdns_rs485_tx_callback);
 			cdns_rs485_tx_setup(cdns_uart);
 			return hrtimer_start(&cdns_uart->tx_timer,
 					     ms_to_ktime(port->rs485.delay_rts_before_send),

From 3f8d93d1371f460ed30ebfa30fb930c0605035fc Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:55:14 +0100
Subject: [PATCH 0333/1173] io_uring: Use helper function
 hrtimer_update_function()

The field 'function' of struct hrtimer should not be changed directly, as
the write is lockless and a concurrent timer expiry might end up using the
wrong function pointer.

Switch to use hrtimer_update_function() which also performs runtime checks
that it is safe to modify the callback.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/9b33f490fb1d207d3918ef5e116dc3412ae35c1e.1738746927.git.namcao@linutronix.de
---
 io_uring/io_uring.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index ceacf6230e342..936f8b4106cf3 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -2421,7 +2421,7 @@ static enum hrtimer_restart io_cqring_min_timer_wakeup(struct hrtimer *timer)
 			goto out_wake;
 	}
 
-	iowq->t.function = io_cqring_timer_wakeup;
+	hrtimer_update_function(&iowq->t, io_cqring_timer_wakeup);
 	hrtimer_set_expires(timer, iowq->timeout);
 	return HRTIMER_RESTART;
 out_wake:

From 86a578e780a9fb0e1a1b6f3f3aa847c29b5255b9 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 5 Feb 2025 11:55:15 +0100
Subject: [PATCH 0334/1173] wifi: rt2x00: Switch to use
 hrtimer_update_function()

The field 'function' of struct hrtimer should not be changed directly, as
the write is lockless and a concurrent timer expiry might end up using the
wrong function pointer.

Switch to use hrtimer_update_function() which also performs runtime checks
that it is safe to modify the callback.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/82dcc0eae40bb84e6452f242751c0650e79bd87e.1738746927.git.namcao@linutronix.de
---
 drivers/net/wireless/ralink/rt2x00/rt2800mmio.c | 2 +-
 drivers/net/wireless/ralink/rt2x00/rt2800usb.c  | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800mmio.c b/drivers/net/wireless/ralink/rt2x00/rt2800mmio.c
index 5323acff962a3..45775ecdf2215 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2800mmio.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2800mmio.c
@@ -842,7 +842,7 @@ int rt2800mmio_probe_hw(struct rt2x00_dev *rt2x00dev)
 	/*
 	 * Set txstatus timer function.
 	 */
-	rt2x00dev->txstatus_timer.function = rt2800mmio_tx_sta_fifo_timeout;
+	hrtimer_update_function(&rt2x00dev->txstatus_timer, rt2800mmio_tx_sta_fifo_timeout);
 
 	/*
 	 * Overwrite TX done handler
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800usb.c b/drivers/net/wireless/ralink/rt2x00/rt2800usb.c
index 160bef79acdb7..b51a23300ba24 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2800usb.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2800usb.c
@@ -618,7 +618,7 @@ static int rt2800usb_probe_hw(struct rt2x00_dev *rt2x00dev)
 	/*
 	 * Set txstatus timer function.
 	 */
-	rt2x00dev->txstatus_timer.function = rt2800usb_tx_sta_fifo_timeout;
+	hrtimer_update_function(&rt2x00dev->txstatus_timer, rt2800usb_tx_sta_fifo_timeout);
 
 	/*
 	 * Overwrite TX done handler

From c893ee3f95f16fcb98da934d61483d0b7d8ed568 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Mon, 17 Feb 2025 17:17:41 -0600
Subject: [PATCH 0335/1173] x86/amd_node: Add a smn_read_register() helper

Some of the ACP drivers will poll registers through SMN using
read_poll_timeout() which requires returning the result of the register read
as the argument.

Add a helper to do just that.

Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20250217231747.1656228-2-superm1@kernel.org
---
 arch/x86/include/asm/amd_node.h | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/arch/x86/include/asm/amd_node.h b/arch/x86/include/asm/amd_node.h
index 002c3afbd30f9..23fe617898a8f 100644
--- a/arch/x86/include/asm/amd_node.h
+++ b/arch/x86/include/asm/amd_node.h
@@ -46,4 +46,15 @@ static inline int __must_check amd_smn_hsmp_rdwr(u16 node, u32 address, u32 *val
 }
 #endif /* CONFIG_AMD_NODE */
 
+/* helper for use with read_poll_timeout */
+static inline int smn_read_register(u32 reg)
+{
+	int data, rc;
+
+	rc = amd_smn_read(0, reg, &data);
+	if (rc)
+		return rc;
+
+	return data;
+}
 #endif /*_ASM_X86_AMD_NODE_H_*/

From ed83aff5a94e1d623c007159a6a7f1c3ef202c6c Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Wed, 12 Feb 2025 12:01:15 +0100
Subject: [PATCH 0336/1173] s390: Update defconfigs

Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/configs/debug_defconfig | 2 ++
 arch/s390/configs/defconfig       | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 44f01a4bc810f..80bdfbae6e5b4 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -469,6 +469,7 @@ CONFIG_SCSI_DH_ALUA=m
 CONFIG_MD=y
 CONFIG_BLK_DEV_MD=y
 # CONFIG_MD_BITMAP_FILE is not set
+CONFIG_MD_LINEAR=m
 CONFIG_MD_CLUSTER=m
 CONFIG_BCACHE=m
 CONFIG_BLK_DEV_DM=y
@@ -874,6 +875,7 @@ CONFIG_RCU_CPU_STALL_TIMEOUT=300
 CONFIG_LATENCYTOP=y
 CONFIG_BOOTTIME_TRACING=y
 CONFIG_FUNCTION_GRAPH_RETVAL=y
+CONFIG_FUNCTION_GRAPH_RETADDR=y
 CONFIG_FPROBE=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_STACK_TRACER=y
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index 8bcd37edd3c97..449a0e996b963 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -459,6 +459,7 @@ CONFIG_SCSI_DH_ALUA=m
 CONFIG_MD=y
 CONFIG_BLK_DEV_MD=y
 # CONFIG_MD_BITMAP_FILE is not set
+CONFIG_MD_LINEAR=m
 CONFIG_MD_CLUSTER=m
 CONFIG_BCACHE=m
 CONFIG_BLK_DEV_DM=y
@@ -825,6 +826,7 @@ CONFIG_RCU_CPU_STALL_TIMEOUT=60
 CONFIG_LATENCYTOP=y
 CONFIG_BOOTTIME_TRACING=y
 CONFIG_FUNCTION_GRAPH_RETVAL=y
+CONFIG_FUNCTION_GRAPH_RETADDR=y
 CONFIG_FPROBE=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_STACK_TRACER=y

From 173767c218cc1da74704e7863f165ac8a9796f3e Mon Sep 17 00:00:00 2001
From: Sami Tolvanen <samitolvanen@google.com>
Date: Thu, 13 Feb 2025 21:16:14 +0000
Subject: [PATCH 0337/1173] s390/purgatory: Use -D__DISABLE_EXPORTS

The object files in purgatory do not export symbols, so disable exports
for all the object files, not only sha256.o, with -D__DISABLE_EXPORTS.

This fixes a build failure with CONFIG_GENDWARFKSYMS, where we would
otherwise attempt to calculate symbol versions for purgatory objects and
fail because they're not built with debugging information:

error: gendwarfksyms: process_module: dwarf_get_units failed: no debugging information?
make[5]: *** [../scripts/Makefile.build:207: arch/s390/purgatory/string.o] Error 1
make[5]: *** Deleting file 'arch/s390/purgatory/string.o'

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202502120752.U3fOKScQ-lkp@intel.com/
Signed-off-by: Sami Tolvanen <samitolvanen@google.com>
Link: https://lore.kernel.org/r/20250213211614.3537605-2-samitolvanen@google.com
Acked-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/purgatory/Makefile | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/arch/s390/purgatory/Makefile b/arch/s390/purgatory/Makefile
index bdcf2a3b6c41b..bd39b36e7bd68 100644
--- a/arch/s390/purgatory/Makefile
+++ b/arch/s390/purgatory/Makefile
@@ -8,7 +8,7 @@ PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y))
 $(obj)/sha256.o: $(srctree)/lib/crypto/sha256.c FORCE
 	$(call if_changed_rule,cc_o_c)
 
-CFLAGS_sha256.o := -D__DISABLE_EXPORTS -D__NO_FORTIFY
+CFLAGS_sha256.o := -D__NO_FORTIFY
 
 $(obj)/mem.o: $(srctree)/arch/s390/lib/mem.S FORCE
 	$(call if_changed_rule,as_o_S)
@@ -19,9 +19,11 @@ KBUILD_CFLAGS += -fno-zero-initialized-in-bss -fno-builtin -ffreestanding
 KBUILD_CFLAGS += -Os -m64 -msoft-float -fno-common
 KBUILD_CFLAGS += -fno-stack-protector
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
+KBUILD_CFLAGS += -D__DISABLE_EXPORTS
 KBUILD_CFLAGS += $(CLANG_FLAGS)
 KBUILD_CFLAGS += $(call cc-option,-fno-PIE)
 KBUILD_AFLAGS := $(filter-out -DCC_USING_EXPOLINE,$(KBUILD_AFLAGS))
+KBUILD_AFLAGS += -D__DISABLE_EXPORTS
 
 # Since we link purgatory with -r unresolved symbols are not checked, so we
 # also link a purgatory.chk binary without -r to check for unresolved symbols.

From c3a589fd9fcbf295a7402a4b188dc9277d505f4f Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Tue, 18 Feb 2025 12:11:34 +0100
Subject: [PATCH 0338/1173] s390/boot: Fix ESSA detection

The cmma_test_essa() inline assembly uses tmp as input and output, however
tmp is specified as output only, which allows the compiler to optimize the
initialization of tmp away.

Therefore the ESSA detection may or may not work depending on previous
contents of the register that the compiler selected for tmp.

Fix this by using the correct constraint modifier.

Fixes: 468a3bc2b7b9 ("s390/cmma: move parsing of cmma kernel parameter to early boot code")
Cc: stable@vger.kernel.org
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Reviewed-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/boot/startup.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index 885bd1dd2c82f..9276e0576d0ab 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -86,7 +86,7 @@ static int cmma_test_essa(void)
 		: [reg1] "=&d" (reg1),
 		  [reg2] "=&a" (reg2),
 		  [rc] "+&d" (rc),
-		  [tmp] "=&d" (tmp),
+		  [tmp] "+&d" (tmp),
 		  "+Q" (get_lowcore()->program_new_psw),
 		  "=Q" (old)
 		: [psw_old] "a" (&old),

From 293f324ce96d700112c726682b14094d1b54e09c Mon Sep 17 00:00:00 2001
From: Charlie Jenkins <charlie@rivosinc.com>
Date: Thu, 13 Feb 2025 13:06:21 -0800
Subject: [PATCH 0339/1173] tools: Unify top-level quiet infrastructure

Commit f2868b1a66d4f40f ("perf tools: Expose quiet/verbose variables in
Makefile.perf") moved the quiet infrastructure out of
tools/build/Makefile.build and into the top-level Makefile.perf file so
that the quiet infrastructure could be used throughout perf and not just
in Makefile.build.

Extract out the quiet infrastructure into Makefile.include so that it
can be leveraged outside of perf.

Fixes: f2868b1a66d4f40f ("perf tools: Expose quiet/verbose variables in Makefile.perf")
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Benjamin Tissoires <bentiss@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Hao Luo <haoluo@google.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Kosina <jikos@kernel.org>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: Josh Poimboeuf <jpoimboe@kernel.org>
Cc: KP Singh <kpsingh@kernel.org>
Cc: Lukasz Luba <lukasz.luba@arm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Martin KaFai Lau <martin.lau@linux.dev>
Cc: Mykola Lysenko <mykolal@fb.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Quentin Monnet <qmo@kernel.org>
Cc: Rafael J. Wysocki <rafael@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Song Liu <song@kernel.org>
Cc: Stanislav Fomichev <sdf@google.com>
Cc: Steven Rostedt (VMware) <rostedt@goodmis.org>
Cc: Yonghong Song <yonghong.song@linux.dev>
Cc: Zhang Rui <rui.zhang@intel.com>
Link: https://lore.kernel.org/r/20250213-quiet_tools-v3-1-07de4482a581@rivosinc.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/build/Makefile           |  8 +------
 tools/perf/Makefile.perf       | 41 ----------------------------------
 tools/scripts/Makefile.include | 30 +++++++++++++++++++++++++
 3 files changed, 31 insertions(+), 48 deletions(-)

diff --git a/tools/build/Makefile b/tools/build/Makefile
index 18ad131f6ea74..63ef218787616 100644
--- a/tools/build/Makefile
+++ b/tools/build/Makefile
@@ -17,13 +17,7 @@ $(call allow-override,LD,$(CROSS_COMPILE)ld)
 
 export HOSTCC HOSTLD HOSTAR
 
-ifeq ($(V),1)
-  Q =
-else
-  Q = @
-endif
-
-export Q srctree CC LD
+export srctree CC LD
 
 MAKEFLAGS := --no-print-directory
 build     := -f $(srctree)/tools/build/Makefile.build dir=. obj
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 55d6ce9ea52fb..05c083bb11220 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -161,47 +161,6 @@ export VPATH
 SOURCE := $(shell ln -sf $(srctree)/tools/perf $(OUTPUT)/source)
 endif
 
-# Beautify output
-# ---------------------------------------------------------------------------
-#
-# Most of build commands in Kbuild start with "cmd_". You can optionally define
-# "quiet_cmd_*". If defined, the short log is printed. Otherwise, no log from
-# that command is printed by default.
-#
-# e.g.)
-#    quiet_cmd_depmod = DEPMOD  $(MODLIB)
-#          cmd_depmod = $(srctree)/scripts/depmod.sh $(DEPMOD) $(KERNELRELEASE)
-#
-# A simple variant is to prefix commands with $(Q) - that's useful
-# for commands that shall be hidden in non-verbose mode.
-#
-#    $(Q)$(MAKE) $(build)=scripts/basic
-#
-# To put more focus on warnings, be less verbose as default
-# Use 'make V=1' to see the full commands
-
-ifeq ($(V),1)
-  quiet =
-  Q =
-else
-  quiet=quiet_
-  Q=@
-endif
-
-# If the user is running make -s (silent mode), suppress echoing of commands
-# make-4.0 (and later) keep single letter options in the 1st word of MAKEFLAGS.
-ifeq ($(filter 3.%,$(MAKE_VERSION)),)
-short-opts := $(firstword -$(MAKEFLAGS))
-else
-short-opts := $(filter-out --%,$(MAKEFLAGS))
-endif
-
-ifneq ($(findstring s,$(short-opts)),)
-  quiet=silent_
-endif
-
-export quiet Q
-
 # Do not use make's built-in rules
 # (this improves performance and avoids hard-to-debug behaviour);
 MAKEFLAGS += -r
diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include
index 0aa4005017c72..45f4abef70640 100644
--- a/tools/scripts/Makefile.include
+++ b/tools/scripts/Makefile.include
@@ -136,6 +136,33 @@ else
 NO_SUBDIR = :
 endif
 
+# Beautify output
+# ---------------------------------------------------------------------------
+#
+# Most of build commands in Kbuild start with "cmd_". You can optionally define
+# "quiet_cmd_*". If defined, the short log is printed. Otherwise, no log from
+# that command is printed by default.
+#
+# e.g.)
+#    quiet_cmd_depmod = DEPMOD  $(MODLIB)
+#          cmd_depmod = $(srctree)/scripts/depmod.sh $(DEPMOD) $(KERNELRELEASE)
+#
+# A simple variant is to prefix commands with $(Q) - that's useful
+# for commands that shall be hidden in non-verbose mode.
+#
+#    $(Q)$(MAKE) $(build)=scripts/basic
+#
+# To put more focus on warnings, be less verbose as default
+# Use 'make V=1' to see the full commands
+
+ifeq ($(V),1)
+  quiet =
+  Q =
+else
+  quiet = quiet_
+  Q = @
+endif
+
 # If the user is running make -s (silent mode), suppress echoing of commands
 # make-4.0 (and later) keep single letter options in the 1st word of MAKEFLAGS.
 ifeq ($(filter 3.%,$(MAKE_VERSION)),)
@@ -146,8 +173,11 @@ endif
 
 ifneq ($(findstring s,$(short-opts)),)
   silent=1
+  quiet=silent_
 endif
 
+export quiet Q
+
 #
 # Define a callable command for descending to a new directory
 #

From d403120cb9d4787b283ea202b2162f459d18fe9d Mon Sep 17 00:00:00 2001
From: Kurt Borja <kuurtb@gmail.com>
Date: Wed, 12 Feb 2025 14:30:58 -0500
Subject: [PATCH 0340/1173] ACPI: platform_profile: Fix memory leak in
 profile_class_is_visible()

If class_find_device() finds a device, it's reference count is
incremented.

Call put_device() to drop this reference before returning.

Fixes: 77be5cacb2c2 ("ACPI: platform_profile: Create class for ACPI platform profile")
Signed-off-by: Kurt Borja <kuurtb@gmail.com>
Reviewed-by: Mark Pearson <mpearson-lenovo@squebb.ca>
Link: https://patch.msgid.link/20250212193058.32110-1-kuurtb@gmail.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/platform_profile.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/acpi/platform_profile.c b/drivers/acpi/platform_profile.c
index fc92e43d0fe93..2ad53cc6aae53 100644
--- a/drivers/acpi/platform_profile.c
+++ b/drivers/acpi/platform_profile.c
@@ -417,8 +417,14 @@ static int profile_class_registered(struct device *dev, const void *data)
 
 static umode_t profile_class_is_visible(struct kobject *kobj, struct attribute *attr, int idx)
 {
-	if (!class_find_device(&platform_profile_class, NULL, NULL, profile_class_registered))
+	struct device *dev;
+
+	dev = class_find_device(&platform_profile_class, NULL, NULL, profile_class_registered);
+	if (!dev)
 		return 0;
+
+	put_device(dev);
+
 	return attr->mode;
 }
 

From 643f209ba3fdd4099416aaf9efa8266f7366d6fb Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jos=C3=A9=20Roberto=20de=20Souza?= <jose.souza@intel.com>
Date: Thu, 23 Jan 2025 12:22:04 -0800
Subject: [PATCH 0341/1173] drm/xe: Make GUC binaries dump consistent with
 other binaries in devcoredump
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

All other(hwsp, hwctx and vmas) binaries follow this format:
[name].length: 0x1000
[name].data: xxxxxxx
[name].error: errno

The error one is just in case by some reason it was not able to
capture the binary.

So this GuC binaries should follow the same patern.

v2:
- renamed GUC binary to LOG

Cc: John Harrison <John.C.Harrison@Intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250123202307.95103-3-jose.souza@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit cb1f868ca13756c0c18ba54d1591332476760d07)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_guc_ct.c  | 6 ++++--
 drivers/gpu/drm/xe/xe_guc_log.c | 3 ++-
 2 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index 50c8076b51585..497036675a38c 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -1723,9 +1723,11 @@ void xe_guc_ct_snapshot_print(struct xe_guc_ct_snapshot *snapshot,
 		drm_printf(p, "\tg2h outstanding: %d\n",
 			   snapshot->g2h_outstanding);
 
-		if (snapshot->ctb)
-			xe_print_blob_ascii85(p, "CTB data", '\n',
+		if (snapshot->ctb) {
+			drm_printf(p, "[CTB].length: 0x%lx\n", snapshot->ctb_size);
+			xe_print_blob_ascii85(p, "[CTB].data", '\n',
 					      snapshot->ctb, 0, snapshot->ctb_size);
+		}
 	} else {
 		drm_puts(p, "CT disabled\n");
 	}
diff --git a/drivers/gpu/drm/xe/xe_guc_log.c b/drivers/gpu/drm/xe/xe_guc_log.c
index 2baa4d95571fb..2457572ed86ad 100644
--- a/drivers/gpu/drm/xe/xe_guc_log.c
+++ b/drivers/gpu/drm/xe/xe_guc_log.c
@@ -208,10 +208,11 @@ void xe_guc_log_snapshot_print(struct xe_guc_log_snapshot *snapshot, struct drm_
 	drm_printf(p, "GuC timestamp: 0x%08llX [%llu]\n", snapshot->stamp, snapshot->stamp);
 	drm_printf(p, "Log level: %u\n", snapshot->level);
 
+	drm_printf(p, "[LOG].length: 0x%lx\n", snapshot->size);
 	remain = snapshot->size;
 	for (i = 0; i < snapshot->num_chunks; i++) {
 		size_t size = min(GUC_LOG_CHUNK_SIZE, remain);
-		const char *prefix = i ? NULL : "Log data";
+		const char *prefix = i ? NULL : "[LOG].data";
 		char suffix = i == snapshot->num_chunks - 1 ? '\n' : 0;
 
 		xe_print_blob_ascii85(p, prefix, suffix, snapshot->copy[i], 0, size);

From 42367eca7604e16e170bd6bd94ef61ffdd335f4a Mon Sep 17 00:00:00 2001
From: Charlie Jenkins <charlie@rivosinc.com>
Date: Thu, 13 Feb 2025 13:06:22 -0800
Subject: [PATCH 0342/1173] tools: Remove redundant quiet setup

Q is exported from Makefile.include so it is not necessary to manually
set it.

Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Quentin Monnet <qmo@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Benjamin Tissoires <bentiss@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Hao Luo <haoluo@google.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Kosina <jikos@kernel.org>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: Josh Poimboeuf <jpoimboe@kernel.org>
Cc: KP Singh <kpsingh@kernel.org>
Cc: Lukasz Luba <lukasz.luba@arm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Martin KaFai Lau <martin.lau@linux.dev>
Cc: Mykola Lysenko <mykolal@fb.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rafael J. Wysocki <rafael@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Song Liu <song@kernel.org>
Cc: Stanislav Fomichev <sdf@google.com>
Cc: Steven Rostedt (VMware) <rostedt@goodmis.org>
Cc: Yonghong Song <yonghong.song@linux.dev>
Cc: Zhang Rui <rui.zhang@intel.com>
Link: https://lore.kernel.org/r/20250213-quiet_tools-v3-2-07de4482a581@rivosinc.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/arm64/tools/Makefile           |  6 ------
 tools/bpf/Makefile                        |  6 ------
 tools/bpf/bpftool/Documentation/Makefile  |  6 ------
 tools/bpf/bpftool/Makefile                |  6 ------
 tools/bpf/resolve_btfids/Makefile         |  2 --
 tools/bpf/runqslower/Makefile             |  5 +----
 tools/lib/bpf/Makefile                    | 13 -------------
 tools/lib/perf/Makefile                   | 13 -------------
 tools/lib/thermal/Makefile                | 13 -------------
 tools/objtool/Makefile                    |  6 ------
 tools/testing/selftests/bpf/Makefile.docs |  6 ------
 tools/testing/selftests/hid/Makefile      |  2 --
 tools/thermal/lib/Makefile                | 13 -------------
 tools/tracing/latency/Makefile            |  6 ------
 tools/tracing/rtla/Makefile               |  6 ------
 tools/verification/rv/Makefile            |  6 ------
 16 files changed, 1 insertion(+), 114 deletions(-)

diff --git a/tools/arch/arm64/tools/Makefile b/tools/arch/arm64/tools/Makefile
index 7b42feedf6471..de4f1b66ef014 100644
--- a/tools/arch/arm64/tools/Makefile
+++ b/tools/arch/arm64/tools/Makefile
@@ -13,12 +13,6 @@ AWK	?= awk
 MKDIR	?= mkdir
 RM	?= rm
 
-ifeq ($(V),1)
-Q =
-else
-Q = @
-endif
-
 arm64_tools_dir = $(top_srcdir)/arch/arm64/tools
 arm64_sysreg_tbl = $(arm64_tools_dir)/sysreg
 arm64_gen_sysreg = $(arm64_tools_dir)/gen-sysreg.awk
diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile
index 243b79f2b451e..062bbd6cd048e 100644
--- a/tools/bpf/Makefile
+++ b/tools/bpf/Makefile
@@ -27,12 +27,6 @@ srctree := $(patsubst %/,%,$(dir $(CURDIR)))
 srctree := $(patsubst %/,%,$(dir $(srctree)))
 endif
 
-ifeq ($(V),1)
-  Q =
-else
-  Q = @
-endif
-
 FEATURE_USER = .bpf
 FEATURE_TESTS = libbfd disassembler-four-args disassembler-init-styled
 FEATURE_DISPLAY = libbfd
diff --git a/tools/bpf/bpftool/Documentation/Makefile b/tools/bpf/bpftool/Documentation/Makefile
index 4315652678b9f..bf843f328812e 100644
--- a/tools/bpf/bpftool/Documentation/Makefile
+++ b/tools/bpf/bpftool/Documentation/Makefile
@@ -5,12 +5,6 @@ INSTALL ?= install
 RM ?= rm -f
 RMDIR ?= rmdir --ignore-fail-on-non-empty
 
-ifeq ($(V),1)
-  Q =
-else
-  Q = @
-endif
-
 prefix ?= /usr/local
 mandir ?= $(prefix)/man
 man8dir = $(mandir)/man8
diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index dd9f3ec842017..6ea4823b770cb 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -7,12 +7,6 @@ srctree := $(patsubst %/,%,$(dir $(srctree)))
 srctree := $(patsubst %/,%,$(dir $(srctree)))
 endif
 
-ifeq ($(V),1)
-  Q =
-else
-  Q = @
-endif
-
 BPF_DIR = $(srctree)/tools/lib/bpf
 
 ifneq ($(OUTPUT),)
diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile
index 4b8079f294f65..afbddea3a39c6 100644
--- a/tools/bpf/resolve_btfids/Makefile
+++ b/tools/bpf/resolve_btfids/Makefile
@@ -5,10 +5,8 @@ include ../../scripts/Makefile.arch
 srctree := $(abspath $(CURDIR)/../../../)
 
 ifeq ($(V),1)
-  Q =
   msg =
 else
-  Q = @
   ifeq ($(silent),1)
     msg =
   else
diff --git a/tools/bpf/runqslower/Makefile b/tools/bpf/runqslower/Makefile
index c4f1f1735af65..e49203ebd48c1 100644
--- a/tools/bpf/runqslower/Makefile
+++ b/tools/bpf/runqslower/Makefile
@@ -26,10 +26,7 @@ VMLINUX_BTF_PATHS := $(if $(O),$(O)/vmlinux)		\
 VMLINUX_BTF_PATH := $(or $(VMLINUX_BTF),$(firstword			       \
 					  $(wildcard $(VMLINUX_BTF_PATHS))))
 
-ifeq ($(V),1)
-Q =
-else
-Q = @
+ifneq ($(V),1)
 MAKEFLAGS += --no-print-directory
 submake_extras := feature_display=0
 endif
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 857a5f7b413d6..168140f8e6461 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -53,13 +53,6 @@ include $(srctree)/tools/scripts/Makefile.include
 
 # copy a bit from Linux kbuild
 
-ifeq ("$(origin V)", "command line")
-  VERBOSE = $(V)
-endif
-ifndef VERBOSE
-  VERBOSE = 0
-endif
-
 INCLUDES = -I$(or $(OUTPUT),.) \
 	   -I$(srctree)/tools/include -I$(srctree)/tools/include/uapi \
 	   -I$(srctree)/tools/arch/$(SRCARCH)/include
@@ -96,12 +89,6 @@ override CFLAGS += $(CLANG_CROSS_FLAGS)
 # flags specific for shared library
 SHLIB_FLAGS := -DSHARED -fPIC
 
-ifeq ($(VERBOSE),1)
-  Q =
-else
-  Q = @
-endif
-
 # Disable command line variables (CFLAGS) override from top
 # level Makefile (perf), otherwise build Makefile will get
 # the same command line setup.
diff --git a/tools/lib/perf/Makefile b/tools/lib/perf/Makefile
index 3a9b2140aa048..e9a7ac2c062e2 100644
--- a/tools/lib/perf/Makefile
+++ b/tools/lib/perf/Makefile
@@ -39,19 +39,6 @@ libdir = $(prefix)/$(libdir_relative)
 libdir_SQ = $(subst ','\'',$(libdir))
 libdir_relative_SQ = $(subst ','\'',$(libdir_relative))
 
-ifeq ("$(origin V)", "command line")
-  VERBOSE = $(V)
-endif
-ifndef VERBOSE
-  VERBOSE = 0
-endif
-
-ifeq ($(VERBOSE),1)
-  Q =
-else
-  Q = @
-endif
-
 TEST_ARGS := $(if $(V),-v)
 
 # Set compile option CFLAGS
diff --git a/tools/lib/thermal/Makefile b/tools/lib/thermal/Makefile
index 8890fd57b110c..a1f5e388644d3 100644
--- a/tools/lib/thermal/Makefile
+++ b/tools/lib/thermal/Makefile
@@ -39,19 +39,6 @@ libdir = $(prefix)/$(libdir_relative)
 libdir_SQ = $(subst ','\'',$(libdir))
 libdir_relative_SQ = $(subst ','\'',$(libdir_relative))
 
-ifeq ("$(origin V)", "command line")
-  VERBOSE = $(V)
-endif
-ifndef VERBOSE
-  VERBOSE = 0
-endif
-
-ifeq ($(VERBOSE),1)
-  Q =
-else
-  Q = @
-endif
-
 # Set compile option CFLAGS
 ifdef EXTRA_CFLAGS
   CFLAGS := $(EXTRA_CFLAGS)
diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index f56e277275341..7a65948892e56 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -46,12 +46,6 @@ HOST_OVERRIDES := CC="$(HOSTCC)" LD="$(HOSTLD)" AR="$(HOSTAR)"
 AWK = awk
 MKDIR = mkdir
 
-ifeq ($(V),1)
-  Q =
-else
-  Q = @
-endif
-
 BUILD_ORC := n
 
 ifeq ($(SRCARCH),x86)
diff --git a/tools/testing/selftests/bpf/Makefile.docs b/tools/testing/selftests/bpf/Makefile.docs
index eb6a4fea8c794..f7f9e7088bb38 100644
--- a/tools/testing/selftests/bpf/Makefile.docs
+++ b/tools/testing/selftests/bpf/Makefile.docs
@@ -7,12 +7,6 @@ INSTALL ?= install
 RM ?= rm -f
 RMDIR ?= rmdir --ignore-fail-on-non-empty
 
-ifeq ($(V),1)
-  Q =
-else
-  Q = @
-endif
-
 prefix ?= /usr/local
 mandir ?= $(prefix)/man
 man2dir = $(mandir)/man2
diff --git a/tools/testing/selftests/hid/Makefile b/tools/testing/selftests/hid/Makefile
index 0336353bd15f0..2839d2612ce3a 100644
--- a/tools/testing/selftests/hid/Makefile
+++ b/tools/testing/selftests/hid/Makefile
@@ -43,10 +43,8 @@ TEST_GEN_PROGS = hid_bpf hidraw
 # $3 - target (assumed to be file); only file name will be emitted;
 # $4 - optional extra arg, emitted as-is, if provided.
 ifeq ($(V),1)
-Q =
 msg =
 else
-Q = @
 msg = @printf '  %-8s%s %s%s\n' "$(1)" "$(if $(2), [$(2)])" "$(notdir $(3))" "$(if $(4), $(4))";
 MAKEFLAGS += --no-print-directory
 submake_extras := feature_display=0
diff --git a/tools/thermal/lib/Makefile b/tools/thermal/lib/Makefile
index f2552f73a64c7..056d212f25cf5 100644
--- a/tools/thermal/lib/Makefile
+++ b/tools/thermal/lib/Makefile
@@ -39,19 +39,6 @@ libdir = $(prefix)/$(libdir_relative)
 libdir_SQ = $(subst ','\'',$(libdir))
 libdir_relative_SQ = $(subst ','\'',$(libdir_relative))
 
-ifeq ("$(origin V)", "command line")
-  VERBOSE = $(V)
-endif
-ifndef VERBOSE
-  VERBOSE = 0
-endif
-
-ifeq ($(VERBOSE),1)
-  Q =
-else
-  Q = @
-endif
-
 # Set compile option CFLAGS
 ifdef EXTRA_CFLAGS
   CFLAGS := $(EXTRA_CFLAGS)
diff --git a/tools/tracing/latency/Makefile b/tools/tracing/latency/Makefile
index 6518b03e05c71..257a56b1899f2 100644
--- a/tools/tracing/latency/Makefile
+++ b/tools/tracing/latency/Makefile
@@ -37,12 +37,6 @@ FEATURE_TESTS	+= libtracefs
 FEATURE_DISPLAY	:= libtraceevent
 FEATURE_DISPLAY	+= libtracefs
 
-ifeq ($(V),1)
-  Q 		=
-else
-  Q 		= @
-endif
-
 all: $(LATENCY-COLLECTOR)
 
 include $(srctree)/tools/build/Makefile.include
diff --git a/tools/tracing/rtla/Makefile b/tools/tracing/rtla/Makefile
index a6a7dee16622d..a1727c414e44b 100644
--- a/tools/tracing/rtla/Makefile
+++ b/tools/tracing/rtla/Makefile
@@ -37,12 +37,6 @@ FEATURE_DISPLAY	:= libtraceevent
 FEATURE_DISPLAY	+= libtracefs
 FEATURE_DISPLAY	+= libcpupower
 
-ifeq ($(V),1)
-  Q		=
-else
-  Q		= @
-endif
-
 all: $(RTLA)
 
 include $(srctree)/tools/build/Makefile.include
diff --git a/tools/verification/rv/Makefile b/tools/verification/rv/Makefile
index 411d62b3d8eb9..5b898360ba481 100644
--- a/tools/verification/rv/Makefile
+++ b/tools/verification/rv/Makefile
@@ -35,12 +35,6 @@ FEATURE_TESTS	+= libtracefs
 FEATURE_DISPLAY	:= libtraceevent
 FEATURE_DISPLAY	+= libtracefs
 
-ifeq ($(V),1)
-  Q		=
-else
-  Q		= @
-endif
-
 all: $(RV)
 
 include $(srctree)/tools/build/Makefile.include

From a3f172359e22b2c11b750d23560481a55bf86af1 Mon Sep 17 00:00:00 2001
From: Hector Martin <marcan@marcan.st>
Date: Tue, 18 Feb 2025 18:35:35 +1000
Subject: [PATCH 0343/1173] ASoC: tas2764: Fix power control mask

Reviewed-by: Neal Gompa <neal@gompa.dev>
Signed-off-by: Hector Martin <marcan@marcan.st>
Signed-off-by: James Calligeros <jcalligeros99@gmail.com>
Link: https://patch.msgid.link/20250218-apple-codec-changes-v2-1-932760fd7e07@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/tas2764.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/codecs/tas2764.h b/sound/soc/codecs/tas2764.h
index 168af772a898f..d13ecae9c9c2f 100644
--- a/sound/soc/codecs/tas2764.h
+++ b/sound/soc/codecs/tas2764.h
@@ -25,7 +25,7 @@
 
 /* Power Control */
 #define TAS2764_PWR_CTRL		TAS2764_REG(0X0, 0x02)
-#define TAS2764_PWR_CTRL_MASK		GENMASK(1, 0)
+#define TAS2764_PWR_CTRL_MASK		GENMASK(2, 0)
 #define TAS2764_PWR_CTRL_ACTIVE		0x0
 #define TAS2764_PWR_CTRL_MUTE		BIT(0)
 #define TAS2764_PWR_CTRL_SHUTDOWN	BIT(1)

From f5468beeab1b1adfc63c2717b1f29ef3f49a5fab Mon Sep 17 00:00:00 2001
From: Hector Martin <marcan@marcan.st>
Date: Tue, 18 Feb 2025 18:36:02 +1000
Subject: [PATCH 0344/1173] ASoC: tas2764: Set the SDOUT polarity correctly

TX launch polarity needs to be the opposite of RX capture polarity, to
generate the right bit slot alignment.

Reviewed-by: Neal Gompa <neal@gompa.dev>
Signed-off-by: Hector Martin <marcan@marcan.st>
Signed-off-by: James Calligeros <jcalligeros99@gmail.com>
Link: https://patch.msgid.link/20250218-apple-codec-changes-v2-28-932760fd7e07@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/tas2764.c | 10 +++++++++-
 sound/soc/codecs/tas2764.h |  6 ++++++
 2 files changed, 15 insertions(+), 1 deletion(-)

diff --git a/sound/soc/codecs/tas2764.c b/sound/soc/codecs/tas2764.c
index d482cd194c08c..58315eab492a1 100644
--- a/sound/soc/codecs/tas2764.c
+++ b/sound/soc/codecs/tas2764.c
@@ -365,7 +365,7 @@ static int tas2764_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 {
 	struct snd_soc_component *component = dai->component;
 	struct tas2764_priv *tas2764 = snd_soc_component_get_drvdata(component);
-	u8 tdm_rx_start_slot = 0, asi_cfg_0 = 0, asi_cfg_1 = 0;
+	u8 tdm_rx_start_slot = 0, asi_cfg_0 = 0, asi_cfg_1 = 0, asi_cfg_4 = 0;
 	int ret;
 
 	switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
@@ -374,12 +374,14 @@ static int tas2764_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 		fallthrough;
 	case SND_SOC_DAIFMT_NB_NF:
 		asi_cfg_1 = TAS2764_TDM_CFG1_RX_RISING;
+		asi_cfg_4 = TAS2764_TDM_CFG4_TX_FALLING;
 		break;
 	case SND_SOC_DAIFMT_IB_IF:
 		asi_cfg_0 ^= TAS2764_TDM_CFG0_FRAME_START;
 		fallthrough;
 	case SND_SOC_DAIFMT_IB_NF:
 		asi_cfg_1 = TAS2764_TDM_CFG1_RX_FALLING;
+		asi_cfg_4 = TAS2764_TDM_CFG4_TX_RISING;
 		break;
 	}
 
@@ -389,6 +391,12 @@ static int tas2764_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 	if (ret < 0)
 		return ret;
 
+	ret = snd_soc_component_update_bits(component, TAS2764_TDM_CFG4,
+					    TAS2764_TDM_CFG4_TX_MASK,
+					    asi_cfg_4);
+	if (ret < 0)
+		return ret;
+
 	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
 	case SND_SOC_DAIFMT_I2S:
 		asi_cfg_0 ^= TAS2764_TDM_CFG0_FRAME_START;
diff --git a/sound/soc/codecs/tas2764.h b/sound/soc/codecs/tas2764.h
index d13ecae9c9c2f..9490f2686e389 100644
--- a/sound/soc/codecs/tas2764.h
+++ b/sound/soc/codecs/tas2764.h
@@ -79,6 +79,12 @@
 #define TAS2764_TDM_CFG3_RXS_SHIFT	0x4
 #define TAS2764_TDM_CFG3_MASK		GENMASK(3, 0)
 
+/* TDM Configuration Reg4 */
+#define TAS2764_TDM_CFG4		TAS2764_REG(0X0, 0x0d)
+#define TAS2764_TDM_CFG4_TX_MASK	BIT(0)
+#define TAS2764_TDM_CFG4_TX_RISING	0x0
+#define TAS2764_TDM_CFG4_TX_FALLING	BIT(0)
+
 /* TDM Configuration Reg5 */
 #define TAS2764_TDM_CFG5		TAS2764_REG(0X0, 0x0e)
 #define TAS2764_TDM_CFG5_VSNS_MASK	BIT(6)

From 0c28e4d1e10d2aae608094620bb386e6fd73d55e Mon Sep 17 00:00:00 2001
From: Stuart Hayhurst <stuart.a.hayhurst@gmail.com>
Date: Thu, 13 Feb 2025 13:38:49 +0000
Subject: [PATCH 0345/1173] HID: corsair-void: Update power supply values with
 a unified work handler

corsair_void_process_receiver can be called from an interrupt context,
locking battery_mutex in it was causing a kernel panic.
Fix it by moving the critical section into its own work, sharing this
work with battery_add_work and battery_remove_work to remove the need
for any locking

Closes: https://bugzilla.suse.com/show_bug.cgi?id=1236843
Fixes: 6ea2a6fd3872 ("HID: corsair-void: Add Corsair Void headset family driver")
Cc: stable@vger.kernel.org
Signed-off-by: Stuart Hayhurst <stuart.a.hayhurst@gmail.com>
Reviewed-by: Jiri Slaby <jirislaby@kernel.org>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-corsair-void.c | 83 ++++++++++++++++++----------------
 1 file changed, 43 insertions(+), 40 deletions(-)

diff --git a/drivers/hid/hid-corsair-void.c b/drivers/hid/hid-corsair-void.c
index 56e858066c3c3..afbd67aa97192 100644
--- a/drivers/hid/hid-corsair-void.c
+++ b/drivers/hid/hid-corsair-void.c
@@ -71,11 +71,9 @@
 
 #include <linux/bitfield.h>
 #include <linux/bitops.h>
-#include <linux/cleanup.h>
 #include <linux/device.h>
 #include <linux/hid.h>
 #include <linux/module.h>
-#include <linux/mutex.h>
 #include <linux/power_supply.h>
 #include <linux/usb.h>
 #include <linux/workqueue.h>
@@ -120,6 +118,12 @@ enum {
 	CORSAIR_VOID_BATTERY_CHARGING	= 5,
 };
 
+enum {
+	CORSAIR_VOID_ADD_BATTERY	= 0,
+	CORSAIR_VOID_REMOVE_BATTERY	= 1,
+	CORSAIR_VOID_UPDATE_BATTERY	= 2,
+};
+
 static enum power_supply_property corsair_void_battery_props[] = {
 	POWER_SUPPLY_PROP_STATUS,
 	POWER_SUPPLY_PROP_PRESENT,
@@ -155,12 +159,12 @@ struct corsair_void_drvdata {
 
 	struct power_supply *battery;
 	struct power_supply_desc battery_desc;
-	struct mutex battery_mutex;
 
 	struct delayed_work delayed_status_work;
 	struct delayed_work delayed_firmware_work;
-	struct work_struct battery_remove_work;
-	struct work_struct battery_add_work;
+
+	unsigned long battery_work_flags;
+	struct work_struct battery_work;
 };
 
 /*
@@ -260,11 +264,9 @@ static void corsair_void_process_receiver(struct corsair_void_drvdata *drvdata,
 
 	/* Inform power supply if battery values changed */
 	if (memcmp(&orig_battery_data, battery_data, sizeof(*battery_data))) {
-		scoped_guard(mutex, &drvdata->battery_mutex) {
-			if (drvdata->battery) {
-				power_supply_changed(drvdata->battery);
-			}
-		}
+		set_bit(CORSAIR_VOID_UPDATE_BATTERY,
+			&drvdata->battery_work_flags);
+		schedule_work(&drvdata->battery_work);
 	}
 }
 
@@ -536,29 +538,11 @@ static void corsair_void_firmware_work_handler(struct work_struct *work)
 
 }
 
-static void corsair_void_battery_remove_work_handler(struct work_struct *work)
-{
-	struct corsair_void_drvdata *drvdata;
-
-	drvdata = container_of(work, struct corsair_void_drvdata,
-			       battery_remove_work);
-	scoped_guard(mutex, &drvdata->battery_mutex) {
-		if (drvdata->battery) {
-			power_supply_unregister(drvdata->battery);
-			drvdata->battery = NULL;
-		}
-	}
-}
-
-static void corsair_void_battery_add_work_handler(struct work_struct *work)
+static void corsair_void_add_battery(struct corsair_void_drvdata *drvdata)
 {
-	struct corsair_void_drvdata *drvdata;
 	struct power_supply_config psy_cfg = {};
 	struct power_supply *new_supply;
 
-	drvdata = container_of(work, struct corsair_void_drvdata,
-			       battery_add_work);
-	guard(mutex)(&drvdata->battery_mutex);
 	if (drvdata->battery)
 		return;
 
@@ -583,16 +567,42 @@ static void corsair_void_battery_add_work_handler(struct work_struct *work)
 	drvdata->battery = new_supply;
 }
 
+static void corsair_void_battery_work_handler(struct work_struct *work)
+{
+	struct corsair_void_drvdata *drvdata = container_of(work,
+		struct corsair_void_drvdata, battery_work);
+
+	bool add_battery = test_and_clear_bit(CORSAIR_VOID_ADD_BATTERY,
+					      &drvdata->battery_work_flags);
+	bool remove_battery = test_and_clear_bit(CORSAIR_VOID_REMOVE_BATTERY,
+						 &drvdata->battery_work_flags);
+	bool update_battery = test_and_clear_bit(CORSAIR_VOID_UPDATE_BATTERY,
+						 &drvdata->battery_work_flags);
+
+	if (add_battery && !remove_battery) {
+		corsair_void_add_battery(drvdata);
+	} else if (remove_battery && !add_battery && drvdata->battery) {
+		power_supply_unregister(drvdata->battery);
+		drvdata->battery = NULL;
+	}
+
+	if (update_battery && drvdata->battery)
+		power_supply_changed(drvdata->battery);
+
+}
+
 static void corsair_void_headset_connected(struct corsair_void_drvdata *drvdata)
 {
-	schedule_work(&drvdata->battery_add_work);
+	set_bit(CORSAIR_VOID_ADD_BATTERY, &drvdata->battery_work_flags);
+	schedule_work(&drvdata->battery_work);
 	schedule_delayed_work(&drvdata->delayed_firmware_work,
 			      msecs_to_jiffies(100));
 }
 
 static void corsair_void_headset_disconnected(struct corsair_void_drvdata *drvdata)
 {
-	schedule_work(&drvdata->battery_remove_work);
+	set_bit(CORSAIR_VOID_REMOVE_BATTERY, &drvdata->battery_work_flags);
+	schedule_work(&drvdata->battery_work);
 
 	corsair_void_set_unknown_wireless_data(drvdata);
 	corsair_void_set_unknown_batt(drvdata);
@@ -678,13 +688,7 @@ static int corsair_void_probe(struct hid_device *hid_dev,
 	drvdata->battery_desc.get_property = corsair_void_battery_get_property;
 
 	drvdata->battery = NULL;
-	INIT_WORK(&drvdata->battery_remove_work,
-		  corsair_void_battery_remove_work_handler);
-	INIT_WORK(&drvdata->battery_add_work,
-		  corsair_void_battery_add_work_handler);
-	ret = devm_mutex_init(drvdata->dev, &drvdata->battery_mutex);
-	if (ret)
-		return ret;
+	INIT_WORK(&drvdata->battery_work, corsair_void_battery_work_handler);
 
 	ret = sysfs_create_group(&hid_dev->dev.kobj, &corsair_void_attr_group);
 	if (ret)
@@ -721,8 +725,7 @@ static void corsair_void_remove(struct hid_device *hid_dev)
 	struct corsair_void_drvdata *drvdata = hid_get_drvdata(hid_dev);
 
 	hid_hw_stop(hid_dev);
-	cancel_work_sync(&drvdata->battery_remove_work);
-	cancel_work_sync(&drvdata->battery_add_work);
+	cancel_work_sync(&drvdata->battery_work);
 	if (drvdata->battery)
 		power_supply_unregister(drvdata->battery);
 

From 213e24250feed3bcf58d7594298df2d7e78a88ab Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Tue, 28 Jan 2025 07:42:42 -0800
Subject: [PATCH 0346/1173] drm/xe/guc: Fix size_t print format
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use %zx format to print size_t to remove the following warning when
building for i386:

>> drivers/gpu/drm/xe/xe_guc_ct.c:1727:43: warning: format specifies type 'unsigned long' but the argument has type 'size_t' (aka 'unsigned int') [-Wformat]
    1727 |                         drm_printf(p, "[CTB].length: 0x%lx\n", snapshot->ctb_size);
         |                                                        ~~~     ^~~~~~~~~~~~~~~~~~
         |                                                        %zx

Cc: José Roberto de Souza <jose.souza@intel.com>
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202501281627.H6nj184e-lkp@intel.com/
Fixes: 643f209ba3fd ("drm/xe: Make GUC binaries dump consistent with other binaries in devcoredump")
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250128154242.3371687-1-lucas.demarchi@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit 7748289df510638ba61fed86b59ce7d2fb4a194c)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_guc_ct.c  | 2 +-
 drivers/gpu/drm/xe/xe_guc_log.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index 497036675a38c..72ad576fc18eb 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -1724,7 +1724,7 @@ void xe_guc_ct_snapshot_print(struct xe_guc_ct_snapshot *snapshot,
 			   snapshot->g2h_outstanding);
 
 		if (snapshot->ctb) {
-			drm_printf(p, "[CTB].length: 0x%lx\n", snapshot->ctb_size);
+			drm_printf(p, "[CTB].length: 0x%zx\n", snapshot->ctb_size);
 			xe_print_blob_ascii85(p, "[CTB].data", '\n',
 					      snapshot->ctb, 0, snapshot->ctb_size);
 		}
diff --git a/drivers/gpu/drm/xe/xe_guc_log.c b/drivers/gpu/drm/xe/xe_guc_log.c
index 2457572ed86ad..0ca3056d8bd3f 100644
--- a/drivers/gpu/drm/xe/xe_guc_log.c
+++ b/drivers/gpu/drm/xe/xe_guc_log.c
@@ -208,7 +208,7 @@ void xe_guc_log_snapshot_print(struct xe_guc_log_snapshot *snapshot, struct drm_
 	drm_printf(p, "GuC timestamp: 0x%08llX [%llu]\n", snapshot->stamp, snapshot->stamp);
 	drm_printf(p, "Log level: %u\n", snapshot->level);
 
-	drm_printf(p, "[LOG].length: 0x%lx\n", snapshot->size);
+	drm_printf(p, "[LOG].length: 0x%zx\n", snapshot->size);
 	remain = snapshot->size;
 	for (i = 0; i < snapshot->num_chunks; i++) {
 		size_t size = min(GUC_LOG_CHUNK_SIZE, remain);

From 1fc61eeefe10d9996d2b875214d89f0909d03417 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Tue, 18 Feb 2025 16:47:40 -0700
Subject: [PATCH 0347/1173] io_uring: fix spelling error in uapi io_uring.h

This is obviously not that important, but when changes are synced back
from the kernel to liburing, the codespell CI ends up erroring because
of this misspelling. Let's just correct it and avoid this biting us
again on an import.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/uapi/linux/io_uring.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index e11c826385277..050fa8eb2e8f8 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -380,7 +380,7 @@ enum io_uring_op {
  *				result 	will be the number of buffers send, with
  *				the starting buffer ID in cqe->flags as per
  *				usual for provided buffer usage. The buffers
- *				will be	contigious from the starting buffer ID.
+ *				will be	contiguous from the starting buffer ID.
  */
 #define IORING_RECVSEND_POLL_FIRST	(1U << 0)
 #define IORING_RECV_MULTISHOT		(1U << 1)

From 4fa382be430421e1445f9c95c4dc9b7e0949ae8a Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Fri, 14 Feb 2025 14:43:44 -0800
Subject: [PATCH 0348/1173] scsi: ufs: core: Fix ufshcd_is_ufs_dev_busy() and
 ufshcd_eh_timed_out()

ufshcd_is_ufs_dev_busy(), ufshcd_print_host_state() and
ufshcd_eh_timed_out() are used in both modes (legacy mode and MCQ mode).
hba->outstanding_reqs only represents the outstanding requests in legacy
mode. Hence, change hba->outstanding_reqs into scsi_host_busy(hba->host) in
these functions.

Fixes: eacb139b77ff ("scsi: ufs: core: mcq: Enable multi-circular queue")
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20250214224352.3025151-1-bvanassche@acm.org
Reviewed-by: Peter Wang <peter.wang@mediatek.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 1893a7ad95316..f9303e66bb798 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -266,7 +266,7 @@ static bool ufshcd_has_pending_tasks(struct ufs_hba *hba)
 
 static bool ufshcd_is_ufs_dev_busy(struct ufs_hba *hba)
 {
-	return hba->outstanding_reqs || ufshcd_has_pending_tasks(hba);
+	return scsi_host_busy(hba->host) || ufshcd_has_pending_tasks(hba);
 }
 
 static const struct ufs_dev_quirk ufs_fixups[] = {
@@ -628,8 +628,8 @@ static void ufshcd_print_host_state(struct ufs_hba *hba)
 	const struct scsi_device *sdev_ufs = hba->ufs_device_wlun;
 
 	dev_err(hba->dev, "UFS Host state=%d\n", hba->ufshcd_state);
-	dev_err(hba->dev, "outstanding reqs=0x%lx tasks=0x%lx\n",
-		hba->outstanding_reqs, hba->outstanding_tasks);
+	dev_err(hba->dev, "%d outstanding reqs, tasks=0x%lx\n",
+		scsi_host_busy(hba->host), hba->outstanding_tasks);
 	dev_err(hba->dev, "saved_err=0x%x, saved_uic_err=0x%x\n",
 		hba->saved_err, hba->saved_uic_err);
 	dev_err(hba->dev, "Device power mode=%d, UIC link state=%d\n",
@@ -8882,7 +8882,7 @@ static enum scsi_timeout_action ufshcd_eh_timed_out(struct scsi_cmnd *scmd)
 	dev_info(hba->dev, "%s() finished; outstanding_tasks = %#lx.\n",
 		 __func__, hba->outstanding_tasks);
 
-	return hba->outstanding_reqs ? SCSI_EH_RESET_TIMER : SCSI_EH_DONE;
+	return scsi_host_busy(hba->host) ? SCSI_EH_RESET_TIMER : SCSI_EH_DONE;
 }
 
 static const struct attribute_group *ufshcd_driver_groups[] = {

From eff2eb592efd73f00590d578c3d6021f604df62c Mon Sep 17 00:00:00 2001
From: Andrew Donnellan <ajd@linux.ibm.com>
Date: Wed, 19 Feb 2025 17:48:07 +1100
Subject: [PATCH 0349/1173] cxl: Fix cross-reference in documentation and add
 deprecation warning

commit 5731d41af924 ("cxl: Deprecate driver") labelled the cxl driver as
deprecated and moved the ABI documentation to the obsolete/ subdirectory,
but didn't update cxl.rst, causing a warning once ff7ff6eb4f809 ("docs:
media: Allow creating cross-references for RC ABI") was merged.

Fix the cross-reference, and also add a deprecation warning.

Fixes: 5731d41af924 ("cxl: Deprecate driver")
Reported-by: Bagas Sanjaya <bagasdotme@gmail.com>
Signed-off-by: Andrew Donnellan <ajd@linux.ibm.com>
Acked-by: Bagas Sanjaya <bagasdotme@gmail.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20250219064807.175107-1-ajd@linux.ibm.com
---
 Documentation/arch/powerpc/cxl.rst | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/Documentation/arch/powerpc/cxl.rst b/Documentation/arch/powerpc/cxl.rst
index d2d77057610e4..778adda740d24 100644
--- a/Documentation/arch/powerpc/cxl.rst
+++ b/Documentation/arch/powerpc/cxl.rst
@@ -18,6 +18,7 @@ Introduction
     both access system memory directly and with the same effective
     addresses.
 
+    **This driver is deprecated and will be removed in a future release.**
 
 Hardware overview
 =================
@@ -453,7 +454,7 @@ Sysfs Class
 
     A cxl sysfs class is added under /sys/class/cxl to facilitate
     enumeration and tuning of the accelerators. Its layout is
-    described in Documentation/ABI/testing/sysfs-class-cxl
+    described in Documentation/ABI/obsolete/sysfs-class-cxl
 
 
 Udev rules

From 8821f36333e27c8355d4a730649923f938e1e4b9 Mon Sep 17 00:00:00 2001
From: Friedrich Vock <friedrich.vock@gmx.de>
Date: Mon, 27 Jan 2025 16:27:52 +0100
Subject: [PATCH 0350/1173] cgroup/dmem: Don't open-code
 css_for_each_descendant_pre

The current implementation has a bug: If the current css doesn't
contain any pool that is a descendant of the "pool" (i.e. when
found_descendant == false), then "pool" will point to some unrelated
pool. If the current css has a child, we'll overwrite parent_pool with
this unrelated pool on the next iteration.

Since we can just check whether a pool refers to the same region to
determine whether or not it's related, all the additional pool tracking
is unnecessary, so just switch to using css_for_each_descendant_pre for
traversal.

Fixes: b168ed458dde ("kernel/cgroup: Add "dmem" memory accounting cgroup")
Signed-off-by: Friedrich Vock <friedrich.vock@gmx.de>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250127152754.21325-1-friedrich.vock@gmx.de
Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
---
 kernel/cgroup/dmem.c | 50 ++++++++++----------------------------------
 1 file changed, 11 insertions(+), 39 deletions(-)

diff --git a/kernel/cgroup/dmem.c b/kernel/cgroup/dmem.c
index fbe34299673d3..10b63433f0573 100644
--- a/kernel/cgroup/dmem.c
+++ b/kernel/cgroup/dmem.c
@@ -220,60 +220,32 @@ dmem_cgroup_calculate_protection(struct dmem_cgroup_pool_state *limit_pool,
 				 struct dmem_cgroup_pool_state *test_pool)
 {
 	struct page_counter *climit;
-	struct cgroup_subsys_state *css, *next_css;
+	struct cgroup_subsys_state *css;
 	struct dmemcg_state *dmemcg_iter;
-	struct dmem_cgroup_pool_state *pool, *parent_pool;
-	bool found_descendant;
+	struct dmem_cgroup_pool_state *pool, *found_pool;
 
 	climit = &limit_pool->cnt;
 
 	rcu_read_lock();
-	parent_pool = pool = limit_pool;
-	css = &limit_pool->cs->css;
 
-	/*
-	 * This logic is roughly equivalent to css_foreach_descendant_pre,
-	 * except we also track the parent pool to find out which pool we need
-	 * to calculate protection values for.
-	 *
-	 * We can stop the traversal once we find test_pool among the
-	 * descendants since we don't really care about any others.
-	 */
-	while (pool != test_pool) {
-		next_css = css_next_child(NULL, css);
-		if (next_css) {
-			parent_pool = pool;
-		} else {
-			while (css != &limit_pool->cs->css) {
-				next_css = css_next_child(css, css->parent);
-				if (next_css)
-					break;
-				css = css->parent;
-				parent_pool = pool_parent(parent_pool);
-			}
-			/*
-			 * We can only hit this when test_pool is not a
-			 * descendant of limit_pool.
-			 */
-			if (WARN_ON_ONCE(css == &limit_pool->cs->css))
-				break;
-		}
-		css = next_css;
-
-		found_descendant = false;
+	css_for_each_descendant_pre(css, &limit_pool->cs->css) {
 		dmemcg_iter = container_of(css, struct dmemcg_state, css);
+		found_pool = NULL;
 
 		list_for_each_entry_rcu(pool, &dmemcg_iter->pools, css_node) {
-			if (pool_parent(pool) == parent_pool) {
-				found_descendant = true;
+			if (pool->region == limit_pool->region) {
+				found_pool = pool;
 				break;
 			}
 		}
-		if (!found_descendant)
+		if (!found_pool)
 			continue;
 
 		page_counter_calculate_protection(
-			climit, &pool->cnt, true);
+			climit, &found_pool->cnt, true);
+
+		if (found_pool == test_pool)
+			break;
 	}
 	rcu_read_unlock();
 }

From 44afc10d4678d5a3a4ab8c25750be00f037298cf Mon Sep 17 00:00:00 2001
From: Ryan McClelland <rymcclel@gmail.com>
Date: Thu, 16 Jan 2025 22:49:24 -0800
Subject: [PATCH 0351/1173] HID: nintendo: fix gencon button events map

This fixes the button event map to match the 3-button recommendation
as well as the redundant 'z' in the button map events for the Sega
MD/Gen 6 Button.

Signed-off-by: Ryan McClelland <rymcclel@gmail.com>
Reviewed-by: Daniel J. Ogorchock <djogorchock@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-nintendo.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/hid/hid-nintendo.c b/drivers/hid/hid-nintendo.c
index 11ac246176ae1..839d5bcd72b1e 100644
--- a/drivers/hid/hid-nintendo.c
+++ b/drivers/hid/hid-nintendo.c
@@ -457,13 +457,13 @@ static const struct joycon_ctlr_button_mapping snescon_button_mappings[] = {
 };
 
 static const struct joycon_ctlr_button_mapping gencon_button_mappings[] = {
-	{ BTN_A,	JC_BTN_A,	},
-	{ BTN_B,	JC_BTN_B,	},
-	{ BTN_C,	JC_BTN_R,	},
-	{ BTN_X,	JC_BTN_X,	}, /* MD/GEN 6B Only */
-	{ BTN_Y,	JC_BTN_Y,	}, /* MD/GEN 6B Only */
-	{ BTN_Z,	JC_BTN_L,	}, /* MD/GEN 6B Only */
-	{ BTN_SELECT,	JC_BTN_ZR,	},
+	{ BTN_WEST,	JC_BTN_A,	}, /* A */
+	{ BTN_SOUTH,	JC_BTN_B,	}, /* B */
+	{ BTN_EAST,	JC_BTN_R,	}, /* C */
+	{ BTN_TL,	JC_BTN_X,	}, /* X MD/GEN 6B Only */
+	{ BTN_NORTH,	JC_BTN_Y,	}, /* Y MD/GEN 6B Only */
+	{ BTN_TR,	JC_BTN_L,	}, /* Z MD/GEN 6B Only */
+	{ BTN_SELECT,	JC_BTN_ZR,	}, /* Mode */
 	{ BTN_START,	JC_BTN_PLUS,	},
 	{ BTN_MODE,	JC_BTN_HOME,	},
 	{ BTN_Z,	JC_BTN_CAP,	},

From 4bd0725c09f377ffaf22b834241f6c050742e4fc Mon Sep 17 00:00:00 2001
From: Yu-Chun Lin <eleanor15x@gmail.com>
Date: Tue, 18 Feb 2025 00:50:13 +0800
Subject: [PATCH 0352/1173] HID: google: fix unused variable warning under
 !CONFIG_ACPI

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

>> drivers/hid/hid-google-hammer.c:261:36: warning: 'cbas_ec_acpi_ids' defined but not used [-Wunused-const-variable=]
     261 | static const struct acpi_device_id cbas_ec_acpi_ids[] = {
         |                                    ^~~~~~~~~~~~~~~~

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

Fixes: eb1aac4c8744f75 ("HID: google: add support tablet mode switch for Whiskers")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202501201141.jctFH5eB-lkp@intel.com/
Signed-off-by: Yu-Chun Lin <eleanor15x@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-google-hammer.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/hid/hid-google-hammer.c b/drivers/hid/hid-google-hammer.c
index 0f292b5d3e26d..eb6fd2dc75d0a 100644
--- a/drivers/hid/hid-google-hammer.c
+++ b/drivers/hid/hid-google-hammer.c
@@ -268,11 +268,13 @@ static void cbas_ec_remove(struct platform_device *pdev)
 	mutex_unlock(&cbas_ec_reglock);
 }
 
+#ifdef CONFIG_ACPI
 static const struct acpi_device_id cbas_ec_acpi_ids[] = {
 	{ "GOOG000B", 0 },
 	{ }
 };
 MODULE_DEVICE_TABLE(acpi, cbas_ec_acpi_ids);
+#endif
 
 #ifdef CONFIG_OF
 static const struct of_device_id cbas_ec_of_match[] = {

From 823987841424289339fdb4ba90e6d2c3792836db Mon Sep 17 00:00:00 2001
From: Zhang Lixu <lixu.zhang@intel.com>
Date: Tue, 18 Feb 2025 14:37:29 +0800
Subject: [PATCH 0353/1173] HID: intel-ish-hid: Fix use-after-free issue in
 hid_ishtp_cl_remove()

During the `rmmod` operation for the `intel_ishtp_hid` driver, a
use-after-free issue can occur in the hid_ishtp_cl_remove() function.
The function hid_ishtp_cl_deinit() is called before ishtp_hid_remove(),
which can lead to accessing freed memory or resources during the
removal process.

Call Trace:
 ? ishtp_cl_send+0x168/0x220 [intel_ishtp]
 ? hid_output_report+0xe3/0x150 [hid]
 hid_ishtp_set_feature+0xb5/0x120 [intel_ishtp_hid]
 ishtp_hid_request+0x7b/0xb0 [intel_ishtp_hid]
 hid_hw_request+0x1f/0x40 [hid]
 sensor_hub_set_feature+0x11f/0x190 [hid_sensor_hub]
 _hid_sensor_power_state+0x147/0x1e0 [hid_sensor_trigger]
 hid_sensor_runtime_resume+0x22/0x30 [hid_sensor_trigger]
 sensor_hub_remove+0xa8/0xe0 [hid_sensor_hub]
 hid_device_remove+0x49/0xb0 [hid]
 hid_destroy_device+0x6f/0x90 [hid]
 ishtp_hid_remove+0x42/0x70 [intel_ishtp_hid]
 hid_ishtp_cl_remove+0x6b/0xb0 [intel_ishtp_hid]
 ishtp_cl_device_remove+0x4a/0x60 [intel_ishtp]
 ...

Additionally, ishtp_hid_remove() is a HID level power off, which should
occur before the ISHTP level disconnect.

This patch resolves the issue by reordering the calls in
hid_ishtp_cl_remove(). The function ishtp_hid_remove() is now
called before hid_ishtp_cl_deinit().

Fixes: f645a90e8ff7 ("HID: intel-ish-hid: ishtp-hid-client: use helper functions for connection")
Signed-off-by: Zhang Lixu <lixu.zhang@intel.com>
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/intel-ish-hid/ishtp-hid-client.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hid/intel-ish-hid/ishtp-hid-client.c b/drivers/hid/intel-ish-hid/ishtp-hid-client.c
index cb04cd1d980bd..6550ad5bfbb53 100644
--- a/drivers/hid/intel-ish-hid/ishtp-hid-client.c
+++ b/drivers/hid/intel-ish-hid/ishtp-hid-client.c
@@ -832,9 +832,9 @@ static void hid_ishtp_cl_remove(struct ishtp_cl_device *cl_device)
 			hid_ishtp_cl);
 
 	dev_dbg(ishtp_device(cl_device), "%s\n", __func__);
-	hid_ishtp_cl_deinit(hid_ishtp_cl);
 	ishtp_put_device(cl_device);
 	ishtp_hid_remove(client_data);
+	hid_ishtp_cl_deinit(hid_ishtp_cl);
 
 	hid_ishtp_cl = NULL;
 

From 07583a0010696a17fb0942e0b499a62785c5fc9f Mon Sep 17 00:00:00 2001
From: Zhang Lixu <lixu.zhang@intel.com>
Date: Tue, 18 Feb 2025 14:37:30 +0800
Subject: [PATCH 0354/1173] HID: intel-ish-hid: Fix use-after-free issue in
 ishtp_hid_remove()

The system can experience a random crash a few minutes after the driver is
removed. This issue occurs due to improper handling of memory freeing in
the ishtp_hid_remove() function.

The function currently frees the `driver_data` directly within the loop
that destroys the HID devices, which can lead to accessing freed memory.
Specifically, `hid_destroy_device()` uses `driver_data` when it calls
`hid_ishtp_set_feature()` to power off the sensor, so freeing
`driver_data` beforehand can result in accessing invalid memory.

This patch resolves the issue by storing the `driver_data` in a temporary
variable before calling `hid_destroy_device()`, and then freeing the
`driver_data` after the device is destroyed.

Fixes: 0b28cb4bcb17 ("HID: intel-ish-hid: ISH HID client driver")
Signed-off-by: Zhang Lixu <lixu.zhang@intel.com>
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/intel-ish-hid/ishtp-hid.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/hid/intel-ish-hid/ishtp-hid.c b/drivers/hid/intel-ish-hid/ishtp-hid.c
index 00c6f0ebf3563..be2c62fc8251d 100644
--- a/drivers/hid/intel-ish-hid/ishtp-hid.c
+++ b/drivers/hid/intel-ish-hid/ishtp-hid.c
@@ -261,12 +261,14 @@ int ishtp_hid_probe(unsigned int cur_hid_dev,
  */
 void ishtp_hid_remove(struct ishtp_cl_data *client_data)
 {
+	void *data;
 	int i;
 
 	for (i = 0; i < client_data->num_hid_devices; ++i) {
 		if (client_data->hid_sensor_hubs[i]) {
-			kfree(client_data->hid_sensor_hubs[i]->driver_data);
+			data = client_data->hid_sensor_hubs[i]->driver_data;
 			hid_destroy_device(client_data->hid_sensor_hubs[i]);
+			kfree(data);
 			client_data->hid_sensor_hubs[i] = NULL;
 		}
 	}

From 3dbc0215e3c502a9f3221576da0fdc9847fb9721 Mon Sep 17 00:00:00 2001
From: Aaron Kling <webgeek1234@gmail.com>
Date: Tue, 18 Feb 2025 03:28:03 -0600
Subject: [PATCH 0355/1173] drm/nouveau/pmu: Fix gp10b firmware guard

Most kernel configs enable multiple Tegra SoC generations, causing this
typo to go unnoticed. But in the case where a kernel config is strictly
for Tegra186, this is a problem.

Fixes: 989863d7cbe5 ("drm/nouveau/pmu: select implementation based on available firmware")
Signed-off-by: Aaron Kling <webgeek1234@gmail.com>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20250218-nouveau-gm10b-guard-v2-1-a4de71500d48@gmail.com
---
 drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c
index a6f410ba60bc9..d393bc540f862 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c
@@ -75,7 +75,7 @@ gp10b_pmu_acr = {
 	.bootstrap_multiple_falcons = gp10b_pmu_acr_bootstrap_multiple_falcons,
 };
 
-#if IS_ENABLED(CONFIG_ARCH_TEGRA_210_SOC)
+#if IS_ENABLED(CONFIG_ARCH_TEGRA_186_SOC)
 MODULE_FIRMWARE("nvidia/gp10b/pmu/desc.bin");
 MODULE_FIRMWARE("nvidia/gp10b/pmu/image.bin");
 MODULE_FIRMWARE("nvidia/gp10b/pmu/sig.bin");

From 6586788f0a8d0f3b33b1383885575f5b5f7b9dad Mon Sep 17 00:00:00 2001
From: Karol Herbst <kherbst@redhat.com>
Date: Sat, 15 Feb 2025 08:37:53 +0100
Subject: [PATCH 0356/1173] MAINTAINERS: Remove myself

I was pondering with myself for a while if I should just make it official
that I'm not really involved in the kernel community anymore, neither as a
reviewer, nor as a maintainer.

Most of the time I simply excused myself with "if something urgent comes
up, I can chime in and help out". Lyude and Danilo are doing a wonderful
job and I've put all my trust into them.

However, there is one thing I can't stand and it's hurting me the most.
I'm convinced, no, my core believe is, that inclusivity and respect,
working with others as equals, no power plays involved, is how we should
work together within the Free and Open Source community.

I can understand maintainers needing to learn, being concerned on
technical points. Everybody deserves the time to understand and learn. It
is my true belief that most people are capable of change eventually. I
truly believe this community can change from within, however this doesn't
mean it's going to be a smooth process.

The moment I made up my mind about this was reading the following words
written by a maintainer within the kernel community:

	"we are the thin blue line"

This isn't okay. This isn't creating an inclusive environment. This isn't
okay with the current political situation especially in the US. A
maintainer speaking those words can't be kept. No matter how important
or critical or relevant they are. They need to be removed until they
learn. Learn what those words mean for a lot of marginalized people. Learn
about what horrors it evokes in their minds.

I can't in good faith remain to be part of a project and its community
where those words are tolerated. Those words are not technical, they are
a political statement. Even if unintentionally, such words carry power,
they carry meanings one needs to be aware of. They do cause an immense
amount of harm.

I wish the best of luck for everybody to continue to try to work from
within. You got my full support and I won't hold it against anybody trying
to improve the community, it's a thankless job, it's a lot of work. People
will continue to burn out.

I got burned out enough by myself caring about the bits I maintained, but
eventually I had to realize my limits. The obligation I felt was eating me
from inside. It stopped being fun at some point and I reached a point
where I simply couldn't continue the work I was so motivated doing as I've
did in the early days.

Please respect my wishes and put this statement as is into the tree.
Leaving anything out destroys its entire meaning.

Respectfully

Karol

Signed-off-by: Karol Herbst <kherbst@redhat.com>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20250215073753.1217002-2-kherbst@redhat.com
---
 MAINTAINERS | 2 --
 1 file changed, 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index fd4f528bc4145..18ade2ea4f3c4 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7354,7 +7354,6 @@ F:	Documentation/devicetree/bindings/display/panel/novatek,nt36672a.yaml
 F:	drivers/gpu/drm/panel/panel-novatek-nt36672a.c
 
 DRM DRIVER FOR NVIDIA GEFORCE/QUADRO GPUS
-M:	Karol Herbst <kherbst@redhat.com>
 M:	Lyude Paul <lyude@redhat.com>
 M:	Danilo Krummrich <dakr@kernel.org>
 L:	dri-devel@lists.freedesktop.org
@@ -23819,7 +23818,6 @@ F:	tools/testing/selftests/ftrace/
 TRACING MMIO ACCESSES (MMIOTRACE)
 M:	Steven Rostedt <rostedt@goodmis.org>
 M:	Masami Hiramatsu <mhiramat@kernel.org>
-R:	Karol Herbst <karolherbst@gmail.com>
 R:	Pekka Paalanen <ppaalanen@gmail.com>
 L:	linux-kernel@vger.kernel.org
 L:	nouveau@lists.freedesktop.org

From 60255f3704fde70ed3c4d62f919aa4b46f841f70 Mon Sep 17 00:00:00 2001
From: Niravkumar L Rabara <niravkumar.l.rabara@intel.com>
Date: Sun, 16 Feb 2025 11:15:36 +0800
Subject: [PATCH 0357/1173] mtd: rawnand: cadence: fix unchecked dereference

Add NULL check before variable dereference to fix static checker warning.

Fixes: d76d22b5096c ("mtd: rawnand: cadence: use dma_map_resource for sdma address")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/all/e448a22c-bada-448d-9167-7af71305130d@stanley.mountain/
Signed-off-by: Niravkumar L Rabara <niravkumar.l.rabara@intel.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/cadence-nand-controller.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/mtd/nand/raw/cadence-nand-controller.c b/drivers/mtd/nand/raw/cadence-nand-controller.c
index 0b2db4173e723..6667eea955977 100644
--- a/drivers/mtd/nand/raw/cadence-nand-controller.c
+++ b/drivers/mtd/nand/raw/cadence-nand-controller.c
@@ -2972,8 +2972,10 @@ static int cadence_nand_init(struct cdns_nand_ctrl *cdns_ctrl)
 static void cadence_nand_remove(struct cdns_nand_ctrl *cdns_ctrl)
 {
 	cadence_nand_chips_cleanup(cdns_ctrl);
-	dma_unmap_resource(cdns_ctrl->dmac->device->dev, cdns_ctrl->io.iova_dma,
-			   cdns_ctrl->io.size, DMA_BIDIRECTIONAL, 0);
+	if (cdns_ctrl->dmac)
+		dma_unmap_resource(cdns_ctrl->dmac->device->dev,
+				   cdns_ctrl->io.iova_dma, cdns_ctrl->io.size,
+				   DMA_BIDIRECTIONAL, 0);
 	cadence_nand_irq_cleanup(cdns_ctrl->irq, cdns_ctrl);
 	kfree(cdns_ctrl->buf);
 	dma_free_coherent(cdns_ctrl->dev, sizeof(struct cadence_nand_cdma_desc),

From a8e8ffcc3afce2ee5fb70162aeaef3f03573ee1e Mon Sep 17 00:00:00 2001
From: Alexander Usyskin <alexander.usyskin@intel.com>
Date: Sun, 9 Feb 2025 13:05:50 +0200
Subject: [PATCH 0358/1173] mei: me: add panther lake P DID

Add Panther Lake P device id.

Cc: stable <stable@kernel.org>
Co-developed-by: Tomas Winkler <tomasw@gmail.com>
Signed-off-by: Tomas Winkler <tomasw@gmail.com>
Signed-off-by: Alexander Usyskin <alexander.usyskin@intel.com>
Link: https://lore.kernel.org/r/20250209110550.1582982-1-alexander.usyskin@intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/mei/hw-me-regs.h | 2 ++
 drivers/misc/mei/pci-me.c     | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h
index c3a6657dcd4a2..a5f88ec97df75 100644
--- a/drivers/misc/mei/hw-me-regs.h
+++ b/drivers/misc/mei/hw-me-regs.h
@@ -117,6 +117,8 @@
 
 #define MEI_DEV_ID_LNL_M      0xA870  /* Lunar Lake Point M */
 
+#define MEI_DEV_ID_PTL_P      0xE470  /* Panther Lake P */
+
 /*
  * MEI HW Section
  */
diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c
index 6589635f8ba32..d6ff9d82ae94b 100644
--- a/drivers/misc/mei/pci-me.c
+++ b/drivers/misc/mei/pci-me.c
@@ -124,6 +124,8 @@ static const struct pci_device_id mei_me_pci_tbl[] = {
 
 	{MEI_PCI_DEVICE(MEI_DEV_ID_LNL_M, MEI_ME_PCH15_CFG)},
 
+	{MEI_PCI_DEVICE(MEI_DEV_ID_PTL_P, MEI_ME_PCH15_CFG)},
+
 	/* required last entry */
 	{0, }
 };

From fdb1ada57cf8b8752cdf54f08709d76d74999544 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Fri, 14 Feb 2025 22:24:25 +0100
Subject: [PATCH 0359/1173] mei: vsc: Use "wakeuphostint" when getting the host
 wakeup GPIO

The _CRS ACPI resources table has 2 entries for the host wakeup GPIO,
the first one being a regular GpioIo () resource while the second one
is a GpioInt () resource for the same pin.

The acpi_gpio_mapping table used by vsc-tp.c maps the first Gpio ()
resource to "wakeuphost-gpios" where as the second GpioInt () entry
is mapped to "wakeuphostint-gpios".

Using "wakeuphost" to request the GPIO as was done until now, means
that the gpiolib-acpi code does not know that the GPIO is active-low
as that info is only available in the GpioInt () entry.

Things were still working before due to the following happening:

1. Since the 2 entries point to the same pin they share a struct gpio_desc
2. The SPI core creates the SPI device vsc-tp.c binds to and calls
   acpi_dev_gpio_irq_get(). This does use the second entry and sets
   FLAG_ACTIVE_LOW in gpio_desc.flags .
3. vsc_tp_probe() requests the "wakeuphost" GPIO and inherits the
   active-low flag set by acpi_dev_gpio_irq_get()

But there is a possible scenario where things do not work:

1. - 3. happen as above
4. After requesting the "wakeuphost" GPIO, the "resetfw" GPIO is requested
   next, but its USB GPIO controller is not available yet, so this call
   returns -EPROBE_DEFER.
5. The gpio_desc for "wakeuphost" is put() and during this the active-low
   flag is cleared from gpio_desc.flags .
6. Later on vsc_tp_probe() requests the "wakeuphost" GPIO again, but now it
   is not marked active-low.

The difference can also be seen in /sys/kernel/debug/gpio, which contains
the following line for this GPIO:

 gpio-535 (                    |wakeuphost          ) in  hi IRQ ACTIVE LOW

If the second scenario is hit the "ACTIVE LOW" at the end disappears and
things do not work.

Fix this by requesting the GPIO through the "wakeuphostint" mapping instead
which provides active-low info without relying on acpi_dev_gpio_irq_get()
pre-populating this info in the gpio_desc.

Link: https://bugzilla.redhat.com/show_bug.cgi?id=2316918
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Tested-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Fixes: 566f5ca97680 ("mei: Add transport driver for IVSC device")
Cc: stable <stable@kernel.org>
Link: https://lore.kernel.org/r/20250214212425.84021-1-hdegoede@redhat.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/mei/vsc-tp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/misc/mei/vsc-tp.c b/drivers/misc/mei/vsc-tp.c
index 35d349fee7698..7be1649b19725 100644
--- a/drivers/misc/mei/vsc-tp.c
+++ b/drivers/misc/mei/vsc-tp.c
@@ -502,7 +502,7 @@ static int vsc_tp_probe(struct spi_device *spi)
 	if (ret)
 		return ret;
 
-	tp->wakeuphost = devm_gpiod_get(dev, "wakeuphost", GPIOD_IN);
+	tp->wakeuphost = devm_gpiod_get(dev, "wakeuphostint", GPIOD_IN);
 	if (IS_ERR(tp->wakeuphost))
 		return PTR_ERR(tp->wakeuphost);
 

From c90aad369899a607cfbc002bebeafd51e31900cd Mon Sep 17 00:00:00 2001
From: Nikita Zhandarovich <n.zhandarovich@fintech.ru>
Date: Thu, 13 Feb 2025 15:22:57 +0300
Subject: [PATCH 0360/1173] usb: atm: cxacru: fix a flaw in existing endpoint
 checks

Syzbot once again identified a flaw in usb endpoint checking, see [1].
This time the issue stems from a commit authored by me (2eabb655a968
("usb: atm: cxacru: fix endpoint checking in cxacru_bind()")).

While using usb_find_common_endpoints() may usually be enough to
discard devices with wrong endpoints, in this case one needs more
than just finding and identifying the sufficient number of endpoints
of correct types - one needs to check the endpoint's address as well.

Since cxacru_bind() fills URBs with CXACRU_EP_CMD address in mind,
switch the endpoint verification approach to usb_check_XXX_endpoints()
instead to fix incomplete ep testing.

[1] Syzbot report:
usb 5-1: BOGUS urb xfer, pipe 3 != type 1
WARNING: CPU: 0 PID: 1378 at drivers/usb/core/urb.c:504 usb_submit_urb+0xc4e/0x18c0 drivers/usb/core/urb.c:503
...
RIP: 0010:usb_submit_urb+0xc4e/0x18c0 drivers/usb/core/urb.c:503
...
Call Trace:
 <TASK>
 cxacru_cm+0x3c8/0xe50 drivers/usb/atm/cxacru.c:649
 cxacru_card_status drivers/usb/atm/cxacru.c:760 [inline]
 cxacru_bind+0xcf9/0x1150 drivers/usb/atm/cxacru.c:1223
 usbatm_usb_probe+0x314/0x1d30 drivers/usb/atm/usbatm.c:1058
 cxacru_usb_probe+0x184/0x220 drivers/usb/atm/cxacru.c:1377
 usb_probe_interface+0x641/0xbb0 drivers/usb/core/driver.c:396
 really_probe+0x2b9/0xad0 drivers/base/dd.c:658
 __driver_probe_device+0x1a2/0x390 drivers/base/dd.c:800
 driver_probe_device+0x50/0x430 drivers/base/dd.c:830
...

Reported-and-tested-by: syzbot+ccbbc229a024fa3e13b5@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=ccbbc229a024fa3e13b5
Fixes: 2eabb655a968 ("usb: atm: cxacru: fix endpoint checking in cxacru_bind()")
Cc: stable@kernel.org
Signed-off-by: Nikita Zhandarovich <n.zhandarovich@fintech.ru>
Link: https://lore.kernel.org/r/20250213122259.730772-1-n.zhandarovich@fintech.ru
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/atm/cxacru.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/usb/atm/cxacru.c b/drivers/usb/atm/cxacru.c
index 0dd85d2635b99..47d06af33747d 100644
--- a/drivers/usb/atm/cxacru.c
+++ b/drivers/usb/atm/cxacru.c
@@ -1131,7 +1131,10 @@ static int cxacru_bind(struct usbatm_data *usbatm_instance,
 	struct cxacru_data *instance;
 	struct usb_device *usb_dev = interface_to_usbdev(intf);
 	struct usb_host_endpoint *cmd_ep = usb_dev->ep_in[CXACRU_EP_CMD];
-	struct usb_endpoint_descriptor *in, *out;
+	static const u8 ep_addrs[] = {
+		CXACRU_EP_CMD + USB_DIR_IN,
+		CXACRU_EP_CMD + USB_DIR_OUT,
+		0};
 	int ret;
 
 	/* instance init */
@@ -1179,13 +1182,11 @@ static int cxacru_bind(struct usbatm_data *usbatm_instance,
 	}
 
 	if (usb_endpoint_xfer_int(&cmd_ep->desc))
-		ret = usb_find_common_endpoints(intf->cur_altsetting,
-						NULL, NULL, &in, &out);
+		ret = usb_check_int_endpoints(intf, ep_addrs);
 	else
-		ret = usb_find_common_endpoints(intf->cur_altsetting,
-						&in, &out, NULL, NULL);
+		ret = usb_check_bulk_endpoints(intf, ep_addrs);
 
-	if (ret) {
+	if (!ret) {
 		usb_err(usbatm_instance, "cxacru_bind: interface has incorrect endpoints\n");
 		ret = -ENODEV;
 		goto fail;

From 17c2c87c37862c3e95b55f660681cc6e8d66660e Mon Sep 17 00:00:00 2001
From: Prashanth K <prashanth.k@oss.qualcomm.com>
Date: Wed, 12 Feb 2025 15:38:40 +0530
Subject: [PATCH 0361/1173] usb: gadget: u_ether: Set is_suspend flag if remote
 wakeup fails

Currently while UDC suspends, u_ether attempts to remote wakeup
the host if there are any pending transfers. However, if remote
wakeup fails, the UDC remains suspended but the is_suspend flag
is not set. And since is_suspend flag isn't set, the subsequent
eth_start_xmit() would queue USB requests to suspended UDC.

To fix this, bail out from gether_suspend() only if remote wakeup
operation is successful.

Cc: stable <stable@kernel.org>
Fixes: 0a1af6dfa077 ("usb: gadget: f_ecm: Add suspend/resume and remote wakeup support")
Signed-off-by: Prashanth K <prashanth.k@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20250212100840.3812153-1-prashanth.k@oss.qualcomm.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/u_ether.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c
index 09e2838917e29..f58590bf5e02f 100644
--- a/drivers/usb/gadget/function/u_ether.c
+++ b/drivers/usb/gadget/function/u_ether.c
@@ -1052,8 +1052,8 @@ void gether_suspend(struct gether *link)
 		 * There is a transfer in progress. So we trigger a remote
 		 * wakeup to inform the host.
 		 */
-		ether_wakeup_host(dev->port_usb);
-		return;
+		if (!ether_wakeup_host(dev->port_usb))
+			return;
 	}
 	spin_lock_irqsave(&dev->lock, flags);
 	link->is_suspend = true;

From 40e89ff5750fca2c1d6da93f98a2038716bba86c Mon Sep 17 00:00:00 2001
From: Prashanth K <prashanth.k@oss.qualcomm.com>
Date: Mon, 17 Feb 2025 17:33:28 +0530
Subject: [PATCH 0362/1173] usb: gadget: Set self-powered based on MaxPower and
 bmAttributes

Currently the USB gadget will be set as bus-powered based solely
on whether its bMaxPower is greater than 100mA, but this may miss
devices that may legitimately draw less than 100mA but still want
to report as bus-powered. Similarly during suspend & resume, USB
gadget is incorrectly marked as bus/self powered without checking
the bmAttributes field. Fix these by configuring the USB gadget
as self or bus powered based on bmAttributes, and explicitly set
it as bus-powered if it draws more than 100mA.

Cc: stable <stable@kernel.org>
Fixes: 5e5caf4fa8d3 ("usb: gadget: composite: Inform controller driver of self-powered")
Signed-off-by: Prashanth K <prashanth.k@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20250217120328.2446639-1-prashanth.k@oss.qualcomm.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/composite.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index bdda8c74602de..1fb28bbf6c458 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -1050,10 +1050,11 @@ static int set_config(struct usb_composite_dev *cdev,
 	else
 		usb_gadget_set_remote_wakeup(gadget, 0);
 done:
-	if (power <= USB_SELF_POWER_VBUS_MAX_DRAW)
-		usb_gadget_set_selfpowered(gadget);
-	else
+	if (power > USB_SELF_POWER_VBUS_MAX_DRAW ||
+	    !(c->bmAttributes & USB_CONFIG_ATT_SELFPOWER))
 		usb_gadget_clear_selfpowered(gadget);
+	else
+		usb_gadget_set_selfpowered(gadget);
 
 	usb_gadget_vbus_draw(gadget, power);
 	if (result >= 0 && cdev->delayed_status)
@@ -2615,7 +2616,9 @@ void composite_suspend(struct usb_gadget *gadget)
 
 	cdev->suspended = 1;
 
-	usb_gadget_set_selfpowered(gadget);
+	if (cdev->config->bmAttributes & USB_CONFIG_ATT_SELFPOWER)
+		usb_gadget_set_selfpowered(gadget);
+
 	usb_gadget_vbus_draw(gadget, 2);
 }
 
@@ -2649,8 +2652,11 @@ void composite_resume(struct usb_gadget *gadget)
 		else
 			maxpower = min(maxpower, 900U);
 
-		if (maxpower > USB_SELF_POWER_VBUS_MAX_DRAW)
+		if (maxpower > USB_SELF_POWER_VBUS_MAX_DRAW ||
+		    !(cdev->config->bmAttributes & USB_CONFIG_ATT_SELFPOWER))
 			usb_gadget_clear_selfpowered(gadget);
+		else
+			usb_gadget_set_selfpowered(gadget);
 
 		usb_gadget_vbus_draw(gadget, maxpower);
 	} else {

From d6b82dafd17db0658f089b9cdec573982ca82bc5 Mon Sep 17 00:00:00 2001
From: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Date: Wed, 19 Feb 2025 12:47:00 +0100
Subject: [PATCH 0363/1173] usb: typec: tcpci_rt1711h: Unmask alert interrupts
 to fix functionality

During probe, the TCPC alert interrupts are getting masked to
avoid unwanted interrupts during chip setup: this is ok to do
but there is no unmasking happening at any later time, which
means that the chip will not raise any interrupt, essentially
making it not functional as, while internally it does perform
all of the intended functions, it won't signal anything to the
outside.

Unmask the alert interrupts to fix functionality.

Fixes: ce08eaeb6388 ("staging: typec: rt1711h typec chip driver")
Cc: stable <stable@kernel.org>
Signed-off-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Link: https://lore.kernel.org/r/20250219114700.41700-1-angelogioacchino.delregno@collabora.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/tcpci_rt1711h.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/usb/typec/tcpm/tcpci_rt1711h.c b/drivers/usb/typec/tcpm/tcpci_rt1711h.c
index 64f6dd0dc6609..88c50b984e8a3 100644
--- a/drivers/usb/typec/tcpm/tcpci_rt1711h.c
+++ b/drivers/usb/typec/tcpm/tcpci_rt1711h.c
@@ -334,6 +334,11 @@ static int rt1711h_probe(struct i2c_client *client)
 {
 	int ret;
 	struct rt1711h_chip *chip;
+	const u16 alert_mask = TCPC_ALERT_TX_SUCCESS | TCPC_ALERT_TX_DISCARDED |
+			       TCPC_ALERT_TX_FAILED | TCPC_ALERT_RX_HARD_RST |
+			       TCPC_ALERT_RX_STATUS | TCPC_ALERT_POWER_STATUS |
+			       TCPC_ALERT_CC_STATUS | TCPC_ALERT_RX_BUF_OVF |
+			       TCPC_ALERT_FAULT;
 
 	chip = devm_kzalloc(&client->dev, sizeof(*chip), GFP_KERNEL);
 	if (!chip)
@@ -382,6 +387,12 @@ static int rt1711h_probe(struct i2c_client *client)
 					dev_name(chip->dev), chip);
 	if (ret < 0)
 		return ret;
+
+	/* Enable alert interrupts */
+	ret = rt1711h_write16(chip, TCPC_ALERT_MASK, alert_mask);
+	if (ret < 0)
+		return ret;
+
 	enable_irq_wake(client->irq);
 
 	return 0;

From 976e7e9bdc7719a023a4ecccd2e3daec9ab20a40 Mon Sep 17 00:00:00 2001
From: "Christian A. Ehrhardt" <lk@c--e.de>
Date: Mon, 17 Feb 2025 13:54:39 +0300
Subject: [PATCH 0364/1173] acpi: typec: ucsi: Introduce a ->poll_cci method

For the ACPI backend of UCSI the UCSI "registers" are just a memory copy
of the register values in an opregion. The ACPI implementation in the
BIOS ensures that the opregion contents are synced to the embedded
controller and it ensures that the registers (in particular CCI) are
synced back to the opregion on notifications. While there is an ACPI call
that syncs the actual registers to the opregion there is rarely a need to
do this and on some ACPI implementations it actually breaks in various
interesting ways.

The only reason to force a sync from the embedded controller is to poll
CCI while notifications are disabled. Only the ucsi core knows if this
is the case and guessing based on the current command is suboptimal, i.e.
leading to the following spurious assertion splat:

WARNING: CPU: 3 PID: 76 at drivers/usb/typec/ucsi/ucsi.c:1388 ucsi_reset_ppm+0x1b4/0x1c0 [typec_ucsi]
CPU: 3 UID: 0 PID: 76 Comm: kworker/3:0 Not tainted 6.12.11-200.fc41.x86_64 #1
Hardware name: LENOVO 21D0/LNVNB161216, BIOS J6CN45WW 03/17/2023
Workqueue: events_long ucsi_init_work [typec_ucsi]
RIP: 0010:ucsi_reset_ppm+0x1b4/0x1c0 [typec_ucsi]
Call Trace:
 <TASK>
 ucsi_init_work+0x3c/0xac0 [typec_ucsi]
 process_one_work+0x179/0x330
 worker_thread+0x252/0x390
 kthread+0xd2/0x100
 ret_from_fork+0x34/0x50
 ret_from_fork_asm+0x1a/0x30
 </TASK>

Thus introduce a ->poll_cci() method that works like ->read_cci() with an
additional forced sync and document that this should be used when polling
with notifications disabled. For all other backends that presumably don't
have this issue use the same implementation for both methods.

Fixes: fa48d7e81624 ("usb: typec: ucsi: Do not call ACPI _DSM method for UCSI read operations")
Cc: stable <stable@kernel.org>
Signed-off-by: Christian A. Ehrhardt <lk@c--e.de>
Tested-by: Fedor Pchelkin <boddah8794@gmail.com>
Signed-off-by: Fedor Pchelkin <boddah8794@gmail.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20250217105442.113486-2-boddah8794@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/ucsi/ucsi.c           | 10 +++++-----
 drivers/usb/typec/ucsi/ucsi.h           |  2 ++
 drivers/usb/typec/ucsi/ucsi_acpi.c      | 21 ++++++++++++++-------
 drivers/usb/typec/ucsi/ucsi_ccg.c       |  1 +
 drivers/usb/typec/ucsi/ucsi_glink.c     |  1 +
 drivers/usb/typec/ucsi/ucsi_stm32g0.c   |  1 +
 drivers/usb/typec/ucsi/ucsi_yoga_c630.c |  1 +
 7 files changed, 25 insertions(+), 12 deletions(-)

diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c
index fcf499cc9458c..0fe1476f4c297 100644
--- a/drivers/usb/typec/ucsi/ucsi.c
+++ b/drivers/usb/typec/ucsi/ucsi.c
@@ -1346,7 +1346,7 @@ static int ucsi_reset_ppm(struct ucsi *ucsi)
 
 	mutex_lock(&ucsi->ppm_lock);
 
-	ret = ucsi->ops->read_cci(ucsi, &cci);
+	ret = ucsi->ops->poll_cci(ucsi, &cci);
 	if (ret < 0)
 		goto out;
 
@@ -1364,7 +1364,7 @@ static int ucsi_reset_ppm(struct ucsi *ucsi)
 
 		tmo = jiffies + msecs_to_jiffies(UCSI_TIMEOUT_MS);
 		do {
-			ret = ucsi->ops->read_cci(ucsi, &cci);
+			ret = ucsi->ops->poll_cci(ucsi, &cci);
 			if (ret < 0)
 				goto out;
 			if (cci & UCSI_CCI_COMMAND_COMPLETE)
@@ -1393,7 +1393,7 @@ static int ucsi_reset_ppm(struct ucsi *ucsi)
 		/* Give the PPM time to process a reset before reading CCI */
 		msleep(20);
 
-		ret = ucsi->ops->read_cci(ucsi, &cci);
+		ret = ucsi->ops->poll_cci(ucsi, &cci);
 		if (ret)
 			goto out;
 
@@ -1929,8 +1929,8 @@ struct ucsi *ucsi_create(struct device *dev, const struct ucsi_operations *ops)
 	struct ucsi *ucsi;
 
 	if (!ops ||
-	    !ops->read_version || !ops->read_cci || !ops->read_message_in ||
-	    !ops->sync_control || !ops->async_control)
+	    !ops->read_version || !ops->read_cci || !ops->poll_cci ||
+	    !ops->read_message_in || !ops->sync_control || !ops->async_control)
 		return ERR_PTR(-EINVAL);
 
 	ucsi = kzalloc(sizeof(*ucsi), GFP_KERNEL);
diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h
index 82735eb34f0e3..28780acc4af2e 100644
--- a/drivers/usb/typec/ucsi/ucsi.h
+++ b/drivers/usb/typec/ucsi/ucsi.h
@@ -62,6 +62,7 @@ struct dentry;
  * struct ucsi_operations - UCSI I/O operations
  * @read_version: Read implemented UCSI version
  * @read_cci: Read CCI register
+ * @poll_cci: Read CCI register while polling with notifications disabled
  * @read_message_in: Read message data from UCSI
  * @sync_control: Blocking control operation
  * @async_control: Non-blocking control operation
@@ -76,6 +77,7 @@ struct dentry;
 struct ucsi_operations {
 	int (*read_version)(struct ucsi *ucsi, u16 *version);
 	int (*read_cci)(struct ucsi *ucsi, u32 *cci);
+	int (*poll_cci)(struct ucsi *ucsi, u32 *cci);
 	int (*read_message_in)(struct ucsi *ucsi, void *val, size_t val_len);
 	int (*sync_control)(struct ucsi *ucsi, u64 command);
 	int (*async_control)(struct ucsi *ucsi, u64 command);
diff --git a/drivers/usb/typec/ucsi/ucsi_acpi.c b/drivers/usb/typec/ucsi/ucsi_acpi.c
index 5c55155519634..ac1ebb5d95272 100644
--- a/drivers/usb/typec/ucsi/ucsi_acpi.c
+++ b/drivers/usb/typec/ucsi/ucsi_acpi.c
@@ -59,19 +59,24 @@ static int ucsi_acpi_read_version(struct ucsi *ucsi, u16 *version)
 static int ucsi_acpi_read_cci(struct ucsi *ucsi, u32 *cci)
 {
 	struct ucsi_acpi *ua = ucsi_get_drvdata(ucsi);
-	int ret;
-
-	if (UCSI_COMMAND(ua->cmd) == UCSI_PPM_RESET) {
-		ret = ucsi_acpi_dsm(ua, UCSI_DSM_FUNC_READ);
-		if (ret)
-			return ret;
-	}
 
 	memcpy(cci, ua->base + UCSI_CCI, sizeof(*cci));
 
 	return 0;
 }
 
+static int ucsi_acpi_poll_cci(struct ucsi *ucsi, u32 *cci)
+{
+	struct ucsi_acpi *ua = ucsi_get_drvdata(ucsi);
+	int ret;
+
+	ret = ucsi_acpi_dsm(ua, UCSI_DSM_FUNC_READ);
+	if (ret)
+		return ret;
+
+	return ucsi_acpi_read_cci(ucsi, cci);
+}
+
 static int ucsi_acpi_read_message_in(struct ucsi *ucsi, void *val, size_t val_len)
 {
 	struct ucsi_acpi *ua = ucsi_get_drvdata(ucsi);
@@ -94,6 +99,7 @@ static int ucsi_acpi_async_control(struct ucsi *ucsi, u64 command)
 static const struct ucsi_operations ucsi_acpi_ops = {
 	.read_version = ucsi_acpi_read_version,
 	.read_cci = ucsi_acpi_read_cci,
+	.poll_cci = ucsi_acpi_poll_cci,
 	.read_message_in = ucsi_acpi_read_message_in,
 	.sync_control = ucsi_sync_control_common,
 	.async_control = ucsi_acpi_async_control
@@ -142,6 +148,7 @@ static int ucsi_gram_sync_control(struct ucsi *ucsi, u64 command)
 static const struct ucsi_operations ucsi_gram_ops = {
 	.read_version = ucsi_acpi_read_version,
 	.read_cci = ucsi_acpi_read_cci,
+	.poll_cci = ucsi_acpi_poll_cci,
 	.read_message_in = ucsi_gram_read_message_in,
 	.sync_control = ucsi_gram_sync_control,
 	.async_control = ucsi_acpi_async_control
diff --git a/drivers/usb/typec/ucsi/ucsi_ccg.c b/drivers/usb/typec/ucsi/ucsi_ccg.c
index 740171f24ef9f..4b1668733a4be 100644
--- a/drivers/usb/typec/ucsi/ucsi_ccg.c
+++ b/drivers/usb/typec/ucsi/ucsi_ccg.c
@@ -664,6 +664,7 @@ static int ucsi_ccg_sync_control(struct ucsi *ucsi, u64 command)
 static const struct ucsi_operations ucsi_ccg_ops = {
 	.read_version = ucsi_ccg_read_version,
 	.read_cci = ucsi_ccg_read_cci,
+	.poll_cci = ucsi_ccg_read_cci,
 	.read_message_in = ucsi_ccg_read_message_in,
 	.sync_control = ucsi_ccg_sync_control,
 	.async_control = ucsi_ccg_async_control,
diff --git a/drivers/usb/typec/ucsi/ucsi_glink.c b/drivers/usb/typec/ucsi/ucsi_glink.c
index fed39d4580905..8af79101a2fc7 100644
--- a/drivers/usb/typec/ucsi/ucsi_glink.c
+++ b/drivers/usb/typec/ucsi/ucsi_glink.c
@@ -206,6 +206,7 @@ static void pmic_glink_ucsi_connector_status(struct ucsi_connector *con)
 static const struct ucsi_operations pmic_glink_ucsi_ops = {
 	.read_version = pmic_glink_ucsi_read_version,
 	.read_cci = pmic_glink_ucsi_read_cci,
+	.poll_cci = pmic_glink_ucsi_read_cci,
 	.read_message_in = pmic_glink_ucsi_read_message_in,
 	.sync_control = ucsi_sync_control_common,
 	.async_control = pmic_glink_ucsi_async_control,
diff --git a/drivers/usb/typec/ucsi/ucsi_stm32g0.c b/drivers/usb/typec/ucsi/ucsi_stm32g0.c
index 6923fad31d795..57ef7d83a4121 100644
--- a/drivers/usb/typec/ucsi/ucsi_stm32g0.c
+++ b/drivers/usb/typec/ucsi/ucsi_stm32g0.c
@@ -424,6 +424,7 @@ static irqreturn_t ucsi_stm32g0_irq_handler(int irq, void *data)
 static const struct ucsi_operations ucsi_stm32g0_ops = {
 	.read_version = ucsi_stm32g0_read_version,
 	.read_cci = ucsi_stm32g0_read_cci,
+	.poll_cci = ucsi_stm32g0_read_cci,
 	.read_message_in = ucsi_stm32g0_read_message_in,
 	.sync_control = ucsi_sync_control_common,
 	.async_control = ucsi_stm32g0_async_control,
diff --git a/drivers/usb/typec/ucsi/ucsi_yoga_c630.c b/drivers/usb/typec/ucsi/ucsi_yoga_c630.c
index 4cae85c0dc12a..d33e3f2dd1d80 100644
--- a/drivers/usb/typec/ucsi/ucsi_yoga_c630.c
+++ b/drivers/usb/typec/ucsi/ucsi_yoga_c630.c
@@ -74,6 +74,7 @@ static int yoga_c630_ucsi_async_control(struct ucsi *ucsi, u64 command)
 static const struct ucsi_operations yoga_c630_ucsi_ops = {
 	.read_version = yoga_c630_ucsi_read_version,
 	.read_cci = yoga_c630_ucsi_read_cci,
+	.poll_cci = yoga_c630_ucsi_read_cci,
 	.read_message_in = yoga_c630_ucsi_read_message_in,
 	.sync_control = ucsi_sync_control_common,
 	.async_control = yoga_c630_ucsi_async_control,

From bf4f9ae1cb08ccaafbe6874be6c46f59b83ae778 Mon Sep 17 00:00:00 2001
From: Fedor Pchelkin <boddah8794@gmail.com>
Date: Mon, 17 Feb 2025 13:54:40 +0300
Subject: [PATCH 0365/1173] usb: typec: ucsi: increase timeout for PPM reset
 operations

It is observed that on some systems an initial PPM reset during the boot
phase can trigger a timeout:

[    6.482546] ucsi_acpi USBC000:00: failed to reset PPM!
[    6.482551] ucsi_acpi USBC000:00: error -ETIMEDOUT: PPM init failed

Still, increasing the timeout value, albeit being the most straightforward
solution, eliminates the problem: the initial PPM reset may take up to
~8000-10000ms on some Lenovo laptops. When it is reset after the above
period of time (or even if ucsi_reset_ppm() is not called overall), UCSI
works as expected.

Moreover, if the ucsi_acpi module is loaded/unloaded manually after the
system has booted, reading the CCI values and resetting the PPM works
perfectly, without any timeout. Thus it's only a boot-time issue.

The reason for this behavior is not clear but it may be the consequence
of some tricks that the firmware performs or be an actual firmware bug.
As a workaround, increase the timeout to avoid failing the UCSI
initialization prematurely.

Fixes: b1b59e16075f ("usb: typec: ucsi: Increase command completion timeout value")
Cc: stable <stable@kernel.org>
Signed-off-by: Fedor Pchelkin <boddah8794@gmail.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20250217105442.113486-3-boddah8794@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/ucsi/ucsi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c
index 0fe1476f4c297..7a56d3f840d75 100644
--- a/drivers/usb/typec/ucsi/ucsi.c
+++ b/drivers/usb/typec/ucsi/ucsi.c
@@ -25,7 +25,7 @@
  * difficult to estimate the time it takes for the system to process the command
  * before it is actually passed to the PPM.
  */
-#define UCSI_TIMEOUT_MS		5000
+#define UCSI_TIMEOUT_MS		10000
 
 /*
  * UCSI_SWAP_TIMEOUT_MS - Timeout for role swap requests

From a321d163de3d8aa38a6449ab2becf4b1581aed96 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Wed, 8 Jan 2025 19:09:27 +0530
Subject: [PATCH 0366/1173] bus: mhi: host: pci_generic: Use
 pci_try_reset_function() to avoid deadlock

There are multiple places from where the recovery work gets scheduled
asynchronously. Also, there are multiple places where the caller waits
synchronously for the recovery to be completed. One such place is during
the PM shutdown() callback.

If the device is not alive during recovery_work, it will try to reset the
device using pci_reset_function(). This function internally will take the
device_lock() first before resetting the device. By this time, if the lock
has already been acquired, then recovery_work will get stalled while
waiting for the lock. And if the lock was already acquired by the caller
which waits for the recovery_work to be completed, it will lead to
deadlock.

This is what happened on the X1E80100 CRD device when the device died
before shutdown() callback. Driver core calls the driver's shutdown()
callback while holding the device_lock() leading to deadlock.

And this deadlock scenario can occur on other paths as well, like during
the PM suspend() callback, where the driver core would hold the
device_lock() before calling driver's suspend() callback. And if the
recovery_work was already started, it could lead to deadlock. This is also
observed on the X1E80100 CRD.

So to fix both issues, use pci_try_reset_function() in recovery_work. This
function first checks for the availability of the device_lock() before
trying to reset the device. If the lock is available, it will acquire it
and reset the device. Otherwise, it will return -EAGAIN. If that happens,
recovery_work will fail with the error message "Recovery failed" as not
much could be done.

Cc: stable@vger.kernel.org # 5.12
Reported-by: Johan Hovold <johan@kernel.org>
Closes: https://lore.kernel.org/mhi/Z1me8iaK7cwgjL92@hovoldconsulting.com
Fixes: 7389337f0a78 ("mhi: pci_generic: Add suspend/resume/recovery procedure")
Reviewed-by: Johan Hovold <johan+linaro@kernel.org>
Tested-by: Johan Hovold <johan+linaro@kernel.org>
Analyzed-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/mhi/Z2KKjWY2mPen6GPL@hovoldconsulting.com/
Reviewed-by: Loic Poulain <loic.poulain@linaro.org>
Link: https://lore.kernel.org/r/20250108-mhi_recovery_fix-v1-1-a0a00a17da46@linaro.org
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/bus/mhi/host/pci_generic.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/bus/mhi/host/pci_generic.c b/drivers/bus/mhi/host/pci_generic.c
index c41119b9079f0..7ffea0f981628 100644
--- a/drivers/bus/mhi/host/pci_generic.c
+++ b/drivers/bus/mhi/host/pci_generic.c
@@ -1095,8 +1095,9 @@ static void mhi_pci_recovery_work(struct work_struct *work)
 err_unprepare:
 	mhi_unprepare_after_power_down(mhi_cntrl);
 err_try_reset:
-	if (pci_reset_function(pdev))
-		dev_err(&pdev->dev, "Recovery failed\n");
+	err = pci_try_reset_function(pdev);
+	if (err)
+		dev_err(&pdev->dev, "Recovery failed: %d\n", err);
 }
 
 static void health_check(struct timer_list *t)

From fa2e55811ae25020a5e9b23a8932e67e6d6261a4 Mon Sep 17 00:00:00 2001
From: Mike Lothian <mike@fireburn.co.uk>
Date: Fri, 14 Feb 2025 12:28:00 +0000
Subject: [PATCH 0367/1173] ntsync: Set the permissions to be 0666

This allows ntsync to be usuable by non-root processes out of the box

Signed-off-by: Mike Lothian <mike@fireburn.co.uk>
Reviewed-by: Elizabeth Figura <zfigura@codeweavers.com>
Link: https://lore.kernel.org/r/20250214122759.2629-2-mike@fireburn.co.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/ntsync.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/misc/ntsync.c b/drivers/misc/ntsync.c
index 055395cde42b6..0b4e56d59b3da 100644
--- a/drivers/misc/ntsync.c
+++ b/drivers/misc/ntsync.c
@@ -1208,6 +1208,7 @@ static struct miscdevice ntsync_misc = {
 	.minor		= MISC_DYNAMIC_MINOR,
 	.name		= NTSYNC_NAME,
 	.fops		= &ntsync_fops,
+	.mode		= 0666,
 };
 
 module_misc_device(ntsync_misc);

From fb3331f53e3cb1f1505f918f4f33bb0a3a231e4f Mon Sep 17 00:00:00 2001
From: Caleb Sander Mateos <csander@purestorage.com>
Date: Tue, 18 Feb 2025 20:34:43 -0700
Subject: [PATCH 0368/1173] io_uring/rsrc: remove unused constants

IO_NODE_ALLOC_CACHE_MAX has been unused since commit fbbb8e991d86
("io_uring/rsrc: get rid of io_rsrc_node allocation cache") removed the
rsrc_node_cache.

IO_RSRC_TAG_TABLE_SHIFT and IO_RSRC_TAG_TABLE_MASK have been unused
since commit 7029acd8a950 ("io_uring/rsrc: get rid of per-ring
io_rsrc_node list") removed the separate tag table for registered nodes.

Signed-off-by: Caleb Sander Mateos <csander@purestorage.com>
Reviewed-by: Li Zetao <lizetao1@huawei.com>
Link: https://lore.kernel.org/r/20250219033444.2020136-1-csander@purestorage.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/rsrc.h | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h
index 190f7ee45de93..89ea0135a1a0d 100644
--- a/io_uring/rsrc.h
+++ b/io_uring/rsrc.h
@@ -4,12 +4,6 @@
 
 #include <linux/lockdep.h>
 
-#define IO_NODE_ALLOC_CACHE_MAX 32
-
-#define IO_RSRC_TAG_TABLE_SHIFT	(PAGE_SHIFT - 3)
-#define IO_RSRC_TAG_TABLE_MAX	(1U << IO_RSRC_TAG_TABLE_SHIFT)
-#define IO_RSRC_TAG_TABLE_MASK	(IO_RSRC_TAG_TABLE_MAX - 1)
-
 enum {
 	IORING_RSRC_FILE		= 0,
 	IORING_RSRC_BUFFER		= 1,

From 954b8915ff86353037d4246c7129d807a75f898b Mon Sep 17 00:00:00 2001
From: Eddie James <eajames@linux.ibm.com>
Date: Thu, 13 Feb 2025 16:57:46 -0600
Subject: [PATCH 0369/1173] MAINTAINERS: change maintainer for FSI

Due to job transitions, both Joel and Jeremy can no longer maintain
the FSI subsystem. I will take over.
I also replaced Alistair with Ninad as a reviewer, as Alistair doesn't
have access to hardware and hasn't been active.
I also removed the link to Joel's FSI tree as he won't be maintaining
it.

Signed-off-by: Eddie James <eajames@linux.ibm.com>
Acked-by: Jeremy Kerr <jk@ozlabs.org>
Link: https://lore.kernel.org/r/20250213225746.2159118-1-eajames@linux.ibm.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 MAINTAINERS | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 25c86f47353de..f6026443526b5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9439,14 +9439,11 @@ F:	include/linux/fscrypt.h
 F:	include/uapi/linux/fscrypt.h
 
 FSI SUBSYSTEM
-M:	Jeremy Kerr <jk@ozlabs.org>
-M:	Joel Stanley <joel@jms.id.au>
-R:	Alistar Popple <alistair@popple.id.au>
-R:	Eddie James <eajames@linux.ibm.com>
+M:	Eddie James <eajames@linux.ibm.com>
+R:	Ninad Palsule <ninad@linux.ibm.com>
 L:	linux-fsi@lists.ozlabs.org
 S:	Supported
 Q:	http://patchwork.ozlabs.org/project/linux-fsi/list/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/joel/fsi.git
 F:	drivers/fsi/
 F:	include/linux/fsi*.h
 F:	include/trace/events/fsi*.h

From c84e125fff2615b4d9c259e762596134eddd2f27 Mon Sep 17 00:00:00 2001
From: Vasiliy Kovalev <kovalev@altlinux.org>
Date: Sat, 15 Feb 2025 00:51:48 +0300
Subject: [PATCH 0370/1173] ovl: fix UAF in ovl_dentry_update_reval by moving
 dput() in ovl_link_up

The issue was caused by dput(upper) being called before
ovl_dentry_update_reval(), while upper->d_flags was still
accessed in ovl_dentry_remote().

Move dput(upper) after its last use to prevent use-after-free.

BUG: KASAN: slab-use-after-free in ovl_dentry_remote fs/overlayfs/util.c:162 [inline]
BUG: KASAN: slab-use-after-free in ovl_dentry_update_reval+0xd2/0xf0 fs/overlayfs/util.c:167

Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:88 [inline]
 dump_stack_lvl+0x116/0x1f0 lib/dump_stack.c:114
 print_address_description mm/kasan/report.c:377 [inline]
 print_report+0xc3/0x620 mm/kasan/report.c:488
 kasan_report+0xd9/0x110 mm/kasan/report.c:601
 ovl_dentry_remote fs/overlayfs/util.c:162 [inline]
 ovl_dentry_update_reval+0xd2/0xf0 fs/overlayfs/util.c:167
 ovl_link_up fs/overlayfs/copy_up.c:610 [inline]
 ovl_copy_up_one+0x2105/0x3490 fs/overlayfs/copy_up.c:1170
 ovl_copy_up_flags+0x18d/0x200 fs/overlayfs/copy_up.c:1223
 ovl_rename+0x39e/0x18c0 fs/overlayfs/dir.c:1136
 vfs_rename+0xf84/0x20a0 fs/namei.c:4893
...
 </TASK>

Fixes: b07d5cc93e1b ("ovl: update of dentry revalidate flags after copy up")
Reported-by: syzbot+316db8a1191938280eb6@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=316db8a1191938280eb6
Signed-off-by: Vasiliy Kovalev <kovalev@altlinux.org>
Link: https://lore.kernel.org/r/20250214215148.761147-1-kovalev@altlinux.org
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/overlayfs/copy_up.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 0c28e5fa34077..d7310fcf38881 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -618,7 +618,6 @@ static int ovl_link_up(struct ovl_copy_up_ctx *c)
 	err = PTR_ERR(upper);
 	if (!IS_ERR(upper)) {
 		err = ovl_do_link(ofs, ovl_dentry_upper(c->dentry), udir, upper);
-		dput(upper);
 
 		if (!err) {
 			/* Restore timestamps on parent (best effort) */
@@ -626,6 +625,7 @@ static int ovl_link_up(struct ovl_copy_up_ctx *c)
 			ovl_dentry_set_upper_alias(c->dentry);
 			ovl_dentry_update_reval(c->dentry, upper);
 		}
+		dput(upper);
 	}
 	inode_unlock(udir);
 	if (err)

From 838c17fd077e611b12c78feb0feee1b30ed09b63 Mon Sep 17 00:00:00 2001
From: Su Hui <suhui@nfschina.com>
Date: Tue, 11 Feb 2025 09:53:55 +0800
Subject: [PATCH 0371/1173] accel/amdxdna: Add missing include linux/slab.h
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When compiling without CONFIG_IA32_EMULATION, there can be some errors:

drivers/accel/amdxdna/amdxdna_mailbox.c: In function ‘mailbox_release_msg’:
drivers/accel/amdxdna/amdxdna_mailbox.c:197:2: error: implicit declaration
of function ‘kfree’.
  197 |  kfree(mb_msg);
      |  ^~~~~
drivers/accel/amdxdna/amdxdna_mailbox.c: In function ‘xdna_mailbox_send_msg’:
drivers/accel/amdxdna/amdxdna_mailbox.c:418:11: error:implicit declaration
of function ‘kzalloc’.
  418 |  mb_msg = kzalloc(sizeof(*mb_msg) + pkg_size, GFP_KERNEL);
      |           ^~~~~~~

Add the missing include.

Fixes: b87f920b9344 ("accel/amdxdna: Support hardware mailbox")
Signed-off-by: Su Hui <suhui@nfschina.com>
Reviewed-by: Lizhi Hou <lizhi.hou@amd.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250211015354.3388171-1-suhui@nfschina.com
---
 drivers/accel/amdxdna/amdxdna_mailbox.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/accel/amdxdna/amdxdna_mailbox.c b/drivers/accel/amdxdna/amdxdna_mailbox.c
index 814b16bb1953f..e5301fac13971 100644
--- a/drivers/accel/amdxdna/amdxdna_mailbox.c
+++ b/drivers/accel/amdxdna/amdxdna_mailbox.c
@@ -8,6 +8,7 @@
 #include <linux/bitfield.h>
 #include <linux/interrupt.h>
 #include <linux/iopoll.h>
+#include <linux/slab.h>
 #include <linux/xarray.h>
 
 #define CREATE_TRACE_POINTS

From b9275eabe31e6679ae12c46a4a0a18d622db4570 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Tue, 18 Feb 2025 00:38:27 +0200
Subject: [PATCH 0372/1173] drm/i915/dp: Fix error handling during 128b/132b
 link training

At the end of a 128b/132b link training sequence, the HW expects the
transcoder training pattern to be set to TPS2 and from that to normal
mode (disabling the training pattern). Transitioning from TPS1 directly
to normal mode leaves the transcoder in a stuck state, resulting in
page-flip timeouts later in the modeset sequence.

Atm, in case of a failure during link training, the transcoder may be
still set to output the TPS1 pattern. Later the transcoder is then set
from TPS1 directly to normal mode in intel_dp_stop_link_train(), leading
to modeset failures later as described above. Fix this by setting the
training patter to TPS2, if the link training failed at any point.

The clue in the specification about the above HW behavior is the
explicit mention that TPS2 must be set after the link training sequence
(and there isn't a similar requirement specified for the 8b/10b link
training), see the Bspec links below.

v2: Add bspec aspect/link to the commit log. (Jani)

Bspec: 54128, 65448, 68849
Cc: stable@vger.kernel.org # v5.18+
Cc: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Acked-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250217223828.1166093-2-imre.deak@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
(cherry picked from commit 8b4bbaf8ddc1f68f3ee96a706f65fdb1bcd9d355)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 .../gpu/drm/i915/display/intel_dp_link_training.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
index 8b1977cfec503..6696a32cdd3e6 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
@@ -1563,7 +1563,7 @@ intel_dp_128b132b_link_train(struct intel_dp *intel_dp,
 
 	if (wait_for(intel_dp_128b132b_intra_hop(intel_dp, crtc_state) == 0, 500)) {
 		lt_err(intel_dp, DP_PHY_DPRX, "128b/132b intra-hop not clear\n");
-		return false;
+		goto out;
 	}
 
 	if (intel_dp_128b132b_lane_eq(intel_dp, crtc_state) &&
@@ -1575,6 +1575,19 @@ intel_dp_128b132b_link_train(struct intel_dp *intel_dp,
 	       passed ? "passed" : "failed",
 	       crtc_state->port_clock, crtc_state->lane_count);
 
+out:
+	/*
+	 * Ensure that the training pattern does get set to TPS2 even in case
+	 * of a failure, as is the case at the end of a passing link training
+	 * and what is expected by the transcoder. Leaving TPS1 set (and
+	 * disabling the link train mode in DP_TP_CTL later from TPS1 directly)
+	 * would result in a stuck transcoder HW state and flip-done timeouts
+	 * later in the modeset sequence.
+	 */
+	if (!passed)
+		intel_dp_program_link_training_pattern(intel_dp, crtc_state,
+						       DP_PHY_DPRX, DP_TRAINING_PATTERN_2);
+
 	return passed;
 }
 

From 8058b49bf6fff777bf3f47309c7b15dbef2191af Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Tue, 18 Feb 2025 00:38:28 +0200
Subject: [PATCH 0373/1173] drm/i915/dp: Fix disabling the transcoder function
 in 128b/132b mode

During disabling the transcoder in DP 128b/132b mode (both in case of an
MST master transcoder and in case of SST) the transcoder function must
be first disabled without changing any other field in the register (in
particular leaving the DDI port and mode select fields unchanged) and
clearing the DDI port and mode select fields separately, later during
the disabling sequences. Fix the sequence accordingly.

Bspec: 54128, 65448, 68849
Cc: Jani Nikula <jani.nikula@intel.com>
Fixes: 79a6734cd56e ("drm/i915/ddi: disable trancoder port select for 128b/132b SST")
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250217223828.1166093-3-imre.deak@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
(cherry picked from commit 2ed653c7b843db0670136330480842d76cb65cd8)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/display/intel_ddi.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 2b9240ab547d8..18c66992aa1d8 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -658,7 +658,6 @@ void intel_ddi_disable_transcoder_func(const struct intel_crtc_state *crtc_state
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
-	bool is_mst = intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST);
 	u32 ctl;
 
 	if (DISPLAY_VER(dev_priv) >= 11)
@@ -678,8 +677,7 @@ void intel_ddi_disable_transcoder_func(const struct intel_crtc_state *crtc_state
 			 TRANS_DDI_PORT_SYNC_MASTER_SELECT_MASK);
 
 	if (DISPLAY_VER(dev_priv) >= 12) {
-		if (!intel_dp_mst_is_master_trans(crtc_state) ||
-		    (!is_mst && intel_dp_is_uhbr(crtc_state))) {
+		if (!intel_dp_mst_is_master_trans(crtc_state)) {
 			ctl &= ~(TGL_TRANS_DDI_PORT_MASK |
 				 TRANS_DDI_MODE_SELECT_MASK);
 		}
@@ -3134,7 +3132,7 @@ static void intel_ddi_post_disable_dp(struct intel_atomic_state *state,
 	intel_dp_set_power(intel_dp, DP_SET_POWER_D3);
 
 	if (DISPLAY_VER(dev_priv) >= 12) {
-		if (is_mst) {
+		if (is_mst || intel_dp_is_uhbr(old_crtc_state)) {
 			enum transcoder cpu_transcoder = old_crtc_state->cpu_transcoder;
 
 			intel_de_rmw(dev_priv,

From 67b0025d19f99fb9fbb8b62e6975553c183f3a16 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Wed, 19 Feb 2025 01:33:37 +0000
Subject: [PATCH 0374/1173] io_uring/rw: forbid multishot async reads

At the moment we can't sanely handle queuing an async request from a
multishot context, so disable them. It shouldn't matter as pollable
files / socekts don't normally do async.

Patching it in __io_read() is not the cleanest way, but it's simpler
than other options, so let's fix it there and clean up on top.

Cc: stable@vger.kernel.org
Reported-by: chase xd <sl1589472800@gmail.com>
Fixes: fc68fcda04910 ("io_uring/rw: add support for IORING_OP_READ_MULTISHOT")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/7d51732c125159d17db4fe16f51ec41b936973f8.1739919038.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/rw.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/io_uring/rw.c b/io_uring/rw.c
index 7aa1e4c9f64a3..e8efd97fdee5b 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -880,7 +880,15 @@ static int __io_read(struct io_kiocb *req, unsigned int issue_flags)
 	if (unlikely(ret))
 		return ret;
 
-	ret = io_iter_do_read(rw, &io->iter);
+	if (unlikely(req->opcode == IORING_OP_READ_MULTISHOT)) {
+		void *cb_copy = rw->kiocb.ki_complete;
+
+		rw->kiocb.ki_complete = NULL;
+		ret = io_iter_do_read(rw, &io->iter);
+		rw->kiocb.ki_complete = cb_copy;
+	} else {
+		ret = io_iter_do_read(rw, &io->iter);
+	}
 
 	/*
 	 * Some file systems like to return -EOPNOTSUPP for an IOCB_NOWAIT
@@ -904,7 +912,8 @@ static int __io_read(struct io_kiocb *req, unsigned int issue_flags)
 	} else if (ret == -EIOCBQUEUED) {
 		return IOU_ISSUE_SKIP_COMPLETE;
 	} else if (ret == req->cqe.res || ret <= 0 || !force_nonblock ||
-		   (req->flags & REQ_F_NOWAIT) || !need_complete_io(req)) {
+		   (req->flags & REQ_F_NOWAIT) || !need_complete_io(req) ||
+		   (issue_flags & IO_URING_F_MULTISHOT)) {
 		/* read all, failed, already did sync or don't want to retry */
 		goto done;
 	}

From 4e43133c6f2319d3e205ea986c507b25d9b41e64 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Wed, 19 Feb 2025 01:33:38 +0000
Subject: [PATCH 0375/1173] io_uring/rw: don't directly use ki_complete

We want to avoid checking ->ki_complete directly in the io_uring
completion path. Fortunately we have only two callback the selection
of which depend on the ring constant flags, i.e. IOPOLL, so use that
to infer the function.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/4eb4bdab8cbcf5bc87083f7047edc81e920ab83c.1739919038.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/rw.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/io_uring/rw.c b/io_uring/rw.c
index e8efd97fdee5b..27ccc82d78436 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -563,8 +563,10 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res)
 	smp_store_release(&req->iopoll_completed, 1);
 }
 
-static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret)
+static inline void io_rw_done(struct io_kiocb *req, ssize_t ret)
 {
+	struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
+
 	/* IO was queued async, completion will happen later */
 	if (ret == -EIOCBQUEUED)
 		return;
@@ -586,8 +588,10 @@ static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret)
 		}
 	}
 
-	INDIRECT_CALL_2(kiocb->ki_complete, io_complete_rw_iopoll,
-			io_complete_rw, kiocb, ret);
+	if (req->ctx->flags & IORING_SETUP_IOPOLL)
+		io_complete_rw_iopoll(&rw->kiocb, ret);
+	else
+		io_complete_rw(&rw->kiocb, ret);
 }
 
 static int kiocb_done(struct io_kiocb *req, ssize_t ret,
@@ -598,7 +602,7 @@ static int kiocb_done(struct io_kiocb *req, ssize_t ret,
 
 	if (ret >= 0 && req->flags & REQ_F_CUR_POS)
 		req->file->f_pos = rw->kiocb.ki_pos;
-	if (ret >= 0 && (rw->kiocb.ki_complete == io_complete_rw)) {
+	if (ret >= 0 && !(req->ctx->flags & IORING_SETUP_IOPOLL)) {
 		__io_complete_rw_common(req, ret);
 		/*
 		 * Safe to call io_end from here as we're inline
@@ -609,7 +613,7 @@ static int kiocb_done(struct io_kiocb *req, ssize_t ret,
 		io_req_rw_cleanup(req, issue_flags);
 		return IOU_OK;
 	} else {
-		io_rw_done(&rw->kiocb, ret);
+		io_rw_done(req, ret);
 	}
 
 	return IOU_ISSUE_SKIP_COMPLETE;

From 74f3e875268f1ce2dd01029c29560263212077df Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Wed, 19 Feb 2025 01:33:39 +0000
Subject: [PATCH 0376/1173] io_uring/rw: move ki_complete init into prep

Initialise ki_complete during request prep stage, we'll depend on it not
being reset during issue in the following patch.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/817624086bd5f0448b08c80623399919fda82f34.1739919038.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/rw.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/io_uring/rw.c b/io_uring/rw.c
index 27ccc82d78436..d162565053892 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -23,6 +23,9 @@
 #include "poll.h"
 #include "rw.h"
 
+static void io_complete_rw(struct kiocb *kiocb, long res);
+static void io_complete_rw_iopoll(struct kiocb *kiocb, long res);
+
 struct io_rw {
 	/* NOTE: kiocb has the file as the first member, so don't do it here */
 	struct kiocb			kiocb;
@@ -289,6 +292,11 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 	rw->kiocb.dio_complete = NULL;
 	rw->kiocb.ki_flags = 0;
 
+	if (req->ctx->flags & IORING_SETUP_IOPOLL)
+		rw->kiocb.ki_complete = io_complete_rw_iopoll;
+	else
+		rw->kiocb.ki_complete = io_complete_rw;
+
 	rw->addr = READ_ONCE(sqe->addr);
 	rw->len = READ_ONCE(sqe->len);
 	rw->flags = READ_ONCE(sqe->rw_flags);
@@ -817,10 +825,8 @@ static int io_rw_init_file(struct io_kiocb *req, fmode_t mode, int rw_type)
 	if (ctx->flags & IORING_SETUP_IOPOLL) {
 		if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll)
 			return -EOPNOTSUPP;
-
 		kiocb->private = NULL;
 		kiocb->ki_flags |= IOCB_HIPRI;
-		kiocb->ki_complete = io_complete_rw_iopoll;
 		req->iopoll_completed = 0;
 		if (ctx->flags & IORING_SETUP_HYBRID_IOPOLL) {
 			/* make sure every req only blocks once*/
@@ -830,7 +836,6 @@ static int io_rw_init_file(struct io_kiocb *req, fmode_t mode, int rw_type)
 	} else {
 		if (kiocb->ki_flags & IOCB_HIPRI)
 			return -EINVAL;
-		kiocb->ki_complete = io_complete_rw;
 	}
 
 	if (req->flags & REQ_F_HAS_METADATA) {

From 4614de748e78a295ee9b1f54ca87280b101fbdf0 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Wed, 19 Feb 2025 01:33:40 +0000
Subject: [PATCH 0377/1173] io_uring/rw: clean up mshot forced sync mode

Move code forcing synchronous execution of multishot read requests out
a more generic __io_read().

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/4ad7b928c776d1ad59addb9fff64ef2d1fc474d5.1739919038.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/rw.c | 12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/io_uring/rw.c b/io_uring/rw.c
index d162565053892..9edc6baebd01c 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -889,15 +889,7 @@ static int __io_read(struct io_kiocb *req, unsigned int issue_flags)
 	if (unlikely(ret))
 		return ret;
 
-	if (unlikely(req->opcode == IORING_OP_READ_MULTISHOT)) {
-		void *cb_copy = rw->kiocb.ki_complete;
-
-		rw->kiocb.ki_complete = NULL;
-		ret = io_iter_do_read(rw, &io->iter);
-		rw->kiocb.ki_complete = cb_copy;
-	} else {
-		ret = io_iter_do_read(rw, &io->iter);
-	}
+	ret = io_iter_do_read(rw, &io->iter);
 
 	/*
 	 * Some file systems like to return -EOPNOTSUPP for an IOCB_NOWAIT
@@ -995,6 +987,8 @@ int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags)
 	if (!io_file_can_poll(req))
 		return -EBADFD;
 
+	/* make it sync, multishot doesn't support async execution */
+	rw->kiocb.ki_complete = NULL;
 	ret = __io_read(req, issue_flags);
 
 	/*

From fcf857ee1958e9247298251f7615d0c76f1e9b38 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Sat, 1 Feb 2025 14:59:02 -0500
Subject: [PATCH 0378/1173] NFS: O_DIRECT writes must check and adjust the file
 length

While it is uncommon for delegations to be held while O_DIRECT writes
are in progress, it is possible. The xfstests generic/647 and
generic/729 both end up triggering that state, and end up failing due to
the fact that the file size is not adjusted.

Reported-by: Chuck Lever <chuck.lever@oracle.com>
Link: https://bugzilla.kernel.org/show_bug.cgi?id=219738
Cc: stable@vger.kernel.org
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>
---
 fs/nfs/direct.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index f45beea92d034..40e13c9a2873f 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -130,6 +130,20 @@ static void nfs_direct_truncate_request(struct nfs_direct_req *dreq,
 		dreq->count = req_start;
 }
 
+static void nfs_direct_file_adjust_size_locked(struct inode *inode,
+					       loff_t offset, size_t count)
+{
+	loff_t newsize = offset + (loff_t)count;
+	loff_t oldsize = i_size_read(inode);
+
+	if (newsize > oldsize) {
+		i_size_write(inode, newsize);
+		NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_SIZE;
+		trace_nfs_size_grow(inode, newsize);
+		nfs_inc_stats(inode, NFSIOS_EXTENDWRITE);
+	}
+}
+
 /**
  * nfs_swap_rw - NFS address space operation for swap I/O
  * @iocb: target I/O control block
@@ -741,6 +755,7 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
 	struct nfs_direct_req *dreq = hdr->dreq;
 	struct nfs_commit_info cinfo;
 	struct nfs_page *req = nfs_list_entry(hdr->pages.next);
+	struct inode *inode = dreq->inode;
 	int flags = NFS_ODIRECT_DONE;
 
 	trace_nfs_direct_write_completion(dreq);
@@ -762,6 +777,10 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
 	}
 	spin_unlock(&dreq->lock);
 
+	spin_lock(&inode->i_lock);
+	nfs_direct_file_adjust_size_locked(inode, dreq->io_start, dreq->count);
+	spin_unlock(&inode->i_lock);
+
 	while (!list_empty(&hdr->pages)) {
 
 		req = nfs_list_entry(hdr->pages.next);

From 88025c67fe3c025a0123bc7af50535b97f7af89a Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Sat, 1 Feb 2025 14:59:03 -0500
Subject: [PATCH 0379/1173] NFS: Adjust delegated timestamps for O_DIRECT reads
 and writes

Adjust the timestamps if O_DIRECT is being combined with attribute
delegations.

Fixes: e12912d94137 ("NFSv4: Add support for delegated atime and mtime attributes")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>
---
 fs/nfs/direct.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 40e13c9a2873f..f32f8d7c9122b 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -56,6 +56,7 @@
 #include <linux/uaccess.h>
 #include <linux/atomic.h>
 
+#include "delegation.h"
 #include "internal.h"
 #include "iostat.h"
 #include "pnfs.h"
@@ -286,6 +287,8 @@ static void nfs_direct_read_completion(struct nfs_pgio_header *hdr)
 	nfs_direct_count_bytes(dreq, hdr);
 	spin_unlock(&dreq->lock);
 
+	nfs_update_delegated_atime(dreq->inode);
+
 	while (!list_empty(&hdr->pages)) {
 		struct nfs_page *req = nfs_list_entry(hdr->pages.next);
 		struct page *page = req->wb_page;
@@ -779,6 +782,7 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
 
 	spin_lock(&inode->i_lock);
 	nfs_direct_file_adjust_size_locked(inode, dreq->io_start, dreq->count);
+	nfs_update_delegated_mtime_locked(dreq->inode);
 	spin_unlock(&inode->i_lock);
 
 	while (!list_empty(&hdr->pages)) {

From 5bbd6e863b15a85221e49b9bdb2d5d8f0bb91f3d Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Sat, 1 Feb 2025 15:00:02 -0500
Subject: [PATCH 0380/1173] SUNRPC: Prevent looping due to rpc_signal_task()
 races

If rpc_signal_task() is called while a task is in an rpc_call_done()
callback function, and the latter calls rpc_restart_call(), the task can
end up looping due to the RPC_TASK_SIGNALLED flag being set without the
tk_rpc_status being set.
Removing the redundant mechanism for signalling the task fixes the
looping behaviour.

Reported-by: Li Lingfeng <lilingfeng3@huawei.com>
Fixes: 39494194f93b ("SUNRPC: Fix races with rpc_killall_tasks()")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>
---
 include/linux/sunrpc/sched.h  | 3 +--
 include/trace/events/sunrpc.h | 3 +--
 net/sunrpc/sched.c            | 2 --
 3 files changed, 2 insertions(+), 6 deletions(-)

diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index fec1e8a1570c3..eac57914dcf32 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -158,7 +158,6 @@ enum {
 	RPC_TASK_NEED_XMIT,
 	RPC_TASK_NEED_RECV,
 	RPC_TASK_MSG_PIN_WAIT,
-	RPC_TASK_SIGNALLED,
 };
 
 #define rpc_test_and_set_running(t) \
@@ -171,7 +170,7 @@ enum {
 
 #define RPC_IS_ACTIVATED(t)	test_bit(RPC_TASK_ACTIVE, &(t)->tk_runstate)
 
-#define RPC_SIGNALLED(t)	test_bit(RPC_TASK_SIGNALLED, &(t)->tk_runstate)
+#define RPC_SIGNALLED(t)	(READ_ONCE(task->tk_rpc_status) == -ERESTARTSYS)
 
 /*
  * Task priorities.
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index b13dc275ef4a7..851841336ee65 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -360,8 +360,7 @@ TRACE_EVENT(rpc_request,
 		{ (1UL << RPC_TASK_ACTIVE), "ACTIVE" },			\
 		{ (1UL << RPC_TASK_NEED_XMIT), "NEED_XMIT" },		\
 		{ (1UL << RPC_TASK_NEED_RECV), "NEED_RECV" },		\
-		{ (1UL << RPC_TASK_MSG_PIN_WAIT), "MSG_PIN_WAIT" },	\
-		{ (1UL << RPC_TASK_SIGNALLED), "SIGNALLED" })
+		{ (1UL << RPC_TASK_MSG_PIN_WAIT), "MSG_PIN_WAIT" })
 
 DECLARE_EVENT_CLASS(rpc_task_running,
 
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index cef623ea15060..9b45fbdc90cab 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -864,8 +864,6 @@ void rpc_signal_task(struct rpc_task *task)
 	if (!rpc_task_set_rpc_status(task, -ERESTARTSYS))
 		return;
 	trace_rpc_task_signalled(task, task->tk_action);
-	set_bit(RPC_TASK_SIGNALLED, &task->tk_runstate);
-	smp_mb__after_atomic();
 	queue = READ_ONCE(task->tk_waitqueue);
 	if (queue)
 		rpc_wake_up_queued_task(queue, task);

From 8f8df955f078e1a023ee55161935000a67651f38 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Sat, 1 Feb 2025 15:00:09 -0500
Subject: [PATCH 0381/1173] NFSv4: Fix a deadlock when recovering state on a
 sillyrenamed file

If the file is sillyrenamed, and slated for delete on close, it is
possible for a server reboot to triggeer an open reclaim, with can again
race with the application call to close(). When that happens, the call
to put_nfs_open_context() can trigger a synchronous delegreturn call
which deadlocks because it is not marked as privileged.

Instead, ensure that the call to nfs4_inode_return_delegation_on_close()
catches the delegreturn, and schedules it asynchronously.

Reported-by: Li Lingfeng <lilingfeng3@huawei.com>
Fixes: adb4b42d19ae ("Return the delegation when deleting sillyrenamed files")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>
---
 fs/nfs/delegation.c | 37 +++++++++++++++++++++++++++++++++++++
 fs/nfs/delegation.h |  1 +
 fs/nfs/nfs4proc.c   |  3 +++
 3 files changed, 41 insertions(+)

diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 035ba52742a50..4db912f562305 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -780,6 +780,43 @@ int nfs4_inode_return_delegation(struct inode *inode)
 	return 0;
 }
 
+/**
+ * nfs4_inode_set_return_delegation_on_close - asynchronously return a delegation
+ * @inode: inode to process
+ *
+ * This routine is called to request that the delegation be returned as soon
+ * as the file is closed. If the file is already closed, the delegation is
+ * immediately returned.
+ */
+void nfs4_inode_set_return_delegation_on_close(struct inode *inode)
+{
+	struct nfs_delegation *delegation;
+	struct nfs_delegation *ret = NULL;
+
+	if (!inode)
+		return;
+	rcu_read_lock();
+	delegation = nfs4_get_valid_delegation(inode);
+	if (!delegation)
+		goto out;
+	spin_lock(&delegation->lock);
+	if (!delegation->inode)
+		goto out_unlock;
+	if (list_empty(&NFS_I(inode)->open_files) &&
+	    !test_and_set_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) {
+		/* Refcount matched in nfs_end_delegation_return() */
+		ret = nfs_get_delegation(delegation);
+	} else
+		set_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags);
+out_unlock:
+	spin_unlock(&delegation->lock);
+	if (ret)
+		nfs_clear_verifier_delegated(inode);
+out:
+	rcu_read_unlock();
+	nfs_end_delegation_return(inode, ret, 0);
+}
+
 /**
  * nfs4_inode_return_delegation_on_close - asynchronously return a delegation
  * @inode: inode to process
diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h
index 71524d34ed207..8ff5ab9c5c256 100644
--- a/fs/nfs/delegation.h
+++ b/fs/nfs/delegation.h
@@ -49,6 +49,7 @@ void nfs_inode_reclaim_delegation(struct inode *inode, const struct cred *cred,
 				  unsigned long pagemod_limit, u32 deleg_type);
 int nfs4_inode_return_delegation(struct inode *inode);
 void nfs4_inode_return_delegation_on_close(struct inode *inode);
+void nfs4_inode_set_return_delegation_on_close(struct inode *inode);
 int nfs_async_inode_return_delegation(struct inode *inode, const nfs4_stateid *stateid);
 void nfs_inode_evict_delegation(struct inode *inode);
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index df9669d4ded7f..c25ecdb76d304 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -3906,8 +3906,11 @@ nfs4_atomic_open(struct inode *dir, struct nfs_open_context *ctx,
 
 static void nfs4_close_context(struct nfs_open_context *ctx, int is_sync)
 {
+	struct dentry *dentry = ctx->dentry;
 	if (ctx->state == NULL)
 		return;
+	if (dentry->d_flags & DCACHE_NFSFS_RENAMED)
+		nfs4_inode_set_return_delegation_on_close(d_inode(dentry));
 	if (is_sync)
 		nfs4_close_sync(ctx->state, _nfs4_ctx_to_openmode(ctx));
 	else

From 7a2f6f7687c5f7083a35317cddec5ad9fa491443 Mon Sep 17 00:00:00 2001
From: Benjamin Coddington <bcodding@redhat.com>
Date: Tue, 11 Feb 2025 12:31:57 -0500
Subject: [PATCH 0382/1173] SUNRPC: Handle -ETIMEDOUT return from tlshd

If the TLS handshake attempt returns -ETIMEDOUT, we currently translate
that error into -EACCES.  This becomes problematic for cases where the RPC
layer is attempting to re-connect in paths that don't resonably handle
-EACCES, for example: writeback.  The RPC layer can handle -ETIMEDOUT quite
well, however - so if the handshake returns this error let's just pass it
along.

Fixes: 75eb6af7acdf ("SUNRPC: Add a TCP-with-TLS RPC transport class")
Signed-off-by: Benjamin Coddington <bcodding@redhat.com>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>
---
 net/sunrpc/xprtsock.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index c60936d8cef71..6b80b2aaf7639 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -2581,7 +2581,15 @@ static void xs_tls_handshake_done(void *data, int status, key_serial_t peerid)
 	struct sock_xprt *lower_transport =
 				container_of(lower_xprt, struct sock_xprt, xprt);
 
-	lower_transport->xprt_err = status ? -EACCES : 0;
+	switch (status) {
+	case 0:
+	case -EACCES:
+	case -ETIMEDOUT:
+		lower_transport->xprt_err = status;
+		break;
+	default:
+		lower_transport->xprt_err = -EACCES;
+	}
 	complete(&lower_transport->handshake_done);
 	xprt_put(lower_xprt);
 }

From 102c51c50db88aedd00a318b7708ad60dbec2e95 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Fri, 14 Feb 2025 13:37:24 +0000
Subject: [PATCH 0383/1173] KVM: arm64: Fix tcr_el2 initialisation in hVHE mode

When not running in VHE mode, cpu_prepare_hyp_mode() computes the value
of TCR_EL2 using the host's TCR_EL1 settings as a starting point. For
nVHE, this amounts to masking out everything apart from the TG0, SH0,
ORGN0, IRGN0 and T0SZ fields before setting the RES1 bits, shifting the
IPS field down to the PS field and setting DS if LPA2 is enabled.

Unfortunately, for hVHE, things go slightly wonky: EPD1 is correctly set
to disable walks via TTBR1_EL2 but then the T1SZ and IPS fields are
corrupted when we mistakenly attempt to initialise the PS and DS fields
in their E2H=0 positions. Furthermore, many fields are retained from
TCR_EL1 which should not be propagated to TCR_EL2. Notably, this means
we can end up with A1 set despite not initialising TTBR1_EL2 at all.
This has been shown to cause unexpected translation faults at EL2 with
pKVM due to TLB invalidation not taking effect when running with a
non-zero ASID.

Fix the TCR_EL2 initialisation code to set PS and DS only when E2H=0,
masking out HD, HA and A1 when E2H=1.

Cc: Marc Zyngier <maz@kernel.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Fixes: ad744e8cb346 ("arm64: Allow arm64_sw.hvhe on command line")
Signed-off-by: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20250214133724.13179-1-will@kernel.org
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_arm.h |  2 +-
 arch/arm64/kvm/arm.c             | 15 +++++++--------
 2 files changed, 8 insertions(+), 9 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 8d94a6c0ed5c4..c2417a424b98d 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -119,7 +119,7 @@
 #define TCR_EL2_IRGN0_MASK	TCR_IRGN0_MASK
 #define TCR_EL2_T0SZ_MASK	0x3f
 #define TCR_EL2_MASK	(TCR_EL2_TG0_MASK | TCR_EL2_SH0_MASK | \
-			 TCR_EL2_ORGN0_MASK | TCR_EL2_IRGN0_MASK | TCR_EL2_T0SZ_MASK)
+			 TCR_EL2_ORGN0_MASK | TCR_EL2_IRGN0_MASK)
 
 /* VTCR_EL2 Registers bits */
 #define VTCR_EL2_DS		TCR_EL2_DS
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index b8e55a441282f..bc7a37cea2420 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -1980,7 +1980,7 @@ static int kvm_init_vector_slots(void)
 static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits)
 {
 	struct kvm_nvhe_init_params *params = per_cpu_ptr_nvhe_sym(kvm_init_params, cpu);
-	unsigned long tcr, ips;
+	unsigned long tcr;
 
 	/*
 	 * Calculate the raw per-cpu offset without a translation from the
@@ -1994,19 +1994,18 @@ static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits)
 	params->mair_el2 = read_sysreg(mair_el1);
 
 	tcr = read_sysreg(tcr_el1);
-	ips = FIELD_GET(TCR_IPS_MASK, tcr);
 	if (cpus_have_final_cap(ARM64_KVM_HVHE)) {
+		tcr &= ~(TCR_HD | TCR_HA | TCR_A1 | TCR_T0SZ_MASK);
 		tcr |= TCR_EPD1_MASK;
 	} else {
+		unsigned long ips = FIELD_GET(TCR_IPS_MASK, tcr);
+
 		tcr &= TCR_EL2_MASK;
-		tcr |= TCR_EL2_RES1;
+		tcr |= TCR_EL2_RES1 | FIELD_PREP(TCR_EL2_PS_MASK, ips);
+		if (lpa2_is_enabled())
+			tcr |= TCR_EL2_DS;
 	}
-	tcr &= ~TCR_T0SZ_MASK;
 	tcr |= TCR_T0SZ(hyp_va_bits);
-	tcr &= ~TCR_EL2_PS_MASK;
-	tcr |= FIELD_PREP(TCR_EL2_PS_MASK, ips);
-	if (lpa2_is_enabled())
-		tcr |= TCR_EL2_DS;
 	params->tcr_el2 = tcr;
 
 	params->pgd_pa = kvm_mmu_get_httbr();

From 3d8c6f26893d55fab218ad086719de1fc9bb86ba Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Mon, 10 Feb 2025 13:31:11 +0200
Subject: [PATCH 0384/1173] RDMA/mlx5: Fix implicit ODP hang on parent
 deregistration

Fix the destroy_unused_implicit_child_mr() to prevent hanging during
parent deregistration as of below [1].

Upon entering destroy_unused_implicit_child_mr(), the reference count
for the implicit MR parent is incremented using:
refcount_inc_not_zero().

A corresponding decrement must be performed if
free_implicit_child_mr_work() is not called.

The code has been updated to properly manage the reference count that
was incremented.

[1]
INFO: task python3:2157 blocked for more than 120 seconds.
Not tainted 6.12.0-rc7+ #1633
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
task:python3         state:D stack:0     pid:2157 tgid:2157  ppid:1685   flags:0x00000000
Call Trace:
<TASK>
__schedule+0x420/0xd30
schedule+0x47/0x130
__mlx5_ib_dereg_mr+0x379/0x5d0 [mlx5_ib]
? __pfx_autoremove_wake_function+0x10/0x10
ib_dereg_mr_user+0x5f/0x120 [ib_core]
? lock_release+0xc6/0x280
destroy_hw_idr_uobject+0x1d/0x60 [ib_uverbs]
uverbs_destroy_uobject+0x58/0x1d0 [ib_uverbs]
uobj_destroy+0x3f/0x70 [ib_uverbs]
ib_uverbs_cmd_verbs+0x3e4/0xbb0 [ib_uverbs]
? __pfx_uverbs_destroy_def_handler+0x10/0x10 [ib_uverbs]
? lock_acquire+0xc1/0x2f0
? ib_uverbs_ioctl+0xcb/0x170 [ib_uverbs]
? ib_uverbs_ioctl+0x116/0x170 [ib_uverbs]
? lock_release+0xc6/0x280
ib_uverbs_ioctl+0xe7/0x170 [ib_uverbs]
? ib_uverbs_ioctl+0xcb/0x170 [ib_uverbs]
 __x64_sys_ioctl+0x1b0/0xa70
? kmem_cache_free+0x221/0x400
do_syscall_64+0x6b/0x140
entry_SYSCALL_64_after_hwframe+0x76/0x7e
RIP: 0033:0x7f20f21f017b
RSP: 002b:00007ffcfc4a77c8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 00007ffcfc4a78d8 RCX: 00007f20f21f017b
RDX: 00007ffcfc4a78c0 RSI: 00000000c0181b01 RDI: 0000000000000003
RBP: 00007ffcfc4a78a0 R08: 000056147d125190 R09: 00007f20f1f14c60
R10: 0000000000000001 R11: 0000000000000246 R12: 00007ffcfc4a7890
R13: 000000000000001c R14: 000056147d100fc0 R15: 00007f20e365c9d0
</TASK>

Fixes: d3d930411ce3 ("RDMA/mlx5: Fix implicit ODP use after free")
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Reviewed-by: Artemy Kovalyov <artemyko@nvidia.com>
Link: https://patch.msgid.link/80f2fcd19952dfa7d9981d93fd6359b4471f8278.1739186929.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/mlx5/odp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index f1e23583e6c08..e77c9280c07e4 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -242,6 +242,7 @@ static void destroy_unused_implicit_child_mr(struct mlx5_ib_mr *mr)
 	if (__xa_cmpxchg(&imr->implicit_children, idx, mr, NULL, GFP_KERNEL) !=
 	    mr) {
 		xa_unlock(&imr->implicit_children);
+		mlx5r_deref_odp_mkey(&imr->mmkey);
 		return;
 	}
 

From c534ffda781f44a1c6ac25ef6e0e444da38ca8af Mon Sep 17 00:00:00 2001
From: Patrisious Haddad <phaddad@nvidia.com>
Date: Mon, 10 Feb 2025 13:32:39 +0200
Subject: [PATCH 0385/1173] RDMA/mlx5: Fix AH static rate parsing

Previously static rate wasn't translated according to our PRM but simply
used the 4 lower bytes.

Correctly translate static rate value passed in AH creation attribute
according to our PRM expected values.

In addition change 800GB mapping to zero, which is the PRM
specified value.

Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters")
Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Reviewed-by: Maor Gottlieb <maorg@nvidia.com>
Link: https://patch.msgid.link/18ef4cc5396caf80728341eb74738cd777596f60.1739187089.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/mlx5/ah.c | 3 ++-
 drivers/infiniband/hw/mlx5/qp.c | 6 +++---
 drivers/infiniband/hw/mlx5/qp.h | 1 +
 3 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/ah.c b/drivers/infiniband/hw/mlx5/ah.c
index 505bc47fd575d..99036afb3aef0 100644
--- a/drivers/infiniband/hw/mlx5/ah.c
+++ b/drivers/infiniband/hw/mlx5/ah.c
@@ -67,7 +67,8 @@ static void create_ib_ah(struct mlx5_ib_dev *dev, struct mlx5_ib_ah *ah,
 		ah->av.tclass = grh->traffic_class;
 	}
 
-	ah->av.stat_rate_sl = (rdma_ah_get_static_rate(ah_attr) << 4);
+	ah->av.stat_rate_sl =
+		(mlx5r_ib_rate(dev, rdma_ah_get_static_rate(ah_attr)) << 4);
 
 	if (ah_attr->type == RDMA_AH_ATTR_TYPE_ROCE) {
 		if (init_attr->xmit_slave)
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 08d22db8dca91..88724d15705d4 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -3447,11 +3447,11 @@ static int ib_to_mlx5_rate_map(u8 rate)
 	return 0;
 }
 
-static int ib_rate_to_mlx5(struct mlx5_ib_dev *dev, u8 rate)
+int mlx5r_ib_rate(struct mlx5_ib_dev *dev, u8 rate)
 {
 	u32 stat_rate_support;
 
-	if (rate == IB_RATE_PORT_CURRENT)
+	if (rate == IB_RATE_PORT_CURRENT || rate == IB_RATE_800_GBPS)
 		return 0;
 
 	if (rate < IB_RATE_2_5_GBPS || rate > IB_RATE_800_GBPS)
@@ -3596,7 +3596,7 @@ static int mlx5_set_path(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 		       sizeof(grh->dgid.raw));
 	}
 
-	err = ib_rate_to_mlx5(dev, rdma_ah_get_static_rate(ah));
+	err = mlx5r_ib_rate(dev, rdma_ah_get_static_rate(ah));
 	if (err < 0)
 		return err;
 	MLX5_SET(ads, path, stat_rate, err);
diff --git a/drivers/infiniband/hw/mlx5/qp.h b/drivers/infiniband/hw/mlx5/qp.h
index b6ee7c3ee1ca1..2530e7730635f 100644
--- a/drivers/infiniband/hw/mlx5/qp.h
+++ b/drivers/infiniband/hw/mlx5/qp.h
@@ -56,4 +56,5 @@ int mlx5_core_xrcd_dealloc(struct mlx5_ib_dev *dev, u32 xrcdn);
 int mlx5_ib_qp_set_counter(struct ib_qp *qp, struct rdma_counter *counter);
 int mlx5_ib_qp_event_init(void);
 void mlx5_ib_qp_event_cleanup(void);
+int mlx5r_ib_rate(struct mlx5_ib_dev *dev, u8 rate);
 #endif /* _MLX5_IB_QP_H */

From 4738d3d3e12d70a5067baba147daf57e57b77548 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 11 Feb 2025 20:50:13 +0200
Subject: [PATCH 0386/1173] intel_th: msu: Fix kernel-doc warnings

Correct function comments to prevent kernel-doc warnings
found when using "W=1".

msu.c:162: warning: Function parameter or struct member 'mbuf_priv' not described in 'msc'
msu.c:164: warning: Function parameter or struct member 'orig_addr' not described in 'msc'
msu.c:164: warning: Function parameter or struct member 'orig_sz' not described in 'msc'

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Link: https://lore.kernel.org/r/20250211185017.1759193-2-alexander.shishkin@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/hwtracing/intel_th/msu.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c
index 66123d684ac9e..492d8eba37ebc 100644
--- a/drivers/hwtracing/intel_th/msu.c
+++ b/drivers/hwtracing/intel_th/msu.c
@@ -108,7 +108,7 @@ struct msc_iter {
  * @reg_base:		register window base address
  * @thdev:		intel_th_device pointer
  * @mbuf:		MSU buffer, if assigned
- * @mbuf_priv		MSU buffer's private data, if @mbuf
+ * @mbuf_priv:		MSU buffer's private data, if @mbuf
  * @win_list:		list of windows in multiblock mode
  * @single_sgt:		single mode buffer
  * @cur_win:		current window
@@ -117,6 +117,8 @@ struct msc_iter {
  * @single_wrap:	single mode wrap occurred
  * @base:		buffer's base pointer
  * @base_addr:		buffer's base address
+ * @orig_addr:		MSC0 buffer's base address
+ * @orig_sz:		MSC0 buffer's size
  * @user_count:		number of users of the buffer
  * @mmap_count:		number of mappings
  * @buf_mutex:		mutex to serialize access to buffer-related bits

From 04190ec6d02aa8fee0f03189bb7762b44739c253 Mon Sep 17 00:00:00 2001
From: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Date: Tue, 11 Feb 2025 20:50:14 +0200
Subject: [PATCH 0387/1173] intel_th: msu: Fix less trivial kernel-doc warnings

Correct function comments to prevent kernel-doc warnings found when using
"W=1" that the drive-by fixers had trouble documenting and skipped over.

msu.c:168: warning: Function parameter or struct member 'msu_base' not described in 'msc'
msu.c:168: warning: Function parameter or struct member 'work' not described in 'msc'
msu.c:168: warning: Function parameter or struct member 'switch_on_unlock' not described in 'msc'
msu.c:168: warning: Function parameter or struct member 'iter_list' not described in 'msc'
msu.c:168: warning: Function parameter or struct member 'stop_on_full' not described in 'msc'
msu.c:168: warning: Function parameter or struct member 'do_irq' not described in 'msc'
msu.c:168: warning: Function parameter or struct member 'multi_is_broken' not described in 'msc'

Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20250211185017.1759193-3-alexander.shishkin@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/hwtracing/intel_th/msu.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c
index 492d8eba37ebc..bf99d79a41920 100644
--- a/drivers/hwtracing/intel_th/msu.c
+++ b/drivers/hwtracing/intel_th/msu.c
@@ -105,13 +105,16 @@ struct msc_iter {
 
 /**
  * struct msc - MSC device representation
- * @reg_base:		register window base address
+ * @reg_base:		register window base address for the entire MSU
+ * @msu_base:		register window base address for this MSC
  * @thdev:		intel_th_device pointer
  * @mbuf:		MSU buffer, if assigned
  * @mbuf_priv:		MSU buffer's private data, if @mbuf
+ * @work:		a work to stop the trace when the buffer is full
  * @win_list:		list of windows in multiblock mode
  * @single_sgt:		single mode buffer
  * @cur_win:		current window
+ * @switch_on_unlock:	window to switch to when it becomes available
  * @nr_pages:		total number of pages allocated for this buffer
  * @single_sz:		amount of data in single mode
  * @single_wrap:	single mode wrap occurred
@@ -122,8 +125,12 @@ struct msc_iter {
  * @user_count:		number of users of the buffer
  * @mmap_count:		number of mappings
  * @buf_mutex:		mutex to serialize access to buffer-related bits
+ * @iter_list:		list of open file descriptor iterators
+ * @stop_on_full:	stop the trace if the current window is full
  * @enabled:		MSC is enabled
  * @wrap:		wrapping is enabled
+ * @do_irq:		IRQ resource is available, handle interrupts
+ * @multi_is_broken:	multiblock mode enabled (not disabled by PCI drvdata)
  * @mode:		MSC operating mode
  * @burst_len:		write burst length
  * @index:		number of this MSC in the MSU

From b5edccae9f447a92d475267d94c33f4926963eec Mon Sep 17 00:00:00 2001
From: Pawel Chmielewski <pawel.chmielewski@intel.com>
Date: Tue, 11 Feb 2025 20:50:15 +0200
Subject: [PATCH 0388/1173] intel_th: pci: Add Arrow Lake support

Add support for the Trace Hub in Arrow Lake.

Signed-off-by: Pawel Chmielewski <pawel.chmielewski@intel.com>
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: stable@kernel.org
Link: https://lore.kernel.org/r/20250211185017.1759193-4-alexander.shishkin@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/hwtracing/intel_th/pci.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c
index e9d8d28e055f3..3e03ee788bb94 100644
--- a/drivers/hwtracing/intel_th/pci.c
+++ b/drivers/hwtracing/intel_th/pci.c
@@ -334,6 +334,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa824),
 		.driver_data = (kernel_ulong_t)&intel_th_2x,
 	},
+	{
+		/* Arrow Lake */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7724),
+		.driver_data = (kernel_ulong_t)&intel_th_2x,
+	},
 	{
 		/* Alder Lake CPU */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x466f),

From a70034d6c0d5f3cdee40bb00a578e17fd2ebe426 Mon Sep 17 00:00:00 2001
From: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Date: Tue, 11 Feb 2025 20:50:16 +0200
Subject: [PATCH 0389/1173] intel_th: pci: Add Panther Lake-H support

Add support for the Trace Hub in Panther Lake-H.

Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: stable@kernel.org
Link: https://lore.kernel.org/r/20250211185017.1759193-5-alexander.shishkin@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/hwtracing/intel_th/pci.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c
index 3e03ee788bb94..004e68286fd43 100644
--- a/drivers/hwtracing/intel_th/pci.c
+++ b/drivers/hwtracing/intel_th/pci.c
@@ -339,6 +339,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7724),
 		.driver_data = (kernel_ulong_t)&intel_th_2x,
 	},
+	{
+		/* Panther Lake-H */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe324),
+		.driver_data = (kernel_ulong_t)&intel_th_2x,
+	},
 	{
 		/* Alder Lake CPU */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x466f),

From 49114ff05770264ae233f50023fc64a719a9dcf9 Mon Sep 17 00:00:00 2001
From: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Date: Tue, 11 Feb 2025 20:50:17 +0200
Subject: [PATCH 0390/1173] intel_th: pci: Add Panther Lake-P/U support

Add support for the Trace Hub in Panther Lake-P/U.

Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: stable@kernel.org
Link: https://lore.kernel.org/r/20250211185017.1759193-6-alexander.shishkin@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/hwtracing/intel_th/pci.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c
index 004e68286fd43..e3def163d5cf7 100644
--- a/drivers/hwtracing/intel_th/pci.c
+++ b/drivers/hwtracing/intel_th/pci.c
@@ -344,6 +344,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe324),
 		.driver_data = (kernel_ulong_t)&intel_th_2x,
 	},
+	{
+		/* Panther Lake-P/U */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe424),
+		.driver_data = (kernel_ulong_t)&intel_th_2x,
+	},
 	{
 		/* Alder Lake CPU */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x466f),

From 78eb41f518f414378643ab022241df2a9dcd008b Mon Sep 17 00:00:00 2001
From: Luca Ceresoli <luca.ceresoli@bootlin.com>
Date: Thu, 13 Feb 2025 15:05:13 +0100
Subject: [PATCH 0391/1173] drivers: core: fix device leak in
 __fw_devlink_relax_cycles()

Commit bac3b10b78e5 ("driver core: fw_devlink: Stop trying to optimize
cycle detection logic") introduced a new struct device *con_dev and a
get_dev_from_fwnode() call to get it, but without adding a corresponding
put_device().

Closes: https://lore.kernel.org/all/20241204124826.2e055091@booty/
Fixes: bac3b10b78e5 ("driver core: fw_devlink: Stop trying to optimize cycle detection logic")
Cc: stable@vger.kernel.org
Reviewed-by: Saravana Kannan <saravanak@google.com>
Signed-off-by: Luca Ceresoli <luca.ceresoli@bootlin.com>
Link: https://lore.kernel.org/r/20250213-fix__fw_devlink_relax_cycles_missing_device_put-v2-1-8cd3b03e6a3f@bootlin.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/base/core.c b/drivers/base/core.c
index 5a1f051981149..2fde698430dff 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -2079,6 +2079,7 @@ static bool __fw_devlink_relax_cycles(struct fwnode_handle *con_handle,
 out:
 	sup_handle->flags &= ~FWNODE_FLAG_VISITED;
 	put_device(sup_dev);
+	put_device(con_dev);
 	put_device(par_dev);
 	return ret;
 }

From c783e1258f29c5caac9eea0aea6b172870f1baf8 Mon Sep 17 00:00:00 2001
From: Marek Szyprowski <m.szyprowski@samsung.com>
Date: Thu, 20 Feb 2025 13:03:14 +0100
Subject: [PATCH 0392/1173] usb: gadget: Fix setting self-powered state on
 suspend

cdev->config might be NULL, so check it before dereferencing.

CC: stable <stable@kernel.org>
Fixes: 40e89ff5750f ("usb: gadget: Set self-powered based on MaxPower and bmAttributes")
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20250220120314.3614330-1-m.szyprowski@samsung.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/composite.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index 1fb28bbf6c458..4bcf73bae7610 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -2616,7 +2616,8 @@ void composite_suspend(struct usb_gadget *gadget)
 
 	cdev->suspended = 1;
 
-	if (cdev->config->bmAttributes & USB_CONFIG_ATT_SELFPOWER)
+	if (cdev->config &&
+	    cdev->config->bmAttributes & USB_CONFIG_ATT_SELFPOWER)
 		usb_gadget_set_selfpowered(gadget);
 
 	usb_gadget_vbus_draw(gadget, 2);

From 96fa9ec477ff60bed87e1441fd43e003179f3253 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Wed, 19 Feb 2025 15:43:56 +0100
Subject: [PATCH 0393/1173] gpiolib: don't bail out if get_direction() fails in
 gpiochip_add_data()

Since commit 9d846b1aebbe ("gpiolib: check the return value of
gpio_chip::get_direction()") we check the return value of the
get_direction() callback as per its API contract. Some drivers have been
observed to fail to register now as they may call get_direction() in
gpiochip_add_data() in contexts where it has always silently failed.
Until we audit all drivers, replace the bail-out to a kernel log
warning.

Fixes: 9d846b1aebbe ("gpiolib: check the return value of gpio_chip::get_direction()")
Reported-by: Mark Brown <broonie@kernel.org>
Closes: https://lore.kernel.org/all/Z7VFB1nST6lbmBIo@finisterre.sirena.org.uk/
Reported-by: Marek Szyprowski <m.szyprowski@samsung.com>
Closes: https://lore.kernel.org/all/dfe03f88-407e-4ef1-ad30-42db53bbd4e4@samsung.com/
Tested-by: Mark Brown <broonie@kernel.org>
Reviewed-by: Mark Brown <broonie@kernel.org>
Tested-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20250219144356.258635-1-brgl@bgdev.pl
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpiolib.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 5529d8b65f6fb..fc19df5a64c2b 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1059,7 +1059,15 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data,
 		if (gc->get_direction && gpiochip_line_is_valid(gc, desc_index)) {
 			ret = gc->get_direction(gc, desc_index);
 			if (ret < 0)
-				goto err_cleanup_desc_srcu;
+				/*
+				 * FIXME: Bail-out here once all GPIO drivers
+				 * are updated to not return errors in
+				 * situations that can be considered normal
+				 * operation.
+				 */
+				dev_warn(&gdev->dev,
+					 "%s: get_direction failed: %d\n",
+					 __func__, ret);
 
 			assign_bit(FLAG_IS_OUT, &desc->flags, !ret);
 		} else {

From 91d44c1afc61a2fec37a9c7a3485368309391e0b Mon Sep 17 00:00:00 2001
From: Qiu-ji Chen <chenqiuji666@gmail.com>
Date: Sat, 18 Jan 2025 15:08:33 +0800
Subject: [PATCH 0394/1173] cdx: Fix possible UAF error in
 driver_override_show()

Fixed a possible UAF problem in driver_override_show() in drivers/cdx/cdx.c

This function driver_override_show() is part of DEVICE_ATTR_RW, which
includes both driver_override_show() and driver_override_store().
These functions can be executed concurrently in sysfs.

The driver_override_store() function uses driver_set_override() to
update the driver_override value, and driver_set_override() internally
locks the device (device_lock(dev)). If driver_override_show() reads
cdx_dev->driver_override without locking, it could potentially access
a freed pointer if driver_override_store() frees the string
concurrently. This could lead to printing a kernel address, which is a
security risk since DEVICE_ATTR can be read by all users.

Additionally, a similar pattern is used in drivers/amba/bus.c, as well
as many other bus drivers, where device_lock() is taken in the show
function, and it has been working without issues.

This potential bug was detected by our experimental static analysis
tool, which analyzes locking APIs and paired functions to identify
data races and atomicity violations.

Fixes: 1f86a00c1159 ("bus/fsl-mc: add support for 'driver_override' in the mc-bus")
Cc: stable <stable@kernel.org>
Signed-off-by: Qiu-ji Chen <chenqiuji666@gmail.com>
Link: https://lore.kernel.org/r/20250118070833.27201-1-chenqiuji666@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/cdx/cdx.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/cdx/cdx.c b/drivers/cdx/cdx.c
index c573ed2ee71a8..7811aa7340537 100644
--- a/drivers/cdx/cdx.c
+++ b/drivers/cdx/cdx.c
@@ -473,8 +473,12 @@ static ssize_t driver_override_show(struct device *dev,
 				    struct device_attribute *attr, char *buf)
 {
 	struct cdx_device *cdx_dev = to_cdx_device(dev);
+	ssize_t len;
 
-	return sysfs_emit(buf, "%s\n", cdx_dev->driver_override);
+	device_lock(dev);
+	len = sysfs_emit(buf, "%s\n", cdx_dev->driver_override);
+	device_unlock(dev);
+	return len;
 }
 static DEVICE_ATTR_RW(driver_override);
 

From 1c000dcaad2bef20189f3868207f515ef4b637ee Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 17 Feb 2025 14:26:48 +0530
Subject: [PATCH 0395/1173] irqchip/irq-msi-lib: Optionally set default
 irq_eoi()/irq_ack()

msi_lib_init_dev_msi_info() sets the default irq_eoi()/irq_ack() callbacks
unconditionally. This is correct for all existing users, but prevents the
IMSIC driver to be moved to the MSI library implementation.

Introduce chip_flags in struct msi_parent_ops, which instruct the library
to selectively set the callbacks depending on the flags, and update all
current users to set them.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250217085657.789309-3-apatel@ventanamicro.com
---
 drivers/irqchip/irq-gic-v2m.c               |  1 +
 drivers/irqchip/irq-gic-v3-its-msi-parent.c |  1 +
 drivers/irqchip/irq-gic-v3-mbi.c            |  1 +
 drivers/irqchip/irq-imx-mu-msi.c            |  1 +
 drivers/irqchip/irq-loongson-pch-msi.c      |  1 +
 drivers/irqchip/irq-msi-lib.c               | 11 ++++++-----
 drivers/irqchip/irq-mvebu-gicp.c            |  1 +
 drivers/irqchip/irq-mvebu-odmi.c            |  1 +
 drivers/irqchip/irq-mvebu-sei.c             |  1 +
 include/linux/msi.h                         | 11 +++++++++++
 10 files changed, 25 insertions(+), 5 deletions(-)

diff --git a/drivers/irqchip/irq-gic-v2m.c b/drivers/irqchip/irq-gic-v2m.c
index be35c5349986a..1e3476c335ca8 100644
--- a/drivers/irqchip/irq-gic-v2m.c
+++ b/drivers/irqchip/irq-gic-v2m.c
@@ -255,6 +255,7 @@ static void __init gicv2m_teardown(void)
 static struct msi_parent_ops gicv2m_msi_parent_ops = {
 	.supported_flags	= GICV2M_MSI_FLAGS_SUPPORTED,
 	.required_flags		= GICV2M_MSI_FLAGS_REQUIRED,
+	.chip_flags		= MSI_CHIP_FLAG_SET_EOI | MSI_CHIP_FLAG_SET_ACK,
 	.bus_select_token	= DOMAIN_BUS_NEXUS,
 	.bus_select_mask	= MATCH_PCI_MSI | MATCH_PLATFORM_MSI,
 	.prefix			= "GICv2m-",
diff --git a/drivers/irqchip/irq-gic-v3-its-msi-parent.c b/drivers/irqchip/irq-gic-v3-its-msi-parent.c
index e150365fbe892..bdb04c8081480 100644
--- a/drivers/irqchip/irq-gic-v3-its-msi-parent.c
+++ b/drivers/irqchip/irq-gic-v3-its-msi-parent.c
@@ -203,6 +203,7 @@ static bool its_init_dev_msi_info(struct device *dev, struct irq_domain *domain,
 const struct msi_parent_ops gic_v3_its_msi_parent_ops = {
 	.supported_flags	= ITS_MSI_FLAGS_SUPPORTED,
 	.required_flags		= ITS_MSI_FLAGS_REQUIRED,
+	.chip_flags		= MSI_CHIP_FLAG_SET_EOI | MSI_CHIP_FLAG_SET_ACK,
 	.bus_select_token	= DOMAIN_BUS_NEXUS,
 	.bus_select_mask	= MATCH_PCI_MSI | MATCH_PLATFORM_MSI,
 	.prefix			= "ITS-",
diff --git a/drivers/irqchip/irq-gic-v3-mbi.c b/drivers/irqchip/irq-gic-v3-mbi.c
index 3fe870f8ee174..3e1d8a1cda5e6 100644
--- a/drivers/irqchip/irq-gic-v3-mbi.c
+++ b/drivers/irqchip/irq-gic-v3-mbi.c
@@ -201,6 +201,7 @@ static bool mbi_init_dev_msi_info(struct device *dev, struct irq_domain *domain,
 static const struct msi_parent_ops gic_v3_mbi_msi_parent_ops = {
 	.supported_flags	= MBI_MSI_FLAGS_SUPPORTED,
 	.required_flags		= MBI_MSI_FLAGS_REQUIRED,
+	.chip_flags		= MSI_CHIP_FLAG_SET_EOI | MSI_CHIP_FLAG_SET_ACK,
 	.bus_select_token	= DOMAIN_BUS_NEXUS,
 	.bus_select_mask	= MATCH_PCI_MSI | MATCH_PLATFORM_MSI,
 	.prefix			= "MBI-",
diff --git a/drivers/irqchip/irq-imx-mu-msi.c b/drivers/irqchip/irq-imx-mu-msi.c
index 4342a21de1eb0..69aacdfc8bef0 100644
--- a/drivers/irqchip/irq-imx-mu-msi.c
+++ b/drivers/irqchip/irq-imx-mu-msi.c
@@ -214,6 +214,7 @@ static void imx_mu_msi_irq_handler(struct irq_desc *desc)
 static const struct msi_parent_ops imx_mu_msi_parent_ops = {
 	.supported_flags	= IMX_MU_MSI_FLAGS_SUPPORTED,
 	.required_flags		= IMX_MU_MSI_FLAGS_REQUIRED,
+	.chip_flags		= MSI_CHIP_FLAG_SET_EOI | MSI_CHIP_FLAG_SET_ACK,
 	.bus_select_token       = DOMAIN_BUS_NEXUS,
 	.bus_select_mask	= MATCH_PLATFORM_MSI,
 	.prefix			= "MU-MSI-",
diff --git a/drivers/irqchip/irq-loongson-pch-msi.c b/drivers/irqchip/irq-loongson-pch-msi.c
index bd337ecddb409..9c62108b3ad58 100644
--- a/drivers/irqchip/irq-loongson-pch-msi.c
+++ b/drivers/irqchip/irq-loongson-pch-msi.c
@@ -146,6 +146,7 @@ static const struct irq_domain_ops pch_msi_middle_domain_ops = {
 static struct msi_parent_ops pch_msi_parent_ops = {
 	.required_flags		= PCH_MSI_FLAGS_REQUIRED,
 	.supported_flags	= PCH_MSI_FLAGS_SUPPORTED,
+	.chip_flags		= MSI_CHIP_FLAG_SET_EOI | MSI_CHIP_FLAG_SET_ACK,
 	.bus_select_mask	= MATCH_PCI_MSI,
 	.bus_select_token	= DOMAIN_BUS_NEXUS,
 	.prefix			= "PCH-",
diff --git a/drivers/irqchip/irq-msi-lib.c b/drivers/irqchip/irq-msi-lib.c
index d8e29fc0d4068..51464c6257f37 100644
--- a/drivers/irqchip/irq-msi-lib.c
+++ b/drivers/irqchip/irq-msi-lib.c
@@ -28,6 +28,7 @@ bool msi_lib_init_dev_msi_info(struct device *dev, struct irq_domain *domain,
 			       struct msi_domain_info *info)
 {
 	const struct msi_parent_ops *pops = real_parent->msi_parent_ops;
+	struct irq_chip *chip = info->chip;
 	u32 required_flags;
 
 	/* Parent ops available? */
@@ -92,10 +93,10 @@ bool msi_lib_init_dev_msi_info(struct device *dev, struct irq_domain *domain,
 	info->flags			|= required_flags;
 
 	/* Chip updates for all child bus types */
-	if (!info->chip->irq_eoi)
-		info->chip->irq_eoi	= irq_chip_eoi_parent;
-	if (!info->chip->irq_ack)
-		info->chip->irq_ack	= irq_chip_ack_parent;
+	if (!chip->irq_eoi && (pops->chip_flags & MSI_CHIP_FLAG_SET_EOI))
+		chip->irq_eoi = irq_chip_eoi_parent;
+	if (!chip->irq_ack && (pops->chip_flags & MSI_CHIP_FLAG_SET_ACK))
+		chip->irq_ack = irq_chip_ack_parent;
 
 	/*
 	 * The device MSI domain can never have a set affinity callback. It
@@ -105,7 +106,7 @@ bool msi_lib_init_dev_msi_info(struct device *dev, struct irq_domain *domain,
 	 * device MSI domain aside of mask/unmask which is provided e.g. by
 	 * PCI/MSI device domains.
 	 */
-	info->chip->irq_set_affinity	= msi_domain_set_affinity;
+	chip->irq_set_affinity = msi_domain_set_affinity;
 	return true;
 }
 EXPORT_SYMBOL_GPL(msi_lib_init_dev_msi_info);
diff --git a/drivers/irqchip/irq-mvebu-gicp.c b/drivers/irqchip/irq-mvebu-gicp.c
index 2b6183919ea48..d67f93f6d7505 100644
--- a/drivers/irqchip/irq-mvebu-gicp.c
+++ b/drivers/irqchip/irq-mvebu-gicp.c
@@ -161,6 +161,7 @@ static const struct irq_domain_ops gicp_domain_ops = {
 static const struct msi_parent_ops gicp_msi_parent_ops = {
 	.supported_flags	= GICP_MSI_FLAGS_SUPPORTED,
 	.required_flags		= GICP_MSI_FLAGS_REQUIRED,
+	.chip_flags		= MSI_CHIP_FLAG_SET_EOI | MSI_CHIP_FLAG_SET_ACK,
 	.bus_select_token       = DOMAIN_BUS_GENERIC_MSI,
 	.bus_select_mask	= MATCH_PLATFORM_MSI,
 	.prefix			= "GICP-",
diff --git a/drivers/irqchip/irq-mvebu-odmi.c b/drivers/irqchip/irq-mvebu-odmi.c
index ff19bfd258dce..28f7e81df94f0 100644
--- a/drivers/irqchip/irq-mvebu-odmi.c
+++ b/drivers/irqchip/irq-mvebu-odmi.c
@@ -157,6 +157,7 @@ static const struct irq_domain_ops odmi_domain_ops = {
 static const struct msi_parent_ops odmi_msi_parent_ops = {
 	.supported_flags	= ODMI_MSI_FLAGS_SUPPORTED,
 	.required_flags		= ODMI_MSI_FLAGS_REQUIRED,
+	.chip_flags		= MSI_CHIP_FLAG_SET_EOI | MSI_CHIP_FLAG_SET_ACK,
 	.bus_select_token	= DOMAIN_BUS_GENERIC_MSI,
 	.bus_select_mask	= MATCH_PLATFORM_MSI,
 	.prefix			= "ODMI-",
diff --git a/drivers/irqchip/irq-mvebu-sei.c b/drivers/irqchip/irq-mvebu-sei.c
index 065166ab5dbc0..ebd4a9014e8da 100644
--- a/drivers/irqchip/irq-mvebu-sei.c
+++ b/drivers/irqchip/irq-mvebu-sei.c
@@ -356,6 +356,7 @@ static void mvebu_sei_reset(struct mvebu_sei *sei)
 static const struct msi_parent_ops sei_msi_parent_ops = {
 	.supported_flags	= SEI_MSI_FLAGS_SUPPORTED,
 	.required_flags		= SEI_MSI_FLAGS_REQUIRED,
+	.chip_flags		= MSI_CHIP_FLAG_SET_EOI | MSI_CHIP_FLAG_SET_ACK,
 	.bus_select_mask	= MATCH_PLATFORM_MSI,
 	.bus_select_token	= DOMAIN_BUS_GENERIC_MSI,
 	.prefix			= "SEI-",
diff --git a/include/linux/msi.h b/include/linux/msi.h
index b10093c4d00ea..9abef442c1463 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -558,11 +558,21 @@ enum {
 	MSI_FLAG_NO_AFFINITY		= (1 << 21),
 };
 
+/*
+ * Flags for msi_parent_ops::chip_flags
+ */
+enum {
+	MSI_CHIP_FLAG_SET_EOI		= (1 << 0),
+	MSI_CHIP_FLAG_SET_ACK		= (1 << 1),
+};
+
 /**
  * struct msi_parent_ops - MSI parent domain callbacks and configuration info
  *
  * @supported_flags:	Required: The supported MSI flags of the parent domain
  * @required_flags:	Optional: The required MSI flags of the parent MSI domain
+ * @chip_flags:		Optional: Select MSI chip callbacks to update with defaults
+ *			in msi_lib_init_dev_msi_info().
  * @bus_select_token:	Optional: The bus token of the real parent domain for
  *			irq_domain::select()
  * @bus_select_mask:	Optional: A mask of supported BUS_DOMAINs for
@@ -575,6 +585,7 @@ enum {
 struct msi_parent_ops {
 	u32		supported_flags;
 	u32		required_flags;
+	u32		chip_flags;
 	u32		bus_select_token;
 	u32		bus_select_mask;
 	const char	*prefix;

From fe35ecee8ec8d42b1d24ed70e5b33192294bcef0 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 17 Feb 2025 14:26:49 +0530
Subject: [PATCH 0396/1173] irqchip/riscv-imsic: Move to common MSI library

Simplify the leaf MSI domain handling in the RISC-V IMSIC driver by
using msi_lib_init_dev_msi_info() and msi_lib_irq_domain_select()
provided by the common MSI library.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250217085657.789309-4-apatel@ventanamicro.com
---
 drivers/irqchip/Kconfig                    |   8 +-
 drivers/irqchip/irq-riscv-imsic-platform.c | 114 +--------------------
 2 files changed, 6 insertions(+), 116 deletions(-)

diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index be063bfb50c4b..bc3f12af2dc78 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -589,13 +589,7 @@ config RISCV_IMSIC
 	select IRQ_DOMAIN_HIERARCHY
 	select GENERIC_IRQ_MATRIX_ALLOCATOR
 	select GENERIC_MSI_IRQ
-
-config RISCV_IMSIC_PCI
-	bool
-	depends on RISCV_IMSIC
-	depends on PCI
-	depends on PCI_MSI
-	default RISCV_IMSIC
+	select IRQ_MSI_LIB
 
 config SIFIVE_PLIC
 	bool
diff --git a/drivers/irqchip/irq-riscv-imsic-platform.c b/drivers/irqchip/irq-riscv-imsic-platform.c
index 5d7c30ad8855b..9a5e7b4541f6e 100644
--- a/drivers/irqchip/irq-riscv-imsic-platform.c
+++ b/drivers/irqchip/irq-riscv-imsic-platform.c
@@ -20,6 +20,7 @@
 #include <linux/spinlock.h>
 #include <linux/smp.h>
 
+#include "irq-msi-lib.h"
 #include "irq-riscv-imsic-state.h"
 
 static bool imsic_cpu_page_phys(unsigned int cpu, unsigned int guest_index,
@@ -174,22 +175,6 @@ static void imsic_irq_domain_free(struct irq_domain *domain, unsigned int virq,
 	irq_domain_free_irqs_parent(domain, virq, nr_irqs);
 }
 
-static int imsic_irq_domain_select(struct irq_domain *domain, struct irq_fwspec *fwspec,
-				   enum irq_domain_bus_token bus_token)
-{
-	const struct msi_parent_ops *ops = domain->msi_parent_ops;
-	u32 busmask = BIT(bus_token);
-
-	if (fwspec->fwnode != domain->fwnode || fwspec->param_count != 0)
-		return 0;
-
-	/* Handle pure domain searches */
-	if (bus_token == ops->bus_select_token)
-		return 1;
-
-	return !!(ops->bus_select_mask & busmask);
-}
-
 #ifdef CONFIG_GENERIC_IRQ_DEBUGFS
 static void imsic_irq_debug_show(struct seq_file *m, struct irq_domain *d,
 				 struct irq_data *irqd, int ind)
@@ -206,110 +191,21 @@ static void imsic_irq_debug_show(struct seq_file *m, struct irq_domain *d,
 static const struct irq_domain_ops imsic_base_domain_ops = {
 	.alloc		= imsic_irq_domain_alloc,
 	.free		= imsic_irq_domain_free,
-	.select		= imsic_irq_domain_select,
+	.select		= msi_lib_irq_domain_select,
 #ifdef CONFIG_GENERIC_IRQ_DEBUGFS
 	.debug_show	= imsic_irq_debug_show,
 #endif
 };
 
-#ifdef CONFIG_RISCV_IMSIC_PCI
-
-static void imsic_pci_mask_irq(struct irq_data *d)
-{
-	pci_msi_mask_irq(d);
-	irq_chip_mask_parent(d);
-}
-
-static void imsic_pci_unmask_irq(struct irq_data *d)
-{
-	irq_chip_unmask_parent(d);
-	pci_msi_unmask_irq(d);
-}
-
-#define MATCH_PCI_MSI		BIT(DOMAIN_BUS_PCI_MSI)
-
-#else
-
-#define MATCH_PCI_MSI		0
-
-#endif
-
-static bool imsic_init_dev_msi_info(struct device *dev,
-				    struct irq_domain *domain,
-				    struct irq_domain *real_parent,
-				    struct msi_domain_info *info)
-{
-	const struct msi_parent_ops *pops = real_parent->msi_parent_ops;
-
-	/* MSI parent domain specific settings */
-	switch (real_parent->bus_token) {
-	case DOMAIN_BUS_NEXUS:
-		if (WARN_ON_ONCE(domain != real_parent))
-			return false;
-#ifdef CONFIG_SMP
-		info->chip->irq_set_affinity = irq_chip_set_affinity_parent;
-#endif
-		break;
-	default:
-		WARN_ON_ONCE(1);
-		return false;
-	}
-
-	/* Is the target supported? */
-	switch (info->bus_token) {
-#ifdef CONFIG_RISCV_IMSIC_PCI
-	case DOMAIN_BUS_PCI_DEVICE_MSI:
-	case DOMAIN_BUS_PCI_DEVICE_MSIX:
-		info->chip->irq_mask = imsic_pci_mask_irq;
-		info->chip->irq_unmask = imsic_pci_unmask_irq;
-		break;
-#endif
-	case DOMAIN_BUS_DEVICE_MSI:
-		/*
-		 * Per-device MSI should never have any MSI feature bits
-		 * set. It's sole purpose is to create a dumb interrupt
-		 * chip which has a device specific irq_write_msi_msg()
-		 * callback.
-		 */
-		if (WARN_ON_ONCE(info->flags))
-			return false;
-
-		/* Core managed MSI descriptors */
-		info->flags |= MSI_FLAG_ALLOC_SIMPLE_MSI_DESCS |
-			       MSI_FLAG_FREE_MSI_DESCS;
-		break;
-	case DOMAIN_BUS_WIRED_TO_MSI:
-		break;
-	default:
-		WARN_ON_ONCE(1);
-		return false;
-	}
-
-	/* Use hierarchial chip operations re-trigger */
-	info->chip->irq_retrigger = irq_chip_retrigger_hierarchy;
-
-	/*
-	 * Mask out the domain specific MSI feature flags which are not
-	 * supported by the real parent.
-	 */
-	info->flags &= pops->supported_flags;
-
-	/* Enforce the required flags */
-	info->flags |= pops->required_flags;
-
-	return true;
-}
-
-#define MATCH_PLATFORM_MSI		BIT(DOMAIN_BUS_PLATFORM_MSI)
-
 static const struct msi_parent_ops imsic_msi_parent_ops = {
 	.supported_flags	= MSI_GENERIC_FLAGS_MASK |
 				  MSI_FLAG_PCI_MSIX,
 	.required_flags		= MSI_FLAG_USE_DEF_DOM_OPS |
-				  MSI_FLAG_USE_DEF_CHIP_OPS,
+				  MSI_FLAG_USE_DEF_CHIP_OPS |
+				  MSI_FLAG_PCI_MSI_MASK_PARENT,
 	.bus_select_token	= DOMAIN_BUS_NEXUS,
 	.bus_select_mask	= MATCH_PCI_MSI | MATCH_PLATFORM_MSI,
-	.init_dev_msi_info	= imsic_init_dev_msi_info,
+	.init_dev_msi_info	= msi_lib_init_dev_msi_info,
 };
 
 int imsic_irqdomain_init(void)

From 751dc837dabd275d0ab165fc737c10f80e2e863a Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 17 Feb 2025 14:26:50 +0530
Subject: [PATCH 0397/1173] genirq: Introduce common irq_force_complete_move()
 implementation

CONFIG_GENERIC_PENDING_IRQ requires an architecture specific implementation
of irq_force_complete_move() for CPU hotplug. At the moment, only x86
implements this unconditionally, but for RISC-V irq_force_complete_move()
is only needed when the RISC-V IMSIC driver is in use and not needed
otherwise.

To allow runtime configuration of this mechanism, introduce a common
irq_force_complete_move() implementation in the interrupt core code, which
only invokes the completion function, when a interrupt chip in the
hierarchy implements it.

Switch X86 over to the new mechanism. No functional change intended.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250217085657.789309-5-apatel@ventanamicro.com
---
 arch/x86/kernel/apic/vector.c | 231 ++++++++++++++++------------------
 include/linux/irq.h           |   5 +-
 kernel/irq/internals.h        |   2 +
 kernel/irq/migration.c        |  10 ++
 4 files changed, 123 insertions(+), 125 deletions(-)

diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 736f62812f5c2..72fa4bb78f0a6 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -888,8 +888,109 @@ static int apic_set_affinity(struct irq_data *irqd,
 	return err ? err : IRQ_SET_MASK_OK;
 }
 
+static void free_moved_vector(struct apic_chip_data *apicd)
+{
+	unsigned int vector = apicd->prev_vector;
+	unsigned int cpu = apicd->prev_cpu;
+	bool managed = apicd->is_managed;
+
+	/*
+	 * Managed interrupts are usually not migrated away
+	 * from an online CPU, but CPU isolation 'managed_irq'
+	 * can make that happen.
+	 * 1) Activation does not take the isolation into account
+	 *    to keep the code simple
+	 * 2) Migration away from an isolated CPU can happen when
+	 *    a non-isolated CPU which is in the calculated
+	 *    affinity mask comes online.
+	 */
+	trace_vector_free_moved(apicd->irq, cpu, vector, managed);
+	irq_matrix_free(vector_matrix, cpu, vector, managed);
+	per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED;
+	hlist_del_init(&apicd->clist);
+	apicd->prev_vector = 0;
+	apicd->move_in_progress = 0;
+}
+
+/*
+ * Called from fixup_irqs() with @desc->lock held and interrupts disabled.
+ */
+static void apic_force_complete_move(struct irq_data *irqd)
+{
+	unsigned int cpu = smp_processor_id();
+	struct apic_chip_data *apicd;
+	unsigned int vector;
+
+	guard(raw_spinlock)(&vector_lock);
+	apicd = apic_chip_data(irqd);
+	if (!apicd)
+		return;
+
+	/*
+	 * If prev_vector is empty or the descriptor is neither currently
+	 * nor previously on the outgoing CPU no action required.
+	 */
+	vector = apicd->prev_vector;
+	if (!vector || (apicd->cpu != cpu && apicd->prev_cpu != cpu))
+		return;
+
+	/*
+	 * This is tricky. If the cleanup of the old vector has not been
+	 * done yet, then the following setaffinity call will fail with
+	 * -EBUSY. This can leave the interrupt in a stale state.
+	 *
+	 * All CPUs are stuck in stop machine with interrupts disabled so
+	 * calling __irq_complete_move() would be completely pointless.
+	 *
+	 * 1) The interrupt is in move_in_progress state. That means that we
+	 *    have not seen an interrupt since the io_apic was reprogrammed to
+	 *    the new vector.
+	 *
+	 * 2) The interrupt has fired on the new vector, but the cleanup IPIs
+	 *    have not been processed yet.
+	 */
+	if (apicd->move_in_progress) {
+		/*
+		 * In theory there is a race:
+		 *
+		 * set_ioapic(new_vector) <-- Interrupt is raised before update
+		 *			      is effective, i.e. it's raised on
+		 *			      the old vector.
+		 *
+		 * So if the target cpu cannot handle that interrupt before
+		 * the old vector is cleaned up, we get a spurious interrupt
+		 * and in the worst case the ioapic irq line becomes stale.
+		 *
+		 * But in case of cpu hotplug this should be a non issue
+		 * because if the affinity update happens right before all
+		 * cpus rendezvous in stop machine, there is no way that the
+		 * interrupt can be blocked on the target cpu because all cpus
+		 * loops first with interrupts enabled in stop machine, so the
+		 * old vector is not yet cleaned up when the interrupt fires.
+		 *
+		 * So the only way to run into this issue is if the delivery
+		 * of the interrupt on the apic/system bus would be delayed
+		 * beyond the point where the target cpu disables interrupts
+		 * in stop machine. I doubt that it can happen, but at least
+		 * there is a theoretical chance. Virtualization might be
+		 * able to expose this, but AFAICT the IOAPIC emulation is not
+		 * as stupid as the real hardware.
+		 *
+		 * Anyway, there is nothing we can do about that at this point
+		 * w/o refactoring the whole fixup_irq() business completely.
+		 * We print at least the irq number and the old vector number,
+		 * so we have the necessary information when a problem in that
+		 * area arises.
+		 */
+		pr_warn("IRQ fixup: irq %d move in progress, old vector %d\n",
+			irqd->irq, vector);
+	}
+	free_moved_vector(apicd);
+}
+
 #else
-# define apic_set_affinity	NULL
+# define apic_set_affinity		NULL
+# define apic_force_complete_move	NULL
 #endif
 
 static int apic_retrigger_irq(struct irq_data *irqd)
@@ -923,39 +1024,16 @@ static void x86_vector_msi_compose_msg(struct irq_data *data,
 }
 
 static struct irq_chip lapic_controller = {
-	.name			= "APIC",
-	.irq_ack		= apic_ack_edge,
-	.irq_set_affinity	= apic_set_affinity,
-	.irq_compose_msi_msg	= x86_vector_msi_compose_msg,
-	.irq_retrigger		= apic_retrigger_irq,
+	.name				= "APIC",
+	.irq_ack			= apic_ack_edge,
+	.irq_set_affinity		= apic_set_affinity,
+	.irq_compose_msi_msg		= x86_vector_msi_compose_msg,
+	.irq_force_complete_move	= apic_force_complete_move,
+	.irq_retrigger			= apic_retrigger_irq,
 };
 
 #ifdef CONFIG_SMP
 
-static void free_moved_vector(struct apic_chip_data *apicd)
-{
-	unsigned int vector = apicd->prev_vector;
-	unsigned int cpu = apicd->prev_cpu;
-	bool managed = apicd->is_managed;
-
-	/*
-	 * Managed interrupts are usually not migrated away
-	 * from an online CPU, but CPU isolation 'managed_irq'
-	 * can make that happen.
-	 * 1) Activation does not take the isolation into account
-	 *    to keep the code simple
-	 * 2) Migration away from an isolated CPU can happen when
-	 *    a non-isolated CPU which is in the calculated
-	 *    affinity mask comes online.
-	 */
-	trace_vector_free_moved(apicd->irq, cpu, vector, managed);
-	irq_matrix_free(vector_matrix, cpu, vector, managed);
-	per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED;
-	hlist_del_init(&apicd->clist);
-	apicd->prev_vector = 0;
-	apicd->move_in_progress = 0;
-}
-
 static void __vector_cleanup(struct vector_cleanup *cl, bool check_irr)
 {
 	struct apic_chip_data *apicd;
@@ -1068,99 +1146,6 @@ void irq_complete_move(struct irq_cfg *cfg)
 		__vector_schedule_cleanup(apicd);
 }
 
-/*
- * Called from fixup_irqs() with @desc->lock held and interrupts disabled.
- */
-void irq_force_complete_move(struct irq_desc *desc)
-{
-	unsigned int cpu = smp_processor_id();
-	struct apic_chip_data *apicd;
-	struct irq_data *irqd;
-	unsigned int vector;
-
-	/*
-	 * The function is called for all descriptors regardless of which
-	 * irqdomain they belong to. For example if an IRQ is provided by
-	 * an irq_chip as part of a GPIO driver, the chip data for that
-	 * descriptor is specific to the irq_chip in question.
-	 *
-	 * Check first that the chip_data is what we expect
-	 * (apic_chip_data) before touching it any further.
-	 */
-	irqd = irq_domain_get_irq_data(x86_vector_domain,
-				       irq_desc_get_irq(desc));
-	if (!irqd)
-		return;
-
-	raw_spin_lock(&vector_lock);
-	apicd = apic_chip_data(irqd);
-	if (!apicd)
-		goto unlock;
-
-	/*
-	 * If prev_vector is empty or the descriptor is neither currently
-	 * nor previously on the outgoing CPU no action required.
-	 */
-	vector = apicd->prev_vector;
-	if (!vector || (apicd->cpu != cpu && apicd->prev_cpu != cpu))
-		goto unlock;
-
-	/*
-	 * This is tricky. If the cleanup of the old vector has not been
-	 * done yet, then the following setaffinity call will fail with
-	 * -EBUSY. This can leave the interrupt in a stale state.
-	 *
-	 * All CPUs are stuck in stop machine with interrupts disabled so
-	 * calling __irq_complete_move() would be completely pointless.
-	 *
-	 * 1) The interrupt is in move_in_progress state. That means that we
-	 *    have not seen an interrupt since the io_apic was reprogrammed to
-	 *    the new vector.
-	 *
-	 * 2) The interrupt has fired on the new vector, but the cleanup IPIs
-	 *    have not been processed yet.
-	 */
-	if (apicd->move_in_progress) {
-		/*
-		 * In theory there is a race:
-		 *
-		 * set_ioapic(new_vector) <-- Interrupt is raised before update
-		 *			      is effective, i.e. it's raised on
-		 *			      the old vector.
-		 *
-		 * So if the target cpu cannot handle that interrupt before
-		 * the old vector is cleaned up, we get a spurious interrupt
-		 * and in the worst case the ioapic irq line becomes stale.
-		 *
-		 * But in case of cpu hotplug this should be a non issue
-		 * because if the affinity update happens right before all
-		 * cpus rendezvous in stop machine, there is no way that the
-		 * interrupt can be blocked on the target cpu because all cpus
-		 * loops first with interrupts enabled in stop machine, so the
-		 * old vector is not yet cleaned up when the interrupt fires.
-		 *
-		 * So the only way to run into this issue is if the delivery
-		 * of the interrupt on the apic/system bus would be delayed
-		 * beyond the point where the target cpu disables interrupts
-		 * in stop machine. I doubt that it can happen, but at least
-		 * there is a theoretical chance. Virtualization might be
-		 * able to expose this, but AFAICT the IOAPIC emulation is not
-		 * as stupid as the real hardware.
-		 *
-		 * Anyway, there is nothing we can do about that at this point
-		 * w/o refactoring the whole fixup_irq() business completely.
-		 * We print at least the irq number and the old vector number,
-		 * so we have the necessary information when a problem in that
-		 * area arises.
-		 */
-		pr_warn("IRQ fixup: irq %d move in progress, old vector %d\n",
-			irqd->irq, vector);
-	}
-	free_moved_vector(apicd);
-unlock:
-	raw_spin_unlock(&vector_lock);
-}
-
 #ifdef CONFIG_HOTPLUG_CPU
 /*
  * Note, this is not accurate accounting, but at least good enough to
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 8daa17f0107ac..56f6583093d28 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -486,6 +486,7 @@ static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d)
  * @ipi_send_mask:	send an IPI to destination cpus in cpumask
  * @irq_nmi_setup:	function called from core code before enabling an NMI
  * @irq_nmi_teardown:	function called from core code after disabling an NMI
+ * @irq_force_complete_move:	optional function to force complete pending irq move
  * @flags:		chip specific flags
  */
 struct irq_chip {
@@ -537,6 +538,8 @@ struct irq_chip {
 	int		(*irq_nmi_setup)(struct irq_data *data);
 	void		(*irq_nmi_teardown)(struct irq_data *data);
 
+	void		(*irq_force_complete_move)(struct irq_data *data);
+
 	unsigned long	flags;
 };
 
@@ -619,11 +622,9 @@ static inline void irq_move_irq(struct irq_data *data)
 		__irq_move_irq(data);
 }
 void irq_move_masked_irq(struct irq_data *data);
-void irq_force_complete_move(struct irq_desc *desc);
 #else
 static inline void irq_move_irq(struct irq_data *data) { }
 static inline void irq_move_masked_irq(struct irq_data *data) { }
-static inline void irq_force_complete_move(struct irq_desc *desc) { }
 #endif
 
 extern int no_irq_affinity;
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index a979523640d0a..d4e190e690bdd 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -442,6 +442,7 @@ static inline struct cpumask *irq_desc_get_pending_mask(struct irq_desc *desc)
 	return desc->pending_mask;
 }
 bool irq_fixup_move_pending(struct irq_desc *desc, bool force_clear);
+void irq_force_complete_move(struct irq_desc *desc);
 #else /* CONFIG_GENERIC_PENDING_IRQ */
 static inline bool irq_can_move_pcntxt(struct irq_data *data)
 {
@@ -467,6 +468,7 @@ static inline bool irq_fixup_move_pending(struct irq_desc *desc, bool fclear)
 {
 	return false;
 }
+static inline void irq_force_complete_move(struct irq_desc *desc) { }
 #endif /* !CONFIG_GENERIC_PENDING_IRQ */
 
 #if !defined(CONFIG_IRQ_DOMAIN) || !defined(CONFIG_IRQ_DOMAIN_HIERARCHY)
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index eb150afd671f6..e110300ad650f 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -35,6 +35,16 @@ bool irq_fixup_move_pending(struct irq_desc *desc, bool force_clear)
 	return true;
 }
 
+void irq_force_complete_move(struct irq_desc *desc)
+{
+	for (struct irq_data *d = irq_desc_get_irq_data(desc); d; d = d->parent_data) {
+		if (d->chip && d->chip->irq_force_complete_move) {
+			d->chip->irq_force_complete_move(d);
+			return;
+		}
+	}
+}
+
 void irq_move_masked_irq(struct irq_data *idata)
 {
 	struct irq_desc *desc = irq_data_to_desc(idata);

From e54b1b5e89ae765e6d71d41883a8f551fde8d0ab Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 17 Feb 2025 14:26:51 +0530
Subject: [PATCH 0398/1173] genirq: Introduce irq_can_move_in_process_context()

Interrupt controller drivers which enable CONFIG_GENERIC_PENDING_IRQ
require to know whether an interrupt can be moved in process context or not
to decide whether they need to invoke the work around for non-atomic MSI
updates or not.

This information can be retrieved via irq_can_move_pcntxt(). That helper
requires access to the top-most interrupt domain data, but the driver which
requires this is usually further down in the hierarchy.

Introduce irq_can_move_in_process_context() which retrieves that
information from the top-most interrupt domain data.

[ tglx: Massaged change log ]

Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250217085657.789309-6-apatel@ventanamicro.com
---
 include/linux/irq.h    |  2 ++
 kernel/irq/migration.c | 10 ++++++++++
 2 files changed, 12 insertions(+)

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 56f6583093d28..dd5df1e2d032d 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -615,6 +615,7 @@ extern int irq_affinity_online_cpu(unsigned int cpu);
 #endif
 
 #if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_PENDING_IRQ)
+bool irq_can_move_in_process_context(struct irq_data *data);
 void __irq_move_irq(struct irq_data *data);
 static inline void irq_move_irq(struct irq_data *data)
 {
@@ -623,6 +624,7 @@ static inline void irq_move_irq(struct irq_data *data)
 }
 void irq_move_masked_irq(struct irq_data *data);
 #else
+static inline bool irq_can_move_in_process_context(struct irq_data *data) { return true; }
 static inline void irq_move_irq(struct irq_data *data) { }
 static inline void irq_move_masked_irq(struct irq_data *data) { }
 #endif
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index e110300ad650f..147cabb4c0779 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -127,3 +127,13 @@ void __irq_move_irq(struct irq_data *idata)
 	if (!masked)
 		idata->chip->irq_unmask(idata);
 }
+
+bool irq_can_move_in_process_context(struct irq_data *data)
+{
+	/*
+	 * Get the top level irq_data in the hierarchy, which is optimized
+	 * away when CONFIG_IRQ_DOMAIN_HIERARCHY is disabled.
+	 */
+	data = irq_desc_get_irq_data(irq_data_to_desc(data));
+	return irq_can_move_pcntxt(data);
+}

From 58d868b67a9ac0db477f714939f21849db5f5178 Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 17 Feb 2025 14:26:52 +0530
Subject: [PATCH 0399/1173] RISC-V: Select CONFIG_GENERIC_PENDING_IRQ

Enable CONFIG_GENERIC_PENDING_IRQ for RISC-V so that RISC-V interrupt chips
can support delayed interrupt mirgration in interrupt context.

Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250217085657.789309-7-apatel@ventanamicro.com
---
 arch/riscv/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 7612c52e9b1e3..a32f397487757 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -111,6 +111,7 @@ config RISCV
 	select GENERIC_IRQ_SHOW
 	select GENERIC_IRQ_SHOW_LEVEL
 	select GENERIC_LIB_DEVMEM_IS_ALLOWED
+	select GENERIC_PENDING_IRQ if SMP
 	select GENERIC_PCI_IOMAP
 	select GENERIC_PTDUMP if MMU
 	select GENERIC_SCHED_CLOCK

From 0f67911e821c67ecfccc365a2103ce276a9a56fe Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 17 Feb 2025 14:26:53 +0530
Subject: [PATCH 0400/1173] irqchip/riscv-imsic: Separate next and previous
 pointers in IMSIC vector

Currently, there is only one "move" pointer in struct imsic_vector so
during vector movement the old vector points to the new vector and new
vector points to itself.

To support forced cleanup of the old vector, add separate "move_next" and
"move_prev" pointers to struct imsic_vector, where during vector movement
the "move_next" pointer of the old vector points to the new vector and the
"move_prev" pointer of the new vector points to the old vector.

Both "move_next" and "move_prev" pointers are cleared separately by
__imsic_local_sync() with a restriction that "move_prev" on the new
CPU is cleared only after the old CPU has cleared "move_next".

Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250217085657.789309-8-apatel@ventanamicro.com
---
 drivers/irqchip/irq-riscv-imsic-early.c |  8 ++-
 drivers/irqchip/irq-riscv-imsic-state.c | 96 +++++++++++++++++--------
 drivers/irqchip/irq-riscv-imsic-state.h |  7 +-
 3 files changed, 78 insertions(+), 33 deletions(-)

diff --git a/drivers/irqchip/irq-riscv-imsic-early.c b/drivers/irqchip/irq-riscv-imsic-early.c
index c5c2e6929a2f5..b5def6268936e 100644
--- a/drivers/irqchip/irq-riscv-imsic-early.c
+++ b/drivers/irqchip/irq-riscv-imsic-early.c
@@ -77,6 +77,12 @@ static void imsic_handle_irq(struct irq_desc *desc)
 	struct imsic_vector *vec;
 	unsigned long local_id;
 
+	/*
+	 * Process pending local synchronization instead of waiting
+	 * for per-CPU local timer to expire.
+	 */
+	imsic_local_sync_all(false);
+
 	chained_irq_enter(chip, desc);
 
 	while ((local_id = csr_swap(CSR_TOPEI, 0))) {
@@ -120,7 +126,7 @@ static int imsic_starting_cpu(unsigned int cpu)
 	 * Interrupts identities might have been enabled/disabled while
 	 * this CPU was not running so sync-up local enable/disable state.
 	 */
-	imsic_local_sync_all();
+	imsic_local_sync_all(true);
 
 	/* Enable local interrupt delivery */
 	imsic_local_delivery(true);
diff --git a/drivers/irqchip/irq-riscv-imsic-state.c b/drivers/irqchip/irq-riscv-imsic-state.c
index b97e6cd89ed74..1aeba76d72795 100644
--- a/drivers/irqchip/irq-riscv-imsic-state.c
+++ b/drivers/irqchip/irq-riscv-imsic-state.c
@@ -124,10 +124,11 @@ void __imsic_eix_update(unsigned long base_id, unsigned long num_id, bool pend,
 	}
 }
 
-static void __imsic_local_sync(struct imsic_local_priv *lpriv)
+static bool __imsic_local_sync(struct imsic_local_priv *lpriv)
 {
 	struct imsic_local_config *mlocal;
 	struct imsic_vector *vec, *mvec;
+	bool ret = true;
 	int i;
 
 	lockdep_assert_held(&lpriv->lock);
@@ -143,35 +144,75 @@ static void __imsic_local_sync(struct imsic_local_priv *lpriv)
 			__imsic_id_clear_enable(i);
 
 		/*
-		 * If the ID was being moved to a new ID on some other CPU
-		 * then we can get a MSI during the movement so check the
-		 * ID pending bit and re-trigger the new ID on other CPU
-		 * using MMIO write.
+		 * Clear the previous vector pointer of the new vector only
+		 * after the movement is complete on the old CPU.
 		 */
-		mvec = READ_ONCE(vec->move);
-		WRITE_ONCE(vec->move, NULL);
-		if (mvec && mvec != vec) {
+		mvec = READ_ONCE(vec->move_prev);
+		if (mvec) {
+			/*
+			 * If the old vector has not been updated then
+			 * try again in the next sync-up call.
+			 */
+			if (READ_ONCE(mvec->move_next)) {
+				ret = false;
+				continue;
+			}
+
+			WRITE_ONCE(vec->move_prev, NULL);
+		}
+
+		/*
+		 * If a vector was being moved to a new vector on some other
+		 * CPU then we can get a MSI during the movement so check the
+		 * ID pending bit and re-trigger the new ID on other CPU using
+		 * MMIO write.
+		 */
+		mvec = READ_ONCE(vec->move_next);
+		if (mvec) {
 			if (__imsic_id_read_clear_pending(i)) {
 				mlocal = per_cpu_ptr(imsic->global.local, mvec->cpu);
 				writel_relaxed(mvec->local_id, mlocal->msi_va);
 			}
 
+			WRITE_ONCE(vec->move_next, NULL);
 			imsic_vector_free(&lpriv->vectors[i]);
 		}
 
 skip:
 		bitmap_clear(lpriv->dirty_bitmap, i, 1);
 	}
+
+	return ret;
 }
 
-void imsic_local_sync_all(void)
+#ifdef CONFIG_SMP
+static void __imsic_local_timer_start(struct imsic_local_priv *lpriv)
+{
+	lockdep_assert_held(&lpriv->lock);
+
+	if (!timer_pending(&lpriv->timer)) {
+		lpriv->timer.expires = jiffies + 1;
+		add_timer_on(&lpriv->timer, smp_processor_id());
+	}
+}
+#else
+static inline void __imsic_local_timer_start(struct imsic_local_priv *lpriv)
+{
+}
+#endif
+
+void imsic_local_sync_all(bool force_all)
 {
 	struct imsic_local_priv *lpriv = this_cpu_ptr(imsic->lpriv);
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&lpriv->lock, flags);
-	bitmap_fill(lpriv->dirty_bitmap, imsic->global.nr_ids + 1);
-	__imsic_local_sync(lpriv);
+
+	if (force_all)
+		bitmap_fill(lpriv->dirty_bitmap, imsic->global.nr_ids + 1);
+	if (!__imsic_local_sync(lpriv))
+		__imsic_local_timer_start(lpriv);
+
 	raw_spin_unlock_irqrestore(&lpriv->lock, flags);
 }
 
@@ -190,12 +231,7 @@ void imsic_local_delivery(bool enable)
 #ifdef CONFIG_SMP
 static void imsic_local_timer_callback(struct timer_list *timer)
 {
-	struct imsic_local_priv *lpriv = this_cpu_ptr(imsic->lpriv);
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&lpriv->lock, flags);
-	__imsic_local_sync(lpriv);
-	raw_spin_unlock_irqrestore(&lpriv->lock, flags);
+	imsic_local_sync_all(false);
 }
 
 static void __imsic_remote_sync(struct imsic_local_priv *lpriv, unsigned int cpu)
@@ -216,14 +252,11 @@ static void __imsic_remote_sync(struct imsic_local_priv *lpriv, unsigned int cpu
 	 */
 	if (cpu_online(cpu)) {
 		if (cpu == smp_processor_id()) {
-			__imsic_local_sync(lpriv);
-			return;
+			if (__imsic_local_sync(lpriv))
+				return;
 		}
 
-		if (!timer_pending(&lpriv->timer)) {
-			lpriv->timer.expires = jiffies + 1;
-			add_timer_on(&lpriv->timer, cpu);
-		}
+		__imsic_local_timer_start(lpriv);
 	}
 }
 #else
@@ -278,8 +311,9 @@ void imsic_vector_unmask(struct imsic_vector *vec)
 	raw_spin_unlock(&lpriv->lock);
 }
 
-static bool imsic_vector_move_update(struct imsic_local_priv *lpriv, struct imsic_vector *vec,
-				     bool new_enable, struct imsic_vector *new_move)
+static bool imsic_vector_move_update(struct imsic_local_priv *lpriv,
+				     struct imsic_vector *vec, bool is_old_vec,
+				     bool new_enable, struct imsic_vector *move_vec)
 {
 	unsigned long flags;
 	bool enabled;
@@ -289,7 +323,10 @@ static bool imsic_vector_move_update(struct imsic_local_priv *lpriv, struct imsi
 	/* Update enable and move details */
 	enabled = READ_ONCE(vec->enable);
 	WRITE_ONCE(vec->enable, new_enable);
-	WRITE_ONCE(vec->move, new_move);
+	if (is_old_vec)
+		WRITE_ONCE(vec->move_next, move_vec);
+	else
+		WRITE_ONCE(vec->move_prev, move_vec);
 
 	/* Mark the vector as dirty and synchronize */
 	bitmap_set(lpriv->dirty_bitmap, vec->local_id, 1);
@@ -322,8 +359,8 @@ void imsic_vector_move(struct imsic_vector *old_vec, struct imsic_vector *new_ve
 	 * interrupt on the old vector while device was being moved
 	 * to the new vector.
 	 */
-	enabled = imsic_vector_move_update(old_lpriv, old_vec, false, new_vec);
-	imsic_vector_move_update(new_lpriv, new_vec, enabled, new_vec);
+	enabled = imsic_vector_move_update(old_lpriv, old_vec, true, false, new_vec);
+	imsic_vector_move_update(new_lpriv, new_vec, false, enabled, old_vec);
 }
 
 #ifdef CONFIG_GENERIC_IRQ_DEBUGFS
@@ -386,7 +423,8 @@ struct imsic_vector *imsic_vector_alloc(unsigned int hwirq, const struct cpumask
 	vec = &lpriv->vectors[local_id];
 	vec->hwirq = hwirq;
 	vec->enable = false;
-	vec->move = NULL;
+	vec->move_next = NULL;
+	vec->move_prev = NULL;
 
 	return vec;
 }
diff --git a/drivers/irqchip/irq-riscv-imsic-state.h b/drivers/irqchip/irq-riscv-imsic-state.h
index 391e442808275..f02842b84ed58 100644
--- a/drivers/irqchip/irq-riscv-imsic-state.h
+++ b/drivers/irqchip/irq-riscv-imsic-state.h
@@ -23,7 +23,8 @@ struct imsic_vector {
 	unsigned int				hwirq;
 	/* Details accessed using local lock held */
 	bool					enable;
-	struct imsic_vector			*move;
+	struct imsic_vector			*move_next;
+	struct imsic_vector			*move_prev;
 };
 
 struct imsic_local_priv {
@@ -74,7 +75,7 @@ static inline void __imsic_id_clear_enable(unsigned long id)
 	__imsic_eix_update(id, 1, false, false);
 }
 
-void imsic_local_sync_all(void);
+void imsic_local_sync_all(bool force_all);
 void imsic_local_delivery(bool enable);
 
 void imsic_vector_mask(struct imsic_vector *vec);
@@ -87,7 +88,7 @@ static inline bool imsic_vector_isenabled(struct imsic_vector *vec)
 
 static inline struct imsic_vector *imsic_vector_get_move(struct imsic_vector *vec)
 {
-	return READ_ONCE(vec->move);
+	return READ_ONCE(vec->move_prev);
 }
 
 void imsic_vector_move(struct imsic_vector *old_vec, struct imsic_vector *new_vec);

From 51611130d57d2061729010bd0575701aa4b7ff74 Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 17 Feb 2025 14:26:54 +0530
Subject: [PATCH 0401/1173] irqchip/riscv-imsic: Implement
 irq_force_complete_move() for IMSIC

Implement irq_force_complete_move() for IMSIC driver so that in-flight
vector movements on a CPU can be cleaned-up when the CPU goes down.

Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250217085657.789309-9-apatel@ventanamicro.com
---
 drivers/irqchip/irq-riscv-imsic-platform.c | 32 ++++++++++++++++++++++
 drivers/irqchip/irq-riscv-imsic-state.c    | 17 ++++++++++++
 drivers/irqchip/irq-riscv-imsic-state.h    |  1 +
 3 files changed, 50 insertions(+)

diff --git a/drivers/irqchip/irq-riscv-imsic-platform.c b/drivers/irqchip/irq-riscv-imsic-platform.c
index 9a5e7b4541f6e..b9e3f9030bdf0 100644
--- a/drivers/irqchip/irq-riscv-imsic-platform.c
+++ b/drivers/irqchip/irq-riscv-imsic-platform.c
@@ -129,6 +129,37 @@ static int imsic_irq_set_affinity(struct irq_data *d, const struct cpumask *mask
 
 	return IRQ_SET_MASK_OK_DONE;
 }
+
+static void imsic_irq_force_complete_move(struct irq_data *d)
+{
+	struct imsic_vector *mvec, *vec = irq_data_get_irq_chip_data(d);
+	unsigned int cpu = smp_processor_id();
+
+	if (WARN_ON(!vec))
+		return;
+
+	/* Do nothing if there is no in-flight move */
+	mvec = imsic_vector_get_move(vec);
+	if (!mvec)
+		return;
+
+	/* Do nothing if the old IMSIC vector does not belong to current CPU */
+	if (mvec->cpu != cpu)
+		return;
+
+	/*
+	 * The best we can do is force cleanup the old IMSIC vector.
+	 *
+	 * The challenges over here are same as x86 vector domain so
+	 * refer to the comments in irq_force_complete_move() function
+	 * implemented at arch/x86/kernel/apic/vector.c.
+	 */
+
+	/* Force cleanup in-flight move */
+	pr_info("IRQ fixup: irq %d move in progress, old vector cpu %d local_id %d\n",
+		d->irq, mvec->cpu, mvec->local_id);
+	imsic_vector_force_move_cleanup(vec);
+}
 #endif
 
 static struct irq_chip imsic_irq_base_chip = {
@@ -137,6 +168,7 @@ static struct irq_chip imsic_irq_base_chip = {
 	.irq_unmask		= imsic_irq_unmask,
 #ifdef CONFIG_SMP
 	.irq_set_affinity	= imsic_irq_set_affinity,
+	.irq_force_complete_move = imsic_irq_force_complete_move,
 #endif
 	.irq_retrigger		= imsic_irq_retrigger,
 	.irq_compose_msi_msg	= imsic_irq_compose_msg,
diff --git a/drivers/irqchip/irq-riscv-imsic-state.c b/drivers/irqchip/irq-riscv-imsic-state.c
index 1aeba76d72795..eb0a9b6a52391 100644
--- a/drivers/irqchip/irq-riscv-imsic-state.c
+++ b/drivers/irqchip/irq-riscv-imsic-state.c
@@ -311,6 +311,23 @@ void imsic_vector_unmask(struct imsic_vector *vec)
 	raw_spin_unlock(&lpriv->lock);
 }
 
+void imsic_vector_force_move_cleanup(struct imsic_vector *vec)
+{
+	struct imsic_local_priv *lpriv;
+	struct imsic_vector *mvec;
+	unsigned long flags;
+
+	lpriv = per_cpu_ptr(imsic->lpriv, vec->cpu);
+	raw_spin_lock_irqsave(&lpriv->lock, flags);
+
+	mvec = READ_ONCE(vec->move_prev);
+	WRITE_ONCE(vec->move_prev, NULL);
+	if (mvec)
+		imsic_vector_free(mvec);
+
+	raw_spin_unlock_irqrestore(&lpriv->lock, flags);
+}
+
 static bool imsic_vector_move_update(struct imsic_local_priv *lpriv,
 				     struct imsic_vector *vec, bool is_old_vec,
 				     bool new_enable, struct imsic_vector *move_vec)
diff --git a/drivers/irqchip/irq-riscv-imsic-state.h b/drivers/irqchip/irq-riscv-imsic-state.h
index f02842b84ed58..19dea0c77738e 100644
--- a/drivers/irqchip/irq-riscv-imsic-state.h
+++ b/drivers/irqchip/irq-riscv-imsic-state.h
@@ -91,6 +91,7 @@ static inline struct imsic_vector *imsic_vector_get_move(struct imsic_vector *ve
 	return READ_ONCE(vec->move_prev);
 }
 
+void imsic_vector_force_move_cleanup(struct imsic_vector *vec);
 void imsic_vector_move(struct imsic_vector *old_vec, struct imsic_vector *new_vec);
 
 struct imsic_vector *imsic_vector_from_local_id(unsigned int cpu, unsigned int local_id);

From 0bd55080ba9e3c16719f75006fd85b932c85f2f4 Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 17 Feb 2025 14:26:55 +0530
Subject: [PATCH 0402/1173] irqchip/riscv-imsic: Avoid interrupt translation in
 interrupt handler

Currently, imsic_handle_irq() uses generic_handle_domain_irq() to handle
the interrupt, which internally has an extra step of resolving hwirq using
domain.

Avoid the translation step by replacing the hardware interrupt number with
the Linux interrupt number in the IMSIC vector data and directly call
generic_handle_irq().

Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250217085657.789309-10-apatel@ventanamicro.com
---
 drivers/irqchip/irq-riscv-imsic-early.c    | 6 ++----
 drivers/irqchip/irq-riscv-imsic-platform.c | 2 +-
 drivers/irqchip/irq-riscv-imsic-state.c    | 8 ++++----
 drivers/irqchip/irq-riscv-imsic-state.h    | 4 ++--
 4 files changed, 9 insertions(+), 11 deletions(-)

diff --git a/drivers/irqchip/irq-riscv-imsic-early.c b/drivers/irqchip/irq-riscv-imsic-early.c
index b5def6268936e..d2e8ed70d396d 100644
--- a/drivers/irqchip/irq-riscv-imsic-early.c
+++ b/drivers/irqchip/irq-riscv-imsic-early.c
@@ -73,7 +73,7 @@ static int __init imsic_ipi_domain_init(void) { return 0; }
 static void imsic_handle_irq(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
-	int err, cpu = smp_processor_id();
+	int cpu = smp_processor_id();
 	struct imsic_vector *vec;
 	unsigned long local_id;
 
@@ -103,9 +103,7 @@ static void imsic_handle_irq(struct irq_desc *desc)
 			continue;
 		}
 
-		err = generic_handle_domain_irq(imsic->base_domain, vec->hwirq);
-		if (unlikely(err))
-			pr_warn_ratelimited("hwirq 0x%x mapping not found\n", vec->hwirq);
+		generic_handle_irq(vec->irq);
 	}
 
 	chained_irq_exit(chip, desc);
diff --git a/drivers/irqchip/irq-riscv-imsic-platform.c b/drivers/irqchip/irq-riscv-imsic-platform.c
index b9e3f9030bdf0..6bf5d63f614e1 100644
--- a/drivers/irqchip/irq-riscv-imsic-platform.c
+++ b/drivers/irqchip/irq-riscv-imsic-platform.c
@@ -111,7 +111,7 @@ static int imsic_irq_set_affinity(struct irq_data *d, const struct cpumask *mask
 		return -EBUSY;
 
 	/* Get a new vector on the desired set of CPUs */
-	new_vec = imsic_vector_alloc(old_vec->hwirq, mask_val);
+	new_vec = imsic_vector_alloc(old_vec->irq, mask_val);
 	if (!new_vec)
 		return -ENOSPC;
 
diff --git a/drivers/irqchip/irq-riscv-imsic-state.c b/drivers/irqchip/irq-riscv-imsic-state.c
index eb0a9b6a52391..b0849af700c33 100644
--- a/drivers/irqchip/irq-riscv-imsic-state.c
+++ b/drivers/irqchip/irq-riscv-imsic-state.c
@@ -422,7 +422,7 @@ struct imsic_vector *imsic_vector_from_local_id(unsigned int cpu, unsigned int l
 	return &lpriv->vectors[local_id];
 }
 
-struct imsic_vector *imsic_vector_alloc(unsigned int hwirq, const struct cpumask *mask)
+struct imsic_vector *imsic_vector_alloc(unsigned int irq, const struct cpumask *mask)
 {
 	struct imsic_vector *vec = NULL;
 	struct imsic_local_priv *lpriv;
@@ -438,7 +438,7 @@ struct imsic_vector *imsic_vector_alloc(unsigned int hwirq, const struct cpumask
 
 	lpriv = per_cpu_ptr(imsic->lpriv, cpu);
 	vec = &lpriv->vectors[local_id];
-	vec->hwirq = hwirq;
+	vec->irq = irq;
 	vec->enable = false;
 	vec->move_next = NULL;
 	vec->move_prev = NULL;
@@ -451,7 +451,7 @@ void imsic_vector_free(struct imsic_vector *vec)
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&imsic->matrix_lock, flags);
-	vec->hwirq = UINT_MAX;
+	vec->irq = 0;
 	irq_matrix_free(imsic->matrix, vec->cpu, vec->local_id, false);
 	raw_spin_unlock_irqrestore(&imsic->matrix_lock, flags);
 }
@@ -510,7 +510,7 @@ static int __init imsic_local_init(void)
 			vec = &lpriv->vectors[i];
 			vec->cpu = cpu;
 			vec->local_id = i;
-			vec->hwirq = UINT_MAX;
+			vec->irq = 0;
 		}
 	}
 
diff --git a/drivers/irqchip/irq-riscv-imsic-state.h b/drivers/irqchip/irq-riscv-imsic-state.h
index 19dea0c77738e..3202ffa4e849d 100644
--- a/drivers/irqchip/irq-riscv-imsic-state.h
+++ b/drivers/irqchip/irq-riscv-imsic-state.h
@@ -20,7 +20,7 @@ struct imsic_vector {
 	unsigned int				cpu;
 	unsigned int				local_id;
 	/* Details saved by driver in the vector */
-	unsigned int				hwirq;
+	unsigned int				irq;
 	/* Details accessed using local lock held */
 	bool					enable;
 	struct imsic_vector			*move_next;
@@ -96,7 +96,7 @@ void imsic_vector_move(struct imsic_vector *old_vec, struct imsic_vector *new_ve
 
 struct imsic_vector *imsic_vector_from_local_id(unsigned int cpu, unsigned int local_id);
 
-struct imsic_vector *imsic_vector_alloc(unsigned int hwirq, const struct cpumask *mask);
+struct imsic_vector *imsic_vector_alloc(unsigned int irq, const struct cpumask *mask);
 void imsic_vector_free(struct imsic_vector *vector);
 
 void imsic_vector_debug_show(struct seq_file *m, struct imsic_vector *vec, int ind);

From c99e1e1d0850ff157f1bc16871acd2dff5a9bcc3 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 22 Jan 2025 07:54:33 +0100
Subject: [PATCH 0403/1173] vbox: add HAS_IOPORT dependency

The vboxguest driver depends on port I/O for debug output:

include/asm-generic/io.h:626:15: error: call to '_outl' declared with attribute error: outl() requires CONFIG_HAS_IOPORT
  626 | #define _outl _outl
include/asm-generic/io.h:663:14: note: in expansion of macro '_outl'
  663 | #define outl _outl
      |              ^~~~~
drivers/virt/vboxguest/vboxguest_utils.c:102:9: note: in expansion of macro 'outl'
  102 |         outl(phys_req, gdev->io_port + VMMDEV_PORT_OFF_REQUEST);
      |         ^~~~

Most arm64 platforms don't actually support port I/O, though it is
currently enabled unconditionally. Refine the vbox dependency to allow
turning HAS_IOPORT off in the future when building for platforms without
port I/O and allow compile-testing on all architectures.

Fixes: 5cf8f938bf5c ("vbox: Enable VBOXGUEST and VBOXSF_FS on ARM64")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20250122065445.1469218-1-arnd@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/virt/vboxguest/Kconfig | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/virt/vboxguest/Kconfig b/drivers/virt/vboxguest/Kconfig
index 11b153e7454e4..eaba28c95e733 100644
--- a/drivers/virt/vboxguest/Kconfig
+++ b/drivers/virt/vboxguest/Kconfig
@@ -1,7 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config VBOXGUEST
 	tristate "Virtual Box Guest integration support"
-	depends on (ARM64 || X86) && PCI && INPUT
+	depends on (ARM64 || X86 || COMPILE_TEST) && PCI && INPUT
+	depends on HAS_IOPORT
 	help
 	  This is a driver for the Virtual Box Guest PCI device used in
 	  Virtual Box virtual machines. Enabling this driver will add

From 896f8e436f9951fa9ef68dab0a3d399ec3a6e1d7 Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 17 Feb 2025 14:26:56 +0530
Subject: [PATCH 0404/1173] irqchip/riscv-imsic: Special handling for
 non-atomic device MSI update

Devices, which have a non-atomic MSI update, might see an intermediate
state when changing the target IMSIC vector from one CPU to another.

To avoid losing interrupts due to this intermediate state, do the following
just like x86 APIC:

 1) First write a temporary IMSIC vector to the device which has the same
    MSI address as the old IMSIC vector and MSI data pointing to the new
    IMSIC vector.

 2) Next write the new IMSIC vector to the device.

Based on the above, the __imsic_local_sync() must check pending status of
both old MSI data and new MSI data on the old CPU. In addition, the
movement of IMSIC vector for non-atomic device MSI update must be done in
interrupt context using IRQCHIP_MOVE_DEFERRED.

Implememnt the logic and enforce the chip flag for PCI/MSI[X].

Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250217085657.789309-11-apatel@ventanamicro.com
---
 drivers/irqchip/irq-riscv-imsic-platform.c | 87 +++++++++++++++++++---
 drivers/irqchip/irq-riscv-imsic-state.c    | 30 +++++++-
 2 files changed, 102 insertions(+), 15 deletions(-)

diff --git a/drivers/irqchip/irq-riscv-imsic-platform.c b/drivers/irqchip/irq-riscv-imsic-platform.c
index 6bf5d63f614e1..b8ae67c25b37a 100644
--- a/drivers/irqchip/irq-riscv-imsic-platform.c
+++ b/drivers/irqchip/irq-riscv-imsic-platform.c
@@ -64,6 +64,11 @@ static int imsic_irq_retrigger(struct irq_data *d)
 	return 0;
 }
 
+static void imsic_irq_ack(struct irq_data *d)
+{
+	irq_move_irq(d);
+}
+
 static void imsic_irq_compose_vector_msg(struct imsic_vector *vec, struct msi_msg *msg)
 {
 	phys_addr_t msi_addr;
@@ -97,6 +102,21 @@ static int imsic_irq_set_affinity(struct irq_data *d, const struct cpumask *mask
 				  bool force)
 {
 	struct imsic_vector *old_vec, *new_vec;
+	struct imsic_vector tmp_vec;
+
+	/*
+	 * Requirements for the downstream irqdomains (or devices):
+	 *
+	 * 1) Downstream irqdomains (or devices) with atomic MSI update can
+	 *    happily do imsic_irq_set_affinity() in the process-context on
+	 *    any CPU so the irqchip of such irqdomains must not set the
+	 *    IRQCHIP_MOVE_DEFERRED flag.
+	 *
+	 * 2) Downstream irqdomains (or devices) with non-atomic MSI update
+	 *    must use imsic_irq_set_affinity() in nterrupt-context upon
+	 *    the next device interrupt so the irqchip of such irqdomains
+	 *    must set the IRQCHIP_MOVE_DEFERRED flag.
+	 */
 
 	old_vec = irq_data_get_irq_chip_data(d);
 	if (WARN_ON(!old_vec))
@@ -115,6 +135,32 @@ static int imsic_irq_set_affinity(struct irq_data *d, const struct cpumask *mask
 	if (!new_vec)
 		return -ENOSPC;
 
+	/*
+	 * Device having non-atomic MSI update might see an intermediate
+	 * state when changing target IMSIC vector from one CPU to another.
+	 *
+	 * To avoid losing interrupt to such intermediate state, do the
+	 * following (just like x86 APIC):
+	 *
+	 * 1) First write a temporary IMSIC vector to the device which
+	 * has MSI address same as the old IMSIC vector but MSI data
+	 * matches the new IMSIC vector.
+	 *
+	 * 2) Next write the new IMSIC vector to the device.
+	 *
+	 * Based on the above, __imsic_local_sync() must check pending
+	 * status of both old MSI data and new MSI data on the old CPU.
+	 */
+	if (!irq_can_move_in_process_context(d) &&
+	    new_vec->local_id != old_vec->local_id) {
+		/* Setup temporary vector */
+		tmp_vec.cpu = old_vec->cpu;
+		tmp_vec.local_id = new_vec->local_id;
+
+		/* Point device to the temporary vector */
+		imsic_msi_update_msg(irq_get_irq_data(d->irq), &tmp_vec);
+	}
+
 	/* Point device to the new vector */
 	imsic_msi_update_msg(irq_get_irq_data(d->irq), new_vec);
 
@@ -163,17 +209,17 @@ static void imsic_irq_force_complete_move(struct irq_data *d)
 #endif
 
 static struct irq_chip imsic_irq_base_chip = {
-	.name			= "IMSIC",
-	.irq_mask		= imsic_irq_mask,
-	.irq_unmask		= imsic_irq_unmask,
+	.name				= "IMSIC",
+	.irq_mask			= imsic_irq_mask,
+	.irq_unmask			= imsic_irq_unmask,
 #ifdef CONFIG_SMP
-	.irq_set_affinity	= imsic_irq_set_affinity,
-	.irq_force_complete_move = imsic_irq_force_complete_move,
+	.irq_set_affinity		= imsic_irq_set_affinity,
+	.irq_force_complete_move	= imsic_irq_force_complete_move,
 #endif
-	.irq_retrigger		= imsic_irq_retrigger,
-	.irq_compose_msi_msg	= imsic_irq_compose_msg,
-	.flags			= IRQCHIP_SKIP_SET_WAKE |
-				  IRQCHIP_MASK_ON_SUSPEND,
+	.irq_retrigger			= imsic_irq_retrigger,
+	.irq_ack			= imsic_irq_ack,
+	.irq_compose_msi_msg		= imsic_irq_compose_msg,
+	.flags				= IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MASK_ON_SUSPEND,
 };
 
 static int imsic_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
@@ -190,7 +236,7 @@ static int imsic_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
 		return -ENOSPC;
 
 	irq_domain_set_info(domain, virq, virq, &imsic_irq_base_chip, vec,
-			    handle_simple_irq, NULL, NULL);
+			    handle_edge_irq, NULL, NULL);
 	irq_set_noprobe(virq);
 	irq_set_affinity(virq, cpu_online_mask);
 	irq_data_update_effective_affinity(irq_get_irq_data(virq), cpumask_of(vec->cpu));
@@ -229,15 +275,34 @@ static const struct irq_domain_ops imsic_base_domain_ops = {
 #endif
 };
 
+static bool imsic_init_dev_msi_info(struct device *dev, struct irq_domain *domain,
+				    struct irq_domain *real_parent, struct msi_domain_info *info)
+{
+	if (!msi_lib_init_dev_msi_info(dev, domain, real_parent, info))
+		return false;
+
+	switch (info->bus_token) {
+	case DOMAIN_BUS_PCI_DEVICE_MSI:
+	case DOMAIN_BUS_PCI_DEVICE_MSIX:
+		info->chip->flags |= IRQCHIP_MOVE_DEFERRED;
+		break;
+	default:
+		break;
+	}
+
+	return true;
+}
+
 static const struct msi_parent_ops imsic_msi_parent_ops = {
 	.supported_flags	= MSI_GENERIC_FLAGS_MASK |
 				  MSI_FLAG_PCI_MSIX,
 	.required_flags		= MSI_FLAG_USE_DEF_DOM_OPS |
 				  MSI_FLAG_USE_DEF_CHIP_OPS |
 				  MSI_FLAG_PCI_MSI_MASK_PARENT,
+	.chip_flags		= MSI_CHIP_FLAG_SET_ACK,
 	.bus_select_token	= DOMAIN_BUS_NEXUS,
 	.bus_select_mask	= MATCH_PCI_MSI | MATCH_PLATFORM_MSI,
-	.init_dev_msi_info	= msi_lib_init_dev_msi_info,
+	.init_dev_msi_info	= imsic_init_dev_msi_info,
 };
 
 int imsic_irqdomain_init(void)
diff --git a/drivers/irqchip/irq-riscv-imsic-state.c b/drivers/irqchip/irq-riscv-imsic-state.c
index b0849af700c33..bdf5cd2037f28 100644
--- a/drivers/irqchip/irq-riscv-imsic-state.c
+++ b/drivers/irqchip/irq-riscv-imsic-state.c
@@ -126,8 +126,8 @@ void __imsic_eix_update(unsigned long base_id, unsigned long num_id, bool pend,
 
 static bool __imsic_local_sync(struct imsic_local_priv *lpriv)
 {
-	struct imsic_local_config *mlocal;
-	struct imsic_vector *vec, *mvec;
+	struct imsic_local_config *tlocal, *mlocal;
+	struct imsic_vector *vec, *tvec, *mvec;
 	bool ret = true;
 	int i;
 
@@ -169,13 +169,35 @@ static bool __imsic_local_sync(struct imsic_local_priv *lpriv)
 		 */
 		mvec = READ_ONCE(vec->move_next);
 		if (mvec) {
-			if (__imsic_id_read_clear_pending(i)) {
+			/*
+			 * Devices having non-atomic MSI update might see
+			 * an intermediate state so check both old ID and
+			 * new ID for pending interrupts.
+			 *
+			 * For details, see imsic_irq_set_affinity().
+			 */
+			tvec = vec->local_id == mvec->local_id ?
+				NULL : &lpriv->vectors[mvec->local_id];
+
+			if (tvec && !irq_can_move_in_process_context(irq_get_irq_data(vec->irq)) &&
+			    __imsic_id_read_clear_pending(tvec->local_id)) {
+				/* Retrigger temporary vector if it was already in-use */
+				if (READ_ONCE(tvec->enable)) {
+					tlocal = per_cpu_ptr(imsic->global.local, tvec->cpu);
+					writel_relaxed(tvec->local_id, tlocal->msi_va);
+				}
+
+				mlocal = per_cpu_ptr(imsic->global.local, mvec->cpu);
+				writel_relaxed(mvec->local_id, mlocal->msi_va);
+			}
+
+			if (__imsic_id_read_clear_pending(vec->local_id)) {
 				mlocal = per_cpu_ptr(imsic->global.local, mvec->cpu);
 				writel_relaxed(mvec->local_id, mlocal->msi_va);
 			}
 
 			WRITE_ONCE(vec->move_next, NULL);
-			imsic_vector_free(&lpriv->vectors[i]);
+			imsic_vector_free(vec);
 		}
 
 skip:

From dcb0d43ba8eb9517e70b1a0e4b0ae0ab657a0e5a Mon Sep 17 00:00:00 2001
From: Visweswara Tanuku <quic_vtanuku@quicinc.com>
Date: Fri, 24 Jan 2025 04:57:40 -0800
Subject: [PATCH 0405/1173] slimbus: messaging: Free transaction ID in delayed
 interrupt scenario

In case of interrupt delay for any reason, slim_do_transfer()
returns timeout error but the transaction ID (TID) is not freed.
This results into invalid memory access inside
qcom_slim_ngd_rx_msgq_cb() due to invalid TID.

Fix the issue by freeing the TID in slim_do_transfer() before
returning timeout error to avoid invalid memory access.

Call trace:
__memcpy_fromio+0x20/0x190
qcom_slim_ngd_rx_msgq_cb+0x130/0x290 [slim_qcom_ngd_ctrl]
vchan_complete+0x2a0/0x4a0
tasklet_action_common+0x274/0x700
tasklet_action+0x28/0x3c
_stext+0x188/0x620
run_ksoftirqd+0x34/0x74
smpboot_thread_fn+0x1d8/0x464
kthread+0x178/0x238
ret_from_fork+0x10/0x20
Code: aa0003e8 91000429 f100044a 3940002b (3800150b)
---[ end trace 0fe00bec2b975c99 ]---
Kernel panic - not syncing: Oops: Fatal exception in interrupt.

Fixes: afbdcc7c384b ("slimbus: Add messaging APIs to slimbus framework")
Cc: stable <stable@kernel.org>
Signed-off-by: Visweswara Tanuku <quic_vtanuku@quicinc.com>
Link: https://lore.kernel.org/r/20250124125740.16897-1-quic_vtanuku@quicinc.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/slimbus/messaging.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/slimbus/messaging.c b/drivers/slimbus/messaging.c
index e7aa9bd4b44b8..6f01d944f9c65 100644
--- a/drivers/slimbus/messaging.c
+++ b/drivers/slimbus/messaging.c
@@ -148,8 +148,9 @@ int slim_do_transfer(struct slim_controller *ctrl, struct slim_msg_txn *txn)
 	}
 
 	ret = ctrl->xfer_msg(ctrl, txn);
-
-	if (!ret && need_tid && !txn->msg->comp) {
+	if (ret == -ETIMEDOUT) {
+		slim_free_txn_tid(ctrl, txn);
+	} else if (!ret && need_tid && !txn->msg->comp) {
 		unsigned long ms = txn->rl + HZ;
 
 		time_left = wait_for_completion_timeout(txn->comp,

From e77aff5528a183462714f750e45add6cc71e276a Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Thu, 30 Jan 2025 21:58:22 +0000
Subject: [PATCH 0406/1173] binderfs: fix use-after-free in binder_devices

Devices created through binderfs are added to the global binder_devices
list but are not removed before being destroyed. This leads to dangling
pointers in the list and subsequent use-after-free errors:

  ==================================================================
  BUG: KASAN: slab-use-after-free in binder_add_device+0x5c/0x9c
  Write of size 8 at addr ffff0000c258d708 by task mount/653

  CPU: 7 UID: 0 PID: 653 Comm: mount Not tainted 6.13.0-09030-g6d61a53dd6f5 #1
  Hardware name: linux,dummy-virt (DT)
  Call trace:
   binder_add_device+0x5c/0x9c
   binderfs_binder_device_create+0x690/0x84c
   [...]
   __arm64_sys_mount+0x324/0x3bc

  Allocated by task 632:
   binderfs_binder_device_create+0x168/0x84c
   binder_ctl_ioctl+0xfc/0x184
   [...]
   __arm64_sys_ioctl+0x110/0x150

  Freed by task 649:
   kfree+0xe0/0x338
   binderfs_evict_inode+0x138/0x1dc
   [...]
  ==================================================================

Remove devices from binder_devices before destroying them.

Cc: Li Li <dualli@google.com>
Reported-by: syzbot+7015dcf45953112c8b45@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=7015dcf45953112c8b45
Fixes: 12d909cac1e1 ("binderfs: add new binder devices to binder_devices")
Signed-off-by: Carlos Llamas <cmllamas@google.com>
Tested-by: syzbot+7015dcf45953112c8b45@syzkaller.appspotmail.com
Link: https://lore.kernel.org/r/20250130215823.1518990-1-cmllamas@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binderfs.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/android/binderfs.c b/drivers/android/binderfs.c
index bc6bae76ccaf1..94c6446604fc9 100644
--- a/drivers/android/binderfs.c
+++ b/drivers/android/binderfs.c
@@ -274,6 +274,7 @@ static void binderfs_evict_inode(struct inode *inode)
 	mutex_unlock(&binderfs_minors_mutex);
 
 	if (refcount_dec_and_test(&device->ref)) {
+		hlist_del_init(&device->hlist);
 		kfree(device->context.name);
 		kfree(device);
 	}

From 819cec1dc47cdeac8f5dd6ba81c1dbee2a68c3bb Mon Sep 17 00:00:00 2001
From: Haoyu Li <lihaoyu499@gmail.com>
Date: Thu, 30 Jan 2025 19:58:11 +0800
Subject: [PATCH 0407/1173] drivers: virt: acrn: hsm: Use kzalloc to avoid info
 leak in pmcmd_ioctl

In the "pmcmd_ioctl" function, three memory objects allocated by
kmalloc are initialized by "hcall_get_cpu_state", which are then
copied to user space. The initializer is indeed implemented in
"acrn_hypercall2" (arch/x86/include/asm/acrn.h). There is a risk of
information leakage due to uninitialized bytes.

Fixes: 3d679d5aec64 ("virt: acrn: Introduce interfaces to query C-states and P-states allowed by hypervisor")
Signed-off-by: Haoyu Li <lihaoyu499@gmail.com>
Cc: stable <stable@kernel.org>
Acked-by: Fei Li <fei1.li@intel.com>
Link: https://lore.kernel.org/r/20250130115811.92424-1-lihaoyu499@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/virt/acrn/hsm.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/virt/acrn/hsm.c b/drivers/virt/acrn/hsm.c
index c24036c4e51ec..e4e196abdaac9 100644
--- a/drivers/virt/acrn/hsm.c
+++ b/drivers/virt/acrn/hsm.c
@@ -49,7 +49,7 @@ static int pmcmd_ioctl(u64 cmd, void __user *uptr)
 	switch (cmd & PMCMD_TYPE_MASK) {
 	case ACRN_PMCMD_GET_PX_CNT:
 	case ACRN_PMCMD_GET_CX_CNT:
-		pm_info = kmalloc(sizeof(u64), GFP_KERNEL);
+		pm_info = kzalloc(sizeof(u64), GFP_KERNEL);
 		if (!pm_info)
 			return -ENOMEM;
 
@@ -64,7 +64,7 @@ static int pmcmd_ioctl(u64 cmd, void __user *uptr)
 		kfree(pm_info);
 		break;
 	case ACRN_PMCMD_GET_PX_DATA:
-		px_data = kmalloc(sizeof(*px_data), GFP_KERNEL);
+		px_data = kzalloc(sizeof(*px_data), GFP_KERNEL);
 		if (!px_data)
 			return -ENOMEM;
 
@@ -79,7 +79,7 @@ static int pmcmd_ioctl(u64 cmd, void __user *uptr)
 		kfree(px_data);
 		break;
 	case ACRN_PMCMD_GET_CX_DATA:
-		cx_data = kmalloc(sizeof(*cx_data), GFP_KERNEL);
+		cx_data = kzalloc(sizeof(*cx_data), GFP_KERNEL);
 		if (!cx_data)
 			return -ENOMEM;
 

From 038ef0754aae76f79b147b8867f9250e6a976872 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 7 Feb 2025 00:03:11 +0200
Subject: [PATCH 0408/1173] eeprom: digsy_mtc: Make GPIO lookup table match the
 device

The dev_id value in the GPIO lookup table must match to
the device instance name, which in this case is combined
of name and platform device ID, i.e. "spi_gpio.1". But
the table assumed that there was no platform device ID
defined, which is wrong. Fix the dev_id value accordingly.

Fixes: 9b00bc7b901f ("spi: spi-gpio: Rewrite to use GPIO descriptors")
Cc: stable <stable@kernel.org>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20250206220311.1554075-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/eeprom/digsy_mtc_eeprom.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/misc/eeprom/digsy_mtc_eeprom.c b/drivers/misc/eeprom/digsy_mtc_eeprom.c
index 88888485e6f8e..ee58f7ce5bfa9 100644
--- a/drivers/misc/eeprom/digsy_mtc_eeprom.c
+++ b/drivers/misc/eeprom/digsy_mtc_eeprom.c
@@ -50,7 +50,7 @@ static struct platform_device digsy_mtc_eeprom = {
 };
 
 static struct gpiod_lookup_table eeprom_spi_gpiod_table = {
-	.dev_id         = "spi_gpio",
+	.dev_id         = "spi_gpio.1",
 	.table          = {
 		GPIO_LOOKUP("gpio@b00", GPIO_EEPROM_CLK,
 			    "sck", GPIO_ACTIVE_HIGH),

From 6d991f569c5ef6eaeadf1238df2c36e3975233ad Mon Sep 17 00:00:00 2001
From: Thadeu Lima de Souza Cascardo <cascardo@igalia.com>
Date: Thu, 23 Jan 2025 09:32:49 -0300
Subject: [PATCH 0409/1173] char: misc: deallocate static minor in error path

When creating sysfs files fail, the allocated minor must be freed such that
it can be later reused. That is specially harmful for static minor numbers,
since those would always fail to register later on.

Fixes: 6d04d2b554b1 ("misc: misc_minor_alloc to use ida for all dynamic/misc dynamic minors")
Cc: stable <stable@kernel.org>
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@igalia.com>
Link: https://lore.kernel.org/r/20250123123249.4081674-5-cascardo@igalia.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/char/misc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/char/misc.c b/drivers/char/misc.c
index 2cf595d2e10b8..f7dd455dd0dd3 100644
--- a/drivers/char/misc.c
+++ b/drivers/char/misc.c
@@ -264,8 +264,8 @@ int misc_register(struct miscdevice *misc)
 		device_create_with_groups(&misc_class, misc->parent, dev,
 					  misc, misc->groups, "%s", misc->name);
 	if (IS_ERR(misc->this_device)) {
+		misc_minor_free(misc->minor);
 		if (is_dynamic) {
-			misc_minor_free(misc->minor);
 			misc->minor = MISC_DYNAMIC_MINOR;
 		}
 		err = PTR_ERR(misc->this_device);

From 32ce5d87d52213a50a513750f01a56f4d01f50cb Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan+linaro@kernel.org>
Date: Fri, 14 Feb 2025 11:21:30 +0100
Subject: [PATCH 0410/1173] bus: simple-pm-bus: fix forced runtime PM use

The simple-pm-bus driver only enables runtime PM for some buses
('simple-pm-bus') yet has started calling pm_runtime_force_suspend() and
pm_runtime_force_resume() during system suspend unconditionally.

This currently works, but that is not obvious and depends on
implementation details which may change at some point.

Add dedicated system sleep ops and only call pm_runtime_force_suspend()
and pm_runtime_force_resume() for buses that use runtime PM to avoid any
future surprises.

Fixes: c45839309c3d ("drivers: bus: simple-pm-bus: Use clocks")
Cc: Liu Ying <victor.liu@nxp.com>
Signed-off-by: Johan Hovold <johan+linaro@kernel.org>
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Acked-by: Liu Ying <victor.liu@nxp.com>
Acked-by: Rafael J. Wysocki <rafael@kernel.org>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20250214102130.3000-1-johan+linaro@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/simple-pm-bus.c | 22 +++++++++++++++++++++-
 1 file changed, 21 insertions(+), 1 deletion(-)

diff --git a/drivers/bus/simple-pm-bus.c b/drivers/bus/simple-pm-bus.c
index 5dea31769f9a8..d8e029e7e53f7 100644
--- a/drivers/bus/simple-pm-bus.c
+++ b/drivers/bus/simple-pm-bus.c
@@ -109,9 +109,29 @@ static int simple_pm_bus_runtime_resume(struct device *dev)
 	return 0;
 }
 
+static int simple_pm_bus_suspend(struct device *dev)
+{
+	struct simple_pm_bus *bus = dev_get_drvdata(dev);
+
+	if (!bus)
+		return 0;
+
+	return pm_runtime_force_suspend(dev);
+}
+
+static int simple_pm_bus_resume(struct device *dev)
+{
+	struct simple_pm_bus *bus = dev_get_drvdata(dev);
+
+	if (!bus)
+		return 0;
+
+	return pm_runtime_force_resume(dev);
+}
+
 static const struct dev_pm_ops simple_pm_bus_pm_ops = {
 	RUNTIME_PM_OPS(simple_pm_bus_runtime_suspend, simple_pm_bus_runtime_resume, NULL)
-	NOIRQ_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume)
+	NOIRQ_SYSTEM_SLEEP_PM_OPS(simple_pm_bus_suspend, simple_pm_bus_resume)
 };
 
 #define ONLY_BUS	((void *) 1) /* Match if the device is only a bus. */

From b4c173dfbb6c78568578ff18f9e8822d7bd0e31b Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@redhat.com>
Date: Thu, 20 Feb 2025 11:02:58 +0100
Subject: [PATCH 0411/1173] fuse: don't truncate cached, mutated symlink

Fuse allows the value of a symlink to change and this property is exploited
by some filesystems (e.g. CVMFS).

It has been observed, that sometimes after changing the symlink contents,
the value is truncated to the old size.

This is caused by fuse_getattr() racing with fuse_reverse_inval_inode().
fuse_reverse_inval_inode() updates the fuse_inode's attr_version, which
results in fuse_change_attributes() exiting before updating the cached
attributes

This is okay, as the cached attributes remain invalid and the next call to
fuse_change_attributes() will likely update the inode with the correct
values.

The reason this causes problems is that cached symlinks will be
returned through page_get_link(), which truncates the symlink to
inode->i_size.  This is correct for filesystems that don't mutate
symlinks, but in this case it causes bad behavior.

The solution is to just remove this truncation.  This can cause a
regression in a filesystem that relies on supplying a symlink larger than
the file size, but this is unlikely.  If that happens we'd need to make
this behavior conditional.

Reported-by: Laura Promberger <laura.promberger@cern.ch>
Tested-by: Sam Lewis <samclewis@google.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Link: https://lore.kernel.org/r/20250220100258.793363-1-mszeredi@redhat.com
Reviewed-by: Bernd Schubert <bschubert@ddn.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/fuse/dir.c      |  2 +-
 fs/namei.c         | 24 +++++++++++++++++++-----
 include/linux/fs.h |  2 ++
 3 files changed, 22 insertions(+), 6 deletions(-)

diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 198862b086ff7..3805f9b06c9d2 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1636,7 +1636,7 @@ static const char *fuse_get_link(struct dentry *dentry, struct inode *inode,
 		goto out_err;
 
 	if (fc->cache_symlinks)
-		return page_get_link(dentry, inode, callback);
+		return page_get_link_raw(dentry, inode, callback);
 
 	err = -ECHILD;
 	if (!dentry)
diff --git a/fs/namei.c b/fs/namei.c
index 3ab9440c5b931..ecb7b95c2ca33 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -5356,10 +5356,9 @@ const char *vfs_get_link(struct dentry *dentry, struct delayed_call *done)
 EXPORT_SYMBOL(vfs_get_link);
 
 /* get the link contents into pagecache */
-const char *page_get_link(struct dentry *dentry, struct inode *inode,
-			  struct delayed_call *callback)
+static char *__page_get_link(struct dentry *dentry, struct inode *inode,
+			     struct delayed_call *callback)
 {
-	char *kaddr;
 	struct page *page;
 	struct address_space *mapping = inode->i_mapping;
 
@@ -5378,8 +5377,23 @@ const char *page_get_link(struct dentry *dentry, struct inode *inode,
 	}
 	set_delayed_call(callback, page_put_link, page);
 	BUG_ON(mapping_gfp_mask(mapping) & __GFP_HIGHMEM);
-	kaddr = page_address(page);
-	nd_terminate_link(kaddr, inode->i_size, PAGE_SIZE - 1);
+	return page_address(page);
+}
+
+const char *page_get_link_raw(struct dentry *dentry, struct inode *inode,
+			      struct delayed_call *callback)
+{
+	return __page_get_link(dentry, inode, callback);
+}
+EXPORT_SYMBOL_GPL(page_get_link_raw);
+
+const char *page_get_link(struct dentry *dentry, struct inode *inode,
+					struct delayed_call *callback)
+{
+	char *kaddr = __page_get_link(dentry, inode, callback);
+
+	if (!IS_ERR(kaddr))
+		nd_terminate_link(kaddr, inode->i_size, PAGE_SIZE - 1);
 	return kaddr;
 }
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 2c3b2f8a621f7..9346adf28f7bc 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3452,6 +3452,8 @@ extern const struct file_operations generic_ro_fops;
 
 extern int readlink_copy(char __user *, int, const char *, int);
 extern int page_readlink(struct dentry *, char __user *, int);
+extern const char *page_get_link_raw(struct dentry *, struct inode *,
+				     struct delayed_call *);
 extern const char *page_get_link(struct dentry *, struct inode *,
 				 struct delayed_call *);
 extern void page_put_link(void *);

From 782cffeec9ad96daa64ffb2d527b2a052fb02552 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Wed, 19 Feb 2025 06:10:05 -0800
Subject: [PATCH 0412/1173] perf/x86/intel: Fix event constraints for LNC

According to the latest event list, update the event constraint tables
for Lion Cove core.

The general rule (the event codes < 0x90 are restricted to counters
0-3.) has been removed. There is no restriction for most of the
performance monitoring events.

Fixes: a932aa0e868f ("perf/x86: Add Lunar Lake and Arrow Lake support")
Reported-by: Amiri Khalil <amiri.khalil@intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20250219141005.2446823-1-kan.liang@linux.intel.com
---
 arch/x86/events/intel/core.c | 20 +++++++-------------
 arch/x86/events/intel/ds.c   |  2 +-
 2 files changed, 8 insertions(+), 14 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index e86333eee2668..cdcebf30468a0 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -397,34 +397,28 @@ static struct event_constraint intel_lnc_event_constraints[] = {
 	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_FETCH_LAT, 6),
 	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_MEM_BOUND, 7),
 
+	INTEL_EVENT_CONSTRAINT(0x20, 0xf),
+
+	INTEL_UEVENT_CONSTRAINT(0x012a, 0xf),
+	INTEL_UEVENT_CONSTRAINT(0x012b, 0xf),
 	INTEL_UEVENT_CONSTRAINT(0x0148, 0x4),
 	INTEL_UEVENT_CONSTRAINT(0x0175, 0x4),
 
 	INTEL_EVENT_CONSTRAINT(0x2e, 0x3ff),
 	INTEL_EVENT_CONSTRAINT(0x3c, 0x3ff),
-	/*
-	 * Generally event codes < 0x90 are restricted to counters 0-3.
-	 * The 0x2E and 0x3C are exception, which has no restriction.
-	 */
-	INTEL_EVENT_CONSTRAINT_RANGE(0x01, 0x8f, 0xf),
 
-	INTEL_UEVENT_CONSTRAINT(0x01a3, 0xf),
-	INTEL_UEVENT_CONSTRAINT(0x02a3, 0xf),
 	INTEL_UEVENT_CONSTRAINT(0x08a3, 0x4),
 	INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4),
 	INTEL_UEVENT_CONSTRAINT(0x04a4, 0x1),
 	INTEL_UEVENT_CONSTRAINT(0x08a4, 0x1),
 	INTEL_UEVENT_CONSTRAINT(0x10a4, 0x1),
 	INTEL_UEVENT_CONSTRAINT(0x01b1, 0x8),
+	INTEL_UEVENT_CONSTRAINT(0x01cd, 0x3fc),
 	INTEL_UEVENT_CONSTRAINT(0x02cd, 0x3),
-	INTEL_EVENT_CONSTRAINT(0xce, 0x1),
 
 	INTEL_EVENT_CONSTRAINT_RANGE(0xd0, 0xdf, 0xf),
-	/*
-	 * Generally event codes >= 0x90 are likely to have no restrictions.
-	 * The exception are defined as above.
-	 */
-	INTEL_EVENT_CONSTRAINT_RANGE(0x90, 0xfe, 0x3ff),
+
+	INTEL_UEVENT_CONSTRAINT(0x00e0, 0xf),
 
 	EVENT_CONSTRAINT_END
 };
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index c2e2eae7309c3..f122882ef278f 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1199,7 +1199,7 @@ struct event_constraint intel_lnc_pebs_event_constraints[] = {
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x100, 0x100000000ULL),	/* INST_RETIRED.PREC_DIST */
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL),
 
-	INTEL_HYBRID_LDLAT_CONSTRAINT(0x1cd, 0x3ff),
+	INTEL_HYBRID_LDLAT_CONSTRAINT(0x1cd, 0x3fc),
 	INTEL_HYBRID_STLAT_CONSTRAINT(0x2cd, 0x3),
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf),	/* MEM_INST_RETIRED.STLB_MISS_LOADS */
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf),	/* MEM_INST_RETIRED.STLB_MISS_STORES */

From fa808ed4e199ed17d878eb75b110bda30dd52434 Mon Sep 17 00:00:00 2001
From: Oliver Upton <oliver.upton@linux.dev>
Date: Wed, 19 Feb 2025 14:07:37 -0800
Subject: [PATCH 0413/1173] KVM: arm64: Ensure a VMID is allocated before
 programming VTTBR_EL2

Vladimir reports that a race condition to attach a VMID to a stage-2 MMU
sometimes results in a vCPU entering the guest with a VMID of 0:

| CPU1                                            |   CPU2
|                                                 |
|                                                 | kvm_arch_vcpu_ioctl_run
|                                                 |   vcpu_load             <= load VTTBR_EL2
|                                                 |                            kvm_vmid->id = 0
|                                                 |
| kvm_arch_vcpu_ioctl_run                         |
|   vcpu_load             <= load VTTBR_EL2       |
|                            with kvm_vmid->id = 0|
|   kvm_arm_vmid_update   <= allocates fresh      |
|                            kvm_vmid->id and     |
|                            reload VTTBR_EL2     |
|                                                 |
|                                                 |   kvm_arm_vmid_update <= observes that kvm_vmid->id
|                                                 |                          already allocated,
|                                                 |                          skips reload VTTBR_EL2

Oh yeah, it's as bad as it looks. Remember that VHE loads the stage-2
MMU eagerly but a VMID only gets attached to the MMU later on in the
KVM_RUN loop.

Even in the "best case" where VTTBR_EL2 correctly gets reprogrammed
before entering the EL1&0 regime, there is a period of time where
hardware is configured with VMID 0. That's completely insane. So, rather
than decorating the 'late' binding with another hack, just allocate the
damn thing up front.

Attaching a VMID from vcpu_load() is still rollover safe since
(surprise!) it'll always get called after a vCPU was preempted.

Excuse me while I go find a brown paper bag.

Cc: stable@vger.kernel.org
Fixes: 934bf871f011 ("KVM: arm64: Load the stage-2 MMU context in kvm_vcpu_load_vhe()")
Reported-by: Vladimir Murzin <vladimir.murzin@arm.com>
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
Link: https://lore.kernel.org/r/20250219220737.130842-1-oliver.upton@linux.dev
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h |  2 +-
 arch/arm64/kvm/arm.c              | 22 ++++++++++------------
 arch/arm64/kvm/vmid.c             | 11 +++--------
 3 files changed, 14 insertions(+), 21 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 3a7ec98ef1238..d919557af5e50 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -1259,7 +1259,7 @@ int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu,
 extern unsigned int __ro_after_init kvm_arm_vmid_bits;
 int __init kvm_arm_vmid_alloc_init(void);
 void __init kvm_arm_vmid_alloc_free(void);
-bool kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid);
+void kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid);
 void kvm_arm_vmid_clear_active(void);
 
 static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch)
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index bc7a37cea2420..0160b49243511 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -559,6 +559,16 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	mmu = vcpu->arch.hw_mmu;
 	last_ran = this_cpu_ptr(mmu->last_vcpu_ran);
 
+	/*
+	 * Ensure a VMID is allocated for the MMU before programming VTTBR_EL2,
+	 * which happens eagerly in VHE.
+	 *
+	 * Also, the VMID allocator only preserves VMIDs that are active at the
+	 * time of rollover, so KVM might need to grab a new VMID for the MMU if
+	 * this is called from kvm_sched_in().
+	 */
+	kvm_arm_vmid_update(&mmu->vmid);
+
 	/*
 	 * We guarantee that both TLBs and I-cache are private to each
 	 * vcpu. If detecting that a vcpu from the same VM has
@@ -1138,18 +1148,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		 */
 		preempt_disable();
 
-		/*
-		 * The VMID allocator only tracks active VMIDs per
-		 * physical CPU, and therefore the VMID allocated may not be
-		 * preserved on VMID roll-over if the task was preempted,
-		 * making a thread's VMID inactive. So we need to call
-		 * kvm_arm_vmid_update() in non-premptible context.
-		 */
-		if (kvm_arm_vmid_update(&vcpu->arch.hw_mmu->vmid) &&
-		    has_vhe())
-			__load_stage2(vcpu->arch.hw_mmu,
-				      vcpu->arch.hw_mmu->arch);
-
 		kvm_pmu_flush_hwstate(vcpu);
 
 		local_irq_disable();
diff --git a/arch/arm64/kvm/vmid.c b/arch/arm64/kvm/vmid.c
index 806223b7022af..7fe8ba1a2851c 100644
--- a/arch/arm64/kvm/vmid.c
+++ b/arch/arm64/kvm/vmid.c
@@ -135,11 +135,10 @@ void kvm_arm_vmid_clear_active(void)
 	atomic64_set(this_cpu_ptr(&active_vmids), VMID_ACTIVE_INVALID);
 }
 
-bool kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid)
+void kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid)
 {
 	unsigned long flags;
 	u64 vmid, old_active_vmid;
-	bool updated = false;
 
 	vmid = atomic64_read(&kvm_vmid->id);
 
@@ -157,21 +156,17 @@ bool kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid)
 	if (old_active_vmid != 0 && vmid_gen_match(vmid) &&
 	    0 != atomic64_cmpxchg_relaxed(this_cpu_ptr(&active_vmids),
 					  old_active_vmid, vmid))
-		return false;
+		return;
 
 	raw_spin_lock_irqsave(&cpu_vmid_lock, flags);
 
 	/* Check that our VMID belongs to the current generation. */
 	vmid = atomic64_read(&kvm_vmid->id);
-	if (!vmid_gen_match(vmid)) {
+	if (!vmid_gen_match(vmid))
 		vmid = new_vmid(kvm_vmid);
-		updated = true;
-	}
 
 	atomic64_set(this_cpu_ptr(&active_vmids), vmid);
 	raw_spin_unlock_irqrestore(&cpu_vmid_lock, flags);
-
-	return updated;
 }
 
 /*

From 9af3b4f2d879da01192d6168e6c651e7fb5b652d Mon Sep 17 00:00:00 2001
From: Dmitry Panchenko <dmitry@d-systems.ee>
Date: Thu, 20 Feb 2025 18:15:37 +0200
Subject: [PATCH 0414/1173] ALSA: usb-audio: Re-add sample rate quirk for
 Pioneer DJM-900NXS2

Re-add the sample-rate quirk for the Pioneer DJM-900NXS2. This
device does not work without setting sample-rate.

Signed-off-by: Dmitry Panchenko <dmitry@d-systems.ee>
Cc: <stable@vger.kernel.org>
Link: https://patch.msgid.link/20250220161540.3624660-1-dmitry@d-systems.ee
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/quirks.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index a97efb7b131ea..09210fb4ac60c 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -1868,6 +1868,7 @@ void snd_usb_set_format_quirk(struct snd_usb_substream *subs,
 	case USB_ID(0x534d, 0x2109): /* MacroSilicon MS2109 */
 		subs->stream_offset_adj = 2;
 		break;
+	case USB_ID(0x2b73, 0x000a): /* Pioneer DJM-900NXS2 */
 	case USB_ID(0x2b73, 0x0013): /* Pioneer DJM-450 */
 		pioneer_djm_set_format_quirk(subs, 0x0082);
 		break;

From f13409bb3f9140dad7256febcb478f0c9600312c Mon Sep 17 00:00:00 2001
From: Daniel Wagner <wagi@kernel.org>
Date: Fri, 14 Feb 2025 09:02:04 +0100
Subject: [PATCH 0415/1173] nvme-fc: rely on state transitions to handle
 connectivity loss

It's not possible to call nvme_state_ctrl_state with holding a spin
lock, because nvme_state_ctrl_state calls cancel_delayed_work_sync
when fastfail is enabled.

Instead syncing the ASSOC_FLAG and state transitions using a lock, it's
possible to only rely on the state machine transitions. That means
nvme_fc_ctrl_connectivity_loss should unconditionally call
nvme_reset_ctrl which avoids the read race on the ctrl state variable.
Actually, it's not necessary to test in which state the ctrl is, the
reset work will only scheduled when the state machine is in LIVE state.

In nvme_fc_create_association, the LIVE state can only be entered if it
was previously CONNECTING. If this is not possible then the reset
handler got triggered. Thus just error out here.

Fixes: ee59e3820ca9 ("nvme-fc: do not ignore connectivity loss during connecting")
Closes: https://lore.kernel.org/all/denqwui6sl5erqmz2gvrwueyxakl5txzbbiu3fgebryzrfxunm@iwxuthct377m/
Reported-by: Shinichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Tested-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Daniel Wagner <wagi@kernel.org>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/fc.c | 67 ++++--------------------------------------
 1 file changed, 6 insertions(+), 61 deletions(-)

diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index f4f1866fbd5b8..b9929a5a7f4e3 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -781,61 +781,12 @@ nvme_fc_abort_lsops(struct nvme_fc_rport *rport)
 static void
 nvme_fc_ctrl_connectivity_loss(struct nvme_fc_ctrl *ctrl)
 {
-	enum nvme_ctrl_state state;
-	unsigned long flags;
-
 	dev_info(ctrl->ctrl.device,
 		"NVME-FC{%d}: controller connectivity lost. Awaiting "
 		"Reconnect", ctrl->cnum);
 
-	spin_lock_irqsave(&ctrl->lock, flags);
 	set_bit(ASSOC_FAILED, &ctrl->flags);
-	state = nvme_ctrl_state(&ctrl->ctrl);
-	spin_unlock_irqrestore(&ctrl->lock, flags);
-
-	switch (state) {
-	case NVME_CTRL_NEW:
-	case NVME_CTRL_LIVE:
-		/*
-		 * Schedule a controller reset. The reset will terminate the
-		 * association and schedule the reconnect timer.  Reconnects
-		 * will be attempted until either the ctlr_loss_tmo
-		 * (max_retries * connect_delay) expires or the remoteport's
-		 * dev_loss_tmo expires.
-		 */
-		if (nvme_reset_ctrl(&ctrl->ctrl)) {
-			dev_warn(ctrl->ctrl.device,
-				"NVME-FC{%d}: Couldn't schedule reset.\n",
-				ctrl->cnum);
-			nvme_delete_ctrl(&ctrl->ctrl);
-		}
-		break;
-
-	case NVME_CTRL_CONNECTING:
-		/*
-		 * The association has already been terminated and the
-		 * controller is attempting reconnects.  No need to do anything
-		 * futher.  Reconnects will be attempted until either the
-		 * ctlr_loss_tmo (max_retries * connect_delay) expires or the
-		 * remoteport's dev_loss_tmo expires.
-		 */
-		break;
-
-	case NVME_CTRL_RESETTING:
-		/*
-		 * Controller is already in the process of terminating the
-		 * association.  No need to do anything further. The reconnect
-		 * step will kick in naturally after the association is
-		 * terminated.
-		 */
-		break;
-
-	case NVME_CTRL_DELETING:
-	case NVME_CTRL_DELETING_NOIO:
-	default:
-		/* no action to take - let it delete */
-		break;
-	}
+	nvme_reset_ctrl(&ctrl->ctrl);
 }
 
 /**
@@ -3071,7 +3022,6 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 	struct nvmefc_ls_rcv_op *disls = NULL;
 	unsigned long flags;
 	int ret;
-	bool changed;
 
 	++ctrl->ctrl.nr_reconnects;
 
@@ -3177,23 +3127,18 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 		else
 			ret = nvme_fc_recreate_io_queues(ctrl);
 	}
+	if (!ret && test_bit(ASSOC_FAILED, &ctrl->flags))
+		ret = -EIO;
 	if (ret)
 		goto out_term_aen_ops;
 
-	spin_lock_irqsave(&ctrl->lock, flags);
-	if (!test_bit(ASSOC_FAILED, &ctrl->flags))
-		changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
-	else
+	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE)) {
 		ret = -EIO;
-	spin_unlock_irqrestore(&ctrl->lock, flags);
-
-	if (ret)
 		goto out_term_aen_ops;
+	}
 
 	ctrl->ctrl.nr_reconnects = 0;
-
-	if (changed)
-		nvme_start_ctrl(&ctrl->ctrl);
+	nvme_start_ctrl(&ctrl->ctrl);
 
 	return 0;	/* Success */
 

From d2fe192348f93fe3a0cb1e33e4aba58e646397f4 Mon Sep 17 00:00:00 2001
From: Daniel Wagner <wagi@kernel.org>
Date: Fri, 14 Feb 2025 09:02:03 +0100
Subject: [PATCH 0416/1173] nvme: only allow entering LIVE from CONNECTING
 state

The fabric transports and also the PCI transport are not entering the
LIVE state from NEW or RESETTING. This makes the state machine more
restrictive and allows to catch not supported state transitions, e.g.
directly switching from RESETTING to LIVE.

Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Daniel Wagner <wagi@kernel.org>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/core.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 818d4e49aab51..f028913e2e622 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -564,8 +564,6 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 	switch (new_state) {
 	case NVME_CTRL_LIVE:
 		switch (old_state) {
-		case NVME_CTRL_NEW:
-		case NVME_CTRL_RESETTING:
 		case NVME_CTRL_CONNECTING:
 			changed = true;
 			fallthrough;

From 860ca5e50f73c2a1cef7eefc9d39d04e275417f7 Mon Sep 17 00:00:00 2001
From: Haoxiang Li <haoxiang_li2024@163.com>
Date: Mon, 17 Feb 2025 15:20:38 +0800
Subject: [PATCH 0417/1173] smb: client: Add check for next_buffer in
 receive_encrypted_standard()

Add check for the return value of cifs_buf_get() and cifs_small_buf_get()
in receive_encrypted_standard() to prevent null pointer dereference.

Fixes: eec04ea11969 ("smb: client: fix OOB in receive_encrypted_standard()")
Cc: stable@vger.kernel.org
Signed-off-by: Haoxiang Li <haoxiang_li2024@163.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2ops.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 23e0c8be7fb52..4dd11eafb69d9 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -4965,6 +4965,10 @@ receive_encrypted_standard(struct TCP_Server_Info *server,
 			next_buffer = (char *)cifs_buf_get();
 		else
 			next_buffer = (char *)cifs_small_buf_get();
+		if (!next_buffer) {
+			cifs_server_dbg(VFS, "No memory for (large) SMB response\n");
+			return -1;
+		}
 		memcpy(next_buffer, buf + next_cmd, pdu_length - next_cmd);
 	}
 

From bd30e8d7bfa6e528f9e746c940e6f7246c7899d6 Mon Sep 17 00:00:00 2001
From: Hsin-chen Chuang <chharry@chromium.org>
Date: Fri, 14 Feb 2025 19:17:09 +0800
Subject: [PATCH 0418/1173] Bluetooth: Always allow SCO packets for user
 channel

The SCO packets from Bluetooth raw socket are now rejected because
hci_conn_num is left 0. This patch allows such the usecase to enable
the userspace SCO support.

Fixes: b16b327edb4d ("Bluetooth: btusb: add sysfs attribute to control USB alt setting")
Signed-off-by: Hsin-chen Chuang <chharry@chromium.org>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btusb.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 90966dfbd2781..8149e53fd0a76 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -2102,7 +2102,8 @@ static int btusb_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 		return submit_or_queue_tx_urb(hdev, urb);
 
 	case HCI_SCODATA_PKT:
-		if (hci_conn_num(hdev, SCO_LINK) < 1)
+		if (!hci_dev_test_flag(hdev, HCI_USER_CHANNEL) &&
+		    hci_conn_num(hdev, SCO_LINK) < 1)
 			return -ENODEV;
 
 		urb = alloc_isoc_urb(hdev, skb);
@@ -2576,7 +2577,8 @@ static int btusb_send_frame_intel(struct hci_dev *hdev, struct sk_buff *skb)
 		return submit_or_queue_tx_urb(hdev, urb);
 
 	case HCI_SCODATA_PKT:
-		if (hci_conn_num(hdev, SCO_LINK) < 1)
+		if (!hci_dev_test_flag(hdev, HCI_USER_CHANNEL) &&
+		    hci_conn_num(hdev, SCO_LINK) < 1)
 			return -ENODEV;
 
 		urb = alloc_isoc_urb(hdev, skb);

From b25120e1d5f2ebb3db00af557709041f47f7f3d0 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Fri, 14 Feb 2025 10:30:25 -0500
Subject: [PATCH 0419/1173] Bluetooth: L2CAP: Fix L2CAP_ECRED_CONN_RSP response

L2CAP_ECRED_CONN_RSP needs to respond DCID in the same order received as
SCID but the order is reversed due to use of list_add which actually
prepend channels to the list so the response is reversed:

> ACL Data RX: Handle 16 flags 0x02 dlen 26
      LE L2CAP: Enhanced Credit Connection Request (0x17) ident 2 len 18
        PSM: 39 (0x0027)
        MTU: 256
        MPS: 251
        Credits: 65535
        Source CID: 116
        Source CID: 117
        Source CID: 118
        Source CID: 119
        Source CID: 120
< ACL Data TX: Handle 16 flags 0x00 dlen 26
      LE L2CAP: Enhanced Credit Connection Response (0x18) ident 2 len 18
        MTU: 517
        MPS: 247
        Credits: 3
        Result: Connection successful (0x0000)
        Destination CID: 68
        Destination CID: 67
        Destination CID: 66
        Destination CID: 65
        Destination CID: 64

Also make sure the response don't include channels that are not on
BT_CONNECT2 since the chan->ident can be set to the same value as in the
following trace:

< ACL Data TX: Handle 16 flags 0x00 dlen 12
      LE L2CAP: LE Flow Control Credit (0x16) ident 6 len 4
        Source CID: 64
        Credits: 1
...
> ACL Data RX: Handle 16 flags 0x02 dlen 18
      LE L2CAP: Enhanced Credit Connection Request (0x17) ident 6 len 10
        PSM: 39 (0x0027)
        MTU: 517
        MPS: 251
        Credits: 255
        Source CID: 70
< ACL Data TX: Handle 16 flags 0x00 dlen 20
      LE L2CAP: Enhanced Credit Connection Response (0x18) ident 6 len 12
        MTU: 517
        MPS: 247
        Credits: 3
        Result: Connection successful (0x0000)
        Destination CID: 64
        Destination CID: 68

Closes: https://github.com/bluez/bluez/issues/1094
Fixes: 9aa9d9473f15 ("Bluetooth: L2CAP: Fix responding with wrong PDU type")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/l2cap_core.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index fec11e576f310..b22078b679726 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -632,7 +632,8 @@ void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan)
 	    test_bit(FLAG_HOLD_HCI_CONN, &chan->flags))
 		hci_conn_hold(conn->hcon);
 
-	list_add(&chan->list, &conn->chan_l);
+	/* Append to the list since the order matters for ECRED */
+	list_add_tail(&chan->list, &conn->chan_l);
 }
 
 void l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan)
@@ -3771,7 +3772,11 @@ static void l2cap_ecred_rsp_defer(struct l2cap_chan *chan, void *data)
 	struct l2cap_ecred_conn_rsp *rsp_flex =
 		container_of(&rsp->pdu.rsp, struct l2cap_ecred_conn_rsp, hdr);
 
-	if (test_bit(FLAG_ECRED_CONN_REQ_SENT, &chan->flags))
+	/* Check if channel for outgoing connection or if it wasn't deferred
+	 * since in those cases it must be skipped.
+	 */
+	if (test_bit(FLAG_ECRED_CONN_REQ_SENT, &chan->flags) ||
+	    !test_and_clear_bit(FLAG_DEFER_SETUP, &chan->flags))
 		return;
 
 	/* Reset ident so only one response is sent */

From 511a3444f72efdc51fa923c4b1f5f0abd545fb20 Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst <dev@lankhorst.se>
Date: Thu, 20 Feb 2025 15:07:57 +0100
Subject: [PATCH 0420/1173] MAINTAINERS: Add entry for DMEM cgroup controller
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The cgroups controller is currently maintained through the
drm-misc tree, so lets add Maxime Ripard, Natalie Vock
and me as specific maintainers for dmem.

We keep the cgroup mailing list CC'd on all cgroup specific patches.

Acked-by: Maxime Ripard <mripard@kernel.org>
Acked-by: Natalie Vock <natalie.vock@gmx.de>
Acked-by: Tejun Heo <tj@kernel.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Koutný <mkoutny@suse.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250220140757.16823-1-dev@lankhorst.se
Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
---
 .mailmap    |  1 +
 MAINTAINERS | 11 +++++++++++
 2 files changed, 12 insertions(+)

diff --git a/.mailmap b/.mailmap
index 399322897938d..b71ee37f805d3 100644
--- a/.mailmap
+++ b/.mailmap
@@ -502,6 +502,7 @@ Nadav Amit <nadav.amit@gmail.com> <namit@cs.technion.ac.il>
 Nadia Yvette Chambers <nyc@holomorphy.com> William Lee Irwin III <wli@holomorphy.com>
 Naoya Horiguchi <nao.horiguchi@gmail.com> <n-horiguchi@ah.jp.nec.com>
 Naoya Horiguchi <nao.horiguchi@gmail.com> <naoya.horiguchi@nec.com>
+Natalie Vock <natalie.vock@gmx.de> <friedrich.vock@gmx.de>
 Nathan Chancellor <nathan@kernel.org> <natechancellor@gmail.com>
 Naveen N Rao <naveen@kernel.org> <naveen.n.rao@linux.ibm.com>
 Naveen N Rao <naveen@kernel.org> <naveen.n.rao@linux.vnet.ibm.com>
diff --git a/MAINTAINERS b/MAINTAINERS
index 18ade2ea4f3c4..473e7814a2925 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5878,6 +5878,17 @@ F:	tools/testing/selftests/cgroup/test_cpuset.c
 F:	tools/testing/selftests/cgroup/test_cpuset_prs.sh
 F:	tools/testing/selftests/cgroup/test_cpuset_v1_base.sh
 
+CONTROL GROUP - DEVICE MEMORY CONTROLLER (DMEM)
+M:	Maarten Lankhorst <dev@lankhorst.se>
+M:	Maxime Ripard <mripard@kernel.org>
+M:	Natalie Vock <natalie.vock@gmx.de>
+L:	cgroups@vger.kernel.org
+L:	dri-devel@lists.freedesktop.org
+S:	Maintained
+T:	git https://gitlab.freedesktop.org/drm/misc/kernel.git
+F:	include/linux/cgroup_dmem.h
+F:	kernel/cgroup/dmem.c
+
 CONTROL GROUP - MEMORY RESOURCE CONTROLLER (MEMCG)
 M:	Johannes Weiner <hannes@cmpxchg.org>
 M:	Michal Hocko <mhocko@kernel.org>

From 992ee3ed6e9fdd0be83a7daa5ff738e3cf86047f Mon Sep 17 00:00:00 2001
From: George Moussalem <george.moussalem@outlook.com>
Date: Wed, 19 Feb 2025 14:09:21 +0100
Subject: [PATCH 0421/1173] net: phy: qcom: qca807x fix condition for
 DAC_DSP_BIAS_CURRENT

While setting the DAC value, the wrong boolean value is evaluated to set
the DSP bias current. So let's correct the conditional statement and use
the right boolean value read from the DTS set in the priv.

Cc: stable@vger.kernel.org
Fixes: d1cb613efbd3 ("net: phy: qcom: add support for QCA807x PHY Family")
Signed-off-by: George Moussalem <george.moussalem@outlook.com>
Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250219130923.7216-1-ansuelsmth@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/qcom/qca807x.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/qcom/qca807x.c b/drivers/net/phy/qcom/qca807x.c
index 3279de857b474..2ad8c2586d643 100644
--- a/drivers/net/phy/qcom/qca807x.c
+++ b/drivers/net/phy/qcom/qca807x.c
@@ -774,7 +774,7 @@ static int qca807x_config_init(struct phy_device *phydev)
 	control_dac &= ~QCA807X_CONTROL_DAC_MASK;
 	if (!priv->dac_full_amplitude)
 		control_dac |= QCA807X_CONTROL_DAC_DSP_AMPLITUDE;
-	if (!priv->dac_full_amplitude)
+	if (!priv->dac_full_bias_current)
 		control_dac |= QCA807X_CONTROL_DAC_DSP_BIAS_CURRENT;
 	if (!priv->dac_disable_bias_current_tweak)
 		control_dac |= QCA807X_CONTROL_DAC_BIAS_CURRENT_TWEAK;

From e31e3f6c0ce473f7ce1e70d54ac8e3ed190509f8 Mon Sep 17 00:00:00 2001
From: Haoxiang Li <haoxiang_li2024@163.com>
Date: Thu, 20 Feb 2025 16:17:14 +0800
Subject: [PATCH 0422/1173] soc: loongson: loongson2_guts: Add check for
 devm_kstrdup()

Add check for the return value of devm_kstrdup() in
loongson2_guts_probe() to catch potential exception.

Fixes: b82621ac8450 ("soc: loongson: add GUTS driver for loongson-2 platforms")
Cc: stable@vger.kernel.org
Signed-off-by: Haoxiang Li <haoxiang_li2024@163.com>
Link: https://lore.kernel.org/r/20250220081714.2676828-1-haoxiang_li2024@163.com
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 drivers/soc/loongson/loongson2_guts.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/soc/loongson/loongson2_guts.c b/drivers/soc/loongson/loongson2_guts.c
index ae42e3a9127fc..16913c3ef65ca 100644
--- a/drivers/soc/loongson/loongson2_guts.c
+++ b/drivers/soc/loongson/loongson2_guts.c
@@ -114,8 +114,11 @@ static int loongson2_guts_probe(struct platform_device *pdev)
 	if (of_property_read_string(root, "model", &machine))
 		of_property_read_string_index(root, "compatible", 0, &machine);
 	of_node_put(root);
-	if (machine)
+	if (machine) {
 		soc_dev_attr.machine = devm_kstrdup(dev, machine, GFP_KERNEL);
+		if (!soc_dev_attr.machine)
+			return -ENOMEM;
+	}
 
 	svr = loongson2_guts_get_svr();
 	soc_die = loongson2_soc_die_match(svr, loongson2_soc_die);

From 68aaa637162787dc3374080efe03366f70b344f1 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Thu, 20 Feb 2025 09:17:17 -0500
Subject: [PATCH 0423/1173] bcachefs: print op->nonce on data update
 inconsistency

"nonce inconstancy" is popping up again, causing us to go emergency
read-only.

This one looks less serious, i.e. specific to the encryption path and
not indicative of a data corruption bug. But we'll need more info to
track it down.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/data_update.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c
index 337494facac64..642fbc60ecab1 100644
--- a/fs/bcachefs/data_update.c
+++ b/fs/bcachefs/data_update.c
@@ -340,6 +340,7 @@ static int __bch2_data_update_index_update(struct btree_trans *trans,
 			struct printbuf buf = PRINTBUF;
 
 			prt_str(&buf, "about to insert invalid key in data update path");
+			prt_printf(&buf, "\nop.nonce: %u", m->op.nonce);
 			prt_str(&buf, "\nold: ");
 			bch2_bkey_val_to_text(&buf, c, old);
 			prt_str(&buf, "\nk:   ");

From c522093b02835f2e897b83e9764e7919edac5d08 Mon Sep 17 00:00:00 2001
From: Alan Huang <mmpgouride@gmail.com>
Date: Thu, 20 Feb 2025 18:56:08 +0800
Subject: [PATCH 0424/1173] bcachefs: Fix memmove when move keys down

The fix alone doesn't fix [1], but should be applied before debugging
that.

[1] https://syzkaller.appspot.com/bug?extid=38a0cbd267eff2d286ff

Signed-off-by: Alan Huang <mmpgouride@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_io.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c
index e371e60e3133e..dece27d9db04e 100644
--- a/fs/bcachefs/btree_io.c
+++ b/fs/bcachefs/btree_io.c
@@ -996,7 +996,7 @@ static int validate_bset_keys(struct bch_fs *c, struct btree *b,
 		}
 got_good_key:
 		le16_add_cpu(&i->u64s, -next_good_key);
-		memmove_u64s_down(k, bkey_p_next(k), (u64 *) vstruct_end(i) - (u64 *) k);
+		memmove_u64s_down(k, (u64 *) k + next_good_key, (u64 *) vstruct_end(i) - (u64 *) k);
 		set_btree_node_need_rewrite(b);
 	}
 fsck_err:

From b522f180ee2b264b771fcbd0ab67d84cdd9e580d Mon Sep 17 00:00:00 2001
From: Fenghua Yu <fenghua.yu@intel.com>
Date: Fri, 31 Jan 2025 11:07:31 -0800
Subject: [PATCH 0425/1173] MAINTAINERS: Change maintainer for RDT

Due to job transition, I am stepping down as RDT maintainer.
Add Tony as a co-maintainer.

Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Reinette Chatre <reinette.chatre@intel.com>
Acked-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/all/20250131190731.3981085-1-fenghua.yu%40intel.com
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index feed152470f68..d1cbaeb58143a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -19779,7 +19779,7 @@ F:	net/rds/
 F:	tools/testing/selftests/net/rds/
 
 RDT - RESOURCE ALLOCATION
-M:	Fenghua Yu <fenghua.yu@intel.com>
+M:	Tony Luck <tony.luck@intel.com>
 M:	Reinette Chatre <reinette.chatre@intel.com>
 L:	linux-kernel@vger.kernel.org
 S:	Supported

From f06e4bfd010faefa637689d2df2c727dbf6e1d27 Mon Sep 17 00:00:00 2001
From: Qunqin Zhao <zhaoqunqin@loongson.cn>
Date: Wed, 19 Feb 2025 10:07:01 +0800
Subject: [PATCH 0426/1173] net: stmmac: dwmac-loongson: Add fix_soc_reset()
 callback

Loongson's DWMAC device may take nearly two seconds to complete DMA reset,
however, the default waiting time for reset is 200 milliseconds.
Therefore, the following error message may appear:

[14.427169] dwmac-loongson-pci 0000:00:03.2: Failed to reset the dma

Fixes: 803fc61df261 ("net: stmmac: dwmac-loongson: Add Loongson Multi-channels GMAC support")
Cc: stable@vger.kernel.org
Signed-off-by: Qunqin Zhao <zhaoqunqin@loongson.cn>
Reviewed-by: Huacai Chen <chenhuacai@loongson.cn>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Acked-by: Yanteng Si <si.yanteng@linux.dev>
Link: https://patch.msgid.link/20250219020701.15139-1-zhaoqunqin@loongson.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/stmicro/stmmac/dwmac-loongson.c   | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
index bfe6e2d631bdf..f5acfb7d4ff65 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
@@ -516,6 +516,19 @@ static int loongson_dwmac_acpi_config(struct pci_dev *pdev,
 	return 0;
 }
 
+/* Loongson's DWMAC device may take nearly two seconds to complete DMA reset */
+static int loongson_dwmac_fix_reset(void *priv, void __iomem *ioaddr)
+{
+	u32 value = readl(ioaddr + DMA_BUS_MODE);
+
+	value |= DMA_BUS_MODE_SFT_RESET;
+	writel(value, ioaddr + DMA_BUS_MODE);
+
+	return readl_poll_timeout(ioaddr + DMA_BUS_MODE, value,
+				  !(value & DMA_BUS_MODE_SFT_RESET),
+				  10000, 2000000);
+}
+
 static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct plat_stmmacenet_data *plat;
@@ -566,6 +579,7 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id
 
 	plat->bsp_priv = ld;
 	plat->setup = loongson_dwmac_setup;
+	plat->fix_soc_reset = loongson_dwmac_fix_reset;
 	ld->dev = &pdev->dev;
 	ld->loongson_id = readl(res.addr + GMAC_VERSION) & 0xff;
 

From dce5c4afd035e8090a26e5d776b1682c0e649683 Mon Sep 17 00:00:00 2001
From: Ye Bin <yebin10@huawei.com>
Date: Mon, 17 Feb 2025 10:16:28 +0800
Subject: [PATCH 0427/1173] scsi: core: Clear driver private data when retrying
 request

After commit 1bad6c4a57ef ("scsi: zero per-cmd private driver data for each
MQ I/O"), the xen-scsifront/virtio_scsi/snic drivers all removed code that
explicitly zeroed driver-private command data.

In combination with commit 464a00c9e0ad ("scsi: core: Kill DRIVER_SENSE"),
after virtio_scsi performs a capacity expansion, the first request will
return a unit attention to indicate that the capacity has changed. And then
the original command is retried. As driver-private command data was not
cleared, the request would return UA again and eventually time out and fail.

Zero driver-private command data when a request is retried.

Fixes: f7de50da1479 ("scsi: xen-scsifront: Remove code that zeroes driver-private command data")
Fixes: c2bb87318baa ("scsi: virtio_scsi: Remove code that zeroes driver-private command data")
Fixes: c3006a926468 ("scsi: snic: Remove code that zeroes driver-private command data")
Signed-off-by: Ye Bin <yebin10@huawei.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20250217021628.2929248-1-yebin@huaweicloud.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_lib.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index be0890e4e7062..f1cfe0bb89b20 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1669,13 +1669,6 @@ static blk_status_t scsi_prepare_cmd(struct request *req)
 	if (in_flight)
 		__set_bit(SCMD_STATE_INFLIGHT, &cmd->state);
 
-	/*
-	 * Only clear the driver-private command data if the LLD does not supply
-	 * a function to initialize that data.
-	 */
-	if (!shost->hostt->init_cmd_priv)
-		memset(cmd + 1, 0, shost->hostt->cmd_size);
-
 	cmd->prot_op = SCSI_PROT_NORMAL;
 	if (blk_rq_bytes(req))
 		cmd->sc_data_direction = rq_dma_dir(req);
@@ -1842,6 +1835,13 @@ static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
 	if (!scsi_host_queue_ready(q, shost, sdev, cmd))
 		goto out_dec_target_busy;
 
+	/*
+	 * Only clear the driver-private command data if the LLD does not supply
+	 * a function to initialize that data.
+	 */
+	if (shost->hostt->cmd_size && !shost->hostt->init_cmd_priv)
+		memset(cmd + 1, 0, shost->hostt->cmd_size);
+
 	if (!(req->rq_flags & RQF_DONTPREP)) {
 		ret = scsi_prepare_cmd(req);
 		if (ret != BLK_STS_OK)

From fe06b7c07f3fbcce2a2ca6f7b0d543b5699ea00f Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Wed, 19 Feb 2025 16:20:47 +0530
Subject: [PATCH 0428/1173] scsi: ufs: core: Set default runtime/system PM
 levels before ufshcd_hba_init()

Commit bb9850704c04 ("scsi: ufs: core: Honor runtime/system PM levels if
set by host controller drivers") introduced the check for setting default
PM levels only if the levels are uninitialized by the host controller
drivers. But it missed the fact that the levels could be initialized to 0
(UFS_PM_LVL_0) on purpose by the controller drivers. Even though none of
the drivers are doing so now, the logic should be fixed irrespectively.

So set the default levels unconditionally before calling ufshcd_hba_init()
API which initializes the controller drivers. It ensures that the
controller drivers could override the default levels if required.

Fixes: bb9850704c04 ("scsi: ufs: core: Honor runtime/system PM levels if set by host controller drivers")
Reported-by: Bao D. Nguyen <quic_nguyenb@quicinc.com>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20250219105047.49932-1-manivannan.sadhasivam@linaro.org
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 30 +++++++++++++++---------------
 1 file changed, 15 insertions(+), 15 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index f9303e66bb798..464f13da259aa 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -10431,6 +10431,21 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 	 */
 	spin_lock_init(&hba->clk_gating.lock);
 
+	/*
+	 * Set the default power management level for runtime and system PM.
+	 * Host controller drivers can override them in their
+	 * 'ufs_hba_variant_ops::init' callback.
+	 *
+	 * Default power saving mode is to keep UFS link in Hibern8 state
+	 * and UFS device in sleep state.
+	 */
+	hba->rpm_lvl = ufs_get_desired_pm_lvl_for_dev_link_state(
+						UFS_SLEEP_PWR_MODE,
+						UIC_LINK_HIBERN8_STATE);
+	hba->spm_lvl = ufs_get_desired_pm_lvl_for_dev_link_state(
+						UFS_SLEEP_PWR_MODE,
+						UIC_LINK_HIBERN8_STATE);
+
 	err = ufshcd_hba_init(hba);
 	if (err)
 		goto out_error;
@@ -10544,21 +10559,6 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 		goto out_disable;
 	}
 
-	/*
-	 * Set the default power management level for runtime and system PM if
-	 * not set by the host controller drivers.
-	 * Default power saving mode is to keep UFS link in Hibern8 state
-	 * and UFS device in sleep state.
-	 */
-	if (!hba->rpm_lvl)
-		hba->rpm_lvl = ufs_get_desired_pm_lvl_for_dev_link_state(
-						UFS_SLEEP_PWR_MODE,
-						UIC_LINK_HIBERN8_STATE);
-	if (!hba->spm_lvl)
-		hba->spm_lvl = ufs_get_desired_pm_lvl_for_dev_link_state(
-						UFS_SLEEP_PWR_MODE,
-						UIC_LINK_HIBERN8_STATE);
-
 	INIT_DELAYED_WORK(&hba->rpm_dev_flush_recheck_work, ufshcd_rpm_dev_flush_recheck_work);
 	INIT_DELAYED_WORK(&hba->ufs_rtc_update_work, ufshcd_rtc_work);
 

From f27a95845b01e86d67c8b014b4f41bd3327daa63 Mon Sep 17 00:00:00 2001
From: Arthur Simchaev <arthur.simchaev@sandisk.com>
Date: Thu, 20 Feb 2025 16:20:39 +0200
Subject: [PATCH 0429/1173] scsi: ufs: core: bsg: Fix crash when arpmb command
 fails

If the device doesn't support arpmb we'll crash due to copying user data in
bsg_transport_sg_io_fn().

In the case where ufs_bsg_exec_advanced_rpmb_req() returns an error, do not
set the job's reply_len.

Memory crash backtrace:
3,1290,531166405,-;ufshcd 0000:00:12.5: ARPMB OP failed: error code -22

4,1308,531166555,-;Call Trace:

4,1309,531166559,-; <TASK>

4,1310,531166565,-; ? show_regs+0x6d/0x80

4,1311,531166575,-; ? die+0x37/0xa0

4,1312,531166583,-; ? do_trap+0xd4/0xf0

4,1313,531166593,-; ? do_error_trap+0x71/0xb0

4,1314,531166601,-; ? usercopy_abort+0x6c/0x80

4,1315,531166610,-; ? exc_invalid_op+0x52/0x80

4,1316,531166622,-; ? usercopy_abort+0x6c/0x80

4,1317,531166630,-; ? asm_exc_invalid_op+0x1b/0x20

4,1318,531166643,-; ? usercopy_abort+0x6c/0x80

4,1319,531166652,-; __check_heap_object+0xe3/0x120

4,1320,531166661,-; check_heap_object+0x185/0x1d0

4,1321,531166670,-; __check_object_size.part.0+0x72/0x150

4,1322,531166679,-; __check_object_size+0x23/0x30

4,1323,531166688,-; bsg_transport_sg_io_fn+0x314/0x3b0

Fixes: 6ff265fc5ef6 ("scsi: ufs: core: bsg: Add advanced RPMB support in ufs_bsg")
Cc: stable@vger.kernel.org
Reviewed-by: Bean Huo <beanhuo@micron.com>
Signed-off-by: Arthur Simchaev <arthur.simchaev@sandisk.com>
Link: https://lore.kernel.org/r/20250220142039.250992-1-arthur.simchaev@sandisk.com
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufs_bsg.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/ufs/core/ufs_bsg.c b/drivers/ufs/core/ufs_bsg.c
index 8d4ad0a3f2cf0..252186124669a 100644
--- a/drivers/ufs/core/ufs_bsg.c
+++ b/drivers/ufs/core/ufs_bsg.c
@@ -194,10 +194,12 @@ static int ufs_bsg_request(struct bsg_job *job)
 	ufshcd_rpm_put_sync(hba);
 	kfree(buff);
 	bsg_reply->result = ret;
-	job->reply_len = !rpmb ? sizeof(struct ufs_bsg_reply) : sizeof(struct ufs_rpmb_reply);
 	/* complete the job here only if no error */
-	if (ret == 0)
+	if (ret == 0) {
+		job->reply_len = rpmb ? sizeof(struct ufs_rpmb_reply) :
+					sizeof(struct ufs_bsg_reply);
 		bsg_job_done(job, ret, bsg_reply->reply_payload_rcv_len);
+	}
 
 	return ret;
 }

From 59f37036bb7ab3d554c24abc856aabca01126414 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Sat, 15 Feb 2025 11:36:15 +0000
Subject: [PATCH 0430/1173] btrfs: fix use-after-free on inode when scanning
 root during em shrinking

At btrfs_scan_root() we are accessing the inode's root (and fs_info) in a
call to btrfs_fs_closing() after we have scheduled the inode for a delayed
iput, and that can result in a use-after-free on the inode in case the
cleaner kthread does the iput before we dereference the inode in the call
to btrfs_fs_closing().

Fix this by using the fs_info stored already in a local variable instead
of doing inode->root->fs_info.

Fixes: 102044384056 ("btrfs: make the extent map shrinker run asynchronously as a work queue job")
CC: stable@vger.kernel.org # 6.13+
Tested-by: Ivan Shapovalov <intelfx@intelfx.name>
Link: https://lore.kernel.org/linux-btrfs/0414d690ac5680d0d77dfc930606cdc36e42e12f.camel@intelfx.name/
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent_map.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 67ce85ff0ae25..bee1b94a10495 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -1222,8 +1222,7 @@ static long btrfs_scan_root(struct btrfs_root *root, struct btrfs_em_shrink_ctx
 		fs_info->em_shrinker_last_ino = btrfs_ino(inode);
 		btrfs_add_delayed_iput(inode);
 
-		if (ctx->scanned >= ctx->nr_to_scan ||
-		    btrfs_fs_closing(inode->root->fs_info))
+		if (ctx->scanned >= ctx->nr_to_scan || btrfs_fs_closing(fs_info))
 			break;
 
 		cond_resched();

From c6c9c4d56483d941f567eb921434c25fc6086dfa Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Sat, 15 Feb 2025 11:04:15 +0000
Subject: [PATCH 0431/1173] btrfs: skip inodes without loaded extent maps when
 shrinking extent maps

If there are inodes that don't have any loaded extent maps, we end up
grabbing a reference on them and later adding a delayed iput, which wakes
up the cleaner and makes it do unnecessary work. This is common when for
example the inodes were open only to run stat(2) or all their extent maps
were already released through the folio release callback
(btrfs_release_folio()) or released by a previous run of the shrinker, or
directories which never have extent maps.

Reported-by: Ivan Shapovalov <intelfx@intelfx.name>
Tested-by: Ivan Shapovalov <intelfx@intelfx.name>
Link: https://lore.kernel.org/linux-btrfs/0414d690ac5680d0d77dfc930606cdc36e42e12f.camel@intelfx.name/
CC: stable@vger.kernel.org # 6.13+
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent_map.c | 78 +++++++++++++++++++++++++++++++------------
 1 file changed, 57 insertions(+), 21 deletions(-)

diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index bee1b94a10495..8c6b85ffd18f6 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -1128,6 +1128,8 @@ static long btrfs_scan_inode(struct btrfs_inode *inode, struct btrfs_em_shrink_c
 	long nr_dropped = 0;
 	struct rb_node *node;
 
+	lockdep_assert_held_write(&tree->lock);
+
 	/*
 	 * Take the mmap lock so that we serialize with the inode logging phase
 	 * of fsync because we may need to set the full sync flag on the inode,
@@ -1139,28 +1141,12 @@ static long btrfs_scan_inode(struct btrfs_inode *inode, struct btrfs_em_shrink_c
 	 * to find new extents, which may not be there yet because ordered
 	 * extents haven't completed yet.
 	 *
-	 * We also do a try lock because otherwise we could deadlock. This is
-	 * because the shrinker for this filesystem may be invoked while we are
-	 * in a path that is holding the mmap lock in write mode. For example in
-	 * a reflink operation while COWing an extent buffer, when allocating
-	 * pages for a new extent buffer and under memory pressure, the shrinker
-	 * may be invoked, and therefore we would deadlock by attempting to read
-	 * lock the mmap lock while we are holding already a write lock on it.
+	 * We also do a try lock because we don't want to block for too long and
+	 * we are holding the extent map tree's lock in write mode.
 	 */
 	if (!down_read_trylock(&inode->i_mmap_lock))
 		return 0;
 
-	/*
-	 * We want to be fast so if the lock is busy we don't want to spend time
-	 * waiting for it - either some task is about to do IO for the inode or
-	 * we may have another task shrinking extent maps, here in this code, so
-	 * skip this inode.
-	 */
-	if (!write_trylock(&tree->lock)) {
-		up_read(&inode->i_mmap_lock);
-		return 0;
-	}
-
 	node = rb_first(&tree->root);
 	while (node) {
 		struct rb_node *next = rb_next(node);
@@ -1201,12 +1187,61 @@ static long btrfs_scan_inode(struct btrfs_inode *inode, struct btrfs_em_shrink_c
 			break;
 		node = next;
 	}
-	write_unlock(&tree->lock);
 	up_read(&inode->i_mmap_lock);
 
 	return nr_dropped;
 }
 
+static struct btrfs_inode *find_first_inode_to_shrink(struct btrfs_root *root,
+						      u64 min_ino)
+{
+	struct btrfs_inode *inode;
+	unsigned long from = min_ino;
+
+	xa_lock(&root->inodes);
+	while (true) {
+		struct extent_map_tree *tree;
+
+		inode = xa_find(&root->inodes, &from, ULONG_MAX, XA_PRESENT);
+		if (!inode)
+			break;
+
+		tree = &inode->extent_tree;
+
+		/*
+		 * We want to be fast so if the lock is busy we don't want to
+		 * spend time waiting for it (some task is about to do IO for
+		 * the inode).
+		 */
+		if (!write_trylock(&tree->lock))
+			goto next;
+
+		/*
+		 * Skip inode if it doesn't have loaded extent maps, so we avoid
+		 * getting a reference and doing an iput later. This includes
+		 * cases like files that were opened for things like stat(2), or
+		 * files with all extent maps previously released through the
+		 * release folio callback (btrfs_release_folio()) or released in
+		 * a previous run, or directories which never have extent maps.
+		 */
+		if (RB_EMPTY_ROOT(&tree->root)) {
+			write_unlock(&tree->lock);
+			goto next;
+		}
+
+		if (igrab(&inode->vfs_inode))
+			break;
+
+		write_unlock(&tree->lock);
+next:
+		from = btrfs_ino(inode) + 1;
+		cond_resched_lock(&root->inodes.xa_lock);
+	}
+	xa_unlock(&root->inodes);
+
+	return inode;
+}
+
 static long btrfs_scan_root(struct btrfs_root *root, struct btrfs_em_shrink_ctx *ctx)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
@@ -1214,9 +1249,10 @@ static long btrfs_scan_root(struct btrfs_root *root, struct btrfs_em_shrink_ctx
 	long nr_dropped = 0;
 	u64 min_ino = fs_info->em_shrinker_last_ino + 1;
 
-	inode = btrfs_find_first_inode(root, min_ino);
+	inode = find_first_inode_to_shrink(root, min_ino);
 	while (inode) {
 		nr_dropped += btrfs_scan_inode(inode, ctx);
+		write_unlock(&inode->extent_tree.lock);
 
 		min_ino = btrfs_ino(inode) + 1;
 		fs_info->em_shrinker_last_ino = btrfs_ino(inode);
@@ -1227,7 +1263,7 @@ static long btrfs_scan_root(struct btrfs_root *root, struct btrfs_em_shrink_ctx
 
 		cond_resched();
 
-		inode = btrfs_find_first_inode(root, min_ino);
+		inode = find_first_inode_to_shrink(root, min_ino);
 	}
 
 	if (inode) {

From 15b3b3254d1453a8db038b7d44b311a2d6c71f98 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Sat, 15 Feb 2025 11:11:29 +0000
Subject: [PATCH 0432/1173] btrfs: do regular iput instead of delayed iput
 during extent map shrinking

The extent map shrinker now runs in the system unbound workqueue and no
longer in kswapd context so it can directly do an iput() on inodes even
if that blocks or needs to acquire any lock (we aren't holding any locks
when requesting the delayed iput from the shrinker). So we don't need to
add a delayed iput, wake up the cleaner and delegate the iput() to the
cleaner, which also adds extra contention on the spinlock that protects
the delayed iputs list.

Reported-by: Ivan Shapovalov <intelfx@intelfx.name>
Tested-by: Ivan Shapovalov <intelfx@intelfx.name>
Link: https://lore.kernel.org/linux-btrfs/0414d690ac5680d0d77dfc930606cdc36e42e12f.camel@intelfx.name/
CC: stable@vger.kernel.org # 6.12+
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent_map.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 8c6b85ffd18f6..7f46abbd6311b 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -1256,7 +1256,7 @@ static long btrfs_scan_root(struct btrfs_root *root, struct btrfs_em_shrink_ctx
 
 		min_ino = btrfs_ino(inode) + 1;
 		fs_info->em_shrinker_last_ino = btrfs_ino(inode);
-		btrfs_add_delayed_iput(inode);
+		iput(&inode->vfs_inode);
 
 		if (ctx->scanned >= ctx->nr_to_scan || btrfs_fs_closing(fs_info))
 			break;

From b1bf18223a8340cf5d52162d320badcfe07b905d Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Mon, 17 Feb 2025 20:16:39 +1030
Subject: [PATCH 0433/1173] btrfs: output an error message if btrfs failed to
 find the seed fsid

[BUG]
If btrfs failed to locate the seed device for whatever reason, mounting
the sprouted device will fail without any meaning error message:

  # mkfs.btrfs -f /dev/test/scratch1
  # btrfstune -S1 /dev/test/scratch1
  # mount /dev/test/scratch1 /mnt/btrfs
  # btrfs dev add -f /dev/test/scratch2 /mnt/btrfs
  # umount /mnt/btrfs
  # btrfs dev scan -u
  # btrfs mount /dev/test/scratch2 /mnt/btrfs
  mount: /mnt/btrfs: fsconfig system call failed: No such file or directory.
        dmesg(1) may have more information after failed mount system call.
  # dmesg -t | tail -n6
  BTRFS info (device dm-5): first mount of filesystem 64252ded-5953-4868-b962-cea48f7ac4ea
  BTRFS info (device dm-5): using crc32c (crc32c-generic) checksum algorithm
  BTRFS info (device dm-5): using free-space-tree
  BTRFS error (device dm-5): failed to read chunk tree: -2
  BTRFS error (device dm-5): open_ctree failed: -2

[CAUSE]
The failure to mount is pretty straight forward, just unable to find the
seed device and its fsid, caused by `btrfs dev scan -u`.

But the lack of any useful info is a problem.

[FIX]
Just add an extra error message in open_seed_devices() to indicate the
error.

Now the error message would look like this:

 BTRFS info (device dm-4): first mount of filesystem 7769223d-4db1-4e4c-ac29-0a96f53576ab
 BTRFS info (device dm-4): using crc32c (crc32c-generic) checksum algorithm
 BTRFS info (device dm-4): using free-space-tree
 BTRFS error (device dm-4): failed to find fsid e87c12e6-584b-4e98-8b88-962c33a619ff when attempting to open seed devices
 BTRFS error (device dm-4): failed to read chunk tree: -2
 BTRFS error (device dm-4): open_ctree failed: -2

Link: https://github.com/kdave/btrfs-progs/issues/959
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/volumes.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index a594f66daedf0..f6ae76815e4b5 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -7196,8 +7196,12 @@ static struct btrfs_fs_devices *open_seed_devices(struct btrfs_fs_info *fs_info,
 
 	fs_devices = find_fsid(fsid, NULL);
 	if (!fs_devices) {
-		if (!btrfs_test_opt(fs_info, DEGRADED))
+		if (!btrfs_test_opt(fs_info, DEGRADED)) {
+			btrfs_err(fs_info,
+		"failed to find fsid %pU when attempting to open seed devices",
+				  fsid);
 			return ERR_PTR(-ENOENT);
+		}
 
 		fs_devices = alloc_fs_devices(fsid);
 		if (IS_ERR(fs_devices))

From efa11fd269c139e29b71ec21bc9c9c0063fde40d Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Wed, 19 Feb 2025 09:06:33 +1030
Subject: [PATCH 0434/1173] btrfs: fix data overwriting bug during buffered
 write when block size < page size

[BUG]
When running generic/418 with a btrfs whose block size < page size
(subpage cases), it always fails.

And the following minimal reproducer is more than enough to trigger it
reliably:

workload()
{
        mkfs.btrfs -s 4k -f $dev > /dev/null
        dmesg -C
        mount $dev $mnt
        $fsstree_dir/src/dio-invalidate-cache -r -b 4096 -n 3 -i 1 -f $mnt/diotest
        ret=$?
        umount $mnt
        stop_trace
        if [ $ret -ne 0 ]; then
                fail
        fi
}

for (( i = 0; i < 1024; i++)); do
        echo "=== $i/$runtime ==="
        workload
done

[CAUSE]
With extra trace printk added to the following functions:
- btrfs_buffered_write()
  * Which folio is touched
  * The file offset (start) where the buffered write is at
  * How many bytes are copied
  * The content of the write (the first 2 bytes)

- submit_one_sector()
  * Which folio is touched
  * The position inside the folio
  * The content of the page cache (the first 2 bytes)

- pagecache_isize_extended()
  * The parameters of the function itself
  * The parameters of the folio_zero_range()

Which are enough to show the problem:

  22.158114: btrfs_buffered_write: folio pos=0 start=0 copied=4096 content=0x0101
  22.158161: submit_one_sector: r/i=5/257 folio=0 pos=0 content=0x0101
  22.158609: btrfs_buffered_write: folio pos=0 start=4096 copied=4096 content=0x0101
  22.158634: btrfs_buffered_write: folio pos=0 start=8192 copied=4096 content=0x0101
  22.158650: pagecache_isize_extended: folio=0 from=4096 to=8192 bsize=4096 zero off=4096 len=8192
  22.158682: submit_one_sector: r/i=5/257 folio=0 pos=4096 content=0x0000
  22.158686: submit_one_sector: r/i=5/257 folio=0 pos=8192 content=0x0101

The tool dio-invalidate-cache will start 3 threads, each doing a buffered
write with 0x01 at offset 0, 4096 and 8192, do a fsync, then do a direct read,
and compare the read buffer with the write buffer.

Note that all 3 btrfs_buffered_write() are writing the correct 0x01 into
the page cache.

But at submit_one_sector(), at file offset 4096, the content is zeroed
out, by pagecache_isize_extended().

The race happens like this:
 Thread A is writing into range [4K, 8K).
 Thread B is writing into range [8K, 12k).

               Thread A              |         Thread B
-------------------------------------+------------------------------------
btrfs_buffered_write()               | btrfs_buffered_write()
|- old_isize = 4K;                   | |- old_isize = 4096;
|- btrfs_inode_lock()                | |
|- write into folio range [4K, 8K)   | |
|- pagecache_isize_extended()        | |
|  extend isize from 4096 to 8192    | |
|  no folio_zero_range() called      | |
|- btrfs_inode_lock()                | |
                                     | |- btrfs_inode_lock()
				     | |- write into folio range [8K, 12K)
				     | |- pagecache_isize_extended()
				     | |  calling folio_zero_range(4K, 8K)
				     | |  This is caused by the old_isize is
				     | |  grabbed too early, without any
				     | |  inode lock.
				     | |- btrfs_inode_unlock()

The @old_isize is grabbed without inode lock, causing race between two
buffered write threads and making pagecache_isize_extended() to zero
range which is still containing cached data.

And this is only affecting subpage btrfs, because for regular blocksize
== page size case, the function pagecache_isize_extended() will do
nothing if the block size >= page size.

[FIX]
Grab the old i_size while holding the inode lock.
This means each buffered write thread will have a stable view of the
old inode size, thus avoid the above race.

CC: stable@vger.kernel.org # 5.15+
Fixes: 5e8b9ef30392 ("btrfs: move pos increment and pagecache extension to btrfs_buffered_write")
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/file.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index ed3c0d6546c5d..0b568c8d24cbc 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1090,7 +1090,7 @@ ssize_t btrfs_buffered_write(struct kiocb *iocb, struct iov_iter *i)
 	u64 lockend;
 	size_t num_written = 0;
 	ssize_t ret;
-	loff_t old_isize = i_size_read(inode);
+	loff_t old_isize;
 	unsigned int ilock_flags = 0;
 	const bool nowait = (iocb->ki_flags & IOCB_NOWAIT);
 	unsigned int bdp_flags = (nowait ? BDP_ASYNC : 0);
@@ -1103,6 +1103,13 @@ ssize_t btrfs_buffered_write(struct kiocb *iocb, struct iov_iter *i)
 	if (ret < 0)
 		return ret;
 
+	/*
+	 * We can only trust the isize with inode lock held, or it can race with
+	 * other buffered writes and cause incorrect call of
+	 * pagecache_isize_extended() to overwrite existing data.
+	 */
+	old_isize = i_size_read(inode);
+
 	ret = generic_write_checks(iocb, i);
 	if (ret <= 0)
 		goto out;

From e9a48ea4d90be251e0d057d41665745caccb0351 Mon Sep 17 00:00:00 2001
From: Stephan Gerhold <stephan.gerhold@linaro.org>
Date: Tue, 18 Feb 2025 16:59:18 +0100
Subject: [PATCH 0435/1173] irqchip/qcom-pdc: Workaround hardware register bug
 on X1E80100

On X1E80100, there is a hardware bug in the register logic of the
IRQ_ENABLE_BANK register: While read accesses work on the normal address,
all write accesses must be made to a shifted address. Without a workaround
for this, the wrong interrupt gets enabled in the PDC and it is impossible
to wakeup from deep suspend (CX collapse). This has not caused problems so
far, because the deep suspend state was not enabled. A workaround is
required now since work is ongoing to fix this.

The PDC has multiple "DRV" regions, each one has a size of 0x10000 and
provides the same set of registers for a particular client in the system.
Linux is one the clients and uses DRV region 2 on X1E. Each "bank" inside
the DRV region consists of 32 interrupt pins that can be enabled using the
IRQ_ENABLE_BANK register:

  IRQ_ENABLE_BANK[bank] = base + IRQ_ENABLE_BANK + bank * sizeof(u32)

On X1E, this works as intended for read access. However, write access to
most banks is shifted by 2:

  IRQ_ENABLE_BANK_X1E[0] = IRQ_ENABLE_BANK[-2]
  IRQ_ENABLE_BANK_X1E[1] = IRQ_ENABLE_BANK[-1]
  IRQ_ENABLE_BANK_X1E[2] = IRQ_ENABLE_BANK[0] = IRQ_ENABLE_BANK[2 - 2]
  IRQ_ENABLE_BANK_X1E[3] = IRQ_ENABLE_BANK[1] = IRQ_ENABLE_BANK[3 - 2]
  IRQ_ENABLE_BANK_X1E[4] = IRQ_ENABLE_BANK[2] = IRQ_ENABLE_BANK[4 - 2]
  IRQ_ENABLE_BANK_X1E[5] = IRQ_ENABLE_BANK[5] (this one works as intended)

The negative indexes underflow to banks of the previous DRV/client region:

  IRQ_ENABLE_BANK_X1E[drv 2][bank 0] = IRQ_ENABLE_BANK[drv 2][bank -2]
                                     = IRQ_ENABLE_BANK[drv 1][bank 5-2]
                                     = IRQ_ENABLE_BANK[drv 1][bank 3]
                                     = IRQ_ENABLE_BANK[drv 1][bank 0 + 3]
  IRQ_ENABLE_BANK_X1E[drv 2][bank 1] = IRQ_ENABLE_BANK[drv 2][bank -1]
                                     = IRQ_ENABLE_BANK[drv 1][bank 5-1]
                                     = IRQ_ENABLE_BANK[drv 1][bank 4]
                                     = IRQ_ENABLE_BANK[drv 1][bank 1 + 3]

Introduce a workaround for the bug by matching the qcom,x1e80100-pdc
compatible and apply the offsets as shown above:

 - Bank 0...1: previous DRV region, bank += 3
 - Bank 1...4: our DRV region, bank -= 2
 - Bank 5: our DRV region, no fixup required

The PDC node in the device tree only describes the DRV region for the Linux
client, but the workaround also requires to map parts of the previous DRV
region to issue writes there. To maintain compatibility with old device
trees, obtain the base address of the preceeding region by applying the
-0x10000 offset. Note that this is also more correct from a conceptual
point of view:

It does not really make use of the other region; it just issues shifted
writes that end up in the registers of the Linux associated DRV region 2.

Signed-off-by: Stephan Gerhold <stephan.gerhold@linaro.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Johan Hovold <johan+linaro@kernel.org>
Link: https://lore.kernel.org/all/20250218-x1e80100-pdc-hw-wa-v2-1-29be4c98e355@linaro.org
---
 drivers/irqchip/qcom-pdc.c | 67 ++++++++++++++++++++++++++++++++++++--
 1 file changed, 64 insertions(+), 3 deletions(-)

diff --git a/drivers/irqchip/qcom-pdc.c b/drivers/irqchip/qcom-pdc.c
index 74b2f124116e3..52d77546aacb9 100644
--- a/drivers/irqchip/qcom-pdc.c
+++ b/drivers/irqchip/qcom-pdc.c
@@ -21,9 +21,11 @@
 #include <linux/types.h>
 
 #define PDC_MAX_GPIO_IRQS	256
+#define PDC_DRV_OFFSET		0x10000
 
 /* Valid only on HW version < 3.2 */
 #define IRQ_ENABLE_BANK		0x10
+#define IRQ_ENABLE_BANK_MAX	(IRQ_ENABLE_BANK + BITS_TO_BYTES(PDC_MAX_GPIO_IRQS))
 #define IRQ_i_CFG		0x110
 
 /* Valid only on HW version >= 3.2 */
@@ -46,13 +48,20 @@ struct pdc_pin_region {
 
 static DEFINE_RAW_SPINLOCK(pdc_lock);
 static void __iomem *pdc_base;
+static void __iomem *pdc_prev_base;
 static struct pdc_pin_region *pdc_region;
 static int pdc_region_cnt;
 static unsigned int pdc_version;
+static bool pdc_x1e_quirk;
+
+static void pdc_base_reg_write(void __iomem *base, int reg, u32 i, u32 val)
+{
+	writel_relaxed(val, base + reg + i * sizeof(u32));
+}
 
 static void pdc_reg_write(int reg, u32 i, u32 val)
 {
-	writel_relaxed(val, pdc_base + reg + i * sizeof(u32));
+	pdc_base_reg_write(pdc_base, reg, i, val);
 }
 
 static u32 pdc_reg_read(int reg, u32 i)
@@ -60,6 +69,34 @@ static u32 pdc_reg_read(int reg, u32 i)
 	return readl_relaxed(pdc_base + reg + i * sizeof(u32));
 }
 
+static void pdc_x1e_irq_enable_write(u32 bank, u32 enable)
+{
+	void __iomem *base;
+
+	/* Remap the write access to work around a hardware bug on X1E */
+	switch (bank) {
+	case 0 ... 1:
+		/* Use previous DRV (client) region and shift to bank 3-4 */
+		base = pdc_prev_base;
+		bank += 3;
+		break;
+	case 2 ... 4:
+		/* Use our own region and shift to bank 0-2 */
+		base = pdc_base;
+		bank -= 2;
+		break;
+	case 5:
+		/* No fixup required for bank 5 */
+		base = pdc_base;
+		break;
+	default:
+		WARN_ON(1);
+		return;
+	}
+
+	pdc_base_reg_write(base, IRQ_ENABLE_BANK, bank, enable);
+}
+
 static void __pdc_enable_intr(int pin_out, bool on)
 {
 	unsigned long enable;
@@ -72,7 +109,11 @@ static void __pdc_enable_intr(int pin_out, bool on)
 
 		enable = pdc_reg_read(IRQ_ENABLE_BANK, index);
 		__assign_bit(mask, &enable, on);
-		pdc_reg_write(IRQ_ENABLE_BANK, index, enable);
+
+		if (pdc_x1e_quirk)
+			pdc_x1e_irq_enable_write(index, enable);
+		else
+			pdc_reg_write(IRQ_ENABLE_BANK, index, enable);
 	} else {
 		enable = pdc_reg_read(IRQ_i_CFG, pin_out);
 		__assign_bit(IRQ_i_CFG_IRQ_ENABLE, &enable, on);
@@ -324,10 +365,29 @@ static int qcom_pdc_init(struct device_node *node, struct device_node *parent)
 	if (res_size > resource_size(&res))
 		pr_warn("%pOF: invalid reg size, please fix DT\n", node);
 
+	/*
+	 * PDC has multiple DRV regions, each one provides the same set of
+	 * registers for a particular client in the system. Due to a hardware
+	 * bug on X1E, some writes to the IRQ_ENABLE_BANK register must be
+	 * issued inside the previous region. This region belongs to
+	 * a different client and is not described in the device tree. Map the
+	 * region with the expected offset to preserve support for old DTs.
+	 */
+	if (of_device_is_compatible(node, "qcom,x1e80100-pdc")) {
+		pdc_prev_base = ioremap(res.start - PDC_DRV_OFFSET, IRQ_ENABLE_BANK_MAX);
+		if (!pdc_prev_base) {
+			pr_err("%pOF: unable to map previous PDC DRV region\n", node);
+			return -ENXIO;
+		}
+
+		pdc_x1e_quirk = true;
+	}
+
 	pdc_base = ioremap(res.start, res_size);
 	if (!pdc_base) {
 		pr_err("%pOF: unable to map PDC registers\n", node);
-		return -ENXIO;
+		ret = -ENXIO;
+		goto fail;
 	}
 
 	pdc_version = pdc_reg_read(PDC_VERSION_REG, 0);
@@ -363,6 +423,7 @@ static int qcom_pdc_init(struct device_node *node, struct device_node *parent)
 fail:
 	kfree(pdc_region);
 	iounmap(pdc_base);
+	iounmap(pdc_prev_base);
 	return ret;
 }
 

From 3ef32d90cdaa0cfa6c4ffd18f8d646a658163e3d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Tue, 4 Feb 2025 13:05:33 +0100
Subject: [PATCH 0436/1173] x86/vdso: Fix latent bug in vclock_pages
 calculation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The vclock pages are *after* the non-vclock pages. Currently there are both
two vclock and two non-vclock pages so the existing logic works by
accident.  As soon as the number of pages changes it will break however.
This will be the case with the introduction of the generic vDSO data
storage.

Use a macro to keep the calculation understandable and in sync between
the linker script and mapping code.

Fixes: e93d2521b27f ("x86/vdso: Split virtual clock pages into dedicated mapping")
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250204-vdso-store-rng-v3-1-13a4669dfc8c@linutronix.de
---
 arch/x86/entry/vdso/vdso-layout.lds.S | 2 +-
 arch/x86/entry/vdso/vma.c             | 2 +-
 arch/x86/include/asm/vdso/vsyscall.h  | 1 +
 3 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/arch/x86/entry/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S
index 872947c1004c3..918606ff92a98 100644
--- a/arch/x86/entry/vdso/vdso-layout.lds.S
+++ b/arch/x86/entry/vdso/vdso-layout.lds.S
@@ -24,7 +24,7 @@ SECTIONS
 
 	timens_page  = vvar_start + PAGE_SIZE;
 
-	vclock_pages = vvar_start + VDSO_NR_VCLOCK_PAGES * PAGE_SIZE;
+	vclock_pages = VDSO_VCLOCK_PAGES_START(vvar_start);
 	pvclock_page = vclock_pages + VDSO_PAGE_PVCLOCK_OFFSET * PAGE_SIZE;
 	hvclock_page = vclock_pages + VDSO_PAGE_HVCLOCK_OFFSET * PAGE_SIZE;
 
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 39e6efc1a9cab..aa62949335ece 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -290,7 +290,7 @@ static int map_vdso(const struct vdso_image *image, unsigned long addr)
 	}
 
 	vma = _install_special_mapping(mm,
-				       addr + (__VVAR_PAGES - VDSO_NR_VCLOCK_PAGES) * PAGE_SIZE,
+				       VDSO_VCLOCK_PAGES_START(addr),
 				       VDSO_NR_VCLOCK_PAGES * PAGE_SIZE,
 				       VM_READ|VM_MAYREAD|VM_IO|VM_DONTDUMP|
 				       VM_PFNMAP,
diff --git a/arch/x86/include/asm/vdso/vsyscall.h b/arch/x86/include/asm/vdso/vsyscall.h
index 37b4a70559a82..88b31d4cdfaf3 100644
--- a/arch/x86/include/asm/vdso/vsyscall.h
+++ b/arch/x86/include/asm/vdso/vsyscall.h
@@ -6,6 +6,7 @@
 #define __VVAR_PAGES	4
 
 #define VDSO_NR_VCLOCK_PAGES	2
+#define VDSO_VCLOCK_PAGES_START(_b)	((_b) + (__VVAR_PAGES - VDSO_NR_VCLOCK_PAGES) * PAGE_SIZE)
 #define VDSO_PAGE_PVCLOCK_OFFSET	0
 #define VDSO_PAGE_HVCLOCK_OFFSET	1
 

From 30533a55ec8e6cd532989421a2d99ec422396fce Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Tue, 4 Feb 2025 13:05:34 +0100
Subject: [PATCH 0437/1173] parisc: Remove unused symbol vdso_data
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The symbol vdso_data is and has been unused.
Remove it.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250204-vdso-store-rng-v3-2-13a4669dfc8c@linutronix.de
---
 arch/parisc/include/asm/vdso.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/arch/parisc/include/asm/vdso.h b/arch/parisc/include/asm/vdso.h
index 2a2dc11b5545f..5f581c1d64606 100644
--- a/arch/parisc/include/asm/vdso.h
+++ b/arch/parisc/include/asm/vdso.h
@@ -12,8 +12,6 @@
 #define VDSO64_SYMBOL(tsk, name) ((tsk)->mm->context.vdso_base + (vdso64_offset_##name))
 #define VDSO32_SYMBOL(tsk, name) ((tsk)->mm->context.vdso_base + (vdso32_offset_##name))
 
-extern struct vdso_data *vdso_data;
-
 #endif /* __ASSEMBLY __ */
 
 /* Default link addresses for the vDSOs */

From 5b47aba858101639a4442c2140b73f64eb796ed1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Tue, 4 Feb 2025 13:05:35 +0100
Subject: [PATCH 0438/1173] vdso: Introduce vdso/align.h
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The vDSO implementation can only include headers from the vdso/
namespace. To enable the usage of the ALIGN() macro from the vDSO, move
linux/align.h to vdso/align.h wholly.
As the only dependency linux/const.h is only a wrapper around
vdso/const.h anyways adapt that dependency.

Also provide a compatibility wrapper linux/align.h.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250204-vdso-store-rng-v3-3-13a4669dfc8c@linutronix.de
---
 include/linux/align.h | 10 +---------
 include/vdso/align.h  | 15 +++++++++++++++
 2 files changed, 16 insertions(+), 9 deletions(-)
 create mode 100644 include/vdso/align.h

diff --git a/include/linux/align.h b/include/linux/align.h
index 2b4acec7b95a2..55debf105a5d6 100644
--- a/include/linux/align.h
+++ b/include/linux/align.h
@@ -2,14 +2,6 @@
 #ifndef _LINUX_ALIGN_H
 #define _LINUX_ALIGN_H
 
-#include <linux/const.h>
-
-/* @a is a power of 2 value */
-#define ALIGN(x, a)		__ALIGN_KERNEL((x), (a))
-#define ALIGN_DOWN(x, a)	__ALIGN_KERNEL((x) - ((a) - 1), (a))
-#define __ALIGN_MASK(x, mask)	__ALIGN_KERNEL_MASK((x), (mask))
-#define PTR_ALIGN(p, a)		((typeof(p))ALIGN((unsigned long)(p), (a)))
-#define PTR_ALIGN_DOWN(p, a)	((typeof(p))ALIGN_DOWN((unsigned long)(p), (a)))
-#define IS_ALIGNED(x, a)		(((x) & ((typeof(x))(a) - 1)) == 0)
+#include <vdso/align.h>
 
 #endif	/* _LINUX_ALIGN_H */
diff --git a/include/vdso/align.h b/include/vdso/align.h
new file mode 100644
index 0000000000000..02dd8626b5c5a
--- /dev/null
+++ b/include/vdso/align.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __VDSO_ALIGN_H
+#define __VDSO_ALIGN_H
+
+#include <vdso/const.h>
+
+/* @a is a power of 2 value */
+#define ALIGN(x, a)		__ALIGN_KERNEL((x), (a))
+#define ALIGN_DOWN(x, a)	__ALIGN_KERNEL((x) - ((a) - 1), (a))
+#define __ALIGN_MASK(x, mask)	__ALIGN_KERNEL_MASK((x), (mask))
+#define PTR_ALIGN(p, a)		((typeof(p))ALIGN((unsigned long)(p), (a)))
+#define PTR_ALIGN_DOWN(p, a)	((typeof(p))ALIGN_DOWN((unsigned long)(p), (a)))
+#define IS_ALIGNED(x, a)		(((x) & ((typeof(x))(a) - 1)) == 0)
+
+#endif	/* __VDSO_ALIGN_H */

From 127b0e05c1669d240426719b3b9db8a8366eed50 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Tue, 4 Feb 2025 13:05:36 +0100
Subject: [PATCH 0439/1173] vdso: Rename included Makefile
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

As the Makefile is included into other Makefiles it can not be used to
define objects to be built from the current source directory.
However the generic datastore will introduce such a local source file.
Rename the included Makefile so it is clear how it is to be used and to
make room for a regular Makefile in lib/vdso/.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250204-vdso-store-rng-v3-4-13a4669dfc8c@linutronix.de
---
 arch/arm/vdso/Makefile                  | 2 +-
 arch/arm64/kernel/vdso/Makefile         | 2 +-
 arch/arm64/kernel/vdso32/Makefile       | 2 +-
 arch/csky/kernel/vdso/Makefile          | 2 +-
 arch/loongarch/vdso/Makefile            | 2 +-
 arch/mips/vdso/Makefile                 | 2 +-
 arch/parisc/kernel/vdso32/Makefile      | 2 +-
 arch/parisc/kernel/vdso64/Makefile      | 2 +-
 arch/powerpc/kernel/vdso/Makefile       | 2 +-
 arch/riscv/kernel/vdso/Makefile         | 2 +-
 arch/s390/kernel/vdso32/Makefile        | 2 +-
 arch/s390/kernel/vdso64/Makefile        | 2 +-
 arch/x86/entry/vdso/Makefile            | 2 +-
 lib/vdso/{Makefile => Makefile.include} | 0
 14 files changed, 13 insertions(+), 13 deletions(-)
 rename lib/vdso/{Makefile => Makefile.include} (100%)

diff --git a/arch/arm/vdso/Makefile b/arch/arm/vdso/Makefile
index 8a306bbec4a0c..cb044bfd145d1 100644
--- a/arch/arm/vdso/Makefile
+++ b/arch/arm/vdso/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 
 # Include the generic Makefile to check the built vdso.
-include $(srctree)/lib/vdso/Makefile
+include $(srctree)/lib/vdso/Makefile.include
 
 hostprogs := vdsomunge
 
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index 35685c0360441..5e27e46aa4967 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -7,7 +7,7 @@
 #
 
 # Include the generic Makefile to check the built vdso.
-include $(srctree)/lib/vdso/Makefile
+include $(srctree)/lib/vdso/Makefile.include
 
 obj-vdso := vgettimeofday.o note.o sigreturn.o vgetrandom.o vgetrandom-chacha.o
 
diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile
index 25a2cb6317f35..f2dfdc7dc8185 100644
--- a/arch/arm64/kernel/vdso32/Makefile
+++ b/arch/arm64/kernel/vdso32/Makefile
@@ -3,7 +3,7 @@
 # Makefile for vdso32
 #
 
-include $(srctree)/lib/vdso/Makefile
+include $(srctree)/lib/vdso/Makefile.include
 
 # Same as cc-*option, but using CC_COMPAT instead of CC
 ifeq ($(CONFIG_CC_IS_CLANG), y)
diff --git a/arch/csky/kernel/vdso/Makefile b/arch/csky/kernel/vdso/Makefile
index 069ef0b17fe52..a3042287a0707 100644
--- a/arch/csky/kernel/vdso/Makefile
+++ b/arch/csky/kernel/vdso/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
 # Include the generic Makefile to check the built vdso.
-include $(srctree)/lib/vdso/Makefile
+include $(srctree)/lib/vdso/Makefile.include
 
 # Symbols present in the vdso
 vdso-syms  += rt_sigreturn
diff --git a/arch/loongarch/vdso/Makefile b/arch/loongarch/vdso/Makefile
index fdde1bcd4e266..1c26147aff701 100644
--- a/arch/loongarch/vdso/Makefile
+++ b/arch/loongarch/vdso/Makefile
@@ -2,7 +2,7 @@
 # Objects to go into the VDSO.
 
 # Include the generic Makefile to check the built vdso.
-include $(srctree)/lib/vdso/Makefile
+include $(srctree)/lib/vdso/Makefile.include
 
 obj-vdso-y := elf.o vgetcpu.o vgettimeofday.o vgetrandom.o \
               vgetrandom-chacha.o sigreturn.o
diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile
index b289b2c1b2946..fb4c493aaffa9 100644
--- a/arch/mips/vdso/Makefile
+++ b/arch/mips/vdso/Makefile
@@ -2,7 +2,7 @@
 # Objects to go into the VDSO.
 
 # Include the generic Makefile to check the built vdso.
-include $(srctree)/lib/vdso/Makefile
+include $(srctree)/lib/vdso/Makefile.include
 
 obj-vdso-y := elf.o vgettimeofday.o sigreturn.o
 
diff --git a/arch/parisc/kernel/vdso32/Makefile b/arch/parisc/kernel/vdso32/Makefile
index 288f8b85978fb..4ee8d17da229b 100644
--- a/arch/parisc/kernel/vdso32/Makefile
+++ b/arch/parisc/kernel/vdso32/Makefile
@@ -1,5 +1,5 @@
 # Include the generic Makefile to check the built vdso.
-include $(srctree)/lib/vdso/Makefile
+include $(srctree)/lib/vdso/Makefile.include
 
 KCOV_INSTRUMENT := n
 
diff --git a/arch/parisc/kernel/vdso64/Makefile b/arch/parisc/kernel/vdso64/Makefile
index bc5d9553f3112..c63f4069170f4 100644
--- a/arch/parisc/kernel/vdso64/Makefile
+++ b/arch/parisc/kernel/vdso64/Makefile
@@ -1,5 +1,5 @@
 # Include the generic Makefile to check the built vdso.
-include $(srctree)/lib/vdso/Makefile
+include $(srctree)/lib/vdso/Makefile.include
 
 KCOV_INSTRUMENT := n
 
diff --git a/arch/powerpc/kernel/vdso/Makefile b/arch/powerpc/kernel/vdso/Makefile
index 0e3ed6fb199ff..e8824f9333261 100644
--- a/arch/powerpc/kernel/vdso/Makefile
+++ b/arch/powerpc/kernel/vdso/Makefile
@@ -3,7 +3,7 @@
 # List of files in the vdso, has to be asm only for now
 
 # Include the generic Makefile to check the built vdso.
-include $(srctree)/lib/vdso/Makefile
+include $(srctree)/lib/vdso/Makefile.include
 
 obj-vdso32 = sigtramp32-32.o gettimeofday-32.o datapage-32.o cacheflush-32.o note-32.o getcpu-32.o
 obj-vdso64 = sigtramp64-64.o gettimeofday-64.o datapage-64.o cacheflush-64.o note-64.o getcpu-64.o
diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile
index 9a1b555e87331..ad73607abc280 100644
--- a/arch/riscv/kernel/vdso/Makefile
+++ b/arch/riscv/kernel/vdso/Makefile
@@ -2,7 +2,7 @@
 # Copied from arch/tile/kernel/vdso/Makefile
 
 # Include the generic Makefile to check the built vdso.
-include $(srctree)/lib/vdso/Makefile
+include $(srctree)/lib/vdso/Makefile.include
 # Symbols present in the vdso
 vdso-syms  = rt_sigreturn
 ifdef CONFIG_64BIT
diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile
index 2c5afb88d2982..1e4ddd1a683ff 100644
--- a/arch/s390/kernel/vdso32/Makefile
+++ b/arch/s390/kernel/vdso32/Makefile
@@ -2,7 +2,7 @@
 # List of files in the vdso
 
 # Include the generic Makefile to check the built vdso.
-include $(srctree)/lib/vdso/Makefile
+include $(srctree)/lib/vdso/Makefile.include
 obj-vdso32 = vdso_user_wrapper-32.o note-32.o
 
 # Build rules
diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile
index ad206f2068d8c..d8f0df7428096 100644
--- a/arch/s390/kernel/vdso64/Makefile
+++ b/arch/s390/kernel/vdso64/Makefile
@@ -2,7 +2,7 @@
 # List of files in the vdso
 
 # Include the generic Makefile to check the built vdso.
-include $(srctree)/lib/vdso/Makefile
+include $(srctree)/lib/vdso/Makefile.include
 obj-vdso64 = vdso_user_wrapper.o note.o vgetrandom-chacha.o
 obj-cvdso64 = vdso64_generic.o getcpu.o vgetrandom.o
 VDSO_CFLAGS_REMOVE := -pg $(CC_FLAGS_FTRACE) $(CC_FLAGS_EXPOLINE)
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index c9216ac4fb1eb..1c0072336e661 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -4,7 +4,7 @@
 #
 
 # Include the generic Makefile to check the built vDSO:
-include $(srctree)/lib/vdso/Makefile
+include $(srctree)/lib/vdso/Makefile.include
 
 # Files to link into the vDSO:
 vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o vgetrandom.o vgetrandom-chacha.o
diff --git a/lib/vdso/Makefile b/lib/vdso/Makefile.include
similarity index 100%
rename from lib/vdso/Makefile
rename to lib/vdso/Makefile.include

From df7fcbefa71090a276fb841ffe19b8e5f12b4767 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Tue, 4 Feb 2025 13:05:37 +0100
Subject: [PATCH 0440/1173] vdso: Add generic time data storage
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Historically each architecture defined their own way to store the vDSO
data page. Add a generic mechanism to provide storage for that page.

Furthermore this generic storage will be extended to also provide
uniform storage for *non*-time-related data, like the random state or
architecture-specific data. These will have their own pages and data
structures, so rename 'vdso_data' into 'vdso_time_data' to make that
split clear from the name.

Also introduce a new consistent naming scheme for the symbols related to
the vDSO, which makes it clear if the symbol is accessible from
userspace or kernel space and the type of data behind the symbol.

The generic fault handler contains an optimization to prefault the vvar
page when the timens page is accessed. This was lifted from s390 and x86.

Co-developed-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250204-vdso-store-rng-v3-5-13a4669dfc8c@linutronix.de
---
 include/asm-generic/vdso/vsyscall.h |  16 +++++
 include/linux/time_namespace.h      |   1 +
 include/linux/vdso_datastore.h      |  10 +++
 include/vdso/datapage.h             |  41 ++++++++---
 kernel/time/vsyscall.c              |   8 +--
 lib/Makefile                        |   2 +-
 lib/vdso/Kconfig                    |   5 ++
 lib/vdso/Makefile                   |   3 +
 lib/vdso/datastore.c                | 103 ++++++++++++++++++++++++++++
 lib/vdso/gettimeofday.c             |  25 +++++--
 10 files changed, 195 insertions(+), 19 deletions(-)
 create mode 100644 include/linux/vdso_datastore.h
 create mode 100644 lib/vdso/Makefile
 create mode 100644 lib/vdso/datastore.c

diff --git a/include/asm-generic/vdso/vsyscall.h b/include/asm-generic/vdso/vsyscall.h
index 01dafd604188f..ac5b93b919932 100644
--- a/include/asm-generic/vdso/vsyscall.h
+++ b/include/asm-generic/vdso/vsyscall.h
@@ -4,12 +4,28 @@
 
 #ifndef __ASSEMBLY__
 
+#ifdef CONFIG_GENERIC_VDSO_DATA_STORE
+
+#ifndef __arch_get_vdso_u_time_data
+static __always_inline const struct vdso_time_data *__arch_get_vdso_u_time_data(void)
+{
+	return vdso_u_time_data;
+}
+#endif
+
+#else  /* !CONFIG_GENERIC_VDSO_DATA_STORE */
+
 #ifndef __arch_get_k_vdso_data
 static __always_inline struct vdso_data *__arch_get_k_vdso_data(void)
 {
 	return NULL;
 }
 #endif /* __arch_get_k_vdso_data */
+#define vdso_k_time_data __arch_get_k_vdso_data()
+
+#define __arch_get_vdso_u_time_data __arch_get_vdso_data
+
+#endif /* CONFIG_GENERIC_VDSO_DATA_STORE */
 
 #ifndef __arch_update_vsyscall
 static __always_inline void __arch_update_vsyscall(struct vdso_data *vdata)
diff --git a/include/linux/time_namespace.h b/include/linux/time_namespace.h
index 876e31b4461d0..4b81db223f545 100644
--- a/include/linux/time_namespace.h
+++ b/include/linux/time_namespace.h
@@ -8,6 +8,7 @@
 #include <linux/ns_common.h>
 #include <linux/err.h>
 #include <linux/time64.h>
+#include <vdso/datapage.h>
 
 struct user_namespace;
 extern struct user_namespace init_user_ns;
diff --git a/include/linux/vdso_datastore.h b/include/linux/vdso_datastore.h
new file mode 100644
index 0000000000000..a91fa24b06e09
--- /dev/null
+++ b/include/linux/vdso_datastore.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_VDSO_DATASTORE_H
+#define _LINUX_VDSO_DATASTORE_H
+
+#include <linux/mm_types.h>
+
+extern const struct vm_special_mapping vdso_vvar_mapping;
+struct vm_area_struct *vdso_install_vvar_mapping(struct mm_struct *mm, unsigned long addr);
+
+#endif /* _LINUX_VDSO_DATASTORE_H */
diff --git a/include/vdso/datapage.h b/include/vdso/datapage.h
index d967baa0cd0c6..b3d8087488ff3 100644
--- a/include/vdso/datapage.h
+++ b/include/vdso/datapage.h
@@ -45,11 +45,11 @@ struct arch_vdso_time_data {};
  *
  * There is one vdso_timestamp object in vvar for each vDSO-accelerated
  * clock_id. For high-resolution clocks, this encodes the time
- * corresponding to vdso_data.cycle_last. For coarse clocks this encodes
+ * corresponding to vdso_time_data.cycle_last. For coarse clocks this encodes
  * the actual time.
  *
  * To be noticed that for highres clocks nsec is left-shifted by
- * vdso_data.cs[x].shift.
+ * vdso_time_data[x].shift.
  */
 struct vdso_timestamp {
 	u64	sec;
@@ -57,7 +57,7 @@ struct vdso_timestamp {
 };
 
 /**
- * struct vdso_data - vdso datapage representation
+ * struct vdso_time_data - vdso datapage representation
  * @seq:		timebase sequence counter
  * @clock_mode:		clock mode
  * @cycle_last:		timebase at clocksource init
@@ -74,7 +74,7 @@ struct vdso_timestamp {
  * @arch_data:		architecture specific data (optional, defaults
  *			to an empty struct)
  *
- * vdso_data will be accessed by 64 bit and compat code at the same time
+ * vdso_time_data will be accessed by 64 bit and compat code at the same time
  * so we should be careful before modifying this structure.
  *
  * The ordering of the struct members is optimized to have fast access to the
@@ -92,7 +92,7 @@ struct vdso_timestamp {
  * For clocks which are not affected by time namespace adjustment the
  * offset must be zero.
  */
-struct vdso_data {
+struct vdso_time_data {
 	u32			seq;
 
 	s32			clock_mode;
@@ -117,6 +117,8 @@ struct vdso_data {
 	struct arch_vdso_time_data arch_data;
 };
 
+#define vdso_data vdso_time_data
+
 /**
  * struct vdso_rng_data - vdso RNG state information
  * @generation:	counter representing the number of RNG reseeds
@@ -136,18 +138,34 @@ struct vdso_rng_data {
  * With the hidden visibility, the compiler simply generates a PC-relative
  * relocation, and this is what we need.
  */
-extern struct vdso_data _vdso_data[CS_BASES] __attribute__((visibility("hidden")));
-extern struct vdso_data _timens_data[CS_BASES] __attribute__((visibility("hidden")));
+#ifndef CONFIG_GENERIC_VDSO_DATA_STORE
+extern struct vdso_time_data _vdso_data[CS_BASES] __attribute__((visibility("hidden")));
+extern struct vdso_time_data _timens_data[CS_BASES] __attribute__((visibility("hidden")));
 extern struct vdso_rng_data _vdso_rng_data __attribute__((visibility("hidden")));
+#else
+extern struct vdso_time_data vdso_u_time_data[CS_BASES] __attribute__((visibility("hidden")));
+
+extern struct vdso_time_data *vdso_k_time_data;
+#endif
 
 /**
  * union vdso_data_store - Generic vDSO data page
  */
 union vdso_data_store {
-	struct vdso_data	data[CS_BASES];
+	struct vdso_time_data	data[CS_BASES];
 	u8			page[1U << CONFIG_PAGE_SHIFT];
 };
 
+#ifdef CONFIG_GENERIC_VDSO_DATA_STORE
+
+enum vdso_pages {
+	VDSO_TIME_PAGE_OFFSET,
+	VDSO_TIMENS_PAGE_OFFSET,
+	VDSO_NR_PAGES
+};
+
+#endif /* CONFIG_GENERIC_VDSO_DATA_STORE */
+
 /*
  * The generic vDSO implementation requires that gettimeofday.h
  * provides:
@@ -164,6 +182,13 @@ union vdso_data_store {
 #include <asm/vdso/gettimeofday.h>
 #endif /* ENABLE_COMPAT_VDSO */
 
+#else /* !__ASSEMBLY__ */
+
+#define VDSO_VVAR_SYMS						\
+	PROVIDE(vdso_u_data = . - __VDSO_PAGES * PAGE_SIZE);	\
+	PROVIDE(vdso_u_time_data = vdso_u_data);		\
+
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __VDSO_DATAPAGE_H */
diff --git a/kernel/time/vsyscall.c b/kernel/time/vsyscall.c
index 05d3831431658..09c1e39a6dd8e 100644
--- a/kernel/time/vsyscall.c
+++ b/kernel/time/vsyscall.c
@@ -77,7 +77,7 @@ static inline void update_vdso_data(struct vdso_data *vdata,
 
 void update_vsyscall(struct timekeeper *tk)
 {
-	struct vdso_data *vdata = __arch_get_k_vdso_data();
+	struct vdso_data *vdata = vdso_k_time_data;
 	struct vdso_timestamp *vdso_ts;
 	s32 clock_mode;
 	u64 nsec;
@@ -128,7 +128,7 @@ void update_vsyscall(struct timekeeper *tk)
 
 void update_vsyscall_tz(void)
 {
-	struct vdso_data *vdata = __arch_get_k_vdso_data();
+	struct vdso_data *vdata = vdso_k_time_data;
 
 	vdata[CS_HRES_COARSE].tz_minuteswest = sys_tz.tz_minuteswest;
 	vdata[CS_HRES_COARSE].tz_dsttime = sys_tz.tz_dsttime;
@@ -150,7 +150,7 @@ void update_vsyscall_tz(void)
  */
 unsigned long vdso_update_begin(void)
 {
-	struct vdso_data *vdata = __arch_get_k_vdso_data();
+	struct vdso_data *vdata = vdso_k_time_data;
 	unsigned long flags = timekeeper_lock_irqsave();
 
 	vdso_write_begin(vdata);
@@ -167,7 +167,7 @@ unsigned long vdso_update_begin(void)
  */
 void vdso_update_end(unsigned long flags)
 {
-	struct vdso_data *vdata = __arch_get_k_vdso_data();
+	struct vdso_data *vdata = vdso_k_time_data;
 
 	vdso_write_end(vdata);
 	__arch_sync_vdso_data(vdata);
diff --git a/lib/Makefile b/lib/Makefile
index d5cfc7afbbb82..fcdee83deb5c6 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -132,7 +132,7 @@ endif
 obj-$(CONFIG_DEBUG_INFO_REDUCED) += debug_info.o
 CFLAGS_debug_info.o += $(call cc-option, -femit-struct-debug-detailed=any)
 
-obj-y += math/ crypto/
+obj-y += math/ crypto/ vdso/
 
 obj-$(CONFIG_GENERIC_IOMAP) += iomap.o
 obj-$(CONFIG_HAS_IOMEM) += iomap_copy.o devres.o
diff --git a/lib/vdso/Kconfig b/lib/vdso/Kconfig
index 82fe827af5426..45df764b49ad6 100644
--- a/lib/vdso/Kconfig
+++ b/lib/vdso/Kconfig
@@ -43,3 +43,8 @@ config VDSO_GETRANDOM
 	bool
 	help
 	  Selected by architectures that support vDSO getrandom().
+
+config GENERIC_VDSO_DATA_STORE
+	bool
+	help
+	  Selected by architectures that use the generic vDSO data store.
diff --git a/lib/vdso/Makefile b/lib/vdso/Makefile
new file mode 100644
index 0000000000000..aedd40aaa950c
--- /dev/null
+++ b/lib/vdso/Makefile
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+obj-$(CONFIG_GENERIC_VDSO_DATA_STORE) += datastore.o
diff --git a/lib/vdso/datastore.c b/lib/vdso/datastore.c
new file mode 100644
index 0000000000000..d3181768424cc
--- /dev/null
+++ b/lib/vdso/datastore.c
@@ -0,0 +1,103 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/linkage.h>
+#include <linux/mmap_lock.h>
+#include <linux/mm.h>
+#include <linux/time_namespace.h>
+#include <linux/types.h>
+#include <linux/vdso_datastore.h>
+#include <vdso/datapage.h>
+
+/*
+ * The vDSO data page.
+ */
+#ifdef CONFIG_HAVE_GENERIC_VDSO
+static union vdso_data_store vdso_time_data_store __page_aligned_data;
+struct vdso_time_data *vdso_k_time_data = vdso_time_data_store.data;
+static_assert(sizeof(vdso_time_data_store) == PAGE_SIZE);
+#endif /* CONFIG_HAVE_GENERIC_VDSO */
+
+static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
+			     struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct page *timens_page = find_timens_vvar_page(vma);
+	unsigned long addr, pfn;
+	vm_fault_t err;
+
+	switch (vmf->pgoff) {
+	case VDSO_TIME_PAGE_OFFSET:
+		if (!IS_ENABLED(CONFIG_HAVE_GENERIC_VDSO))
+			return VM_FAULT_SIGBUS;
+		pfn = __phys_to_pfn(__pa_symbol(vdso_k_time_data));
+		if (timens_page) {
+			/*
+			 * Fault in VVAR page too, since it will be accessed
+			 * to get clock data anyway.
+			 */
+			addr = vmf->address + VDSO_TIMENS_PAGE_OFFSET * PAGE_SIZE;
+			err = vmf_insert_pfn(vma, addr, pfn);
+			if (unlikely(err & VM_FAULT_ERROR))
+				return err;
+			pfn = page_to_pfn(timens_page);
+		}
+		break;
+	case VDSO_TIMENS_PAGE_OFFSET:
+		/*
+		 * If a task belongs to a time namespace then a namespace
+		 * specific VVAR is mapped with the VVAR_DATA_PAGE_OFFSET and
+		 * the real VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET
+		 * offset.
+		 * See also the comment near timens_setup_vdso_data().
+		 */
+		if (!IS_ENABLED(CONFIG_TIME_NS) || !timens_page)
+			return VM_FAULT_SIGBUS;
+		pfn = __phys_to_pfn(__pa_symbol(vdso_k_time_data));
+		break;
+	default:
+		return VM_FAULT_SIGBUS;
+	}
+
+	return vmf_insert_pfn(vma, vmf->address, pfn);
+}
+
+const struct vm_special_mapping vdso_vvar_mapping = {
+	.name	= "[vvar]",
+	.fault	= vvar_fault,
+};
+
+struct vm_area_struct *vdso_install_vvar_mapping(struct mm_struct *mm, unsigned long addr)
+{
+	return _install_special_mapping(mm, addr, VDSO_NR_PAGES * PAGE_SIZE,
+					VM_READ | VM_MAYREAD | VM_IO | VM_DONTDUMP | VM_PFNMAP,
+					&vdso_vvar_mapping);
+}
+
+#ifdef CONFIG_TIME_NS
+/*
+ * The vvar page layout depends on whether a task belongs to the root or
+ * non-root time namespace. Whenever a task changes its namespace, the VVAR
+ * page tables are cleared and then they will be re-faulted with a
+ * corresponding layout.
+ * See also the comment near timens_setup_vdso_data() for details.
+ */
+int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
+{
+	struct mm_struct *mm = task->mm;
+	struct vm_area_struct *vma;
+	VMA_ITERATOR(vmi, mm, 0);
+
+	mmap_read_lock(mm);
+	for_each_vma(vmi, vma) {
+		if (vma_is_special_mapping(vma, &vdso_vvar_mapping))
+			zap_vma_pages(vma);
+	}
+	mmap_read_unlock(mm);
+
+	return 0;
+}
+
+struct vdso_time_data *arch_get_vdso_data(void *vvar_page)
+{
+	return (struct vdso_time_data *)vvar_page;
+}
+#endif
diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c
index c01eaafd80419..20c5b8752fcc8 100644
--- a/lib/vdso/gettimeofday.c
+++ b/lib/vdso/gettimeofday.c
@@ -5,6 +5,9 @@
 #include <vdso/datapage.h>
 #include <vdso/helpers.h>
 
+/* Bring in default accessors */
+#include <vdso/vsyscall.h>
+
 #ifndef vdso_calc_ns
 
 #ifdef VDSO_DELTA_NOMASK
@@ -69,6 +72,16 @@ static inline bool vdso_cycles_ok(u64 cycles)
 #endif
 
 #ifdef CONFIG_TIME_NS
+
+#ifdef CONFIG_GENERIC_VDSO_DATA_STORE
+static __always_inline
+const struct vdso_time_data *__arch_get_vdso_u_timens_data(const struct vdso_time_data *vd)
+{
+	return (void *)vd + PAGE_SIZE;
+}
+#define __arch_get_timens_vdso_data(vd) __arch_get_vdso_u_timens_data(vd)
+#endif /* CONFIG_GENERIC_VDSO_DATA_STORE */
+
 static __always_inline int do_hres_timens(const struct vdso_data *vdns, clockid_t clk,
 					  struct __kernel_timespec *ts)
 {
@@ -282,7 +295,7 @@ __cvdso_clock_gettime_data(const struct vdso_data *vd, clockid_t clock,
 static __maybe_unused int
 __cvdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts)
 {
-	return __cvdso_clock_gettime_data(__arch_get_vdso_data(), clock, ts);
+	return __cvdso_clock_gettime_data(__arch_get_vdso_u_time_data(), clock, ts);
 }
 
 #ifdef BUILD_VDSO32
@@ -308,7 +321,7 @@ __cvdso_clock_gettime32_data(const struct vdso_data *vd, clockid_t clock,
 static __maybe_unused int
 __cvdso_clock_gettime32(clockid_t clock, struct old_timespec32 *res)
 {
-	return __cvdso_clock_gettime32_data(__arch_get_vdso_data(), clock, res);
+	return __cvdso_clock_gettime32_data(__arch_get_vdso_u_time_data(), clock, res);
 }
 #endif /* BUILD_VDSO32 */
 
@@ -342,7 +355,7 @@ __cvdso_gettimeofday_data(const struct vdso_data *vd,
 static __maybe_unused int
 __cvdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
 {
-	return __cvdso_gettimeofday_data(__arch_get_vdso_data(), tv, tz);
+	return __cvdso_gettimeofday_data(__arch_get_vdso_u_time_data(), tv, tz);
 }
 
 #ifdef VDSO_HAS_TIME
@@ -365,7 +378,7 @@ __cvdso_time_data(const struct vdso_data *vd, __kernel_old_time_t *time)
 
 static __maybe_unused __kernel_old_time_t __cvdso_time(__kernel_old_time_t *time)
 {
-	return __cvdso_time_data(__arch_get_vdso_data(), time);
+	return __cvdso_time_data(__arch_get_vdso_u_time_data(), time);
 }
 #endif /* VDSO_HAS_TIME */
 
@@ -425,7 +438,7 @@ int __cvdso_clock_getres_data(const struct vdso_data *vd, clockid_t clock,
 static __maybe_unused
 int __cvdso_clock_getres(clockid_t clock, struct __kernel_timespec *res)
 {
-	return __cvdso_clock_getres_data(__arch_get_vdso_data(), clock, res);
+	return __cvdso_clock_getres_data(__arch_get_vdso_u_time_data(), clock, res);
 }
 
 #ifdef BUILD_VDSO32
@@ -451,7 +464,7 @@ __cvdso_clock_getres_time32_data(const struct vdso_data *vd, clockid_t clock,
 static __maybe_unused int
 __cvdso_clock_getres_time32(clockid_t clock, struct old_timespec32 *res)
 {
-	return __cvdso_clock_getres_time32_data(__arch_get_vdso_data(),
+	return __cvdso_clock_getres_time32_data(__arch_get_vdso_u_time_data(),
 						clock, res);
 }
 #endif /* BUILD_VDSO32 */

From 51d6ca373f459fa6c91743e14ae69854d844aa38 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Tue, 4 Feb 2025 13:05:38 +0100
Subject: [PATCH 0441/1173] vdso: Add generic random data storage
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Extend the generic vDSO data storage with a page for the random state data.
The random state data is stored in a dedicated page, as the existing
storage page is only meant for time-related, time-namespace-aware data.
This simplifies to access logic to not need to handle time namespaces
anymore and also frees up more space in the time-related page.

In case further generic vDSO data store is required it can be added to
the random state page.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250204-vdso-store-rng-v3-6-13a4669dfc8c@linutronix.de
---
 drivers/char/random.c               |  6 +++---
 include/asm-generic/vdso/vsyscall.h | 12 ++++++++++++
 include/vdso/datapage.h             | 10 ++++++++++
 lib/vdso/datastore.c                | 14 ++++++++++++++
 lib/vdso/getrandom.c                |  8 ++++++--
 5 files changed, 45 insertions(+), 5 deletions(-)

diff --git a/drivers/char/random.c b/drivers/char/random.c
index 2581186fa61b7..92cbd24a36d8c 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -278,7 +278,7 @@ static void crng_reseed(struct work_struct *work)
 	WRITE_ONCE(base_crng.generation, next_gen);
 #ifdef CONFIG_VDSO_GETRANDOM
 	/* base_crng.generation's invalid value is ULONG_MAX, while
-	 * _vdso_rng_data.generation's invalid value is 0, so add one to the
+	 * vdso_k_rng_data->generation's invalid value is 0, so add one to the
 	 * former to arrive at the latter. Use smp_store_release so that this
 	 * is ordered with the write above to base_crng.generation. Pairs with
 	 * the smp_rmb() before the syscall in the vDSO code.
@@ -290,7 +290,7 @@ static void crng_reseed(struct work_struct *work)
 	 * because the vDSO side only checks whether the value changed, without
 	 * actually using or interpreting the value.
 	 */
-	smp_store_release((unsigned long *)&__arch_get_k_vdso_rng_data()->generation, next_gen + 1);
+	smp_store_release((unsigned long *)&vdso_k_rng_data->generation, next_gen + 1);
 #endif
 	if (!static_branch_likely(&crng_is_ready))
 		crng_init = CRNG_READY;
@@ -743,7 +743,7 @@ static void __cold _credit_init_bits(size_t bits)
 			queue_work(system_unbound_wq, &set_ready);
 		atomic_notifier_call_chain(&random_ready_notifier, 0, NULL);
 #ifdef CONFIG_VDSO_GETRANDOM
-		WRITE_ONCE(__arch_get_k_vdso_rng_data()->is_ready, true);
+		WRITE_ONCE(vdso_k_rng_data->is_ready, true);
 #endif
 		wake_up_interruptible(&crng_init_wait);
 		kill_fasync(&fasync, SIGIO, POLL_IN);
diff --git a/include/asm-generic/vdso/vsyscall.h b/include/asm-generic/vdso/vsyscall.h
index ac5b93b919932..a5f973e4e2723 100644
--- a/include/asm-generic/vdso/vsyscall.h
+++ b/include/asm-generic/vdso/vsyscall.h
@@ -13,6 +13,13 @@ static __always_inline const struct vdso_time_data *__arch_get_vdso_u_time_data(
 }
 #endif
 
+#ifndef __arch_get_vdso_u_rng_data
+static __always_inline const struct vdso_rng_data *__arch_get_vdso_u_rng_data(void)
+{
+	return &vdso_u_rng_data;
+}
+#endif
+
 #else  /* !CONFIG_GENERIC_VDSO_DATA_STORE */
 
 #ifndef __arch_get_k_vdso_data
@@ -25,6 +32,11 @@ static __always_inline struct vdso_data *__arch_get_k_vdso_data(void)
 
 #define __arch_get_vdso_u_time_data __arch_get_vdso_data
 
+#ifndef __arch_get_vdso_u_rng_data
+#define __arch_get_vdso_u_rng_data() __arch_get_vdso_rng_data()
+#endif
+#define vdso_k_rng_data __arch_get_k_vdso_rng_data()
+
 #endif /* CONFIG_GENERIC_VDSO_DATA_STORE */
 
 #ifndef __arch_update_vsyscall
diff --git a/include/vdso/datapage.h b/include/vdso/datapage.h
index b3d8087488ff3..7dbc8797e3b89 100644
--- a/include/vdso/datapage.h
+++ b/include/vdso/datapage.h
@@ -144,8 +144,10 @@ extern struct vdso_time_data _timens_data[CS_BASES] __attribute__((visibility("h
 extern struct vdso_rng_data _vdso_rng_data __attribute__((visibility("hidden")));
 #else
 extern struct vdso_time_data vdso_u_time_data[CS_BASES] __attribute__((visibility("hidden")));
+extern struct vdso_rng_data vdso_u_rng_data __attribute__((visibility("hidden")));
 
 extern struct vdso_time_data *vdso_k_time_data;
+extern struct vdso_rng_data *vdso_k_rng_data;
 #endif
 
 /**
@@ -161,6 +163,7 @@ union vdso_data_store {
 enum vdso_pages {
 	VDSO_TIME_PAGE_OFFSET,
 	VDSO_TIMENS_PAGE_OFFSET,
+	VDSO_RNG_PAGE_OFFSET,
 	VDSO_NR_PAGES
 };
 
@@ -184,9 +187,16 @@ enum vdso_pages {
 
 #else /* !__ASSEMBLY__ */
 
+#ifdef CONFIG_VDSO_GETRANDOM
+#define __vdso_u_rng_data	PROVIDE(vdso_u_rng_data = vdso_u_data + 2 * PAGE_SIZE);
+#else
+#define __vdso_u_rng_data
+#endif
+
 #define VDSO_VVAR_SYMS						\
 	PROVIDE(vdso_u_data = . - __VDSO_PAGES * PAGE_SIZE);	\
 	PROVIDE(vdso_u_time_data = vdso_u_data);		\
+	__vdso_u_rng_data					\
 
 
 #endif /* !__ASSEMBLY__ */
diff --git a/lib/vdso/datastore.c b/lib/vdso/datastore.c
index d3181768424cc..9260b00dc8520 100644
--- a/lib/vdso/datastore.c
+++ b/lib/vdso/datastore.c
@@ -17,6 +17,15 @@ struct vdso_time_data *vdso_k_time_data = vdso_time_data_store.data;
 static_assert(sizeof(vdso_time_data_store) == PAGE_SIZE);
 #endif /* CONFIG_HAVE_GENERIC_VDSO */
 
+#ifdef CONFIG_VDSO_GETRANDOM
+static union {
+	struct vdso_rng_data	data;
+	u8			page[PAGE_SIZE];
+} vdso_rng_data_store __page_aligned_data;
+struct vdso_rng_data *vdso_k_rng_data = &vdso_rng_data_store.data;
+static_assert(sizeof(vdso_rng_data_store) == PAGE_SIZE);
+#endif /* CONFIG_VDSO_GETRANDOM */
+
 static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
 			     struct vm_area_struct *vma, struct vm_fault *vmf)
 {
@@ -53,6 +62,11 @@ static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
 			return VM_FAULT_SIGBUS;
 		pfn = __phys_to_pfn(__pa_symbol(vdso_k_time_data));
 		break;
+	case VDSO_RNG_PAGE_OFFSET:
+		if (!IS_ENABLED(CONFIG_VDSO_GETRANDOM))
+			return VM_FAULT_SIGBUS;
+		pfn = __phys_to_pfn(__pa_symbol(vdso_k_rng_data));
+		break;
 	default:
 		return VM_FAULT_SIGBUS;
 	}
diff --git a/lib/vdso/getrandom.c b/lib/vdso/getrandom.c
index 938ca539aaa64..440f8a6203a69 100644
--- a/lib/vdso/getrandom.c
+++ b/lib/vdso/getrandom.c
@@ -12,6 +12,9 @@
 #include <uapi/linux/mman.h>
 #include <uapi/linux/random.h>
 
+/* Bring in default accessors */
+#include <vdso/vsyscall.h>
+
 #undef PAGE_SIZE
 #undef PAGE_MASK
 #define PAGE_SIZE (1UL << CONFIG_PAGE_SHIFT)
@@ -152,7 +155,7 @@ __cvdso_getrandom_data(const struct vdso_rng_data *rng_info, void *buffer, size_
 
 		/*
 		 * Prevent the syscall from being reordered wrt current_generation. Pairs with the
-		 * smp_store_release(&_vdso_rng_data.generation) in random.c.
+		 * smp_store_release(&vdso_k_rng_data->generation) in random.c.
 		 */
 		smp_rmb();
 
@@ -256,5 +259,6 @@ __cvdso_getrandom_data(const struct vdso_rng_data *rng_info, void *buffer, size_
 static __always_inline ssize_t
 __cvdso_getrandom(void *buffer, size_t len, unsigned int flags, void *opaque_state, size_t opaque_len)
 {
-	return __cvdso_getrandom_data(__arch_get_vdso_rng_data(), buffer, len, flags, opaque_state, opaque_len);
+	return __cvdso_getrandom_data(__arch_get_vdso_u_rng_data(), buffer, len, flags,
+				      opaque_state, opaque_len);
 }

From 365841e1557ace6e8b4d5ba06a6cf53f699bc684 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Tue, 4 Feb 2025 13:05:39 +0100
Subject: [PATCH 0442/1173] vdso: Add generic architecture-specific data
 storage
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some architectures need to expose architecture-specific data to the vDSO.

Enable the generic vDSO storage mechanism to both store and map this
data. Some architectures require more than a single page, like LoongArch,
so prepare for that usecase, too.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250204-vdso-store-rng-v3-7-13a4669dfc8c@linutronix.de
---
 arch/Kconfig            |  4 ++++
 include/vdso/datapage.h | 25 +++++++++++++++++++++++++
 lib/vdso/datastore.c    | 14 ++++++++++++++
 3 files changed, 43 insertions(+)

diff --git a/arch/Kconfig b/arch/Kconfig
index b8a4ff3655822..9f6eb09ef12d7 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -1584,6 +1584,10 @@ config HAVE_SPARSE_SYSCALL_NR
 	  entries at 4000, 5000 and 6000 locations. This option turns on syscall
 	  related optimizations for a given architecture.
 
+config ARCH_HAS_VDSO_ARCH_DATA
+	depends on GENERIC_VDSO_DATA_STORE
+	bool
+
 config ARCH_HAS_VDSO_TIME_DATA
 	bool
 
diff --git a/include/vdso/datapage.h b/include/vdso/datapage.h
index 7dbc8797e3b89..46658b39c2825 100644
--- a/include/vdso/datapage.h
+++ b/include/vdso/datapage.h
@@ -9,11 +9,13 @@
 #include <uapi/linux/types.h>
 #include <uapi/asm-generic/errno-base.h>
 
+#include <vdso/align.h>
 #include <vdso/bits.h>
 #include <vdso/clocksource.h>
 #include <vdso/ktime.h>
 #include <vdso/limits.h>
 #include <vdso/math64.h>
+#include <vdso/page.h>
 #include <vdso/processor.h>
 #include <vdso/time.h>
 #include <vdso/time32.h>
@@ -25,6 +27,15 @@
 struct arch_vdso_time_data {};
 #endif
 
+#if defined(CONFIG_ARCH_HAS_VDSO_ARCH_DATA)
+#include <asm/vdso/arch_data.h>
+#elif defined(CONFIG_GENERIC_VDSO_DATA_STORE)
+struct vdso_arch_data {
+	/* Needed for the generic code, never actually used at runtime */
+	char __unused;
+};
+#endif
+
 #define VDSO_BASES	(CLOCK_TAI + 1)
 #define VDSO_HRES	(BIT(CLOCK_REALTIME)		| \
 			 BIT(CLOCK_MONOTONIC)		| \
@@ -145,9 +156,11 @@ extern struct vdso_rng_data _vdso_rng_data __attribute__((visibility("hidden")))
 #else
 extern struct vdso_time_data vdso_u_time_data[CS_BASES] __attribute__((visibility("hidden")));
 extern struct vdso_rng_data vdso_u_rng_data __attribute__((visibility("hidden")));
+extern struct vdso_arch_data vdso_u_arch_data __attribute__((visibility("hidden")));
 
 extern struct vdso_time_data *vdso_k_time_data;
 extern struct vdso_rng_data *vdso_k_rng_data;
+extern struct vdso_arch_data *vdso_k_arch_data;
 #endif
 
 /**
@@ -160,10 +173,15 @@ union vdso_data_store {
 
 #ifdef CONFIG_GENERIC_VDSO_DATA_STORE
 
+#define VDSO_ARCH_DATA_SIZE ALIGN(sizeof(struct vdso_arch_data), PAGE_SIZE)
+#define VDSO_ARCH_DATA_PAGES (VDSO_ARCH_DATA_SIZE >> PAGE_SHIFT)
+
 enum vdso_pages {
 	VDSO_TIME_PAGE_OFFSET,
 	VDSO_TIMENS_PAGE_OFFSET,
 	VDSO_RNG_PAGE_OFFSET,
+	VDSO_ARCH_PAGES_START,
+	VDSO_ARCH_PAGES_END = VDSO_ARCH_PAGES_START + VDSO_ARCH_DATA_PAGES - 1,
 	VDSO_NR_PAGES
 };
 
@@ -193,10 +211,17 @@ enum vdso_pages {
 #define __vdso_u_rng_data
 #endif
 
+#ifdef CONFIG_ARCH_HAS_VDSO_ARCH_DATA
+#define __vdso_u_arch_data	PROVIDE(vdso_u_arch_data = vdso_u_data + 3 * PAGE_SIZE);
+#else
+#define __vdso_u_arch_data
+#endif
+
 #define VDSO_VVAR_SYMS						\
 	PROVIDE(vdso_u_data = . - __VDSO_PAGES * PAGE_SIZE);	\
 	PROVIDE(vdso_u_time_data = vdso_u_data);		\
 	__vdso_u_rng_data					\
+	__vdso_u_arch_data					\
 
 
 #endif /* !__ASSEMBLY__ */
diff --git a/lib/vdso/datastore.c b/lib/vdso/datastore.c
index 9260b00dc8520..0959d62d78586 100644
--- a/lib/vdso/datastore.c
+++ b/lib/vdso/datastore.c
@@ -26,6 +26,14 @@ struct vdso_rng_data *vdso_k_rng_data = &vdso_rng_data_store.data;
 static_assert(sizeof(vdso_rng_data_store) == PAGE_SIZE);
 #endif /* CONFIG_VDSO_GETRANDOM */
 
+#ifdef CONFIG_ARCH_HAS_VDSO_ARCH_DATA
+static union {
+	struct vdso_arch_data	data;
+	u8			page[VDSO_ARCH_DATA_SIZE];
+} vdso_arch_data_store __page_aligned_data;
+struct vdso_arch_data *vdso_k_arch_data = &vdso_arch_data_store.data;
+#endif /* CONFIG_ARCH_HAS_VDSO_ARCH_DATA */
+
 static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
 			     struct vm_area_struct *vma, struct vm_fault *vmf)
 {
@@ -67,6 +75,12 @@ static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
 			return VM_FAULT_SIGBUS;
 		pfn = __phys_to_pfn(__pa_symbol(vdso_k_rng_data));
 		break;
+	case VDSO_ARCH_PAGES_START ... VDSO_ARCH_PAGES_END:
+		if (!IS_ENABLED(CONFIG_ARCH_HAS_VDSO_ARCH_DATA))
+			return VM_FAULT_SIGBUS;
+		pfn = __phys_to_pfn(__pa_symbol(vdso_k_arch_data)) +
+			vmf->pgoff - VDSO_ARCH_PAGES_START;
+		break;
 	default:
 		return VM_FAULT_SIGBUS;
 	}

From 0b3bc3354eb9ad36719a044726092750a2ba01ff Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Tue, 4 Feb 2025 13:05:40 +0100
Subject: [PATCH 0443/1173] arm64: vdso: Switch to generic storage
 implementation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The generic storage implementation provides the same features as the
custom one. However it can be shared between architectures, making
maintenance easier.

This switch also moves the random state data out of the time data page.
The currently used hardcoded __VDSO_RND_DATA_OFFSET does not take into
account changes to the time data page layout.

Co-developed-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250204-vdso-store-rng-v3-8-13a4669dfc8c@linutronix.de
---
 arch/arm64/Kconfig                            |  1 +
 arch/arm64/include/asm/vdso.h                 |  2 +-
 .../include/asm/vdso/compat_gettimeofday.h    | 36 +++-----
 arch/arm64/include/asm/vdso/getrandom.h       | 12 ---
 arch/arm64/include/asm/vdso/gettimeofday.h    | 16 +---
 arch/arm64/include/asm/vdso/vsyscall.h        | 25 +-----
 arch/arm64/kernel/vdso.c                      | 90 ++-----------------
 arch/arm64/kernel/vdso/vdso.lds.S             |  7 +-
 arch/arm64/kernel/vdso32/vdso.lds.S           |  7 +-
 9 files changed, 26 insertions(+), 170 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index fcdd0ed3eca89..3770b73f270bb 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -162,6 +162,7 @@ config ARM64
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_TIME_VSYSCALL
 	select GENERIC_GETTIMEOFDAY
+	select GENERIC_VDSO_DATA_STORE
 	select GENERIC_VDSO_TIME_NS
 	select HARDIRQS_SW_RESEND
 	select HAS_IOPORT
diff --git a/arch/arm64/include/asm/vdso.h b/arch/arm64/include/asm/vdso.h
index 3e3c3fdb18427..61679070f595c 100644
--- a/arch/arm64/include/asm/vdso.h
+++ b/arch/arm64/include/asm/vdso.h
@@ -5,7 +5,7 @@
 #ifndef __ASM_VDSO_H
 #define __ASM_VDSO_H
 
-#define __VVAR_PAGES    2
+#define __VDSO_PAGES    4
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/arm64/include/asm/vdso/compat_gettimeofday.h b/arch/arm64/include/asm/vdso/compat_gettimeofday.h
index 778c1202bbbf9..957ee12fcc54b 100644
--- a/arch/arm64/include/asm/vdso/compat_gettimeofday.h
+++ b/arch/arm64/include/asm/vdso/compat_gettimeofday.h
@@ -104,7 +104,7 @@ int clock_getres32_fallback(clockid_t _clkid, struct old_timespec32 *_ts)
 }
 
 static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
-						 const struct vdso_data *vd)
+						 const struct vdso_time_data *vd)
 {
 	u64 res;
 
@@ -131,43 +131,31 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
 	return res;
 }
 
-static __always_inline const struct vdso_data *__arch_get_vdso_data(void)
+static __always_inline const struct vdso_time_data *__arch_get_vdso_u_time_data(void)
 {
-	const struct vdso_data *ret;
+	const struct vdso_time_data *ret;
 
 	/*
-	 * This simply puts &_vdso_data into ret. The reason why we don't use
-	 * `ret = _vdso_data` is that the compiler tends to optimise this in a
-	 * very suboptimal way: instead of keeping &_vdso_data in a register,
-	 * it goes through a relocation almost every time _vdso_data must be
+	 * This simply puts &_vdso_time_data into ret. The reason why we don't use
+	 * `ret = _vdso_time_data` is that the compiler tends to optimise this in a
+	 * very suboptimal way: instead of keeping &_vdso_time_data in a register,
+	 * it goes through a relocation almost every time _vdso_time_data must be
 	 * accessed (even in subfunctions). This is both time and space
 	 * consuming: each relocation uses a word in the code section, and it
 	 * has to be loaded at runtime.
 	 *
 	 * This trick hides the assignment from the compiler. Since it cannot
 	 * track where the pointer comes from, it will only use one relocation
-	 * where __arch_get_vdso_data() is called, and then keep the result in
-	 * a register.
+	 * where __aarch64_get_vdso_u_time_data() is called, and then keep the
+	 * result in a register.
 	 */
-	asm volatile("mov %0, %1" : "=r"(ret) : "r"(_vdso_data));
+	asm volatile("mov %0, %1" : "=r"(ret) : "r"(vdso_u_time_data));
 
 	return ret;
 }
+#define __arch_get_vdso_u_time_data __arch_get_vdso_u_time_data
 
-#ifdef CONFIG_TIME_NS
-static __always_inline
-const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd)
-{
-	const struct vdso_data *ret;
-
-	/* See __arch_get_vdso_data(). */
-	asm volatile("mov %0, %1" : "=r"(ret) : "r"(_timens_data));
-
-	return ret;
-}
-#endif
-
-static inline bool vdso_clocksource_ok(const struct vdso_data *vd)
+static inline bool vdso_clocksource_ok(const struct vdso_time_data *vd)
 {
 	return vd->clock_mode == VDSO_CLOCKMODE_ARCHTIMER;
 }
diff --git a/arch/arm64/include/asm/vdso/getrandom.h b/arch/arm64/include/asm/vdso/getrandom.h
index 342f807e20444..a2197da1951b0 100644
--- a/arch/arm64/include/asm/vdso/getrandom.h
+++ b/arch/arm64/include/asm/vdso/getrandom.h
@@ -33,18 +33,6 @@ static __always_inline ssize_t getrandom_syscall(void *_buffer, size_t _len, uns
 	return ret;
 }
 
-static __always_inline const struct vdso_rng_data *__arch_get_vdso_rng_data(void)
-{
-	/*
-	 * The RNG data is in the real VVAR data page, but if a task belongs to a time namespace
-	 * then VVAR_DATA_PAGE_OFFSET points to the namespace-specific VVAR page and VVAR_TIMENS_
-	 * PAGE_OFFSET points to the real VVAR page.
-	 */
-	if (IS_ENABLED(CONFIG_TIME_NS) && _vdso_data->clock_mode == VDSO_CLOCKMODE_TIMENS)
-		return (void *)&_vdso_rng_data + VVAR_TIMENS_PAGE_OFFSET * (1UL << CONFIG_PAGE_SHIFT);
-	return &_vdso_rng_data;
-}
-
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_VDSO_GETRANDOM_H */
diff --git a/arch/arm64/include/asm/vdso/gettimeofday.h b/arch/arm64/include/asm/vdso/gettimeofday.h
index 764d13e2916c5..92a2b59a9f3df 100644
--- a/arch/arm64/include/asm/vdso/gettimeofday.h
+++ b/arch/arm64/include/asm/vdso/gettimeofday.h
@@ -67,7 +67,7 @@ int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
 }
 
 static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
-						 const struct vdso_data *vd)
+						 const struct vdso_time_data *vd)
 {
 	u64 res;
 
@@ -99,20 +99,6 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
 	return res;
 }
 
-static __always_inline
-const struct vdso_data *__arch_get_vdso_data(void)
-{
-	return _vdso_data;
-}
-
-#ifdef CONFIG_TIME_NS
-static __always_inline
-const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd)
-{
-	return _timens_data;
-}
-#endif
-
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/arm64/include/asm/vdso/vsyscall.h b/arch/arm64/include/asm/vdso/vsyscall.h
index eea51946d45a2..3f65cbd00635a 100644
--- a/arch/arm64/include/asm/vdso/vsyscall.h
+++ b/arch/arm64/include/asm/vdso/vsyscall.h
@@ -2,41 +2,18 @@
 #ifndef __ASM_VDSO_VSYSCALL_H
 #define __ASM_VDSO_VSYSCALL_H
 
-#define __VDSO_RND_DATA_OFFSET  480
-
 #ifndef __ASSEMBLY__
 
 #include <vdso/datapage.h>
 
-enum vvar_pages {
-	VVAR_DATA_PAGE_OFFSET,
-	VVAR_TIMENS_PAGE_OFFSET,
-	VVAR_NR_PAGES,
-};
-
 #define VDSO_PRECISION_MASK	~(0xFF00ULL<<48)
 
-extern struct vdso_data *vdso_data;
 
 /*
  * Update the vDSO data page to keep in sync with kernel timekeeping.
  */
 static __always_inline
-struct vdso_data *__arm64_get_k_vdso_data(void)
-{
-	return vdso_data;
-}
-#define __arch_get_k_vdso_data __arm64_get_k_vdso_data
-
-static __always_inline
-struct vdso_rng_data *__arm64_get_k_vdso_rnd_data(void)
-{
-	return (void *)vdso_data + __VDSO_RND_DATA_OFFSET;
-}
-#define __arch_get_k_vdso_rng_data __arm64_get_k_vdso_rnd_data
-
-static __always_inline
-void __arm64_update_vsyscall(struct vdso_data *vdata)
+void __arm64_update_vsyscall(struct vdso_time_data *vdata)
 {
 	vdata[CS_HRES_COARSE].mask	= VDSO_PRECISION_MASK;
 	vdata[CS_RAW].mask		= VDSO_PRECISION_MASK;
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index e8ed8e5b713b5..887ac0b05961e 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -18,7 +18,7 @@
 #include <linux/sched.h>
 #include <linux/signal.h>
 #include <linux/slab.h>
-#include <linux/time_namespace.h>
+#include <linux/vdso_datastore.h>
 #include <linux/vmalloc.h>
 #include <vdso/datapage.h>
 #include <vdso/helpers.h>
@@ -57,12 +57,6 @@ static struct vdso_abi_info vdso_info[] __ro_after_init = {
 #endif /* CONFIG_COMPAT_VDSO */
 };
 
-/*
- * The vDSO data page.
- */
-static union vdso_data_store vdso_data_store __page_aligned_data;
-struct vdso_data *vdso_data = vdso_data_store.data;
-
 static int vdso_mremap(const struct vm_special_mapping *sm,
 		struct vm_area_struct *new_vma)
 {
@@ -104,78 +98,6 @@ static int __init __vdso_init(enum vdso_abi abi)
 	return 0;
 }
 
-#ifdef CONFIG_TIME_NS
-struct vdso_data *arch_get_vdso_data(void *vvar_page)
-{
-	return (struct vdso_data *)(vvar_page);
-}
-
-static const struct vm_special_mapping vvar_map;
-
-/*
- * The vvar mapping contains data for a specific time namespace, so when a task
- * changes namespace we must unmap its vvar data for the old namespace.
- * Subsequent faults will map in data for the new namespace.
- *
- * For more details see timens_setup_vdso_data().
- */
-int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
-{
-	struct mm_struct *mm = task->mm;
-	struct vm_area_struct *vma;
-	VMA_ITERATOR(vmi, mm, 0);
-
-	mmap_read_lock(mm);
-
-	for_each_vma(vmi, vma) {
-		if (vma_is_special_mapping(vma, &vvar_map))
-			zap_vma_pages(vma);
-	}
-
-	mmap_read_unlock(mm);
-	return 0;
-}
-#endif
-
-static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
-			     struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-	struct page *timens_page = find_timens_vvar_page(vma);
-	unsigned long pfn;
-
-	switch (vmf->pgoff) {
-	case VVAR_DATA_PAGE_OFFSET:
-		if (timens_page)
-			pfn = page_to_pfn(timens_page);
-		else
-			pfn = sym_to_pfn(vdso_data);
-		break;
-#ifdef CONFIG_TIME_NS
-	case VVAR_TIMENS_PAGE_OFFSET:
-		/*
-		 * If a task belongs to a time namespace then a namespace
-		 * specific VVAR is mapped with the VVAR_DATA_PAGE_OFFSET and
-		 * the real VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET
-		 * offset.
-		 * See also the comment near timens_setup_vdso_data().
-		 */
-		if (!timens_page)
-			return VM_FAULT_SIGBUS;
-		pfn = sym_to_pfn(vdso_data);
-		break;
-#endif /* CONFIG_TIME_NS */
-	default:
-		return VM_FAULT_SIGBUS;
-	}
-
-	return vmf_insert_pfn(vma, vmf->address, pfn);
-}
-
-static const struct vm_special_mapping vvar_map = {
-	.name   = "[vvar]",
-	.fault = vvar_fault,
-};
-
 static int __setup_additional_pages(enum vdso_abi abi,
 				    struct mm_struct *mm,
 				    struct linux_binprm *bprm,
@@ -185,11 +107,11 @@ static int __setup_additional_pages(enum vdso_abi abi,
 	unsigned long gp_flags = 0;
 	void *ret;
 
-	BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES);
+	BUILD_BUG_ON(VDSO_NR_PAGES != __VDSO_PAGES);
 
 	vdso_text_len = vdso_info[abi].vdso_pages << PAGE_SHIFT;
 	/* Be sure to map the data page */
-	vdso_mapping_len = vdso_text_len + VVAR_NR_PAGES * PAGE_SIZE;
+	vdso_mapping_len = vdso_text_len + VDSO_NR_PAGES * PAGE_SIZE;
 
 	vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0);
 	if (IS_ERR_VALUE(vdso_base)) {
@@ -197,16 +119,14 @@ static int __setup_additional_pages(enum vdso_abi abi,
 		goto up_fail;
 	}
 
-	ret = _install_special_mapping(mm, vdso_base, VVAR_NR_PAGES * PAGE_SIZE,
-				       VM_READ|VM_MAYREAD|VM_PFNMAP,
-				       &vvar_map);
+	ret = vdso_install_vvar_mapping(mm, vdso_base);
 	if (IS_ERR(ret))
 		goto up_fail;
 
 	if (system_supports_bti_kernel())
 		gp_flags = VM_ARM64_BTI;
 
-	vdso_base += VVAR_NR_PAGES * PAGE_SIZE;
+	vdso_base += VDSO_NR_PAGES * PAGE_SIZE;
 	mm->context.vdso = (void *)vdso_base;
 	ret = _install_special_mapping(mm, vdso_base, vdso_text_len,
 				       VM_READ|VM_EXEC|gp_flags|
diff --git a/arch/arm64/kernel/vdso/vdso.lds.S b/arch/arm64/kernel/vdso/vdso.lds.S
index 4ec32e86a8da2..2e20d0593f182 100644
--- a/arch/arm64/kernel/vdso/vdso.lds.S
+++ b/arch/arm64/kernel/vdso/vdso.lds.S
@@ -20,11 +20,8 @@ OUTPUT_ARCH(aarch64)
 
 SECTIONS
 {
-	PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE);
-	PROVIDE(_vdso_rng_data = _vdso_data + __VDSO_RND_DATA_OFFSET);
-#ifdef CONFIG_TIME_NS
-	PROVIDE(_timens_data = _vdso_data + PAGE_SIZE);
-#endif
+	VDSO_VVAR_SYMS
+
 	. = SIZEOF_HEADERS;
 
 	.hash		: { *(.hash) }			:text
diff --git a/arch/arm64/kernel/vdso32/vdso.lds.S b/arch/arm64/kernel/vdso32/vdso.lds.S
index 732702a187e9e..e02b27487ce80 100644
--- a/arch/arm64/kernel/vdso32/vdso.lds.S
+++ b/arch/arm64/kernel/vdso32/vdso.lds.S
@@ -12,16 +12,15 @@
 #include <asm/page.h>
 #include <asm/vdso.h>
 #include <asm-generic/vmlinux.lds.h>
+#include <vdso/datapage.h>
 
 OUTPUT_FORMAT("elf32-littlearm", "elf32-bigarm", "elf32-littlearm")
 OUTPUT_ARCH(arm)
 
 SECTIONS
 {
-	PROVIDE_HIDDEN(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE);
-#ifdef CONFIG_TIME_NS
-	PROVIDE_HIDDEN(_timens_data = _vdso_data + PAGE_SIZE);
-#endif
+	VDSO_VVAR_SYMS
+
 	. = SIZEOF_HEADERS;
 
 	.hash		: { *(.hash) }			:text

From 46fe55b204bfb007e0f0a5409dcda063ad98b089 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Tue, 4 Feb 2025 13:05:41 +0100
Subject: [PATCH 0444/1173] riscv: vdso: Switch to generic storage
 implementation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The generic storage implementation provides the same features as the
custom one. However it can be shared between architectures, making
maintenance easier.

Co-developed-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250204-vdso-store-rng-v3-9-13a4669dfc8c@linutronix.de
---
 arch/riscv/Kconfig                            |  3 +-
 arch/riscv/include/asm/vdso.h                 |  2 +-
 .../asm/vdso/{time_data.h => arch_data.h}     |  8 +-
 arch/riscv/include/asm/vdso/gettimeofday.h    | 14 +--
 arch/riscv/include/asm/vdso/vsyscall.h        |  9 --
 arch/riscv/kernel/sys_hwprobe.c               |  3 +-
 arch/riscv/kernel/vdso.c                      | 90 +------------------
 arch/riscv/kernel/vdso/hwprobe.c              |  6 +-
 arch/riscv/kernel/vdso/vdso.lds.S             |  7 +-
 9 files changed, 18 insertions(+), 124 deletions(-)
 rename arch/riscv/include/asm/vdso/{time_data.h => arch_data.h} (71%)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 7612c52e9b1e3..aa8ea53186c04 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -53,7 +53,7 @@ config RISCV
 	select ARCH_HAS_SYSCALL_WRAPPER
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAS_UBSAN
-	select ARCH_HAS_VDSO_TIME_DATA
+	select ARCH_HAS_VDSO_ARCH_DATA if GENERIC_VDSO_DATA_STORE
 	select ARCH_KEEP_MEMBLOCK if ACPI
 	select ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE	if 64BIT && MMU
 	select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX
@@ -116,6 +116,7 @@ config RISCV
 	select GENERIC_SCHED_CLOCK
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_TIME_VSYSCALL if MMU && 64BIT
+	select GENERIC_VDSO_DATA_STORE if MMU
 	select GENERIC_VDSO_TIME_NS if HAVE_GENERIC_VDSO
 	select HARDIRQS_SW_RESEND
 	select HAS_IOPORT if MMU
diff --git a/arch/riscv/include/asm/vdso.h b/arch/riscv/include/asm/vdso.h
index f891478829a52..c130d8100232c 100644
--- a/arch/riscv/include/asm/vdso.h
+++ b/arch/riscv/include/asm/vdso.h
@@ -14,7 +14,7 @@
  */
 #ifdef CONFIG_MMU
 
-#define __VVAR_PAGES    2
+#define __VDSO_PAGES    4
 
 #ifndef __ASSEMBLY__
 #include <generated/vdso-offsets.h>
diff --git a/arch/riscv/include/asm/vdso/time_data.h b/arch/riscv/include/asm/vdso/arch_data.h
similarity index 71%
rename from arch/riscv/include/asm/vdso/time_data.h
rename to arch/riscv/include/asm/vdso/arch_data.h
index dfa65228999be..da57a3786f7a5 100644
--- a/arch/riscv/include/asm/vdso/time_data.h
+++ b/arch/riscv/include/asm/vdso/arch_data.h
@@ -1,12 +1,12 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __RISCV_ASM_VDSO_TIME_DATA_H
-#define __RISCV_ASM_VDSO_TIME_DATA_H
+#ifndef __RISCV_ASM_VDSO_ARCH_DATA_H
+#define __RISCV_ASM_VDSO_ARCH_DATA_H
 
 #include <linux/types.h>
 #include <vdso/datapage.h>
 #include <asm/hwprobe.h>
 
-struct arch_vdso_time_data {
+struct vdso_arch_data {
 	/* Stash static answers to the hwprobe queries when all CPUs are selected. */
 	__u64 all_cpu_hwprobe_values[RISCV_HWPROBE_MAX_KEY + 1];
 
@@ -14,4 +14,4 @@ struct arch_vdso_time_data {
 	__u8 homogeneous_cpus;
 };
 
-#endif /* __RISCV_ASM_VDSO_TIME_DATA_H */
+#endif /* __RISCV_ASM_VDSO_ARCH_DATA_H */
diff --git a/arch/riscv/include/asm/vdso/gettimeofday.h b/arch/riscv/include/asm/vdso/gettimeofday.h
index ba3283cf7acca..29164f84f93ce 100644
--- a/arch/riscv/include/asm/vdso/gettimeofday.h
+++ b/arch/riscv/include/asm/vdso/gettimeofday.h
@@ -69,7 +69,7 @@ int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
 #endif /* CONFIG_GENERIC_TIME_VSYSCALL */
 
 static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
-						 const struct vdso_data *vd)
+						 const struct vdso_time_data *vd)
 {
 	/*
 	 * The purpose of csr_read(CSR_TIME) is to trap the system into
@@ -79,18 +79,6 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
 	return csr_read(CSR_TIME);
 }
 
-static __always_inline const struct vdso_data *__arch_get_vdso_data(void)
-{
-	return _vdso_data;
-}
-
-#ifdef CONFIG_TIME_NS
-static __always_inline
-const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd)
-{
-	return _timens_data;
-}
-#endif
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/riscv/include/asm/vdso/vsyscall.h b/arch/riscv/include/asm/vdso/vsyscall.h
index e8a9c4b53c0c9..1140b54b4bc82 100644
--- a/arch/riscv/include/asm/vdso/vsyscall.h
+++ b/arch/riscv/include/asm/vdso/vsyscall.h
@@ -6,15 +6,6 @@
 
 #include <vdso/datapage.h>
 
-extern struct vdso_data *vdso_data;
-
-static __always_inline struct vdso_data *__riscv_get_k_vdso_data(void)
-{
-	return vdso_data;
-}
-
-#define __arch_get_k_vdso_data __riscv_get_k_vdso_data
-
 /* The asm-generic header needs to be included after the definitions above */
 #include <asm-generic/vdso/vsyscall.h>
 
diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c
index bcd3b816306c2..04a4e54955128 100644
--- a/arch/riscv/kernel/sys_hwprobe.c
+++ b/arch/riscv/kernel/sys_hwprobe.c
@@ -450,8 +450,7 @@ static int do_riscv_hwprobe(struct riscv_hwprobe __user *pairs,
 
 static int __init init_hwprobe_vdso_data(void)
 {
-	struct vdso_data *vd = __arch_get_k_vdso_data();
-	struct arch_vdso_time_data *avd = &vd->arch_data;
+	struct vdso_arch_data *avd = vdso_k_arch_data;
 	u64 id_bitsmash = 0;
 	struct riscv_hwprobe pair;
 	int key;
diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c
index 3ca3ae4277e18..cc2895d1fbc2f 100644
--- a/arch/riscv/kernel/vdso.c
+++ b/arch/riscv/kernel/vdso.c
@@ -13,20 +13,11 @@
 #include <linux/err.h>
 #include <asm/page.h>
 #include <asm/vdso.h>
-#include <linux/time_namespace.h>
+#include <linux/vdso_datastore.h>
 #include <vdso/datapage.h>
 #include <vdso/vsyscall.h>
 
-enum vvar_pages {
-	VVAR_DATA_PAGE_OFFSET,
-	VVAR_TIMENS_PAGE_OFFSET,
-	VVAR_NR_PAGES,
-};
-
-#define VVAR_SIZE  (VVAR_NR_PAGES << PAGE_SHIFT)
-
-static union vdso_data_store vdso_data_store __page_aligned_data;
-struct vdso_data *vdso_data = vdso_data_store.data;
+#define VVAR_SIZE  (VDSO_NR_PAGES << PAGE_SHIFT)
 
 struct __vdso_info {
 	const char *name;
@@ -79,78 +70,6 @@ static void __init __vdso_init(struct __vdso_info *vdso_info)
 	vdso_info->cm->pages = vdso_pagelist;
 }
 
-#ifdef CONFIG_TIME_NS
-struct vdso_data *arch_get_vdso_data(void *vvar_page)
-{
-	return (struct vdso_data *)(vvar_page);
-}
-
-static const struct vm_special_mapping rv_vvar_map;
-
-/*
- * The vvar mapping contains data for a specific time namespace, so when a task
- * changes namespace we must unmap its vvar data for the old namespace.
- * Subsequent faults will map in data for the new namespace.
- *
- * For more details see timens_setup_vdso_data().
- */
-int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
-{
-	struct mm_struct *mm = task->mm;
-	struct vm_area_struct *vma;
-	VMA_ITERATOR(vmi, mm, 0);
-
-	mmap_read_lock(mm);
-
-	for_each_vma(vmi, vma) {
-		if (vma_is_special_mapping(vma, &rv_vvar_map))
-			zap_vma_pages(vma);
-	}
-
-	mmap_read_unlock(mm);
-	return 0;
-}
-#endif
-
-static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
-			     struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-	struct page *timens_page = find_timens_vvar_page(vma);
-	unsigned long pfn;
-
-	switch (vmf->pgoff) {
-	case VVAR_DATA_PAGE_OFFSET:
-		if (timens_page)
-			pfn = page_to_pfn(timens_page);
-		else
-			pfn = sym_to_pfn(vdso_data);
-		break;
-#ifdef CONFIG_TIME_NS
-	case VVAR_TIMENS_PAGE_OFFSET:
-		/*
-		 * If a task belongs to a time namespace then a namespace
-		 * specific VVAR is mapped with the VVAR_DATA_PAGE_OFFSET and
-		 * the real VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET
-		 * offset.
-		 * See also the comment near timens_setup_vdso_data().
-		 */
-		if (!timens_page)
-			return VM_FAULT_SIGBUS;
-		pfn = sym_to_pfn(vdso_data);
-		break;
-#endif /* CONFIG_TIME_NS */
-	default:
-		return VM_FAULT_SIGBUS;
-	}
-
-	return vmf_insert_pfn(vma, vmf->address, pfn);
-}
-
-static const struct vm_special_mapping rv_vvar_map = {
-	.name   = "[vvar]",
-	.fault = vvar_fault,
-};
-
 static struct vm_special_mapping rv_vdso_map __ro_after_init = {
 	.name   = "[vdso]",
 	.mremap = vdso_mremap,
@@ -196,7 +115,7 @@ static int __setup_additional_pages(struct mm_struct *mm,
 	unsigned long vdso_base, vdso_text_len, vdso_mapping_len;
 	void *ret;
 
-	BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES);
+	BUILD_BUG_ON(VDSO_NR_PAGES != __VDSO_PAGES);
 
 	vdso_text_len = vdso_info->vdso_pages << PAGE_SHIFT;
 	/* Be sure to map the data page */
@@ -208,8 +127,7 @@ static int __setup_additional_pages(struct mm_struct *mm,
 		goto up_fail;
 	}
 
-	ret = _install_special_mapping(mm, vdso_base, VVAR_SIZE,
-		(VM_READ | VM_MAYREAD | VM_PFNMAP), &rv_vvar_map);
+	ret = vdso_install_vvar_mapping(mm, vdso_base);
 	if (IS_ERR(ret))
 		goto up_fail;
 
diff --git a/arch/riscv/kernel/vdso/hwprobe.c b/arch/riscv/kernel/vdso/hwprobe.c
index a158c029344f6..2ddeba6c68dda 100644
--- a/arch/riscv/kernel/vdso/hwprobe.c
+++ b/arch/riscv/kernel/vdso/hwprobe.c
@@ -16,8 +16,7 @@ static int riscv_vdso_get_values(struct riscv_hwprobe *pairs, size_t pair_count,
 				 size_t cpusetsize, unsigned long *cpus,
 				 unsigned int flags)
 {
-	const struct vdso_data *vd = __arch_get_vdso_data();
-	const struct arch_vdso_time_data *avd = &vd->arch_data;
+	const struct vdso_arch_data *avd = &vdso_u_arch_data;
 	bool all_cpus = !cpusetsize && !cpus;
 	struct riscv_hwprobe *p = pairs;
 	struct riscv_hwprobe *end = pairs + pair_count;
@@ -51,8 +50,7 @@ static int riscv_vdso_get_cpus(struct riscv_hwprobe *pairs, size_t pair_count,
 			       size_t cpusetsize, unsigned long *cpus,
 			       unsigned int flags)
 {
-	const struct vdso_data *vd = __arch_get_vdso_data();
-	const struct arch_vdso_time_data *avd = &vd->arch_data;
+	const struct vdso_arch_data *avd = &vdso_u_arch_data;
 	struct riscv_hwprobe *p = pairs;
 	struct riscv_hwprobe *end = pairs + pair_count;
 	unsigned char *c = (unsigned char *)cpus;
diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S
index cbe2a179331d2..8e86965a8aae4 100644
--- a/arch/riscv/kernel/vdso/vdso.lds.S
+++ b/arch/riscv/kernel/vdso/vdso.lds.S
@@ -4,15 +4,14 @@
  */
 #include <asm/page.h>
 #include <asm/vdso.h>
+#include <vdso/datapage.h>
 
 OUTPUT_ARCH(riscv)
 
 SECTIONS
 {
-	PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE);
-#ifdef CONFIG_TIME_NS
-	PROVIDE(_timens_data = _vdso_data + PAGE_SIZE);
-#endif
+	VDSO_VVAR_SYMS
+
 	. = SIZEOF_HEADERS;
 
 	.hash		: { *(.hash) }			:text

From d2862bb9d9ca58f41319a55db0ca275774ae0c6a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Tue, 4 Feb 2025 13:05:42 +0100
Subject: [PATCH 0445/1173] LoongArch: vDSO: Switch to generic storage
 implementation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The generic storage implementation provides the same features as the
custom one. However it can be shared between architectures, making
maintenance easier.

Co-developed-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250204-vdso-store-rng-v3-10-13a4669dfc8c@linutronix.de
---
 arch/loongarch/Kconfig                        |  2 +
 arch/loongarch/include/asm/vdso.h             |  1 -
 arch/loongarch/include/asm/vdso/arch_data.h   | 25 +++++
 arch/loongarch/include/asm/vdso/getrandom.h   |  5 -
 .../loongarch/include/asm/vdso/gettimeofday.h | 14 +--
 arch/loongarch/include/asm/vdso/vdso.h        | 38 +-------
 arch/loongarch/include/asm/vdso/vsyscall.h    | 17 ----
 arch/loongarch/kernel/asm-offsets.c           |  2 +-
 arch/loongarch/kernel/vdso.c                  | 92 +------------------
 arch/loongarch/vdso/vdso.lds.S                |  8 +-
 arch/loongarch/vdso/vgetcpu.c                 | 12 +--
 11 files changed, 39 insertions(+), 177 deletions(-)
 create mode 100644 arch/loongarch/include/asm/vdso/arch_data.h

diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 2b8bd27a852fe..d7ddf2a43e63b 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -30,6 +30,7 @@ config LOONGARCH
 	select ARCH_HAS_SET_MEMORY
 	select ARCH_HAS_SET_DIRECT_MAP
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
+	select ARCH_HAS_VDSO_ARCH_DATA
 	select ARCH_INLINE_READ_LOCK if !PREEMPTION
 	select ARCH_INLINE_READ_LOCK_BH if !PREEMPTION
 	select ARCH_INLINE_READ_LOCK_IRQ if !PREEMPTION
@@ -106,6 +107,7 @@ config LOONGARCH
 	select GENERIC_SCHED_CLOCK
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_TIME_VSYSCALL
+	select GENERIC_VDSO_DATA_STORE
 	select GENERIC_VDSO_TIME_NS
 	select GPIOLIB
 	select HAS_IOPORT
diff --git a/arch/loongarch/include/asm/vdso.h b/arch/loongarch/include/asm/vdso.h
index d3ba35eb23e77..f72ec79e2dde5 100644
--- a/arch/loongarch/include/asm/vdso.h
+++ b/arch/loongarch/include/asm/vdso.h
@@ -31,7 +31,6 @@ struct loongarch_vdso_info {
 	unsigned long size;
 	unsigned long offset_sigreturn;
 	struct vm_special_mapping code_mapping;
-	struct vm_special_mapping data_mapping;
 };
 
 extern struct loongarch_vdso_info vdso_info;
diff --git a/arch/loongarch/include/asm/vdso/arch_data.h b/arch/loongarch/include/asm/vdso/arch_data.h
new file mode 100644
index 0000000000000..322d0a5f1c844
--- /dev/null
+++ b/arch/loongarch/include/asm/vdso/arch_data.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Author: Huacai Chen <chenhuacai@loongson.cn>
+ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
+ */
+
+#ifndef _VDSO_ARCH_DATA_H
+#define _VDSO_ARCH_DATA_H
+
+#ifndef __ASSEMBLY__
+
+#include <asm/asm.h>
+#include <asm/vdso.h>
+
+struct vdso_pcpu_data {
+	u32 node;
+} ____cacheline_aligned_in_smp;
+
+struct vdso_arch_data {
+	struct vdso_pcpu_data pdata[NR_CPUS];
+};
+
+#endif /* __ASSEMBLY__ */
+
+#endif
diff --git a/arch/loongarch/include/asm/vdso/getrandom.h b/arch/loongarch/include/asm/vdso/getrandom.h
index e80f3c4ac7481..48c43f55b039b 100644
--- a/arch/loongarch/include/asm/vdso/getrandom.h
+++ b/arch/loongarch/include/asm/vdso/getrandom.h
@@ -28,11 +28,6 @@ static __always_inline ssize_t getrandom_syscall(void *_buffer, size_t _len, uns
 	return ret;
 }
 
-static __always_inline const struct vdso_rng_data *__arch_get_vdso_rng_data(void)
-{
-	return &_loongarch_data.rng_data;
-}
-
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_VDSO_GETRANDOM_H */
diff --git a/arch/loongarch/include/asm/vdso/gettimeofday.h b/arch/loongarch/include/asm/vdso/gettimeofday.h
index 7eb3f041af764..88cfcf1331163 100644
--- a/arch/loongarch/include/asm/vdso/gettimeofday.h
+++ b/arch/loongarch/include/asm/vdso/gettimeofday.h
@@ -72,7 +72,7 @@ static __always_inline int clock_getres_fallback(
 }
 
 static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
-						 const struct vdso_data *vd)
+						 const struct vdso_time_data *vd)
 {
 	uint64_t count;
 
@@ -89,18 +89,6 @@ static inline bool loongarch_vdso_hres_capable(void)
 }
 #define __arch_vdso_hres_capable loongarch_vdso_hres_capable
 
-static __always_inline const struct vdso_data *__arch_get_vdso_data(void)
-{
-	return _vdso_data;
-}
-
-#ifdef CONFIG_TIME_NS
-static __always_inline
-const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd)
-{
-	return _timens_data;
-}
-#endif
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/loongarch/include/asm/vdso/vdso.h b/arch/loongarch/include/asm/vdso/vdso.h
index 1c183a9b2115a..50c65fb29dafb 100644
--- a/arch/loongarch/include/asm/vdso/vdso.h
+++ b/arch/loongarch/include/asm/vdso/vdso.h
@@ -12,43 +12,9 @@
 #include <asm/asm.h>
 #include <asm/page.h>
 #include <asm/vdso.h>
+#include <vdso/datapage.h>
 
-struct vdso_pcpu_data {
-	u32 node;
-} ____cacheline_aligned_in_smp;
-
-struct loongarch_vdso_data {
-	struct vdso_pcpu_data pdata[NR_CPUS];
-	struct vdso_rng_data rng_data;
-};
-
-/*
- * The layout of vvar:
- *
- *                      high
- * +---------------------+--------------------------+
- * | loongarch vdso data | LOONGARCH_VDSO_DATA_SIZE |
- * +---------------------+--------------------------+
- * |  time-ns vdso data  |        PAGE_SIZE         |
- * +---------------------+--------------------------+
- * |  generic vdso data  |        PAGE_SIZE         |
- * +---------------------+--------------------------+
- *                      low
- */
-#define LOONGARCH_VDSO_DATA_SIZE PAGE_ALIGN(sizeof(struct loongarch_vdso_data))
-#define LOONGARCH_VDSO_DATA_PAGES (LOONGARCH_VDSO_DATA_SIZE >> PAGE_SHIFT)
-
-enum vvar_pages {
-	VVAR_GENERIC_PAGE_OFFSET,
-	VVAR_TIMENS_PAGE_OFFSET,
-	VVAR_LOONGARCH_PAGES_START,
-	VVAR_LOONGARCH_PAGES_END = VVAR_LOONGARCH_PAGES_START + LOONGARCH_VDSO_DATA_PAGES - 1,
-	VVAR_NR_PAGES,
-};
-
-#define VVAR_SIZE (VVAR_NR_PAGES << PAGE_SHIFT)
-
-extern struct loongarch_vdso_data _loongarch_data __attribute__((visibility("hidden")));
+#define VVAR_SIZE (VDSO_NR_PAGES << PAGE_SHIFT)
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/loongarch/include/asm/vdso/vsyscall.h b/arch/loongarch/include/asm/vdso/vsyscall.h
index 8987e951d0a93..1140b54b4bc82 100644
--- a/arch/loongarch/include/asm/vdso/vsyscall.h
+++ b/arch/loongarch/include/asm/vdso/vsyscall.h
@@ -6,23 +6,6 @@
 
 #include <vdso/datapage.h>
 
-extern struct vdso_data *vdso_data;
-extern struct vdso_rng_data *vdso_rng_data;
-
-static __always_inline
-struct vdso_data *__loongarch_get_k_vdso_data(void)
-{
-	return vdso_data;
-}
-#define __arch_get_k_vdso_data __loongarch_get_k_vdso_data
-
-static __always_inline
-struct vdso_rng_data *__loongarch_get_k_vdso_rng_data(void)
-{
-	return vdso_rng_data;
-}
-#define __arch_get_k_vdso_rng_data __loongarch_get_k_vdso_rng_data
-
 /* The asm-generic header needs to be included after the definitions above */
 #include <asm-generic/vdso/vsyscall.h>
 
diff --git a/arch/loongarch/kernel/asm-offsets.c b/arch/loongarch/kernel/asm-offsets.c
index 8be1c38ad8eb2..6f1524bba957e 100644
--- a/arch/loongarch/kernel/asm-offsets.c
+++ b/arch/loongarch/kernel/asm-offsets.c
@@ -315,6 +315,6 @@ static void __used output_vdso_defines(void)
 {
 	COMMENT("LoongArch vDSO offsets.");
 
-	DEFINE(__VVAR_PAGES, VVAR_NR_PAGES);
+	DEFINE(__VDSO_PAGES, VDSO_NR_PAGES);
 	BLANK();
 }
diff --git a/arch/loongarch/kernel/vdso.c b/arch/loongarch/kernel/vdso.c
index 05e5fbac102a9..10cf1608c7b32 100644
--- a/arch/loongarch/kernel/vdso.c
+++ b/arch/loongarch/kernel/vdso.c
@@ -14,7 +14,7 @@
 #include <linux/random.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
-#include <linux/time_namespace.h>
+#include <linux/vdso_datastore.h>
 
 #include <asm/page.h>
 #include <asm/vdso.h>
@@ -25,18 +25,6 @@
 
 extern char vdso_start[], vdso_end[];
 
-/* Kernel-provided data used by the VDSO. */
-static union vdso_data_store generic_vdso_data __page_aligned_data;
-
-static union {
-	u8 page[LOONGARCH_VDSO_DATA_SIZE];
-	struct loongarch_vdso_data vdata;
-} loongarch_vdso_data __page_aligned_data;
-
-struct vdso_data *vdso_data = generic_vdso_data.data;
-struct vdso_pcpu_data *vdso_pdata = loongarch_vdso_data.vdata.pdata;
-struct vdso_rng_data *vdso_rng_data = &loongarch_vdso_data.vdata.rng_data;
-
 static int vdso_mremap(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma)
 {
 	current->mm->context.vdso = (void *)(new_vma->vm_start);
@@ -44,53 +32,12 @@ static int vdso_mremap(const struct vm_special_mapping *sm, struct vm_area_struc
 	return 0;
 }
 
-static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
-			     struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-	unsigned long pfn;
-	struct page *timens_page = find_timens_vvar_page(vma);
-
-	switch (vmf->pgoff) {
-	case VVAR_GENERIC_PAGE_OFFSET:
-		if (!timens_page)
-			pfn = sym_to_pfn(vdso_data);
-		else
-			pfn = page_to_pfn(timens_page);
-		break;
-#ifdef CONFIG_TIME_NS
-	case VVAR_TIMENS_PAGE_OFFSET:
-		/*
-		 * If a task belongs to a time namespace then a namespace specific
-		 * VVAR is mapped with the VVAR_GENERIC_PAGE_OFFSET and the real
-		 * VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET offset.
-		 * See also the comment near timens_setup_vdso_data().
-		 */
-		if (!timens_page)
-			return VM_FAULT_SIGBUS;
-		else
-			pfn = sym_to_pfn(vdso_data);
-		break;
-#endif /* CONFIG_TIME_NS */
-	case VVAR_LOONGARCH_PAGES_START ... VVAR_LOONGARCH_PAGES_END:
-		pfn = sym_to_pfn(&loongarch_vdso_data) + vmf->pgoff - VVAR_LOONGARCH_PAGES_START;
-		break;
-	default:
-		return VM_FAULT_SIGBUS;
-	}
-
-	return vmf_insert_pfn(vma, vmf->address, pfn);
-}
-
 struct loongarch_vdso_info vdso_info = {
 	.vdso = vdso_start,
 	.code_mapping = {
 		.name = "[vdso]",
 		.mremap = vdso_mremap,
 	},
-	.data_mapping = {
-		.name = "[vvar]",
-		.fault = vvar_fault,
-	},
 	.offset_sigreturn = vdso_offset_sigreturn,
 };
 
@@ -101,7 +48,7 @@ static int __init init_vdso(void)
 	BUG_ON(!PAGE_ALIGNED(vdso_info.vdso));
 
 	for_each_possible_cpu(cpu)
-		vdso_pdata[cpu].node = cpu_to_node(cpu);
+		vdso_k_arch_data->pdata[cpu].node = cpu_to_node(cpu);
 
 	vdso_info.size = PAGE_ALIGN(vdso_end - vdso_start);
 	vdso_info.code_mapping.pages =
@@ -115,37 +62,6 @@ static int __init init_vdso(void)
 }
 subsys_initcall(init_vdso);
 
-#ifdef CONFIG_TIME_NS
-struct vdso_data *arch_get_vdso_data(void *vvar_page)
-{
-	return (struct vdso_data *)(vvar_page);
-}
-
-/*
- * The vvar mapping contains data for a specific time namespace, so when a
- * task changes namespace we must unmap its vvar data for the old namespace.
- * Subsequent faults will map in data for the new namespace.
- *
- * For more details see timens_setup_vdso_data().
- */
-int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
-{
-	struct mm_struct *mm = task->mm;
-	struct vm_area_struct *vma;
-
-	VMA_ITERATOR(vmi, mm, 0);
-
-	mmap_read_lock(mm);
-	for_each_vma(vmi, vma) {
-		if (vma_is_special_mapping(vma, &vdso_info.data_mapping))
-			zap_vma_pages(vma);
-	}
-	mmap_read_unlock(mm);
-
-	return 0;
-}
-#endif
-
 static unsigned long vdso_base(void)
 {
 	unsigned long base = STACK_TOP;
@@ -181,9 +97,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 		goto out;
 	}
 
-	vma = _install_special_mapping(mm, data_addr, VVAR_SIZE,
-				       VM_READ | VM_MAYREAD | VM_PFNMAP,
-				       &info->data_mapping);
+	vma = vdso_install_vvar_mapping(mm, data_addr);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		goto out;
diff --git a/arch/loongarch/vdso/vdso.lds.S b/arch/loongarch/vdso/vdso.lds.S
index 160cfaef2de45..8ff9864999475 100644
--- a/arch/loongarch/vdso/vdso.lds.S
+++ b/arch/loongarch/vdso/vdso.lds.S
@@ -5,6 +5,7 @@
  */
 #include <asm/page.h>
 #include <generated/asm-offsets.h>
+#include <vdso/datapage.h>
 
 OUTPUT_FORMAT("elf64-loongarch", "elf64-loongarch", "elf64-loongarch")
 
@@ -12,11 +13,8 @@ OUTPUT_ARCH(loongarch)
 
 SECTIONS
 {
-	PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE);
-#ifdef CONFIG_TIME_NS
-	PROVIDE(_timens_data = _vdso_data + PAGE_SIZE);
-#endif
-	PROVIDE(_loongarch_data = _vdso_data + 2 * PAGE_SIZE);
+	VDSO_VVAR_SYMS
+
 	. = SIZEOF_HEADERS;
 
 	.hash		: { *(.hash) }			:text
diff --git a/arch/loongarch/vdso/vgetcpu.c b/arch/loongarch/vdso/vgetcpu.c
index 0db51258b2a7c..5301cd9d0f839 100644
--- a/arch/loongarch/vdso/vgetcpu.c
+++ b/arch/loongarch/vdso/vgetcpu.c
@@ -19,27 +19,19 @@ static __always_inline int read_cpu_id(void)
 	return cpu_id;
 }
 
-static __always_inline const struct vdso_pcpu_data *get_pcpu_data(void)
-{
-	return _loongarch_data.pdata;
-}
-
 extern
 int __vdso_getcpu(unsigned int *cpu, unsigned int *node, struct getcpu_cache *unused);
 int __vdso_getcpu(unsigned int *cpu, unsigned int *node, struct getcpu_cache *unused)
 {
 	int cpu_id;
-	const struct vdso_pcpu_data *data;
 
 	cpu_id = read_cpu_id();
 
 	if (cpu)
 		*cpu = cpu_id;
 
-	if (node) {
-		data = get_pcpu_data();
-		*node = data[cpu_id].node;
-	}
+	if (node)
+		*node = vdso_u_arch_data.pdata[cpu_id].node;
 
 	return 0;
 }

From 31e9fa2ba9ad64ef09eb4a8326e5cc8af3f6fa1d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Tue, 4 Feb 2025 13:05:43 +0100
Subject: [PATCH 0446/1173] arm: vdso: Switch to generic storage implementation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The generic storage implementation provides the same features as the
custom one. However it can be shared between architectures, making
maintenance easier.

Co-developed-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250204-vdso-store-rng-v3-11-13a4669dfc8c@linutronix.de
---
 arch/arm/include/asm/vdso.h              |  2 ++
 arch/arm/include/asm/vdso/gettimeofday.h |  7 +----
 arch/arm/include/asm/vdso/vsyscall.h     | 12 ++-------
 arch/arm/kernel/asm-offsets.c            |  4 ---
 arch/arm/kernel/vdso.c                   | 34 +++++-------------------
 arch/arm/mm/Kconfig                      |  1 +
 arch/arm/vdso/vdso.lds.S                 |  4 +--
 7 files changed, 15 insertions(+), 49 deletions(-)

diff --git a/arch/arm/include/asm/vdso.h b/arch/arm/include/asm/vdso.h
index 5b85889f82eeb..88364a6727ffc 100644
--- a/arch/arm/include/asm/vdso.h
+++ b/arch/arm/include/asm/vdso.h
@@ -4,6 +4,8 @@
 
 #ifdef __KERNEL__
 
+#define __VDSO_PAGES	4
+
 #ifndef __ASSEMBLY__
 
 struct mm_struct;
diff --git a/arch/arm/include/asm/vdso/gettimeofday.h b/arch/arm/include/asm/vdso/gettimeofday.h
index 592d3d015ca72..1e9f81639c88c 100644
--- a/arch/arm/include/asm/vdso/gettimeofday.h
+++ b/arch/arm/include/asm/vdso/gettimeofday.h
@@ -112,7 +112,7 @@ static inline bool arm_vdso_hres_capable(void)
 #define __arch_vdso_hres_capable arm_vdso_hres_capable
 
 static __always_inline u64 __arch_get_hw_counter(int clock_mode,
-						 const struct vdso_data *vd)
+						 const struct vdso_time_data *vd)
 {
 #ifdef CONFIG_ARM_ARCH_TIMER
 	u64 cycle_now;
@@ -135,11 +135,6 @@ static __always_inline u64 __arch_get_hw_counter(int clock_mode,
 #endif
 }
 
-static __always_inline const struct vdso_data *__arch_get_vdso_data(void)
-{
-	return _vdso_data;
-}
-
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/arm/include/asm/vdso/vsyscall.h b/arch/arm/include/asm/vdso/vsyscall.h
index 705414710dcdb..4e7226ad02ec4 100644
--- a/arch/arm/include/asm/vdso/vsyscall.h
+++ b/arch/arm/include/asm/vdso/vsyscall.h
@@ -7,22 +7,14 @@
 #include <vdso/datapage.h>
 #include <asm/cacheflush.h>
 
-extern struct vdso_data *vdso_data;
 extern bool cntvct_ok;
 
 static __always_inline
-struct vdso_data *__arm_get_k_vdso_data(void)
-{
-	return vdso_data;
-}
-#define __arch_get_k_vdso_data __arm_get_k_vdso_data
-
-static __always_inline
-void __arm_sync_vdso_data(struct vdso_data *vdata)
+void __arch_sync_vdso_time_data(struct vdso_time_data *vdata)
 {
 	flush_dcache_page(virt_to_page(vdata));
 }
-#define __arch_sync_vdso_data __arm_sync_vdso_data
+#define __arch_sync_vdso_time_data __arch_sync_vdso_time_data
 
 /* The asm-generic header needs to be included after the definitions above */
 #include <asm-generic/vdso/vsyscall.h>
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index 4853875740d0f..123f4a8ef4466 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -153,10 +153,6 @@ int main(void)
   DEFINE(CACHE_WRITEBACK_ORDER, __CACHE_WRITEBACK_ORDER);
   DEFINE(CACHE_WRITEBACK_GRANULE, __CACHE_WRITEBACK_GRANULE);
   BLANK();
-#ifdef CONFIG_VDSO
-  DEFINE(VDSO_DATA_SIZE,	sizeof(union vdso_data_store));
-#endif
-  BLANK();
 #ifdef CONFIG_ARM_MPU
   DEFINE(MPU_RNG_INFO_RNGS,	offsetof(struct mpu_rgn_info, rgns));
   DEFINE(MPU_RNG_INFO_USED,	offsetof(struct mpu_rgn_info, used));
diff --git a/arch/arm/kernel/vdso.c b/arch/arm/kernel/vdso.c
index 29dd2f3c62fec..325448ffbba0c 100644
--- a/arch/arm/kernel/vdso.c
+++ b/arch/arm/kernel/vdso.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/cache.h>
+#include <linux/vdso_datastore.h>
 #include <linux/elf.h>
 #include <linux/err.h>
 #include <linux/kernel.h>
@@ -33,15 +34,6 @@ extern char vdso_start[], vdso_end[];
 /* Total number of pages needed for the data and text portions of the VDSO. */
 unsigned int vdso_total_pages __ro_after_init;
 
-static union vdso_data_store vdso_data_store __page_aligned_data;
-struct vdso_data *vdso_data = vdso_data_store.data;
-
-static struct page *vdso_data_page __ro_after_init;
-static const struct vm_special_mapping vdso_data_mapping = {
-	.name = "[vvar]",
-	.pages = &vdso_data_page,
-};
-
 static int vdso_mremap(const struct vm_special_mapping *sm,
 		struct vm_area_struct *new_vma)
 {
@@ -192,9 +184,6 @@ static int __init vdso_init(void)
 	if (vdso_text_pagelist == NULL)
 		return -ENOMEM;
 
-	/* Grab the VDSO data page. */
-	vdso_data_page = virt_to_page(vdso_data);
-
 	/* Grab the VDSO text pages. */
 	for (i = 0; i < text_pages; i++) {
 		struct page *page;
@@ -205,7 +194,7 @@ static int __init vdso_init(void)
 
 	vdso_text_mapping.pages = vdso_text_pagelist;
 
-	vdso_total_pages = 1; /* for the data/vvar page */
+	vdso_total_pages = VDSO_NR_PAGES; /* for the data/vvar pages */
 	vdso_total_pages += text_pages;
 
 	cntvct_ok = cntvct_functional();
@@ -216,16 +205,7 @@ static int __init vdso_init(void)
 }
 arch_initcall(vdso_init);
 
-static int install_vvar(struct mm_struct *mm, unsigned long addr)
-{
-	struct vm_area_struct *vma;
-
-	vma = _install_special_mapping(mm, addr, PAGE_SIZE,
-				       VM_READ | VM_MAYREAD,
-				       &vdso_data_mapping);
-
-	return PTR_ERR_OR_ZERO(vma);
-}
+static_assert(__VDSO_PAGES == VDSO_NR_PAGES);
 
 /* assumes mmap_lock is write-locked */
 void arm_install_vdso(struct mm_struct *mm, unsigned long addr)
@@ -238,12 +218,12 @@ void arm_install_vdso(struct mm_struct *mm, unsigned long addr)
 	if (vdso_text_pagelist == NULL)
 		return;
 
-	if (install_vvar(mm, addr))
+	if (IS_ERR(vdso_install_vvar_mapping(mm, addr)))
 		return;
 
-	/* Account for vvar page. */
-	addr += PAGE_SIZE;
-	len = (vdso_total_pages - 1) << PAGE_SHIFT;
+	/* Account for vvar pages. */
+	addr += VDSO_NR_PAGES * PAGE_SIZE;
+	len = (vdso_total_pages - VDSO_NR_PAGES) << PAGE_SHIFT;
 
 	vma = _install_special_mapping(mm, addr, len,
 		VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC,
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 2b6f50dd54784..5c1023a6d78c1 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -928,6 +928,7 @@ config VDSO
 	select GENERIC_TIME_VSYSCALL
 	select GENERIC_VDSO_32
 	select GENERIC_GETTIMEOFDAY
+	select GENERIC_VDSO_DATA_STORE
 	help
 	  Place in the process address space an ELF shared object
 	  providing fast implementations of gettimeofday and
diff --git a/arch/arm/vdso/vdso.lds.S b/arch/arm/vdso/vdso.lds.S
index 9bfa0f52923c8..7c08371f44002 100644
--- a/arch/arm/vdso/vdso.lds.S
+++ b/arch/arm/vdso/vdso.lds.S
@@ -11,16 +11,16 @@
  */
 
 #include <linux/const.h>
-#include <asm/asm-offsets.h>
 #include <asm/page.h>
 #include <asm/vdso.h>
+#include <vdso/datapage.h>
 
 OUTPUT_FORMAT("elf32-littlearm", "elf32-bigarm", "elf32-littlearm")
 OUTPUT_ARCH(arm)
 
 SECTIONS
 {
-	PROVIDE(_vdso_data = . - VDSO_DATA_SIZE);
+	VDSO_VVAR_SYMS
 
 	. = SIZEOF_HEADERS;
 

From 9bf39a65b20cd03b10c618b1b1c4703538a5b564 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Tue, 4 Feb 2025 13:05:44 +0100
Subject: [PATCH 0447/1173] s390/vdso: Switch to generic storage implementation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The generic storage implementation provides the same features as the
custom one. However it can be shared between architectures, making
maintenance easier.

Co-developed-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Heiko Carstens <hca@linux.ibm.com>
Link: https://lore.kernel.org/all/20250204-vdso-store-rng-v3-12-13a4669dfc8c@linutronix.de
---
 arch/s390/Kconfig                         |  1 +
 arch/s390/include/asm/vdso.h              |  4 +-
 arch/s390/include/asm/vdso/getrandom.h    | 12 ---
 arch/s390/include/asm/vdso/gettimeofday.h | 15 +---
 arch/s390/include/asm/vdso/vsyscall.h     | 20 -----
 arch/s390/kernel/time.c                   |  6 +-
 arch/s390/kernel/vdso.c                   | 97 ++---------------------
 arch/s390/kernel/vdso32/vdso32.lds.S      |  7 +-
 arch/s390/kernel/vdso64/vdso64.lds.S      |  8 +-
 9 files changed, 17 insertions(+), 153 deletions(-)

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 9c9ec08d78c71..7ed6f229250cf 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -166,6 +166,7 @@ config S390
 	select GENERIC_PTDUMP
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_TIME_VSYSCALL
+	select GENERIC_VDSO_DATA_STORE
 	select GENERIC_VDSO_TIME_NS
 	select GENERIC_IOREMAP if PCI
 	select HAVE_ALIGNED_STRUCT_PAGE
diff --git a/arch/s390/include/asm/vdso.h b/arch/s390/include/asm/vdso.h
index 92c73e4d97a93..420a073fdde5d 100644
--- a/arch/s390/include/asm/vdso.h
+++ b/arch/s390/include/asm/vdso.h
@@ -6,13 +6,11 @@
 
 #ifndef __ASSEMBLY__
 
-extern struct vdso_data *vdso_data;
-
 int vdso_getcpu_init(void);
 
 #endif /* __ASSEMBLY__ */
 
-#define __VVAR_PAGES	2
+#define __VDSO_PAGES	4
 
 #define VDSO_VERSION_STRING	LINUX_2.6.29
 
diff --git a/arch/s390/include/asm/vdso/getrandom.h b/arch/s390/include/asm/vdso/getrandom.h
index 36355af7160be..f8713ce39bb2f 100644
--- a/arch/s390/include/asm/vdso/getrandom.h
+++ b/arch/s390/include/asm/vdso/getrandom.h
@@ -23,18 +23,6 @@ static __always_inline ssize_t getrandom_syscall(void *buffer, size_t len, unsig
 	return syscall3(__NR_getrandom, (long)buffer, (long)len, (long)flags);
 }
 
-static __always_inline const struct vdso_rng_data *__arch_get_vdso_rng_data(void)
-{
-	/*
-	 * The RNG data is in the real VVAR data page, but if a task belongs to a time namespace
-	 * then VVAR_DATA_PAGE_OFFSET points to the namespace-specific VVAR page and VVAR_TIMENS_
-	 * PAGE_OFFSET points to the real VVAR page.
-	 */
-	if (IS_ENABLED(CONFIG_TIME_NS) && _vdso_data->clock_mode == VDSO_CLOCKMODE_TIMENS)
-		return (void *)&_vdso_rng_data + VVAR_TIMENS_PAGE_OFFSET * PAGE_SIZE;
-	return &_vdso_rng_data;
-}
-
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_VDSO_GETRANDOM_H */
diff --git a/arch/s390/include/asm/vdso/gettimeofday.h b/arch/s390/include/asm/vdso/gettimeofday.h
index 7937765ccfa5b..fb4564308e9d7 100644
--- a/arch/s390/include/asm/vdso/gettimeofday.h
+++ b/arch/s390/include/asm/vdso/gettimeofday.h
@@ -14,12 +14,7 @@
 #include <linux/compiler.h>
 
 
-static __always_inline const struct vdso_data *__arch_get_vdso_data(void)
-{
-	return _vdso_data;
-}
-
-static inline u64 __arch_get_hw_counter(s32 clock_mode, const struct vdso_data *vd)
+static inline u64 __arch_get_hw_counter(s32 clock_mode, const struct vdso_time_data *vd)
 {
 	u64 adj, now;
 
@@ -49,12 +44,4 @@ long clock_getres_fallback(clockid_t clkid, struct __kernel_timespec *ts)
 	return syscall2(__NR_clock_getres, (long)clkid, (long)ts);
 }
 
-#ifdef CONFIG_TIME_NS
-static __always_inline
-const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd)
-{
-	return _timens_data;
-}
-#endif
-
 #endif
diff --git a/arch/s390/include/asm/vdso/vsyscall.h b/arch/s390/include/asm/vdso/vsyscall.h
index 3eb576ecd3bd9..d346ebe513015 100644
--- a/arch/s390/include/asm/vdso/vsyscall.h
+++ b/arch/s390/include/asm/vdso/vsyscall.h
@@ -2,32 +2,12 @@
 #ifndef __ASM_VDSO_VSYSCALL_H
 #define __ASM_VDSO_VSYSCALL_H
 
-#define __VDSO_RND_DATA_OFFSET	768
-
 #ifndef __ASSEMBLY__
 
 #include <linux/hrtimer.h>
 #include <vdso/datapage.h>
 #include <asm/vdso.h>
 
-enum vvar_pages {
-	VVAR_DATA_PAGE_OFFSET,
-	VVAR_TIMENS_PAGE_OFFSET,
-	VVAR_NR_PAGES
-};
-
-static __always_inline struct vdso_data *__s390_get_k_vdso_data(void)
-{
-	return vdso_data;
-}
-#define __arch_get_k_vdso_data __s390_get_k_vdso_data
-
-static __always_inline struct vdso_rng_data *__s390_get_k_vdso_rnd_data(void)
-{
-	return (void *)vdso_data + __VDSO_RND_DATA_OFFSET;
-}
-#define __arch_get_k_vdso_rng_data __s390_get_k_vdso_rnd_data
-
 /* The asm-generic header needs to be included after the definitions above */
 #include <asm-generic/vdso/vsyscall.h>
 
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index e9f47c3a61978..41ca3586b19f6 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -84,7 +84,7 @@ void __init time_early_init(void)
 	/* Initialize TOD steering parameters */
 	tod_steering_end = tod_clock_base.tod;
 	for (cs = 0; cs < CS_BASES; cs++)
-		vdso_data[cs].arch_data.tod_steering_end = tod_steering_end;
+		vdso_k_time_data[cs].arch_data.tod_steering_end = tod_steering_end;
 
 	if (!test_facility(28))
 		return;
@@ -390,8 +390,8 @@ static void clock_sync_global(long delta)
 		      tod_steering_delta);
 	tod_steering_end = now + (abs(tod_steering_delta) << 15);
 	for (cs = 0; cs < CS_BASES; cs++) {
-		vdso_data[cs].arch_data.tod_steering_end = tod_steering_end;
-		vdso_data[cs].arch_data.tod_steering_delta = tod_steering_delta;
+		vdso_k_time_data[cs].arch_data.tod_steering_end = tod_steering_end;
+		vdso_k_time_data[cs].arch_data.tod_steering_delta = tod_steering_delta;
 	}
 
 	/* Update LPAR offset. */
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index 598b512cde012..70c8f9ad13cde 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -16,8 +16,8 @@
 #include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/smp.h>
-#include <linux/time_namespace.h>
 #include <linux/random.h>
+#include <linux/vdso_datastore.h>
 #include <vdso/datapage.h>
 #include <asm/vdso/vsyscall.h>
 #include <asm/alternative.h>
@@ -26,85 +26,6 @@
 extern char vdso64_start[], vdso64_end[];
 extern char vdso32_start[], vdso32_end[];
 
-static struct vm_special_mapping vvar_mapping;
-
-static union vdso_data_store vdso_data_store __page_aligned_data;
-
-struct vdso_data *vdso_data = vdso_data_store.data;
-
-#ifdef CONFIG_TIME_NS
-struct vdso_data *arch_get_vdso_data(void *vvar_page)
-{
-	return (struct vdso_data *)(vvar_page);
-}
-
-/*
- * The VVAR page layout depends on whether a task belongs to the root or
- * non-root time namespace. Whenever a task changes its namespace, the VVAR
- * page tables are cleared and then they will be re-faulted with a
- * corresponding layout.
- * See also the comment near timens_setup_vdso_data() for details.
- */
-int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
-{
-	struct mm_struct *mm = task->mm;
-	VMA_ITERATOR(vmi, mm, 0);
-	struct vm_area_struct *vma;
-
-	mmap_read_lock(mm);
-	for_each_vma(vmi, vma) {
-		if (!vma_is_special_mapping(vma, &vvar_mapping))
-			continue;
-		zap_vma_pages(vma);
-		break;
-	}
-	mmap_read_unlock(mm);
-	return 0;
-}
-#endif
-
-static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
-			     struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-	struct page *timens_page = find_timens_vvar_page(vma);
-	unsigned long addr, pfn;
-	vm_fault_t err;
-
-	switch (vmf->pgoff) {
-	case VVAR_DATA_PAGE_OFFSET:
-		pfn = virt_to_pfn(vdso_data);
-		if (timens_page) {
-			/*
-			 * Fault in VVAR page too, since it will be accessed
-			 * to get clock data anyway.
-			 */
-			addr = vmf->address + VVAR_TIMENS_PAGE_OFFSET * PAGE_SIZE;
-			err = vmf_insert_pfn(vma, addr, pfn);
-			if (unlikely(err & VM_FAULT_ERROR))
-				return err;
-			pfn = page_to_pfn(timens_page);
-		}
-		break;
-#ifdef CONFIG_TIME_NS
-	case VVAR_TIMENS_PAGE_OFFSET:
-		/*
-		 * If a task belongs to a time namespace then a namespace
-		 * specific VVAR is mapped with the VVAR_DATA_PAGE_OFFSET and
-		 * the real VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET
-		 * offset.
-		 * See also the comment near timens_setup_vdso_data().
-		 */
-		if (!timens_page)
-			return VM_FAULT_SIGBUS;
-		pfn = virt_to_pfn(vdso_data);
-		break;
-#endif /* CONFIG_TIME_NS */
-	default:
-		return VM_FAULT_SIGBUS;
-	}
-	return vmf_insert_pfn(vma, vmf->address, pfn);
-}
-
 static int vdso_mremap(const struct vm_special_mapping *sm,
 		       struct vm_area_struct *vma)
 {
@@ -112,11 +33,6 @@ static int vdso_mremap(const struct vm_special_mapping *sm,
 	return 0;
 }
 
-static struct vm_special_mapping vvar_mapping = {
-	.name = "[vvar]",
-	.fault = vvar_fault,
-};
-
 static struct vm_special_mapping vdso64_mapping = {
 	.name = "[vdso]",
 	.mremap = vdso_mremap,
@@ -142,7 +58,7 @@ static int map_vdso(unsigned long addr, unsigned long vdso_mapping_len)
 	struct vm_area_struct *vma;
 	int rc;
 
-	BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES);
+	BUILD_BUG_ON(VDSO_NR_PAGES != __VDSO_PAGES);
 	if (mmap_write_lock_killable(mm))
 		return -EINTR;
 
@@ -157,14 +73,11 @@ static int map_vdso(unsigned long addr, unsigned long vdso_mapping_len)
 	rc = vvar_start;
 	if (IS_ERR_VALUE(vvar_start))
 		goto out;
-	vma = _install_special_mapping(mm, vvar_start, VVAR_NR_PAGES*PAGE_SIZE,
-				       VM_READ|VM_MAYREAD|VM_IO|VM_DONTDUMP|
-				       VM_PFNMAP,
-				       &vvar_mapping);
+	vma = vdso_install_vvar_mapping(mm, vvar_start);
 	rc = PTR_ERR(vma);
 	if (IS_ERR(vma))
 		goto out;
-	vdso_text_start = vvar_start + VVAR_NR_PAGES * PAGE_SIZE;
+	vdso_text_start = vvar_start + VDSO_NR_PAGES * PAGE_SIZE;
 	/* VM_MAYWRITE for COW so gdb can set breakpoints */
 	vma = _install_special_mapping(mm, vdso_text_start, vdso_text_len,
 				       VM_READ|VM_EXEC|
@@ -220,7 +133,7 @@ unsigned long vdso_text_size(void)
 
 unsigned long vdso_size(void)
 {
-	return vdso_text_size() + VVAR_NR_PAGES * PAGE_SIZE;
+	return vdso_text_size() + VDSO_NR_PAGES * PAGE_SIZE;
 }
 
 int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
diff --git a/arch/s390/kernel/vdso32/vdso32.lds.S b/arch/s390/kernel/vdso32/vdso32.lds.S
index c916c4f73f766..9630d58c20806 100644
--- a/arch/s390/kernel/vdso32/vdso32.lds.S
+++ b/arch/s390/kernel/vdso32/vdso32.lds.S
@@ -6,16 +6,15 @@
 
 #include <asm/page.h>
 #include <asm/vdso.h>
+#include <vdso/datapage.h>
 
 OUTPUT_FORMAT("elf32-s390", "elf32-s390", "elf32-s390")
 OUTPUT_ARCH(s390:31-bit)
 
 SECTIONS
 {
-	PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE);
-#ifdef CONFIG_TIME_NS
-	PROVIDE(_timens_data = _vdso_data + PAGE_SIZE);
-#endif
+	VDSO_VVAR_SYMS
+
 	. = SIZEOF_HEADERS;
 
 	.hash		: { *(.hash) }			:text
diff --git a/arch/s390/kernel/vdso64/vdso64.lds.S b/arch/s390/kernel/vdso64/vdso64.lds.S
index ec42b7d9cb530..e4f6551ae8988 100644
--- a/arch/s390/kernel/vdso64/vdso64.lds.S
+++ b/arch/s390/kernel/vdso64/vdso64.lds.S
@@ -7,17 +7,15 @@
 #include <asm/vdso/vsyscall.h>
 #include <asm/page.h>
 #include <asm/vdso.h>
+#include <vdso/datapage.h>
 
 OUTPUT_FORMAT("elf64-s390", "elf64-s390", "elf64-s390")
 OUTPUT_ARCH(s390:64-bit)
 
 SECTIONS
 {
-	PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE);
-	PROVIDE(_vdso_rng_data = _vdso_data + __VDSO_RND_DATA_OFFSET);
-#ifdef CONFIG_TIME_NS
-	PROVIDE(_timens_data = _vdso_data + PAGE_SIZE);
-#endif
+	VDSO_VVAR_SYMS
+
 	. = SIZEOF_HEADERS;
 
 	.hash		: { *(.hash) }			:text

From 69896119dc9d6cdb7db3914a88c4a7b31e342a20 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Tue, 4 Feb 2025 13:05:45 +0100
Subject: [PATCH 0448/1173] MIPS: vdso: Switch to generic storage
 implementation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The generic storage implementation provides the same features as the
custom one. However it can be shared between architectures, making
maintenance easier.

Co-developed-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250204-vdso-store-rng-v3-13-13a4669dfc8c@linutronix.de
---
 arch/mips/Kconfig                         |  1 +
 arch/mips/include/asm/vdso/gettimeofday.h |  9 +++--
 arch/mips/include/asm/vdso/vdso.h         | 19 ++++-----
 arch/mips/include/asm/vdso/vsyscall.h     | 14 +------
 arch/mips/kernel/vdso.c                   | 47 +++++++++--------------
 arch/mips/vdso/vdso.lds.S                 |  5 ++-
 6 files changed, 38 insertions(+), 57 deletions(-)

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 1924f2d839323..b51168e319ea3 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -51,6 +51,7 @@ config MIPS
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_IDLE_POLL_SETUP
 	select GENERIC_TIME_VSYSCALL
+	select GENERIC_VDSO_DATA_STORE
 	select GUP_GET_PXX_LOW_HIGH if CPU_MIPS32 && PHYS_ADDR_T_64BIT
 	select HAS_IOPORT if !NO_IOPORT_MAP || ISA
 	select HAVE_ARCH_COMPILER_H
diff --git a/arch/mips/include/asm/vdso/gettimeofday.h b/arch/mips/include/asm/vdso/gettimeofday.h
index 44a45f3fa4b01..fd32baa30e172 100644
--- a/arch/mips/include/asm/vdso/gettimeofday.h
+++ b/arch/mips/include/asm/vdso/gettimeofday.h
@@ -167,7 +167,7 @@ static __always_inline u64 read_r4k_count(void)
 
 #ifdef CONFIG_CLKSRC_MIPS_GIC
 
-static __always_inline u64 read_gic_count(const struct vdso_data *data)
+static __always_inline u64 read_gic_count(const struct vdso_time_data *data)
 {
 	void __iomem *gic = get_gic(data);
 	u32 hi, hi2, lo;
@@ -184,7 +184,7 @@ static __always_inline u64 read_gic_count(const struct vdso_data *data)
 #endif
 
 static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
-						 const struct vdso_data *vd)
+						 const struct vdso_time_data *vd)
 {
 #ifdef CONFIG_CSRC_R4K
 	if (clock_mode == VDSO_CLOCKMODE_R4K)
@@ -209,10 +209,11 @@ static inline bool mips_vdso_hres_capable(void)
 }
 #define __arch_vdso_hres_capable mips_vdso_hres_capable
 
-static __always_inline const struct vdso_data *__arch_get_vdso_data(void)
+static __always_inline const struct vdso_time_data *__arch_get_vdso_u_time_data(void)
 {
-	return get_vdso_data();
+	return get_vdso_time_data();
 }
+#define __arch_get_vdso_u_time_data __arch_get_vdso_u_time_data
 
 #endif /* !__ASSEMBLY__ */
 
diff --git a/arch/mips/include/asm/vdso/vdso.h b/arch/mips/include/asm/vdso/vdso.h
index 6cd88191fefa9..acd0efcd3d93e 100644
--- a/arch/mips/include/asm/vdso/vdso.h
+++ b/arch/mips/include/asm/vdso/vdso.h
@@ -5,16 +5,18 @@
  */
 
 #include <asm/sgidefs.h>
+#include <vdso/page.h>
+
+#define __VDSO_PAGES 4
 
 #ifndef __ASSEMBLY__
 
 #include <asm/asm.h>
-#include <asm/page.h>
 #include <asm/vdso.h>
 
-static inline unsigned long get_vdso_base(void)
+static inline const struct vdso_time_data *get_vdso_time_data(void)
 {
-	unsigned long addr;
+	const struct vdso_time_data *addr;
 
 	/*
 	 * We can't use cpu_has_mips_r6 since it needs the cpu_data[]
@@ -27,7 +29,7 @@ static inline unsigned long get_vdso_base(void)
 	 * We can't use addiupc because there is no label-label
 	 * support for the addiupc reloc
 	 */
-	__asm__("lapc	%0, _start			\n"
+	__asm__("lapc	%0, vdso_u_time_data		\n"
 		: "=r" (addr) : :);
 #else
 	/*
@@ -46,7 +48,7 @@ static inline unsigned long get_vdso_base(void)
 	"	.set noreorder				\n"
 	"	bal	1f				\n"
 	"	 nop					\n"
-	"	.word	_start - .			\n"
+	"	.word	vdso_u_time_data - .		\n"
 	"1:	lw	%0, 0($31)			\n"
 	"	" STR(PTR_ADDU) " %0, $31, %0		\n"
 	"	.set pop				\n"
@@ -58,14 +60,9 @@ static inline unsigned long get_vdso_base(void)
 	return addr;
 }
 
-static inline const struct vdso_data *get_vdso_data(void)
-{
-	return (const struct vdso_data *)(get_vdso_base() - PAGE_SIZE);
-}
-
 #ifdef CONFIG_CLKSRC_MIPS_GIC
 
-static inline void __iomem *get_gic(const struct vdso_data *data)
+static inline void __iomem *get_gic(const struct vdso_time_data *data)
 {
 	return (void __iomem *)((unsigned long)data & PAGE_MASK) - PAGE_SIZE;
 }
diff --git a/arch/mips/include/asm/vdso/vsyscall.h b/arch/mips/include/asm/vdso/vsyscall.h
index a4582870aaea4..2b1debb62dee0 100644
--- a/arch/mips/include/asm/vdso/vsyscall.h
+++ b/arch/mips/include/asm/vdso/vsyscall.h
@@ -2,22 +2,12 @@
 #ifndef __ASM_VDSO_VSYSCALL_H
 #define __ASM_VDSO_VSYSCALL_H
 
+#include <asm/page.h>
+
 #ifndef __ASSEMBLY__
 
 #include <vdso/datapage.h>
 
-extern struct vdso_data *vdso_data;
-
-/*
- * Update the vDSO data page to keep in sync with kernel timekeeping.
- */
-static __always_inline
-struct vdso_data *__mips_get_k_vdso_data(void)
-{
-	return vdso_data;
-}
-#define __arch_get_k_vdso_data __mips_get_k_vdso_data
-
 /* The asm-generic header needs to be included after the definitions above */
 #include <asm-generic/vdso/vsyscall.h>
 
diff --git a/arch/mips/kernel/vdso.c b/arch/mips/kernel/vdso.c
index 75c9d3618f588..de096777172f0 100644
--- a/arch/mips/kernel/vdso.c
+++ b/arch/mips/kernel/vdso.c
@@ -15,6 +15,7 @@
 #include <linux/random.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include <linux/vdso_datastore.h>
 
 #include <asm/abi.h>
 #include <asm/mips-cps.h>
@@ -23,20 +24,7 @@
 #include <vdso/helpers.h>
 #include <vdso/vsyscall.h>
 
-/* Kernel-provided data used by the VDSO. */
-static union vdso_data_store mips_vdso_data __page_aligned_data;
-struct vdso_data *vdso_data = mips_vdso_data.data;
-
-/*
- * Mapping for the VDSO data/GIC pages. The real pages are mapped manually, as
- * what we map and where within the area they are mapped is determined at
- * runtime.
- */
-static struct page *no_pages[] = { NULL };
-static struct vm_special_mapping vdso_vvar_mapping = {
-	.name = "[vvar]",
-	.pages = no_pages,
-};
+static_assert(VDSO_NR_PAGES == __VDSO_PAGES);
 
 static void __init init_vdso_image(struct mips_vdso_image *image)
 {
@@ -90,7 +78,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 {
 	struct mips_vdso_image *image = current->thread.abi->vdso;
 	struct mm_struct *mm = current->mm;
-	unsigned long gic_size, vvar_size, size, base, data_addr, vdso_addr, gic_pfn, gic_base;
+	unsigned long gic_size, size, base, data_addr, vdso_addr, gic_pfn, gic_base;
 	struct vm_area_struct *vma;
 	int ret;
 
@@ -119,8 +107,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	 * the counter registers at the start.
 	 */
 	gic_size = mips_gic_present() ? PAGE_SIZE : 0;
-	vvar_size = gic_size + PAGE_SIZE;
-	size = vvar_size + image->size;
+	size = gic_size + VDSO_NR_PAGES * PAGE_SIZE + image->size;
 
 	/*
 	 * Find a region that's large enough for us to perform the
@@ -143,15 +130,13 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	 */
 	if (cpu_has_dc_aliases) {
 		base = __ALIGN_MASK(base, shm_align_mask);
-		base += ((unsigned long)vdso_data - gic_size) & shm_align_mask;
+		base += ((unsigned long)vdso_k_time_data - gic_size) & shm_align_mask;
 	}
 
 	data_addr = base + gic_size;
-	vdso_addr = data_addr + PAGE_SIZE;
+	vdso_addr = data_addr + VDSO_NR_PAGES * PAGE_SIZE;
 
-	vma = _install_special_mapping(mm, base, vvar_size,
-				       VM_READ | VM_MAYREAD,
-				       &vdso_vvar_mapping);
+	vma = vdso_install_vvar_mapping(mm, data_addr);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		goto out;
@@ -161,6 +146,17 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	if (gic_size) {
 		gic_base = (unsigned long)mips_gic_base + MIPS_GIC_USER_OFS;
 		gic_pfn = PFN_DOWN(__pa(gic_base));
+		static const struct vm_special_mapping gic_mapping = {
+			.name	= "[gic]",
+			.pages	= (struct page **) { NULL },
+		};
+
+		vma = _install_special_mapping(mm, base, gic_size, VM_READ | VM_MAYREAD,
+					       &gic_mapping);
+		if (IS_ERR(vma)) {
+			ret = PTR_ERR(vma);
+			goto out;
+		}
 
 		ret = io_remap_pfn_range(vma, base, gic_pfn, gic_size,
 					 pgprot_noncached(vma->vm_page_prot));
@@ -168,13 +164,6 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 			goto out;
 	}
 
-	/* Map data page. */
-	ret = remap_pfn_range(vma, data_addr,
-			      virt_to_phys(vdso_data) >> PAGE_SHIFT,
-			      PAGE_SIZE, vma->vm_page_prot);
-	if (ret)
-		goto out;
-
 	/* Map VDSO image. */
 	vma = _install_special_mapping(mm, vdso_addr, image->size,
 				       VM_READ | VM_EXEC |
diff --git a/arch/mips/vdso/vdso.lds.S b/arch/mips/vdso/vdso.lds.S
index 836465e3bcb8a..c8bbe56d89cb0 100644
--- a/arch/mips/vdso/vdso.lds.S
+++ b/arch/mips/vdso/vdso.lds.S
@@ -5,6 +5,8 @@
  */
 
 #include <asm/sgidefs.h>
+#include <asm/vdso/vdso.h>
+#include <vdso/datapage.h>
 
 #if _MIPS_SIM == _MIPS_SIM_ABI64
 OUTPUT_FORMAT("elf64-tradlittlemips", "elf64-tradbigmips", "elf64-tradlittlemips")
@@ -18,7 +20,8 @@ OUTPUT_ARCH(mips)
 
 SECTIONS
 {
-	PROVIDE(_start = .);
+	VDSO_VVAR_SYMS
+
 	. = SIZEOF_HEADERS;
 
 	/*

From 223970df2bff4caa308246404383baee2b79dba2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Tue, 4 Feb 2025 13:05:46 +0100
Subject: [PATCH 0449/1173] powerpc/vdso: Switch to generic storage
 implementation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The generic storage implementation provides the same features as the
custom one. However it can be shared between architectures, making
maintenance easier.

Co-developed-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Link: https://lore.kernel.org/all/20250204-vdso-store-rng-v3-14-13a4669dfc8c@linutronix.de
---
 arch/powerpc/Kconfig                         |   2 +
 arch/powerpc/include/asm/vdso.h              |   1 +
 arch/powerpc/include/asm/vdso/arch_data.h    |  37 ++++++
 arch/powerpc/include/asm/vdso/getrandom.h    |  11 +-
 arch/powerpc/include/asm/vdso/gettimeofday.h |  29 ++---
 arch/powerpc/include/asm/vdso/vsyscall.h     |  13 ---
 arch/powerpc/include/asm/vdso_datapage.h     |  44 +------
 arch/powerpc/kernel/asm-offsets.c            |   1 -
 arch/powerpc/kernel/time.c                   |   2 +-
 arch/powerpc/kernel/vdso.c                   | 115 ++-----------------
 arch/powerpc/kernel/vdso/cacheflush.S        |   2 +-
 arch/powerpc/kernel/vdso/datapage.S          |   4 +-
 arch/powerpc/kernel/vdso/gettimeofday.S      |   4 +-
 arch/powerpc/kernel/vdso/vdso32.lds.S        |   4 +-
 arch/powerpc/kernel/vdso/vdso64.lds.S        |   4 +-
 arch/powerpc/kernel/vdso/vgettimeofday.c     |  14 +--
 16 files changed, 89 insertions(+), 198 deletions(-)
 create mode 100644 arch/powerpc/include/asm/vdso/arch_data.h

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 424f188e62d98..8a2a6e403eb1e 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -159,6 +159,7 @@ config PPC
 	select ARCH_HAS_TICK_BROADCAST		if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAS_UACCESS_FLUSHCACHE
 	select ARCH_HAS_UBSAN
+	select ARCH_HAS_VDSO_ARCH_DATA
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_HAVE_EXTRA_ELF_NOTES        if SPU_BASE
 	select ARCH_KEEP_MEMBLOCK
@@ -209,6 +210,7 @@ config PPC
 	select GENERIC_PTDUMP
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_TIME_VSYSCALL
+	select GENERIC_VDSO_DATA_STORE
 	select GENERIC_VDSO_TIME_NS
 	select HAS_IOPORT			if PCI
 	select HAVE_ARCH_AUDITSYSCALL
diff --git a/arch/powerpc/include/asm/vdso.h b/arch/powerpc/include/asm/vdso.h
index 8d972bc98b55f..1ca23fbfe087a 100644
--- a/arch/powerpc/include/asm/vdso.h
+++ b/arch/powerpc/include/asm/vdso.h
@@ -3,6 +3,7 @@
 #define _ASM_POWERPC_VDSO_H
 
 #define VDSO_VERSION_STRING	LINUX_2.6.15
+#define __VDSO_PAGES		4
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/powerpc/include/asm/vdso/arch_data.h b/arch/powerpc/include/asm/vdso/arch_data.h
new file mode 100644
index 0000000000000..c240a6b875181
--- /dev/null
+++ b/arch/powerpc/include/asm/vdso/arch_data.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2002 Peter Bergner <bergner@vnet.ibm.com>, IBM
+ * Copyright (C) 2005 Benjamin Herrenschmidy <benh@kernel.crashing.org>,
+ * 		      IBM Corp.
+ */
+#ifndef _ASM_POWERPC_VDSO_ARCH_DATA_H
+#define _ASM_POWERPC_VDSO_ARCH_DATA_H
+
+#include <linux/unistd.h>
+#include <linux/types.h>
+
+#define SYSCALL_MAP_SIZE      ((NR_syscalls + 31) / 32)
+
+#ifdef CONFIG_PPC64
+
+struct vdso_arch_data {
+	__u64 tb_ticks_per_sec;			/* Timebase tics / sec */
+	__u32 dcache_block_size;		/* L1 d-cache block size     */
+	__u32 icache_block_size;		/* L1 i-cache block size     */
+	__u32 dcache_log_block_size;		/* L1 d-cache log block size */
+	__u32 icache_log_block_size;		/* L1 i-cache log block size */
+	__u32 syscall_map[SYSCALL_MAP_SIZE];	/* Map of syscalls  */
+	__u32 compat_syscall_map[SYSCALL_MAP_SIZE];	/* Map of compat syscalls */
+};
+
+#else /* CONFIG_PPC64 */
+
+struct vdso_arch_data {
+	__u64 tb_ticks_per_sec;		/* Timebase tics / sec */
+	__u32 syscall_map[SYSCALL_MAP_SIZE]; /* Map of syscalls */
+	__u32 compat_syscall_map[0];	/* No compat syscalls on PPC32 */
+};
+
+#endif /* CONFIG_PPC64 */
+
+#endif /* _ASM_POWERPC_VDSO_ARCH_DATA_H */
diff --git a/arch/powerpc/include/asm/vdso/getrandom.h b/arch/powerpc/include/asm/vdso/getrandom.h
index 80ce0709725eb..067a5396aac6e 100644
--- a/arch/powerpc/include/asm/vdso/getrandom.h
+++ b/arch/powerpc/include/asm/vdso/getrandom.h
@@ -43,20 +43,21 @@ static __always_inline ssize_t getrandom_syscall(void *buffer, size_t len, unsig
 			    (unsigned long)len, (unsigned long)flags);
 }
 
-static __always_inline struct vdso_rng_data *__arch_get_vdso_rng_data(void)
+static __always_inline const struct vdso_rng_data *__arch_get_vdso_u_rng_data(void)
 {
-	struct vdso_arch_data *data;
+	struct vdso_rng_data *data;
 
 	asm (
 		"	bcl	20, 31, .+4 ;"
 		"0:	mflr	%0 ;"
-		"	addis	%0, %0, (_vdso_datapage - 0b)@ha ;"
-		"	addi	%0, %0, (_vdso_datapage - 0b)@l  ;"
+		"	addis	%0, %0, (vdso_u_rng_data - 0b)@ha ;"
+		"	addi	%0, %0, (vdso_u_rng_data - 0b)@l  ;"
 		: "=r" (data) : : "lr"
 	);
 
-	return &data->rng_data;
+	return data;
 }
+#define __arch_get_vdso_u_rng_data __arch_get_vdso_u_rng_data
 
 ssize_t __c_kernel_getrandom(void *buffer, size_t len, unsigned int flags, void *opaque_state,
 			     size_t opaque_len);
diff --git a/arch/powerpc/include/asm/vdso/gettimeofday.h b/arch/powerpc/include/asm/vdso/gettimeofday.h
index c6390890a60c2..dc955f2e0cc51 100644
--- a/arch/powerpc/include/asm/vdso/gettimeofday.h
+++ b/arch/powerpc/include/asm/vdso/gettimeofday.h
@@ -94,22 +94,12 @@ int clock_getres32_fallback(clockid_t _clkid, struct old_timespec32 *_ts)
 #endif
 
 static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
-						 const struct vdso_data *vd)
+						 const struct vdso_time_data *vd)
 {
 	return get_tb();
 }
 
-const struct vdso_data *__arch_get_vdso_data(void);
-
-#ifdef CONFIG_TIME_NS
-static __always_inline
-const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd)
-{
-	return (void *)vd + (1U << CONFIG_PAGE_SHIFT);
-}
-#endif
-
-static inline bool vdso_clocksource_ok(const struct vdso_data *vd)
+static inline bool vdso_clocksource_ok(const struct vdso_time_data *vd)
 {
 	return true;
 }
@@ -135,21 +125,22 @@ static __always_inline u64 vdso_shift_ns(u64 ns, unsigned long shift)
 
 #ifdef __powerpc64__
 int __c_kernel_clock_gettime(clockid_t clock, struct __kernel_timespec *ts,
-			     const struct vdso_data *vd);
+			     const struct vdso_time_data *vd);
 int __c_kernel_clock_getres(clockid_t clock_id, struct __kernel_timespec *res,
-			    const struct vdso_data *vd);
+			    const struct vdso_time_data *vd);
 #else
 int __c_kernel_clock_gettime(clockid_t clock, struct old_timespec32 *ts,
-			     const struct vdso_data *vd);
+			     const struct vdso_time_data *vd);
 int __c_kernel_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts,
-			       const struct vdso_data *vd);
+			       const struct vdso_time_data *vd);
 int __c_kernel_clock_getres(clockid_t clock_id, struct old_timespec32 *res,
-			    const struct vdso_data *vd);
+			    const struct vdso_time_data *vd);
 #endif
 int __c_kernel_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz,
-			    const struct vdso_data *vd);
+			    const struct vdso_time_data *vd);
 __kernel_old_time_t __c_kernel_time(__kernel_old_time_t *time,
-				    const struct vdso_data *vd);
+				    const struct vdso_time_data *vd);
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_POWERPC_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/powerpc/include/asm/vdso/vsyscall.h b/arch/powerpc/include/asm/vdso/vsyscall.h
index 48560a1195595..c2c9ae1b22e71 100644
--- a/arch/powerpc/include/asm/vdso/vsyscall.h
+++ b/arch/powerpc/include/asm/vdso/vsyscall.h
@@ -6,19 +6,6 @@
 
 #include <asm/vdso_datapage.h>
 
-static __always_inline
-struct vdso_data *__arch_get_k_vdso_data(void)
-{
-	return vdso_data->data;
-}
-#define __arch_get_k_vdso_data __arch_get_k_vdso_data
-
-static __always_inline
-struct vdso_rng_data *__arch_get_k_vdso_rng_data(void)
-{
-	return &vdso_data->rng_data;
-}
-
 /* The asm-generic header needs to be included after the definitions above */
 #include <asm-generic/vdso/vsyscall.h>
 
diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h
index a202f5b634795..95d45a50355d2 100644
--- a/arch/powerpc/include/asm/vdso_datapage.h
+++ b/arch/powerpc/include/asm/vdso_datapage.h
@@ -11,56 +11,18 @@
 
 #ifndef __ASSEMBLY__
 
-#include <linux/unistd.h>
-#include <linux/time.h>
 #include <vdso/datapage.h>
 
-#define SYSCALL_MAP_SIZE      ((NR_syscalls + 31) / 32)
-
-#ifdef CONFIG_PPC64
-
-struct vdso_arch_data {
-	__u64 tb_ticks_per_sec;			/* Timebase tics / sec */
-	__u32 dcache_block_size;		/* L1 d-cache block size     */
-	__u32 icache_block_size;		/* L1 i-cache block size     */
-	__u32 dcache_log_block_size;		/* L1 d-cache log block size */
-	__u32 icache_log_block_size;		/* L1 i-cache log block size */
-	__u32 syscall_map[SYSCALL_MAP_SIZE];	/* Map of syscalls  */
-	__u32 compat_syscall_map[SYSCALL_MAP_SIZE];	/* Map of compat syscalls */
-
-	struct vdso_rng_data rng_data;
-
-	struct vdso_data data[CS_BASES] __aligned(1 << CONFIG_PAGE_SHIFT);
-};
-
-#else /* CONFIG_PPC64 */
-
-struct vdso_arch_data {
-	__u64 tb_ticks_per_sec;		/* Timebase tics / sec */
-	__u32 syscall_map[SYSCALL_MAP_SIZE]; /* Map of syscalls */
-	__u32 compat_syscall_map[0];	/* No compat syscalls on PPC32 */
-	struct vdso_rng_data rng_data;
-
-	struct vdso_data data[CS_BASES] __aligned(1 << CONFIG_PAGE_SHIFT);
-};
-
-#endif /* CONFIG_PPC64 */
-
-extern struct vdso_arch_data *vdso_data;
-
 #else /* __ASSEMBLY__ */
 
-.macro get_datapage ptr offset=0
+.macro get_datapage ptr symbol
 	bcl	20, 31, .+4
 999:
 	mflr	\ptr
-	addis	\ptr, \ptr, (_vdso_datapage - 999b + \offset)@ha
-	addi	\ptr, \ptr, (_vdso_datapage - 999b + \offset)@l
+	addis	\ptr, \ptr, (\symbol - 999b)@ha
+	addi	\ptr, \ptr, (\symbol - 999b)@l
 .endm
 
-#include <asm/asm-offsets.h>
-#include <asm/page.h>
-
 #endif /* __ASSEMBLY__ */
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 7a390bd4f4af3..b3048f6d3822c 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -334,7 +334,6 @@ int main(void)
 #endif /* ! CONFIG_PPC64 */
 
 	/* datapage offsets for use by vdso */
-	OFFSET(VDSO_DATA_OFFSET, vdso_arch_data, data);
 	OFFSET(CFG_TB_TICKS_PER_SEC, vdso_arch_data, tb_ticks_per_sec);
 #ifdef CONFIG_PPC64
 	OFFSET(CFG_ICACHE_BLOCKSZ, vdso_arch_data, icache_block_size);
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 0727332ad86fb..15784c5c95c77 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -950,7 +950,7 @@ void __init time_init(void)
 		sys_tz.tz_dsttime = 0;
 	}
 
-	vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;
+	vdso_k_arch_data->tb_ticks_per_sec = tb_ticks_per_sec;
 #ifdef CONFIG_PPC64_PROC_SYSTEMCFG
 	systemcfg->tb_ticks_per_sec = tb_ticks_per_sec;
 #endif
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index 43379365ce1b3..219d67bcf747e 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -17,7 +17,7 @@
 #include <linux/elf.h>
 #include <linux/security.h>
 #include <linux/syscalls.h>
-#include <linux/time_namespace.h>
+#include <linux/vdso_datastore.h>
 #include <vdso/datapage.h>
 
 #include <asm/syscall.h>
@@ -32,6 +32,8 @@
 #include <asm/vdso_datapage.h>
 #include <asm/setup.h>
 
+static_assert(__VDSO_PAGES == VDSO_NR_PAGES);
+
 /* The alignment of the vDSO */
 #define VDSO_ALIGNMENT	(1 << 16)
 
@@ -40,24 +42,6 @@ extern char vdso64_start, vdso64_end;
 
 long sys_ni_syscall(void);
 
-/*
- * The vdso data page (aka. systemcfg for old ppc64 fans) is here.
- * Once the early boot kernel code no longer needs to muck around
- * with it, it will become dynamically allocated
- */
-static union {
-	struct vdso_arch_data	data;
-	u8			page[2 * PAGE_SIZE];
-} vdso_data_store __page_aligned_data;
-struct vdso_arch_data *vdso_data = &vdso_data_store.data;
-
-enum vvar_pages {
-	VVAR_BASE_PAGE_OFFSET,
-	VVAR_TIME_PAGE_OFFSET,
-	VVAR_TIMENS_PAGE_OFFSET,
-	VVAR_NR_PAGES,
-};
-
 static int vdso_mremap(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma,
 		       unsigned long text_size)
 {
@@ -96,14 +80,6 @@ static void vdso_close(const struct vm_special_mapping *sm, struct vm_area_struc
 	mm->context.vdso = NULL;
 }
 
-static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
-			     struct vm_area_struct *vma, struct vm_fault *vmf);
-
-static struct vm_special_mapping vvar_spec __ro_after_init = {
-	.name = "[vvar]",
-	.fault = vvar_fault,
-};
-
 static struct vm_special_mapping vdso32_spec __ro_after_init = {
 	.name = "[vdso]",
 	.mremap = vdso32_mremap,
@@ -116,73 +92,6 @@ static struct vm_special_mapping vdso64_spec __ro_after_init = {
 	.close = vdso_close,
 };
 
-#ifdef CONFIG_TIME_NS
-struct vdso_data *arch_get_vdso_data(void *vvar_page)
-{
-	return vvar_page;
-}
-
-/*
- * The vvar mapping contains data for a specific time namespace, so when a task
- * changes namespace we must unmap its vvar data for the old namespace.
- * Subsequent faults will map in data for the new namespace.
- *
- * For more details see timens_setup_vdso_data().
- */
-int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
-{
-	struct mm_struct *mm = task->mm;
-	VMA_ITERATOR(vmi, mm, 0);
-	struct vm_area_struct *vma;
-
-	mmap_read_lock(mm);
-	for_each_vma(vmi, vma) {
-		if (vma_is_special_mapping(vma, &vvar_spec))
-			zap_vma_pages(vma);
-	}
-	mmap_read_unlock(mm);
-
-	return 0;
-}
-#endif
-
-static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
-			     struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-	struct page *timens_page = find_timens_vvar_page(vma);
-	unsigned long pfn;
-
-	switch (vmf->pgoff) {
-	case VVAR_BASE_PAGE_OFFSET:
-		pfn = virt_to_pfn(vdso_data);
-		break;
-	case VVAR_TIME_PAGE_OFFSET:
-		if (timens_page)
-			pfn = page_to_pfn(timens_page);
-		else
-			pfn = virt_to_pfn(vdso_data->data);
-		break;
-#ifdef CONFIG_TIME_NS
-	case VVAR_TIMENS_PAGE_OFFSET:
-		/*
-		 * If a task belongs to a time namespace then a namespace
-		 * specific VVAR is mapped with the VVAR_DATA_PAGE_OFFSET and
-		 * the real VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET
-		 * offset.
-		 * See also the comment near timens_setup_vdso_data().
-		 */
-		if (!timens_page)
-			return VM_FAULT_SIGBUS;
-		pfn = virt_to_pfn(vdso_data->data);
-		break;
-#endif /* CONFIG_TIME_NS */
-	default:
-		return VM_FAULT_SIGBUS;
-	}
-
-	return vmf_insert_pfn(vma, vmf->address, pfn);
-}
-
 /*
  * This is called from binfmt_elf, we create the special vma for the
  * vDSO and insert it into the mm struct tree
@@ -191,7 +100,7 @@ static int __arch_setup_additional_pages(struct linux_binprm *bprm, int uses_int
 {
 	unsigned long vdso_size, vdso_base, mappings_size;
 	struct vm_special_mapping *vdso_spec;
-	unsigned long vvar_size = VVAR_NR_PAGES * PAGE_SIZE;
+	unsigned long vvar_size = VDSO_NR_PAGES * PAGE_SIZE;
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 
@@ -217,9 +126,7 @@ static int __arch_setup_additional_pages(struct linux_binprm *bprm, int uses_int
 	/* Add required alignment. */
 	vdso_base = ALIGN(vdso_base, VDSO_ALIGNMENT);
 
-	vma = _install_special_mapping(mm, vdso_base, vvar_size,
-				       VM_READ | VM_MAYREAD | VM_IO |
-				       VM_DONTDUMP | VM_PFNMAP, &vvar_spec);
+	vma = vdso_install_vvar_mapping(mm, vdso_base);
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
@@ -299,10 +206,10 @@ static void __init vdso_setup_syscall_map(void)
 
 	for (i = 0; i < NR_syscalls; i++) {
 		if (sys_call_table[i] != (void *)&sys_ni_syscall)
-			vdso_data->syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f);
+			vdso_k_arch_data->syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f);
 		if (IS_ENABLED(CONFIG_COMPAT) &&
 		    compat_sys_call_table[i] != (void *)&sys_ni_syscall)
-			vdso_data->compat_syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f);
+			vdso_k_arch_data->compat_syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f);
 	}
 }
 
@@ -352,10 +259,10 @@ static struct page ** __init vdso_setup_pages(void *start, void *end)
 static int __init vdso_init(void)
 {
 #ifdef CONFIG_PPC64
-	vdso_data->dcache_block_size = ppc64_caches.l1d.block_size;
-	vdso_data->icache_block_size = ppc64_caches.l1i.block_size;
-	vdso_data->dcache_log_block_size = ppc64_caches.l1d.log_block_size;
-	vdso_data->icache_log_block_size = ppc64_caches.l1i.log_block_size;
+	vdso_k_arch_data->dcache_block_size = ppc64_caches.l1d.block_size;
+	vdso_k_arch_data->icache_block_size = ppc64_caches.l1i.block_size;
+	vdso_k_arch_data->dcache_log_block_size = ppc64_caches.l1d.log_block_size;
+	vdso_k_arch_data->icache_log_block_size = ppc64_caches.l1i.log_block_size;
 #endif /* CONFIG_PPC64 */
 
 	vdso_setup_syscall_map();
diff --git a/arch/powerpc/kernel/vdso/cacheflush.S b/arch/powerpc/kernel/vdso/cacheflush.S
index 0085ae464dac9..488d3ade11e64 100644
--- a/arch/powerpc/kernel/vdso/cacheflush.S
+++ b/arch/powerpc/kernel/vdso/cacheflush.S
@@ -30,7 +30,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
 #ifdef CONFIG_PPC64
 	mflr	r12
   .cfi_register lr,r12
-	get_datapage	r10
+	get_datapage	r10 vdso_u_arch_data
 	mtlr	r12
   .cfi_restore	lr
 #endif
diff --git a/arch/powerpc/kernel/vdso/datapage.S b/arch/powerpc/kernel/vdso/datapage.S
index db8e167f01667..d23b2e8e2a34c 100644
--- a/arch/powerpc/kernel/vdso/datapage.S
+++ b/arch/powerpc/kernel/vdso/datapage.S
@@ -28,7 +28,7 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map)
 	mflr	r12
   .cfi_register lr,r12
 	mr.	r4,r3
-	get_datapage	r3
+	get_datapage	r3 vdso_u_arch_data
 	mtlr	r12
 #ifdef __powerpc64__
 	addi	r3,r3,CFG_SYSCALL_MAP64
@@ -52,7 +52,7 @@ V_FUNCTION_BEGIN(__kernel_get_tbfreq)
   .cfi_startproc
 	mflr	r12
   .cfi_register lr,r12
-	get_datapage	r3
+	get_datapage	r3 vdso_u_arch_data
 #ifndef __powerpc64__
 	lwz	r4,(CFG_TB_TICKS_PER_SEC + 4)(r3)
 #endif
diff --git a/arch/powerpc/kernel/vdso/gettimeofday.S b/arch/powerpc/kernel/vdso/gettimeofday.S
index 5333848322ca6..79c9672124447 100644
--- a/arch/powerpc/kernel/vdso/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso/gettimeofday.S
@@ -33,9 +33,9 @@
   .cfi_rel_offset r2, PPC_MIN_STKFRM + STK_GOT
 #endif
 	.ifeq	\call_time
-		get_datapage	r5 VDSO_DATA_OFFSET
+		get_datapage	r5 vdso_u_time_data
 	.else
-		get_datapage	r4 VDSO_DATA_OFFSET
+		get_datapage	r4 vdso_u_time_data
 	.endif
 	bl		CFUNC(DOTSYM(\funct))
 	PPC_LL		r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1)
diff --git a/arch/powerpc/kernel/vdso/vdso32.lds.S b/arch/powerpc/kernel/vdso/vdso32.lds.S
index 1a1b0b6d681a9..72a1012b8a205 100644
--- a/arch/powerpc/kernel/vdso/vdso32.lds.S
+++ b/arch/powerpc/kernel/vdso/vdso32.lds.S
@@ -6,6 +6,7 @@
 #include <asm/vdso.h>
 #include <asm/page.h>
 #include <asm-generic/vmlinux.lds.h>
+#include <vdso/datapage.h>
 
 #ifdef __LITTLE_ENDIAN__
 OUTPUT_FORMAT("elf32-powerpcle", "elf32-powerpcle", "elf32-powerpcle")
@@ -16,7 +17,8 @@ OUTPUT_ARCH(powerpc:common)
 
 SECTIONS
 {
-	PROVIDE(_vdso_datapage = . - 3 * PAGE_SIZE);
+	VDSO_VVAR_SYMS
+
 	. = SIZEOF_HEADERS;
 
 	.hash          	: { *(.hash) }			:text
diff --git a/arch/powerpc/kernel/vdso/vdso64.lds.S b/arch/powerpc/kernel/vdso/vdso64.lds.S
index e21b5506cad62..32102a05eaa7e 100644
--- a/arch/powerpc/kernel/vdso/vdso64.lds.S
+++ b/arch/powerpc/kernel/vdso/vdso64.lds.S
@@ -6,6 +6,7 @@
 #include <asm/vdso.h>
 #include <asm/page.h>
 #include <asm-generic/vmlinux.lds.h>
+#include <vdso/datapage.h>
 
 #ifdef __LITTLE_ENDIAN__
 OUTPUT_FORMAT("elf64-powerpcle", "elf64-powerpcle", "elf64-powerpcle")
@@ -16,7 +17,8 @@ OUTPUT_ARCH(powerpc:common64)
 
 SECTIONS
 {
-	PROVIDE(_vdso_datapage = . - 3 * PAGE_SIZE);
+	VDSO_VVAR_SYMS
+
 	. = SIZEOF_HEADERS;
 
 	.hash		: { *(.hash) }			:text
diff --git a/arch/powerpc/kernel/vdso/vgettimeofday.c b/arch/powerpc/kernel/vdso/vgettimeofday.c
index 55a287c9a7366..6f5167d81af5f 100644
--- a/arch/powerpc/kernel/vdso/vgettimeofday.c
+++ b/arch/powerpc/kernel/vdso/vgettimeofday.c
@@ -7,43 +7,43 @@
 
 #ifdef __powerpc64__
 int __c_kernel_clock_gettime(clockid_t clock, struct __kernel_timespec *ts,
-			     const struct vdso_data *vd)
+			     const struct vdso_time_data *vd)
 {
 	return __cvdso_clock_gettime_data(vd, clock, ts);
 }
 
 int __c_kernel_clock_getres(clockid_t clock_id, struct __kernel_timespec *res,
-			    const struct vdso_data *vd)
+			    const struct vdso_time_data *vd)
 {
 	return __cvdso_clock_getres_data(vd, clock_id, res);
 }
 #else
 int __c_kernel_clock_gettime(clockid_t clock, struct old_timespec32 *ts,
-			     const struct vdso_data *vd)
+			     const struct vdso_time_data *vd)
 {
 	return __cvdso_clock_gettime32_data(vd, clock, ts);
 }
 
 int __c_kernel_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts,
-			       const struct vdso_data *vd)
+			       const struct vdso_time_data *vd)
 {
 	return __cvdso_clock_gettime_data(vd, clock, ts);
 }
 
 int __c_kernel_clock_getres(clockid_t clock_id, struct old_timespec32 *res,
-			    const struct vdso_data *vd)
+			    const struct vdso_time_data *vd)
 {
 	return __cvdso_clock_getres_time32_data(vd, clock_id, res);
 }
 #endif
 
 int __c_kernel_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz,
-			    const struct vdso_data *vd)
+			    const struct vdso_time_data *vd)
 {
 	return __cvdso_gettimeofday_data(vd, tv, tz);
 }
 
-__kernel_old_time_t __c_kernel_time(__kernel_old_time_t *time, const struct vdso_data *vd)
+__kernel_old_time_t __c_kernel_time(__kernel_old_time_t *time, const struct vdso_time_data *vd)
 {
 	return __cvdso_time_data(vd, time);
 }

From dafde29605ebf214747e7602f4f22d3f617373a5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Tue, 4 Feb 2025 13:05:47 +0100
Subject: [PATCH 0450/1173] x86/vdso: Switch to generic storage implementation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The generic storage implementation provides the same features as the
custom one. However it can be shared between architectures, making
maintenance easier.

This switch also moves the random state data out of the time data page.
The currently used hardcoded __VDSO_RND_DATA_OFFSET does not take into
account changes to the time data page layout.

Co-developed-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250204-vdso-store-rng-v3-15-13a4669dfc8c@linutronix.de
---
 arch/x86/Kconfig                         |   1 +
 arch/x86/entry/vdso/vdso-layout.lds.S    |  14 +--
 arch/x86/entry/vdso/vma.c                | 123 ++---------------------
 arch/x86/include/asm/vdso/getrandom.h    |  10 --
 arch/x86/include/asm/vdso/gettimeofday.h |  25 +----
 arch/x86/include/asm/vdso/vsyscall.h     |  24 +----
 6 files changed, 19 insertions(+), 178 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 87198d957e2f1..e66ffd941d17d 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -178,6 +178,7 @@ config X86
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_TIME_VSYSCALL
 	select GENERIC_GETTIMEOFDAY
+	select GENERIC_VDSO_DATA_STORE
 	select GENERIC_VDSO_TIME_NS
 	select GENERIC_VDSO_OVERFLOW_PROTECT
 	select GUP_GET_PXX_LOW_HIGH		if X86_PAE
diff --git a/arch/x86/entry/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S
index 918606ff92a98..e5cecdb0fedf0 100644
--- a/arch/x86/entry/vdso/vdso-layout.lds.S
+++ b/arch/x86/entry/vdso/vdso-layout.lds.S
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <asm/vdso.h>
 #include <asm/vdso/vsyscall.h>
+#include <vdso/datapage.h>
 
 /*
  * Linker script for vDSO.  This is an ELF shared object prelinked to
@@ -17,17 +18,16 @@ SECTIONS
 	 * segment.
 	 */
 
-	vvar_start = . - __VVAR_PAGES * PAGE_SIZE;
-	vvar_page  = vvar_start;
+	VDSO_VVAR_SYMS
 
-	vdso_rng_data = vvar_page + __VDSO_RND_DATA_OFFSET;
-
-	timens_page  = vvar_start + PAGE_SIZE;
-
-	vclock_pages = VDSO_VCLOCK_PAGES_START(vvar_start);
+	vclock_pages = VDSO_VCLOCK_PAGES_START(vdso_u_data);
 	pvclock_page = vclock_pages + VDSO_PAGE_PVCLOCK_OFFSET * PAGE_SIZE;
 	hvclock_page = vclock_pages + VDSO_PAGE_HVCLOCK_OFFSET * PAGE_SIZE;
 
+	/* For compatibility with vdso2c */
+	vvar_page = vdso_u_data;
+	vvar_start = vdso_u_data;
+
 	. = SIZEOF_HEADERS;
 
 	.hash		: { *(.hash) }			:text
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index aa62949335ece..7245e95c573e1 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -14,7 +14,7 @@
 #include <linux/elf.h>
 #include <linux/cpu.h>
 #include <linux/ptrace.h>
-#include <linux/time_namespace.h>
+#include <linux/vdso_datastore.h>
 
 #include <asm/pvclock.h>
 #include <asm/vgtod.h>
@@ -27,13 +27,7 @@
 #include <asm/vdso/vsyscall.h>
 #include <clocksource/hyperv_timer.h>
 
-struct vdso_data *arch_get_vdso_data(void *vvar_page)
-{
-	return (struct vdso_data *)vvar_page;
-}
-
-static union vdso_data_store vdso_data_store __page_aligned_data;
-struct vdso_data *vdso_data = vdso_data_store.data;
+static_assert(VDSO_NR_PAGES + VDSO_NR_VCLOCK_PAGES == __VDSO_PAGES);
 
 unsigned int vclocks_used __read_mostly;
 
@@ -54,7 +48,6 @@ int __init init_vdso_image(const struct vdso_image *image)
 	return 0;
 }
 
-static const struct vm_special_mapping vvar_mapping;
 struct linux_binprm;
 
 static vm_fault_t vdso_fault(const struct vm_special_mapping *sm,
@@ -98,99 +91,6 @@ static int vdso_mremap(const struct vm_special_mapping *sm,
 	return 0;
 }
 
-#ifdef CONFIG_TIME_NS
-/*
- * The vvar page layout depends on whether a task belongs to the root or
- * non-root time namespace. Whenever a task changes its namespace, the VVAR
- * page tables are cleared and then they will re-faulted with a
- * corresponding layout.
- * See also the comment near timens_setup_vdso_data() for details.
- */
-int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
-{
-	struct mm_struct *mm = task->mm;
-	struct vm_area_struct *vma;
-	VMA_ITERATOR(vmi, mm, 0);
-
-	mmap_read_lock(mm);
-	for_each_vma(vmi, vma) {
-		if (vma_is_special_mapping(vma, &vvar_mapping))
-			zap_vma_pages(vma);
-	}
-	mmap_read_unlock(mm);
-
-	return 0;
-}
-#endif
-
-static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
-		      struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-	const struct vdso_image *image = vma->vm_mm->context.vdso_image;
-	unsigned long pfn;
-	long sym_offset;
-
-	if (!image)
-		return VM_FAULT_SIGBUS;
-
-	sym_offset = (long)(vmf->pgoff << PAGE_SHIFT) +
-		image->sym_vvar_start;
-
-	/*
-	 * Sanity check: a symbol offset of zero means that the page
-	 * does not exist for this vdso image, not that the page is at
-	 * offset zero relative to the text mapping.  This should be
-	 * impossible here, because sym_offset should only be zero for
-	 * the page past the end of the vvar mapping.
-	 */
-	if (sym_offset == 0)
-		return VM_FAULT_SIGBUS;
-
-	if (sym_offset == image->sym_vvar_page) {
-		struct page *timens_page = find_timens_vvar_page(vma);
-
-		pfn = __pa_symbol(vdso_data) >> PAGE_SHIFT;
-
-		/*
-		 * If a task belongs to a time namespace then a namespace
-		 * specific VVAR is mapped with the sym_vvar_page offset and
-		 * the real VVAR page is mapped with the sym_timens_page
-		 * offset.
-		 * See also the comment near timens_setup_vdso_data().
-		 */
-		if (timens_page) {
-			unsigned long addr;
-			vm_fault_t err;
-
-			/*
-			 * Optimization: inside time namespace pre-fault
-			 * VVAR page too. As on timens page there are only
-			 * offsets for clocks on VVAR, it'll be faulted
-			 * shortly by VDSO code.
-			 */
-			addr = vmf->address + (image->sym_timens_page - sym_offset);
-			err = vmf_insert_pfn(vma, addr, pfn);
-			if (unlikely(err & VM_FAULT_ERROR))
-				return err;
-
-			pfn = page_to_pfn(timens_page);
-		}
-
-		return vmf_insert_pfn(vma, vmf->address, pfn);
-
-	} else if (sym_offset == image->sym_timens_page) {
-		struct page *timens_page = find_timens_vvar_page(vma);
-
-		if (!timens_page)
-			return VM_FAULT_SIGBUS;
-
-		pfn = __pa_symbol(vdso_data) >> PAGE_SHIFT;
-		return vmf_insert_pfn(vma, vmf->address, pfn);
-	}
-
-	return VM_FAULT_SIGBUS;
-}
-
 static vm_fault_t vvar_vclock_fault(const struct vm_special_mapping *sm,
 				    struct vm_area_struct *vma, struct vm_fault *vmf)
 {
@@ -212,7 +112,6 @@ static vm_fault_t vvar_vclock_fault(const struct vm_special_mapping *sm,
 	case VDSO_PAGE_HVCLOCK_OFFSET:
 	{
 		unsigned long pfn = hv_get_tsc_pfn();
-
 		if (pfn && vclock_was_used(VDSO_CLOCKMODE_HVCLOCK))
 			return vmf_insert_pfn(vma, vmf->address, pfn);
 		break;
@@ -228,10 +127,6 @@ static const struct vm_special_mapping vdso_mapping = {
 	.fault = vdso_fault,
 	.mremap = vdso_mremap,
 };
-static const struct vm_special_mapping vvar_mapping = {
-	.name = "[vvar]",
-	.fault = vvar_fault,
-};
 static const struct vm_special_mapping vvar_vclock_mapping = {
 	.name = "[vvar_vclock]",
 	.fault = vvar_vclock_fault,
@@ -253,13 +148,13 @@ static int map_vdso(const struct vdso_image *image, unsigned long addr)
 		return -EINTR;
 
 	addr = get_unmapped_area(NULL, addr,
-				 image->size - image->sym_vvar_start, 0, 0);
+				 image->size + __VDSO_PAGES * PAGE_SIZE, 0, 0);
 	if (IS_ERR_VALUE(addr)) {
 		ret = addr;
 		goto up_fail;
 	}
 
-	text_start = addr - image->sym_vvar_start;
+	text_start = addr + __VDSO_PAGES * PAGE_SIZE;
 
 	/*
 	 * MAYWRITE to allow gdb to COW and set breakpoints
@@ -276,13 +171,7 @@ static int map_vdso(const struct vdso_image *image, unsigned long addr)
 		goto up_fail;
 	}
 
-	vma = _install_special_mapping(mm,
-				       addr,
-				       (__VVAR_PAGES - VDSO_NR_VCLOCK_PAGES) * PAGE_SIZE,
-				       VM_READ|VM_MAYREAD|VM_IO|VM_DONTDUMP|
-				       VM_PFNMAP,
-				       &vvar_mapping);
-
+	vma = vdso_install_vvar_mapping(mm, addr);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		do_munmap(mm, text_start, image->size, NULL);
@@ -327,7 +216,7 @@ int map_vdso_once(const struct vdso_image *image, unsigned long addr)
 	 */
 	for_each_vma(vmi, vma) {
 		if (vma_is_special_mapping(vma, &vdso_mapping) ||
-				vma_is_special_mapping(vma, &vvar_mapping) ||
+				vma_is_special_mapping(vma, &vdso_vvar_mapping) ||
 				vma_is_special_mapping(vma, &vvar_vclock_mapping)) {
 			mmap_write_unlock(mm);
 			return -EEXIST;
diff --git a/arch/x86/include/asm/vdso/getrandom.h b/arch/x86/include/asm/vdso/getrandom.h
index 2bf9c0e970c3e..af85539f6557b 100644
--- a/arch/x86/include/asm/vdso/getrandom.h
+++ b/arch/x86/include/asm/vdso/getrandom.h
@@ -27,16 +27,6 @@ static __always_inline ssize_t getrandom_syscall(void *buffer, size_t len, unsig
 	return ret;
 }
 
-extern struct vdso_rng_data vdso_rng_data
-	__attribute__((visibility("hidden")));
-
-static __always_inline const struct vdso_rng_data *__arch_get_vdso_rng_data(void)
-{
-	if (IS_ENABLED(CONFIG_TIME_NS) && __arch_get_vdso_data()->clock_mode == VDSO_CLOCKMODE_TIMENS)
-		return (void *)&vdso_rng_data + ((void *)&timens_page - (void *)__arch_get_vdso_data());
-	return &vdso_rng_data;
-}
-
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_VDSO_GETRANDOM_H */
diff --git a/arch/x86/include/asm/vdso/gettimeofday.h b/arch/x86/include/asm/vdso/gettimeofday.h
index 375a34b0f3657..edec796832e08 100644
--- a/arch/x86/include/asm/vdso/gettimeofday.h
+++ b/arch/x86/include/asm/vdso/gettimeofday.h
@@ -19,12 +19,6 @@
 #include <asm/pvclock.h>
 #include <clocksource/hyperv_timer.h>
 
-extern struct vdso_data vvar_page
-	__attribute__((visibility("hidden")));
-
-extern struct vdso_data timens_page
-	__attribute__((visibility("hidden")));
-
 #define VDSO_HAS_TIME 1
 
 #define VDSO_HAS_CLOCK_GETRES 1
@@ -59,14 +53,6 @@ extern struct ms_hyperv_tsc_page hvclock_page
 	__attribute__((visibility("hidden")));
 #endif
 
-#ifdef CONFIG_TIME_NS
-static __always_inline
-const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd)
-{
-	return &timens_page;
-}
-#endif
-
 #ifndef BUILD_VDSO32
 
 static __always_inline
@@ -250,7 +236,7 @@ static u64 vread_hvclock(void)
 #endif
 
 static inline u64 __arch_get_hw_counter(s32 clock_mode,
-					const struct vdso_data *vd)
+					const struct vdso_time_data *vd)
 {
 	if (likely(clock_mode == VDSO_CLOCKMODE_TSC))
 		return (u64)rdtsc_ordered() & S64_MAX;
@@ -275,12 +261,7 @@ static inline u64 __arch_get_hw_counter(s32 clock_mode,
 	return U64_MAX;
 }
 
-static __always_inline const struct vdso_data *__arch_get_vdso_data(void)
-{
-	return &vvar_page;
-}
-
-static inline bool arch_vdso_clocksource_ok(const struct vdso_data *vd)
+static inline bool arch_vdso_clocksource_ok(const struct vdso_time_data *vd)
 {
 	return true;
 }
@@ -319,7 +300,7 @@ static inline bool arch_vdso_cycles_ok(u64 cycles)
  * declares everything with the MSB/Sign-bit set as invalid. Therefore the
  * effective mask is S64_MAX.
  */
-static __always_inline u64 vdso_calc_ns(const struct vdso_data *vd, u64 cycles, u64 base)
+static __always_inline u64 vdso_calc_ns(const struct vdso_time_data *vd, u64 cycles, u64 base)
 {
 	u64 delta = cycles - vd->cycle_last;
 
diff --git a/arch/x86/include/asm/vdso/vsyscall.h b/arch/x86/include/asm/vdso/vsyscall.h
index 88b31d4cdfaf3..ebbf63420af03 100644
--- a/arch/x86/include/asm/vdso/vsyscall.h
+++ b/arch/x86/include/asm/vdso/vsyscall.h
@@ -2,11 +2,10 @@
 #ifndef __ASM_VDSO_VSYSCALL_H
 #define __ASM_VDSO_VSYSCALL_H
 
-#define __VDSO_RND_DATA_OFFSET  640
-#define __VVAR_PAGES	4
+#define __VDSO_PAGES	6
 
 #define VDSO_NR_VCLOCK_PAGES	2
-#define VDSO_VCLOCK_PAGES_START(_b)	((_b) + (__VVAR_PAGES - VDSO_NR_VCLOCK_PAGES) * PAGE_SIZE)
+#define VDSO_VCLOCK_PAGES_START(_b)	((_b) + (__VDSO_PAGES - VDSO_NR_VCLOCK_PAGES) * PAGE_SIZE)
 #define VDSO_PAGE_PVCLOCK_OFFSET	0
 #define VDSO_PAGE_HVCLOCK_OFFSET	1
 
@@ -15,25 +14,6 @@
 #include <vdso/datapage.h>
 #include <asm/vgtod.h>
 
-extern struct vdso_data *vdso_data;
-
-/*
- * Update the vDSO data page to keep in sync with kernel timekeeping.
- */
-static __always_inline
-struct vdso_data *__x86_get_k_vdso_data(void)
-{
-	return vdso_data;
-}
-#define __arch_get_k_vdso_data __x86_get_k_vdso_data
-
-static __always_inline
-struct vdso_rng_data *__x86_get_k_vdso_rng_data(void)
-{
-	return (void *)vdso_data + __VDSO_RND_DATA_OFFSET;
-}
-#define __arch_get_k_vdso_rng_data __x86_get_k_vdso_rng_data
-
 /* The asm-generic header needs to be included after the definitions above */
 #include <asm-generic/vdso/vsyscall.h>
 

From 9729dceab17bba8a122e26875f05d291b969ce7c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Tue, 4 Feb 2025 13:05:48 +0100
Subject: [PATCH 0451/1173] x86/vdso/vdso2c: Remove page handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The values are not used anymore.
Also the sanity checks performed by vdso2c can never trigger as they
only validate invariants already enforced by the linker script.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250204-vdso-store-rng-v3-16-13a4669dfc8c@linutronix.de
---
 arch/x86/entry/vdso/vdso-layout.lds.S |  4 ----
 arch/x86/entry/vdso/vdso2c.c          | 21 ---------------------
 arch/x86/entry/vdso/vdso2c.h          | 20 --------------------
 arch/x86/include/asm/vdso.h           |  6 ------
 4 files changed, 51 deletions(-)

diff --git a/arch/x86/entry/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S
index e5cecdb0fedf0..ec1ac191a0578 100644
--- a/arch/x86/entry/vdso/vdso-layout.lds.S
+++ b/arch/x86/entry/vdso/vdso-layout.lds.S
@@ -24,10 +24,6 @@ SECTIONS
 	pvclock_page = vclock_pages + VDSO_PAGE_PVCLOCK_OFFSET * PAGE_SIZE;
 	hvclock_page = vclock_pages + VDSO_PAGE_HVCLOCK_OFFSET * PAGE_SIZE;
 
-	/* For compatibility with vdso2c */
-	vvar_page = vdso_u_data;
-	vvar_start = vdso_u_data;
-
 	. = SIZEOF_HEADERS;
 
 	.hash		: { *(.hash) }			:text
diff --git a/arch/x86/entry/vdso/vdso2c.c b/arch/x86/entry/vdso/vdso2c.c
index 90d15f2a72055..f84e8f8fa5fe6 100644
--- a/arch/x86/entry/vdso/vdso2c.c
+++ b/arch/x86/entry/vdso/vdso2c.c
@@ -69,33 +69,12 @@
 
 const char *outfilename;
 
-/* Symbols that we need in vdso2c. */
-enum {
-	sym_vvar_start,
-	sym_vvar_page,
-	sym_pvclock_page,
-	sym_hvclock_page,
-	sym_timens_page,
-};
-
-const int special_pages[] = {
-	sym_vvar_page,
-	sym_pvclock_page,
-	sym_hvclock_page,
-	sym_timens_page,
-};
-
 struct vdso_sym {
 	const char *name;
 	bool export;
 };
 
 struct vdso_sym required_syms[] = {
-	[sym_vvar_start] = {"vvar_start", true},
-	[sym_vvar_page] = {"vvar_page", true},
-	[sym_pvclock_page] = {"pvclock_page", true},
-	[sym_hvclock_page] = {"hvclock_page", true},
-	[sym_timens_page] = {"timens_page", true},
 	{"VDSO32_NOTE_MASK", true},
 	{"__kernel_vsyscall", true},
 	{"__kernel_sigreturn", true},
diff --git a/arch/x86/entry/vdso/vdso2c.h b/arch/x86/entry/vdso/vdso2c.h
index 67b3e37576a64..78ed1c1f28b92 100644
--- a/arch/x86/entry/vdso/vdso2c.h
+++ b/arch/x86/entry/vdso/vdso2c.h
@@ -150,26 +150,6 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
 		}
 	}
 
-	/* Validate mapping addresses. */
-	for (i = 0; i < sizeof(special_pages) / sizeof(special_pages[0]); i++) {
-		INT_BITS symval = syms[special_pages[i]];
-
-		if (!symval)
-			continue;  /* The mapping isn't used; ignore it. */
-
-		if (symval % 4096)
-			fail("%s must be a multiple of 4096\n",
-			     required_syms[i].name);
-		if (symval + 4096 < syms[sym_vvar_start])
-			fail("%s underruns vvar_start\n",
-			     required_syms[i].name);
-		if (symval + 4096 > 0)
-			fail("%s is on the wrong side of the vdso text\n",
-			     required_syms[i].name);
-	}
-	if (syms[sym_vvar_start] % 4096)
-		fail("vvar_begin must be a multiple of 4096\n");
-
 	if (!image_name) {
 		fwrite(stripped_addr, stripped_len, 1, outfile);
 		return;
diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h
index d7f6592b74a94..80be0da733df4 100644
--- a/arch/x86/include/asm/vdso.h
+++ b/arch/x86/include/asm/vdso.h
@@ -18,12 +18,6 @@ struct vdso_image {
 	unsigned long extable_base, extable_len;
 	const void *extable;
 
-	long sym_vvar_start;  /* Negative offset to the vvar area */
-
-	long sym_vvar_page;
-	long sym_pvclock_page;
-	long sym_hvclock_page;
-	long sym_timens_page;
 	long sym_VDSO32_NOTE_MASK;
 	long sym___kernel_sigreturn;
 	long sym___kernel_rt_sigreturn;

From 998a8a2608199fc07c3a49200c73708e9df01e0f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Tue, 4 Feb 2025 13:05:49 +0100
Subject: [PATCH 0452/1173] vdso: Remove remnants of architecture-specific
 random state storage
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

All users of the random vDSO are using the generic storage
implementation. Remove the now unnecessary compatibility accessor
functions and symbols.

Co-developed-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250204-vdso-store-rng-v3-17-13a4669dfc8c@linutronix.de
---
 include/asm-generic/vdso/vsyscall.h | 5 -----
 include/vdso/datapage.h             | 1 -
 2 files changed, 6 deletions(-)

diff --git a/include/asm-generic/vdso/vsyscall.h b/include/asm-generic/vdso/vsyscall.h
index a5f973e4e2723..13e2ac3736ee9 100644
--- a/include/asm-generic/vdso/vsyscall.h
+++ b/include/asm-generic/vdso/vsyscall.h
@@ -32,11 +32,6 @@ static __always_inline struct vdso_data *__arch_get_k_vdso_data(void)
 
 #define __arch_get_vdso_u_time_data __arch_get_vdso_data
 
-#ifndef __arch_get_vdso_u_rng_data
-#define __arch_get_vdso_u_rng_data() __arch_get_vdso_rng_data()
-#endif
-#define vdso_k_rng_data __arch_get_k_vdso_rng_data()
-
 #endif /* CONFIG_GENERIC_VDSO_DATA_STORE */
 
 #ifndef __arch_update_vsyscall
diff --git a/include/vdso/datapage.h b/include/vdso/datapage.h
index 46658b39c2825..497907c3aa11f 100644
--- a/include/vdso/datapage.h
+++ b/include/vdso/datapage.h
@@ -152,7 +152,6 @@ struct vdso_rng_data {
 #ifndef CONFIG_GENERIC_VDSO_DATA_STORE
 extern struct vdso_time_data _vdso_data[CS_BASES] __attribute__((visibility("hidden")));
 extern struct vdso_time_data _timens_data[CS_BASES] __attribute__((visibility("hidden")));
-extern struct vdso_rng_data _vdso_rng_data __attribute__((visibility("hidden")));
 #else
 extern struct vdso_time_data vdso_u_time_data[CS_BASES] __attribute__((visibility("hidden")));
 extern struct vdso_rng_data vdso_u_rng_data __attribute__((visibility("hidden")));

From ac1a42f4e4e296b5ba5fdb39444f65d6e5196240 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Tue, 4 Feb 2025 13:05:50 +0100
Subject: [PATCH 0453/1173] vdso: Remove remnants of architecture-specific time
 storage
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

All users of the time releated parts of the vDSO are now using the generic
storage implementation. Remove the therefore unnecessary compatibility
accessor functions and symbols.

Co-developed-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250204-vdso-store-rng-v3-18-13a4669dfc8c@linutronix.de
---
 include/asm-generic/vdso/vsyscall.h | 20 +++--------
 include/linux/time_namespace.h      |  3 --
 include/vdso/datapage.h             | 19 +----------
 include/vdso/helpers.h              |  8 ++---
 kernel/time/namespace.c             | 12 +++----
 kernel/time/vsyscall.c              | 19 +++++------
 lib/vdso/datastore.c                | 10 +++---
 lib/vdso/gettimeofday.c             | 51 ++++++++++++++---------------
 8 files changed, 53 insertions(+), 89 deletions(-)

diff --git a/include/asm-generic/vdso/vsyscall.h b/include/asm-generic/vdso/vsyscall.h
index 13e2ac3736ee9..1fb3000f50364 100644
--- a/include/asm-generic/vdso/vsyscall.h
+++ b/include/asm-generic/vdso/vsyscall.h
@@ -20,31 +20,19 @@ static __always_inline const struct vdso_rng_data *__arch_get_vdso_u_rng_data(vo
 }
 #endif
 
-#else  /* !CONFIG_GENERIC_VDSO_DATA_STORE */
-
-#ifndef __arch_get_k_vdso_data
-static __always_inline struct vdso_data *__arch_get_k_vdso_data(void)
-{
-	return NULL;
-}
-#endif /* __arch_get_k_vdso_data */
-#define vdso_k_time_data __arch_get_k_vdso_data()
-
-#define __arch_get_vdso_u_time_data __arch_get_vdso_data
-
 #endif /* CONFIG_GENERIC_VDSO_DATA_STORE */
 
 #ifndef __arch_update_vsyscall
-static __always_inline void __arch_update_vsyscall(struct vdso_data *vdata)
+static __always_inline void __arch_update_vsyscall(struct vdso_time_data *vdata)
 {
 }
 #endif /* __arch_update_vsyscall */
 
-#ifndef __arch_sync_vdso_data
-static __always_inline void __arch_sync_vdso_data(struct vdso_data *vdata)
+#ifndef __arch_sync_vdso_time_data
+static __always_inline void __arch_sync_vdso_time_data(struct vdso_time_data *vdata)
 {
 }
-#endif /* __arch_sync_vdso_data */
+#endif /* __arch_sync_vdso_time_data */
 
 #endif /* !__ASSEMBLY__ */
 
diff --git a/include/linux/time_namespace.h b/include/linux/time_namespace.h
index 4b81db223f545..0b8b32bf06551 100644
--- a/include/linux/time_namespace.h
+++ b/include/linux/time_namespace.h
@@ -8,7 +8,6 @@
 #include <linux/ns_common.h>
 #include <linux/err.h>
 #include <linux/time64.h>
-#include <vdso/datapage.h>
 
 struct user_namespace;
 extern struct user_namespace init_user_ns;
@@ -166,6 +165,4 @@ static inline ktime_t timens_ktime_to_host(clockid_t clockid, ktime_t tim)
 }
 #endif
 
-struct vdso_data *arch_get_vdso_data(void *vvar_page);
-
 #endif /* _LINUX_TIMENS_H */
diff --git a/include/vdso/datapage.h b/include/vdso/datapage.h
index 497907c3aa11f..ed4fb4c06e3ee 100644
--- a/include/vdso/datapage.h
+++ b/include/vdso/datapage.h
@@ -128,8 +128,6 @@ struct vdso_time_data {
 	struct arch_vdso_time_data arch_data;
 };
 
-#define vdso_data vdso_time_data
-
 /**
  * struct vdso_rng_data - vdso RNG state information
  * @generation:	counter representing the number of RNG reseeds
@@ -149,10 +147,7 @@ struct vdso_rng_data {
  * With the hidden visibility, the compiler simply generates a PC-relative
  * relocation, and this is what we need.
  */
-#ifndef CONFIG_GENERIC_VDSO_DATA_STORE
-extern struct vdso_time_data _vdso_data[CS_BASES] __attribute__((visibility("hidden")));
-extern struct vdso_time_data _timens_data[CS_BASES] __attribute__((visibility("hidden")));
-#else
+#ifdef CONFIG_GENERIC_VDSO_DATA_STORE
 extern struct vdso_time_data vdso_u_time_data[CS_BASES] __attribute__((visibility("hidden")));
 extern struct vdso_rng_data vdso_u_rng_data __attribute__((visibility("hidden")));
 extern struct vdso_arch_data vdso_u_arch_data __attribute__((visibility("hidden")));
@@ -160,17 +155,6 @@ extern struct vdso_arch_data vdso_u_arch_data __attribute__((visibility("hidden"
 extern struct vdso_time_data *vdso_k_time_data;
 extern struct vdso_rng_data *vdso_k_rng_data;
 extern struct vdso_arch_data *vdso_k_arch_data;
-#endif
-
-/**
- * union vdso_data_store - Generic vDSO data page
- */
-union vdso_data_store {
-	struct vdso_time_data	data[CS_BASES];
-	u8			page[1U << CONFIG_PAGE_SHIFT];
-};
-
-#ifdef CONFIG_GENERIC_VDSO_DATA_STORE
 
 #define VDSO_ARCH_DATA_SIZE ALIGN(sizeof(struct vdso_arch_data), PAGE_SIZE)
 #define VDSO_ARCH_DATA_PAGES (VDSO_ARCH_DATA_SIZE >> PAGE_SHIFT)
@@ -189,7 +173,6 @@ enum vdso_pages {
 /*
  * The generic vDSO implementation requires that gettimeofday.h
  * provides:
- * - __arch_get_vdso_data(): to get the vdso datapage.
  * - __arch_get_hw_counter(): to get the hw counter based on the
  *   clock_mode.
  * - gettimeofday_fallback(): fallback for gettimeofday.
diff --git a/include/vdso/helpers.h b/include/vdso/helpers.h
index 3ddb03bb05cbe..41c3087070c7a 100644
--- a/include/vdso/helpers.h
+++ b/include/vdso/helpers.h
@@ -7,7 +7,7 @@
 #include <asm/barrier.h>
 #include <vdso/datapage.h>
 
-static __always_inline u32 vdso_read_begin(const struct vdso_data *vd)
+static __always_inline u32 vdso_read_begin(const struct vdso_time_data *vd)
 {
 	u32 seq;
 
@@ -18,7 +18,7 @@ static __always_inline u32 vdso_read_begin(const struct vdso_data *vd)
 	return seq;
 }
 
-static __always_inline u32 vdso_read_retry(const struct vdso_data *vd,
+static __always_inline u32 vdso_read_retry(const struct vdso_time_data *vd,
 					   u32 start)
 {
 	u32 seq;
@@ -28,7 +28,7 @@ static __always_inline u32 vdso_read_retry(const struct vdso_data *vd,
 	return seq != start;
 }
 
-static __always_inline void vdso_write_begin(struct vdso_data *vd)
+static __always_inline void vdso_write_begin(struct vdso_time_data *vd)
 {
 	/*
 	 * WRITE_ONCE() is required otherwise the compiler can validly tear
@@ -40,7 +40,7 @@ static __always_inline void vdso_write_begin(struct vdso_data *vd)
 	smp_wmb();
 }
 
-static __always_inline void vdso_write_end(struct vdso_data *vd)
+static __always_inline void vdso_write_end(struct vdso_time_data *vd)
 {
 	smp_wmb();
 	/*
diff --git a/kernel/time/namespace.c b/kernel/time/namespace.c
index 0775b9ec952af..12f55aa539adb 100644
--- a/kernel/time/namespace.c
+++ b/kernel/time/namespace.c
@@ -165,18 +165,18 @@ static struct timens_offset offset_from_ts(struct timespec64 off)
  *     HVCLOCK
  *     VVAR
  *
- * The check for vdso_data->clock_mode is in the unlikely path of
+ * The check for vdso_time_data->clock_mode is in the unlikely path of
  * the seq begin magic. So for the non-timens case most of the time
  * 'seq' is even, so the branch is not taken.
  *
  * If 'seq' is odd, i.e. a concurrent update is in progress, the extra check
- * for vdso_data->clock_mode is a non-issue. The task is spin waiting for the
+ * for vdso_time_data->clock_mode is a non-issue. The task is spin waiting for the
  * update to finish and for 'seq' to become even anyway.
  *
- * Timens page has vdso_data->clock_mode set to VDSO_CLOCKMODE_TIMENS which
+ * Timens page has vdso_time_data->clock_mode set to VDSO_CLOCKMODE_TIMENS which
  * enforces the time namespace handling path.
  */
-static void timens_setup_vdso_data(struct vdso_data *vdata,
+static void timens_setup_vdso_data(struct vdso_time_data *vdata,
 				   struct time_namespace *ns)
 {
 	struct timens_offset *offset = vdata->offset;
@@ -219,7 +219,7 @@ static DEFINE_MUTEX(offset_lock);
 static void timens_set_vvar_page(struct task_struct *task,
 				struct time_namespace *ns)
 {
-	struct vdso_data *vdata;
+	struct vdso_time_data *vdata;
 	unsigned int i;
 
 	if (ns == &init_time_ns)
@@ -235,7 +235,7 @@ static void timens_set_vvar_page(struct task_struct *task,
 		goto out;
 
 	ns->frozen_offsets = true;
-	vdata = arch_get_vdso_data(page_address(ns->vvar_page));
+	vdata = page_address(ns->vvar_page);
 
 	for (i = 0; i < CS_BASES; i++)
 		timens_setup_vdso_data(&vdata[i], ns);
diff --git a/kernel/time/vsyscall.c b/kernel/time/vsyscall.c
index 09c1e39a6dd8e..418192296ef7d 100644
--- a/kernel/time/vsyscall.c
+++ b/kernel/time/vsyscall.c
@@ -15,8 +15,7 @@
 
 #include "timekeeping_internal.h"
 
-static inline void update_vdso_data(struct vdso_data *vdata,
-				    struct timekeeper *tk)
+static inline void update_vdso_time_data(struct vdso_time_data *vdata, struct timekeeper *tk)
 {
 	struct vdso_timestamp *vdso_ts;
 	u64 nsec, sec;
@@ -77,7 +76,7 @@ static inline void update_vdso_data(struct vdso_data *vdata,
 
 void update_vsyscall(struct timekeeper *tk)
 {
-	struct vdso_data *vdata = vdso_k_time_data;
+	struct vdso_time_data *vdata = vdso_k_time_data;
 	struct vdso_timestamp *vdso_ts;
 	s32 clock_mode;
 	u64 nsec;
@@ -117,23 +116,23 @@ void update_vsyscall(struct timekeeper *tk)
 	 * update of the high resolution parts.
 	 */
 	if (clock_mode != VDSO_CLOCKMODE_NONE)
-		update_vdso_data(vdata, tk);
+		update_vdso_time_data(vdata, tk);
 
 	__arch_update_vsyscall(vdata);
 
 	vdso_write_end(vdata);
 
-	__arch_sync_vdso_data(vdata);
+	__arch_sync_vdso_time_data(vdata);
 }
 
 void update_vsyscall_tz(void)
 {
-	struct vdso_data *vdata = vdso_k_time_data;
+	struct vdso_time_data *vdata = vdso_k_time_data;
 
 	vdata[CS_HRES_COARSE].tz_minuteswest = sys_tz.tz_minuteswest;
 	vdata[CS_HRES_COARSE].tz_dsttime = sys_tz.tz_dsttime;
 
-	__arch_sync_vdso_data(vdata);
+	__arch_sync_vdso_time_data(vdata);
 }
 
 /**
@@ -150,7 +149,7 @@ void update_vsyscall_tz(void)
  */
 unsigned long vdso_update_begin(void)
 {
-	struct vdso_data *vdata = vdso_k_time_data;
+	struct vdso_time_data *vdata = vdso_k_time_data;
 	unsigned long flags = timekeeper_lock_irqsave();
 
 	vdso_write_begin(vdata);
@@ -167,9 +166,9 @@ unsigned long vdso_update_begin(void)
  */
 void vdso_update_end(unsigned long flags)
 {
-	struct vdso_data *vdata = vdso_k_time_data;
+	struct vdso_time_data *vdata = vdso_k_time_data;
 
 	vdso_write_end(vdata);
-	__arch_sync_vdso_data(vdata);
+	__arch_sync_vdso_time_data(vdata);
 	timekeeper_unlock_irqrestore(flags);
 }
diff --git a/lib/vdso/datastore.c b/lib/vdso/datastore.c
index 0959d62d78586..e227fbbcb7969 100644
--- a/lib/vdso/datastore.c
+++ b/lib/vdso/datastore.c
@@ -12,7 +12,10 @@
  * The vDSO data page.
  */
 #ifdef CONFIG_HAVE_GENERIC_VDSO
-static union vdso_data_store vdso_time_data_store __page_aligned_data;
+static union {
+	struct vdso_time_data	data[CS_BASES];
+	u8			page[PAGE_SIZE];
+} vdso_time_data_store __page_aligned_data;
 struct vdso_time_data *vdso_k_time_data = vdso_time_data_store.data;
 static_assert(sizeof(vdso_time_data_store) == PAGE_SIZE);
 #endif /* CONFIG_HAVE_GENERIC_VDSO */
@@ -123,9 +126,4 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
 
 	return 0;
 }
-
-struct vdso_time_data *arch_get_vdso_data(void *vvar_page)
-{
-	return (struct vdso_time_data *)vvar_page;
-}
 #endif
diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c
index 20c5b8752fcc8..299f027116ee0 100644
--- a/lib/vdso/gettimeofday.c
+++ b/lib/vdso/gettimeofday.c
@@ -17,12 +17,12 @@
 #endif
 
 #ifdef CONFIG_GENERIC_VDSO_OVERFLOW_PROTECT
-static __always_inline bool vdso_delta_ok(const struct vdso_data *vd, u64 delta)
+static __always_inline bool vdso_delta_ok(const struct vdso_time_data *vd, u64 delta)
 {
 	return delta < vd->max_cycles;
 }
 #else
-static __always_inline bool vdso_delta_ok(const struct vdso_data *vd, u64 delta)
+static __always_inline bool vdso_delta_ok(const struct vdso_time_data *vd, u64 delta)
 {
 	return true;
 }
@@ -39,7 +39,7 @@ static __always_inline u64 vdso_shift_ns(u64 ns, u32 shift)
  * Default implementation which works for all sane clocksources. That
  * obviously excludes x86/TSC.
  */
-static __always_inline u64 vdso_calc_ns(const struct vdso_data *vd, u64 cycles, u64 base)
+static __always_inline u64 vdso_calc_ns(const struct vdso_time_data *vd, u64 cycles, u64 base)
 {
 	u64 delta = (cycles - vd->cycle_last) & VDSO_DELTA_MASK(vd);
 
@@ -58,7 +58,7 @@ static inline bool __arch_vdso_hres_capable(void)
 #endif
 
 #ifndef vdso_clocksource_ok
-static inline bool vdso_clocksource_ok(const struct vdso_data *vd)
+static inline bool vdso_clocksource_ok(const struct vdso_time_data *vd)
 {
 	return vd->clock_mode != VDSO_CLOCKMODE_NONE;
 }
@@ -79,21 +79,20 @@ const struct vdso_time_data *__arch_get_vdso_u_timens_data(const struct vdso_tim
 {
 	return (void *)vd + PAGE_SIZE;
 }
-#define __arch_get_timens_vdso_data(vd) __arch_get_vdso_u_timens_data(vd)
 #endif /* CONFIG_GENERIC_VDSO_DATA_STORE */
 
-static __always_inline int do_hres_timens(const struct vdso_data *vdns, clockid_t clk,
+static __always_inline int do_hres_timens(const struct vdso_time_data *vdns, clockid_t clk,
 					  struct __kernel_timespec *ts)
 {
 	const struct timens_offset *offs = &vdns->offset[clk];
 	const struct vdso_timestamp *vdso_ts;
-	const struct vdso_data *vd;
+	const struct vdso_time_data *vd;
 	u64 cycles, ns;
 	u32 seq;
 	s64 sec;
 
 	vd = vdns - (clk == CLOCK_MONOTONIC_RAW ? CS_RAW : CS_HRES_COARSE);
-	vd = __arch_get_timens_vdso_data(vd);
+	vd = __arch_get_vdso_u_timens_data(vd);
 	if (clk != CLOCK_MONOTONIC_RAW)
 		vd = &vd[CS_HRES_COARSE];
 	else
@@ -128,19 +127,19 @@ static __always_inline int do_hres_timens(const struct vdso_data *vdns, clockid_
 }
 #else
 static __always_inline
-const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd)
+const struct vdso_time_data *__arch_get_vdso_u_timens_data(const struct vdso_time_data *vd)
 {
 	return NULL;
 }
 
-static __always_inline int do_hres_timens(const struct vdso_data *vdns, clockid_t clk,
+static __always_inline int do_hres_timens(const struct vdso_time_data *vdns, clockid_t clk,
 					  struct __kernel_timespec *ts)
 {
 	return -EINVAL;
 }
 #endif
 
-static __always_inline int do_hres(const struct vdso_data *vd, clockid_t clk,
+static __always_inline int do_hres(const struct vdso_time_data *vd, clockid_t clk,
 				   struct __kernel_timespec *ts)
 {
 	const struct vdso_timestamp *vdso_ts = &vd->basetime[clk];
@@ -192,10 +191,10 @@ static __always_inline int do_hres(const struct vdso_data *vd, clockid_t clk,
 }
 
 #ifdef CONFIG_TIME_NS
-static __always_inline int do_coarse_timens(const struct vdso_data *vdns, clockid_t clk,
+static __always_inline int do_coarse_timens(const struct vdso_time_data *vdns, clockid_t clk,
 					    struct __kernel_timespec *ts)
 {
-	const struct vdso_data *vd = __arch_get_timens_vdso_data(vdns);
+	const struct vdso_time_data *vd = __arch_get_vdso_u_timens_data(vdns);
 	const struct vdso_timestamp *vdso_ts = &vd->basetime[clk];
 	const struct timens_offset *offs = &vdns->offset[clk];
 	u64 nsec;
@@ -221,14 +220,14 @@ static __always_inline int do_coarse_timens(const struct vdso_data *vdns, clocki
 	return 0;
 }
 #else
-static __always_inline int do_coarse_timens(const struct vdso_data *vdns, clockid_t clk,
+static __always_inline int do_coarse_timens(const struct vdso_time_data *vdns, clockid_t clk,
 					    struct __kernel_timespec *ts)
 {
 	return -1;
 }
 #endif
 
-static __always_inline int do_coarse(const struct vdso_data *vd, clockid_t clk,
+static __always_inline int do_coarse(const struct vdso_time_data *vd, clockid_t clk,
 				     struct __kernel_timespec *ts)
 {
 	const struct vdso_timestamp *vdso_ts = &vd->basetime[clk];
@@ -255,7 +254,7 @@ static __always_inline int do_coarse(const struct vdso_data *vd, clockid_t clk,
 }
 
 static __always_inline int
-__cvdso_clock_gettime_common(const struct vdso_data *vd, clockid_t clock,
+__cvdso_clock_gettime_common(const struct vdso_time_data *vd, clockid_t clock,
 			     struct __kernel_timespec *ts)
 {
 	u32 msk;
@@ -282,7 +281,7 @@ __cvdso_clock_gettime_common(const struct vdso_data *vd, clockid_t clock,
 }
 
 static __maybe_unused int
-__cvdso_clock_gettime_data(const struct vdso_data *vd, clockid_t clock,
+__cvdso_clock_gettime_data(const struct vdso_time_data *vd, clockid_t clock,
 			   struct __kernel_timespec *ts)
 {
 	int ret = __cvdso_clock_gettime_common(vd, clock, ts);
@@ -300,7 +299,7 @@ __cvdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts)
 
 #ifdef BUILD_VDSO32
 static __maybe_unused int
-__cvdso_clock_gettime32_data(const struct vdso_data *vd, clockid_t clock,
+__cvdso_clock_gettime32_data(const struct vdso_time_data *vd, clockid_t clock,
 			     struct old_timespec32 *res)
 {
 	struct __kernel_timespec ts;
@@ -326,7 +325,7 @@ __cvdso_clock_gettime32(clockid_t clock, struct old_timespec32 *res)
 #endif /* BUILD_VDSO32 */
 
 static __maybe_unused int
-__cvdso_gettimeofday_data(const struct vdso_data *vd,
+__cvdso_gettimeofday_data(const struct vdso_time_data *vd,
 			  struct __kernel_old_timeval *tv, struct timezone *tz)
 {
 
@@ -343,7 +342,7 @@ __cvdso_gettimeofday_data(const struct vdso_data *vd,
 	if (unlikely(tz != NULL)) {
 		if (IS_ENABLED(CONFIG_TIME_NS) &&
 		    vd->clock_mode == VDSO_CLOCKMODE_TIMENS)
-			vd = __arch_get_timens_vdso_data(vd);
+			vd = __arch_get_vdso_u_timens_data(vd);
 
 		tz->tz_minuteswest = vd[CS_HRES_COARSE].tz_minuteswest;
 		tz->tz_dsttime = vd[CS_HRES_COARSE].tz_dsttime;
@@ -360,13 +359,13 @@ __cvdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
 
 #ifdef VDSO_HAS_TIME
 static __maybe_unused __kernel_old_time_t
-__cvdso_time_data(const struct vdso_data *vd, __kernel_old_time_t *time)
+__cvdso_time_data(const struct vdso_time_data *vd, __kernel_old_time_t *time)
 {
 	__kernel_old_time_t t;
 
 	if (IS_ENABLED(CONFIG_TIME_NS) &&
 	    vd->clock_mode == VDSO_CLOCKMODE_TIMENS)
-		vd = __arch_get_timens_vdso_data(vd);
+		vd = __arch_get_vdso_u_timens_data(vd);
 
 	t = READ_ONCE(vd[CS_HRES_COARSE].basetime[CLOCK_REALTIME].sec);
 
@@ -384,7 +383,7 @@ static __maybe_unused __kernel_old_time_t __cvdso_time(__kernel_old_time_t *time
 
 #ifdef VDSO_HAS_CLOCK_GETRES
 static __maybe_unused
-int __cvdso_clock_getres_common(const struct vdso_data *vd, clockid_t clock,
+int __cvdso_clock_getres_common(const struct vdso_time_data *vd, clockid_t clock,
 				struct __kernel_timespec *res)
 {
 	u32 msk;
@@ -396,7 +395,7 @@ int __cvdso_clock_getres_common(const struct vdso_data *vd, clockid_t clock,
 
 	if (IS_ENABLED(CONFIG_TIME_NS) &&
 	    vd->clock_mode == VDSO_CLOCKMODE_TIMENS)
-		vd = __arch_get_timens_vdso_data(vd);
+		vd = __arch_get_vdso_u_timens_data(vd);
 
 	/*
 	 * Convert the clockid to a bitmask and use it to check which
@@ -425,7 +424,7 @@ int __cvdso_clock_getres_common(const struct vdso_data *vd, clockid_t clock,
 }
 
 static __maybe_unused
-int __cvdso_clock_getres_data(const struct vdso_data *vd, clockid_t clock,
+int __cvdso_clock_getres_data(const struct vdso_time_data *vd, clockid_t clock,
 			      struct __kernel_timespec *res)
 {
 	int ret = __cvdso_clock_getres_common(vd, clock, res);
@@ -443,7 +442,7 @@ int __cvdso_clock_getres(clockid_t clock, struct __kernel_timespec *res)
 
 #ifdef BUILD_VDSO32
 static __maybe_unused int
-__cvdso_clock_getres_time32_data(const struct vdso_data *vd, clockid_t clock,
+__cvdso_clock_getres_time32_data(const struct vdso_time_data *vd, clockid_t clock,
 				 struct old_timespec32 *res)
 {
 	struct __kernel_timespec ts;

From 2d81e1bb625238d40a686ed909ff3e1abab7556a Mon Sep 17 00:00:00 2001
From: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Date: Mon, 17 Feb 2025 01:16:32 +0300
Subject: [PATCH 0454/1173] irqchip/gic-v3: Add Rockchip 3568002 erratum
 workaround

Rockchip RK3566/RK3568 GIC600 integration has DDR addressing
limited to the first 32bit of physical address space. Rockchip
assigned Erratum ID #3568002 for this issue. Add driver quirk for
this Rockchip GIC Erratum.

Note, that the 0x0201743b GIC600 ID is not Rockchip-specific and is
common for many ARM GICv3 implementations. Hence, there is an extra
of_machine_is_compatible() check.

Signed-off-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/all/20250216221634.364158-2-dmitry.osipenko@collabora.com
---
 Documentation/arch/arm64/silicon-errata.rst |  2 ++
 arch/arm64/Kconfig                          |  9 ++++++++
 drivers/irqchip/irq-gic-v3-its.c            | 23 ++++++++++++++++++++-
 3 files changed, 33 insertions(+), 1 deletion(-)

diff --git a/Documentation/arch/arm64/silicon-errata.rst b/Documentation/arch/arm64/silicon-errata.rst
index f074f6219f5c3..f968c13b46a78 100644
--- a/Documentation/arch/arm64/silicon-errata.rst
+++ b/Documentation/arch/arm64/silicon-errata.rst
@@ -284,6 +284,8 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | Rockchip       | RK3588          | #3588001        | ROCKCHIP_ERRATUM_3588001    |
 +----------------+-----------------+-----------------+-----------------------------+
+| Rockchip       | RK3568          | #3568002        | ROCKCHIP_ERRATUM_3568002    |
++----------------+-----------------+-----------------+-----------------------------+
 +----------------+-----------------+-----------------+-----------------------------+
 | Fujitsu        | A64FX           | E#010001        | FUJITSU_ERRATUM_010001      |
 +----------------+-----------------+-----------------+-----------------------------+
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index fcdd0ed3eca89..0507e476f69fb 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1303,6 +1303,15 @@ config NVIDIA_CARMEL_CNP_ERRATUM
 
 	  If unsure, say Y.
 
+config ROCKCHIP_ERRATUM_3568002
+	bool "Rockchip 3568002: GIC600 can not access physical addresses higher than 4GB"
+	default y
+	help
+	  The Rockchip RK3566 and RK3568 GIC600 SoC integrations have AXI
+	  addressing limited to the first 32bit of physical address space.
+
+	  If unsure, say Y.
+
 config ROCKCHIP_ERRATUM_3588001
 	bool "Rockchip 3588001: GIC600 can not support shareability attributes"
 	default y
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 8c3ec5734f1ef..f30ed281882ff 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -205,13 +205,15 @@ static DEFINE_IDA(its_vpeid_ida);
 #define gic_data_rdist_rd_base()	(gic_data_rdist()->rd_base)
 #define gic_data_rdist_vlpi_base()	(gic_data_rdist_rd_base() + SZ_128K)
 
+static gfp_t gfp_flags_quirk;
+
 static struct page *its_alloc_pages_node(int node, gfp_t gfp,
 					 unsigned int order)
 {
 	struct page *page;
 	int ret = 0;
 
-	page = alloc_pages_node(node, gfp, order);
+	page = alloc_pages_node(node, gfp | gfp_flags_quirk, order);
 
 	if (!page)
 		return NULL;
@@ -4887,6 +4889,17 @@ static bool __maybe_unused its_enable_quirk_hip09_162100801(void *data)
 	return true;
 }
 
+static bool __maybe_unused its_enable_rk3568002(void *data)
+{
+	if (!of_machine_is_compatible("rockchip,rk3566") &&
+	    !of_machine_is_compatible("rockchip,rk3568"))
+		return false;
+
+	gfp_flags_quirk |= GFP_DMA32;
+
+	return true;
+}
+
 static const struct gic_quirk its_quirks[] = {
 #ifdef CONFIG_CAVIUM_ERRATUM_22375
 	{
@@ -4954,6 +4967,14 @@ static const struct gic_quirk its_quirks[] = {
 		.property = "dma-noncoherent",
 		.init   = its_set_non_coherent,
 	},
+#ifdef CONFIG_ROCKCHIP_ERRATUM_3568002
+	{
+		.desc   = "ITS: Rockchip erratum RK3568002",
+		.iidr   = 0x0201743b,
+		.mask   = 0xffffffff,
+		.init   = its_enable_rk3568002,
+	},
+#endif
 	{
 	}
 };

From f15be3d4a0a55db2b50f319c378a2d16ceb21f86 Mon Sep 17 00:00:00 2001
From: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Date: Mon, 17 Feb 2025 01:16:33 +0300
Subject: [PATCH 0455/1173] arm64: dts: rockchip: rk356x: Add MSI controller
 node

Rockchip 356x SoC's GIC has two hardware integration issues that
affect MSI functionality of the GIC. Previously, both these GIC
issues were worked around by using MBI for MSI instead of ITS
because kernel GIC driver didn't have necessary quirks.

First issue is about RK356x GIC not supporting programmable
shareability, while reporting it as supported in a GIC's feature
register. Rockchip assigned Erratum ID #3568001 for this issue. This
patch adds dma-noncoherent property to the GIC node, denoting that a SW
workaround is required for mitigating the issue.

Second issue is about GIC AXI master interface addressing limited to
the first 4GB of physical address space. Rockchip assigned Erratum
ID #3568002 for this issue.

Now that kernel supports quirks for both of the erratums, add
MSI controller node to RK356x device-tree.

Signed-off-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250216221634.364158-3-dmitry.osipenko@collabora.com
---
 arch/arm64/boot/dts/rockchip/rk356x-base.dtsi | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/arch/arm64/boot/dts/rockchip/rk356x-base.dtsi b/arch/arm64/boot/dts/rockchip/rk356x-base.dtsi
index e553906291140..89ba0d7f47f7f 100644
--- a/arch/arm64/boot/dts/rockchip/rk356x-base.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk356x-base.dtsi
@@ -284,6 +284,18 @@
 		mbi-alias = <0x0 0xfd410000>;
 		mbi-ranges = <296 24>;
 		msi-controller;
+		ranges;
+		#address-cells = <2>;
+		#size-cells = <2>;
+		dma-noncoherent;
+
+		its: msi-controller@fd440000 {
+			compatible = "arm,gic-v3-its";
+			reg = <0x0 0xfd440000 0 0x20000>;
+			dma-noncoherent;
+			msi-controller;
+			#msi-cells = <1>;
+		};
 	};
 
 	usb_host0_ehci: usb@fd800000 {

From b956c9de91757c9478e24fc9f6a57fd46f0a49f0 Mon Sep 17 00:00:00 2001
From: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Date: Mon, 17 Feb 2025 01:16:34 +0300
Subject: [PATCH 0456/1173] arm64: dts: rockchip: rk356x: Move PCIe MSI to use
 GIC ITS instead of MBI

Rockchip 356x device-tree now supports GIC ITS. Move PCIe controller's
MSI to use ITS instead of MBI. This removes extra CPU overhead of handling
PCIe MBIs by letting GIC's ITS to serve the PCIe MSIs.

Signed-off-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250216221634.364158-4-dmitry.osipenko@collabora.com
---
 arch/arm64/boot/dts/rockchip/rk356x-base.dtsi | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/boot/dts/rockchip/rk356x-base.dtsi b/arch/arm64/boot/dts/rockchip/rk356x-base.dtsi
index 89ba0d7f47f7f..4e730aecf84df 100644
--- a/arch/arm64/boot/dts/rockchip/rk356x-base.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk356x-base.dtsi
@@ -969,7 +969,7 @@
 		num-ib-windows = <6>;
 		num-ob-windows = <2>;
 		max-link-speed = <2>;
-		msi-map = <0x0 &gic 0x0 0x1000>;
+		msi-map = <0x0 &its 0x0 0x1000>;
 		num-lanes = <1>;
 		phys = <&combphy2 PHY_TYPE_PCIE>;
 		phy-names = "pcie-phy";

From 92527e473911b835c2c18b0c55c337c33e85ff00 Mon Sep 17 00:00:00 2001
From: Elizabeth Figura <zfigura@codeweavers.com>
Date: Thu, 20 Feb 2025 13:23:34 -0600
Subject: [PATCH 0457/1173] ntsync: Check wait count based on byte size.

GCC versions below 13 incorrectly detect the copy size as being static and too
small to fit in the "fds" array. Work around this by explicitly calculating the
size and returning EINVAL based on that, instead of based on the object count.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202502072019.LYoCR9bF-lkp@intel.com/
Suggested-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Elizabeth Figura <zfigura@codeweavers.com>

--

Suggested-by as per Arnd's request, but the only thing I changed was preserving
array_size() [as noted by Geert in the linked thread]. I tested and found no
regressions.

v2: Add missing sign-off
Link: https://lore.kernel.org/r/20250220192334.549167-1-zfigura@codeweavers.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/ntsync.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/misc/ntsync.c b/drivers/misc/ntsync.c
index 0b4e56d59b3da..999026a1ae048 100644
--- a/drivers/misc/ntsync.c
+++ b/drivers/misc/ntsync.c
@@ -873,6 +873,7 @@ static int setup_wait(struct ntsync_device *dev,
 {
 	int fds[NTSYNC_MAX_WAIT_COUNT + 1];
 	const __u32 count = args->count;
+	size_t size = array_size(count, sizeof(fds[0]));
 	struct ntsync_q *q;
 	__u32 total_count;
 	__u32 i, j;
@@ -880,15 +881,14 @@ static int setup_wait(struct ntsync_device *dev,
 	if (args->pad || (args->flags & ~NTSYNC_WAIT_REALTIME))
 		return -EINVAL;
 
-	if (args->count > NTSYNC_MAX_WAIT_COUNT)
+	if (size >= sizeof(fds))
 		return -EINVAL;
 
 	total_count = count;
 	if (args->alert)
 		total_count++;
 
-	if (copy_from_user(fds, u64_to_user_ptr(args->objs),
-			   array_size(count, sizeof(*fds))))
+	if (copy_from_user(fds, u64_to_user_ptr(args->objs), size))
 		return -EFAULT;
 	if (args->alert)
 		fds[count] = args->alert;

From d252435aca44d647d57b84de5108556f9c97614a Mon Sep 17 00:00:00 2001
From: BillXiang <xiangwencheng@lanxincomputing.com>
Date: Fri, 21 Feb 2025 18:45:38 +0800
Subject: [PATCH 0458/1173] riscv: KVM: Remove unnecessary vcpu kick
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Remove the unnecessary kick to the vCPU after writing to the vs_file
of IMSIC in kvm_riscv_vcpu_aia_imsic_inject.

For vCPUs that are running, writing to the vs_file directly forwards
the interrupt as an MSI to them and does not need an extra kick.

For vCPUs that are descheduled after emulating WFI, KVM will enable
the guest external interrupt for that vCPU in
kvm_riscv_aia_wakeon_hgei. This means that writing to the vs_file
will cause a guest external interrupt, which will cause KVM to wake
up the vCPU in hgei_interrupt to handle the interrupt properly.

Signed-off-by: BillXiang <xiangwencheng@lanxincomputing.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Radim Krčmář <rkrcmar@ventanamicro.com>
Link: https://lore.kernel.org/r/20250221104538.2147-1-xiangwencheng@lanxincomputing.com
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/aia_imsic.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/riscv/kvm/aia_imsic.c b/arch/riscv/kvm/aia_imsic.c
index a8085cd8215e3..29ef9c2133a93 100644
--- a/arch/riscv/kvm/aia_imsic.c
+++ b/arch/riscv/kvm/aia_imsic.c
@@ -974,7 +974,6 @@ int kvm_riscv_vcpu_aia_imsic_inject(struct kvm_vcpu *vcpu,
 
 	if (imsic->vsfile_cpu >= 0) {
 		writel(iid, imsic->vsfile_va + IMSIC_MMIO_SETIPNUM_LE);
-		kvm_vcpu_kick(vcpu);
 	} else {
 		eix = &imsic->swfile->eix[iid / BITS_PER_TYPE(u64)];
 		set_bit(iid & (BITS_PER_TYPE(u64) - 1), eix->eip);

From 7861640aac52bbbb3dc2cd40fb93dfb3b3d0f43c Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Thu, 20 Feb 2025 13:08:12 -0700
Subject: [PATCH 0459/1173] x86/build: Raise the minimum LLVM version to 15.0.0

In a similar vein as to this pending commit in the x86/asm tree:

  a3e8fe814ad1 ("x86/build: Raise the minimum GCC version to 8.1")

... bump the minimum supported version of LLVM for building x86 kernels
to 15.0.0, as that is the first version that has support for
'-mstack-protector-guard-symbol', which is used unconditionally after:

  80d47defddc0 ("x86/stackprotector/64: Convert to normal per-CPU variable"):

Older Clang versions will fail the build with:

  clang-14: error: unknown argument: '-mstack-protector-guard-symbol=__ref_stack_chk_guard'

Fixes: 80d47defddc0 ("x86/stackprotector/64: Convert to normal per-CPU variable")
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Brian Gerst <brgerst@gmail.com>
Link: https://lore.kernel.org/r/20250220-x86-bump-min-llvm-for-stackp-v1-1-ecb3c906e790@kernel.org
---
 scripts/min-tool-version.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/min-tool-version.sh b/scripts/min-tool-version.sh
index 06c4e410ecaba..787868183b843 100755
--- a/scripts/min-tool-version.sh
+++ b/scripts/min-tool-version.sh
@@ -26,7 +26,7 @@ gcc)
 	fi
 	;;
 llvm)
-	if [ "$SRCARCH" = s390 ]; then
+	if [ "$SRCARCH" = s390 -o "$SRCARCH" = x86 ]; then
 		echo 15.0.0
 	elif [ "$SRCARCH" = loongarch ]; then
 		echo 18.0.0

From 8510edf191d2df0822ea22d6226e4eef87562271 Mon Sep 17 00:00:00 2001
From: Jingbo Xu <jefflexu@linux.alibaba.com>
Date: Tue, 18 Feb 2025 20:02:08 +0800
Subject: [PATCH 0460/1173] mm/filemap: fix miscalculated file range for
 filemap_fdatawrite_range_kick()

iocb->ki_pos has been updated with the number of written bytes since
generic_perform_write().

Besides __filemap_fdatawrite_range() accepts the inclusive end of the
data range.

Fixes: 1d4457576570 ("mm: call filemap_fdatawrite_range_kick() after IOCB_DONTCACHE issue")
Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com>
Link: https://lore.kernel.org/r/20250218120209.88093-2-jefflexu@linux.alibaba.com
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/fs.h | 4 ++--
 mm/filemap.c       | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 9346adf28f7bc..2788df98080f8 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2975,8 +2975,8 @@ static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count)
 	} else if (iocb->ki_flags & IOCB_DONTCACHE) {
 		struct address_space *mapping = iocb->ki_filp->f_mapping;
 
-		filemap_fdatawrite_range_kick(mapping, iocb->ki_pos,
-					      iocb->ki_pos + count);
+		filemap_fdatawrite_range_kick(mapping, iocb->ki_pos - count,
+					      iocb->ki_pos - 1);
 	}
 
 	return count;
diff --git a/mm/filemap.c b/mm/filemap.c
index 804d7365680c1..d4564a79eb353 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -445,7 +445,7 @@ EXPORT_SYMBOL(filemap_fdatawrite_range);
  * filemap_fdatawrite_range_kick - start writeback on a range
  * @mapping:	target address_space
  * @start:	index to start writeback on
- * @end:	last (non-inclusive) index for writeback
+ * @end:	last (inclusive) index for writeback
  *
  * This is a non-integrity writeback helper, to start writing back folios
  * for the indicated range.

From 927289988068a65ccc168eda881ce60f8712707b Mon Sep 17 00:00:00 2001
From: Jingbo Xu <jefflexu@linux.alibaba.com>
Date: Tue, 18 Feb 2025 20:02:09 +0800
Subject: [PATCH 0461/1173] mm/truncate: don't skip dirty page in
 folio_unmap_invalidate()

... otherwise this is a behavior change for the previous callers of
invalidate_complete_folio2(), e.g. the page invalidation routine.

Fixes: 4a9e23159fd3 ("mm/truncate: add folio_unmap_invalidate() helper")
Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com>
Link: https://lore.kernel.org/r/20250218120209.88093-3-jefflexu@linux.alibaba.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 mm/truncate.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/mm/truncate.c b/mm/truncate.c
index e2e115adfbc58..76d8fcd89bd00 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -548,8 +548,6 @@ int folio_unmap_invalidate(struct address_space *mapping, struct folio *folio,
 
 	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
 
-	if (folio_test_dirty(folio))
-		return 0;
 	if (folio_mapped(folio))
 		unmap_mapping_folio(folio);
 	BUG_ON(folio_mapped(folio));

From 517120728484df1ab8b71cba8d2cad19f52f18a1 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Wed, 19 Feb 2025 22:01:24 -0800
Subject: [PATCH 0462/1173] x86/cpufeatures: Make AVX-VNNI depend on AVX

The 'noxsave' boot option disables support for AVX, but support for the
AVX-VNNI feature was still declared on CPUs that support it.  Fix this.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/r/20250220060124.89622-1-ebiggers@kernel.org
---
 arch/x86/kernel/cpu/cpuid-deps.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index 8bd84114c2d96..df838e3bdbe02 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -45,6 +45,7 @@ static const struct cpuid_dep cpuid_deps[] = {
 	{ X86_FEATURE_AES,			X86_FEATURE_XMM2      },
 	{ X86_FEATURE_SHA_NI,			X86_FEATURE_XMM2      },
 	{ X86_FEATURE_GFNI,			X86_FEATURE_XMM2      },
+	{ X86_FEATURE_AVX_VNNI,			X86_FEATURE_AVX       },
 	{ X86_FEATURE_FMA,			X86_FEATURE_AVX       },
 	{ X86_FEATURE_VAES,			X86_FEATURE_AVX       },
 	{ X86_FEATURE_VPCLMULQDQ,		X86_FEATURE_AVX       },

From dc0a241ceaf3b7df6f1a7658b020c92682b75bfc Mon Sep 17 00:00:00 2001
From: Michael Jeanson <mjeanson@efficios.com>
Date: Wed, 19 Feb 2025 15:53:26 -0500
Subject: [PATCH 0463/1173] rseq: Fix rseq registration with CONFIG_DEBUG_RSEQ

With CONFIG_DEBUG_RSEQ=y, at rseq registration the read-only fields are
copied from user-space, if this copy fails the syscall returns -EFAULT
and the registration should not be activated - but it erroneously is.

Move the activation of the registration after the copy of the fields to
fix this bug.

Fixes: 7d5265ffcd8b ("rseq: Validate read-only fields under DEBUG_RSEQ config")
Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/r/20250219205330.324770-1-mjeanson@efficios.com
---
 kernel/rseq.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/kernel/rseq.c b/kernel/rseq.c
index 442aba29bc4cf..2cb16091ec0ae 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -507,9 +507,6 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len,
 		return -EINVAL;
 	if (!access_ok(rseq, rseq_len))
 		return -EFAULT;
-	current->rseq = rseq;
-	current->rseq_len = rseq_len;
-	current->rseq_sig = sig;
 #ifdef CONFIG_DEBUG_RSEQ
 	/*
 	 * Initialize the in-kernel rseq fields copy for validation of
@@ -521,6 +518,14 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len,
 	    get_user(rseq_kernel_fields(current)->mm_cid, &rseq->mm_cid))
 		return -EFAULT;
 #endif
+	/*
+	 * Activate the registration by setting the rseq area address, length
+	 * and signature in the task struct.
+	 */
+	current->rseq = rseq;
+	current->rseq_len = rseq_len;
+	current->rseq_sig = sig;
+
 	/*
 	 * If rseq was previously inactive, and has just been
 	 * registered, ensure the cpu_id_start and cpu_id fields

From c9876cdb3ac4dcdf3c710ff02094165982e2a557 Mon Sep 17 00:00:00 2001
From: Brian Ochoa <brianeochoa@gmail.com>
Date: Wed, 19 Feb 2025 10:09:20 -0500
Subject: [PATCH 0464/1173] docs: arch/x86/sva: Fix two grammar errors under
 Background and FAQ

- Correct "in order" to "in order to"
- Append missing quantifier

Signed-off-by: Brian Ochoa <brianeochoa@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250219150920.445802-1-brianeochoa@gmail.com
---
 Documentation/arch/x86/sva.rst | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/arch/x86/sva.rst b/Documentation/arch/x86/sva.rst
index 33cb050059820..6a759984d4712 100644
--- a/Documentation/arch/x86/sva.rst
+++ b/Documentation/arch/x86/sva.rst
@@ -25,7 +25,7 @@ to cache translations for virtual addresses. The IOMMU driver uses the
 mmu_notifier() support to keep the device TLB cache and the CPU cache in
 sync. When an ATS lookup fails for a virtual address, the device should
 use the PRI in order to request the virtual address to be paged into the
-CPU page tables. The device must use ATS again in order the fetch the
+CPU page tables. The device must use ATS again in order to fetch the
 translation before use.
 
 Shared Hardware Workqueues
@@ -216,7 +216,7 @@ submitting work and processing completions.
 
 Single Root I/O Virtualization (SR-IOV) focuses on providing independent
 hardware interfaces for virtualizing hardware. Hence, it's required to be
-almost fully functional interface to software supporting the traditional
+an almost fully functional interface to software supporting the traditional
 BARs, space for interrupts via MSI-X, its own register layout.
 Virtual Functions (VFs) are assisted by the Physical Function (PF)
 driver.

From 06dd759b68eea200e488cafbcfd382208a940777 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Wed, 19 Feb 2025 16:48:49 +0300
Subject: [PATCH 0465/1173] x86/module: Remove unnecessary check in
 module_finalize()

The "calls" pointer can no longer be NULL after the following
commit:

   ab9fea59487d ("x86/alternative: Simplify callthunk patching")

Delete this unnecessary check.

Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/fcbb2f57-0714-4139-b441-8817365c16a1@stanley.mountain
---
 arch/x86/kernel/module.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index cb9d295e67cbf..615f74c4bd6c0 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -278,10 +278,8 @@ int module_finalize(const Elf_Ehdr *hdr,
 	if (calls) {
 		struct callthunk_sites cs = {};
 
-		if (calls) {
-			cs.call_start = (void *)calls->sh_addr;
-			cs.call_end = (void *)calls->sh_addr + calls->sh_size;
-		}
+		cs.call_start = (void *)calls->sh_addr;
+		cs.call_end = (void *)calls->sh_addr + calls->sh_size;
 
 		callthunks_patch_module_calls(&cs, me);
 	}

From 1937e18cc3cf27e2b3ef70e8c161437051ab7608 Mon Sep 17 00:00:00 2001
From: Stanislav Spassov <stanspas@amazon.de>
Date: Tue, 18 Feb 2025 14:10:45 +0000
Subject: [PATCH 0466/1173] x86/fpu: Fix guest FPU state buffer allocation size

Ongoing work on an optimization to batch-preallocate vCPU state buffers
for KVM revealed a mismatch between the allocation sizes used in
fpu_alloc_guest_fpstate() and fpstate_realloc(). While the former
allocates a buffer sized to fit the default set of XSAVE features
in UABI form (as per fpu_user_cfg), the latter uses its ksize argument
derived (for the requested set of features) in the same way as the sizes
found in fpu_kernel_cfg, i.e. using the compacted in-kernel
representation.

The correct size to use for guest FPU state should indeed be the
kernel one as seen in fpstate_realloc(). The original issue likely
went unnoticed through a combination of UABI size typically being
larger than or equal to kernel size, and/or both amounting to the
same number of allocated 4K pages.

Fixes: 69f6ed1d14c6 ("x86/fpu: Provide infrastructure for KVM FPU cleanup")
Signed-off-by: Stanislav Spassov <stanspas@amazon.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250218141045.85201-1-stanspas@amazon.de
---
 arch/x86/kernel/fpu/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 1209c7aebb211..36df548acc403 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -220,7 +220,7 @@ bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu)
 	struct fpstate *fpstate;
 	unsigned int size;
 
-	size = fpu_user_cfg.default_size + ALIGN(offsetof(struct fpstate, regs), 64);
+	size = fpu_kernel_cfg.default_size + ALIGN(offsetof(struct fpstate, regs), 64);
 	fpstate = vzalloc(size);
 	if (!fpstate)
 		return false;

From 8aeacf257070469ff78a998a968a61d0cadc0de3 Mon Sep 17 00:00:00 2001
From: Joel Granados <joel.granados@kernel.org>
Date: Tue, 18 Feb 2025 10:56:21 +0100
Subject: [PATCH 0467/1173] perf/core: Move perf_event sysctls into
 kernel/events

Move ctl tables to two files:

 - perf_event_{paranoid,mlock_kb,max_sample_rate} and
   perf_cpu_time_max_percent into kernel/events/core.c

 - perf_event_max_{stack,context_per_stack} into
   kernel/events/callchain.c

Make static variables and functions that are fully contained in core.c
and callchain.cand remove them from include/linux/perf_event.h.
Additionally six_hundred_forty_kb is moved to callchain.c.

Two new sysctl tables are added ({callchain,events_core}_sysctl_table)
with their respective sysctl registration functions.

This is part of a greater effort to move ctl tables into their
respective subsystems which will reduce the merge conflicts in
kerenel/sysctl.c.

Signed-off-by: Joel Granados <joel.granados@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250218-jag-mv_ctltables-v1-5-cd3698ab8d29@kernel.org
---
 include/linux/perf_event.h |  9 ------
 kernel/events/callchain.c  | 38 ++++++++++++++++++----
 kernel/events/core.c       | 57 +++++++++++++++++++++++++++++----
 kernel/sysctl.c            | 64 --------------------------------------
 4 files changed, 83 insertions(+), 85 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 2d07bc1193f3a..c4525bae2fe9f 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1652,19 +1652,10 @@ static inline int perf_callchain_store(struct perf_callchain_entry_ctx *ctx, u64
 }
 
 extern int sysctl_perf_event_paranoid;
-extern int sysctl_perf_event_mlock;
 extern int sysctl_perf_event_sample_rate;
-extern int sysctl_perf_cpu_time_max_percent;
 
 extern void perf_sample_event_took(u64 sample_len_ns);
 
-int perf_event_max_sample_rate_handler(const struct ctl_table *table, int write,
-		void *buffer, size_t *lenp, loff_t *ppos);
-int perf_cpu_time_max_percent_handler(const struct ctl_table *table, int write,
-		void *buffer, size_t *lenp, loff_t *ppos);
-int perf_event_max_stack_handler(const struct ctl_table *table, int write,
-		void *buffer, size_t *lenp, loff_t *ppos);
-
 /* Access to perf_event_open(2) syscall. */
 #define PERF_SECURITY_OPEN		0
 
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index 8a47e52a454f4..6c83ad674d010 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -22,6 +22,7 @@ struct callchain_cpus_entries {
 
 int sysctl_perf_event_max_stack __read_mostly = PERF_MAX_STACK_DEPTH;
 int sysctl_perf_event_max_contexts_per_stack __read_mostly = PERF_MAX_CONTEXTS_PER_STACK;
+static const int six_hundred_forty_kb = 640 * 1024;
 
 static inline size_t perf_callchain_entry__sizeof(void)
 {
@@ -266,12 +267,8 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
 	return entry;
 }
 
-/*
- * Used for sysctl_perf_event_max_stack and
- * sysctl_perf_event_max_contexts_per_stack.
- */
-int perf_event_max_stack_handler(const struct ctl_table *table, int write,
-				 void *buffer, size_t *lenp, loff_t *ppos)
+static int perf_event_max_stack_handler(const struct ctl_table *table, int write,
+					void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int *value = table->data;
 	int new_value = *value, ret;
@@ -292,3 +289,32 @@ int perf_event_max_stack_handler(const struct ctl_table *table, int write,
 
 	return ret;
 }
+
+static const struct ctl_table callchain_sysctl_table[] = {
+	{
+		.procname	= "perf_event_max_stack",
+		.data		= &sysctl_perf_event_max_stack,
+		.maxlen		= sizeof(sysctl_perf_event_max_stack),
+		.mode		= 0644,
+		.proc_handler	= perf_event_max_stack_handler,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= (void *)&six_hundred_forty_kb,
+	},
+	{
+		.procname	= "perf_event_max_contexts_per_stack",
+		.data		= &sysctl_perf_event_max_contexts_per_stack,
+		.maxlen		= sizeof(sysctl_perf_event_max_contexts_per_stack),
+		.mode		= 0644,
+		.proc_handler	= perf_event_max_stack_handler,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE_THOUSAND,
+	},
+};
+
+static int __init init_callchain_sysctls(void)
+{
+	register_sysctl_init("kernel", callchain_sysctl_table);
+	return 0;
+}
+core_initcall(init_callchain_sysctls);
+
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 0f8c559907830..45ad0f6083498 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -452,8 +452,8 @@ static struct kmem_cache *perf_event_cache;
  */
 int sysctl_perf_event_paranoid __read_mostly = 2;
 
-/* Minimum for 512 kiB + 1 user control page */
-int sysctl_perf_event_mlock __read_mostly = 512 + (PAGE_SIZE / 1024); /* 'free' kiB per user */
+/* Minimum for 512 kiB + 1 user control page. 'free' kiB per user. */
+static int sysctl_perf_event_mlock __read_mostly = 512 + (PAGE_SIZE / 1024);
 
 /*
  * max perf event sample rate
@@ -463,6 +463,7 @@ int sysctl_perf_event_mlock __read_mostly = 512 + (PAGE_SIZE / 1024); /* 'free'
 #define DEFAULT_CPU_TIME_MAX_PERCENT	25
 
 int sysctl_perf_event_sample_rate __read_mostly	= DEFAULT_MAX_SAMPLE_RATE;
+static int sysctl_perf_cpu_time_max_percent __read_mostly = DEFAULT_CPU_TIME_MAX_PERCENT;
 
 static int max_samples_per_tick __read_mostly	= DIV_ROUND_UP(DEFAULT_MAX_SAMPLE_RATE, HZ);
 static int perf_sample_period_ns __read_mostly	= DEFAULT_SAMPLE_PERIOD_NS;
@@ -484,7 +485,7 @@ static void update_perf_cpu_limits(void)
 
 static bool perf_rotate_context(struct perf_cpu_pmu_context *cpc);
 
-int perf_event_max_sample_rate_handler(const struct ctl_table *table, int write,
+static int perf_event_max_sample_rate_handler(const struct ctl_table *table, int write,
 				       void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret;
@@ -506,9 +507,7 @@ int perf_event_max_sample_rate_handler(const struct ctl_table *table, int write,
 	return 0;
 }
 
-int sysctl_perf_cpu_time_max_percent __read_mostly = DEFAULT_CPU_TIME_MAX_PERCENT;
-
-int perf_cpu_time_max_percent_handler(const struct ctl_table *table, int write,
+static int perf_cpu_time_max_percent_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
@@ -528,6 +527,52 @@ int perf_cpu_time_max_percent_handler(const struct ctl_table *table, int write,
 	return 0;
 }
 
+static const struct ctl_table events_core_sysctl_table[] = {
+	/*
+	 * User-space relies on this file as a feature check for
+	 * perf_events being enabled. It's an ABI, do not remove!
+	 */
+	{
+		.procname	= "perf_event_paranoid",
+		.data		= &sysctl_perf_event_paranoid,
+		.maxlen		= sizeof(sysctl_perf_event_paranoid),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "perf_event_mlock_kb",
+		.data		= &sysctl_perf_event_mlock,
+		.maxlen		= sizeof(sysctl_perf_event_mlock),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "perf_event_max_sample_rate",
+		.data		= &sysctl_perf_event_sample_rate,
+		.maxlen		= sizeof(sysctl_perf_event_sample_rate),
+		.mode		= 0644,
+		.proc_handler	= perf_event_max_sample_rate_handler,
+		.extra1		= SYSCTL_ONE,
+	},
+	{
+		.procname	= "perf_cpu_time_max_percent",
+		.data		= &sysctl_perf_cpu_time_max_percent,
+		.maxlen		= sizeof(sysctl_perf_cpu_time_max_percent),
+		.mode		= 0644,
+		.proc_handler	= perf_cpu_time_max_percent_handler,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE_HUNDRED,
+	},
+};
+
+static int __init init_events_core_sysctls(void)
+{
+	register_sysctl_init("kernel", events_core_sysctl_table);
+	return 0;
+}
+core_initcall(init_events_core_sysctls);
+
+
 /*
  * perf samples are done in some very critical code paths (NMIs).
  * If they take too much CPU time, the system can lock up and not
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index cb57da499ebb1..4484cdb504c78 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -54,7 +54,6 @@
 #include <linux/acpi.h>
 #include <linux/reboot.h>
 #include <linux/ftrace.h>
-#include <linux/perf_event.h>
 #include <linux/oom.h>
 #include <linux/kmod.h>
 #include <linux/capability.h>
@@ -91,12 +90,6 @@ EXPORT_SYMBOL_GPL(sysctl_long_vals);
 #if defined(CONFIG_SYSCTL)
 
 /* Constants used for minimum and maximum */
-
-#ifdef CONFIG_PERF_EVENTS
-static const int six_hundred_forty_kb = 640 * 1024;
-#endif
-
-
 static const int ngroups_max = NGROUPS_MAX;
 static const int cap_last_cap = CAP_LAST_CAP;
 
@@ -1932,63 +1925,6 @@ static const struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
-#endif
-#ifdef CONFIG_PERF_EVENTS
-	/*
-	 * User-space scripts rely on the existence of this file
-	 * as a feature check for perf_events being enabled.
-	 *
-	 * So it's an ABI, do not remove!
-	 */
-	{
-		.procname	= "perf_event_paranoid",
-		.data		= &sysctl_perf_event_paranoid,
-		.maxlen		= sizeof(sysctl_perf_event_paranoid),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "perf_event_mlock_kb",
-		.data		= &sysctl_perf_event_mlock,
-		.maxlen		= sizeof(sysctl_perf_event_mlock),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "perf_event_max_sample_rate",
-		.data		= &sysctl_perf_event_sample_rate,
-		.maxlen		= sizeof(sysctl_perf_event_sample_rate),
-		.mode		= 0644,
-		.proc_handler	= perf_event_max_sample_rate_handler,
-		.extra1		= SYSCTL_ONE,
-	},
-	{
-		.procname	= "perf_cpu_time_max_percent",
-		.data		= &sysctl_perf_cpu_time_max_percent,
-		.maxlen		= sizeof(sysctl_perf_cpu_time_max_percent),
-		.mode		= 0644,
-		.proc_handler	= perf_cpu_time_max_percent_handler,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_ONE_HUNDRED,
-	},
-	{
-		.procname	= "perf_event_max_stack",
-		.data		= &sysctl_perf_event_max_stack,
-		.maxlen		= sizeof(sysctl_perf_event_max_stack),
-		.mode		= 0644,
-		.proc_handler	= perf_event_max_stack_handler,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= (void *)&six_hundred_forty_kb,
-	},
-	{
-		.procname	= "perf_event_max_contexts_per_stack",
-		.data		= &sysctl_perf_event_max_contexts_per_stack,
-		.maxlen		= sizeof(sysctl_perf_event_max_contexts_per_stack),
-		.mode		= 0644,
-		.proc_handler	= perf_event_max_stack_handler,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_ONE_THOUSAND,
-	},
 #endif
 	{
 		.procname	= "panic_on_warn",

From a9ebcb88136ca80cb53de27ca5ae77de18bbe368 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Mon, 17 Feb 2025 18:38:20 +0200
Subject: [PATCH 0468/1173] mm/memremap: Pass down MEMREMAP_* flags to
 arch_memremap_wb()

x86 version of arch_memremap_wb() needs the flags to decide if the mapping
has to be encrypted or decrypted.

Pass down the flag to arch_memremap_wb(). All current implementations
ignore the argument.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: linux-mm@kvack.org
Link: https://lore.kernel.org/r/20250217163822.343400-2-kirill.shutemov@linux.intel.com
---
 arch/arm/include/asm/io.h   | 2 +-
 arch/arm/mm/ioremap.c       | 2 +-
 arch/arm/mm/nommu.c         | 2 +-
 arch/riscv/include/asm/io.h | 2 +-
 kernel/iomem.c              | 5 +++--
 5 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index 1815748f5d2ac..bae5edf348efa 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -381,7 +381,7 @@ void __iomem *ioremap_wc(resource_size_t res_cookie, size_t size);
 void iounmap(volatile void __iomem *io_addr);
 #define iounmap iounmap
 
-void *arch_memremap_wb(phys_addr_t phys_addr, size_t size);
+void *arch_memremap_wb(phys_addr_t phys_addr, size_t size, unsigned long flags);
 #define arch_memremap_wb arch_memremap_wb
 
 /*
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index 89f1c97f3079c..748698e91a4b4 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -436,7 +436,7 @@ void __arm_iomem_set_ro(void __iomem *ptr, size_t size)
 	set_memory_ro((unsigned long)ptr, PAGE_ALIGN(size) / PAGE_SIZE);
 }
 
-void *arch_memremap_wb(phys_addr_t phys_addr, size_t size)
+void *arch_memremap_wb(phys_addr_t phys_addr, size_t size, unsigned long flags)
 {
 	return (__force void *)arch_ioremap_caller(phys_addr, size,
 						   MT_MEMORY_RW,
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index 1a8f6914ee59d..d638cc87807e2 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -248,7 +248,7 @@ void __iomem *pci_remap_cfgspace(resource_size_t res_cookie, size_t size)
 EXPORT_SYMBOL_GPL(pci_remap_cfgspace);
 #endif
 
-void *arch_memremap_wb(phys_addr_t phys_addr, size_t size)
+void *arch_memremap_wb(phys_addr_t phys_addr, size_t size, unsigned long flags)
 {
 	return (void *)phys_addr;
 }
diff --git a/arch/riscv/include/asm/io.h b/arch/riscv/include/asm/io.h
index 1c5c641075d2f..0257f4aa7ff45 100644
--- a/arch/riscv/include/asm/io.h
+++ b/arch/riscv/include/asm/io.h
@@ -136,7 +136,7 @@ __io_writes_outs(outs, u64, q, __io_pbr(), __io_paw())
 #include <asm-generic/io.h>
 
 #ifdef CONFIG_MMU
-#define arch_memremap_wb(addr, size)	\
+#define arch_memremap_wb(addr, size, flags)	\
 	((__force void *)ioremap_prot((addr), (size), _PAGE_KERNEL))
 #endif
 
diff --git a/kernel/iomem.c b/kernel/iomem.c
index dc2120776e1c3..75e61c1c6bc07 100644
--- a/kernel/iomem.c
+++ b/kernel/iomem.c
@@ -6,7 +6,8 @@
 #include <linux/ioremap.h>
 
 #ifndef arch_memremap_wb
-static void *arch_memremap_wb(resource_size_t offset, unsigned long size)
+static void *arch_memremap_wb(resource_size_t offset, unsigned long size,
+			      unsigned long flags)
 {
 #ifdef ioremap_cache
 	return (__force void *)ioremap_cache(offset, size);
@@ -91,7 +92,7 @@ void *memremap(resource_size_t offset, size_t size, unsigned long flags)
 		if (is_ram == REGION_INTERSECTS)
 			addr = try_ram_remap(offset, size, flags);
 		if (!addr)
-			addr = arch_memremap_wb(offset, size);
+			addr = arch_memremap_wb(offset, size, flags);
 	}
 
 	/*

From 81256a50aa0fddefbf4849db8cad9f70c5167c04 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Mon, 17 Feb 2025 18:38:21 +0200
Subject: [PATCH 0469/1173] x86/mm: Make memremap(MEMREMAP_WB) map memory as
 encrypted by default

Currently memremap(MEMREMAP_WB) can produce decrypted/shared mapping:

  memremap(MEMREMAP_WB)
    arch_memremap_wb()
      ioremap_cache()
        __ioremap_caller(.encrytped = false)

In such cases, the IORES_MAP_ENCRYPTED flag on the memory will determine
if the resulting mapping is encrypted or decrypted.

Creating a decrypted mapping without explicit request from the caller is
risky:

  - It can inadvertently expose the guest's data and compromise the
    guest.

  - Accessing private memory via shared/decrypted mapping on TDX will
    either trigger implicit conversion to shared or #VE (depending on
    VMM implementation).

    Implicit conversion is destructive: subsequent access to the same
    memory via private mapping will trigger a hard-to-debug #VE crash.

The kernel already provides a way to request decrypted mapping
explicitly via the MEMREMAP_DEC flag.

Modify memremap(MEMREMAP_WB) to produce encrypted/private mapping by
default unless MEMREMAP_DEC is specified or if the kernel runs on
a machine with SME enabled.

It fixes the crash due to #VE on kexec in TDX guests if CONFIG_EISA is
enabled.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: linux-mm@kvack.org
Link: https://lore.kernel.org/r/20250217163822.343400-3-kirill.shutemov@linux.intel.com
---
 arch/x86/include/asm/io.h | 3 +++
 arch/x86/mm/ioremap.c     | 8 ++++++++
 2 files changed, 11 insertions(+)

diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index ed580c7f9d0aa..1a0dc2b2bf5b8 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -175,6 +175,9 @@ extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size, un
 extern void __iomem *ioremap_encrypted(resource_size_t phys_addr, unsigned long size);
 #define ioremap_encrypted ioremap_encrypted
 
+void *arch_memremap_wb(phys_addr_t phys_addr, size_t size, unsigned long flags);
+#define arch_memremap_wb arch_memremap_wb
+
 /**
  * ioremap     -   map bus memory into CPU space
  * @offset:    bus address of the memory
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 38ff7791a9c72..42c90b4207738 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -503,6 +503,14 @@ void iounmap(volatile void __iomem *addr)
 }
 EXPORT_SYMBOL(iounmap);
 
+void *arch_memremap_wb(phys_addr_t phys_addr, size_t size, unsigned long flags)
+{
+	if ((flags & MEMREMAP_DEC) || cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT))
+		return (void __force *)ioremap_cache(phys_addr, size);
+
+	return (void __force *)ioremap_encrypted(phys_addr, size);
+}
+
 /*
  * Convert a physical pointer to a virtual kernel pointer for /dev/mem
  * access

From 64aad4749d7911f8c5e69d93a929a269605dd3cb Mon Sep 17 00:00:00 2001
From: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Date: Sun, 16 Feb 2025 14:26:14 +0200
Subject: [PATCH 0470/1173] ACPI/processor_idle: Export
 acpi_processor_ffh_play_dead()

The kernel test robot reported the following build error:

  >> ERROR: modpost: "acpi_processor_ffh_play_dead" [drivers/acpi/processor.ko] undefined!

Caused by this recently merged commit:

  541ddf31e300 ("ACPI/processor_idle: Add FFH state handling")

The build failure is due to an oversight in the 'CONFIG_ACPI_PROCESSOR=m' case,
the function export is missing. Add it.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202502151207.FA9UO1iX-lkp@intel.com/
Fixes: 541ddf31e300 ("ACPI/processor_idle: Add FFH state handling")
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/r/de5bf4f116779efde315782a15146fdc77a4a044.camel@linux.intel.com
---
 arch/x86/kernel/acpi/cstate.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index 5bdb65516969d..86c87c01d23df 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -214,6 +214,7 @@ void acpi_processor_ffh_play_dead(struct acpi_processor_cx *cx)
 	percpu_entry = per_cpu_ptr(cpu_cstate_entry, cpu);
 	mwait_play_dead(percpu_entry->states[cx->index].eax);
 }
+EXPORT_SYMBOL_GPL(acpi_processor_ffh_play_dead);
 
 void __cpuidle acpi_processor_ffh_cstate_enter(struct acpi_processor_cx *cx)
 {

From d90c9de9de2f1712df56de6e4f7d6982d358cabe Mon Sep 17 00:00:00 2001
From: "Guilherme G. Piccoli" <gpiccoli@igalia.com>
Date: Sat, 15 Feb 2025 17:58:16 -0300
Subject: [PATCH 0471/1173] x86/tsc: Always save/restore TSC sched_clock() on
 suspend/resume

TSC could be reset in deep ACPI sleep states, even with invariant TSC.

That's the reason we have sched_clock() save/restore functions, to deal
with this situation. But what happens is that such functions are guarded
with a check for the stability of sched_clock - if not considered stable,
the save/restore routines aren't executed.

On top of that, we have a clear comment in native_sched_clock() saying
that *even* with TSC unstable, we continue using TSC for sched_clock due
to its speed.

In other words, if we have a situation of TSC getting detected as unstable,
it marks the sched_clock as unstable as well, so subsequent S3 sleep cycles
could bring bogus sched_clock values due to the lack of the save/restore
mechanism, causing warnings like this:

  [22.954918] ------------[ cut here ]------------
  [22.954923] Delta way too big! 18446743750843854390 ts=18446744072977390405 before=322133536015 after=322133536015 write stamp=18446744072977390405
  [22.954923] If you just came from a suspend/resume,
  [22.954923] please switch to the trace global clock:
  [22.954923]   echo global > /sys/kernel/tracing/trace_clock
  [22.954923] or add trace_clock=global to the kernel command line
  [22.954937] WARNING: CPU: 2 PID: 5728 at kernel/trace/ring_buffer.c:2890 rb_add_timestamp+0x193/0x1c0

Notice that the above was reproduced even with "trace_clock=global".

The fix for that is to _always_ save/restore the sched_clock on suspend
cycle _if TSC is used_ as sched_clock - only if we fallback to jiffies
the sched_clock_stable() check becomes relevant to save/restore the
sched_clock.

Debugged-by: Thadeu Lima de Souza Cascardo <cascardo@igalia.com>
Signed-off-by: Guilherme G. Piccoli <gpiccoli@igalia.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: stable@vger.kernel.org
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250215210314.351480-1-gpiccoli@igalia.com
---
 arch/x86/kernel/tsc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 34dec0b72ea8d..88e5a4ed9db3a 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -959,7 +959,7 @@ static unsigned long long cyc2ns_suspend;
 
 void tsc_save_sched_clock_state(void)
 {
-	if (!sched_clock_stable())
+	if (!static_branch_likely(&__use_tsc) && !sched_clock_stable())
 		return;
 
 	cyc2ns_suspend = sched_clock();
@@ -979,7 +979,7 @@ void tsc_restore_sched_clock_state(void)
 	unsigned long flags;
 	int cpu;
 
-	if (!sched_clock_stable())
+	if (!static_branch_likely(&__use_tsc) && !sched_clock_stable())
 		return;
 
 	local_irq_save(flags);

From 282f395244df3663dc24e97a86087431c9192513 Mon Sep 17 00:00:00 2001
From: Qasim Ijaz <qasdev00@gmail.com>
Date: Sat, 15 Feb 2025 12:52:49 +0000
Subject: [PATCH 0472/1173] x86/mm: Replace open-coded gap bounding with
 clamp()

Rather than manually bounding gap between gap_min and gap_max,
use the well-known clamp() macro to make the code easier to read.

Signed-off-by: Qasim Ijaz <qasdev00@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250215125249.10729-1-qasdev00@gmail.com
---
 arch/x86/mm/mmap.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index b8a6ffffb4519..5ed2109211dab 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -84,7 +84,6 @@ static unsigned long mmap_base(unsigned long rnd, unsigned long task_size,
 {
 	unsigned long gap = rlim_stack->rlim_cur;
 	unsigned long pad = stack_maxrandom_size(task_size) + stack_guard_gap;
-	unsigned long gap_min, gap_max;
 
 	/* Values close to RLIM_INFINITY can overflow. */
 	if (gap + pad > gap)
@@ -94,13 +93,7 @@ static unsigned long mmap_base(unsigned long rnd, unsigned long task_size,
 	 * Top of mmap area (just below the process stack).
 	 * Leave an at least ~128 MB hole with possible stack randomization.
 	 */
-	gap_min = SIZE_128M;
-	gap_max = (task_size / 6) * 5;
-
-	if (gap < gap_min)
-		gap = gap_min;
-	else if (gap > gap_max)
-		gap = gap_max;
+	gap = clamp(gap, SIZE_128M, (task_size / 6) * 5);
 
 	return PAGE_ALIGN(task_size - gap - rnd);
 }

From 38b14061947fa546491656e3f5e388d4fedf8dba Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Thu, 20 Feb 2025 15:20:10 -0500
Subject: [PATCH 0473/1173] ftrace: Fix accounting of adding subops to a
 manager ops

Function graph uses a subops and manager ops mechanism to attach to
ftrace.  The manager ops connects to ftrace and the functions it connects
to is defined by a list of subops that it manages.

The function hash that defines what the above ops attaches to limits the
functions to attach if the hash has any content. If the hash is empty, it
means to trace all functions.

The creation of the manager ops hash is done by iterating over all the
subops hashes. If any of the subops hashes is empty, it means that the
manager ops hash must trace all functions as well.

The issue is in the creation of the manager ops. When a second subops is
attached, a new hash is created by starting it as NULL and adding the
subops one at a time. But the NULL ops is mistaken as an empty hash, and
once an empty hash is found, it stops the loop of subops and just enables
all functions.

  # echo "f:myevent1 kernel_clone" >> /sys/kernel/tracing/dynamic_events
  # cat /sys/kernel/tracing/enabled_functions
kernel_clone (1)           	tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60

  # echo "f:myevent2 schedule_timeout" >> /sys/kernel/tracing/dynamic_events
  # cat /sys/kernel/tracing/enabled_functions
trace_initcall_start_cb (1)             tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60
run_init_process (1)            tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60
try_to_run_init_process (1)             tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60
x86_pmu_show_pmu_cap (1)                tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60
cleanup_rapl_pmus (1)                   tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60
uncore_free_pcibus_map (1)              tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60
uncore_types_exit (1)                   tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60
uncore_pci_exit.part.0 (1)              tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60
kvm_shutdown (1)                tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60
vmx_dump_msrs (1)               tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60
vmx_cleanup_l1d_flush (1)               tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60
[..]

Fix this by initializing the new hash to NULL and if the hash is NULL do
not treat it as an empty hash but instead allocate by copying the content
of the first sub ops. Then on subsequent iterations, the new hash will not
be NULL, but the content of the previous subops. If that first subops
attached to all functions, then new hash may assume that the manager ops
also needs to attach to all functions.

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Link: https://lore.kernel.org/20250220202055.060300046@goodmis.org
Fixes: 5fccc7552ccbc ("ftrace: Add subops logic to allow one ops to manage many")
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/ftrace.c | 33 ++++++++++++++++++++++-----------
 1 file changed, 22 insertions(+), 11 deletions(-)

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 728ecda6e8d4d..bec54dc272049 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3220,15 +3220,22 @@ static struct ftrace_hash *copy_hash(struct ftrace_hash *src)
  *  The filter_hash updates uses just the append_hash() function
  *  and the notrace_hash does not.
  */
-static int append_hash(struct ftrace_hash **hash, struct ftrace_hash *new_hash)
+static int append_hash(struct ftrace_hash **hash, struct ftrace_hash *new_hash,
+		       int size_bits)
 {
 	struct ftrace_func_entry *entry;
 	int size;
 	int i;
 
-	/* An empty hash does everything */
-	if (ftrace_hash_empty(*hash))
-		return 0;
+	if (*hash) {
+		/* An empty hash does everything */
+		if (ftrace_hash_empty(*hash))
+			return 0;
+	} else {
+		*hash = alloc_ftrace_hash(size_bits);
+		if (!*hash)
+			return -ENOMEM;
+	}
 
 	/* If new_hash has everything make hash have everything */
 	if (ftrace_hash_empty(new_hash)) {
@@ -3292,16 +3299,18 @@ static int intersect_hash(struct ftrace_hash **hash, struct ftrace_hash *new_has
 /* Return a new hash that has a union of all @ops->filter_hash entries */
 static struct ftrace_hash *append_hashes(struct ftrace_ops *ops)
 {
-	struct ftrace_hash *new_hash;
+	struct ftrace_hash *new_hash = NULL;
 	struct ftrace_ops *subops;
+	int size_bits;
 	int ret;
 
-	new_hash = alloc_ftrace_hash(ops->func_hash->filter_hash->size_bits);
-	if (!new_hash)
-		return NULL;
+	if (ops->func_hash->filter_hash)
+		size_bits = ops->func_hash->filter_hash->size_bits;
+	else
+		size_bits = FTRACE_HASH_DEFAULT_BITS;
 
 	list_for_each_entry(subops, &ops->subop_list, list) {
-		ret = append_hash(&new_hash, subops->func_hash->filter_hash);
+		ret = append_hash(&new_hash, subops->func_hash->filter_hash, size_bits);
 		if (ret < 0) {
 			free_ftrace_hash(new_hash);
 			return NULL;
@@ -3310,7 +3319,8 @@ static struct ftrace_hash *append_hashes(struct ftrace_ops *ops)
 		if (ftrace_hash_empty(new_hash))
 			break;
 	}
-	return new_hash;
+	/* Can't return NULL as that means this failed */
+	return new_hash ? : EMPTY_HASH;
 }
 
 /* Make @ops trace evenything except what all its subops do not trace */
@@ -3505,7 +3515,8 @@ int ftrace_startup_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int
 		filter_hash = alloc_and_copy_ftrace_hash(size_bits, ops->func_hash->filter_hash);
 		if (!filter_hash)
 			return -ENOMEM;
-		ret = append_hash(&filter_hash, subops->func_hash->filter_hash);
+		ret = append_hash(&filter_hash, subops->func_hash->filter_hash,
+				  size_bits);
 		if (ret < 0) {
 			free_ftrace_hash(filter_hash);
 			return ret;

From 8eb4b09e0bbd30981305643229fe7640ad41b667 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Thu, 20 Feb 2025 15:20:11 -0500
Subject: [PATCH 0474/1173] ftrace: Do not add duplicate entries in subops
 manager ops

Check if a function is already in the manager ops of a subops. A manager
ops contains multiple subops, and if two or more subops are tracing the
same function, the manager ops only needs a single entry in its hash.

Cc: stable@vger.kernel.org
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Link: https://lore.kernel.org/20250220202055.226762894@goodmis.org
Fixes: 4f554e955614f ("ftrace: Add ftrace_set_filter_ips function")
Tested-by: Heiko Carstens <hca@linux.ibm.com>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/ftrace.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index bec54dc272049..6b0c25761ccb1 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -5718,6 +5718,9 @@ __ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove)
 			return -ENOENT;
 		free_hash_entry(hash, entry);
 		return 0;
+	} else if (__ftrace_lookup_ip(hash, ip) != NULL) {
+		/* Already exists */
+		return 0;
 	}
 
 	entry = add_hash_entry(hash, ip);

From ded9140622358a154efb3a777025fa7f7ae2c2d9 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Thu, 20 Feb 2025 15:20:12 -0500
Subject: [PATCH 0475/1173] fprobe: Always unregister fgraph function from ops

When the last fprobe is removed, it calls unregister_ftrace_graph() to
remove the graph_ops from function graph. The issue is when it does so, it
calls return before removing the function from its graph ops via
ftrace_set_filter_ips(). This leaves the last function lingering in the
fprobe's fgraph ops and if a probe is added it also enables that last
function (even though the callback will just drop it, it does add unneeded
overhead to make that call).

  # echo "f:myevent1 kernel_clone" >> /sys/kernel/tracing/dynamic_events
  # cat /sys/kernel/tracing/enabled_functions
kernel_clone (1)           	tramp: 0xffffffffc02f3000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60

  # echo "f:myevent2 schedule_timeout" >> /sys/kernel/tracing/dynamic_events
  # cat /sys/kernel/tracing/enabled_functions
kernel_clone (1)           	tramp: 0xffffffffc02f3000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60
schedule_timeout (1)           	tramp: 0xffffffffc02f3000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60

  # > /sys/kernel/tracing/dynamic_events
  # cat /sys/kernel/tracing/enabled_functions

  # echo "f:myevent3 kmem_cache_free" >> /sys/kernel/tracing/dynamic_events
  # cat /sys/kernel/tracing/enabled_functions
kmem_cache_free (1)           	tramp: 0xffffffffc0219000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60
schedule_timeout (1)           	tramp: 0xffffffffc0219000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60

The above enabled a fprobe on kernel_clone, and then on schedule_timeout.
The content of the enabled_functions shows the functions that have a
callback attached to them. The fprobe attached to those functions
properly. Then the fprobes were cleared, and enabled_functions was empty
after that. But after adding a fprobe on kmem_cache_free, the
enabled_functions shows that the schedule_timeout was attached again. This
is because it was still left in the fprobe ops that is used to tell
function graph what functions it wants callbacks from.

Cc: stable@vger.kernel.org
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Link: https://lore.kernel.org/20250220202055.393254452@goodmis.org
Fixes: 4346ba1604093 ("fprobe: Rewrite fprobe on function-graph tracer")
Tested-by: Heiko Carstens <hca@linux.ibm.com>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/fprobe.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index 2560b312ad576..62e8f7d56602f 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -403,11 +403,9 @@ static void fprobe_graph_remove_ips(unsigned long *addrs, int num)
 	lockdep_assert_held(&fprobe_mutex);
 
 	fprobe_graph_active--;
-	if (!fprobe_graph_active) {
-		/* Q: should we unregister it ? */
+	/* Q: should we unregister it ? */
+	if (!fprobe_graph_active)
 		unregister_ftrace_graph(&fprobe_graph_ops);
-		return;
-	}
 
 	ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 1, 0);
 }

From ca26554a1498bc905c4a39fb42d55d93f3ae8df2 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Thu, 20 Feb 2025 15:20:13 -0500
Subject: [PATCH 0476/1173] fprobe: Fix accounting of when to unregister from
 function graph

When adding a new fprobe, it will update the function hash to the
functions the fprobe is attached to and register with function graph to
have it call the registered functions. The fprobe_graph_active variable
keeps track of the number of fprobes that are using function graph.

If two fprobes attach to the same function, it increments the
fprobe_graph_active for each of them. But when they are removed, the first
fprobe to be removed will see that the function it is attached to is also
used by another fprobe and it will not remove that function from
function_graph. The logic will skip decrementing the fprobe_graph_active
variable.

This causes the fprobe_graph_active variable to not go to zero when all
fprobes are removed, and in doing so it does not unregister from
function graph. As the fgraph ops hash will now be empty, and an empty
filter hash means all functions are enabled, this triggers function graph
to add a callback to the fprobe infrastructure for every function!

 # echo "f:myevent1 kernel_clone" >> /sys/kernel/tracing/dynamic_events
 # echo "f:myevent2 kernel_clone%return" >> /sys/kernel/tracing/dynamic_events
 # cat /sys/kernel/tracing/enabled_functions
kernel_clone (1)           	tramp: 0xffffffffc0024000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60

 # > /sys/kernel/tracing/dynamic_events
 # cat /sys/kernel/tracing/enabled_functions
trace_initcall_start_cb (1)             tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170
run_init_process (1)            tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170
try_to_run_init_process (1)             tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170
x86_pmu_show_pmu_cap (1)                tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170
cleanup_rapl_pmus (1)                   tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170
uncore_free_pcibus_map (1)              tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170
uncore_types_exit (1)                   tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170
uncore_pci_exit.part.0 (1)              tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170
kvm_shutdown (1)                tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170
vmx_dump_msrs (1)               tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170
[..]

 # cat /sys/kernel/tracing/enabled_functions | wc -l
54702

If a fprobe is being removed and all its functions are also traced by
other fprobes, still decrement the fprobe_graph_active counter.

Cc: stable@vger.kernel.org
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Link: https://lore.kernel.org/20250220202055.565129766@goodmis.org
Fixes: 4346ba1604093 ("fprobe: Rewrite fprobe on function-graph tracer")
Closes: https://lore.kernel.org/all/20250217114918.10397-A-hca@linux.ibm.com/
Reported-by: Heiko Carstens <hca@linux.ibm.com>
Tested-by: Heiko Carstens <hca@linux.ibm.com>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/fprobe.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index 62e8f7d56602f..33082c4e8154e 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -407,7 +407,8 @@ static void fprobe_graph_remove_ips(unsigned long *addrs, int num)
 	if (!fprobe_graph_active)
 		unregister_ftrace_graph(&fprobe_graph_ops);
 
-	ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 1, 0);
+	if (num)
+		ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 1, 0);
 }
 
 static int symbols_cmp(const void *a, const void *b)
@@ -677,8 +678,7 @@ int unregister_fprobe(struct fprobe *fp)
 	}
 	del_fprobe_hash(fp);
 
-	if (count)
-		fprobe_graph_remove_ips(addrs, count);
+	fprobe_graph_remove_ips(addrs, count);
 
 	kfree_rcu(hlist_array, rcu);
 	fp->hlist_array = NULL;

From e85c5e9792b942381ad92ccd0ff745b6d408a91f Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Thu, 20 Feb 2025 15:20:14 -0500
Subject: [PATCH 0477/1173] selftests/ftrace: Update fprobe test to check
 enabled_functions file

A few bugs were found in the fprobe accounting logic along with it using
the function graph infrastructure. Update the fprobe selftest to catch
those bugs in case they or something similar shows up in the future.

The test now checks the enabled_functions file which shows all the
functions attached to ftrace or fgraph. When enabling a fprobe, make sure
that its corresponding function is also added to that file. Also add two
more fprobes to enable to make sure that the fprobe logic works properly
with multiple probes.

Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Link: https://lore.kernel.org/20250220202055.733001756@goodmis.org
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Tested-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 .../test.d/dynevent/add_remove_fprobe.tc      | 54 +++++++++++++++++++
 1 file changed, 54 insertions(+)

diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe.tc
index dc25bcf4f9e2c..449f9d8be7462 100644
--- a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe.tc
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe.tc
@@ -7,12 +7,38 @@ echo 0 > events/enable
 echo > dynamic_events
 
 PLACE=$FUNCTION_FORK
+PLACE2="kmem_cache_free"
+PLACE3="schedule_timeout"
 
 echo "f:myevent1 $PLACE" >> dynamic_events
+
+# Make sure the event is attached and is the only one
+grep -q $PLACE enabled_functions
+cnt=`cat enabled_functions | wc -l`
+if [ $cnt -ne 1 ]; then
+	exit_fail
+fi
+
 echo "f:myevent2 $PLACE%return" >> dynamic_events
 
+# It should till be the only attached function
+cnt=`cat enabled_functions | wc -l`
+if [ $cnt -ne 1 ]; then
+	exit_fail
+fi
+
+# add another event
+echo "f:myevent3 $PLACE2" >> dynamic_events
+
+grep -q $PLACE2 enabled_functions
+cnt=`cat enabled_functions | wc -l`
+if [ $cnt -ne 2 ]; then
+	exit_fail
+fi
+
 grep -q myevent1 dynamic_events
 grep -q myevent2 dynamic_events
+grep -q myevent3 dynamic_events
 test -d events/fprobes/myevent1
 test -d events/fprobes/myevent2
 
@@ -21,6 +47,34 @@ echo "-:myevent2" >> dynamic_events
 grep -q myevent1 dynamic_events
 ! grep -q myevent2 dynamic_events
 
+# should still have 2 left
+cnt=`cat enabled_functions | wc -l`
+if [ $cnt -ne 2 ]; then
+	exit_fail
+fi
+
 echo > dynamic_events
 
+# Should have none left
+cnt=`cat enabled_functions | wc -l`
+if [ $cnt -ne 0 ]; then
+	exit_fail
+fi
+
+echo "f:myevent4 $PLACE" >> dynamic_events
+
+# Should only have one enabled
+cnt=`cat enabled_functions | wc -l`
+if [ $cnt -ne 1 ]; then
+	exit_fail
+fi
+
+echo > dynamic_events
+
+# Should have none left
+cnt=`cat enabled_functions | wc -l`
+if [ $cnt -ne 0 ]; then
+	exit_fail
+fi
+
 clear_trace

From 57b76bedc5c52c66968183b5ef57234894c25ce7 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 20 Feb 2025 15:07:49 +0100
Subject: [PATCH 0478/1173] ftrace: Correct preemption accounting for function
 tracing.

The function tracer should record the preemption level at the point when
the function is invoked. If the tracing subsystem decrement the
preemption counter it needs to correct this before feeding the data into
the trace buffer. This was broken in the commit cited below while
shifting the preempt-disabled section.

Use tracing_gen_ctx_dec() which properly subtracts one from the
preemption counter on a preemptible kernel.

Cc: stable@vger.kernel.org
Cc: Wander Lairson Costa <wander@redhat.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/20250220140749.pfw8qoNZ@linutronix.de
Fixes: ce5e48036c9e7 ("ftrace: disable preemption when recursion locked")
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Tested-by: Wander Lairson Costa <wander@redhat.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_functions.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index d358c9935164d..df56f9b760109 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -216,7 +216,7 @@ function_trace_call(unsigned long ip, unsigned long parent_ip,
 
 	parent_ip = function_get_true_parent_ip(parent_ip, fregs);
 
-	trace_ctx = tracing_gen_ctx();
+	trace_ctx = tracing_gen_ctx_dec();
 
 	data = this_cpu_ptr(tr->array_buffer.data);
 	if (!atomic_read(&data->disabled))
@@ -321,7 +321,6 @@ function_no_repeats_trace_call(unsigned long ip, unsigned long parent_ip,
 	struct trace_array *tr = op->private;
 	struct trace_array_cpu *data;
 	unsigned int trace_ctx;
-	unsigned long flags;
 	int bit;
 
 	if (unlikely(!tr->function_enabled))
@@ -347,8 +346,7 @@ function_no_repeats_trace_call(unsigned long ip, unsigned long parent_ip,
 	if (is_repeat_check(tr, last_info, ip, parent_ip))
 		goto out;
 
-	local_save_flags(flags);
-	trace_ctx = tracing_gen_ctx_flags(flags);
+	trace_ctx = tracing_gen_ctx_dec();
 	process_repeats(tr, ip, parent_ip, last_info, trace_ctx);
 
 	trace_function(tr, ip, parent_ip, trace_ctx);

From 2fa6a01345b538faa7b0fae8f723bb6977312428 Mon Sep 17 00:00:00 2001
From: Adrian Huang <ahuang12@lenovo.com>
Date: Thu, 20 Feb 2025 11:15:28 +0800
Subject: [PATCH 0479/1173] tracing: Fix memory leak when reading set_event
 file

kmemleak reports the following memory leak after reading set_event file:

  # cat /sys/kernel/tracing/set_event

  # cat /sys/kernel/debug/kmemleak
  unreferenced object 0xff110001234449e0 (size 16):
  comm "cat", pid 13645, jiffies 4294981880
  hex dump (first 16 bytes):
    01 00 00 00 00 00 00 00 a8 71 e7 84 ff ff ff ff  .........q......
  backtrace (crc c43abbc):
    __kmalloc_cache_noprof+0x3ca/0x4b0
    s_start+0x72/0x2d0
    seq_read_iter+0x265/0x1080
    seq_read+0x2c9/0x420
    vfs_read+0x166/0xc30
    ksys_read+0xf4/0x1d0
    do_syscall_64+0x79/0x150
    entry_SYSCALL_64_after_hwframe+0x76/0x7e

The issue can be reproduced regardless of whether set_event is empty or
not. Here is an example about the valid content of set_event.

  # cat /sys/kernel/tracing/set_event
  sched:sched_process_fork
  sched:sched_switch
  sched:sched_wakeup
  *:*:mod:trace_events_sample

The root cause is that s_next() returns NULL when nothing is found.
This results in s_stop() attempting to free a NULL pointer because its
parameter is NULL.

Fix the issue by freeing the memory appropriately when s_next() fails
to find anything.

Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/20250220031528.7373-1-ahuang12@lenovo.com
Fixes: b355247df104 ("tracing: Cache ":mod:" events for modules not loaded yet")
Signed-off-by: Adrian Huang <ahuang12@lenovo.com>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 4cb275316e51e..513de9ceb80ef 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1591,6 +1591,13 @@ s_next(struct seq_file *m, void *v, loff_t *pos)
 		return iter;
 #endif
 
+	/*
+	 * The iter is allocated in s_start() and passed via the 'v'
+	 * parameter. To stop the iterator, NULL must be returned. But
+	 * the return value is what the 'v' parameter in s_stop() receives
+	 * and frees. Free iter here as it will no longer be used.
+	 */
+	kfree(iter);
 	return NULL;
 }
 
@@ -1667,9 +1674,9 @@ static int s_show(struct seq_file *m, void *v)
 }
 #endif
 
-static void s_stop(struct seq_file *m, void *p)
+static void s_stop(struct seq_file *m, void *v)
 {
-	kfree(p);
+	kfree(v);
 	t_stop(m, NULL);
 }
 

From 4087e16b033140cf2ce509ec23503bddec818a16 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Fri, 14 Feb 2025 16:07:46 +0100
Subject: [PATCH 0480/1173] x86/locking: Use ALT_OUTPUT_SP() for
 percpu_{,try_}cmpxchg{64,128}_op()

percpu_{,try_}cmpxchg{64,128}() macros use CALL instruction inside
asm statement in one of their alternatives. Use ALT_OUTPUT_SP()
macro to add required dependence on %esp register.

ALT_OUTPUT_SP() implements the above dependence by adding
ASM_CALL_CONSTRAINT to its arguments. This constraint should be used
for any inline asm which has a CALL instruction, otherwise the
compiler may schedule the asm before the frame pointer gets set up
by the containing function, causing objtool to print a "call without
frame pointer save/setup" warning.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250214150929.5780-1-ubizjak@gmail.com
---
 arch/x86/include/asm/percpu.h | 28 ++++++++++++++--------------
 1 file changed, 14 insertions(+), 14 deletions(-)

diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index e525cd85f999f..0ab991fba7de3 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -350,9 +350,9 @@ do {									\
 									\
 	asm qual (ALTERNATIVE("call this_cpu_cmpxchg8b_emu",		\
 			      "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
-		  : [var] "+m" (__my_cpu_var(_var)),			\
-		    "+a" (old__.low),					\
-		    "+d" (old__.high)					\
+		  : ALT_OUTPUT_SP([var] "+m" (__my_cpu_var(_var)),	\
+				  "+a" (old__.low),			\
+				  "+d" (old__.high))			\
 		  : "b" (new__.low),					\
 		    "c" (new__.high),					\
 		    "S" (&(_var))					\
@@ -381,10 +381,10 @@ do {									\
 	asm qual (ALTERNATIVE("call this_cpu_cmpxchg8b_emu",		\
 			      "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
 		  CC_SET(z)						\
-		  : CC_OUT(z) (success),				\
-		    [var] "+m" (__my_cpu_var(_var)),			\
-		    "+a" (old__.low),					\
-		    "+d" (old__.high)					\
+		  : ALT_OUTPUT_SP(CC_OUT(z) (success),			\
+				  [var] "+m" (__my_cpu_var(_var)),	\
+				  "+a" (old__.low),			\
+				  "+d" (old__.high))			\
 		  : "b" (new__.low),					\
 		    "c" (new__.high),					\
 		    "S" (&(_var))					\
@@ -421,9 +421,9 @@ do {									\
 									\
 	asm qual (ALTERNATIVE("call this_cpu_cmpxchg16b_emu",		\
 			      "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
-		  : [var] "+m" (__my_cpu_var(_var)),			\
-		    "+a" (old__.low),					\
-		    "+d" (old__.high)					\
+		  : ALT_OUTPUT_SP([var] "+m" (__my_cpu_var(_var)),	\
+				  "+a" (old__.low),			\
+				  "+d" (old__.high))			\
 		  : "b" (new__.low),					\
 		    "c" (new__.high),					\
 		    "S" (&(_var))					\
@@ -452,10 +452,10 @@ do {									\
 	asm qual (ALTERNATIVE("call this_cpu_cmpxchg16b_emu",		\
 			      "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
 		  CC_SET(z)						\
-		  : CC_OUT(z) (success),				\
-		    [var] "+m" (__my_cpu_var(_var)),			\
-		    "+a" (old__.low),					\
-		    "+d" (old__.high)					\
+		  : ALT_OUTPUT_SP(CC_OUT(z) (success),			\
+				  [var] "+m" (__my_cpu_var(_var)),	\
+				  "+a" (old__.low),			\
+				  "+d" (old__.high))			\
 		  : "b" (new__.low),					\
 		    "c" (new__.high),					\
 		    "S" (&(_var))					\

From 2d352ec9fcb5d965318e7855b2406a7a14e9ae13 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Fri, 14 Feb 2025 16:07:47 +0100
Subject: [PATCH 0481/1173] x86/locking: Use asm_inline for
 {,try_}cmpxchg{64,128} emulations

According to:

  https://gcc.gnu.org/onlinedocs/gcc/Size-of-an-asm.html

the usage of asm pseudo directives in the asm template can confuse
the compiler to wrongly estimate the size of the generated
code.

The ALTERNATIVE macro expands to several asm pseudo directives,
so its usage in {,try_}cmpxchg{64,128} causes instruction length estimate
to fail by an order of magnitude (the specially instrumented compiler
reports the estimated length of these asm templates to be more than 20
instructions long).

This incorrect estimate further causes unoptimal inlining
decisions, unoptimal instruction scheduling and unoptimal code block
alignments for functions that use these locking primitives.

Use asm_inline instead:

  https://gcc.gnu.org/pipermail/gcc-patches/2018-December/512349.html

which is a feature that makes GCC pretend some inline assembler code
is tiny (while it would think it is huge), instead of just asm.

For code size estimation, the size of the asm is then taken as
the minimum size of one instruction, ignoring how many instructions
compiler thinks it is.

The effect of this patch on x86_64 target is minor, since 128-bit
functions are rarely used on this target. The code size of the resulting
defconfig object file stays the same:

      text       data     bss      dec         hex filename
  27456612    4638523  814148 32909283     1f627e3 vmlinux-old.o
  27456612    4638523  814148 32909283     1f627e3 vmlinux-new.o

but the patch has minor effect on code layout due to the different
scheduling decisions in functions containing changed macros.

There is no effect on the x64_32 target, the code size of the resulting
defconfig object file and the code layout stays the same:

      text       data     bss      dec         hex filename
  18883870    2679275 1707916 23271061     1631695 vmlinux-old.o
  18883870    2679275 1707916 23271061     1631695 vmlinux-new.o

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250214150929.5780-2-ubizjak@gmail.com
---
 arch/x86/include/asm/cmpxchg_32.h | 32 +++++++------
 arch/x86/include/asm/percpu.h     | 77 +++++++++++++++----------------
 2 files changed, 55 insertions(+), 54 deletions(-)

diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h
index fd1282a783ddb..95b5f990ca88e 100644
--- a/arch/x86/include/asm/cmpxchg_32.h
+++ b/arch/x86/include/asm/cmpxchg_32.h
@@ -91,12 +91,14 @@ static __always_inline bool __try_cmpxchg64_local(volatile u64 *ptr, u64 *oldp,
 	union __u64_halves o = { .full = (_old), },			\
 			   n = { .full = (_new), };			\
 									\
-	asm volatile(ALTERNATIVE(_lock_loc				\
-				 "call cmpxchg8b_emu",			\
-				 _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \
-		     : ALT_OUTPUT_SP("+a" (o.low), "+d" (o.high))	\
-		     : "b" (n.low), "c" (n.high), [ptr] "S" (_ptr)	\
-		     : "memory");					\
+	asm_inline volatile(						\
+		ALTERNATIVE(_lock_loc					\
+			    "call cmpxchg8b_emu",			\
+			    _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8)	\
+		: ALT_OUTPUT_SP("+a" (o.low), "+d" (o.high))		\
+		: "b" (n.low), "c" (n.high),				\
+		  [ptr] "S" (_ptr)					\
+		: "memory");						\
 									\
 	o.full;								\
 })
@@ -119,14 +121,16 @@ static __always_inline u64 arch_cmpxchg64_local(volatile u64 *ptr, u64 old, u64
 			   n = { .full = (_new), };			\
 	bool ret;							\
 									\
-	asm volatile(ALTERNATIVE(_lock_loc				\
-				 "call cmpxchg8b_emu",			\
-				 _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \
-		     CC_SET(e)						\
-		     : ALT_OUTPUT_SP(CC_OUT(e) (ret),			\
-				     "+a" (o.low), "+d" (o.high))	\
-		     : "b" (n.low), "c" (n.high), [ptr] "S" (_ptr)	\
-		     : "memory");					\
+	asm_inline volatile(						\
+		ALTERNATIVE(_lock_loc					\
+			    "call cmpxchg8b_emu",			\
+			    _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \
+		CC_SET(e)						\
+		: ALT_OUTPUT_SP(CC_OUT(e) (ret),			\
+				"+a" (o.low), "+d" (o.high))		\
+		: "b" (n.low), "c" (n.high),				\
+		  [ptr] "S" (_ptr)					\
+		: "memory");						\
 									\
 	if (unlikely(!ret))						\
 		*(_oldp) = o.full;					\
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 0ab991fba7de3..08f5f61690b7a 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -348,15 +348,14 @@ do {									\
 	old__.var = _oval;						\
 	new__.var = _nval;						\
 									\
-	asm qual (ALTERNATIVE("call this_cpu_cmpxchg8b_emu",		\
-			      "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
-		  : ALT_OUTPUT_SP([var] "+m" (__my_cpu_var(_var)),	\
-				  "+a" (old__.low),			\
-				  "+d" (old__.high))			\
-		  : "b" (new__.low),					\
-		    "c" (new__.high),					\
-		    "S" (&(_var))					\
-		  : "memory");						\
+	asm_inline qual (						\
+		ALTERNATIVE("call this_cpu_cmpxchg8b_emu",		\
+			    "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
+		: ALT_OUTPUT_SP([var] "+m" (__my_cpu_var(_var)),	\
+				"+a" (old__.low), "+d" (old__.high))	\
+		: "b" (new__.low), "c" (new__.high),			\
+		  "S" (&(_var))						\
+		: "memory");						\
 									\
 	old__.var;							\
 })
@@ -378,17 +377,16 @@ do {									\
 	old__.var = *_oval;						\
 	new__.var = _nval;						\
 									\
-	asm qual (ALTERNATIVE("call this_cpu_cmpxchg8b_emu",		\
-			      "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
-		  CC_SET(z)						\
-		  : ALT_OUTPUT_SP(CC_OUT(z) (success),			\
-				  [var] "+m" (__my_cpu_var(_var)),	\
-				  "+a" (old__.low),			\
-				  "+d" (old__.high))			\
-		  : "b" (new__.low),					\
-		    "c" (new__.high),					\
-		    "S" (&(_var))					\
-		  : "memory");						\
+	asm_inline qual (						\
+		ALTERNATIVE("call this_cpu_cmpxchg8b_emu",		\
+			    "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
+		CC_SET(z)						\
+		: ALT_OUTPUT_SP(CC_OUT(z) (success),			\
+				[var] "+m" (__my_cpu_var(_var)),	\
+				"+a" (old__.low), "+d" (old__.high))	\
+		: "b" (new__.low), "c" (new__.high),			\
+		  "S" (&(_var))						\
+		: "memory");						\
 	if (unlikely(!success))						\
 		*_oval = old__.var;					\
 									\
@@ -419,15 +417,14 @@ do {									\
 	old__.var = _oval;						\
 	new__.var = _nval;						\
 									\
-	asm qual (ALTERNATIVE("call this_cpu_cmpxchg16b_emu",		\
-			      "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
-		  : ALT_OUTPUT_SP([var] "+m" (__my_cpu_var(_var)),	\
-				  "+a" (old__.low),			\
-				  "+d" (old__.high))			\
-		  : "b" (new__.low),					\
-		    "c" (new__.high),					\
-		    "S" (&(_var))					\
-		  : "memory");						\
+	asm_inline qual (						\
+		ALTERNATIVE("call this_cpu_cmpxchg16b_emu",		\
+			    "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
+		: ALT_OUTPUT_SP([var] "+m" (__my_cpu_var(_var)),	\
+				"+a" (old__.low), "+d" (old__.high))	\
+		: "b" (new__.low), "c" (new__.high),			\
+		  "S" (&(_var))						\
+		: "memory");						\
 									\
 	old__.var;							\
 })
@@ -449,19 +446,19 @@ do {									\
 	old__.var = *_oval;						\
 	new__.var = _nval;						\
 									\
-	asm qual (ALTERNATIVE("call this_cpu_cmpxchg16b_emu",		\
-			      "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
-		  CC_SET(z)						\
-		  : ALT_OUTPUT_SP(CC_OUT(z) (success),			\
-				  [var] "+m" (__my_cpu_var(_var)),	\
-				  "+a" (old__.low),			\
-				  "+d" (old__.high))			\
-		  : "b" (new__.low),					\
-		    "c" (new__.high),					\
-		    "S" (&(_var))					\
-		  : "memory");						\
+	asm_inline qual (						\
+		ALTERNATIVE("call this_cpu_cmpxchg16b_emu",		\
+			    "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
+		CC_SET(z)						\
+		: ALT_OUTPUT_SP(CC_OUT(z) (success),			\
+				[var] "+m" (__my_cpu_var(_var)),	\
+				"+a" (old__.low), "+d" (old__.high))	\
+		: "b" (new__.low), "c" (new__.high),			\
+		  "S" (&(_var))						\
+		: "memory");						\
 	if (unlikely(!success))						\
 		*_oval = old__.var;					\
+									\
 	likely(success);						\
 })
 

From 2d6bff31399b2443aba230cd20f120acb2d4eeb1 Mon Sep 17 00:00:00 2001
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Date: Fri, 14 Feb 2025 11:06:48 +0200
Subject: [PATCH 0482/1173] x86/boot: Move setting of memblock parameters to
 e820__memblock_setup()

Changing memblock parameters, namely bottom_up and allocation upper
limit does not have any effect before memblock initialization in
e820__memblock_setup().

Move the calls to memblock_set_bottom_up() and memblock_set_current_limit()
to e820__memblock_setup() to group all the memblock initial setup and make
setup_arch() more readable.

No functional changes.

Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250214090651.3331663-2-rppt@kernel.org
---
 arch/x86/kernel/e820.c  | 30 ++++++++++++++++++++++++++++++
 arch/x86/kernel/setup.c | 25 -------------------------
 2 files changed, 30 insertions(+), 25 deletions(-)

diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 82b96ed9890ab..8d8bd039d2ac1 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1302,6 +1302,36 @@ void __init e820__memblock_setup(void)
 	int i;
 	u64 end;
 
+#ifdef CONFIG_MEMORY_HOTPLUG
+	/*
+	 * Memory used by the kernel cannot be hot-removed because Linux
+	 * cannot migrate the kernel pages. When memory hotplug is
+	 * enabled, we should prevent memblock from allocating memory
+	 * for the kernel.
+	 *
+	 * ACPI SRAT records all hotpluggable memory ranges. But before
+	 * SRAT is parsed, we don't know about it.
+	 *
+	 * The kernel image is loaded into memory at very early time. We
+	 * cannot prevent this anyway. So on NUMA system, we set any
+	 * node the kernel resides in as un-hotpluggable.
+	 *
+	 * Since on modern servers, one node could have double-digit
+	 * gigabytes memory, we can assume the memory around the kernel
+	 * image is also un-hotpluggable. So before SRAT is parsed, just
+	 * allocate memory near the kernel image to try the best to keep
+	 * the kernel away from hotpluggable memory.
+	 */
+	if (movable_node_is_enabled())
+		memblock_set_bottom_up(true);
+#endif
+
+	/*
+	 * At this point only the first megabyte is mapped for sure, the
+	 * rest of the memory cannot be used for memblock resizing
+	 */
+	memblock_set_current_limit(ISA_END_ADDRESS);
+
 	/*
 	 * The bootstrap memblock region count maximum is 128 entries
 	 * (INIT_MEMBLOCK_REGIONS), but EFI might pass us more E820 entries
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index cebee310e2009..4baadeab8a2ee 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -866,30 +866,6 @@ void __init setup_arch(char **cmdline_p)
 	if (efi_enabled(EFI_BOOT))
 		efi_memblock_x86_reserve_range();
 
-#ifdef CONFIG_MEMORY_HOTPLUG
-	/*
-	 * Memory used by the kernel cannot be hot-removed because Linux
-	 * cannot migrate the kernel pages. When memory hotplug is
-	 * enabled, we should prevent memblock from allocating memory
-	 * for the kernel.
-	 *
-	 * ACPI SRAT records all hotpluggable memory ranges. But before
-	 * SRAT is parsed, we don't know about it.
-	 *
-	 * The kernel image is loaded into memory at very early time. We
-	 * cannot prevent this anyway. So on NUMA system, we set any
-	 * node the kernel resides in as un-hotpluggable.
-	 *
-	 * Since on modern servers, one node could have double-digit
-	 * gigabytes memory, we can assume the memory around the kernel
-	 * image is also un-hotpluggable. So before SRAT is parsed, just
-	 * allocate memory near the kernel image to try the best to keep
-	 * the kernel away from hotpluggable memory.
-	 */
-	if (movable_node_is_enabled())
-		memblock_set_bottom_up(true);
-#endif
-
 	x86_report_nx();
 
 	apic_setup_apic_calls();
@@ -990,7 +966,6 @@ void __init setup_arch(char **cmdline_p)
 
 	cleanup_highmap();
 
-	memblock_set_current_limit(ISA_END_ADDRESS);
 	e820__memblock_setup();
 
 	/*

From 297fb82ebaad50e1c40aab7ac61897bf372842ba Mon Sep 17 00:00:00 2001
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Date: Fri, 14 Feb 2025 11:06:49 +0200
Subject: [PATCH 0483/1173] x86/boot: Split kernel resources setup into the
 setup_kernel_resources() helper function

Makes setup_arch() a bit easier to comprehend.

No functional changes.

Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250214090651.3331663-3-rppt@kernel.org
---
 arch/x86/kernel/setup.c | 36 ++++++++++++++++++++++--------------
 1 file changed, 22 insertions(+), 14 deletions(-)

diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 4baadeab8a2ee..3d95946ab749c 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -527,6 +527,23 @@ void __init reserve_standard_io_resources(void)
 
 }
 
+static void __init setup_kernel_resources(void)
+{
+	code_resource.start = __pa_symbol(_text);
+	code_resource.end = __pa_symbol(_etext)-1;
+	rodata_resource.start = __pa_symbol(__start_rodata);
+	rodata_resource.end = __pa_symbol(__end_rodata)-1;
+	data_resource.start = __pa_symbol(_sdata);
+	data_resource.end = __pa_symbol(_edata)-1;
+	bss_resource.start = __pa_symbol(__bss_start);
+	bss_resource.end = __pa_symbol(__bss_stop)-1;
+
+	insert_resource(&iomem_resource, &code_resource);
+	insert_resource(&iomem_resource, &rodata_resource);
+	insert_resource(&iomem_resource, &data_resource);
+	insert_resource(&iomem_resource, &bss_resource);
+}
+
 static bool __init snb_gfx_workaround_needed(void)
 {
 #ifdef CONFIG_PCI
@@ -845,15 +862,6 @@ void __init setup_arch(char **cmdline_p)
 		root_mountflags &= ~MS_RDONLY;
 	setup_initial_init_mm(_text, _etext, _edata, (void *)_brk_end);
 
-	code_resource.start = __pa_symbol(_text);
-	code_resource.end = __pa_symbol(_etext)-1;
-	rodata_resource.start = __pa_symbol(__start_rodata);
-	rodata_resource.end = __pa_symbol(__end_rodata)-1;
-	data_resource.start = __pa_symbol(_sdata);
-	data_resource.end = __pa_symbol(_edata)-1;
-	bss_resource.start = __pa_symbol(__bss_start);
-	bss_resource.end = __pa_symbol(__bss_stop)-1;
-
 	/*
 	 * x86_configure_nx() is called before parse_early_param() to detect
 	 * whether hardware doesn't support NX (so that the early EHCI debug
@@ -897,11 +905,11 @@ void __init setup_arch(char **cmdline_p)
 	tsc_early_init();
 	x86_init.resources.probe_roms();
 
-	/* after parse_early_param, so could debug it */
-	insert_resource(&iomem_resource, &code_resource);
-	insert_resource(&iomem_resource, &rodata_resource);
-	insert_resource(&iomem_resource, &data_resource);
-	insert_resource(&iomem_resource, &bss_resource);
+	/*
+	 * Add resources for kernel text and data to the iomem_resource.
+	 * Do it after parse_early_param, so it can be debugged.
+	 */
+	setup_kernel_resources();
 
 	e820_add_kernel_range();
 	trim_bios_range();

From d45dd0a9b27ee8be7792ae186bc33ed700144224 Mon Sep 17 00:00:00 2001
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Date: Fri, 14 Feb 2025 11:06:50 +0200
Subject: [PATCH 0484/1173] x86/boot: Split parsing of boot_params into the
 parse_boot_params() helper function

Makes setup_arch() a bit easier to comprehend.

No functional changes.

Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250214090651.3331663-4-rppt@kernel.org
---
 arch/x86/kernel/setup.c | 72 +++++++++++++++++++++++------------------
 1 file changed, 41 insertions(+), 31 deletions(-)

diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 3d95946ab749c..6fb9a851bc197 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -429,6 +429,46 @@ static void __init parse_setup_data(void)
 	}
 }
 
+/*
+ * Translate the fields of 'struct boot_param' into global variables
+ * representing these parameters.
+ */
+static void __init parse_boot_params(void)
+{
+	ROOT_DEV = old_decode_dev(boot_params.hdr.root_dev);
+	screen_info = boot_params.screen_info;
+	edid_info = boot_params.edid_info;
+#ifdef CONFIG_X86_32
+	apm_info.bios = boot_params.apm_bios_info;
+	ist_info = boot_params.ist_info;
+#endif
+	saved_video_mode = boot_params.hdr.vid_mode;
+	bootloader_type = boot_params.hdr.type_of_loader;
+	if ((bootloader_type >> 4) == 0xe) {
+		bootloader_type &= 0xf;
+		bootloader_type |= (boot_params.hdr.ext_loader_type+0x10) << 4;
+	}
+	bootloader_version  = bootloader_type & 0xf;
+	bootloader_version |= boot_params.hdr.ext_loader_ver << 4;
+
+#ifdef CONFIG_BLK_DEV_RAM
+	rd_image_start = boot_params.hdr.ram_size & RAMDISK_IMAGE_START_MASK;
+#endif
+#ifdef CONFIG_EFI
+	if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
+		     EFI32_LOADER_SIGNATURE, 4)) {
+		set_bit(EFI_BOOT, &efi.flags);
+	} else if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
+		     EFI64_LOADER_SIGNATURE, 4)) {
+		set_bit(EFI_BOOT, &efi.flags);
+		set_bit(EFI_64BIT, &efi.flags);
+	}
+#endif
+
+	if (!boot_params.hdr.root_flags)
+		root_mountflags &= ~MS_RDONLY;
+}
+
 static void __init memblock_x86_reserve_range_setup_data(void)
 {
 	struct setup_indirect *indirect;
@@ -806,35 +846,7 @@ void __init setup_arch(char **cmdline_p)
 
 	setup_olpc_ofw_pgd();
 
-	ROOT_DEV = old_decode_dev(boot_params.hdr.root_dev);
-	screen_info = boot_params.screen_info;
-	edid_info = boot_params.edid_info;
-#ifdef CONFIG_X86_32
-	apm_info.bios = boot_params.apm_bios_info;
-	ist_info = boot_params.ist_info;
-#endif
-	saved_video_mode = boot_params.hdr.vid_mode;
-	bootloader_type = boot_params.hdr.type_of_loader;
-	if ((bootloader_type >> 4) == 0xe) {
-		bootloader_type &= 0xf;
-		bootloader_type |= (boot_params.hdr.ext_loader_type+0x10) << 4;
-	}
-	bootloader_version  = bootloader_type & 0xf;
-	bootloader_version |= boot_params.hdr.ext_loader_ver << 4;
-
-#ifdef CONFIG_BLK_DEV_RAM
-	rd_image_start = boot_params.hdr.ram_size & RAMDISK_IMAGE_START_MASK;
-#endif
-#ifdef CONFIG_EFI
-	if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
-		     EFI32_LOADER_SIGNATURE, 4)) {
-		set_bit(EFI_BOOT, &efi.flags);
-	} else if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
-		     EFI64_LOADER_SIGNATURE, 4)) {
-		set_bit(EFI_BOOT, &efi.flags);
-		set_bit(EFI_64BIT, &efi.flags);
-	}
-#endif
+	parse_boot_params();
 
 	x86_init.oem.arch_setup();
 
@@ -858,8 +870,6 @@ void __init setup_arch(char **cmdline_p)
 
 	copy_edd();
 
-	if (!boot_params.hdr.root_flags)
-		root_mountflags &= ~MS_RDONLY;
 	setup_initial_init_mm(_text, _etext, _edata, (void *)_brk_end);
 
 	/*

From efe659ac014647eb048d62475e55cce42d8951d7 Mon Sep 17 00:00:00 2001
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Date: Fri, 14 Feb 2025 11:06:51 +0200
Subject: [PATCH 0485/1173] x86/e820: Drop obsolete E820_TYPE_RESERVED_KERN and
 related code

E820_TYPE_RESERVED_KERN is a relict from the ancient history that was used
to early reserve setup_data, see:

  28bb22379513 ("x86: move reserve_setup_data to setup.c")

Nowadays setup_data is anyway reserved in memblock and there is no point in
carrying E820_TYPE_RESERVED_KERN that behaves exactly like E820_TYPE_RAM
but only complicates the code.

A bonus for removing E820_TYPE_RESERVED_KERN is a small but measurable
speedup of 20 microseconds in init_mem_mappings() on a VM with 32GB or RAM.

Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20250214090651.3331663-5-rppt@kernel.org
---
 arch/x86/include/asm/e820/api.h   |  1 -
 arch/x86/include/asm/e820/types.h |  9 -----
 arch/x86/kernel/e820.c            | 65 ++-----------------------------
 arch/x86/kernel/setup.c           |  1 -
 arch/x86/kernel/tboot.c           |  3 +-
 arch/x86/mm/init_64.c             |  8 ----
 6 files changed, 4 insertions(+), 83 deletions(-)

diff --git a/arch/x86/include/asm/e820/api.h b/arch/x86/include/asm/e820/api.h
index 2e74a7f0e9357..c83645d5b2a86 100644
--- a/arch/x86/include/asm/e820/api.h
+++ b/arch/x86/include/asm/e820/api.h
@@ -29,7 +29,6 @@ extern unsigned long e820__end_of_low_ram_pfn(void);
 extern u64  e820__memblock_alloc_reserved(u64 size, u64 align);
 extern void e820__memblock_setup(void);
 
-extern void e820__reserve_setup_data(void);
 extern void e820__finish_early_params(void);
 extern void e820__reserve_resources(void);
 extern void e820__reserve_resources_late(void);
diff --git a/arch/x86/include/asm/e820/types.h b/arch/x86/include/asm/e820/types.h
index 314f75d886d08..80c4a7266629c 100644
--- a/arch/x86/include/asm/e820/types.h
+++ b/arch/x86/include/asm/e820/types.h
@@ -35,15 +35,6 @@ enum e820_type {
 	 * marking it with the IORES_DESC_SOFT_RESERVED designation.
 	 */
 	E820_TYPE_SOFT_RESERVED	= 0xefffffff,
-
-	/*
-	 * Reserved RAM used by the kernel itself if
-	 * CONFIG_INTEL_TXT=y is enabled, memory of this type
-	 * will be included in the S3 integrity calculation
-	 * and so should not include any memory that the BIOS
-	 * might alter over the S3 transition:
-	 */
-	E820_TYPE_RESERVED_KERN	= 128,
 };
 
 /*
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 8d8bd039d2ac1..9fb67abc32cce 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -187,8 +187,7 @@ void __init e820__range_add(u64 start, u64 size, enum e820_type type)
 static void __init e820_print_type(enum e820_type type)
 {
 	switch (type) {
-	case E820_TYPE_RAM:		/* Fall through: */
-	case E820_TYPE_RESERVED_KERN:	pr_cont("usable");			break;
+	case E820_TYPE_RAM:		pr_cont("usable");			break;
 	case E820_TYPE_RESERVED:	pr_cont("reserved");			break;
 	case E820_TYPE_SOFT_RESERVED:	pr_cont("soft reserved");		break;
 	case E820_TYPE_ACPI:		pr_cont("ACPI data");			break;
@@ -764,7 +763,7 @@ void __init e820__register_nosave_regions(unsigned long limit_pfn)
 
 		pfn = PFN_DOWN(entry->addr + entry->size);
 
-		if (entry->type != E820_TYPE_RAM && entry->type != E820_TYPE_RESERVED_KERN)
+		if (entry->type != E820_TYPE_RAM)
 			register_nosave_region(PFN_UP(entry->addr), pfn);
 
 		if (pfn >= limit_pfn)
@@ -990,60 +989,6 @@ static int __init parse_memmap_opt(char *str)
 }
 early_param("memmap", parse_memmap_opt);
 
-/*
- * Reserve all entries from the bootloader's extensible data nodes list,
- * because if present we are going to use it later on to fetch e820
- * entries from it:
- */
-void __init e820__reserve_setup_data(void)
-{
-	struct setup_indirect *indirect;
-	struct setup_data *data;
-	u64 pa_data, pa_next;
-	u32 len;
-
-	pa_data = boot_params.hdr.setup_data;
-	if (!pa_data)
-		return;
-
-	while (pa_data) {
-		data = early_memremap(pa_data, sizeof(*data));
-		if (!data) {
-			pr_warn("e820: failed to memremap setup_data entry\n");
-			return;
-		}
-
-		len = sizeof(*data);
-		pa_next = data->next;
-
-		e820__range_update(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);
-
-		if (data->type == SETUP_INDIRECT) {
-			len += data->len;
-			early_memunmap(data, sizeof(*data));
-			data = early_memremap(pa_data, len);
-			if (!data) {
-				pr_warn("e820: failed to memremap indirect setup_data\n");
-				return;
-			}
-
-			indirect = (struct setup_indirect *)data->data;
-
-			if (indirect->type != SETUP_INDIRECT)
-				e820__range_update(indirect->addr, indirect->len,
-						   E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);
-		}
-
-		pa_data = pa_next;
-		early_memunmap(data, len);
-	}
-
-	e820__update_table(e820_table);
-
-	pr_info("extended physical RAM map:\n");
-	e820__print_table("reserve setup_data");
-}
-
 /*
  * Called after parse_early_param(), after early parameters (such as mem=)
  * have been processed, in which case we already have an E820 table filled in
@@ -1063,7 +1008,6 @@ void __init e820__finish_early_params(void)
 static const char *__init e820_type_to_string(struct e820_entry *entry)
 {
 	switch (entry->type) {
-	case E820_TYPE_RESERVED_KERN:	/* Fall-through: */
 	case E820_TYPE_RAM:		return "System RAM";
 	case E820_TYPE_ACPI:		return "ACPI Tables";
 	case E820_TYPE_NVS:		return "ACPI Non-volatile Storage";
@@ -1079,7 +1023,6 @@ static const char *__init e820_type_to_string(struct e820_entry *entry)
 static unsigned long __init e820_type_to_iomem_type(struct e820_entry *entry)
 {
 	switch (entry->type) {
-	case E820_TYPE_RESERVED_KERN:	/* Fall-through: */
 	case E820_TYPE_RAM:		return IORESOURCE_SYSTEM_RAM;
 	case E820_TYPE_ACPI:		/* Fall-through: */
 	case E820_TYPE_NVS:		/* Fall-through: */
@@ -1101,7 +1044,6 @@ static unsigned long __init e820_type_to_iores_desc(struct e820_entry *entry)
 	case E820_TYPE_PRAM:		return IORES_DESC_PERSISTENT_MEMORY_LEGACY;
 	case E820_TYPE_RESERVED:	return IORES_DESC_RESERVED;
 	case E820_TYPE_SOFT_RESERVED:	return IORES_DESC_SOFT_RESERVED;
-	case E820_TYPE_RESERVED_KERN:	/* Fall-through: */
 	case E820_TYPE_RAM:		/* Fall-through: */
 	case E820_TYPE_UNUSABLE:	/* Fall-through: */
 	default:			return IORES_DESC_NONE;
@@ -1124,7 +1066,6 @@ static bool __init do_mark_busy(enum e820_type type, struct resource *res)
 	case E820_TYPE_PRAM:
 	case E820_TYPE_PMEM:
 		return false;
-	case E820_TYPE_RESERVED_KERN:
 	case E820_TYPE_RAM:
 	case E820_TYPE_ACPI:
 	case E820_TYPE_NVS:
@@ -1353,7 +1294,7 @@ void __init e820__memblock_setup(void)
 		if (entry->type == E820_TYPE_SOFT_RESERVED)
 			memblock_reserve(entry->addr, entry->size);
 
-		if (entry->type != E820_TYPE_RAM && entry->type != E820_TYPE_RESERVED_KERN)
+		if (entry->type != E820_TYPE_RAM)
 			continue;
 
 		memblock_add(entry->addr, entry->size);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 6fb9a851bc197..46d92d04b6da4 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -895,7 +895,6 @@ void __init setup_arch(char **cmdline_p)
 		setup_clear_cpu_cap(X86_FEATURE_APIC);
 	}
 
-	e820__reserve_setup_data();
 	e820__finish_early_params();
 
 	if (efi_enabled(EFI_BOOT))
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index 4c1bcb6053fc0..46b8f1f16676e 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -200,8 +200,7 @@ static int tboot_setup_sleep(void)
 	tboot->num_mac_regions = 0;
 
 	for (i = 0; i < e820_table->nr_entries; i++) {
-		if ((e820_table->entries[i].type != E820_TYPE_RAM)
-		 && (e820_table->entries[i].type != E820_TYPE_RESERVED_KERN))
+		if (e820_table->entries[i].type != E820_TYPE_RAM)
 			continue;
 
 		add_mac_region(e820_table->entries[i].addr, e820_table->entries[i].size);
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 01ea7c6df3036..519aa53114fac 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -468,8 +468,6 @@ phys_pte_init(pte_t *pte_page, unsigned long paddr, unsigned long paddr_end,
 			if (!after_bootmem &&
 			    !e820__mapped_any(paddr & PAGE_MASK, paddr_next,
 					     E820_TYPE_RAM) &&
-			    !e820__mapped_any(paddr & PAGE_MASK, paddr_next,
-					     E820_TYPE_RESERVED_KERN) &&
 			    !e820__mapped_any(paddr & PAGE_MASK, paddr_next,
 					     E820_TYPE_ACPI))
 				set_pte_init(pte, __pte(0), init);
@@ -525,8 +523,6 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long paddr, unsigned long paddr_end,
 			if (!after_bootmem &&
 			    !e820__mapped_any(paddr & PMD_MASK, paddr_next,
 					     E820_TYPE_RAM) &&
-			    !e820__mapped_any(paddr & PMD_MASK, paddr_next,
-					     E820_TYPE_RESERVED_KERN) &&
 			    !e820__mapped_any(paddr & PMD_MASK, paddr_next,
 					     E820_TYPE_ACPI))
 				set_pmd_init(pmd, __pmd(0), init);
@@ -614,8 +610,6 @@ phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end,
 			if (!after_bootmem &&
 			    !e820__mapped_any(paddr & PUD_MASK, paddr_next,
 					     E820_TYPE_RAM) &&
-			    !e820__mapped_any(paddr & PUD_MASK, paddr_next,
-					     E820_TYPE_RESERVED_KERN) &&
 			    !e820__mapped_any(paddr & PUD_MASK, paddr_next,
 					     E820_TYPE_ACPI))
 				set_pud_init(pud, __pud(0), init);
@@ -703,8 +697,6 @@ phys_p4d_init(p4d_t *p4d_page, unsigned long paddr, unsigned long paddr_end,
 			if (!after_bootmem &&
 			    !e820__mapped_any(paddr & P4D_MASK, paddr_next,
 					     E820_TYPE_RAM) &&
-			    !e820__mapped_any(paddr & P4D_MASK, paddr_next,
-					     E820_TYPE_RESERVED_KERN) &&
 			    !e820__mapped_any(paddr & P4D_MASK, paddr_next,
 					     E820_TYPE_ACPI))
 				set_p4d_init(p4d, __p4d(0), init);

From a37259732a7dc33047fa1e4f9a338088f452e017 Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@surriel.com>
Date: Thu, 13 Feb 2025 11:13:52 -0500
Subject: [PATCH 0486/1173] x86/mm: Make MMU_GATHER_RCU_TABLE_FREE
 unconditional

Currently x86 uses CONFIG_MMU_GATHER_TABLE_FREE when using
paravirt, and not when running on bare metal.

There is no real good reason to do things differently for
each setup. Make them all the same.

Currently get_user_pages_fast synchronizes against page table
freeing in two different ways:

 - on bare metal, by blocking IRQs, which block TLB flush IPIs
 - on paravirt, with MMU_GATHER_RCU_TABLE_FREE

This is done because some paravirt TLB flush implementations
handle the TLB flush in the hypervisor, and will do the flush
even when the target CPU has interrupts disabled.

Always handle page table freeing with MMU_GATHER_RCU_TABLE_FREE.
Using RCU synchronization between page table freeing and get_user_pages_fast()
allows bare metal to also do TLB flushing while interrupts are disabled.

Various places in the mm do still block IRQs or disable preemption
as an implicit way to block RCU frees.

That makes it safe to use INVLPGB on AMD CPUs.

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Rik van Riel <riel@surriel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Manali Shukla <Manali.Shukla@amd.com>
Tested-by: Brendan Jackman <jackmanb@google.com>
Tested-by: Michael Kelley <mhklinux@outlook.com>
Link: https://lore.kernel.org/r/20250213161423.449435-2-riel@surriel.com
---
 arch/x86/Kconfig           |  2 +-
 arch/x86/kernel/paravirt.c | 17 +----------------
 arch/x86/mm/pgtable.c      | 27 ++++-----------------------
 3 files changed, 6 insertions(+), 40 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index c4175f4635eea..d581634c6a59e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -278,7 +278,7 @@ config X86
 	select HAVE_PCI
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
-	select MMU_GATHER_RCU_TABLE_FREE	if PARAVIRT
+	select MMU_GATHER_RCU_TABLE_FREE
 	select MMU_GATHER_MERGE_VMAS
 	select HAVE_POSIX_CPU_TIMERS_TASK_WORK
 	select HAVE_REGS_AND_STACK_ACCESS_API
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 1ccaa3397a670..527f5605aa3e5 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -59,21 +59,6 @@ void __init native_pv_lock_init(void)
 		static_branch_enable(&virt_spin_lock_key);
 }
 
-#ifndef CONFIG_PT_RECLAIM
-static void native_tlb_remove_table(struct mmu_gather *tlb, void *table)
-{
-	struct ptdesc *ptdesc = (struct ptdesc *)table;
-
-	pagetable_dtor(ptdesc);
-	tlb_remove_page(tlb, ptdesc_page(ptdesc));
-}
-#else
-static void native_tlb_remove_table(struct mmu_gather *tlb, void *table)
-{
-	tlb_remove_table(tlb, table);
-}
-#endif
-
 struct static_key paravirt_steal_enabled;
 struct static_key paravirt_steal_rq_enabled;
 
@@ -195,7 +180,7 @@ struct paravirt_patch_template pv_ops = {
 	.mmu.flush_tlb_kernel	= native_flush_tlb_global,
 	.mmu.flush_tlb_one_user	= native_flush_tlb_one_user,
 	.mmu.flush_tlb_multi	= native_flush_tlb_multi,
-	.mmu.tlb_remove_table	= native_tlb_remove_table,
+	.mmu.tlb_remove_table	= tlb_remove_table,
 
 	.mmu.exit_mmap		= paravirt_nop,
 	.mmu.notify_page_enc_status_changed	= paravirt_nop,
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 1fef5ad32d5a8..b1c1f72c1fd1b 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -18,25 +18,6 @@ EXPORT_SYMBOL(physical_mask);
 #define PGTABLE_HIGHMEM 0
 #endif
 
-#ifndef CONFIG_PARAVIRT
-#ifndef CONFIG_PT_RECLAIM
-static inline
-void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table)
-{
-	struct ptdesc *ptdesc = (struct ptdesc *)table;
-
-	pagetable_dtor(ptdesc);
-	tlb_remove_page(tlb, ptdesc_page(ptdesc));
-}
-#else
-static inline
-void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table)
-{
-	tlb_remove_table(tlb, table);
-}
-#endif /* !CONFIG_PT_RECLAIM */
-#endif /* !CONFIG_PARAVIRT */
-
 gfp_t __userpte_alloc_gfp = GFP_PGTABLE_USER | PGTABLE_HIGHMEM;
 
 pgtable_t pte_alloc_one(struct mm_struct *mm)
@@ -64,7 +45,7 @@ early_param("userpte", setup_userpte);
 void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte)
 {
 	paravirt_release_pte(page_to_pfn(pte));
-	paravirt_tlb_remove_table(tlb, page_ptdesc(pte));
+	tlb_remove_table(tlb, page_ptdesc(pte));
 }
 
 #if CONFIG_PGTABLE_LEVELS > 2
@@ -78,21 +59,21 @@ void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd)
 #ifdef CONFIG_X86_PAE
 	tlb->need_flush_all = 1;
 #endif
-	paravirt_tlb_remove_table(tlb, virt_to_ptdesc(pmd));
+	tlb_remove_table(tlb, virt_to_ptdesc(pmd));
 }
 
 #if CONFIG_PGTABLE_LEVELS > 3
 void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud)
 {
 	paravirt_release_pud(__pa(pud) >> PAGE_SHIFT);
-	paravirt_tlb_remove_table(tlb, virt_to_ptdesc(pud));
+	tlb_remove_table(tlb, virt_to_ptdesc(pud));
 }
 
 #if CONFIG_PGTABLE_LEVELS > 4
 void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d)
 {
 	paravirt_release_p4d(__pa(p4d) >> PAGE_SHIFT);
-	paravirt_tlb_remove_table(tlb, virt_to_ptdesc(p4d));
+	tlb_remove_table(tlb, virt_to_ptdesc(p4d));
 }
 #endif	/* CONFIG_PGTABLE_LEVELS > 4 */
 #endif	/* CONFIG_PGTABLE_LEVELS > 3 */

From f2c5c21058270167ce23172022da083b62e5ad4c Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@surriel.com>
Date: Thu, 13 Feb 2025 11:13:53 -0500
Subject: [PATCH 0487/1173] x86/mm: Remove pv_ops.mmu.tlb_remove_table call

Every pv_ops.mmu.tlb_remove_table call ends up calling tlb_remove_table.

Get rid of the indirection by simply calling tlb_remove_table directly,
and not going through the paravirt function pointers.

Suggested-by: Qi Zheng <zhengqi.arch@bytedance.com>
Signed-off-by: Rik van Riel <riel@surriel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Manali Shukla <Manali.Shukla@amd.com>
Tested-by: Brendan Jackman <jackmanb@google.com>
Tested-by: Michael Kelley <mhklinux@outlook.com>
Link: https://lore.kernel.org/r/20250213161423.449435-3-riel@surriel.com
---
 arch/x86/hyperv/mmu.c                 | 1 -
 arch/x86/include/asm/paravirt.h       | 5 -----
 arch/x86/include/asm/paravirt_types.h | 2 --
 arch/x86/kernel/kvm.c                 | 1 -
 arch/x86/kernel/paravirt.c            | 1 -
 arch/x86/xen/mmu_pv.c                 | 1 -
 6 files changed, 11 deletions(-)

diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c
index cc8c3bd0e7c29..1f7c3082a36db 100644
--- a/arch/x86/hyperv/mmu.c
+++ b/arch/x86/hyperv/mmu.c
@@ -239,5 +239,4 @@ void hyperv_setup_mmu_ops(void)
 
 	pr_info("Using hypercall for remote TLB flush\n");
 	pv_ops.mmu.flush_tlb_multi = hyperv_flush_tlb_multi;
-	pv_ops.mmu.tlb_remove_table = tlb_remove_table;
 }
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 041aff51eb50f..38a632a282d40 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -91,11 +91,6 @@ static inline void __flush_tlb_multi(const struct cpumask *cpumask,
 	PVOP_VCALL2(mmu.flush_tlb_multi, cpumask, info);
 }
 
-static inline void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table)
-{
-	PVOP_VCALL2(mmu.tlb_remove_table, tlb, table);
-}
-
 static inline void paravirt_arch_exit_mmap(struct mm_struct *mm)
 {
 	PVOP_VCALL1(mmu.exit_mmap, mm);
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index fea56b04f4365..e26633c004558 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -134,8 +134,6 @@ struct pv_mmu_ops {
 	void (*flush_tlb_multi)(const struct cpumask *cpus,
 				const struct flush_tlb_info *info);
 
-	void (*tlb_remove_table)(struct mmu_gather *tlb, void *table);
-
 	/* Hook for intercepting the destruction of an mm_struct. */
 	void (*exit_mmap)(struct mm_struct *mm);
 	void (*notify_page_enc_status_changed)(unsigned long pfn, int npages, bool enc);
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 7a422a6c5983c..3be9b3342c672 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -838,7 +838,6 @@ static void __init kvm_guest_init(void)
 #ifdef CONFIG_SMP
 	if (pv_tlb_flush_supported()) {
 		pv_ops.mmu.flush_tlb_multi = kvm_flush_tlb_multi;
-		pv_ops.mmu.tlb_remove_table = tlb_remove_table;
 		pr_info("KVM setup pv remote TLB flush\n");
 	}
 
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 527f5605aa3e5..2aa251d0b3089 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -180,7 +180,6 @@ struct paravirt_patch_template pv_ops = {
 	.mmu.flush_tlb_kernel	= native_flush_tlb_global,
 	.mmu.flush_tlb_one_user	= native_flush_tlb_one_user,
 	.mmu.flush_tlb_multi	= native_flush_tlb_multi,
-	.mmu.tlb_remove_table	= tlb_remove_table,
 
 	.mmu.exit_mmap		= paravirt_nop,
 	.mmu.notify_page_enc_status_changed	= paravirt_nop,
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index d078de2c952b3..38971c6dcd4b7 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -2189,7 +2189,6 @@ static const typeof(pv_ops) xen_mmu_ops __initconst = {
 		.flush_tlb_kernel = xen_flush_tlb,
 		.flush_tlb_one_user = xen_flush_tlb_one_user,
 		.flush_tlb_multi = xen_flush_tlb_multi,
-		.tlb_remove_table = tlb_remove_table,
 
 		.pgd_alloc = xen_pgd_alloc,
 		.pgd_free = xen_pgd_free,

From 3fcae7771fb724c276e87e80827b264d2c3ad67e Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 11 Feb 2025 16:57:21 +0200
Subject: [PATCH 0488/1173] x86/pat: Fix W=1 build warning when the
 within_inclusive() function is unused

The within_inclusive() function, in some cases, when CONFIG_X86_64=n,
may be not used.

This, in particular, prevents kernel builds with Clang, `make W=1`
and CONFIG_WERROR=y:

  arch/x86/mm/pat/set_memory.c:215:1: error: unused function 'within_inclusive' [-Werror,-Wunused-function]

Fix this by guarding the definitions with the respective ifdeffery.

See also:

  6863f5643dd7 ("kbuild: allow Clang to find unused static inline functions for W=1 build")

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250211145721.1620552-1-andriy.shevchenko@linux.intel.com
---
 arch/x86/mm/pat/set_memory.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index 7bd0f62ba48fd..84d0bca3be285 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -225,14 +225,14 @@ within(unsigned long addr, unsigned long start, unsigned long end)
 	return addr >= start && addr < end;
 }
 
+#ifdef CONFIG_X86_64
+
 static inline int
 within_inclusive(unsigned long addr, unsigned long start, unsigned long end)
 {
 	return addr >= start && addr <= end;
 }
 
-#ifdef CONFIG_X86_64
-
 /*
  * The kernel image is mapped into two places in the virtual address space
  * (addresses without KASLR, of course):

From 000894d8fc0d787b52a46339f297e20c024a6ca5 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Mon, 10 Feb 2025 12:34:54 +0100
Subject: [PATCH 0489/1173] x86/platform/olpc-xo1-sci: Don't include
 <linux/pm_wakeup.h> directly

The header clearly states that it does not want to be included directly,
only via <linux/(platform_)?device.h>. Which is already present, so
delete the superfluous include.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250210113453.51825-2-wsa+renesas@sang-engineering.com
---
 arch/x86/platform/olpc/olpc-xo1-sci.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/x86/platform/olpc/olpc-xo1-sci.c b/arch/x86/platform/olpc/olpc-xo1-sci.c
index ccb23c73cbe8b..63066e7c85177 100644
--- a/arch/x86/platform/olpc/olpc-xo1-sci.c
+++ b/arch/x86/platform/olpc/olpc-xo1-sci.c
@@ -14,7 +14,6 @@
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
 #include <linux/pm.h>
-#include <linux/pm_wakeup.h>
 #include <linux/power_supply.h>
 #include <linux/suspend.h>
 #include <linux/workqueue.h>

From 0156338a18eba7ee229e59c8928c7056e9753c61 Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Sun, 9 Feb 2025 22:03:32 +0100
Subject: [PATCH 0490/1173] x86/apic: Use str_disabled_enabled() helper in
 print_ipi_mode()

Remove hard-coded strings by using the str_disabled_enabled() helper.

No change in functionality intended.

Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250209210333.5666-2-thorsten.blum@linux.dev
---
 arch/x86/kernel/apic/ipi.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c
index 5da693d633b78..942168da71953 100644
--- a/arch/x86/kernel/apic/ipi.c
+++ b/arch/x86/kernel/apic/ipi.c
@@ -3,6 +3,7 @@
 #include <linux/cpumask.h>
 #include <linux/delay.h>
 #include <linux/smp.h>
+#include <linux/string_choices.h>
 
 #include <asm/io_apic.h>
 
@@ -23,7 +24,7 @@ __setup("no_ipi_broadcast=", apic_ipi_shorthand);
 static int __init print_ipi_mode(void)
 {
 	pr_info("IPI shorthand broadcast: %s\n",
-		apic_ipi_shorthand_off ? "disabled" : "enabled");
+		str_disabled_enabled(apic_ipi_shorthand_off));
 	return 0;
 }
 late_initcall(print_ipi_mode);

From 4ecaa75771a75f2b78a431bf67dea165d19d72a6 Mon Sep 17 00:00:00 2001
From: Yu-Che Cheng <giver@chromium.org>
Date: Wed, 19 Feb 2025 15:07:48 +0800
Subject: [PATCH 0491/1173] thermal: gov_power_allocator: Fix incorrect
 calculation in divvy_up_power()

divvy_up_power() should use weighted_req_power instead of req_power to
calculate granted_power. Otherwise, granted_power may be unexpected as
the denominator total_req_power is a weighted sum.

This is a mistake made during the previous refactor.

Replace req_power with weighted_req_power in divvy_up_power()
calculation.

Fixes: 912e97c67cc3 ("thermal: gov_power_allocator: Move memory allocation out of throttle()")
Signed-off-by: Yu-Che Cheng <giver@chromium.org>
Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
Link: https://patch.msgid.link/20250219-fix-power-allocator-calc-v1-1-48b860291919@chromium.org
[ rjw: Subject and changelog edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/thermal/gov_power_allocator.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/thermal/gov_power_allocator.c b/drivers/thermal/gov_power_allocator.c
index 3b644de3292e2..3b626db55b2b9 100644
--- a/drivers/thermal/gov_power_allocator.c
+++ b/drivers/thermal/gov_power_allocator.c
@@ -370,7 +370,7 @@ static void divvy_up_power(struct power_actor *power, int num_actors,
 
 	for (i = 0; i < num_actors; i++) {
 		struct power_actor *pa = &power[i];
-		u64 req_range = (u64)pa->req_power * power_range;
+		u64 req_range = (u64)pa->weighted_req_power * power_range;
 
 		pa->granted_power = DIV_ROUND_CLOSEST_ULL(req_range,
 							  total_req_power);

From 337369f8ce9e20226402cf139c4f0d3ada7d1705 Mon Sep 17 00:00:00 2001
From: Yunhui Cui <cuiyunhui@bytedance.com>
Date: Sun, 26 Jan 2025 11:32:43 +0800
Subject: [PATCH 0492/1173] locking/mutex: Add MUTEX_WARN_ON() into fast path

Scenario: In platform_device_register, the driver misuses struct
device as platform_data, making kmemdup duplicate a device. Accessing
the duplicate may cause list corruption due to its mutex magic or list
holding old content.
It recurs randomly as the first mutex - getting process skips the slow
path and mutex check. Adding MUTEX_WARN_ON(lock->magic!= lock) in
__mutex_trylock_fast() makes it always happen.

Signed-off-by: Yunhui Cui <cuiyunhui@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250126033243.53069-1-cuiyunhui@bytedance.com
---
 kernel/locking/mutex.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index b36f23de48f1b..19b636f60a24f 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -143,6 +143,8 @@ static __always_inline bool __mutex_trylock_fast(struct mutex *lock)
 	unsigned long curr = (unsigned long)current;
 	unsigned long zero = 0UL;
 
+	MUTEX_WARN_ON(lock->magic != lock);
+
 	if (atomic_long_try_cmpxchg_acquire(&lock->owner, &zero, curr))
 		return true;
 

From b796ea8489918efb34cef0972ec3771b4a7b6f9a Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Wed, 19 Feb 2025 12:17:57 +0100
Subject: [PATCH 0493/1173] sched/core: Remove duplicate included header file
 stats.h

The header file stats.h is included twice. Remove the redundant include
and the following make includecheck warning:

  stats.h is included more than once

Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250219111756.3070-2-thorsten.blum@linux.dev
---
 kernel/sched/core.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 165c90ba64ea9..b00f884701a6b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -91,7 +91,6 @@
 #include "autogroup.h"
 #include "pelt.h"
 #include "smp.h"
-#include "stats.h"
 
 #include "../workqueue_internal.h"
 #include "../../io_uring/io-wq.h"

From 1a5d3492f8e14719184945893c610e0802c05533 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Wed, 19 Feb 2025 14:24:23 +0000
Subject: [PATCH 0494/1173] sched: Add unlikey branch hints to several system
 calls

Adding an unlikely() hint on early error return paths improves the
run-time performance of several sched related system calls.

Benchmarking on an i9-12900 shows the following per system call
performance improvements:

		       before     after     improvement
sched_getattr          182.4ns    170.6ns      ~6.5%
sched_setattr          284.3ns    267.6ns      ~5.9%
sched_getparam         161.6ns    148.1ns      ~8.4%
sched_setparam        1265.4ns   1227.6ns      ~3.0%
sched_getscheduler     129.4ns    118.2ns      ~8.7%
sched_setscheduler    1237.3ns   1216.7ns      ~1.7%

Results are based on running 20 tests with turbo disabled (to reduce
clock freq turbo changes), with 10 second run per test based on the
number of system calls per second. The % standard deviation of the
measurements for the 20 tests was 0.05% to 0.40%, so the results are
reliable.

Tested on kernel build with gcc 14.2.1

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250219142423.45516-1-colin.i.king@gmail.com
---
 kernel/sched/syscalls.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c
index 456d339be98fb..9f40348f1dc7a 100644
--- a/kernel/sched/syscalls.c
+++ b/kernel/sched/syscalls.c
@@ -875,7 +875,7 @@ do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
 {
 	struct sched_param lparam;
 
-	if (!param || pid < 0)
+	if (unlikely(!param || pid < 0))
 		return -EINVAL;
 	if (copy_from_user(&lparam, param, sizeof(struct sched_param)))
 		return -EFAULT;
@@ -984,7 +984,7 @@ SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
 	struct sched_attr attr;
 	int retval;
 
-	if (!uattr || pid < 0 || flags)
+	if (unlikely(!uattr || pid < 0 || flags))
 		return -EINVAL;
 
 	retval = sched_copy_attr(uattr, &attr);
@@ -1049,7 +1049,7 @@ SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
 	struct task_struct *p;
 	int retval;
 
-	if (!param || pid < 0)
+	if (unlikely(!param || pid < 0))
 		return -EINVAL;
 
 	scoped_guard (rcu) {
@@ -1085,8 +1085,8 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
 	struct task_struct *p;
 	int retval;
 
-	if (!uattr || pid < 0 || usize > PAGE_SIZE ||
-	    usize < SCHED_ATTR_SIZE_VER0 || flags)
+	if (unlikely(!uattr || pid < 0 || usize > PAGE_SIZE ||
+		      usize < SCHED_ATTR_SIZE_VER0 || flags))
 		return -EINVAL;
 
 	scoped_guard (rcu) {

From 2df1ad0d25803399056d439425e271802cd243f6 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Sun, 2 Feb 2025 15:23:22 -0500
Subject: [PATCH 0495/1173] x86/arch_prctl: Simplify sys_arch_prctl()

Use in_ia32_syscall() instead of a compat syscall entry.

No change in functionality intended.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Link: https://lore.kernel.org/r/20250202202323.422113-2-brgerst@gmail.com
---
 arch/x86/entry/syscalls/syscall_32.tbl |  2 +-
 arch/x86/include/asm/proto.h           |  3 +--
 arch/x86/kernel/process.c              |  5 ++++-
 arch/x86/kernel/process_32.c           |  5 -----
 arch/x86/kernel/process_64.c           | 18 ------------------
 5 files changed, 6 insertions(+), 27 deletions(-)

diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 4d0fb2fba7e20..62283097a7cc7 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -396,7 +396,7 @@
 381	i386	pkey_alloc		sys_pkey_alloc
 382	i386	pkey_free		sys_pkey_free
 383	i386	statx			sys_statx
-384	i386	arch_prctl		sys_arch_prctl			compat_sys_arch_prctl
+384	i386	arch_prctl		sys_arch_prctl
 385	i386	io_pgetevents		sys_io_pgetevents_time32	compat_sys_io_pgetevents
 386	i386	rseq			sys_rseq
 393	i386	semget			sys_semget
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index 484f4f0131a5c..05224a6958727 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -15,7 +15,6 @@ void entry_SYSCALL_64(void);
 void entry_SYSCALL_64_safe_stack(void);
 void entry_SYSRETQ_unsafe_stack(void);
 void entry_SYSRETQ_end(void);
-long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2);
 #endif
 
 #ifdef CONFIG_X86_32
@@ -41,6 +40,6 @@ void x86_configure_nx(void);
 
 extern int reboot_force;
 
-long do_arch_prctl_common(int option, unsigned long arg2);
+long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2);
 
 #endif /* _ASM_X86_PROTO_H */
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 6da6769d7254a..0f398a42c1e20 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -1043,7 +1043,7 @@ unsigned long __get_wchan(struct task_struct *p)
 	return addr;
 }
 
-long do_arch_prctl_common(int option, unsigned long arg2)
+SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
 {
 	switch (option) {
 	case ARCH_GET_CPUID:
@@ -1058,5 +1058,8 @@ long do_arch_prctl_common(int option, unsigned long arg2)
 		return fpu_xstate_prctl(option, arg2);
 	}
 
+	if (!in_ia32_syscall())
+		return do_arch_prctl_64(current, option, arg2);
+
 	return -EINVAL;
 }
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 0917c7f25720b..2bdab416298ce 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -215,8 +215,3 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
 	return prev_p;
 }
-
-SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
-{
-	return do_arch_prctl_common(option, arg2);
-}
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 226472332a70d..e067c61b5fca2 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -980,24 +980,6 @@ long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2)
 	return ret;
 }
 
-SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
-{
-	long ret;
-
-	ret = do_arch_prctl_64(current, option, arg2);
-	if (ret == -EINVAL)
-		ret = do_arch_prctl_common(option, arg2);
-
-	return ret;
-}
-
-#ifdef CONFIG_IA32_EMULATION
-COMPAT_SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
-{
-	return do_arch_prctl_common(option, arg2);
-}
-#endif
-
 unsigned long KSTK_ESP(struct task_struct *task)
 {
 	return task_pt_regs(task)->sp;

From 684b12916a107157633311f07bb74307221eff92 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Sun, 2 Feb 2025 15:23:23 -0500
Subject: [PATCH 0496/1173] x86/arch_prctl/64: Clean up ARCH_MAP_VDSO_32

process_64.c is not built on native 32-bit, so CONFIG_X86_32 will never
be set.

No change in functionality intended.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Link: https://lore.kernel.org/r/20250202202323.422113-3-brgerst@gmail.com
---
 arch/x86/kernel/process_64.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index e067c61b5fca2..4ca73ddfb30bc 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -942,7 +942,7 @@ long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2)
 	case ARCH_MAP_VDSO_X32:
 		return prctl_map_vdso(&vdso_image_x32, arg2);
 # endif
-# if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
+# ifdef CONFIG_IA32_EMULATION
 	case ARCH_MAP_VDSO_32:
 		return prctl_map_vdso(&vdso_image_32, arg2);
 # endif

From c34d999ca3145d9fe858258cc3342ec493f47d2e Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 18 Feb 2025 19:22:44 +0000
Subject: [PATCH 0497/1173] rxrpc: rxperf: Fix missing decoding of terminal
 magic cookie

The rxperf RPCs seem to have a magic cookie at the end of the request that
was failing to be taken account of by the unmarshalling of the request.
Fix the rxperf code to expect this.

Fixes: 75bfdbf2fca3 ("rxrpc: Implement an in-kernel rxperf server for testing purposes")
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
Link: https://patch.msgid.link/20250218192250.296870-2-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rxrpc/rxperf.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/net/rxrpc/rxperf.c b/net/rxrpc/rxperf.c
index 7ef93407be830..e848a4777b8c7 100644
--- a/net/rxrpc/rxperf.c
+++ b/net/rxrpc/rxperf.c
@@ -478,6 +478,18 @@ static int rxperf_deliver_request(struct rxperf_call *call)
 		call->unmarshal++;
 		fallthrough;
 	case 2:
+		ret = rxperf_extract_data(call, true);
+		if (ret < 0)
+			return ret;
+
+		/* Deal with the terminal magic cookie. */
+		call->iov_len = 4;
+		call->kvec[0].iov_len	= call->iov_len;
+		call->kvec[0].iov_base	= call->tmp;
+		iov_iter_kvec(&call->iter, READ, call->kvec, 1, call->iov_len);
+		call->unmarshal++;
+		fallthrough;
+	case 3:
 		ret = rxperf_extract_data(call, false);
 		if (ret < 0)
 			return ret;

From 833fefa074444b1e7f7e834cbdce59ce02562ed0 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 18 Feb 2025 19:22:45 +0000
Subject: [PATCH 0498/1173] rxrpc: peer->mtu_lock is redundant

The peer->mtu_lock is only used to lock around writes to peer->max_data -
and nothing else; further, all such writes take place in the I/O thread and
the lock is only ever write-locked and never read-locked.

In a couple of places, the write_seqcount_begin() is wrapped in
preempt_disable/enable(), but not in all places.  This can cause lockdep to
complain:

WARNING: CPU: 0 PID: 1549 at include/linux/seqlock.h:221 rxrpc_input_ack_trailer+0x305/0x430
...
RIP: 0010:rxrpc_input_ack_trailer+0x305/0x430

Fix this by just getting rid of the lock.

Fixes: eeaedc5449d9 ("rxrpc: Implement path-MTU probing using padded PING ACKs (RFC8899)")
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
Link: https://patch.msgid.link/20250218192250.296870-3-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rxrpc/ar-internal.h | 1 -
 net/rxrpc/input.c       | 2 --
 net/rxrpc/peer_event.c  | 9 +--------
 net/rxrpc/peer_object.c | 1 -
 4 files changed, 1 insertion(+), 12 deletions(-)

diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 5e740c4862034..a64a0cab1bf7f 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -360,7 +360,6 @@ struct rxrpc_peer {
 	u8			pmtud_jumbo;	/* Max jumbo packets for the MTU */
 	bool			ackr_adv_pmtud;	/* T if the peer advertises path-MTU */
 	unsigned int		ackr_max_data;	/* Maximum data advertised by peer */
-	seqcount_t		mtu_lock;	/* Lockless MTU access management */
 	unsigned int		if_mtu;		/* Local interface MTU (- hdrsize) for this peer */
 	unsigned int		max_data;	/* Maximum packet data capacity for this peer */
 	unsigned short		hdrsize;	/* header size (IP + UDP + RxRPC) */
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 9047ba13bd31e..24aceb183c2c3 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -810,9 +810,7 @@ static void rxrpc_input_ack_trailer(struct rxrpc_call *call, struct sk_buff *skb
 	if (max_mtu < peer->max_data) {
 		trace_rxrpc_pmtud_reduce(peer, sp->hdr.serial, max_mtu,
 					 rxrpc_pmtud_reduce_ack);
-		write_seqcount_begin(&peer->mtu_lock);
 		peer->max_data = max_mtu;
-		write_seqcount_end(&peer->mtu_lock);
 	}
 
 	max_data = umin(max_mtu, peer->max_data);
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index bc283da9ee402..7f4729234957e 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -130,9 +130,7 @@ static void rxrpc_adjust_mtu(struct rxrpc_peer *peer, unsigned int mtu)
 			peer->pmtud_bad = max_data + 1;
 
 		trace_rxrpc_pmtud_reduce(peer, 0, max_data, rxrpc_pmtud_reduce_icmp);
-		write_seqcount_begin(&peer->mtu_lock);
 		peer->max_data = max_data;
-		write_seqcount_end(&peer->mtu_lock);
 	}
 }
 
@@ -408,13 +406,8 @@ void rxrpc_input_probe_for_pmtud(struct rxrpc_connection *conn, rxrpc_serial_t a
 	}
 
 	max_data = umin(max_data, peer->ackr_max_data);
-	if (max_data != peer->max_data) {
-		preempt_disable();
-		write_seqcount_begin(&peer->mtu_lock);
+	if (max_data != peer->max_data)
 		peer->max_data = max_data;
-		write_seqcount_end(&peer->mtu_lock);
-		preempt_enable();
-	}
 
 	jumbo = max_data + sizeof(struct rxrpc_jumbo_header);
 	jumbo /= RXRPC_JUMBO_SUBPKTLEN;
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index 0fcc87f0409f9..2ddc8ed687429 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -235,7 +235,6 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp,
 		peer->service_conns = RB_ROOT;
 		seqlock_init(&peer->service_conn_lock);
 		spin_lock_init(&peer->lock);
-		seqcount_init(&peer->mtu_lock);
 		peer->debug_id = atomic_inc_return(&rxrpc_debug_id);
 		peer->recent_srtt_us = UINT_MAX;
 		peer->cong_ssthresh = RXRPC_TX_MAX_WINDOW;

From 71f5409176f4ffd460689eb5423a20332d00e342 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 18 Feb 2025 19:22:46 +0000
Subject: [PATCH 0499/1173] rxrpc: Fix locking issues with the peer record hash

rxrpc_new_incoming_peer() can't use spin_lock_bh() whilst its caller has
interrupts disabled.

    WARNING: CPU: 0 PID: 1550 at kernel/softirq.c:369 __local_bh_enable_ip+0x46/0xd0
    ...
    Call Trace:
     rxrpc_alloc_incoming_call+0x1b0/0x400
     rxrpc_new_incoming_call+0x1dd/0x5e0
     rxrpc_input_packet+0x84a/0x920
     rxrpc_io_thread+0x40d/0xb40
     kthread+0x2ec/0x300
     ret_from_fork+0x24/0x40
     ret_from_fork_asm+0x1a/0x30
     </TASK>
    irq event stamp: 1811
    hardirqs last  enabled at (1809): _raw_spin_unlock_irq+0x24/0x50
    hardirqs last disabled at (1810): _raw_read_lock_irq+0x17/0x70
    softirqs last  enabled at (1182): handle_softirqs+0x3ee/0x430
    softirqs last disabled at (1811): rxrpc_new_incoming_peer+0x56/0x120

Fix this by using a plain spin_lock() instead.  IRQs are held, so softirqs
can't happen.

Fixes: a2ea9a907260 ("rxrpc: Use irq-disabling spinlocks between app and I/O thread")
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
Link: https://patch.msgid.link/20250218192250.296870-4-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rxrpc/peer_object.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index 2ddc8ed687429..56e09d161a97f 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -324,10 +324,10 @@ void rxrpc_new_incoming_peer(struct rxrpc_local *local, struct rxrpc_peer *peer)
 	hash_key = rxrpc_peer_hash_key(local, &peer->srx);
 	rxrpc_init_peer(local, peer, hash_key);
 
-	spin_lock_bh(&rxnet->peer_hash_lock);
+	spin_lock(&rxnet->peer_hash_lock);
 	hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key);
 	list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive_new);
-	spin_unlock_bh(&rxnet->peer_hash_lock);
+	spin_unlock(&rxnet->peer_hash_lock);
 }
 
 /*

From add117e48df4788a86a21bd0515833c0a6db1ad1 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 18 Feb 2025 19:22:47 +0000
Subject: [PATCH 0500/1173] afs: Fix the server_list to unuse a displaced
 server rather than putting it

When allocating and building an afs_server_list struct object from a VLDB
record, we look up each server address to get the server record for it -
but a server may have more than one entry in the record and we discard the
duplicate pointers.  Currently, however, when we discard, we only put a
server record, not unuse it - but the lookup got as an active-user count.

The active-user count on an afs_server_list object determines its lifetime
whereas the refcount keeps the memory backing it around.  Failing to reduce
the active-user counter prevents the record from being cleaned up and can
lead to multiple copied being seen - and pointing to deleted afs_cell
objects and other such things.

Fix this by switching the incorrect 'put' to an 'unuse' instead.

Without this, occasionally, a dead server record can be seen in
/proc/net/afs/servers and list corruption may be observed:

    list_del corruption. prev->next should be ffff888102423e40, but was 0000000000000000. (prev=ffff88810140cd38)

Fixes: 977e5f8ed0ab ("afs: Split the usage count on struct afs_server")
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
Link: https://patch.msgid.link/20250218192250.296870-5-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 fs/afs/server_list.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/afs/server_list.c b/fs/afs/server_list.c
index 7e7e567a7f8a2..d20cd902ef949 100644
--- a/fs/afs/server_list.c
+++ b/fs/afs/server_list.c
@@ -97,8 +97,8 @@ struct afs_server_list *afs_alloc_server_list(struct afs_volume *volume,
 				break;
 		if (j < slist->nr_servers) {
 			if (slist->servers[j].server == server) {
-				afs_put_server(volume->cell->net, server,
-					       afs_server_trace_put_slist_isort);
+				afs_unuse_server(volume->cell->net, server,
+						 afs_server_trace_put_slist_isort);
 				continue;
 			}
 

From 1f0fc3374f3345ff1d150c5c56ac5016e5d3826a Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 18 Feb 2025 19:22:48 +0000
Subject: [PATCH 0501/1173] afs: Give an afs_server object a ref on the
 afs_cell object it points to

Give an afs_server object a ref on the afs_cell object it points to so that
the cell doesn't get deleted before the server record.

Whilst this is circular (cell -> vol -> server_list -> server -> cell), the
ref only pins the memory, not the lifetime as that's controlled by the
activity counter.  When the volume's activity counter reaches 0, it
detaches from the cell and discards its server list; when a cell's activity
counter reaches 0, it discards its root volume.  At that point, the
circularity is cut.

Fixes: d2ddc776a458 ("afs: Overhaul volume and server record caching and fileserver rotation")
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
Link: https://patch.msgid.link/20250218192250.296870-6-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 fs/afs/server.c            | 3 +++
 include/trace/events/afs.h | 2 ++
 2 files changed, 5 insertions(+)

diff --git a/fs/afs/server.c b/fs/afs/server.c
index 038f9d0ae3af8..4504e16b458cc 100644
--- a/fs/afs/server.c
+++ b/fs/afs/server.c
@@ -163,6 +163,8 @@ static struct afs_server *afs_install_server(struct afs_cell *cell,
 	rb_insert_color(&server->uuid_rb, &net->fs_servers);
 	hlist_add_head_rcu(&server->proc_link, &net->fs_proc);
 
+	afs_get_cell(cell, afs_cell_trace_get_server);
+
 added_dup:
 	write_seqlock(&net->fs_addr_lock);
 	estate = rcu_dereference_protected(server->endpoint_state,
@@ -442,6 +444,7 @@ static void afs_server_rcu(struct rcu_head *rcu)
 			 atomic_read(&server->active), afs_server_trace_free);
 	afs_put_endpoint_state(rcu_access_pointer(server->endpoint_state),
 			       afs_estate_trace_put_server);
+	afs_put_cell(server->cell, afs_cell_trace_put_server);
 	kfree(server);
 }
 
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index b0db89058c911..958a2460330c0 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -174,6 +174,7 @@ enum yfs_cm_operation {
 	EM(afs_cell_trace_get_queue_dns,	"GET q-dns ") \
 	EM(afs_cell_trace_get_queue_manage,	"GET q-mng ") \
 	EM(afs_cell_trace_get_queue_new,	"GET q-new ") \
+	EM(afs_cell_trace_get_server,		"GET server") \
 	EM(afs_cell_trace_get_vol,		"GET vol   ") \
 	EM(afs_cell_trace_insert,		"INSERT    ") \
 	EM(afs_cell_trace_manage,		"MANAGE    ") \
@@ -182,6 +183,7 @@ enum yfs_cm_operation {
 	EM(afs_cell_trace_put_destroy,		"PUT destry") \
 	EM(afs_cell_trace_put_queue_work,	"PUT q-work") \
 	EM(afs_cell_trace_put_queue_fail,	"PUT q-fail") \
+	EM(afs_cell_trace_put_server,		"PUT server") \
 	EM(afs_cell_trace_put_vol,		"PUT vol   ") \
 	EM(afs_cell_trace_see_source,		"SEE source") \
 	EM(afs_cell_trace_see_ws,		"SEE ws    ") \

From 5c70eb5c593d64d93b178905da215a9fd288a4b5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 20 Feb 2025 13:18:54 +0000
Subject: [PATCH 0502/1173] net: better track kernel sockets lifetime

While kernel sockets are dismantled during pernet_operations->exit(),
their freeing can be delayed by any tx packets still held in qdisc
or device queues, due to skb_set_owner_w() prior calls.

This then trigger the following warning from ref_tracker_dir_exit() [1]

To fix this, make sure that kernel sockets own a reference on net->passive.

Add sk_net_refcnt_upgrade() helper, used whenever a kernel socket
is converted to a refcounted one.

[1]

[  136.263918][   T35] ref_tracker: net notrefcnt@ffff8880638f01e0 has 1/2 users at
[  136.263918][   T35]      sk_alloc+0x2b3/0x370
[  136.263918][   T35]      inet6_create+0x6ce/0x10f0
[  136.263918][   T35]      __sock_create+0x4c0/0xa30
[  136.263918][   T35]      inet_ctl_sock_create+0xc2/0x250
[  136.263918][   T35]      igmp6_net_init+0x39/0x390
[  136.263918][   T35]      ops_init+0x31e/0x590
[  136.263918][   T35]      setup_net+0x287/0x9e0
[  136.263918][   T35]      copy_net_ns+0x33f/0x570
[  136.263918][   T35]      create_new_namespaces+0x425/0x7b0
[  136.263918][   T35]      unshare_nsproxy_namespaces+0x124/0x180
[  136.263918][   T35]      ksys_unshare+0x57d/0xa70
[  136.263918][   T35]      __x64_sys_unshare+0x38/0x40
[  136.263918][   T35]      do_syscall_64+0xf3/0x230
[  136.263918][   T35]      entry_SYSCALL_64_after_hwframe+0x77/0x7f
[  136.263918][   T35]
[  136.343488][   T35] ref_tracker: net notrefcnt@ffff8880638f01e0 has 1/2 users at
[  136.343488][   T35]      sk_alloc+0x2b3/0x370
[  136.343488][   T35]      inet6_create+0x6ce/0x10f0
[  136.343488][   T35]      __sock_create+0x4c0/0xa30
[  136.343488][   T35]      inet_ctl_sock_create+0xc2/0x250
[  136.343488][   T35]      ndisc_net_init+0xa7/0x2b0
[  136.343488][   T35]      ops_init+0x31e/0x590
[  136.343488][   T35]      setup_net+0x287/0x9e0
[  136.343488][   T35]      copy_net_ns+0x33f/0x570
[  136.343488][   T35]      create_new_namespaces+0x425/0x7b0
[  136.343488][   T35]      unshare_nsproxy_namespaces+0x124/0x180
[  136.343488][   T35]      ksys_unshare+0x57d/0xa70
[  136.343488][   T35]      __x64_sys_unshare+0x38/0x40
[  136.343488][   T35]      do_syscall_64+0xf3/0x230
[  136.343488][   T35]      entry_SYSCALL_64_after_hwframe+0x77/0x7f

Fixes: 0cafd77dcd03 ("net: add a refcount tracker for kernel sockets")
Reported-by: syzbot+30a19e01a97420719891@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/67b72aeb.050a0220.14d86d.0283.GAE@google.com/T/#u
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250220131854.4048077-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/sock.h       |  1 +
 net/core/sock.c          | 27 ++++++++++++++++++++++-----
 net/mptcp/subflow.c      |  5 +----
 net/netlink/af_netlink.c | 10 ----------
 net/rds/tcp.c            |  8 ++------
 net/smc/af_smc.c         |  5 +----
 net/sunrpc/svcsock.c     |  5 +----
 net/sunrpc/xprtsock.c    |  8 ++------
 8 files changed, 30 insertions(+), 39 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index 8036b3b79cd8b..7ef728324e4e7 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1751,6 +1751,7 @@ static inline bool sock_allow_reclassification(const struct sock *csk)
 struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
 		      struct proto *prot, int kern);
 void sk_free(struct sock *sk);
+void sk_net_refcnt_upgrade(struct sock *sk);
 void sk_destruct(struct sock *sk);
 struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority);
 void sk_free_unlock_clone(struct sock *sk);
diff --git a/net/core/sock.c b/net/core/sock.c
index eae2ae70a2e03..6c0e87f97fa4a 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2246,6 +2246,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
 			get_net_track(net, &sk->ns_tracker, priority);
 			sock_inuse_add(net, 1);
 		} else {
+			net_passive_inc(net);
 			__netns_tracker_alloc(net, &sk->ns_tracker,
 					      false, priority);
 		}
@@ -2270,6 +2271,7 @@ EXPORT_SYMBOL(sk_alloc);
 static void __sk_destruct(struct rcu_head *head)
 {
 	struct sock *sk = container_of(head, struct sock, sk_rcu);
+	struct net *net = sock_net(sk);
 	struct sk_filter *filter;
 
 	if (sk->sk_destruct)
@@ -2301,14 +2303,28 @@ static void __sk_destruct(struct rcu_head *head)
 	put_cred(sk->sk_peer_cred);
 	put_pid(sk->sk_peer_pid);
 
-	if (likely(sk->sk_net_refcnt))
-		put_net_track(sock_net(sk), &sk->ns_tracker);
-	else
-		__netns_tracker_free(sock_net(sk), &sk->ns_tracker, false);
-
+	if (likely(sk->sk_net_refcnt)) {
+		put_net_track(net, &sk->ns_tracker);
+	} else {
+		__netns_tracker_free(net, &sk->ns_tracker, false);
+		net_passive_dec(net);
+	}
 	sk_prot_free(sk->sk_prot_creator, sk);
 }
 
+void sk_net_refcnt_upgrade(struct sock *sk)
+{
+	struct net *net = sock_net(sk);
+
+	WARN_ON_ONCE(sk->sk_net_refcnt);
+	__netns_tracker_free(net, &sk->ns_tracker, false);
+	net_passive_dec(net);
+	sk->sk_net_refcnt = 1;
+	get_net_track(net, &sk->ns_tracker, GFP_KERNEL);
+	sock_inuse_add(net, 1);
+}
+EXPORT_SYMBOL_GPL(sk_net_refcnt_upgrade);
+
 void sk_destruct(struct sock *sk)
 {
 	bool use_call_rcu = sock_flag(sk, SOCK_RCU_FREE);
@@ -2405,6 +2421,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		 * is not properly dismantling its kernel sockets at netns
 		 * destroy time.
 		 */
+		net_passive_inc(sock_net(newsk));
 		__netns_tracker_alloc(sock_net(newsk), &newsk->ns_tracker,
 				      false, priority);
 	}
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index fd021cf8286ef..dfcbef9c46246 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -1772,10 +1772,7 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family,
 	 * needs it.
 	 * Update ns_tracker to current stack trace and refcounted tracker.
 	 */
-	__netns_tracker_free(net, &sf->sk->ns_tracker, false);
-	sf->sk->sk_net_refcnt = 1;
-	get_net_track(net, &sf->sk->ns_tracker, GFP_KERNEL);
-	sock_inuse_add(net, 1);
+	sk_net_refcnt_upgrade(sf->sk);
 	err = tcp_set_ulp(sf->sk, "mptcp");
 	if (err)
 		goto err_free;
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 85311226183a2..a53ea60d0a78d 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -795,16 +795,6 @@ static int netlink_release(struct socket *sock)
 
 	sock_prot_inuse_add(sock_net(sk), &netlink_proto, -1);
 
-	/* Because struct net might disappear soon, do not keep a pointer. */
-	if (!sk->sk_net_refcnt && sock_net(sk) != &init_net) {
-		__netns_tracker_free(sock_net(sk), &sk->ns_tracker, false);
-		/* Because of deferred_put_nlk_sk and use of work queue,
-		 * it is possible  netns will be freed before this socket.
-		 */
-		sock_net_set(sk, &init_net);
-		__netns_tracker_alloc(&init_net, &sk->ns_tracker,
-				      false, GFP_KERNEL);
-	}
 	call_rcu(&nlk->rcu, deferred_put_nlk_sk);
 	return 0;
 }
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index 0581c53e65170..3cc2f303bf786 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -504,12 +504,8 @@ bool rds_tcp_tune(struct socket *sock)
 			release_sock(sk);
 			return false;
 		}
-		/* Update ns_tracker to current stack trace and refcounted tracker */
-		__netns_tracker_free(net, &sk->ns_tracker, false);
-
-		sk->sk_net_refcnt = 1;
-		netns_tracker_alloc(net, &sk->ns_tracker, GFP_KERNEL);
-		sock_inuse_add(net, 1);
+		sk_net_refcnt_upgrade(sk);
+		put_net(net);
 	}
 	rtn = net_generic(net, rds_tcp_netid);
 	if (rtn->sndbuf_size > 0) {
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index ca6984541edbd..3e6cb35baf25a 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -3337,10 +3337,7 @@ int smc_create_clcsk(struct net *net, struct sock *sk, int family)
 	 * which need net ref.
 	 */
 	sk = smc->clcsock->sk;
-	__netns_tracker_free(net, &sk->ns_tracker, false);
-	sk->sk_net_refcnt = 1;
-	get_net_track(net, &sk->ns_tracker, GFP_KERNEL);
-	sock_inuse_add(net, 1);
+	sk_net_refcnt_upgrade(sk);
 	return 0;
 }
 
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index cb3bd12f5818b..72e5a01df3d35 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1541,10 +1541,7 @@ static struct svc_xprt *svc_create_socket(struct svc_serv *serv,
 	newlen = error;
 
 	if (protocol == IPPROTO_TCP) {
-		__netns_tracker_free(net, &sock->sk->ns_tracker, false);
-		sock->sk->sk_net_refcnt = 1;
-		get_net_track(net, &sock->sk->ns_tracker, GFP_KERNEL);
-		sock_inuse_add(net, 1);
+		sk_net_refcnt_upgrade(sock->sk);
 		if ((error = kernel_listen(sock, 64)) < 0)
 			goto bummer;
 	}
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index c60936d8cef71..940fe65b2a351 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -1941,12 +1941,8 @@ static struct socket *xs_create_sock(struct rpc_xprt *xprt,
 		goto out;
 	}
 
-	if (protocol == IPPROTO_TCP) {
-		__netns_tracker_free(xprt->xprt_net, &sock->sk->ns_tracker, false);
-		sock->sk->sk_net_refcnt = 1;
-		get_net_track(xprt->xprt_net, &sock->sk->ns_tracker, GFP_KERNEL);
-		sock_inuse_add(xprt->xprt_net, 1);
-	}
+	if (protocol == IPPROTO_TCP)
+		sk_net_refcnt_upgrade(sock->sk);
 
 	filp = sock_alloc_file(sock, O_NONBLOCK, NULL);
 	if (IS_ERR(filp))

From 0e4427f8f587c4b603475468bb3aee9418574893 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 20 Feb 2025 09:25:59 +0200
Subject: [PATCH 0503/1173] net: loopback: Avoid sending IP packets without an
 Ethernet header

After commit 22600596b675 ("ipv4: give an IPv4 dev to blackhole_netdev")
IPv4 neighbors can be constructed on the blackhole net device, but they
are constructed with an output function (neigh_direct_output()) that
simply calls dev_queue_xmit(). The latter will transmit packets via
'skb->dev' which might not be the blackhole net device if dst_dev_put()
switched 'dst->dev' to the blackhole net device while another CPU was
using the dst entry in ip_output(), but after it already initialized
'skb->dev' from 'dst->dev'.

Specifically, the following can happen:

    CPU1                                      CPU2

udp_sendmsg(sk1)                          udp_sendmsg(sk2)
udp_send_skb()                            [...]
ip_output()
    skb->dev = skb_dst(skb)->dev
                                          dst_dev_put()
                                              dst->dev = blackhole_netdev
ip_finish_output2()
    resolves neigh on dst->dev
neigh_output()
neigh_direct_output()
dev_queue_xmit()

This will result in IPv4 packets being sent without an Ethernet header
via a valid net device:

tcpdump: verbose output suppressed, use -v[v]... for full protocol decode
listening on enp9s0, link-type EN10MB (Ethernet), snapshot length 262144 bytes
22:07:02.329668 20:00:40:11:18:fb > 45:00:00:44:f4:94, ethertype Unknown
(0x58c6), length 68:
        0x0000:  8dda 74ca f1ae ca6c ca6c 0098 969c 0400  ..t....l.l......
        0x0010:  0000 4730 3f18 6800 0000 0000 0000 9971  ..G0?.h........q
        0x0020:  c4c9 9055 a157 0a70 9ead bf83 38ca ab38  ...U.W.p....8..8
        0x0030:  8add ab96 e052                           .....R

Fix by making sure that neighbors are constructed on top of the
blackhole net device with an output function that simply consumes the
packets, in a similar fashion to dst_discard_out() and
blackhole_netdev_xmit().

Fixes: 8d7017fd621d ("blackhole_netdev: use blackhole_netdev to invalidate dst entries")
Fixes: 22600596b675 ("ipv4: give an IPv4 dev to blackhole_netdev")
Reported-by: Florian Meister <fmei@sfs.com>
Closes: https://lore.kernel.org/netdev/20250210084931.23a5c2e4@hermes.local/
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250220072559.782296-1-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/loopback.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index c8840c3b9a1bc..f1d68153987e1 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -244,8 +244,22 @@ static netdev_tx_t blackhole_netdev_xmit(struct sk_buff *skb,
 	return NETDEV_TX_OK;
 }
 
+static int blackhole_neigh_output(struct neighbour *n, struct sk_buff *skb)
+{
+	kfree_skb(skb);
+	return 0;
+}
+
+static int blackhole_neigh_construct(struct net_device *dev,
+				     struct neighbour *n)
+{
+	n->output = blackhole_neigh_output;
+	return 0;
+}
+
 static const struct net_device_ops blackhole_netdev_ops = {
 	.ndo_start_xmit = blackhole_netdev_xmit,
+	.ndo_neigh_construct = blackhole_neigh_construct,
 };
 
 /* This is a dst-dummy device used specifically for invalidated

From c180188ec02281126045414e90d08422a80f75b4 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Thu, 20 Feb 2025 12:07:52 +0100
Subject: [PATCH 0504/1173] net: set the minimum for
 net_hotdata.netdev_budget_usecs

Commit 7acf8a1e8a28 ("Replace 2 jiffies with sysctl netdev_budget_usecs
to enable softirq tuning") added a possibility to set
net_hotdata.netdev_budget_usecs, but added no lower bound checking.

Commit a4837980fd9f ("net: revert default NAPI poll timeout to 2 jiffies")
made the *initial* value HZ-dependent, so the initial value is at least
2 jiffies even for lower HZ values (2 ms for 1000 Hz, 8ms for 250 Hz, 20
ms for 100 Hz).

But a user still can set improper values by a sysctl. Set .extra1
(the lower bound) for net_hotdata.netdev_budget_usecs to the same value
as in the latter commit. That is to 2 jiffies.

Fixes: a4837980fd9f ("net: revert default NAPI poll timeout to 2 jiffies")
Fixes: 7acf8a1e8a28 ("Replace 2 jiffies with sysctl netdev_budget_usecs to enable softirq tuning")
Signed-off-by: Jiri Slaby (SUSE) <jirislaby@kernel.org>
Cc: Dmitry Yakunin <zeil@yandex-team.ru>
Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Link: https://patch.msgid.link/20250220110752.137639-1-jirislaby@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/sysctl_net_core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index ad2741f1346af..c7769ee0d9c55 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -34,6 +34,7 @@ static int min_sndbuf = SOCK_MIN_SNDBUF;
 static int min_rcvbuf = SOCK_MIN_RCVBUF;
 static int max_skb_frags = MAX_SKB_FRAGS;
 static int min_mem_pcpu_rsv = SK_MEMORY_PCPU_RESERVE;
+static int netdev_budget_usecs_min = 2 * USEC_PER_SEC / HZ;
 
 static int net_msg_warn;	/* Unused, but still a sysctl */
 
@@ -587,7 +588,7 @@ static struct ctl_table net_core_table[] = {
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= SYSCTL_ZERO,
+		.extra1		= &netdev_budget_usecs_min,
 	},
 	{
 		.procname	= "fb_tunnels_only_for_init_net",

From 27843ce6ba3d3122b65066550fe33fb8839f8aef Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 20 Feb 2025 15:53:36 +0000
Subject: [PATCH 0505/1173] ipvlan: ensure network headers are in skb linear
 part

syzbot found that ipvlan_process_v6_outbound() was assuming
the IPv6 network header isis present in skb->head [1]

Add the needed pskb_network_may_pull() calls for both
IPv4 and IPv6 handlers.

[1]
BUG: KMSAN: uninit-value in __ipv6_addr_type+0xa2/0x490 net/ipv6/addrconf_core.c:47
  __ipv6_addr_type+0xa2/0x490 net/ipv6/addrconf_core.c:47
  ipv6_addr_type include/net/ipv6.h:555 [inline]
  ip6_route_output_flags_noref net/ipv6/route.c:2616 [inline]
  ip6_route_output_flags+0x51/0x720 net/ipv6/route.c:2651
  ip6_route_output include/net/ip6_route.h:93 [inline]
  ipvlan_route_v6_outbound+0x24e/0x520 drivers/net/ipvlan/ipvlan_core.c:476
  ipvlan_process_v6_outbound drivers/net/ipvlan/ipvlan_core.c:491 [inline]
  ipvlan_process_outbound drivers/net/ipvlan/ipvlan_core.c:541 [inline]
  ipvlan_xmit_mode_l3 drivers/net/ipvlan/ipvlan_core.c:605 [inline]
  ipvlan_queue_xmit+0xd72/0x1780 drivers/net/ipvlan/ipvlan_core.c:671
  ipvlan_start_xmit+0x5b/0x210 drivers/net/ipvlan/ipvlan_main.c:223
  __netdev_start_xmit include/linux/netdevice.h:5150 [inline]
  netdev_start_xmit include/linux/netdevice.h:5159 [inline]
  xmit_one net/core/dev.c:3735 [inline]
  dev_hard_start_xmit+0x247/0xa20 net/core/dev.c:3751
  sch_direct_xmit+0x399/0xd40 net/sched/sch_generic.c:343
  qdisc_restart net/sched/sch_generic.c:408 [inline]
  __qdisc_run+0x14da/0x35d0 net/sched/sch_generic.c:416
  qdisc_run+0x141/0x4d0 include/net/pkt_sched.h:127
  net_tx_action+0x78b/0x940 net/core/dev.c:5484
  handle_softirqs+0x1a0/0x7c0 kernel/softirq.c:561
  __do_softirq+0x14/0x1a kernel/softirq.c:595
  do_softirq+0x9a/0x100 kernel/softirq.c:462
  __local_bh_enable_ip+0x9f/0xb0 kernel/softirq.c:389
  local_bh_enable include/linux/bottom_half.h:33 [inline]
  rcu_read_unlock_bh include/linux/rcupdate.h:919 [inline]
  __dev_queue_xmit+0x2758/0x57d0 net/core/dev.c:4611
  dev_queue_xmit include/linux/netdevice.h:3311 [inline]
  packet_xmit+0x9c/0x6c0 net/packet/af_packet.c:276
  packet_snd net/packet/af_packet.c:3132 [inline]
  packet_sendmsg+0x93e0/0xa7e0 net/packet/af_packet.c:3164
  sock_sendmsg_nosec net/socket.c:718 [inline]

Fixes: 2ad7bf363841 ("ipvlan: Initial check-in of the IPVLAN driver.")
Reported-by: syzbot+93ab4a777bafb9d9f960@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/67b74f01.050a0220.14d86d.02d8.GAE@google.com/T/#u
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Mahesh Bandewar <maheshb@google.com>
Link: https://patch.msgid.link/20250220155336.61884-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ipvlan/ipvlan_core.c | 21 ++++++++++++++++-----
 1 file changed, 16 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index fd591ddb3884d..ca62188a317ad 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -416,20 +416,25 @@ struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, void *lyr3h,
 
 static noinline_for_stack int ipvlan_process_v4_outbound(struct sk_buff *skb)
 {
-	const struct iphdr *ip4h = ip_hdr(skb);
 	struct net_device *dev = skb->dev;
 	struct net *net = dev_net(dev);
-	struct rtable *rt;
 	int err, ret = NET_XMIT_DROP;
+	const struct iphdr *ip4h;
+	struct rtable *rt;
 	struct flowi4 fl4 = {
 		.flowi4_oif = dev->ifindex,
-		.flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(ip4h)),
 		.flowi4_flags = FLOWI_FLAG_ANYSRC,
 		.flowi4_mark = skb->mark,
-		.daddr = ip4h->daddr,
-		.saddr = ip4h->saddr,
 	};
 
+	if (!pskb_network_may_pull(skb, sizeof(struct iphdr)))
+		goto err;
+
+	ip4h = ip_hdr(skb);
+	fl4.daddr = ip4h->daddr;
+	fl4.saddr = ip4h->saddr;
+	fl4.flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(ip4h));
+
 	rt = ip_route_output_flow(net, &fl4, NULL);
 	if (IS_ERR(rt))
 		goto err;
@@ -488,6 +493,12 @@ static int ipvlan_process_v6_outbound(struct sk_buff *skb)
 	struct net_device *dev = skb->dev;
 	int err, ret = NET_XMIT_DROP;
 
+	if (!pskb_network_may_pull(skb, sizeof(struct ipv6hdr))) {
+		DEV_STATS_INC(dev, tx_errors);
+		kfree_skb(skb);
+		return ret;
+	}
+
 	err = ipvlan_route_v6_outbound(dev, skb);
 	if (unlikely(err)) {
 		DEV_STATS_INC(dev, tx_errors);

From fa52f15c745ce55261b92873676f64f7348cfe82 Mon Sep 17 00:00:00 2001
From: Sean Anderson <sean.anderson@linux.dev>
Date: Thu, 20 Feb 2025 11:29:50 -0500
Subject: [PATCH 0506/1173] net: cadence: macb: Synchronize stats calculations

Stats calculations involve a RMW to add the stat update to the existing
value. This is currently not protected by any synchronization mechanism,
so data races are possible. Add a spinlock to protect the update. The
reader side could be protected using u64_stats, but we would still need
a spinlock for the update side anyway. And we always do an update
immediately before reading the stats anyway.

Fixes: 89e5785fc8a6 ("[PATCH] Atmel MACB ethernet driver")
Signed-off-by: Sean Anderson <sean.anderson@linux.dev>
Link: https://patch.msgid.link/20250220162950.95941-1-sean.anderson@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cadence/macb.h      |  2 ++
 drivers/net/ethernet/cadence/macb_main.c | 12 ++++++++++--
 2 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index 5740c98d8c9f0..2847278d9cd48 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -1279,6 +1279,8 @@ struct macb {
 	struct clk		*rx_clk;
 	struct clk		*tsu_clk;
 	struct net_device	*dev;
+	/* Protects hw_stats and ethtool_stats */
+	spinlock_t		stats_lock;
 	union {
 		struct macb_stats	macb;
 		struct gem_stats	gem;
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 48496209fb164..c1f57d96e63fc 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -1978,10 +1978,12 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id)
 
 		if (status & MACB_BIT(ISR_ROVR)) {
 			/* We missed at least one packet */
+			spin_lock(&bp->stats_lock);
 			if (macb_is_gem(bp))
 				bp->hw_stats.gem.rx_overruns++;
 			else
 				bp->hw_stats.macb.rx_overruns++;
+			spin_unlock(&bp->stats_lock);
 
 			if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE)
 				queue_writel(queue, ISR, MACB_BIT(ISR_ROVR));
@@ -3102,6 +3104,7 @@ static struct net_device_stats *gem_get_stats(struct macb *bp)
 	if (!netif_running(bp->dev))
 		return nstat;
 
+	spin_lock_irq(&bp->stats_lock);
 	gem_update_stats(bp);
 
 	nstat->rx_errors = (hwstat->rx_frame_check_sequence_errors +
@@ -3131,6 +3134,7 @@ static struct net_device_stats *gem_get_stats(struct macb *bp)
 	nstat->tx_aborted_errors = hwstat->tx_excessive_collisions;
 	nstat->tx_carrier_errors = hwstat->tx_carrier_sense_errors;
 	nstat->tx_fifo_errors = hwstat->tx_underrun;
+	spin_unlock_irq(&bp->stats_lock);
 
 	return nstat;
 }
@@ -3138,12 +3142,13 @@ static struct net_device_stats *gem_get_stats(struct macb *bp)
 static void gem_get_ethtool_stats(struct net_device *dev,
 				  struct ethtool_stats *stats, u64 *data)
 {
-	struct macb *bp;
+	struct macb *bp = netdev_priv(dev);
 
-	bp = netdev_priv(dev);
+	spin_lock_irq(&bp->stats_lock);
 	gem_update_stats(bp);
 	memcpy(data, &bp->ethtool_stats, sizeof(u64)
 			* (GEM_STATS_LEN + QUEUE_STATS_LEN * MACB_MAX_QUEUES));
+	spin_unlock_irq(&bp->stats_lock);
 }
 
 static int gem_get_sset_count(struct net_device *dev, int sset)
@@ -3193,6 +3198,7 @@ static struct net_device_stats *macb_get_stats(struct net_device *dev)
 		return gem_get_stats(bp);
 
 	/* read stats from hardware */
+	spin_lock_irq(&bp->stats_lock);
 	macb_update_stats(bp);
 
 	/* Convert HW stats into netdevice stats */
@@ -3226,6 +3232,7 @@ static struct net_device_stats *macb_get_stats(struct net_device *dev)
 	nstat->tx_carrier_errors = hwstat->tx_carrier_errors;
 	nstat->tx_fifo_errors = hwstat->tx_underruns;
 	/* Don't know about heartbeat or window errors... */
+	spin_unlock_irq(&bp->stats_lock);
 
 	return nstat;
 }
@@ -5097,6 +5104,7 @@ static int macb_probe(struct platform_device *pdev)
 		}
 	}
 	spin_lock_init(&bp->lock);
+	spin_lock_init(&bp->stats_lock);
 
 	/* setup capabilities */
 	macb_configure_caps(bp, macb_config);

From 28b04731a38c80092f47437af6c2770765e0b99f Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 20 Feb 2025 16:50:12 -0800
Subject: [PATCH 0507/1173] MAINTAINERS: fix DWMAC S32 entry

Using L: with more than a bare email address causes getmaintainer.pl
to be unable to parse the entry. Fix this by doing as other entries
that use this email address and convert it to an R: entry.

Link: https://patch.msgid.link/20250221005012.1051897-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 3864d473f52f2..ac15093537c6b 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2877,7 +2877,7 @@ F:	drivers/pinctrl/nxp/
 
 ARM/NXP S32G/S32R DWMAC ETHERNET DRIVER
 M:	Jan Petrous <jan.petrous@oss.nxp.com>
-L:	NXP S32 Linux Team <s32@nxp.com>
+R:	s32@nxp.com
 S:	Maintained
 F:	Documentation/devicetree/bindings/net/nxp,s32-dwmac.yaml
 F:	drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c

From 781813db7909d945c33d3b035822225f3598774d Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Thu, 20 Feb 2025 16:12:12 +0100
Subject: [PATCH 0508/1173] i2c: core: Allocate temporary client dynamically
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

drivers/i2c/i2c-core-base.c: In function ‘i2c_detect.isra’:
drivers/i2c/i2c-core-base.c:2544:1: warning: the frame size of 1312 bytes is larger than 1024 bytes [-Wframe-larger-than=]
 2544 | }
      | ^

Fix this by allocating the temporary client structure dynamically, as it
is a rather large structure (1216 bytes, depending on kernel config).
This is basically a revert of the to-be-fixed commit with some
checkpatch improvements.

Fixes: 735668f8e5c9 ("i2c: core: Allocate temp client on the stack in i2c_detect")
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Su Hui <suhui@nfschina.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
[wsa: updated commit message, merged tags from similar patch]
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
 drivers/i2c/i2c-core-base.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c
index 35a221e2c11c1..7ad1ad5c8c3f5 100644
--- a/drivers/i2c/i2c-core-base.c
+++ b/drivers/i2c/i2c-core-base.c
@@ -2506,7 +2506,7 @@ static int i2c_detect_address(struct i2c_client *temp_client,
 static int i2c_detect(struct i2c_adapter *adapter, struct i2c_driver *driver)
 {
 	const unsigned short *address_list;
-	struct i2c_client temp_client;
+	struct i2c_client *temp_client;
 	int i, err = 0;
 
 	address_list = driver->address_list;
@@ -2527,19 +2527,24 @@ static int i2c_detect(struct i2c_adapter *adapter, struct i2c_driver *driver)
 		return 0;
 
 	/* Set up a temporary client to help detect callback */
-	memset(&temp_client, 0, sizeof(temp_client));
-	temp_client.adapter = adapter;
+	temp_client = kzalloc(sizeof(*temp_client), GFP_KERNEL);
+	if (!temp_client)
+		return -ENOMEM;
+
+	temp_client->adapter = adapter;
 
 	for (i = 0; address_list[i] != I2C_CLIENT_END; i += 1) {
 		dev_dbg(&adapter->dev,
 			"found normal entry for adapter %d, addr 0x%02x\n",
 			i2c_adapter_id(adapter), address_list[i]);
-		temp_client.addr = address_list[i];
-		err = i2c_detect_address(&temp_client, driver);
+		temp_client->addr = address_list[i];
+		err = i2c_detect_address(temp_client, driver);
 		if (unlikely(err))
 			break;
 	}
 
+	kfree(temp_client);
+
 	return err;
 }
 

From 50cef76d5cb0e199cda19f026842560f6eedc4f7 Mon Sep 17 00:00:00 2001
From: "Borislav Petkov (AMD)" <bp@alien8.de>
Date: Thu, 23 Jan 2025 14:44:53 +0100
Subject: [PATCH 0509/1173] x86/microcode/AMD: Load only SHA256-checksummed
 patches

Load patches for which the driver carries a SHA256 checksum of the patch
blob.

This can be disabled by adding "microcode.amd_sha_check=off" on the
kernel cmdline. But it is highly NOT recommended.

Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
---
 arch/x86/Kconfig                         |   1 +
 arch/x86/kernel/cpu/microcode/amd.c      | 111 +++++-
 arch/x86/kernel/cpu/microcode/amd_shas.c | 444 +++++++++++++++++++++++
 3 files changed, 554 insertions(+), 2 deletions(-)
 create mode 100644 arch/x86/kernel/cpu/microcode/amd_shas.c

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index be2c311f5118d..0e27ebd7e36a9 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1341,6 +1341,7 @@ config X86_REBOOTFIXUPS
 config MICROCODE
 	def_bool y
 	depends on CPU_SUP_AMD || CPU_SUP_INTEL
+	select CRYPTO_LIB_SHA256 if CPU_SUP_AMD
 
 config MICROCODE_INITRD32
 	def_bool y
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 31f90e129b083..95ac1c6a84fbe 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -23,14 +23,18 @@
 
 #include <linux/earlycpio.h>
 #include <linux/firmware.h>
+#include <linux/bsearch.h>
 #include <linux/uaccess.h>
 #include <linux/vmalloc.h>
 #include <linux/initrd.h>
 #include <linux/kernel.h>
 #include <linux/pci.h>
 
+#include <crypto/sha2.h>
+
 #include <asm/microcode.h>
 #include <asm/processor.h>
+#include <asm/cmdline.h>
 #include <asm/setup.h>
 #include <asm/cpu.h>
 #include <asm/msr.h>
@@ -145,6 +149,98 @@ ucode_path[] __maybe_unused = "kernel/x86/microcode/AuthenticAMD.bin";
  */
 static u32 bsp_cpuid_1_eax __ro_after_init;
 
+static bool sha_check = true;
+
+struct patch_digest {
+	u32 patch_id;
+	u8 sha256[SHA256_DIGEST_SIZE];
+};
+
+#include "amd_shas.c"
+
+static int cmp_id(const void *key, const void *elem)
+{
+	struct patch_digest *pd = (struct patch_digest *)elem;
+	u32 patch_id = *(u32 *)key;
+
+	if (patch_id == pd->patch_id)
+		return 0;
+	else if (patch_id < pd->patch_id)
+		return -1;
+	else
+		return 1;
+}
+
+static bool need_sha_check(u32 cur_rev)
+{
+	switch (cur_rev >> 8) {
+	case 0x80012: return cur_rev <= 0x800126f; break;
+	case 0x83010: return cur_rev <= 0x830107c; break;
+	case 0x86001: return cur_rev <= 0x860010e; break;
+	case 0x86081: return cur_rev <= 0x8608108; break;
+	case 0x87010: return cur_rev <= 0x8701034; break;
+	case 0x8a000: return cur_rev <= 0x8a0000a; break;
+	case 0xa0011: return cur_rev <= 0xa0011da; break;
+	case 0xa0012: return cur_rev <= 0xa001243; break;
+	case 0xa1011: return cur_rev <= 0xa101153; break;
+	case 0xa1012: return cur_rev <= 0xa10124e; break;
+	case 0xa1081: return cur_rev <= 0xa108109; break;
+	case 0xa2010: return cur_rev <= 0xa20102f; break;
+	case 0xa2012: return cur_rev <= 0xa201212; break;
+	case 0xa6012: return cur_rev <= 0xa60120a; break;
+	case 0xa7041: return cur_rev <= 0xa704109; break;
+	case 0xa7052: return cur_rev <= 0xa705208; break;
+	case 0xa7080: return cur_rev <= 0xa708009; break;
+	case 0xa70c0: return cur_rev <= 0xa70C009; break;
+	case 0xaa002: return cur_rev <= 0xaa00218; break;
+	default: break;
+	}
+
+	pr_info("You should not be seeing this. Please send the following couple of lines to x86-<at>-kernel.org\n");
+	pr_info("CPUID(1).EAX: 0x%x, current revision: 0x%x\n", bsp_cpuid_1_eax, cur_rev);
+	return true;
+}
+
+static bool verify_sha256_digest(u32 patch_id, u32 cur_rev, const u8 *data, unsigned int len)
+{
+	struct patch_digest *pd = NULL;
+	u8 digest[SHA256_DIGEST_SIZE];
+	struct sha256_state s;
+	int i;
+
+	if (x86_family(bsp_cpuid_1_eax) < 0x17 ||
+	    x86_family(bsp_cpuid_1_eax) > 0x19)
+		return true;
+
+	if (!need_sha_check(cur_rev))
+		return true;
+
+	if (!sha_check)
+		return true;
+
+	pd = bsearch(&patch_id, phashes, ARRAY_SIZE(phashes), sizeof(struct patch_digest), cmp_id);
+	if (!pd) {
+		pr_err("No sha256 digest for patch ID: 0x%x found\n", patch_id);
+		return false;
+	}
+
+	sha256_init(&s);
+	sha256_update(&s, data, len);
+	sha256_final(&s, digest);
+
+	if (memcmp(digest, pd->sha256, sizeof(digest))) {
+		pr_err("Patch 0x%x SHA256 digest mismatch!\n", patch_id);
+
+		for (i = 0; i < SHA256_DIGEST_SIZE; i++)
+			pr_cont("0x%x ", digest[i]);
+		pr_info("\n");
+
+		return false;
+	}
+
+	return true;
+}
+
 static u32 get_patch_level(void)
 {
 	u32 rev, dummy __always_unused;
@@ -497,6 +593,9 @@ static bool __apply_microcode_amd(struct microcode_amd *mc, u32 *cur_rev,
 {
 	unsigned long p_addr = (unsigned long)&mc->hdr.data_code;
 
+	if (!verify_sha256_digest(mc->hdr.patch_id, *cur_rev, (const u8 *)p_addr, psize))
+		return -1;
+
 	native_wrmsrl(MSR_AMD64_PATCH_LOADER, p_addr);
 
 	if (x86_family(bsp_cpuid_1_eax) == 0x17) {
@@ -571,8 +670,17 @@ void __init load_ucode_amd_bsp(struct early_load_data *ed, unsigned int cpuid_1_
 	struct cont_desc desc = { };
 	struct microcode_amd *mc;
 	struct cpio_data cp = { };
+	char buf[4];
 	u32 rev;
 
+	if (cmdline_find_option(boot_command_line, "microcode.amd_sha_check", buf, 4)) {
+		if (!strncmp(buf, "off", 3)) {
+			sha_check = false;
+			pr_warn_once("It is a very very bad idea to disable the blobs SHA check!\n");
+			add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK);
+		}
+	}
+
 	bsp_cpuid_1_eax = cpuid_1_eax;
 
 	rev = get_patch_level();
@@ -902,8 +1010,7 @@ static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover,
 }
 
 /* Scan the blob in @data and add microcode patches to the cache. */
-static enum ucode_state __load_microcode_amd(u8 family, const u8 *data,
-					     size_t size)
+static enum ucode_state __load_microcode_amd(u8 family, const u8 *data, size_t size)
 {
 	u8 *fw = (u8 *)data;
 	size_t offset;
diff --git a/arch/x86/kernel/cpu/microcode/amd_shas.c b/arch/x86/kernel/cpu/microcode/amd_shas.c
new file mode 100644
index 0000000000000..2a1655b1fdd88
--- /dev/null
+++ b/arch/x86/kernel/cpu/microcode/amd_shas.c
@@ -0,0 +1,444 @@
+/* Keep 'em sorted. */
+static const struct patch_digest phashes[] = {
+ { 0x8001227, {
+		0x99,0xc0,0x9b,0x2b,0xcc,0x9f,0x52,0x1b,
+		0x1a,0x5f,0x1d,0x83,0xa1,0x6c,0xc4,0x46,
+		0xe2,0x6c,0xda,0x73,0xfb,0x2d,0x23,0xa8,
+		0x77,0xdc,0x15,0x31,0x33,0x4a,0x46,0x18,
+	}
+ },
+ { 0x8001250, {
+		0xc0,0x0b,0x6b,0x19,0xfd,0x5c,0x39,0x60,
+		0xd5,0xc3,0x57,0x46,0x54,0xe4,0xd1,0xaa,
+		0xa8,0xf7,0x1f,0xa8,0x6a,0x60,0x3e,0xe3,
+		0x27,0x39,0x8e,0x53,0x30,0xf8,0x49,0x19,
+	}
+ },
+ { 0x800126e, {
+		0xf3,0x8b,0x2b,0xb6,0x34,0xe3,0xc8,0x2c,
+		0xef,0xec,0x63,0x6d,0xc8,0x76,0x77,0xb3,
+		0x25,0x5a,0xb7,0x52,0x8c,0x83,0x26,0xe6,
+		0x4c,0xbe,0xbf,0xe9,0x7d,0x22,0x6a,0x43,
+	}
+ },
+ { 0x800126f, {
+		0x2b,0x5a,0xf2,0x9c,0xdd,0xd2,0x7f,0xec,
+		0xec,0x96,0x09,0x57,0xb0,0x96,0x29,0x8b,
+		0x2e,0x26,0x91,0xf0,0x49,0x33,0x42,0x18,
+		0xdd,0x4b,0x65,0x5a,0xd4,0x15,0x3d,0x33,
+	}
+ },
+ { 0x800820d, {
+		0x68,0x98,0x83,0xcd,0x22,0x0d,0xdd,0x59,
+		0x73,0x2c,0x5b,0x37,0x1f,0x84,0x0e,0x67,
+		0x96,0x43,0x83,0x0c,0x46,0x44,0xab,0x7c,
+		0x7b,0x65,0x9e,0x57,0xb5,0x90,0x4b,0x0e,
+	}
+ },
+ { 0x8301025, {
+		0xe4,0x7d,0xdb,0x1e,0x14,0xb4,0x5e,0x36,
+		0x8f,0x3e,0x48,0x88,0x3c,0x6d,0x76,0xa1,
+		0x59,0xc6,0xc0,0x72,0x42,0xdf,0x6c,0x30,
+		0x6f,0x0b,0x28,0x16,0x61,0xfc,0x79,0x77,
+	}
+ },
+ { 0x8301055, {
+		0x81,0x7b,0x99,0x1b,0xae,0x2d,0x4f,0x9a,
+		0xef,0x13,0xce,0xb5,0x10,0xaf,0x6a,0xea,
+		0xe5,0xb0,0x64,0x98,0x10,0x68,0x34,0x3b,
+		0x9d,0x7a,0xd6,0x22,0x77,0x5f,0xb3,0x5b,
+	}
+ },
+ { 0x8301072, {
+		0xcf,0x76,0xa7,0x1a,0x49,0xdf,0x2a,0x5e,
+		0x9e,0x40,0x70,0xe5,0xdd,0x8a,0xa8,0x28,
+		0x20,0xdc,0x91,0xd8,0x2c,0xa6,0xa0,0xb1,
+		0x2d,0x22,0x26,0x94,0x4b,0x40,0x85,0x30,
+	}
+ },
+ { 0x830107a, {
+		0x2a,0x65,0x8c,0x1a,0x5e,0x07,0x21,0x72,
+		0xdf,0x90,0xa6,0x51,0x37,0xd3,0x4b,0x34,
+		0xc4,0xda,0x03,0xe1,0x8a,0x6c,0xfb,0x20,
+		0x04,0xb2,0x81,0x05,0xd4,0x87,0xf4,0x0a,
+	}
+ },
+ { 0x830107b, {
+		0xb3,0x43,0x13,0x63,0x56,0xc1,0x39,0xad,
+		0x10,0xa6,0x2b,0xcc,0x02,0xe6,0x76,0x2a,
+		0x1e,0x39,0x58,0x3e,0x23,0x6e,0xa4,0x04,
+		0x95,0xea,0xf9,0x6d,0xc2,0x8a,0x13,0x19,
+	}
+ },
+ { 0x830107c, {
+		0x21,0x64,0xde,0xfb,0x9f,0x68,0x96,0x47,
+		0x70,0x5c,0xe2,0x8f,0x18,0x52,0x6a,0xac,
+		0xa4,0xd2,0x2e,0xe0,0xde,0x68,0x66,0xc3,
+		0xeb,0x1e,0xd3,0x3f,0xbc,0x51,0x1d,0x38,
+	}
+ },
+ { 0x860010d, {
+		0x86,0xb6,0x15,0x83,0xbc,0x3b,0x9c,0xe0,
+		0xb3,0xef,0x1d,0x99,0x84,0x35,0x15,0xf7,
+		0x7c,0x2a,0xc6,0x42,0xdb,0x73,0x07,0x5c,
+		0x7d,0xc3,0x02,0xb5,0x43,0x06,0x5e,0xf8,
+	}
+ },
+ { 0x8608108, {
+		0x14,0xfe,0x57,0x86,0x49,0xc8,0x68,0xe2,
+		0x11,0xa3,0xcb,0x6e,0xff,0x6e,0xd5,0x38,
+		0xfe,0x89,0x1a,0xe0,0x67,0xbf,0xc4,0xcc,
+		0x1b,0x9f,0x84,0x77,0x2b,0x9f,0xaa,0xbd,
+	}
+ },
+ { 0x8701034, {
+		0xc3,0x14,0x09,0xa8,0x9c,0x3f,0x8d,0x83,
+		0x9b,0x4c,0xa5,0xb7,0x64,0x8b,0x91,0x5d,
+		0x85,0x6a,0x39,0x26,0x1e,0x14,0x41,0xa8,
+		0x75,0xea,0xa6,0xf9,0xc9,0xd1,0xea,0x2b,
+	}
+ },
+ { 0x8a00008, {
+		0xd7,0x2a,0x93,0xdc,0x05,0x2f,0xa5,0x6e,
+		0x0c,0x61,0x2c,0x07,0x9f,0x38,0xe9,0x8e,
+		0xef,0x7d,0x2a,0x05,0x4d,0x56,0xaf,0x72,
+		0xe7,0x56,0x47,0x6e,0x60,0x27,0xd5,0x8c,
+	}
+ },
+ { 0x8a0000a, {
+		0x73,0x31,0x26,0x22,0xd4,0xf9,0xee,0x3c,
+		0x07,0x06,0xe7,0xb9,0xad,0xd8,0x72,0x44,
+		0x33,0x31,0xaa,0x7d,0xc3,0x67,0x0e,0xdb,
+		0x47,0xb5,0xaa,0xbc,0xf5,0xbb,0xd9,0x20,
+	}
+ },
+ { 0xa00104c, {
+		0x3c,0x8a,0xfe,0x04,0x62,0xd8,0x6d,0xbe,
+		0xa7,0x14,0x28,0x64,0x75,0xc0,0xa3,0x76,
+		0xb7,0x92,0x0b,0x97,0x0a,0x8e,0x9c,0x5b,
+		0x1b,0xc8,0x9d,0x3a,0x1e,0x81,0x3d,0x3b,
+	}
+ },
+ { 0xa00104e, {
+		0xc4,0x35,0x82,0x67,0xd2,0x86,0xe5,0xb2,
+		0xfd,0x69,0x12,0x38,0xc8,0x77,0xba,0xe0,
+		0x70,0xf9,0x77,0x89,0x10,0xa6,0x74,0x4e,
+		0x56,0x58,0x13,0xf5,0x84,0x70,0x28,0x0b,
+	}
+ },
+ { 0xa001053, {
+		0x92,0x0e,0xf4,0x69,0x10,0x3b,0xf9,0x9d,
+		0x31,0x1b,0xa6,0x99,0x08,0x7d,0xd7,0x25,
+		0x7e,0x1e,0x89,0xba,0x35,0x8d,0xac,0xcb,
+		0x3a,0xb4,0xdf,0x58,0x12,0xcf,0xc0,0xc3,
+	}
+ },
+ { 0xa001058, {
+		0x33,0x7d,0xa9,0xb5,0x4e,0x62,0x13,0x36,
+		0xef,0x66,0xc9,0xbd,0x0a,0xa6,0x3b,0x19,
+		0xcb,0xf5,0xc2,0xc3,0x55,0x47,0x20,0xec,
+		0x1f,0x7b,0xa1,0x44,0x0e,0x8e,0xa4,0xb2,
+	}
+ },
+ { 0xa001075, {
+		0x39,0x02,0x82,0xd0,0x7c,0x26,0x43,0xe9,
+		0x26,0xa3,0xd9,0x96,0xf7,0x30,0x13,0x0a,
+		0x8a,0x0e,0xac,0xe7,0x1d,0xdc,0xe2,0x0f,
+		0xcb,0x9e,0x8d,0xbc,0xd2,0xa2,0x44,0xe0,
+	}
+ },
+ { 0xa001078, {
+		0x2d,0x67,0xc7,0x35,0xca,0xef,0x2f,0x25,
+		0x4c,0x45,0x93,0x3f,0x36,0x01,0x8c,0xce,
+		0xa8,0x5b,0x07,0xd3,0xc1,0x35,0x3c,0x04,
+		0x20,0xa2,0xfc,0xdc,0xe6,0xce,0x26,0x3e,
+	}
+ },
+ { 0xa001079, {
+		0x43,0xe2,0x05,0x9c,0xfd,0xb7,0x5b,0xeb,
+		0x5b,0xe9,0xeb,0x3b,0x96,0xf4,0xe4,0x93,
+		0x73,0x45,0x3e,0xac,0x8d,0x3b,0xe4,0xdb,
+		0x10,0x31,0xc1,0xe4,0xa2,0xd0,0x5a,0x8a,
+	}
+ },
+ { 0xa00107a, {
+		0x5f,0x92,0xca,0xff,0xc3,0x59,0x22,0x5f,
+		0x02,0xa0,0x91,0x3b,0x4a,0x45,0x10,0xfd,
+		0x19,0xe1,0x8a,0x6d,0x9a,0x92,0xc1,0x3f,
+		0x75,0x78,0xac,0x78,0x03,0x1d,0xdb,0x18,
+	}
+ },
+ { 0xa001143, {
+		0x56,0xca,0xf7,0x43,0x8a,0x4c,0x46,0x80,
+		0xec,0xde,0xe5,0x9c,0x50,0x84,0x9a,0x42,
+		0x27,0xe5,0x51,0x84,0x8f,0x19,0xc0,0x8d,
+		0x0c,0x25,0xb4,0xb0,0x8f,0x10,0xf3,0xf8,
+	}
+ },
+ { 0xa001144, {
+		0x42,0xd5,0x9b,0xa7,0xd6,0x15,0x29,0x41,
+		0x61,0xc4,0x72,0x3f,0xf3,0x06,0x78,0x4b,
+		0x65,0xf3,0x0e,0xfa,0x9c,0x87,0xde,0x25,
+		0xbd,0xb3,0x9a,0xf4,0x75,0x13,0x53,0xdc,
+	}
+ },
+ { 0xa00115d, {
+		0xd4,0xc4,0x49,0x36,0x89,0x0b,0x47,0xdd,
+		0xfb,0x2f,0x88,0x3b,0x5f,0xf2,0x8e,0x75,
+		0xc6,0x6c,0x37,0x5a,0x90,0x25,0x94,0x3e,
+		0x36,0x9c,0xae,0x02,0x38,0x6c,0xf5,0x05,
+	}
+ },
+ { 0xa001173, {
+		0x28,0xbb,0x9b,0xd1,0xa0,0xa0,0x7e,0x3a,
+		0x59,0x20,0xc0,0xa9,0xb2,0x5c,0xc3,0x35,
+		0x53,0x89,0xe1,0x4c,0x93,0x2f,0x1d,0xc3,
+		0xe5,0xf7,0xf3,0xc8,0x9b,0x61,0xaa,0x9e,
+	}
+ },
+ { 0xa0011a8, {
+		0x97,0xc6,0x16,0x65,0x99,0xa4,0x85,0x3b,
+		0xf6,0xce,0xaa,0x49,0x4a,0x3a,0xc5,0xb6,
+		0x78,0x25,0xbc,0x53,0xaf,0x5d,0xcf,0xf4,
+		0x23,0x12,0xbb,0xb1,0xbc,0x8a,0x02,0x2e,
+	}
+ },
+ { 0xa0011ce, {
+		0xcf,0x1c,0x90,0xa3,0x85,0x0a,0xbf,0x71,
+		0x94,0x0e,0x80,0x86,0x85,0x4f,0xd7,0x86,
+		0xae,0x38,0x23,0x28,0x2b,0x35,0x9b,0x4e,
+		0xfe,0xb8,0xcd,0x3d,0x3d,0x39,0xc9,0x6a,
+	}
+ },
+ { 0xa0011d1, {
+		0xdf,0x0e,0xca,0xde,0xf6,0xce,0x5c,0x1e,
+		0x4c,0xec,0xd7,0x71,0x83,0xcc,0xa8,0x09,
+		0xc7,0xc5,0xfe,0xb2,0xf7,0x05,0xd2,0xc5,
+		0x12,0xdd,0xe4,0xf3,0x92,0x1c,0x3d,0xb8,
+	}
+ },
+ { 0xa0011d3, {
+		0x91,0xe6,0x10,0xd7,0x57,0xb0,0x95,0x0b,
+		0x9a,0x24,0xee,0xf7,0xcf,0x56,0xc1,0xa6,
+		0x4a,0x52,0x7d,0x5f,0x9f,0xdf,0xf6,0x00,
+		0x65,0xf7,0xea,0xe8,0x2a,0x88,0xe2,0x26,
+	}
+ },
+ { 0xa0011d5, {
+		0xed,0x69,0x89,0xf4,0xeb,0x64,0xc2,0x13,
+		0xe0,0x51,0x1f,0x03,0x26,0x52,0x7d,0xb7,
+		0x93,0x5d,0x65,0xca,0xb8,0x12,0x1d,0x62,
+		0x0d,0x5b,0x65,0x34,0x69,0xb2,0x62,0x21,
+	}
+ },
+ { 0xa001223, {
+		0xfb,0x32,0x5f,0xc6,0x83,0x4f,0x8c,0xb8,
+		0xa4,0x05,0xf9,0x71,0x53,0x01,0x16,0xc4,
+		0x83,0x75,0x94,0xdd,0xeb,0x7e,0xb7,0x15,
+		0x8e,0x3b,0x50,0x29,0x8a,0x9c,0xcc,0x45,
+	}
+ },
+ { 0xa001224, {
+		0x0e,0x0c,0xdf,0xb4,0x89,0xee,0x35,0x25,
+		0xdd,0x9e,0xdb,0xc0,0x69,0x83,0x0a,0xad,
+		0x26,0xa9,0xaa,0x9d,0xfc,0x3c,0xea,0xf9,
+		0x6c,0xdc,0xd5,0x6d,0x8b,0x6e,0x85,0x4a,
+	}
+ },
+ { 0xa001227, {
+		0xab,0xc6,0x00,0x69,0x4b,0x50,0x87,0xad,
+		0x5f,0x0e,0x8b,0xea,0x57,0x38,0xce,0x1d,
+		0x0f,0x75,0x26,0x02,0xf6,0xd6,0x96,0xe9,
+		0x87,0xb9,0xd6,0x20,0x27,0x7c,0xd2,0xe0,
+	}
+ },
+ { 0xa001229, {
+		0x7f,0x49,0x49,0x48,0x46,0xa5,0x50,0xa6,
+		0x28,0x89,0x98,0xe2,0x9e,0xb4,0x7f,0x75,
+		0x33,0xa7,0x04,0x02,0xe4,0x82,0xbf,0xb4,
+		0xa5,0x3a,0xba,0x24,0x8d,0x31,0x10,0x1d,
+	}
+ },
+ { 0xa00122e, {
+		0x56,0x94,0xa9,0x5d,0x06,0x68,0xfe,0xaf,
+		0xdf,0x7a,0xff,0x2d,0xdf,0x74,0x0f,0x15,
+		0x66,0xfb,0x00,0xb5,0x51,0x97,0x9b,0xfa,
+		0xcb,0x79,0x85,0x46,0x25,0xb4,0xd2,0x10,
+	}
+ },
+ { 0xa001231, {
+		0x0b,0x46,0xa5,0xfc,0x18,0x15,0xa0,0x9e,
+		0xa6,0xdc,0xb7,0xff,0x17,0xf7,0x30,0x64,
+		0xd4,0xda,0x9e,0x1b,0xc3,0xfc,0x02,0x3b,
+		0xe2,0xc6,0x0e,0x41,0x54,0xb5,0x18,0xdd,
+	}
+ },
+ { 0xa001234, {
+		0x88,0x8d,0xed,0xab,0xb5,0xbd,0x4e,0xf7,
+		0x7f,0xd4,0x0e,0x95,0x34,0x91,0xff,0xcc,
+		0xfb,0x2a,0xcd,0xf7,0xd5,0xdb,0x4c,0x9b,
+		0xd6,0x2e,0x73,0x50,0x8f,0x83,0x79,0x1a,
+	}
+ },
+ { 0xa001236, {
+		0x3d,0x30,0x00,0xb9,0x71,0xba,0x87,0x78,
+		0xa8,0x43,0x55,0xc4,0x26,0x59,0xcf,0x9d,
+		0x93,0xce,0x64,0x0e,0x8b,0x72,0x11,0x8b,
+		0xa3,0x8f,0x51,0xe9,0xca,0x98,0xaa,0x25,
+	}
+ },
+ { 0xa001238, {
+		0x72,0xf7,0x4b,0x0c,0x7d,0x58,0x65,0xcc,
+		0x00,0xcc,0x57,0x16,0x68,0x16,0xf8,0x2a,
+		0x1b,0xb3,0x8b,0xe1,0xb6,0x83,0x8c,0x7e,
+		0xc0,0xcd,0x33,0xf2,0x8d,0xf9,0xef,0x59,
+	}
+ },
+ { 0xa00820c, {
+		0xa8,0x0c,0x81,0xc0,0xa6,0x00,0xe7,0xf3,
+		0x5f,0x65,0xd3,0xb9,0x6f,0xea,0x93,0x63,
+		0xf1,0x8c,0x88,0x45,0xd7,0x82,0x80,0xd1,
+		0xe1,0x3b,0x8d,0xb2,0xf8,0x22,0x03,0xe2,
+	}
+ },
+ { 0xa10113e, {
+		0x05,0x3c,0x66,0xd7,0xa9,0x5a,0x33,0x10,
+		0x1b,0xf8,0x9c,0x8f,0xed,0xfc,0xa7,0xa0,
+		0x15,0xe3,0x3f,0x4b,0x1d,0x0d,0x0a,0xd5,
+		0xfa,0x90,0xc4,0xed,0x9d,0x90,0xaf,0x53,
+	}
+ },
+ { 0xa101144, {
+		0xb3,0x0b,0x26,0x9a,0xf8,0x7c,0x02,0x26,
+		0x35,0x84,0x53,0xa4,0xd3,0x2c,0x7c,0x09,
+		0x68,0x7b,0x96,0xb6,0x93,0xef,0xde,0xbc,
+		0xfd,0x4b,0x15,0xd2,0x81,0xd3,0x51,0x47,
+	}
+ },
+ { 0xa101148, {
+		0x20,0xd5,0x6f,0x40,0x4a,0xf6,0x48,0x90,
+		0xc2,0x93,0x9a,0xc2,0xfd,0xac,0xef,0x4f,
+		0xfa,0xc0,0x3d,0x92,0x3c,0x6d,0x01,0x08,
+		0xf1,0x5e,0xb0,0xde,0xb4,0x98,0xae,0xc4,
+	}
+ },
+ { 0xa10123e, {
+		0x03,0xb9,0x2c,0x76,0x48,0x93,0xc9,0x18,
+		0xfb,0x56,0xfd,0xf7,0xe2,0x1d,0xca,0x4d,
+		0x1d,0x13,0x53,0x63,0xfe,0x42,0x6f,0xfc,
+		0x19,0x0f,0xf1,0xfc,0xa7,0xdd,0x89,0x1b,
+	}
+ },
+ { 0xa101244, {
+		0x71,0x56,0xb5,0x9f,0x21,0xbf,0xb3,0x3c,
+		0x8c,0xd7,0x36,0xd0,0x34,0x52,0x1b,0xb1,
+		0x46,0x2f,0x04,0xf0,0x37,0xd8,0x1e,0x72,
+		0x24,0xa2,0x80,0x84,0x83,0x65,0x84,0xc0,
+	}
+ },
+ { 0xa101248, {
+		0xed,0x3b,0x95,0xa6,0x68,0xa7,0x77,0x3e,
+		0xfc,0x17,0x26,0xe2,0x7b,0xd5,0x56,0x22,
+		0x2c,0x1d,0xef,0xeb,0x56,0xdd,0xba,0x6e,
+		0x1b,0x7d,0x64,0x9d,0x4b,0x53,0x13,0x75,
+	}
+ },
+ { 0xa108108, {
+		0xed,0xc2,0xec,0xa1,0x15,0xc6,0x65,0xe9,
+		0xd0,0xef,0x39,0xaa,0x7f,0x55,0x06,0xc6,
+		0xf5,0xd4,0x3f,0x7b,0x14,0xd5,0x60,0x2c,
+		0x28,0x1e,0x9c,0x59,0x69,0x99,0x4d,0x16,
+	}
+ },
+ { 0xa20102d, {
+		0xf9,0x6e,0xf2,0x32,0xd3,0x0f,0x5f,0x11,
+		0x59,0xa1,0xfe,0xcc,0xcd,0x9b,0x42,0x89,
+		0x8b,0x89,0x2f,0xb5,0xbb,0x82,0xef,0x23,
+		0x8c,0xe9,0x19,0x3e,0xcc,0x3f,0x7b,0xb4,
+	}
+ },
+ { 0xa201210, {
+		0xe8,0x6d,0x51,0x6a,0x8e,0x72,0xf3,0xfe,
+		0x6e,0x16,0xbc,0x62,0x59,0x40,0x17,0xe9,
+		0x6d,0x3d,0x0e,0x6b,0xa7,0xac,0xe3,0x68,
+		0xf7,0x55,0xf0,0x13,0xbb,0x22,0xf6,0x41,
+	}
+ },
+ { 0xa404107, {
+		0xbb,0x04,0x4e,0x47,0xdd,0x5e,0x26,0x45,
+		0x1a,0xc9,0x56,0x24,0xa4,0x4c,0x82,0xb0,
+		0x8b,0x0d,0x9f,0xf9,0x3a,0xdf,0xc6,0x81,
+		0x13,0xbc,0xc5,0x25,0xe4,0xc5,0xc3,0x99,
+	}
+ },
+ { 0xa500011, {
+		0x23,0x3d,0x70,0x7d,0x03,0xc3,0xc4,0xf4,
+		0x2b,0x82,0xc6,0x05,0xda,0x80,0x0a,0xf1,
+		0xd7,0x5b,0x65,0x3a,0x7d,0xab,0xdf,0xa2,
+		0x11,0x5e,0x96,0x7e,0x71,0xe9,0xfc,0x74,
+	}
+ },
+ { 0xa601209, {
+		0x66,0x48,0xd4,0x09,0x05,0xcb,0x29,0x32,
+		0x66,0xb7,0x9a,0x76,0xcd,0x11,0xf3,0x30,
+		0x15,0x86,0xcc,0x5d,0x97,0x0f,0xc0,0x46,
+		0xe8,0x73,0xe2,0xd6,0xdb,0xd2,0x77,0x1d,
+	}
+ },
+ { 0xa704107, {
+		0xf3,0xc6,0x58,0x26,0xee,0xac,0x3f,0xd6,
+		0xce,0xa1,0x72,0x47,0x3b,0xba,0x2b,0x93,
+		0x2a,0xad,0x8e,0x6b,0xea,0x9b,0xb7,0xc2,
+		0x64,0x39,0x71,0x8c,0xce,0xe7,0x41,0x39,
+	}
+ },
+ { 0xa705206, {
+		0x8d,0xc0,0x76,0xbd,0x58,0x9f,0x8f,0xa4,
+		0x12,0x9d,0x21,0xfb,0x48,0x21,0xbc,0xe7,
+		0x67,0x6f,0x04,0x18,0xae,0x20,0x87,0x4b,
+		0x03,0x35,0xe9,0xbe,0xfb,0x06,0xdf,0xfc,
+	}
+ },
+ { 0xa708007, {
+		0x6b,0x76,0xcc,0x78,0xc5,0x8a,0xa3,0xe3,
+		0x32,0x2d,0x79,0xe4,0xc3,0x80,0xdb,0xb2,
+		0x07,0xaa,0x3a,0xe0,0x57,0x13,0x72,0x80,
+		0xdf,0x92,0x73,0x84,0x87,0x3c,0x73,0x93,
+	}
+ },
+ { 0xa70c005, {
+		0x88,0x5d,0xfb,0x79,0x64,0xd8,0x46,0x3b,
+		0x4a,0x83,0x8e,0x77,0x7e,0xcf,0xb3,0x0f,
+		0x1f,0x1f,0xf1,0x97,0xeb,0xfe,0x56,0x55,
+		0xee,0x49,0xac,0xe1,0x8b,0x13,0xc5,0x13,
+	}
+ },
+ { 0xaa00116, {
+		0xe8,0x4c,0x2c,0x88,0xa1,0xac,0x24,0x63,
+		0x65,0xe5,0xaa,0x2d,0x16,0xa9,0xc3,0xf5,
+		0xfe,0x1d,0x5e,0x65,0xc7,0xaa,0x92,0x4d,
+		0x91,0xee,0x76,0xbb,0x4c,0x66,0x78,0xc9,
+	}
+ },
+ { 0xaa00212, {
+		0xbd,0x57,0x5d,0x0a,0x0a,0x30,0xc1,0x75,
+		0x95,0x58,0x5e,0x93,0x02,0x28,0x43,0x71,
+		0xed,0x42,0x29,0xc8,0xec,0x34,0x2b,0xb2,
+		0x1a,0x65,0x4b,0xfe,0x07,0x0f,0x34,0xa1,
+	}
+ },
+ { 0xaa00213, {
+		0xed,0x58,0xb7,0x76,0x81,0x7f,0xd9,0x3a,
+		0x1a,0xff,0x8b,0x34,0xb8,0x4a,0x99,0x0f,
+		0x28,0x49,0x6c,0x56,0x2b,0xdc,0xb7,0xed,
+		0x96,0xd5,0x9d,0xc1,0x7a,0xd4,0x51,0x9b,
+	}
+ },
+ { 0xaa00215, {
+		0x55,0xd3,0x28,0xcb,0x87,0xa9,0x32,0xe9,
+		0x4e,0x85,0x4b,0x7c,0x6b,0xd5,0x7c,0xd4,
+		0x1b,0x51,0x71,0x3a,0x0e,0x0b,0xdc,0x9b,
+		0x68,0x2f,0x46,0xee,0xfe,0xc6,0x6d,0xef,
+	}
+ },
+};

From 7ffb791423c7c518269a9aad35039ef824a40adb Mon Sep 17 00:00:00 2001
From: Balbir Singh <balbirs@nvidia.com>
Date: Fri, 7 Feb 2025 10:42:34 +1100
Subject: [PATCH 0510/1173] x86/kaslr: Reduce KASLR entropy on most x86 systems

When CONFIG_PCI_P2PDMA=y (which is basically enabled on all
large x86 distros), it maps the PFN's via a ZONE_DEVICE
mapping using devm_memremap_pages(). The mapped virtual
address range corresponds to the pci_resource_start()
of the BAR address and size corresponding to the BAR length.

When KASLR is enabled, the direct map range of the kernel is
reduced to the size of physical memory plus additional padding.
If the BAR address is beyond this limit, PCI peer to peer DMA
mappings fail.

Fix this by not shrinking the size of the direct map when
CONFIG_PCI_P2PDMA=y.

This reduces the total available entropy, but it's better than
the current work around of having to disable KASLR completely.

[ mingo: Clarified the changelog to point out the broad impact ... ]

Signed-off-by: Balbir Singh <balbirs@nvidia.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Kees Cook <kees@kernel.org>
Acked-by: Bjorn Helgaas <bhelgaas@google.com> # drivers/pci/Kconfig
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andy Lutomirski <luto@kernel.org>
Link: https://lore.kernel.org/lkml/20250206023201.1481957-1-balbirs@nvidia.com/
Link: https://lore.kernel.org/r/20250206234234.1912585-1-balbirs@nvidia.com
--
 arch/x86/mm/kaslr.c | 10 ++++++++--
 drivers/pci/Kconfig |  6 ++++++
 2 files changed, 14 insertions(+), 2 deletions(-)
---
 arch/x86/mm/kaslr.c | 10 ++++++++--
 drivers/pci/Kconfig |  6 ++++++
 2 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index 11a93542d1983..3c306de52fd4d 100644
--- a/arch/x86/mm/kaslr.c
+++ b/arch/x86/mm/kaslr.c
@@ -113,8 +113,14 @@ void __init kernel_randomize_memory(void)
 	memory_tb = DIV_ROUND_UP(max_pfn << PAGE_SHIFT, 1UL << TB_SHIFT) +
 		CONFIG_RANDOMIZE_MEMORY_PHYSICAL_PADDING;
 
-	/* Adapt physical memory region size based on available memory */
-	if (memory_tb < kaslr_regions[0].size_tb)
+	/*
+	 * Adapt physical memory region size based on available memory,
+	 * except when CONFIG_PCI_P2PDMA is enabled. P2PDMA exposes the
+	 * device BAR space assuming the direct map space is large enough
+	 * for creating a ZONE_DEVICE mapping in the direct map corresponding
+	 * to the physical BAR address.
+	 */
+	if (!IS_ENABLED(CONFIG_PCI_P2PDMA) && (memory_tb < kaslr_regions[0].size_tb))
 		kaslr_regions[0].size_tb = memory_tb;
 
 	/*
diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index 2fbd379923fd1..5c3054aaec8c1 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -203,6 +203,12 @@ config PCI_P2PDMA
 	  P2P DMA transactions must be between devices behind the same root
 	  port.
 
+	  Enabling this option will reduce the entropy of x86 KASLR memory
+	  regions. For example - on a 46 bit system, the entropy goes down
+	  from 16 bits to 15 bits. The actual reduction in entropy depends
+	  on the physical address bits, on processor features, kernel config
+	  (5 level page table) and physical memory present on the system.
+
 	  If unsure, say N.
 
 config PCI_LABEL

From 5bebe2e4fe27bf68b4993d62be2f8bae9e6229d6 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Wed, 29 Jan 2025 16:47:50 +0100
Subject: [PATCH 0511/1173] x86/boot: Change some static bootflag functions to
 bool

The return values of some functions are of boolean type. Change the
type of these function to bool and adjust their return values.

No functional change intended.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250129154920.6773-1-ubizjak@gmail.com
---
 arch/x86/kernel/bootflag.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kernel/bootflag.c b/arch/x86/kernel/bootflag.c
index 3fed7ae58b603..4d89a2d80d0f3 100644
--- a/arch/x86/kernel/bootflag.c
+++ b/arch/x86/kernel/bootflag.c
@@ -20,7 +20,7 @@
 
 int sbf_port __initdata = -1;	/* set via acpi_boot_init() */
 
-static int __init parity(u8 v)
+static bool __init parity(u8 v)
 {
 	int x = 0;
 	int i;
@@ -30,7 +30,7 @@ static int __init parity(u8 v)
 		v >>= 1;
 	}
 
-	return x;
+	return !!x;
 }
 
 static void __init sbf_write(u8 v)
@@ -66,14 +66,14 @@ static u8 __init sbf_read(void)
 	return v;
 }
 
-static int __init sbf_value_valid(u8 v)
+static bool __init sbf_value_valid(u8 v)
 {
 	if (v & SBF_RESERVED)		/* Reserved bits */
-		return 0;
+		return false;
 	if (!parity(v))
-		return 0;
+		return false;
 
-	return 1;
+	return true;
 }
 
 static int __init sbf_init(void)

From a2498e5c453b3d8d054d77751487cd593332f8c2 Mon Sep 17 00:00:00 2001
From: Dave Young <dyoung@redhat.com>
Date: Tue, 28 Jan 2025 21:32:31 +0800
Subject: [PATCH 0512/1173] x86/kexec: Export e820_table_kexec[] to sysfs

Previously the e820_table_kexec[] was exported to sysfs since kexec-tools uses
the memmap entries to prepare the e820 table for the new kernel.

The following commit, ~8 years ago, introduced e820_table_firmware[] and changed
the behavior to export the firmware table instead:

  12df216c61c8 ("x86/boot/e820: Introduce the bootloader provided e820_table_firmware[] table")

Originally the kexec_file_load and kexec_load syscalls both used e820_table_kexec[].
Since the sysfs exported entries are from e820_table_firmware[] people
now need to tune both tables for kexec.

Restore the old behavior so the kexec_load and kexec_file_load syscalls work with
only one table update.  The e820_table_firmware[] is used by hibernation kernel
code and it works without the sysfs exporting. Also remove the SEV
e820_table_firmware[] updating code.

Also update the code comments here and drop the comments about setup_data
reservation since it is not needed any more after this change was made
a year ago:

  fc7f27cda843 ("x86/kexec: Do not update E820 kexec table for setup_data")

[ mingo: Tidy up the changelog and comments. ]

Signed-off-by: Dave Young <dyoung@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Ashish Kalra <ashish.kalra@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Joerg Roedel <jroedel@suse.de>
Cc: Baoquan He <bhe@redhat.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Link: https://lore.kernel.org/r/Z5jcb1GKhLvH8kDc@darkstar.users.ipa.redhat.com
---
 arch/x86/kernel/e820.c  | 20 ++++++++++----------
 arch/x86/virt/svm/sev.c |  1 -
 2 files changed, 10 insertions(+), 11 deletions(-)

diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 9fb67abc32cce..57120f0749cc3 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -28,18 +28,13 @@
  *   the first 128 E820 memory entries in boot_params.e820_table and the remaining
  *   (if any) entries of the SETUP_E820_EXT nodes. We use this to:
  *
- *       - inform the user about the firmware's notion of memory layout
- *         via /sys/firmware/memmap
- *
  *       - the hibernation code uses it to generate a kernel-independent CRC32
  *         checksum of the physical memory layout of a system.
  *
  * - 'e820_table_kexec': a slightly modified (by the kernel) firmware version
  *   passed to us by the bootloader - the major difference between
- *   e820_table_firmware[] and this one is that, the latter marks the setup_data
- *   list created by the EFI boot stub as reserved, so that kexec can reuse the
- *   setup_data information in the second kernel. Besides, e820_table_kexec[]
- *   might also be modified by the kexec itself to fake a mptable.
+ *   e820_table_firmware[] and this one is that e820_table_kexec[]
+ *   might be modified by the kexec itself to fake an mptable.
  *   We use this to:
  *
  *       - kexec, which is a bootloader in disguise, uses the original E820
@@ -47,6 +42,11 @@
  *         can have a restricted E820 map while the kexec()-ed kexec-kernel
  *         can have access to full memory - etc.
  *
+ *         Export the memory layout via /sys/firmware/memmap. kexec-tools uses
+ *         the entries to create an E820 table for the kexec kernel.
+ *
+ *         kexec_file_load in-kernel code uses the table for the kexec kernel.
+ *
  * - 'e820_table': this is the main E820 table that is massaged by the
  *   low level x86 platform code, or modified by boot parameters, before
  *   passed on to higher level MM layers.
@@ -1117,9 +1117,9 @@ void __init e820__reserve_resources(void)
 		res++;
 	}
 
-	/* Expose the bootloader-provided memory layout to the sysfs. */
-	for (i = 0; i < e820_table_firmware->nr_entries; i++) {
-		struct e820_entry *entry = e820_table_firmware->entries + i;
+	/* Expose the kexec e820 table to the sysfs. */
+	for (i = 0; i < e820_table_kexec->nr_entries; i++) {
+		struct e820_entry *entry = e820_table_kexec->entries + i;
 
 		firmware_map_add_early(entry->addr, entry->addr + entry->size, e820_type_to_string(entry));
 	}
diff --git a/arch/x86/virt/svm/sev.c b/arch/x86/virt/svm/sev.c
index 42e74a5a7d786..fc473ca12c44d 100644
--- a/arch/x86/virt/svm/sev.c
+++ b/arch/x86/virt/svm/sev.c
@@ -198,7 +198,6 @@ static void __init __snp_fixup_e820_tables(u64 pa)
 		pr_info("Reserving start/end of RMP table on a 2MB boundary [0x%016llx]\n", pa);
 		e820__range_update(pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED);
 		e820__range_update_table(e820_table_kexec, pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED);
-		e820__range_update_table(e820_table_firmware, pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED);
 		if (!memblock_is_region_reserved(pa, PMD_SIZE))
 			memblock_reserve(pa, PMD_SIZE);
 	}

From 43bb700cff6bc2f0d337006b864192227fb05dc1 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 27 Jan 2025 17:22:52 +0100
Subject: [PATCH 0513/1173] x86/cpu: Update Intel Family comments

Because who can ever remember all these names.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250127162252.GK16742@noisy.programming.kicks-ass.net
---
 arch/x86/include/asm/intel-family.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 8359113e3e58e..f9f67afeb48a7 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -110,9 +110,9 @@
 
 #define INTEL_SAPPHIRERAPIDS_X		IFM(6, 0x8F) /* Golden Cove */
 
-#define INTEL_EMERALDRAPIDS_X		IFM(6, 0xCF)
+#define INTEL_EMERALDRAPIDS_X		IFM(6, 0xCF) /* Raptor Cove */
 
-#define INTEL_GRANITERAPIDS_X		IFM(6, 0xAD)
+#define INTEL_GRANITERAPIDS_X		IFM(6, 0xAD) /* Redwood Cove */
 #define INTEL_GRANITERAPIDS_D		IFM(6, 0xAE)
 
 /* "Hybrid" Processors (P-Core/E-Core) */
@@ -126,16 +126,16 @@
 #define INTEL_RAPTORLAKE_P		IFM(6, 0xBA)
 #define INTEL_RAPTORLAKE_S		IFM(6, 0xBF)
 
-#define INTEL_METEORLAKE		IFM(6, 0xAC)
+#define INTEL_METEORLAKE		IFM(6, 0xAC) /* Redwood Cove / Crestmont */
 #define INTEL_METEORLAKE_L		IFM(6, 0xAA)
 
-#define INTEL_ARROWLAKE_H		IFM(6, 0xC5)
+#define INTEL_ARROWLAKE_H		IFM(6, 0xC5) /* Lion Cove / Skymont */
 #define INTEL_ARROWLAKE			IFM(6, 0xC6)
 #define INTEL_ARROWLAKE_U		IFM(6, 0xB5)
 
-#define INTEL_LUNARLAKE_M		IFM(6, 0xBD)
+#define INTEL_LUNARLAKE_M		IFM(6, 0xBD) /* Lion Cove / Skymont */
 
-#define INTEL_PANTHERLAKE_L		IFM(6, 0xCC)
+#define INTEL_PANTHERLAKE_L		IFM(6, 0xCC) /* Cougar Cove / Crestmont */
 
 /* "Small Core" Processors (Atom/E-Core) */
 

From ec8f5b4659b4044db55e1f7d947703dd4948626c Mon Sep 17 00:00:00 2001
From: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Date: Mon, 27 Jan 2025 16:31:55 +0100
Subject: [PATCH 0514/1173] selftests/lam: Move cpu_has_la57() to use cpuinfo
 flag

In current form cpu_has_la57() reports platform's support for LA57
through reading the output of cpuid. A much more useful information is
whether 5-level paging is actually enabled on the running system.

Check whether 5-level paging is enabled by trying to map a page in the
high linear address space.

Signed-off-by: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/r/8b1ca51b13e6d94b5a42b6930d81b692cbb0bcbb.1737990375.git.maciej.wieczor-retman@intel.com
---
 tools/testing/selftests/x86/lam.c | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/x86/lam.c b/tools/testing/selftests/x86/lam.c
index 4d4a76532dc9a..60170a31aa696 100644
--- a/tools/testing/selftests/x86/lam.c
+++ b/tools/testing/selftests/x86/lam.c
@@ -124,14 +124,18 @@ static inline int cpu_has_lam(void)
 	return (cpuinfo[0] & (1 << 26));
 }
 
-/* Check 5-level page table feature in CPUID.(EAX=07H, ECX=00H):ECX.[bit 16] */
-static inline int cpu_has_la57(void)
+static inline int la57_enabled(void)
 {
-	unsigned int cpuinfo[4];
+	int ret;
+	void *p;
+
+	p = mmap((void *)HIGH_ADDR, PAGE_SIZE, PROT_READ | PROT_WRITE,
+		 MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED, -1, 0);
 
-	__cpuid_count(0x7, 0, cpuinfo[0], cpuinfo[1], cpuinfo[2], cpuinfo[3]);
+	ret = p == MAP_FAILED ? 0 : 1;
 
-	return (cpuinfo[2] & (1 << 16));
+	munmap(p, PAGE_SIZE);
+	return ret;
 }
 
 /*
@@ -322,7 +326,7 @@ static int handle_mmap(struct testcases *test)
 		   flags, -1, 0);
 	if (ptr == MAP_FAILED) {
 		if (test->addr == HIGH_ADDR)
-			if (!cpu_has_la57())
+			if (!la57_enabled())
 				return 3; /* unsupport LA57 */
 		return 1;
 	}

From 51f909dcd178655b104d979a6870535268724498 Mon Sep 17 00:00:00 2001
From: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Date: Mon, 27 Jan 2025 16:31:56 +0100
Subject: [PATCH 0515/1173] selftests/lam: Skip test if LAM is disabled

Until LASS is merged into the kernel:

  https://lore.kernel.org/all/20241028160917.1380714-1-alexander.shishkin@linux.intel.com/

LAM is left disabled in the config file. Running the LAM selftest with
disabled LAM only results in unhelpful output.

Use one of LAM syscalls() to determine whether the kernel was compiled
with LAM support (CONFIG_ADDRESS_MASKING) or not. Skip running the tests
in the latter case.

Merge CPUID checking function with the one mentioned above to achieve a
single function that shows LAM's availability from both CPU and the
kernel.

Signed-off-by: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/r/251d0f45f6a768030115e8d04bc85458910cb0dc.1737990375.git.maciej.wieczor-retman@intel.com
---
 tools/testing/selftests/x86/lam.c | 23 ++++++++++++++++++-----
 1 file changed, 18 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/x86/lam.c b/tools/testing/selftests/x86/lam.c
index 60170a31aa696..df91a41a5babc 100644
--- a/tools/testing/selftests/x86/lam.c
+++ b/tools/testing/selftests/x86/lam.c
@@ -115,13 +115,28 @@ static void segv_handler(int sig)
 	siglongjmp(segv_env, 1);
 }
 
-static inline int cpu_has_lam(void)
+static inline int lam_is_available(void)
 {
 	unsigned int cpuinfo[4];
+	unsigned long bits = 0;
+	int ret;
 
 	__cpuid_count(0x7, 1, cpuinfo[0], cpuinfo[1], cpuinfo[2], cpuinfo[3]);
 
-	return (cpuinfo[0] & (1 << 26));
+	/* Check if cpu supports LAM */
+	if (!(cpuinfo[0] & (1 << 26))) {
+		ksft_print_msg("LAM is not supported!\n");
+		return 0;
+	}
+
+	/* Return 0 if CONFIG_ADDRESS_MASKING is not set */
+	ret = syscall(SYS_arch_prctl, ARCH_GET_MAX_TAG_BITS, &bits);
+	if (ret) {
+		ksft_print_msg("LAM is disabled in the kernel!\n");
+		return 0;
+	}
+
+	return 1;
 }
 
 static inline int la57_enabled(void)
@@ -1185,10 +1200,8 @@ int main(int argc, char **argv)
 
 	tests_cnt = 0;
 
-	if (!cpu_has_lam()) {
-		ksft_print_msg("Unsupported LAM feature!\n");
+	if (!lam_is_available())
 		return KSFT_SKIP;
-	}
 
 	while ((c = getopt(argc, argv, "ht:")) != -1) {
 		switch (c) {

From 782b819827ee84532f3069e37aa091c1be00fa44 Mon Sep 17 00:00:00 2001
From: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Date: Mon, 27 Jan 2025 16:31:57 +0100
Subject: [PATCH 0516/1173] selftests/lam: Test get_user() LAM pointer handling

Recent change in how get_user() handles pointers:

  https://lore.kernel.org/all/20241024013214.129639-1-torvalds@linux-foundation.org/

has a specific case for LAM. It assigns a different bitmask that's
later used to check whether a pointer comes from userland in get_user().

Add test case to LAM that utilizes a ioctl (FIOASYNC) syscall which uses
get_user() in its implementation. Execute the syscall with differently
tagged pointers to verify that valid user pointers are passing through
and invalid kernel/non-canonical pointers are not.

Signed-off-by: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/r/1624d9d1b9502517053a056652d50dc5d26884ac.1737990375.git.maciej.wieczor-retman@intel.com
---
 tools/testing/selftests/x86/lam.c | 108 ++++++++++++++++++++++++++++++
 1 file changed, 108 insertions(+)

diff --git a/tools/testing/selftests/x86/lam.c b/tools/testing/selftests/x86/lam.c
index df91a41a5babc..b6166a5f37d67 100644
--- a/tools/testing/selftests/x86/lam.c
+++ b/tools/testing/selftests/x86/lam.c
@@ -4,6 +4,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <sys/syscall.h>
+#include <sys/ioctl.h>
 #include <time.h>
 #include <signal.h>
 #include <setjmp.h>
@@ -43,7 +44,15 @@
 #define FUNC_INHERITE           0x20
 #define FUNC_PASID              0x40
 
+/* get_user() pointer test cases */
+#define GET_USER_USER           0
+#define GET_USER_KERNEL_TOP     1
+#define GET_USER_KERNEL_BOT     2
+#define GET_USER_KERNEL         3
+
 #define TEST_MASK               0x7f
+#define L5_SIGN_EXT_MASK        (0xFFUL << 56)
+#define L4_SIGN_EXT_MASK        (0x1FFFFUL << 47)
 
 #define LOW_ADDR                (0x1UL << 30)
 #define HIGH_ADDR               (0x3UL << 48)
@@ -389,6 +398,78 @@ static int handle_syscall(struct testcases *test)
 	return ret;
 }
 
+static int get_user_syscall(struct testcases *test)
+{
+	uint64_t ptr_address, bitmask;
+	int fd, ret = 0;
+	void *ptr;
+
+	if (la57_enabled()) {
+		bitmask = L5_SIGN_EXT_MASK;
+		ptr_address = HIGH_ADDR;
+	} else {
+		bitmask = L4_SIGN_EXT_MASK;
+		ptr_address = LOW_ADDR;
+	}
+
+	ptr = mmap((void *)ptr_address, PAGE_SIZE, PROT_READ | PROT_WRITE,
+		   MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED, -1, 0);
+
+	if (ptr == MAP_FAILED) {
+		perror("failed to map byte to pass into get_user");
+		return 1;
+	}
+
+	if (set_lam(test->lam) != 0) {
+		ret = 2;
+		goto error;
+	}
+
+	fd = memfd_create("lam_ioctl", 0);
+	if (fd == -1) {
+		munmap(ptr, PAGE_SIZE);
+		exit(EXIT_FAILURE);
+	}
+
+	switch (test->later) {
+	case GET_USER_USER:
+		/* Control group - properly tagged user pointer */
+		ptr = (void *)set_metadata((uint64_t)ptr, test->lam);
+		break;
+	case GET_USER_KERNEL_TOP:
+		/* Kernel address with top bit cleared */
+		bitmask &= (bitmask >> 1);
+		ptr = (void *)((uint64_t)ptr | bitmask);
+		break;
+	case GET_USER_KERNEL_BOT:
+		/* Kernel address with bottom sign-extension bit cleared */
+		bitmask &= (bitmask << 1);
+		ptr = (void *)((uint64_t)ptr | bitmask);
+		break;
+	case GET_USER_KERNEL:
+		/* Try to pass a kernel address */
+		ptr = (void *)((uint64_t)ptr | bitmask);
+		break;
+	default:
+		printf("Invalid test case value passed!\n");
+		break;
+	}
+
+	/*
+	 * Use FIOASYNC ioctl because it utilizes get_user() internally and is
+	 * very non-invasive to the system. Pass differently tagged pointers to
+	 * get_user() in order to verify that valid user pointers are going
+	 * through and invalid kernel/non-canonical pointers are not.
+	 */
+	if (ioctl(fd, FIOASYNC, ptr) != 0)
+		ret = 1;
+
+	close(fd);
+error:
+	munmap(ptr, PAGE_SIZE);
+	return ret;
+}
+
 int sys_uring_setup(unsigned int entries, struct io_uring_params *p)
 {
 	return (int)syscall(__NR_io_uring_setup, entries, p);
@@ -902,6 +983,33 @@ static struct testcases syscall_cases[] = {
 		.test_func = handle_syscall,
 		.msg = "SYSCALL:[Negative] Disable LAM. Dereferencing pointer with metadata.\n",
 	},
+	{
+		.later = GET_USER_USER,
+		.lam = LAM_U57_BITS,
+		.test_func = get_user_syscall,
+		.msg = "GET_USER: get_user() and pass a properly tagged user pointer.\n",
+	},
+	{
+		.later = GET_USER_KERNEL_TOP,
+		.expected = 1,
+		.lam = LAM_U57_BITS,
+		.test_func = get_user_syscall,
+		.msg = "GET_USER:[Negative] get_user() with a kernel pointer and the top bit cleared.\n",
+	},
+	{
+		.later = GET_USER_KERNEL_BOT,
+		.expected = 1,
+		.lam = LAM_U57_BITS,
+		.test_func = get_user_syscall,
+		.msg = "GET_USER:[Negative] get_user() with a kernel pointer and the bottom sign-extension bit cleared.\n",
+	},
+	{
+		.later = GET_USER_KERNEL,
+		.expected = 1,
+		.lam = LAM_U57_BITS,
+		.test_func = get_user_syscall,
+		.msg = "GET_USER:[Negative] get_user() and pass a kernel pointer.\n",
+	},
 };
 
 static struct testcases mmap_cases[] = {

From 3acfcefa795c6cfb08c68467060bd7aa30557077 Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Wed, 22 Jan 2025 15:41:03 +0800
Subject: [PATCH 0517/1173] perf/x86/intel/bts: Allocate bts_ctx only if
 necessary

Avoid unnecessary per-CPU memory allocation on unsupported CPUs,
this can save 12K memory for each CPU

Signed-off-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Kan Liang <kan.liang@linux.intel.com>
Link: https://lore.kernel.org/r/20250122074103.3091-1-lirongqing@baidu.com
---
 arch/x86/events/intel/bts.c | 22 +++++++++++++---------
 1 file changed, 13 insertions(+), 9 deletions(-)

diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index 8f78b0c900ef4..8e09319544975 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -36,7 +36,7 @@ enum {
 	BTS_STATE_ACTIVE,
 };
 
-static DEFINE_PER_CPU(struct bts_ctx, bts_ctx);
+static struct bts_ctx __percpu *bts_ctx;
 
 #define BTS_RECORD_SIZE		24
 #define BTS_SAFETY_MARGIN	4080
@@ -231,7 +231,7 @@ bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle);
 
 static void __bts_event_start(struct perf_event *event)
 {
-	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+	struct bts_ctx *bts = this_cpu_ptr(bts_ctx);
 	struct bts_buffer *buf = perf_get_aux(&bts->handle);
 	u64 config = 0;
 
@@ -260,7 +260,7 @@ static void __bts_event_start(struct perf_event *event)
 static void bts_event_start(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+	struct bts_ctx *bts = this_cpu_ptr(bts_ctx);
 	struct bts_buffer *buf;
 
 	buf = perf_aux_output_begin(&bts->handle, event);
@@ -290,7 +290,7 @@ static void bts_event_start(struct perf_event *event, int flags)
 
 static void __bts_event_stop(struct perf_event *event, int state)
 {
-	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+	struct bts_ctx *bts = this_cpu_ptr(bts_ctx);
 
 	/* ACTIVE -> INACTIVE(PMI)/STOPPED(->stop()) */
 	WRITE_ONCE(bts->state, state);
@@ -305,7 +305,7 @@ static void __bts_event_stop(struct perf_event *event, int state)
 static void bts_event_stop(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+	struct bts_ctx *bts = this_cpu_ptr(bts_ctx);
 	struct bts_buffer *buf = NULL;
 	int state = READ_ONCE(bts->state);
 
@@ -338,7 +338,7 @@ static void bts_event_stop(struct perf_event *event, int flags)
 
 void intel_bts_enable_local(void)
 {
-	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+	struct bts_ctx *bts = this_cpu_ptr(bts_ctx);
 	int state = READ_ONCE(bts->state);
 
 	/*
@@ -358,7 +358,7 @@ void intel_bts_enable_local(void)
 
 void intel_bts_disable_local(void)
 {
-	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+	struct bts_ctx *bts = this_cpu_ptr(bts_ctx);
 
 	/*
 	 * Here we transition from ACTIVE to INACTIVE;
@@ -450,7 +450,7 @@ bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle)
 int intel_bts_interrupt(void)
 {
 	struct debug_store *ds = this_cpu_ptr(&cpu_hw_events)->ds;
-	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+	struct bts_ctx *bts = this_cpu_ptr(bts_ctx);
 	struct perf_event *event = bts->handle.event;
 	struct bts_buffer *buf;
 	s64 old_head;
@@ -518,7 +518,7 @@ static void bts_event_del(struct perf_event *event, int mode)
 
 static int bts_event_add(struct perf_event *event, int mode)
 {
-	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+	struct bts_ctx *bts = this_cpu_ptr(bts_ctx);
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 
@@ -605,6 +605,10 @@ static __init int bts_init(void)
 		return -ENODEV;
 	}
 
+	bts_ctx = alloc_percpu(struct bts_ctx);
+	if (!bts_ctx)
+		return -ENOMEM;
+
 	bts_pmu.capabilities	= PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_ITRACE |
 				  PERF_PMU_CAP_EXCLUSIVE;
 	bts_pmu.task_ctx_nr	= perf_sw_context;

From 3c27b40830cad0917c92fecf0c9cb1ec41de17cc Mon Sep 17 00:00:00 2001
From: Michael Jeanson <mjeanson@efficios.com>
Date: Tue, 21 Jan 2025 16:33:52 -0500
Subject: [PATCH 0518/1173] selftests/rseq: Add rseq syscall errors test

This test adds coverage of expected errors during rseq registration and
unregistration, it disables glibc integration and will thus always
exercise the rseq syscall explictly.

Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/r/20250121213402.1754762-1-mjeanson@efficios.com
---
 tools/testing/selftests/rseq/.gitignore       |   1 +
 tools/testing/selftests/rseq/Makefile         |   9 +-
 tools/testing/selftests/rseq/rseq.c           |   6 +-
 tools/testing/selftests/rseq/rseq.h           |   5 +
 .../selftests/rseq/run_syscall_errors_test.sh |   5 +
 .../selftests/rseq/syscall_errors_test.c      | 124 ++++++++++++++++++
 6 files changed, 145 insertions(+), 5 deletions(-)
 create mode 100755 tools/testing/selftests/rseq/run_syscall_errors_test.sh
 create mode 100644 tools/testing/selftests/rseq/syscall_errors_test.c

diff --git a/tools/testing/selftests/rseq/.gitignore b/tools/testing/selftests/rseq/.gitignore
index 16496de5f6ce4..0fda241fa62b0 100644
--- a/tools/testing/selftests/rseq/.gitignore
+++ b/tools/testing/selftests/rseq/.gitignore
@@ -9,3 +9,4 @@ param_test_compare_twice
 param_test_mm_cid
 param_test_mm_cid_benchmark
 param_test_mm_cid_compare_twice
+syscall_errors_test
diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile
index 5a3432fceb586..0d0a5fae59547 100644
--- a/tools/testing/selftests/rseq/Makefile
+++ b/tools/testing/selftests/rseq/Makefile
@@ -16,11 +16,12 @@ OVERRIDE_TARGETS = 1
 
 TEST_GEN_PROGS = basic_test basic_percpu_ops_test basic_percpu_ops_mm_cid_test param_test \
 		param_test_benchmark param_test_compare_twice param_test_mm_cid \
-		param_test_mm_cid_benchmark param_test_mm_cid_compare_twice
+		param_test_mm_cid_benchmark param_test_mm_cid_compare_twice \
+		syscall_errors_test
 
 TEST_GEN_PROGS_EXTENDED = librseq.so
 
-TEST_PROGS = run_param_test.sh
+TEST_PROGS = run_param_test.sh run_syscall_errors_test.sh
 
 TEST_FILES := settings
 
@@ -54,3 +55,7 @@ $(OUTPUT)/param_test_mm_cid_benchmark: param_test.c $(TEST_GEN_PROGS_EXTENDED) \
 $(OUTPUT)/param_test_mm_cid_compare_twice: param_test.c $(TEST_GEN_PROGS_EXTENDED) \
 					rseq.h rseq-*.h
 	$(CC) $(CFLAGS) -DBUILDOPT_RSEQ_PERCPU_MM_CID -DRSEQ_COMPARE_TWICE $< $(LDLIBS) -lrseq -o $@
+
+$(OUTPUT)/syscall_errors_test: syscall_errors_test.c $(TEST_GEN_PROGS_EXTENDED) \
+					rseq.h rseq-*.h
+	$(CC) $(CFLAGS) $< $(LDLIBS) -lrseq -o $@
diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c
index f6156790c3b4d..1e29db92094d8 100644
--- a/tools/testing/selftests/rseq/rseq.c
+++ b/tools/testing/selftests/rseq/rseq.c
@@ -87,7 +87,7 @@ static int sys_getcpu(unsigned *cpu, unsigned *node)
 	return syscall(__NR_getcpu, cpu, node, NULL);
 }
 
-int rseq_available(void)
+bool rseq_available(void)
 {
 	int rc;
 
@@ -96,9 +96,9 @@ int rseq_available(void)
 		abort();
 	switch (errno) {
 	case ENOSYS:
-		return 0;
+		return false;
 	case EINVAL:
-		return 1;
+		return true;
 	default:
 		abort();
 	}
diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h
index ba424ce80a719..f51a5fdb04443 100644
--- a/tools/testing/selftests/rseq/rseq.h
+++ b/tools/testing/selftests/rseq/rseq.h
@@ -159,6 +159,11 @@ int32_t rseq_fallback_current_cpu(void);
  */
 int32_t rseq_fallback_current_node(void);
 
+/*
+ * Returns true if rseq is supported.
+ */
+bool rseq_available(void);
+
 /*
  * Values returned can be either the current CPU number, -1 (rseq is
  * uninitialized), or -2 (rseq initialization has failed).
diff --git a/tools/testing/selftests/rseq/run_syscall_errors_test.sh b/tools/testing/selftests/rseq/run_syscall_errors_test.sh
new file mode 100755
index 0000000000000..9272246b39f24
--- /dev/null
+++ b/tools/testing/selftests/rseq/run_syscall_errors_test.sh
@@ -0,0 +1,5 @@
+#!/bin/bash
+# SPDX-License-Identifier: MIT
+# SPDX-FileCopyrightText: 2024 Michael Jeanson <mjeanson@efficios.com>
+
+GLIBC_TUNABLES="${GLIBC_TUNABLES:-}:glibc.pthread.rseq=0" ./syscall_errors_test
diff --git a/tools/testing/selftests/rseq/syscall_errors_test.c b/tools/testing/selftests/rseq/syscall_errors_test.c
new file mode 100644
index 0000000000000..a5d9e1f8a2dc2
--- /dev/null
+++ b/tools/testing/selftests/rseq/syscall_errors_test.c
@@ -0,0 +1,124 @@
+// SPDX-License-Identifier: MIT
+// SPDX-FileCopyrightText: 2024 Michael Jeanson <mjeanson@efficios.com>
+
+#ifndef _GNU_SOURCE
+#define _GNU_SOURCE
+#endif
+
+#include <assert.h>
+#include <stdint.h>
+#include <syscall.h>
+#include <string.h>
+#include <unistd.h>
+
+#include "rseq.h"
+
+static int sys_rseq(void *rseq_abi, uint32_t rseq_len,
+		    int flags, uint32_t sig)
+{
+	return syscall(__NR_rseq, rseq_abi, rseq_len, flags, sig);
+}
+
+/*
+ * Check the value of errno on some expected failures of the rseq syscall.
+ */
+
+int main(void)
+{
+	struct rseq_abi *global_rseq = rseq_get_abi();
+	int ret;
+	int errno_copy;
+
+	if (!rseq_available()) {
+		fprintf(stderr, "rseq syscall unavailable");
+		goto error;
+	}
+
+	/* The current thread is NOT registered. */
+
+	/* EINVAL */
+	errno = 0;
+	ret = sys_rseq(global_rseq, 32, -1, RSEQ_SIG);
+	errno_copy = errno;
+	fprintf(stderr, "Registration with invalid flag fails with errno set to EINVAL (ret = %d, errno = %s)\n", ret, strerrorname_np(errno_copy));
+	if (ret == 0 || errno_copy != EINVAL)
+		goto error;
+
+	errno = 0;
+	ret = sys_rseq((char *) global_rseq + 1, 32, 0, RSEQ_SIG);
+	errno_copy = errno;
+	fprintf(stderr, "Registration with unaligned rseq_abi fails with errno set to EINVAL (ret = %d, errno = %s)\n", ret, strerrorname_np(errno_copy));
+	if (ret == 0 || errno_copy != EINVAL)
+		goto error;
+
+	errno = 0;
+	ret = sys_rseq(global_rseq, 31, 0, RSEQ_SIG);
+	errno_copy = errno;
+	fprintf(stderr, "Registration with invalid size fails with errno set to EINVAL (ret = %d, errno = %s)\n", ret, strerrorname_np(errno_copy));
+	if (ret == 0 || errno_copy != EINVAL)
+		goto error;
+
+
+#if defined(__LP64__) && (!defined(__s390__) && !defined(__s390x__))
+	/*
+	 * We haven't found a reliable way to find an invalid address when
+	 * running a 32bit userspace on a 64bit kernel, so only run this test
+	 * on 64bit builds for the moment.
+	 *
+	 * Also exclude architectures that select
+	 * CONFIG_ALTERNATE_USER_ADDRESS_SPACE where the kernel and userspace
+	 * have their own address space and this failure can't happen.
+	 */
+
+	/* EFAULT */
+	errno = 0;
+	ret = sys_rseq((void *) -4096UL, 32, 0, RSEQ_SIG);
+	errno_copy = errno;
+	fprintf(stderr, "Registration with invalid address fails with errno set to EFAULT (ret = %d, errno = %s)\n", ret, strerrorname_np(errno_copy));
+	if (ret == 0 || errno_copy != EFAULT)
+		goto error;
+#endif
+
+	errno = 0;
+	ret = sys_rseq(global_rseq, 32, 0, RSEQ_SIG);
+	errno_copy = errno;
+	fprintf(stderr, "Registration succeeds for the current thread (ret = %d, errno = %s)\n", ret, strerrorname_np(errno_copy));
+	if (ret != 0 && errno != 0)
+		goto error;
+
+	/* The current thread is registered. */
+
+	/* EBUSY */
+	errno = 0;
+	ret = sys_rseq(global_rseq, 32, 0, RSEQ_SIG);
+	errno_copy = errno;
+	fprintf(stderr, "Double registration fails with errno set to EBUSY (ret = %d, errno = %s)\n", ret, strerrorname_np(errno_copy));
+	if (ret == 0 || errno_copy != EBUSY)
+		goto error;
+
+	/* EPERM */
+	errno = 0;
+	ret = sys_rseq(global_rseq, 32, RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG + 1);
+	errno_copy = errno;
+	fprintf(stderr, "Unregistration with wrong RSEQ_SIG fails with errno to EPERM (ret = %d, errno = %s)\n", ret, strerrorname_np(errno_copy));
+	if (ret == 0 || errno_copy != EPERM)
+		goto error;
+
+	errno = 0;
+	ret = sys_rseq(global_rseq, 32, RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG);
+	errno_copy = errno;
+	fprintf(stderr, "Unregistration succeeds for the current thread (ret = %d, errno = %s)\n", ret, strerrorname_np(errno_copy));
+	if (ret != 0)
+		goto error;
+
+	errno = 0;
+	ret = sys_rseq(global_rseq, 32, RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG);
+	errno_copy = errno;
+	fprintf(stderr, "Double unregistration fails with errno set to EINVAL (ret = %d, errno = %s)\n", ret, strerrorname_np(errno_copy));
+	if (ret == 0 || errno_copy != EINVAL)
+		goto error;
+
+	return 0;
+error:
+	return -1;
+}

From e1a0bdbdfdf08428f0ede5ae49c7f4139ac73ef5 Mon Sep 17 00:00:00 2001
From: Patrisious Haddad <phaddad@nvidia.com>
Date: Thu, 20 Feb 2025 08:47:10 +0200
Subject: [PATCH 0519/1173] RDMA/mlx5: Fix bind QP error cleanup flow

When there is a failure during bind QP, the cleanup flow destroys the
counter regardless if it is the one that created it or not, which is
problematic since if it isn't the one that created it, that counter could
still be in use.

Fix that by destroying the counter only if it was created during this call.

Fixes: 45842fc627c7 ("IB/mlx5: Support statistic q counter configuration")
Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Reviewed-by: Mark Zhang <markzhang@nvidia.com>
Link: https://patch.msgid.link/25dfefddb0ebefa668c32e06a94d84e3216257cf.1740033937.git.leon@kernel.org
Reviewed-by: Zhu Yanjun <yanjun.zhu@linux.dev>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/mlx5/counters.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/counters.c b/drivers/infiniband/hw/mlx5/counters.c
index 4f6c1968a2ee3..81cfa74147a18 100644
--- a/drivers/infiniband/hw/mlx5/counters.c
+++ b/drivers/infiniband/hw/mlx5/counters.c
@@ -546,6 +546,7 @@ static int mlx5_ib_counter_bind_qp(struct rdma_counter *counter,
 				   struct ib_qp *qp)
 {
 	struct mlx5_ib_dev *dev = to_mdev(qp->device);
+	bool new = false;
 	int err;
 
 	if (!counter->id) {
@@ -560,6 +561,7 @@ static int mlx5_ib_counter_bind_qp(struct rdma_counter *counter,
 			return err;
 		counter->id =
 			MLX5_GET(alloc_q_counter_out, out, counter_set_id);
+		new = true;
 	}
 
 	err = mlx5_ib_qp_set_counter(qp, counter);
@@ -569,8 +571,10 @@ static int mlx5_ib_counter_bind_qp(struct rdma_counter *counter,
 	return 0;
 
 fail_set_counter:
-	mlx5_ib_counter_dealloc(counter);
-	counter->id = 0;
+	if (new) {
+		mlx5_ib_counter_dealloc(counter);
+		counter->id = 0;
+	}
 
 	return err;
 }

From 51184c3c96a19b5143710ef91426e311f4364bac Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 10 Jan 2025 22:33:33 -0800
Subject: [PATCH 0520/1173] x86/usercopy: Fix kernel-doc func param name in
 clean_cache_range()'s description

Use @addr instead of @vaddr in the kernel-doc comment for
clean_cache_range() to eliminate warnings:

  arch/x86/lib/usercopy_64.c:29: warning: Function parameter or struct member 'addr' not described in 'clean_cache_range'
  arch/x86/lib/usercopy_64.c:29: warning: Excess function parameter 'vaddr' description in 'clean_cache_range'

Fixes: 0aed55af8834 ("x86, uaccess: introduce copy_from_iter_flushcache for pmem / cache-bypass operations")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20250111063333.911084-1-rdunlap@infradead.org
---
 arch/x86/lib/usercopy_64.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index e9251b89a9e93..654280aaa3e9e 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -18,7 +18,7 @@
 #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
 /**
  * clean_cache_range - write back a cache range with CLWB
- * @vaddr:	virtual start address
+ * @addr:	virtual start address
  * @size:	number of bytes to write back
  *
  * Write back a cache range using the CLWB (cache line write back)

From b66535356a4834a234f99e16a97eb51f2c6c5a7d Mon Sep 17 00:00:00 2001
From: Kashyap Desai <kashyap.desai@broadcom.com>
Date: Sat, 22 Feb 2025 07:20:21 -0800
Subject: [PATCH 0521/1173] RDMA/bnxt_re: Fix the page details for the srq
 created by kernel consumers

While using nvme target with use_srq on, below kernel panic is noticed.

[  549.698111] bnxt_en 0000:41:00.0 enp65s0np0: FEC autoneg off encoding: Clause 91 RS(544,514)
[  566.393619] Oops: divide error: 0000 [#1] PREEMPT SMP NOPTI
..
[  566.393799]  <TASK>
[  566.393807]  ? __die_body+0x1a/0x60
[  566.393823]  ? die+0x38/0x60
[  566.393835]  ? do_trap+0xe4/0x110
[  566.393847]  ? bnxt_qplib_alloc_init_hwq+0x1d4/0x580 [bnxt_re]
[  566.393867]  ? bnxt_qplib_alloc_init_hwq+0x1d4/0x580 [bnxt_re]
[  566.393881]  ? do_error_trap+0x7c/0x120
[  566.393890]  ? bnxt_qplib_alloc_init_hwq+0x1d4/0x580 [bnxt_re]
[  566.393911]  ? exc_divide_error+0x34/0x50
[  566.393923]  ? bnxt_qplib_alloc_init_hwq+0x1d4/0x580 [bnxt_re]
[  566.393939]  ? asm_exc_divide_error+0x16/0x20
[  566.393966]  ? bnxt_qplib_alloc_init_hwq+0x1d4/0x580 [bnxt_re]
[  566.393997]  bnxt_qplib_create_srq+0xc9/0x340 [bnxt_re]
[  566.394040]  bnxt_re_create_srq+0x335/0x3b0 [bnxt_re]
[  566.394057]  ? srso_return_thunk+0x5/0x5f
[  566.394068]  ? __init_swait_queue_head+0x4a/0x60
[  566.394090]  ib_create_srq_user+0xa7/0x150 [ib_core]
[  566.394147]  nvmet_rdma_queue_connect+0x7d0/0xbe0 [nvmet_rdma]
[  566.394174]  ? lock_release+0x22c/0x3f0
[  566.394187]  ? srso_return_thunk+0x5/0x5f

Page size and shift info is set only for the user space SRQs.
Set page size and page shift for kernel space SRQs also.

Fixes: 0c4dcd602817 ("RDMA/bnxt_re: Refactor hardware queue memory allocation")
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://patch.msgid.link/1740237621-29291-1-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/bnxt_re/ib_verbs.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index 2de101d6e8255..6f5db32082dd7 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -1870,6 +1870,8 @@ int bnxt_re_create_srq(struct ib_srq *ib_srq,
 	srq->qplib_srq.threshold = srq_init_attr->attr.srq_limit;
 	srq->srq_limit = srq_init_attr->attr.srq_limit;
 	srq->qplib_srq.eventq_hw_ring_id = rdev->nqr->nq[0].ring_id;
+	srq->qplib_srq.sg_info.pgsize = PAGE_SIZE;
+	srq->qplib_srq.sg_info.pgshft = PAGE_SHIFT;
 	nq = &rdev->nqr->nq[0];
 
 	if (udata) {

From 174e5e9da4f5946de3d09c32ee56cbbc9d70505b Mon Sep 17 00:00:00 2001
From: Patrick Rudolph <patrick.rudolph@9elements.com>
Date: Fri, 21 Feb 2025 09:12:42 +0100
Subject: [PATCH 0522/1173] efi/cper: Fix cper_ia_proc_ctx alignment

According to the UEFI Common Platform Error Record appendix, the
IA32/X64 Processor Context Information Structure is a variable length
structure, but "is padded with zeros if the size is not a multiple
of 16 bytes".

Currently this isn't honoured, causing all but the first structure to
be garbage when printed. Thus align the size to be a multiple of 16.

Signed-off-by: Patrick Rudolph <patrick.rudolph@9elements.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/cper-x86.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/firmware/efi/cper-x86.c b/drivers/firmware/efi/cper-x86.c
index 438ed9eff6d01..3949d7b5e808f 100644
--- a/drivers/firmware/efi/cper-x86.c
+++ b/drivers/firmware/efi/cper-x86.c
@@ -325,7 +325,7 @@ void cper_print_proc_ia(const char *pfx, const struct cper_sec_proc_ia *proc)
 
 	ctx_info = (struct cper_ia_proc_ctx *)err_info;
 	for (i = 0; i < VALID_PROC_CXT_INFO_NUM(proc->validation_bits); i++) {
-		int size = sizeof(*ctx_info) + ctx_info->reg_arr_size;
+		int size = ALIGN(sizeof(*ctx_info) + ctx_info->reg_arr_size, 16);
 		int groupsize = 4;
 
 		printk("%sContext Information Structure %d:\n", pfx, i);

From d6a2d02aa060531607f4a8411ec384470faa2761 Mon Sep 17 00:00:00 2001
From: Patrick Rudolph <patrick.rudolph@9elements.com>
Date: Fri, 21 Feb 2025 12:15:16 +0100
Subject: [PATCH 0523/1173] efi/cper: Fix cper_arm_ctx_info alignment

According to the UEFI Common Platform Error Record appendix, the
processor context information structure is a variable length structure,
but "is padded with zeros if the size is not a multiple of 16 bytes".

Currently this isn't honoured, causing all but the first structure to
be garbage when printed. Thus align the size to be a multiple of 16.

Signed-off-by: Patrick Rudolph <patrick.rudolph@9elements.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/cper-arm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/firmware/efi/cper-arm.c b/drivers/firmware/efi/cper-arm.c
index fa9c1c3bf168b..f0a63d09d3c49 100644
--- a/drivers/firmware/efi/cper-arm.c
+++ b/drivers/firmware/efi/cper-arm.c
@@ -311,7 +311,7 @@ void cper_print_proc_arm(const char *pfx,
 	ctx_info = (struct cper_arm_ctx_info *)err_info;
 	max_ctx_type = ARRAY_SIZE(arm_reg_ctx_strs) - 1;
 	for (i = 0; i < proc->context_info_num; i++) {
-		int size = sizeof(*ctx_info) + ctx_info->size;
+		int size = ALIGN(sizeof(*ctx_info) + ctx_info->size, 16);
 
 		printk("%sContext info structure %d:\n", pfx, i);
 		if (len < size) {

From cb6ae457bc6af58c84a7854df5e7e32ba1c6a715 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Sun, 23 Feb 2025 16:48:54 +0100
Subject: [PATCH 0524/1173] efivarfs: Defer PM notifier registration until
 .fill_super

syzbot reports an issue that turns out to be caused by the fact that the
efivarfs PM notifier may be invoked before the efivarfs_fs_info::sb
field is populated, resulting in a NULL deference.

So defer the registration until efivarfs_fill_super() is invoked.

Reported-by: syzbot+00d13e505ef530a45100@syzkaller.appspotmail.com
Tested-by: syzbot+00d13e505ef530a45100@syzkaller.appspotmail.com
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 fs/efivarfs/super.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index 09fcf731e65d6..6eae8cf655c12 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -367,6 +367,8 @@ static int efivarfs_fill_super(struct super_block *sb, struct fs_context *fc)
 	if (err)
 		return err;
 
+	register_pm_notifier(&sfi->pm_nb);
+
 	return efivar_init(efivarfs_callback, sb, true);
 }
 
@@ -552,7 +554,6 @@ static int efivarfs_init_fs_context(struct fs_context *fc)
 
 	sfi->pm_nb.notifier_call = efivarfs_pm_notify;
 	sfi->pm_nb.priority = 0;
-	register_pm_notifier(&sfi->pm_nb);
 
 	return 0;
 }

From dc8bd769e70ecae0916bf1b05acad6120c6bd6f0 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Sun, 23 Feb 2025 17:13:38 +0100
Subject: [PATCH 0525/1173] x86/ioperm: Use atomic64_inc_return() in
 ksys_ioperm()

Use atomic64_inc_return(&ref) instead of atomic64_add_return(1, &ref)
to use optimized implementation on targets that define
atomic_inc_return() and to remove now unneeded initialization of the
%eax/%edx register pair before the call to atomic64_inc_return().

On x86_32 the code improves from:

 1b0:    b9 00 00 00 00           mov    $0x0,%ecx
            1b1: R_386_32    .bss
 1b5:    89 43 0c                 mov    %eax,0xc(%ebx)
 1b8:    31 d2                    xor    %edx,%edx
 1ba:    b8 01 00 00 00           mov    $0x1,%eax
 1bf:    e8 fc ff ff ff           call   1c0 <ksys_ioperm+0xa8>
            1c0: R_386_PC32    atomic64_add_return_cx8
 1c4:    89 03                    mov    %eax,(%ebx)
 1c6:    89 53 04                 mov    %edx,0x4(%ebx)

to:

 1b0:    be 00 00 00 00           mov    $0x0,%esi
            1b1: R_386_32    .bss
 1b5:    89 43 0c                 mov    %eax,0xc(%ebx)
 1b8:    e8 fc ff ff ff           call   1b9 <ksys_ioperm+0xa1>
            1b9: R_386_PC32    atomic64_inc_return_cx8
 1bd:    89 03                    mov    %eax,(%ebx)
 1bf:    89 53 04                 mov    %edx,0x4(%ebx)

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250223161355.3607-1-ubizjak@gmail.com
---
 arch/x86/kernel/ioport.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c
index e2fab3ceb09fb..6290dd120f5e4 100644
--- a/arch/x86/kernel/ioport.c
+++ b/arch/x86/kernel/ioport.c
@@ -144,7 +144,7 @@ long ksys_ioperm(unsigned long from, unsigned long num, int turn_on)
 	 * Update the sequence number to force a TSS update on return to
 	 * user mode.
 	 */
-	iobm->sequence = atomic64_add_return(1, &io_bitmap_sequence);
+	iobm->sequence = atomic64_inc_return(&io_bitmap_sequence);
 
 	return 0;
 }

From d082ecbc71e9e0bf49883ee4afd435a77a5101b6 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 23 Feb 2025 12:32:57 -0800
Subject: [PATCH 0526/1173] Linux 6.14-rc4

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index 96407c1d6be16..30dab4c8b0120 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 14
 SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc4
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*

From cf3e6960263a2ecdf5528056b321e41557e9b03d Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sat, 22 Feb 2025 09:05:36 -0500
Subject: [PATCH 0527/1173] bcachefs: fix bch2_extent_ptr_eq()

Reviewed-by: Thorsten Blum <thorsten.blum@linux.dev>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/extents.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/bcachefs/extents.h b/fs/bcachefs/extents.h
index 620b284aa34f0..204d765dd74c8 100644
--- a/fs/bcachefs/extents.h
+++ b/fs/bcachefs/extents.h
@@ -704,7 +704,7 @@ static inline bool bch2_extent_ptr_eq(struct bch_extent_ptr ptr1,
 		ptr1.unwritten	== ptr2.unwritten &&
 		ptr1.offset	== ptr2.offset &&
 		ptr1.dev	== ptr2.dev &&
-		ptr1.dev	== ptr2.dev);
+		ptr1.gen	== ptr2.gen);
 }
 
 void bch2_ptr_swab(struct bkey_s);

From f15176b8b6e72ac30e14fd273282d2b72562d26b Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Thu, 20 Feb 2025 19:48:15 +0100
Subject: [PATCH 0528/1173] net: dsa: rtl8366rb: Fix compilation problem

When the kernel is compiled without LED framework support the
rtl8366rb fails to build like this:

rtl8366rb.o: in function `rtl8366rb_setup_led':
rtl8366rb.c:953:(.text.unlikely.rtl8366rb_setup_led+0xe8):
  undefined reference to `led_init_default_state_get'
rtl8366rb.c:980:(.text.unlikely.rtl8366rb_setup_led+0x240):
  undefined reference to `devm_led_classdev_register_ext'

As this is constantly coming up in different randconfig builds,
bite the bullet and create a separate file for the offending
code, split out a header with all stuff needed both in the
core driver and the leds code.

Add a new bool Kconfig option for the LED compile target, such
that it depends on LEDS_CLASS=y || LEDS_CLASS=RTL8366RB
which make LED support always available when LEDS_CLASS is
compiled into the kernel and enforce that if the LEDS_CLASS
is a module, then the RTL8366RB driver needs to be a module
as well so that modprobe can resolve the dependencies.

Fixes: 32d617005475 ("net: dsa: realtek: add LED drivers for rtl8366rb")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202502070525.xMUImayb-lkp@intel.com/
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/realtek/Kconfig          |   6 +
 drivers/net/dsa/realtek/Makefile         |   3 +
 drivers/net/dsa/realtek/rtl8366rb-leds.c | 177 ++++++++++++++++
 drivers/net/dsa/realtek/rtl8366rb.c      | 258 +----------------------
 drivers/net/dsa/realtek/rtl8366rb.h      | 107 ++++++++++
 5 files changed, 299 insertions(+), 252 deletions(-)
 create mode 100644 drivers/net/dsa/realtek/rtl8366rb-leds.c
 create mode 100644 drivers/net/dsa/realtek/rtl8366rb.h

diff --git a/drivers/net/dsa/realtek/Kconfig b/drivers/net/dsa/realtek/Kconfig
index 6989972eebc30..10687722d14c0 100644
--- a/drivers/net/dsa/realtek/Kconfig
+++ b/drivers/net/dsa/realtek/Kconfig
@@ -43,4 +43,10 @@ config NET_DSA_REALTEK_RTL8366RB
 	help
 	  Select to enable support for Realtek RTL8366RB.
 
+config NET_DSA_REALTEK_RTL8366RB_LEDS
+	bool "Support RTL8366RB LED control"
+	depends on (LEDS_CLASS=y || LEDS_CLASS=NET_DSA_REALTEK_RTL8366RB)
+	depends on NET_DSA_REALTEK_RTL8366RB
+	default NET_DSA_REALTEK_RTL8366RB
+
 endif
diff --git a/drivers/net/dsa/realtek/Makefile b/drivers/net/dsa/realtek/Makefile
index 35491dc20d6d6..17367bcba496c 100644
--- a/drivers/net/dsa/realtek/Makefile
+++ b/drivers/net/dsa/realtek/Makefile
@@ -12,4 +12,7 @@ endif
 
 obj-$(CONFIG_NET_DSA_REALTEK_RTL8366RB) += rtl8366.o
 rtl8366-objs 				:= rtl8366-core.o rtl8366rb.o
+ifdef CONFIG_NET_DSA_REALTEK_RTL8366RB_LEDS
+rtl8366-objs 				+= rtl8366rb-leds.o
+endif
 obj-$(CONFIG_NET_DSA_REALTEK_RTL8365MB) += rtl8365mb.o
diff --git a/drivers/net/dsa/realtek/rtl8366rb-leds.c b/drivers/net/dsa/realtek/rtl8366rb-leds.c
new file mode 100644
index 0000000000000..99c890681ae60
--- /dev/null
+++ b/drivers/net/dsa/realtek/rtl8366rb-leds.c
@@ -0,0 +1,177 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bitops.h>
+#include <linux/regmap.h>
+#include <net/dsa.h>
+#include "rtl83xx.h"
+#include "rtl8366rb.h"
+
+static inline u32 rtl8366rb_led_group_port_mask(u8 led_group, u8 port)
+{
+	switch (led_group) {
+	case 0:
+		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
+	case 1:
+		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
+	case 2:
+		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
+	case 3:
+		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
+	default:
+		return 0;
+	}
+}
+
+static int rb8366rb_get_port_led(struct rtl8366rb_led *led)
+{
+	struct realtek_priv *priv = led->priv;
+	u8 led_group = led->led_group;
+	u8 port_num = led->port_num;
+	int ret;
+	u32 val;
+
+	ret = regmap_read(priv->map, RTL8366RB_LED_X_X_CTRL_REG(led_group),
+			  &val);
+	if (ret) {
+		dev_err(priv->dev, "error reading LED on port %d group %d\n",
+			led_group, port_num);
+		return ret;
+	}
+
+	return !!(val & rtl8366rb_led_group_port_mask(led_group, port_num));
+}
+
+static int rb8366rb_set_port_led(struct rtl8366rb_led *led, bool enable)
+{
+	struct realtek_priv *priv = led->priv;
+	u8 led_group = led->led_group;
+	u8 port_num = led->port_num;
+	int ret;
+
+	ret = regmap_update_bits(priv->map,
+				 RTL8366RB_LED_X_X_CTRL_REG(led_group),
+				 rtl8366rb_led_group_port_mask(led_group,
+							       port_num),
+				 enable ? 0xffff : 0);
+	if (ret) {
+		dev_err(priv->dev, "error updating LED on port %d group %d\n",
+			led_group, port_num);
+		return ret;
+	}
+
+	/* Change the LED group to manual controlled LEDs if required */
+	ret = rb8366rb_set_ledgroup_mode(priv, led_group,
+					 RTL8366RB_LEDGROUP_FORCE);
+
+	if (ret) {
+		dev_err(priv->dev, "error updating LED GROUP group %d\n",
+			led_group);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int
+rtl8366rb_cled_brightness_set_blocking(struct led_classdev *ldev,
+				       enum led_brightness brightness)
+{
+	struct rtl8366rb_led *led = container_of(ldev, struct rtl8366rb_led,
+						 cdev);
+
+	return rb8366rb_set_port_led(led, brightness == LED_ON);
+}
+
+static int rtl8366rb_setup_led(struct realtek_priv *priv, struct dsa_port *dp,
+			       struct fwnode_handle *led_fwnode)
+{
+	struct rtl8366rb *rb = priv->chip_data;
+	struct led_init_data init_data = { };
+	enum led_default_state state;
+	struct rtl8366rb_led *led;
+	u32 led_group;
+	int ret;
+
+	ret = fwnode_property_read_u32(led_fwnode, "reg", &led_group);
+	if (ret)
+		return ret;
+
+	if (led_group >= RTL8366RB_NUM_LEDGROUPS) {
+		dev_warn(priv->dev, "Invalid LED reg %d defined for port %d",
+			 led_group, dp->index);
+		return -EINVAL;
+	}
+
+	led = &rb->leds[dp->index][led_group];
+	led->port_num = dp->index;
+	led->led_group = led_group;
+	led->priv = priv;
+
+	state = led_init_default_state_get(led_fwnode);
+	switch (state) {
+	case LEDS_DEFSTATE_ON:
+		led->cdev.brightness = 1;
+		rb8366rb_set_port_led(led, 1);
+		break;
+	case LEDS_DEFSTATE_KEEP:
+		led->cdev.brightness =
+			rb8366rb_get_port_led(led);
+		break;
+	case LEDS_DEFSTATE_OFF:
+	default:
+		led->cdev.brightness = 0;
+		rb8366rb_set_port_led(led, 0);
+	}
+
+	led->cdev.max_brightness = 1;
+	led->cdev.brightness_set_blocking =
+		rtl8366rb_cled_brightness_set_blocking;
+	init_data.fwnode = led_fwnode;
+	init_data.devname_mandatory = true;
+
+	init_data.devicename = kasprintf(GFP_KERNEL, "Realtek-%d:0%d:%d",
+					 dp->ds->index, dp->index, led_group);
+	if (!init_data.devicename)
+		return -ENOMEM;
+
+	ret = devm_led_classdev_register_ext(priv->dev, &led->cdev, &init_data);
+	if (ret) {
+		dev_warn(priv->dev, "Failed to init LED %d for port %d",
+			 led_group, dp->index);
+		return ret;
+	}
+
+	return 0;
+}
+
+int rtl8366rb_setup_leds(struct realtek_priv *priv)
+{
+	struct dsa_switch *ds = &priv->ds;
+	struct device_node *leds_np;
+	struct dsa_port *dp;
+	int ret = 0;
+
+	dsa_switch_for_each_port(dp, ds) {
+		if (!dp->dn)
+			continue;
+
+		leds_np = of_get_child_by_name(dp->dn, "leds");
+		if (!leds_np) {
+			dev_dbg(priv->dev, "No leds defined for port %d",
+				dp->index);
+			continue;
+		}
+
+		for_each_child_of_node_scoped(leds_np, led_np) {
+			ret = rtl8366rb_setup_led(priv, dp,
+						  of_fwnode_handle(led_np));
+			if (ret)
+				break;
+		}
+
+		of_node_put(leds_np);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
diff --git a/drivers/net/dsa/realtek/rtl8366rb.c b/drivers/net/dsa/realtek/rtl8366rb.c
index 4c4a95d4380ce..f54771cab56d4 100644
--- a/drivers/net/dsa/realtek/rtl8366rb.c
+++ b/drivers/net/dsa/realtek/rtl8366rb.c
@@ -27,11 +27,7 @@
 #include "realtek-smi.h"
 #include "realtek-mdio.h"
 #include "rtl83xx.h"
-
-#define RTL8366RB_PORT_NUM_CPU		5
-#define RTL8366RB_NUM_PORTS		6
-#define RTL8366RB_PHY_NO_MAX		4
-#define RTL8366RB_PHY_ADDR_MAX		31
+#include "rtl8366rb.h"
 
 /* Switch Global Configuration register */
 #define RTL8366RB_SGCR				0x0000
@@ -176,39 +172,6 @@
  */
 #define RTL8366RB_VLAN_INGRESS_CTRL2_REG	0x037f
 
-/* LED control registers */
-/* The LED blink rate is global; it is used by all triggers in all groups. */
-#define RTL8366RB_LED_BLINKRATE_REG		0x0430
-#define RTL8366RB_LED_BLINKRATE_MASK		0x0007
-#define RTL8366RB_LED_BLINKRATE_28MS		0x0000
-#define RTL8366RB_LED_BLINKRATE_56MS		0x0001
-#define RTL8366RB_LED_BLINKRATE_84MS		0x0002
-#define RTL8366RB_LED_BLINKRATE_111MS		0x0003
-#define RTL8366RB_LED_BLINKRATE_222MS		0x0004
-#define RTL8366RB_LED_BLINKRATE_446MS		0x0005
-
-/* LED trigger event for each group */
-#define RTL8366RB_LED_CTRL_REG			0x0431
-#define RTL8366RB_LED_CTRL_OFFSET(led_group)	\
-	(4 * (led_group))
-#define RTL8366RB_LED_CTRL_MASK(led_group)	\
-	(0xf << RTL8366RB_LED_CTRL_OFFSET(led_group))
-
-/* The RTL8366RB_LED_X_X registers are used to manually set the LED state only
- * when the corresponding LED group in RTL8366RB_LED_CTRL_REG is
- * RTL8366RB_LEDGROUP_FORCE. Otherwise, it is ignored.
- */
-#define RTL8366RB_LED_0_1_CTRL_REG		0x0432
-#define RTL8366RB_LED_2_3_CTRL_REG		0x0433
-#define RTL8366RB_LED_X_X_CTRL_REG(led_group)	\
-	((led_group) <= 1 ? \
-		RTL8366RB_LED_0_1_CTRL_REG : \
-		RTL8366RB_LED_2_3_CTRL_REG)
-#define RTL8366RB_LED_0_X_CTRL_MASK		GENMASK(5, 0)
-#define RTL8366RB_LED_X_1_CTRL_MASK		GENMASK(11, 6)
-#define RTL8366RB_LED_2_X_CTRL_MASK		GENMASK(5, 0)
-#define RTL8366RB_LED_X_3_CTRL_MASK		GENMASK(11, 6)
-
 #define RTL8366RB_MIB_COUNT			33
 #define RTL8366RB_GLOBAL_MIB_COUNT		1
 #define RTL8366RB_MIB_COUNTER_PORT_OFFSET	0x0050
@@ -244,7 +207,6 @@
 #define RTL8366RB_PORT_STATUS_AN_MASK		0x0080
 
 #define RTL8366RB_NUM_VLANS		16
-#define RTL8366RB_NUM_LEDGROUPS		4
 #define RTL8366RB_NUM_VIDS		4096
 #define RTL8366RB_PRIORITYMAX		7
 #define RTL8366RB_NUM_FIDS		8
@@ -351,46 +313,6 @@
 #define RTL8366RB_GREEN_FEATURE_TX	BIT(0)
 #define RTL8366RB_GREEN_FEATURE_RX	BIT(2)
 
-enum rtl8366_ledgroup_mode {
-	RTL8366RB_LEDGROUP_OFF			= 0x0,
-	RTL8366RB_LEDGROUP_DUP_COL		= 0x1,
-	RTL8366RB_LEDGROUP_LINK_ACT		= 0x2,
-	RTL8366RB_LEDGROUP_SPD1000		= 0x3,
-	RTL8366RB_LEDGROUP_SPD100		= 0x4,
-	RTL8366RB_LEDGROUP_SPD10		= 0x5,
-	RTL8366RB_LEDGROUP_SPD1000_ACT		= 0x6,
-	RTL8366RB_LEDGROUP_SPD100_ACT		= 0x7,
-	RTL8366RB_LEDGROUP_SPD10_ACT		= 0x8,
-	RTL8366RB_LEDGROUP_SPD100_10_ACT	= 0x9,
-	RTL8366RB_LEDGROUP_FIBER		= 0xa,
-	RTL8366RB_LEDGROUP_AN_FAULT		= 0xb,
-	RTL8366RB_LEDGROUP_LINK_RX		= 0xc,
-	RTL8366RB_LEDGROUP_LINK_TX		= 0xd,
-	RTL8366RB_LEDGROUP_MASTER		= 0xe,
-	RTL8366RB_LEDGROUP_FORCE		= 0xf,
-
-	__RTL8366RB_LEDGROUP_MODE_MAX
-};
-
-struct rtl8366rb_led {
-	u8 port_num;
-	u8 led_group;
-	struct realtek_priv *priv;
-	struct led_classdev cdev;
-};
-
-/**
- * struct rtl8366rb - RTL8366RB-specific data
- * @max_mtu: per-port max MTU setting
- * @pvid_enabled: if PVID is set for respective port
- * @leds: per-port and per-ledgroup led info
- */
-struct rtl8366rb {
-	unsigned int max_mtu[RTL8366RB_NUM_PORTS];
-	bool pvid_enabled[RTL8366RB_NUM_PORTS];
-	struct rtl8366rb_led leds[RTL8366RB_NUM_PORTS][RTL8366RB_NUM_LEDGROUPS];
-};
-
 static struct rtl8366_mib_counter rtl8366rb_mib_counters[] = {
 	{ 0,  0, 4, "IfInOctets"				},
 	{ 0,  4, 4, "EtherStatsOctets"				},
@@ -831,9 +753,10 @@ static int rtl8366rb_jam_table(const struct rtl8366rb_jam_tbl_entry *jam_table,
 	return 0;
 }
 
-static int rb8366rb_set_ledgroup_mode(struct realtek_priv *priv,
-				      u8 led_group,
-				      enum rtl8366_ledgroup_mode mode)
+/* This code is used also with LEDs disabled */
+int rb8366rb_set_ledgroup_mode(struct realtek_priv *priv,
+			       u8 led_group,
+			       enum rtl8366_ledgroup_mode mode)
 {
 	int ret;
 	u32 val;
@@ -850,144 +773,7 @@ static int rb8366rb_set_ledgroup_mode(struct realtek_priv *priv,
 	return 0;
 }
 
-static inline u32 rtl8366rb_led_group_port_mask(u8 led_group, u8 port)
-{
-	switch (led_group) {
-	case 0:
-		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
-	case 1:
-		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
-	case 2:
-		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
-	case 3:
-		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
-	default:
-		return 0;
-	}
-}
-
-static int rb8366rb_get_port_led(struct rtl8366rb_led *led)
-{
-	struct realtek_priv *priv = led->priv;
-	u8 led_group = led->led_group;
-	u8 port_num = led->port_num;
-	int ret;
-	u32 val;
-
-	ret = regmap_read(priv->map, RTL8366RB_LED_X_X_CTRL_REG(led_group),
-			  &val);
-	if (ret) {
-		dev_err(priv->dev, "error reading LED on port %d group %d\n",
-			led_group, port_num);
-		return ret;
-	}
-
-	return !!(val & rtl8366rb_led_group_port_mask(led_group, port_num));
-}
-
-static int rb8366rb_set_port_led(struct rtl8366rb_led *led, bool enable)
-{
-	struct realtek_priv *priv = led->priv;
-	u8 led_group = led->led_group;
-	u8 port_num = led->port_num;
-	int ret;
-
-	ret = regmap_update_bits(priv->map,
-				 RTL8366RB_LED_X_X_CTRL_REG(led_group),
-				 rtl8366rb_led_group_port_mask(led_group,
-							       port_num),
-				 enable ? 0xffff : 0);
-	if (ret) {
-		dev_err(priv->dev, "error updating LED on port %d group %d\n",
-			led_group, port_num);
-		return ret;
-	}
-
-	/* Change the LED group to manual controlled LEDs if required */
-	ret = rb8366rb_set_ledgroup_mode(priv, led_group,
-					 RTL8366RB_LEDGROUP_FORCE);
-
-	if (ret) {
-		dev_err(priv->dev, "error updating LED GROUP group %d\n",
-			led_group);
-		return ret;
-	}
-
-	return 0;
-}
-
-static int
-rtl8366rb_cled_brightness_set_blocking(struct led_classdev *ldev,
-				       enum led_brightness brightness)
-{
-	struct rtl8366rb_led *led = container_of(ldev, struct rtl8366rb_led,
-						 cdev);
-
-	return rb8366rb_set_port_led(led, brightness == LED_ON);
-}
-
-static int rtl8366rb_setup_led(struct realtek_priv *priv, struct dsa_port *dp,
-			       struct fwnode_handle *led_fwnode)
-{
-	struct rtl8366rb *rb = priv->chip_data;
-	struct led_init_data init_data = { };
-	enum led_default_state state;
-	struct rtl8366rb_led *led;
-	u32 led_group;
-	int ret;
-
-	ret = fwnode_property_read_u32(led_fwnode, "reg", &led_group);
-	if (ret)
-		return ret;
-
-	if (led_group >= RTL8366RB_NUM_LEDGROUPS) {
-		dev_warn(priv->dev, "Invalid LED reg %d defined for port %d",
-			 led_group, dp->index);
-		return -EINVAL;
-	}
-
-	led = &rb->leds[dp->index][led_group];
-	led->port_num = dp->index;
-	led->led_group = led_group;
-	led->priv = priv;
-
-	state = led_init_default_state_get(led_fwnode);
-	switch (state) {
-	case LEDS_DEFSTATE_ON:
-		led->cdev.brightness = 1;
-		rb8366rb_set_port_led(led, 1);
-		break;
-	case LEDS_DEFSTATE_KEEP:
-		led->cdev.brightness =
-			rb8366rb_get_port_led(led);
-		break;
-	case LEDS_DEFSTATE_OFF:
-	default:
-		led->cdev.brightness = 0;
-		rb8366rb_set_port_led(led, 0);
-	}
-
-	led->cdev.max_brightness = 1;
-	led->cdev.brightness_set_blocking =
-		rtl8366rb_cled_brightness_set_blocking;
-	init_data.fwnode = led_fwnode;
-	init_data.devname_mandatory = true;
-
-	init_data.devicename = kasprintf(GFP_KERNEL, "Realtek-%d:0%d:%d",
-					 dp->ds->index, dp->index, led_group);
-	if (!init_data.devicename)
-		return -ENOMEM;
-
-	ret = devm_led_classdev_register_ext(priv->dev, &led->cdev, &init_data);
-	if (ret) {
-		dev_warn(priv->dev, "Failed to init LED %d for port %d",
-			 led_group, dp->index);
-		return ret;
-	}
-
-	return 0;
-}
-
+/* This code is used also with LEDs disabled */
 static int rtl8366rb_setup_all_leds_off(struct realtek_priv *priv)
 {
 	int ret = 0;
@@ -1008,38 +794,6 @@ static int rtl8366rb_setup_all_leds_off(struct realtek_priv *priv)
 	return ret;
 }
 
-static int rtl8366rb_setup_leds(struct realtek_priv *priv)
-{
-	struct dsa_switch *ds = &priv->ds;
-	struct device_node *leds_np;
-	struct dsa_port *dp;
-	int ret = 0;
-
-	dsa_switch_for_each_port(dp, ds) {
-		if (!dp->dn)
-			continue;
-
-		leds_np = of_get_child_by_name(dp->dn, "leds");
-		if (!leds_np) {
-			dev_dbg(priv->dev, "No leds defined for port %d",
-				dp->index);
-			continue;
-		}
-
-		for_each_child_of_node_scoped(leds_np, led_np) {
-			ret = rtl8366rb_setup_led(priv, dp,
-						  of_fwnode_handle(led_np));
-			if (ret)
-				break;
-		}
-
-		of_node_put(leds_np);
-		if (ret)
-			return ret;
-	}
-	return 0;
-}
-
 static int rtl8366rb_setup(struct dsa_switch *ds)
 {
 	struct realtek_priv *priv = ds->priv;
diff --git a/drivers/net/dsa/realtek/rtl8366rb.h b/drivers/net/dsa/realtek/rtl8366rb.h
new file mode 100644
index 0000000000000..685ff3275faa1
--- /dev/null
+++ b/drivers/net/dsa/realtek/rtl8366rb.h
@@ -0,0 +1,107 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#ifndef _RTL8366RB_H
+#define _RTL8366RB_H
+
+#include "realtek.h"
+
+#define RTL8366RB_PORT_NUM_CPU		5
+#define RTL8366RB_NUM_PORTS		6
+#define RTL8366RB_PHY_NO_MAX		4
+#define RTL8366RB_NUM_LEDGROUPS		4
+#define RTL8366RB_PHY_ADDR_MAX		31
+
+/* LED control registers */
+/* The LED blink rate is global; it is used by all triggers in all groups. */
+#define RTL8366RB_LED_BLINKRATE_REG		0x0430
+#define RTL8366RB_LED_BLINKRATE_MASK		0x0007
+#define RTL8366RB_LED_BLINKRATE_28MS		0x0000
+#define RTL8366RB_LED_BLINKRATE_56MS		0x0001
+#define RTL8366RB_LED_BLINKRATE_84MS		0x0002
+#define RTL8366RB_LED_BLINKRATE_111MS		0x0003
+#define RTL8366RB_LED_BLINKRATE_222MS		0x0004
+#define RTL8366RB_LED_BLINKRATE_446MS		0x0005
+
+/* LED trigger event for each group */
+#define RTL8366RB_LED_CTRL_REG			0x0431
+#define RTL8366RB_LED_CTRL_OFFSET(led_group)	\
+	(4 * (led_group))
+#define RTL8366RB_LED_CTRL_MASK(led_group)	\
+	(0xf << RTL8366RB_LED_CTRL_OFFSET(led_group))
+
+/* The RTL8366RB_LED_X_X registers are used to manually set the LED state only
+ * when the corresponding LED group in RTL8366RB_LED_CTRL_REG is
+ * RTL8366RB_LEDGROUP_FORCE. Otherwise, it is ignored.
+ */
+#define RTL8366RB_LED_0_1_CTRL_REG		0x0432
+#define RTL8366RB_LED_2_3_CTRL_REG		0x0433
+#define RTL8366RB_LED_X_X_CTRL_REG(led_group)	\
+	((led_group) <= 1 ? \
+		RTL8366RB_LED_0_1_CTRL_REG : \
+		RTL8366RB_LED_2_3_CTRL_REG)
+#define RTL8366RB_LED_0_X_CTRL_MASK		GENMASK(5, 0)
+#define RTL8366RB_LED_X_1_CTRL_MASK		GENMASK(11, 6)
+#define RTL8366RB_LED_2_X_CTRL_MASK		GENMASK(5, 0)
+#define RTL8366RB_LED_X_3_CTRL_MASK		GENMASK(11, 6)
+
+enum rtl8366_ledgroup_mode {
+	RTL8366RB_LEDGROUP_OFF			= 0x0,
+	RTL8366RB_LEDGROUP_DUP_COL		= 0x1,
+	RTL8366RB_LEDGROUP_LINK_ACT		= 0x2,
+	RTL8366RB_LEDGROUP_SPD1000		= 0x3,
+	RTL8366RB_LEDGROUP_SPD100		= 0x4,
+	RTL8366RB_LEDGROUP_SPD10		= 0x5,
+	RTL8366RB_LEDGROUP_SPD1000_ACT		= 0x6,
+	RTL8366RB_LEDGROUP_SPD100_ACT		= 0x7,
+	RTL8366RB_LEDGROUP_SPD10_ACT		= 0x8,
+	RTL8366RB_LEDGROUP_SPD100_10_ACT	= 0x9,
+	RTL8366RB_LEDGROUP_FIBER		= 0xa,
+	RTL8366RB_LEDGROUP_AN_FAULT		= 0xb,
+	RTL8366RB_LEDGROUP_LINK_RX		= 0xc,
+	RTL8366RB_LEDGROUP_LINK_TX		= 0xd,
+	RTL8366RB_LEDGROUP_MASTER		= 0xe,
+	RTL8366RB_LEDGROUP_FORCE		= 0xf,
+
+	__RTL8366RB_LEDGROUP_MODE_MAX
+};
+
+#if IS_ENABLED(CONFIG_NET_DSA_REALTEK_RTL8366RB_LEDS)
+
+struct rtl8366rb_led {
+	u8 port_num;
+	u8 led_group;
+	struct realtek_priv *priv;
+	struct led_classdev cdev;
+};
+
+int rtl8366rb_setup_leds(struct realtek_priv *priv);
+
+#else
+
+static inline int rtl8366rb_setup_leds(struct realtek_priv *priv)
+{
+	return 0;
+}
+
+#endif /* IS_ENABLED(CONFIG_LEDS_CLASS) */
+
+/**
+ * struct rtl8366rb - RTL8366RB-specific data
+ * @max_mtu: per-port max MTU setting
+ * @pvid_enabled: if PVID is set for respective port
+ * @leds: per-port and per-ledgroup led info
+ */
+struct rtl8366rb {
+	unsigned int max_mtu[RTL8366RB_NUM_PORTS];
+	bool pvid_enabled[RTL8366RB_NUM_PORTS];
+#if IS_ENABLED(CONFIG_NET_DSA_REALTEK_RTL8366RB_LEDS)
+	struct rtl8366rb_led leds[RTL8366RB_NUM_PORTS][RTL8366RB_NUM_LEDGROUPS];
+#endif
+};
+
+/* This code is used also with LEDs disabled */
+int rb8366rb_set_ledgroup_mode(struct realtek_priv *priv,
+			       u8 led_group,
+			       enum rtl8366_ledgroup_mode mode);
+
+#endif /* _RTL8366RB_H */

From 02cfe2b6529c6c5fcf39d52a826927f4f93392af Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Mon, 24 Feb 2025 11:27:02 +0100
Subject: [PATCH 0529/1173] pidfs: remove d_op->d_delete

Pidfs only deals with unhashed dentries and there's currently no way for
them to become hashed. So remove d_op->d_delete.

Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/pidfs.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/pidfs.c b/fs/pidfs.c
index 63f9699ebac36..c0478b3c55d9f 100644
--- a/fs/pidfs.c
+++ b/fs/pidfs.c
@@ -521,7 +521,6 @@ static char *pidfs_dname(struct dentry *dentry, char *buffer, int buflen)
 }
 
 const struct dentry_operations pidfs_dentry_operations = {
-	.d_delete	= always_delete_dentry,
 	.d_dname	= pidfs_dname,
 	.d_prune	= stashed_dentry_prune,
 };

From 425e3e3bd62c568a4365af0923d6ebad71a7dcfc Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Mon, 24 Feb 2025 11:30:35 +0100
Subject: [PATCH 0530/1173] nsfs: remove d_op->d_delete

Nsfs only deals with unhashed dentries and there's currently no way for
them to become hashed. So remove d_op->d_delete.

Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/nsfs.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/nsfs.c b/fs/nsfs.c
index 663f8656158d5..f7fddf8ecf73f 100644
--- a/fs/nsfs.c
+++ b/fs/nsfs.c
@@ -37,7 +37,6 @@ static char *ns_dname(struct dentry *dentry, char *buffer, int buflen)
 }
 
 const struct dentry_operations ns_dentry_operations = {
-	.d_delete	= always_delete_dentry,
 	.d_dname	= ns_dname,
 	.d_prune	= stashed_dentry_prune,
 };

From 36e1b81f599a093ec7477e4593e110104adcfb96 Mon Sep 17 00:00:00 2001
From: Ken Raeburn <raeburn@redhat.com>
Date: Wed, 19 Feb 2025 17:56:00 -0500
Subject: [PATCH 0531/1173] dm vdo: add missing spin_lock_init

Signed-off-by: Ken Raeburn <raeburn@redhat.com>
Signed-off-by: Matthew Sakai <msakai@redhat.com>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Cc: stable@vger.kernel.org
---
 drivers/md/dm-vdo/dedupe.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/md/dm-vdo/dedupe.c b/drivers/md/dm-vdo/dedupe.c
index b6f8e2dc7729f..3f3d29af1be47 100644
--- a/drivers/md/dm-vdo/dedupe.c
+++ b/drivers/md/dm-vdo/dedupe.c
@@ -2178,6 +2178,7 @@ static int initialize_index(struct vdo *vdo, struct hash_zones *zones)
 
 	vdo_set_dedupe_index_timeout_interval(vdo_dedupe_index_timeout_interval);
 	vdo_set_dedupe_index_min_timer_interval(vdo_dedupe_index_min_timer_interval);
+	spin_lock_init(&zones->lock);
 
 	/*
 	 * Since we will save up the timeouts that would have been reported but were ratelimited,

From 5b0c02f9b8acf2a791e531bbc09acae2d51f4f9b Mon Sep 17 00:00:00 2001
From: Nicolas Frattaroli <nicolas.frattaroli@collabora.com>
Date: Sat, 22 Feb 2025 20:39:57 +0100
Subject: [PATCH 0532/1173] ASoC: es8328: fix route from DAC to output

The ES8328 codec driver, which is also used for the ES8388 chip that
appears to have an identical register map, claims that the output can
either take the route from DAC->Mixer->Output or through DAC->Output
directly. To the best of what I could find, this is not true, and
creates problems.

Without DACCONTROL17 bit index 7 set for the left channel, as well as
DACCONTROL20 bit index 7 set for the right channel, I cannot get any
analog audio out on Left Out 2 and Right Out 2 respectively, despite the
DAPM routes claiming that this should be possible. Furthermore, the same
is the case for Left Out 1 and Right Out 1, showing that those two don't
have a direct route from DAC to output bypassing the mixer either.

Those control bits toggle whether the DACs are fed (stale bread?) into
their respective mixers. If one "unmutes" the mixer controls in
alsamixer, then sure, the audio output works, but if it doesn't work
without the mixer being fed the DAC input then evidently it's not a
direct output from the DAC.

ES8328/ES8388 are seemingly not alone in this. ES8323, which uses a
separate driver for what appears to be a very similar register map,
simply flips those two bits on in its probe function, and then pretends
there is no power management whatsoever for the individual controls.
Fair enough.

My theory as to why nobody has noticed this up to this point is that
everyone just assumes it's their fault when they had to unmute an
additional control in ALSA.

Fix this in the es8328 driver by removing the erroneous direct route,
then get rid of the playback switch controls and have those bits tied to
the mixer's widget instead, which until now had no register to play
with.

Fixes: 567e4f98922c ("ASoC: add es8328 codec driver")
Signed-off-by: Nicolas Frattaroli <nicolas.frattaroli@collabora.com>
Link: https://patch.msgid.link/20250222-es8328-route-bludgeoning-v1-1-99bfb7fb22d9@collabora.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/es8328.c | 15 ++++-----------
 1 file changed, 4 insertions(+), 11 deletions(-)

diff --git a/sound/soc/codecs/es8328.c b/sound/soc/codecs/es8328.c
index f3c97da798dc8..76159c45e6b52 100644
--- a/sound/soc/codecs/es8328.c
+++ b/sound/soc/codecs/es8328.c
@@ -233,7 +233,6 @@ static const struct snd_kcontrol_new es8328_right_line_controls =
 
 /* Left Mixer */
 static const struct snd_kcontrol_new es8328_left_mixer_controls[] = {
-	SOC_DAPM_SINGLE("Playback Switch", ES8328_DACCONTROL17, 7, 1, 0),
 	SOC_DAPM_SINGLE("Left Bypass Switch", ES8328_DACCONTROL17, 6, 1, 0),
 	SOC_DAPM_SINGLE("Right Playback Switch", ES8328_DACCONTROL18, 7, 1, 0),
 	SOC_DAPM_SINGLE("Right Bypass Switch", ES8328_DACCONTROL18, 6, 1, 0),
@@ -243,7 +242,6 @@ static const struct snd_kcontrol_new es8328_left_mixer_controls[] = {
 static const struct snd_kcontrol_new es8328_right_mixer_controls[] = {
 	SOC_DAPM_SINGLE("Left Playback Switch", ES8328_DACCONTROL19, 7, 1, 0),
 	SOC_DAPM_SINGLE("Left Bypass Switch", ES8328_DACCONTROL19, 6, 1, 0),
-	SOC_DAPM_SINGLE("Playback Switch", ES8328_DACCONTROL20, 7, 1, 0),
 	SOC_DAPM_SINGLE("Right Bypass Switch", ES8328_DACCONTROL20, 6, 1, 0),
 };
 
@@ -336,10 +334,10 @@ static const struct snd_soc_dapm_widget es8328_dapm_widgets[] = {
 	SND_SOC_DAPM_DAC("Left DAC", "Left Playback", ES8328_DACPOWER,
 			ES8328_DACPOWER_LDAC_OFF, 1),
 
-	SND_SOC_DAPM_MIXER("Left Mixer", SND_SOC_NOPM, 0, 0,
+	SND_SOC_DAPM_MIXER("Left Mixer", ES8328_DACCONTROL17, 7, 0,
 		&es8328_left_mixer_controls[0],
 		ARRAY_SIZE(es8328_left_mixer_controls)),
-	SND_SOC_DAPM_MIXER("Right Mixer", SND_SOC_NOPM, 0, 0,
+	SND_SOC_DAPM_MIXER("Right Mixer", ES8328_DACCONTROL20, 7, 0,
 		&es8328_right_mixer_controls[0],
 		ARRAY_SIZE(es8328_right_mixer_controls)),
 
@@ -418,19 +416,14 @@ static const struct snd_soc_dapm_route es8328_dapm_routes[] = {
 	{ "Right Line Mux", "PGA", "Right PGA Mux" },
 	{ "Right Line Mux", "Differential", "Differential Mux" },
 
-	{ "Left Out 1", NULL, "Left DAC" },
-	{ "Right Out 1", NULL, "Right DAC" },
-	{ "Left Out 2", NULL, "Left DAC" },
-	{ "Right Out 2", NULL, "Right DAC" },
-
-	{ "Left Mixer", "Playback Switch", "Left DAC" },
+	{ "Left Mixer", NULL, "Left DAC" },
 	{ "Left Mixer", "Left Bypass Switch", "Left Line Mux" },
 	{ "Left Mixer", "Right Playback Switch", "Right DAC" },
 	{ "Left Mixer", "Right Bypass Switch", "Right Line Mux" },
 
 	{ "Right Mixer", "Left Playback Switch", "Left DAC" },
 	{ "Right Mixer", "Left Bypass Switch", "Left Line Mux" },
-	{ "Right Mixer", "Playback Switch", "Right DAC" },
+	{ "Right Mixer", NULL, "Right DAC" },
 	{ "Right Mixer", "Right Bypass Switch", "Right Line Mux" },
 
 	{ "DAC DIG", NULL, "DAC STM" },

From 0fe8813baf4b2e865d3b2c735ce1a15b86002c74 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 17 Jan 2025 06:41:07 -0800
Subject: [PATCH 0533/1173] perf/core: Add RCU read lock protection to
 perf_iterate_ctx()

The perf_iterate_ctx() function performs RCU list traversal but
currently lacks RCU read lock protection. This causes lockdep warnings
when running perf probe with unshare(1) under CONFIG_PROVE_RCU_LIST=y:

	WARNING: suspicious RCU usage
	kernel/events/core.c:8168 RCU-list traversed in non-reader section!!

	 Call Trace:
	  lockdep_rcu_suspicious
	  ? perf_event_addr_filters_apply
	  perf_iterate_ctx
	  perf_event_exec
	  begin_new_exec
	  ? load_elf_phdrs
	  load_elf_binary
	  ? lock_acquire
	  ? find_held_lock
	  ? bprm_execve
	  bprm_execve
	  do_execveat_common.isra.0
	  __x64_sys_execve
	  do_syscall_64
	  entry_SYSCALL_64_after_hwframe

This protection was previously present but was removed in commit
bd2756811766 ("perf: Rewrite core context handling"). Add back the
necessary rcu_read_lock()/rcu_read_unlock() pair around
perf_iterate_ctx() call in perf_event_exec().

[ mingo: Use scoped_guard() as suggested by Peter ]

Fixes: bd2756811766 ("perf: Rewrite core context handling")
Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250117-fix_perf_rcu-v1-1-13cb9210fc6a@debian.org
---
 kernel/events/core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index bcb09e011e9e1..7dabbcaf825a0 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8321,7 +8321,8 @@ void perf_event_exec(void)
 
 	perf_event_enable_on_exec(ctx);
 	perf_event_remove_on_exec(ctx);
-	perf_iterate_ctx(ctx, perf_event_addr_filters_exec, NULL, true);
+	scoped_guard(rcu)
+		perf_iterate_ctx(ctx, perf_event_addr_filters_exec, NULL, true);
 
 	perf_unpin_context(ctx);
 	put_ctx(ctx);

From 2016066c66192a99d9e0ebf433789c490a6785a2 Mon Sep 17 00:00:00 2001
From: Luo Gengkun <luogengkun@huaweicloud.com>
Date: Wed, 22 Jan 2025 07:33:56 +0000
Subject: [PATCH 0534/1173] perf/core: Order the PMU list to fix warning about
 unordered pmu_ctx_list

Syskaller triggers a warning due to prev_epc->pmu != next_epc->pmu in
perf_event_swap_task_ctx_data(). vmcore shows that two lists have the same
perf_event_pmu_context, but not in the same order.

The problem is that the order of pmu_ctx_list for the parent is impacted by
the time when an event/PMU is added. While the order for a child is
impacted by the event order in the pinned_groups and flexible_groups. So
the order of pmu_ctx_list in the parent and child may be different.

To fix this problem, insert the perf_event_pmu_context to its proper place
after iteration of the pmu_ctx_list.

The follow testcase can trigger above warning:

 # perf record -e cycles --call-graph lbr -- taskset -c 3 ./a.out &
 # perf stat -e cpu-clock,cs -p xxx // xxx is the pid of a.out

 test.c

 void main() {
        int count = 0;
        pid_t pid;

        printf("%d running\n", getpid());
        sleep(30);
        printf("running\n");

        pid = fork();
        if (pid == -1) {
                printf("fork error\n");
                return;
        }
        if (pid == 0) {
                while (1) {
                        count++;
                }
        } else {
                while (1) {
                        count++;
                }
        }
 }

The testcase first opens an LBR event, so it will allocate task_ctx_data,
and then open tracepoint and software events, so the parent context will
have 3 different perf_event_pmu_contexts. On inheritance, child ctx will
insert the perf_event_pmu_context in another order and the warning will
trigger.

[ mingo: Tidied up the changelog. ]

Fixes: bd2756811766 ("perf: Rewrite core context handling")
Signed-off-by: Luo Gengkun <luogengkun@huaweicloud.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Link: https://lore.kernel.org/r/20250122073356.1824736-1-luogengkun@huaweicloud.com
---
 kernel/events/core.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 7dabbcaf825a0..086d46d096963 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4950,7 +4950,7 @@ static struct perf_event_pmu_context *
 find_get_pmu_context(struct pmu *pmu, struct perf_event_context *ctx,
 		     struct perf_event *event)
 {
-	struct perf_event_pmu_context *new = NULL, *epc;
+	struct perf_event_pmu_context *new = NULL, *pos = NULL, *epc;
 	void *task_ctx_data = NULL;
 
 	if (!ctx->task) {
@@ -5007,12 +5007,19 @@ find_get_pmu_context(struct pmu *pmu, struct perf_event_context *ctx,
 			atomic_inc(&epc->refcount);
 			goto found_epc;
 		}
+		/* Make sure the pmu_ctx_list is sorted by PMU type: */
+		if (!pos && epc->pmu->type > pmu->type)
+			pos = epc;
 	}
 
 	epc = new;
 	new = NULL;
 
-	list_add(&epc->pmu_ctx_entry, &ctx->pmu_ctx_list);
+	if (!pos)
+		list_add_tail(&epc->pmu_ctx_entry, &ctx->pmu_ctx_list);
+	else
+		list_add(&epc->pmu_ctx_entry, pos->pmu_ctx_entry.prev);
+
 	epc->ctx = ctx;
 
 found_epc:

From 0da83ab025bc45e9742e87c2cce19bff423377c8 Mon Sep 17 00:00:00 2001
From: Chancel Liu <chancel.liu@nxp.com>
Date: Mon, 17 Feb 2025 10:04:37 +0900
Subject: [PATCH 0535/1173] ASoC: fsl: Rename stream name of SAI DAI driver

If stream names of DAI driver are duplicated there'll be warnings when
machine driver tries to add widgets on a route:

[    8.831335] fsl-asoc-card sound-wm8960: ASoC: sink widget CPU-Playback overwritten
[    8.839917] fsl-asoc-card sound-wm8960: ASoC: source widget CPU-Capture overwritten

Use different stream names to avoid such warnings.
DAI names in AUDMIX are also updated accordingly.

Fixes: 15c958390460 ("ASoC: fsl_sai: Add separate DAI for transmitter and receiver")
Signed-off-by: Chancel Liu <chancel.liu@nxp.com>
Acked-by: Shengjiu Wang <shengjiu.wang@gmail.com>
Link: https://patch.msgid.link/20250217010437.258621-1-chancel.liu@nxp.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/fsl/fsl_sai.c    | 6 +++---
 sound/soc/fsl/imx-audmix.c | 4 ++--
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c
index c4eb87c5d39e4..9f33dd11d47f6 100644
--- a/sound/soc/fsl/fsl_sai.c
+++ b/sound/soc/fsl/fsl_sai.c
@@ -994,10 +994,10 @@ static struct snd_soc_dai_driver fsl_sai_dai_template[] = {
 	{
 		.name = "sai-tx",
 		.playback = {
-			.stream_name = "CPU-Playback",
+			.stream_name = "SAI-Playback",
 			.channels_min = 1,
 			.channels_max = 32,
-				.rate_min = 8000,
+			.rate_min = 8000,
 			.rate_max = 2822400,
 			.rates = SNDRV_PCM_RATE_KNOT,
 			.formats = FSL_SAI_FORMATS,
@@ -1007,7 +1007,7 @@ static struct snd_soc_dai_driver fsl_sai_dai_template[] = {
 	{
 		.name = "sai-rx",
 		.capture = {
-			.stream_name = "CPU-Capture",
+			.stream_name = "SAI-Capture",
 			.channels_min = 1,
 			.channels_max = 32,
 			.rate_min = 8000,
diff --git a/sound/soc/fsl/imx-audmix.c b/sound/soc/fsl/imx-audmix.c
index 50ecc5f51100e..dac5d4ddacd6e 100644
--- a/sound/soc/fsl/imx-audmix.c
+++ b/sound/soc/fsl/imx-audmix.c
@@ -119,8 +119,8 @@ static const struct snd_soc_ops imx_audmix_be_ops = {
 static const char *name[][3] = {
 	{"HiFi-AUDMIX-FE-0", "HiFi-AUDMIX-FE-1", "HiFi-AUDMIX-FE-2"},
 	{"sai-tx", "sai-tx", "sai-rx"},
-	{"AUDMIX-Playback-0", "AUDMIX-Playback-1", "CPU-Capture"},
-	{"CPU-Playback", "CPU-Playback", "AUDMIX-Capture-0"},
+	{"AUDMIX-Playback-0", "AUDMIX-Playback-1", "SAI-Capture"},
+	{"SAI-Playback", "SAI-Playback", "AUDMIX-Capture-0"},
 };
 
 static int imx_audmix_probe(struct platform_device *pdev)

From d31babd7e304d3b800d36ff74be6739405b985f2 Mon Sep 17 00:00:00 2001
From: Nicolas Frattaroli <nicolas.frattaroli@collabora.com>
Date: Fri, 21 Feb 2025 21:39:32 +0100
Subject: [PATCH 0536/1173] ASoC: dapm-graph: set fill colour of turned on
 nodes

Some tools like KGraphViewer interpret the "ON" nodes not having an
explicitly set fill colour as them being entirely black, which obscures
the text on them and looks funny. In fact, I thought they were off for
the longest time. Comparing to the output of the `dot` tool, I assume
they are supposed to be white.

Instead of speclawyering over who's in the wrong and must immediately
atone for their wickedness at the altar of RFC2119, just be explicit
about it, set the fillcolor to white, and nobody gets confused.

Signed-off-by: Nicolas Frattaroli <nicolas.frattaroli@collabora.com>
Tested-by: Luca Ceresoli <luca.ceresoli@bootlin.com>
Reviewed-by: Luca Ceresoli <luca.ceresoli@bootlin.com>
Link: https://patch.msgid.link/20250221-dapm-graph-node-colour-v1-1-514ed0aa7069@collabora.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 tools/sound/dapm-graph | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/sound/dapm-graph b/tools/sound/dapm-graph
index f14bdfedee8f1..b6196ee5065a4 100755
--- a/tools/sound/dapm-graph
+++ b/tools/sound/dapm-graph
@@ -10,7 +10,7 @@ set -eu
 
 STYLE_COMPONENT_ON="color=dodgerblue;style=bold"
 STYLE_COMPONENT_OFF="color=gray40;style=filled;fillcolor=gray90"
-STYLE_NODE_ON="shape=box,style=bold,color=green4"
+STYLE_NODE_ON="shape=box,style=bold,color=green4,fillcolor=white"
 STYLE_NODE_OFF="shape=box,style=filled,color=gray30,fillcolor=gray95"
 
 # Print usage and exit

From 39ec9eaaa165d297d008d1fa385748430bd18e4d Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Wed, 19 Feb 2025 11:53:16 -0800
Subject: [PATCH 0537/1173] coredump: Only sort VMAs when core_sort_vma sysctl
 is set

The sorting of VMAs by size in commit 7d442a33bfe8 ("binfmt_elf: Dump
smaller VMAs first in ELF cores") breaks elfutils[1]. Instead, sort
based on the setting of the new sysctl, core_sort_vma, which defaults
to 0, no sorting.

Reported-by: Michael Stapelberg <michael@stapelberg.ch>
Closes: https://lore.kernel.org/all/20250218085407.61126-1-michael@stapelberg.de/ [1]
Fixes: 7d442a33bfe8 ("binfmt_elf: Dump smaller VMAs first in ELF cores")
Signed-off-by: Kees Cook <kees@kernel.org>
---
 Documentation/admin-guide/sysctl/kernel.rst | 11 +++++++++++
 fs/coredump.c                               | 15 +++++++++++++--
 2 files changed, 24 insertions(+), 2 deletions(-)

diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst
index a43b78b4b6464..dd49a89a62d35 100644
--- a/Documentation/admin-guide/sysctl/kernel.rst
+++ b/Documentation/admin-guide/sysctl/kernel.rst
@@ -212,6 +212,17 @@ pid>/``).
 This value defaults to 0.
 
 
+core_sort_vma
+=============
+
+The default coredump writes VMAs in address order. By setting
+``core_sort_vma`` to 1, VMAs will be written from smallest size
+to largest size. This is known to break at least elfutils, but
+can be handy when dealing with very large (and truncated)
+coredumps where the more useful debugging details are included
+in the smaller VMAs.
+
+
 core_uses_pid
 =============
 
diff --git a/fs/coredump.c b/fs/coredump.c
index 591700e1b2ce6..4375c70144d0a 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -63,6 +63,7 @@ static void free_vma_snapshot(struct coredump_params *cprm);
 
 static int core_uses_pid;
 static unsigned int core_pipe_limit;
+static unsigned int core_sort_vma;
 static char core_pattern[CORENAME_MAX_SIZE] = "core";
 static int core_name_size = CORENAME_MAX_SIZE;
 unsigned int core_file_note_size_limit = CORE_FILE_NOTE_SIZE_DEFAULT;
@@ -1026,6 +1027,15 @@ static const struct ctl_table coredump_sysctls[] = {
 		.extra1		= (unsigned int *)&core_file_note_size_min,
 		.extra2		= (unsigned int *)&core_file_note_size_max,
 	},
+	{
+		.procname	= "core_sort_vma",
+		.data		= &core_sort_vma,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_douintvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
 };
 
 static int __init init_fs_coredump_sysctls(void)
@@ -1256,8 +1266,9 @@ static bool dump_vma_snapshot(struct coredump_params *cprm)
 		cprm->vma_data_size += m->dump_size;
 	}
 
-	sort(cprm->vma_meta, cprm->vma_count, sizeof(*cprm->vma_meta),
-		cmp_vma_size, NULL);
+	if (core_sort_vma)
+		sort(cprm->vma_meta, cprm->vma_count, sizeof(*cprm->vma_meta),
+		     cmp_vma_size, NULL);
 
 	return true;
 }

From bddf10d26e6e5114e7415a0e442ec6f51a559468 Mon Sep 17 00:00:00 2001
From: Tong Tiangen <tongtiangen@huawei.com>
Date: Mon, 24 Feb 2025 11:11:49 +0800
Subject: [PATCH 0538/1173] uprobes: Reject the shared zeropage in
 uprobe_write_opcode()

We triggered the following crash in syzkaller tests:

  BUG: Bad page state in process syz.7.38  pfn:1eff3
  page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x1eff3
  flags: 0x3fffff00004004(referenced|reserved|node=0|zone=1|lastcpupid=0x1fffff)
  raw: 003fffff00004004 ffffe6c6c07bfcc8 ffffe6c6c07bfcc8 0000000000000000
  raw: 0000000000000000 0000000000000000 00000000fffffffe 0000000000000000
  page dumped because: PAGE_FLAGS_CHECK_AT_FREE flag(s) set
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014
  Call Trace:
   <TASK>
   dump_stack_lvl+0x32/0x50
   bad_page+0x69/0xf0
   free_unref_page_prepare+0x401/0x500
   free_unref_page+0x6d/0x1b0
   uprobe_write_opcode+0x460/0x8e0
   install_breakpoint.part.0+0x51/0x80
   register_for_each_vma+0x1d9/0x2b0
   __uprobe_register+0x245/0x300
   bpf_uprobe_multi_link_attach+0x29b/0x4f0
   link_create+0x1e2/0x280
   __sys_bpf+0x75f/0xac0
   __x64_sys_bpf+0x1a/0x30
   do_syscall_64+0x56/0x100
   entry_SYSCALL_64_after_hwframe+0x78/0xe2

   BUG: Bad rss-counter state mm:00000000452453e0 type:MM_FILEPAGES val:-1

The following syzkaller test case can be used to reproduce:

  r2 = creat(&(0x7f0000000000)='./file0\x00', 0x8)
  write$nbd(r2, &(0x7f0000000580)=ANY=[], 0x10)
  r4 = openat(0xffffffffffffff9c, &(0x7f0000000040)='./file0\x00', 0x42, 0x0)
  mmap$IORING_OFF_SQ_RING(&(0x7f0000ffd000/0x3000)=nil, 0x3000, 0x0, 0x12, r4, 0x0)
  r5 = userfaultfd(0x80801)
  ioctl$UFFDIO_API(r5, 0xc018aa3f, &(0x7f0000000040)={0xaa, 0x20})
  r6 = userfaultfd(0x80801)
  ioctl$UFFDIO_API(r6, 0xc018aa3f, &(0x7f0000000140))
  ioctl$UFFDIO_REGISTER(r6, 0xc020aa00, &(0x7f0000000100)={{&(0x7f0000ffc000/0x4000)=nil, 0x4000}, 0x2})
  ioctl$UFFDIO_ZEROPAGE(r5, 0xc020aa04, &(0x7f0000000000)={{&(0x7f0000ffd000/0x1000)=nil, 0x1000}})
  r7 = bpf$PROG_LOAD(0x5, &(0x7f0000000140)={0x2, 0x3, &(0x7f0000000200)=ANY=[@ANYBLOB="1800000000120000000000000000000095"], &(0x7f0000000000)='GPL\x00', 0x7, 0x0, 0x0, 0x0, 0x0, '\x00', 0x0, @fallback=0x30, 0xffffffffffffffff, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x10, 0x0, @void, @value}, 0x94)
  bpf$BPF_LINK_CREATE_XDP(0x1c, &(0x7f0000000040)={r7, 0x0, 0x30, 0x1e, @val=@uprobe_multi={&(0x7f0000000080)='./file0\x00', &(0x7f0000000100)=[0x2], 0x0, 0x0, 0x1}}, 0x40)

The cause is that zero pfn is set to the PTE without increasing the RSS
count in mfill_atomic_pte_zeropage() and the refcount of zero folio does
not increase accordingly. Then, the operation on the same pfn is performed
in uprobe_write_opcode()->__replace_page() to unconditional decrease the
RSS count and old_folio's refcount.

Therefore, two bugs are introduced:

 1. The RSS count is incorrect, when process exit, the check_mm() report
    error "Bad rss-count".

 2. The reserved folio (zero folio) is freed when folio->refcount is zero,
    then free_pages_prepare->free_page_is_bad() report error
    "Bad page state".

There is more, the following warning could also theoretically be triggered:

  __replace_page()
    -> ...
      -> folio_remove_rmap_pte()
        -> VM_WARN_ON_FOLIO(is_zero_folio(folio), folio)

Considering that uprobe hit on the zero folio is a very rare case, just
reject zero old folio immediately after get_user_page_vma_remote().

[ mingo: Cleaned up the changelog ]

Fixes: 7396fa818d62 ("uprobes/core: Make background page replacement logic account for rss_stat counters")
Fixes: 2b1444983508 ("uprobes, mm, x86: Add the ability to install and remove uprobes breakpoints")
Signed-off-by: Tong Tiangen <tongtiangen@huawei.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Link: https://lore.kernel.org/r/20250224031149.1598949-1-tongtiangen@huawei.com
---
 kernel/events/uprobes.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index bf2a87a0a3787..af53fbd2d12c4 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -495,6 +495,11 @@ int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
 	if (ret <= 0)
 		goto put_old;
 
+	if (is_zero_page(old_page)) {
+		ret = -EINVAL;
+		goto put_old;
+	}
+
 	if (WARN(!is_register && PageCompound(old_page),
 		 "uprobe unregister should never work on compound page\n")) {
 		ret = -EINVAL;

From d40459cc157f8ed8d28434c761ca7010630351be Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Mon, 24 Feb 2025 08:16:34 +0100
Subject: [PATCH 0539/1173] x86/percpu: Unify __pcpu_op{1,2}_N() macros to
 __pcpu_op_N()

Unify __pcpu_op1_N() and __pcpu_op2_N() macros to __pcpu_op_N()
by applying the macro only to asm mnemonic, not to the mnemonic
plus its arguments.

No functional change intended.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250224071648.15913-1-ubizjak@gmail.com
---
 arch/x86/include/asm/percpu.h | 38 +++++++++++++++++------------------
 1 file changed, 18 insertions(+), 20 deletions(-)

diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 1a76eb87c5d86..c2a9dfce36a57 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -106,15 +106,10 @@
 #define __pcpu_cast_4(val)	((u32)(((unsigned long) val) & 0xffffffff))
 #define __pcpu_cast_8(val)	((u64)(val))
 
-#define __pcpu_op1_1(op, dst)	op "b " dst
-#define __pcpu_op1_2(op, dst)	op "w " dst
-#define __pcpu_op1_4(op, dst)	op "l " dst
-#define __pcpu_op1_8(op, dst)	op "q " dst
-
-#define __pcpu_op2_1(op, src, dst) op "b " src ", " dst
-#define __pcpu_op2_2(op, src, dst) op "w " src ", " dst
-#define __pcpu_op2_4(op, src, dst) op "l " src ", " dst
-#define __pcpu_op2_8(op, src, dst) op "q " src ", " dst
+#define __pcpu_op_1(op)		op "b "
+#define __pcpu_op_2(op)		op "w "
+#define __pcpu_op_4(op)		op "l "
+#define __pcpu_op_8(op)		op "q "
 
 #define __pcpu_reg_1(mod, x)	mod "q" (x)
 #define __pcpu_reg_2(mod, x)	mod "r" (x)
@@ -146,7 +141,8 @@ do {									\
 ({									\
 	__pcpu_type_##size pfo_val__;					\
 									\
-	asm qual (__pcpu_op2_##size("mov", __percpu_arg([var]), "%[val]") \
+	asm qual (__pcpu_op_##size("mov")				\
+		  __percpu_arg([var]) ", %[val]"			\
 	    : [val] __pcpu_reg_##size("=", pfo_val__)			\
 	    : [var] "m" (__my_cpu_var(_var)));				\
 									\
@@ -162,7 +158,8 @@ do {									\
 		pto_tmp__ = (_val);					\
 		(void)pto_tmp__;					\
 	}								\
-	asm qual(__pcpu_op2_##size("mov", "%[val]", __percpu_arg([var])) \
+	asm qual (__pcpu_op_##size("mov") "%[val], "			\
+		  __percpu_arg([var])					\
 	    : [var] "=m" (__my_cpu_var(_var))				\
 	    : [val] __pcpu_reg_imm_##size(pto_val__));			\
 } while (0)
@@ -179,7 +176,8 @@ do {									\
 ({									\
 	__pcpu_type_##size pfo_val__;					\
 									\
-	asm(__pcpu_op2_##size("mov", __force_percpu_arg(a[var]), "%[val]") \
+	asm(__pcpu_op_##size("mov")					\
+	    __force_percpu_arg(a[var]) ", %[val]"			\
 	    : [val] __pcpu_reg_##size("=", pfo_val__)			\
 	    : [var] "i" (&(_var)));					\
 									\
@@ -188,7 +186,7 @@ do {									\
 
 #define percpu_unary_op(size, qual, op, _var)				\
 ({									\
-	asm qual (__pcpu_op1_##size(op, __percpu_arg([var]))		\
+	asm qual (__pcpu_op_##size(op) __percpu_arg([var])		\
 	    : [var] "+m" (__my_cpu_var(_var)));				\
 })
 
@@ -201,7 +199,7 @@ do {									\
 		pto_tmp__ = (_val);					\
 		(void)pto_tmp__;					\
 	}								\
-	asm qual(__pcpu_op2_##size(op, "%[val]", __percpu_arg([var]))	\
+	asm qual (__pcpu_op_##size(op) "%[val], " __percpu_arg([var])	\
 	    : [var] "+m" (__my_cpu_var(_var))				\
 	    : [val] __pcpu_reg_imm_##size(pto_val__));			\
 } while (0)
@@ -237,8 +235,8 @@ do {									\
 ({									\
 	__pcpu_type_##size paro_tmp__ = __pcpu_cast_##size(_val);	\
 									\
-	asm qual (__pcpu_op2_##size("xadd", "%[tmp]",			\
-				     __percpu_arg([var]))		\
+	asm qual (__pcpu_op_##size("xadd") "%[tmp], "			\
+		  __percpu_arg([var])					\
 		  : [tmp] __pcpu_reg_##size("+", paro_tmp__),		\
 		    [var] "+m" (__my_cpu_var(_var))			\
 		  : : "memory");					\
@@ -281,8 +279,8 @@ do {									\
 	__pcpu_type_##size pco_old__ = __pcpu_cast_##size(_oval);	\
 	__pcpu_type_##size pco_new__ = __pcpu_cast_##size(_nval);	\
 									\
-	asm qual (__pcpu_op2_##size("cmpxchg", "%[nval]",		\
-				    __percpu_arg([var]))		\
+	asm qual (__pcpu_op_##size("cmpxchg") "%[nval], "		\
+		  __percpu_arg([var])					\
 		  : [oval] "+a" (pco_old__),				\
 		    [var] "+m" (__my_cpu_var(_var))			\
 		  : [nval] __pcpu_reg_##size(, pco_new__)		\
@@ -298,8 +296,8 @@ do {									\
 	__pcpu_type_##size pco_old__ = *pco_oval__;			\
 	__pcpu_type_##size pco_new__ = __pcpu_cast_##size(_nval);	\
 									\
-	asm qual (__pcpu_op2_##size("cmpxchg", "%[nval]",		\
-				    __percpu_arg([var]))		\
+	asm qual (__pcpu_op_##size("cmpxchg") "%[nval], "		\
+		  __percpu_arg([var])					\
 		  CC_SET(z)						\
 		  : CC_OUT(z) (success),				\
 		    [oval] "+a" (pco_old__),				\

From 815291c11acda54515f1af5ce6fe307490de9127 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 24 Feb 2025 08:28:59 -0800
Subject: [PATCH 0540/1173] configfs: update MAINTAINERS

Joel will go back to maintain configfs alone on a time permitting basis.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Joel Becker <jlbec@evilplan.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 4ff26fa94895d..089c1178f25a5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5856,7 +5856,6 @@ F:	Documentation/security/snp-tdx-threat-model.rst
 
 CONFIGFS
 M:	Joel Becker <jlbec@evilplan.org>
-M:	Christoph Hellwig <hch@lst.de>
 S:	Supported
 T:	git git://git.infradead.org/users/hch/configfs.git
 F:	fs/configfs/

From f7d5db965f3e132887779c6b449452db2b807caa Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 24 Feb 2025 08:27:21 -0800
Subject: [PATCH 0541/1173] dma-mapping: update MAINTAINERS

Marek has graciously offered to maintain the dma-mapping tree.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 089c1178f25a5..a78eaaa24a699 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6878,7 +6878,6 @@ F:	kernel/dma/map_benchmark.c
 F:	tools/testing/selftests/dma/
 
 DMA MAPPING HELPERS
-M:	Christoph Hellwig <hch@lst.de>
 M:	Marek Szyprowski <m.szyprowski@samsung.com>
 R:	Robin Murphy <robin.murphy@arm.com>
 L:	iommu@lists.linux.dev

From e043dc16c28c8446e66c55adfe7c6e862a6a7bb7 Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Fri, 21 Feb 2025 14:38:41 +0000
Subject: [PATCH 0542/1173] drm/xe/userptr: restore invalidation list on error
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On error restore anything still on the pin_list back to the invalidation
list on error. For the actual pin, so long as the vma is tracked on
either list it should get picked up on the next pin, however it looks
possible for the vma to get nuked but still be present on this per vm
pin_list leading to corruption. An alternative might be then to instead
just remove the link when destroying the vma.

v2:
 - Also add some asserts.
 - Keep the overzealous locking so that we are consistent with the docs;
   updating the docs and related bits will be done as a follow up.

Fixes: ed2bdf3b264d ("drm/xe/vm: Subclass userptr vmas")
Suggested-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: <stable@vger.kernel.org> # v6.8+
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250221143840.167150-4-matthew.auld@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit 4e37e928928b730de9aa9a2f5dc853feeebc1742)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_vm.c | 28 +++++++++++++++++++++-------
 1 file changed, 21 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 690330352d4cd..47f7d8f2094b6 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -666,15 +666,16 @@ int xe_vm_userptr_pin(struct xe_vm *vm)
 
 	/* Collect invalidated userptrs */
 	spin_lock(&vm->userptr.invalidated_lock);
+	xe_assert(vm->xe, list_empty(&vm->userptr.repin_list));
 	list_for_each_entry_safe(uvma, next, &vm->userptr.invalidated,
 				 userptr.invalidate_link) {
 		list_del_init(&uvma->userptr.invalidate_link);
-		list_move_tail(&uvma->userptr.repin_link,
-			       &vm->userptr.repin_list);
+		list_add_tail(&uvma->userptr.repin_link,
+			      &vm->userptr.repin_list);
 	}
 	spin_unlock(&vm->userptr.invalidated_lock);
 
-	/* Pin and move to temporary list */
+	/* Pin and move to bind list */
 	list_for_each_entry_safe(uvma, next, &vm->userptr.repin_list,
 				 userptr.repin_link) {
 		err = xe_vma_userptr_pin_pages(uvma);
@@ -690,10 +691,10 @@ int xe_vm_userptr_pin(struct xe_vm *vm)
 			err = xe_vm_invalidate_vma(&uvma->vma);
 			xe_vm_unlock(vm);
 			if (err)
-				return err;
+				break;
 		} else {
-			if (err < 0)
-				return err;
+			if (err)
+				break;
 
 			list_del_init(&uvma->userptr.repin_link);
 			list_move_tail(&uvma->vma.combined_links.rebind,
@@ -701,7 +702,19 @@ int xe_vm_userptr_pin(struct xe_vm *vm)
 		}
 	}
 
-	return 0;
+	if (err) {
+		down_write(&vm->userptr.notifier_lock);
+		spin_lock(&vm->userptr.invalidated_lock);
+		list_for_each_entry_safe(uvma, next, &vm->userptr.repin_list,
+					 userptr.repin_link) {
+			list_del_init(&uvma->userptr.repin_link);
+			list_move_tail(&uvma->userptr.invalidate_link,
+				       &vm->userptr.invalidated);
+		}
+		spin_unlock(&vm->userptr.invalidated_lock);
+		up_write(&vm->userptr.notifier_lock);
+	}
+	return err;
 }
 
 /**
@@ -1066,6 +1079,7 @@ static void xe_vma_destroy(struct xe_vma *vma, struct dma_fence *fence)
 		xe_assert(vm->xe, vma->gpuva.flags & XE_VMA_DESTROYED);
 
 		spin_lock(&vm->userptr.invalidated_lock);
+		xe_assert(vm->xe, list_empty(&to_userptr_vma(vma)->userptr.repin_link));
 		list_del(&to_userptr_vma(vma)->userptr.invalidate_link);
 		spin_unlock(&vm->userptr.invalidated_lock);
 	} else if (!xe_vma_is_null(vma)) {

From a9f4fa3a7efa65615ff7db13023ac84516e99e21 Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Fri, 21 Feb 2025 14:38:42 +0000
Subject: [PATCH 0543/1173] drm/xe/userptr: fix EFAULT handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently we treat EFAULT from hmm_range_fault() as a non-fatal error
when called from xe_vm_userptr_pin() with the idea that we want to avoid
killing the entire vm and chucking an error, under the assumption that
the user just did an unmap or something, and has no intention of
actually touching that memory from the GPU.  At this point we have
already zapped the PTEs so any access should generate a page fault, and
if the pin fails there also it will then become fatal.

However it looks like it's possible for the userptr vma to still be on
the rebind list in preempt_rebind_work_func(), if we had to retry the
pin again due to something happening in the caller before we did the
rebind step, but in the meantime needing to re-validate the userptr and
this time hitting the EFAULT.

This explains an internal user report of hitting:

[  191.738349] WARNING: CPU: 1 PID: 157 at drivers/gpu/drm/xe/xe_res_cursor.h:158 xe_pt_stage_bind.constprop.0+0x60a/0x6b0 [xe]
[  191.738551] Workqueue: xe-ordered-wq preempt_rebind_work_func [xe]
[  191.738616] RIP: 0010:xe_pt_stage_bind.constprop.0+0x60a/0x6b0 [xe]
[  191.738690] Call Trace:
[  191.738692]  <TASK>
[  191.738694]  ? show_regs+0x69/0x80
[  191.738698]  ? __warn+0x93/0x1a0
[  191.738703]  ? xe_pt_stage_bind.constprop.0+0x60a/0x6b0 [xe]
[  191.738759]  ? report_bug+0x18f/0x1a0
[  191.738764]  ? handle_bug+0x63/0xa0
[  191.738767]  ? exc_invalid_op+0x19/0x70
[  191.738770]  ? asm_exc_invalid_op+0x1b/0x20
[  191.738777]  ? xe_pt_stage_bind.constprop.0+0x60a/0x6b0 [xe]
[  191.738834]  ? ret_from_fork_asm+0x1a/0x30
[  191.738849]  bind_op_prepare+0x105/0x7b0 [xe]
[  191.738906]  ? dma_resv_reserve_fences+0x301/0x380
[  191.738912]  xe_pt_update_ops_prepare+0x28c/0x4b0 [xe]
[  191.738966]  ? kmemleak_alloc+0x4b/0x80
[  191.738973]  ops_execute+0x188/0x9d0 [xe]
[  191.739036]  xe_vm_rebind+0x4ce/0x5a0 [xe]
[  191.739098]  ? trace_hardirqs_on+0x4d/0x60
[  191.739112]  preempt_rebind_work_func+0x76f/0xd00 [xe]

Followed by NPD, when running some workload, since the sg was never
actually populated but the vma is still marked for rebind when it should
be skipped for this special EFAULT case. This is confirmed to fix the
user report.

v2 (MattB):
 - Move earlier.
v3 (MattB):
 - Update the commit message to make it clear that this indeed fixes the
   issue.

Fixes: 521db22a1d70 ("drm/xe: Invalidate userptr VMA on page pin fault")
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: <stable@vger.kernel.org> # v6.10+
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250221143840.167150-5-matthew.auld@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit 6b93cb98910c826c2e2004942f8b060311e43618)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_vm.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 47f7d8f2094b6..30259eba450b5 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -681,6 +681,18 @@ int xe_vm_userptr_pin(struct xe_vm *vm)
 		err = xe_vma_userptr_pin_pages(uvma);
 		if (err == -EFAULT) {
 			list_del_init(&uvma->userptr.repin_link);
+			/*
+			 * We might have already done the pin once already, but
+			 * then had to retry before the re-bind happened, due
+			 * some other condition in the caller, but in the
+			 * meantime the userptr got dinged by the notifier such
+			 * that we need to revalidate here, but this time we hit
+			 * the EFAULT. In such a case make sure we remove
+			 * ourselves from the rebind list to avoid going down in
+			 * flames.
+			 */
+			if (!list_empty(&uvma->vma.combined_links.rebind))
+				list_del_init(&uvma->vma.combined_links.rebind);
 
 			/* Wait for pending binds */
 			xe_vm_lock(vm, false);

From db10fde5c4f96231e1d2bbfd01feb5f2f59b96d1 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 20 Feb 2025 18:51:40 -0800
Subject: [PATCH 0544/1173] net: ethtool: fix ioctl confusing drivers about
 desired HDS user config

The legacy ioctl path does not have support for extended attributes.
So we issue a GET to fetch the current settings from the driver,
in an attempt to keep them unchanged. HDS is a bit "special" as
the GET only returns on/off while the SET takes a "ternary" argument
(on/off/default). If the driver was in the "default" setting -
executing the ioctl path binds it to on or off, even tho the user
did not intend to change HDS config.

Factor the relevant logic out of the netlink code and reuse it.

Fixes: 87c8f8496a05 ("bnxt_en: add support for tcp-data-split ethtool command")
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Tested-by: Daniel Xu <dxu@dxuuu.xyz>
Tested-by: Taehee Yoo <ap420073@gmail.com>
Link: https://patch.msgid.link/20250221025141.1132944-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ethtool/common.c | 16 ++++++++++++++++
 net/ethtool/common.h |  6 ++++++
 net/ethtool/ioctl.c  |  4 ++--
 net/ethtool/rings.c  |  9 ++++-----
 4 files changed, 28 insertions(+), 7 deletions(-)

diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index d88e9080643b8..b97374b508f67 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -6,6 +6,7 @@
 #include <linux/rtnetlink.h>
 #include <linux/ptp_clock_kernel.h>
 #include <linux/phy_link_topology.h>
+#include <net/netdev_queues.h>
 
 #include "netlink.h"
 #include "common.h"
@@ -771,6 +772,21 @@ int ethtool_check_ops(const struct ethtool_ops *ops)
 	return 0;
 }
 
+void ethtool_ringparam_get_cfg(struct net_device *dev,
+			       struct ethtool_ringparam *param,
+			       struct kernel_ethtool_ringparam *kparam,
+			       struct netlink_ext_ack *extack)
+{
+	memset(param, 0, sizeof(*param));
+	memset(kparam, 0, sizeof(*kparam));
+
+	param->cmd = ETHTOOL_GRINGPARAM;
+	dev->ethtool_ops->get_ringparam(dev, param, kparam, extack);
+
+	/* Driver gives us current state, we want to return current config */
+	kparam->tcp_data_split = dev->cfg->hds_config;
+}
+
 static void ethtool_init_tsinfo(struct kernel_ethtool_ts_info *info)
 {
 	memset(info, 0, sizeof(*info));
diff --git a/net/ethtool/common.h b/net/ethtool/common.h
index 58e9e7db06f90..a1088c2441d0a 100644
--- a/net/ethtool/common.h
+++ b/net/ethtool/common.h
@@ -51,6 +51,12 @@ int ethtool_check_max_channel(struct net_device *dev,
 			      struct ethtool_channels channels,
 			      struct genl_info *info);
 int ethtool_check_rss_ctx_busy(struct net_device *dev, u32 rss_context);
+
+void ethtool_ringparam_get_cfg(struct net_device *dev,
+			       struct ethtool_ringparam *param,
+			       struct kernel_ethtool_ringparam *kparam,
+			       struct netlink_ext_ack *extack);
+
 int __ethtool_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *info);
 int ethtool_get_ts_info_by_phc(struct net_device *dev,
 			       struct kernel_ethtool_ts_info *info,
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 7609ce2b2c5e2..1c3ba2247776b 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -2059,8 +2059,8 @@ static int ethtool_get_ringparam(struct net_device *dev, void __user *useraddr)
 
 static int ethtool_set_ringparam(struct net_device *dev, void __user *useraddr)
 {
-	struct ethtool_ringparam ringparam, max = { .cmd = ETHTOOL_GRINGPARAM };
 	struct kernel_ethtool_ringparam kernel_ringparam;
+	struct ethtool_ringparam ringparam, max;
 	int ret;
 
 	if (!dev->ethtool_ops->set_ringparam || !dev->ethtool_ops->get_ringparam)
@@ -2069,7 +2069,7 @@ static int ethtool_set_ringparam(struct net_device *dev, void __user *useraddr)
 	if (copy_from_user(&ringparam, useraddr, sizeof(ringparam)))
 		return -EFAULT;
 
-	dev->ethtool_ops->get_ringparam(dev, &max, &kernel_ringparam, NULL);
+	ethtool_ringparam_get_cfg(dev, &max, &kernel_ringparam, NULL);
 
 	/* ensure new ring parameters are within the maximums */
 	if (ringparam.rx_pending > max.rx_max_pending ||
diff --git a/net/ethtool/rings.c b/net/ethtool/rings.c
index 7839bfd1ac6a0..aeedd5ec6b8cd 100644
--- a/net/ethtool/rings.c
+++ b/net/ethtool/rings.c
@@ -215,17 +215,16 @@ ethnl_set_rings_validate(struct ethnl_req_info *req_info,
 static int
 ethnl_set_rings(struct ethnl_req_info *req_info, struct genl_info *info)
 {
-	struct kernel_ethtool_ringparam kernel_ringparam = {};
-	struct ethtool_ringparam ringparam = {};
+	struct kernel_ethtool_ringparam kernel_ringparam;
 	struct net_device *dev = req_info->dev;
+	struct ethtool_ringparam ringparam;
 	struct nlattr **tb = info->attrs;
 	const struct nlattr *err_attr;
 	bool mod = false;
 	int ret;
 
-	dev->ethtool_ops->get_ringparam(dev, &ringparam,
-					&kernel_ringparam, info->extack);
-	kernel_ringparam.tcp_data_split = dev->cfg->hds_config;
+	ethtool_ringparam_get_cfg(dev, &ringparam, &kernel_ringparam,
+				  info->extack);
 
 	ethnl_update_u32(&ringparam.rx_pending, tb[ETHTOOL_A_RINGS_RX], &mod);
 	ethnl_update_u32(&ringparam.rx_mini_pending,

From 29b036be1b0bfcfc958380d5931325997fddf08a Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 20 Feb 2025 18:51:41 -0800
Subject: [PATCH 0545/1173] selftests: drv-net: test XDP, HDS auto and the
 ioctl path

Test XDP and HDS interaction. While at it add a test for using the IOCTL,
as that turned out to be the real culprit.

Testing bnxt:

  # NETIF=eth0 ./ksft-net-drv/drivers/net/hds.py
  KTAP version 1
  1..12
  ok 1 hds.get_hds
  ok 2 hds.get_hds_thresh
  ok 3 hds.set_hds_disable # SKIP disabling of HDS not supported by the device
  ok 4 hds.set_hds_enable
  ok 5 hds.set_hds_thresh_zero
  ok 6 hds.set_hds_thresh_max
  ok 7 hds.set_hds_thresh_gt
  ok 8 hds.set_xdp
  ok 9 hds.enabled_set_xdp
  ok 10 hds.ioctl
  ok 11 hds.ioctl_set_xdp
  ok 12 hds.ioctl_enabled_set_xdp
  # Totals: pass:11 fail:0 xfail:0 xpass:0 skip:1 error:0

and netdevsim:

  # ./ksft-net-drv/drivers/net/hds.py
  KTAP version 1
  1..12
  ok 1 hds.get_hds
  ok 2 hds.get_hds_thresh
  ok 3 hds.set_hds_disable
  ok 4 hds.set_hds_enable
  ok 5 hds.set_hds_thresh_zero
  ok 6 hds.set_hds_thresh_max
  ok 7 hds.set_hds_thresh_gt
  ok 8 hds.set_xdp
  ok 9 hds.enabled_set_xdp
  ok 10 hds.ioctl
  ok 11 hds.ioctl_set_xdp
  ok 12 hds.ioctl_enabled_set_xdp
  # Totals: pass:12 fail:0 xfail:0 xpass:0 skip:0 error:0

Netdevsim needs a sane default for tx/rx ring size.

ethtool 6.11 is needed for the --disable-netlink option.

Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Tested-by: Taehee Yoo <ap420073@gmail.com>
Link: https://patch.msgid.link/20250221025141.1132944-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/netdevsim/ethtool.c               |   2 +
 tools/testing/selftests/drivers/net/hds.py    | 145 +++++++++++++++++-
 tools/testing/selftests/net/lib/Makefile      |   3 +
 .../testing/selftests/net/lib/xdp_dummy.bpf.c |  13 ++
 4 files changed, 160 insertions(+), 3 deletions(-)
 create mode 100644 tools/testing/selftests/net/lib/xdp_dummy.bpf.c

diff --git a/drivers/net/netdevsim/ethtool.c b/drivers/net/netdevsim/ethtool.c
index 5c80fbee79138..7ab358616e035 100644
--- a/drivers/net/netdevsim/ethtool.c
+++ b/drivers/net/netdevsim/ethtool.c
@@ -184,9 +184,11 @@ static const struct ethtool_ops nsim_ethtool_ops = {
 
 static void nsim_ethtool_ring_init(struct netdevsim *ns)
 {
+	ns->ethtool.ring.rx_pending = 512;
 	ns->ethtool.ring.rx_max_pending = 4096;
 	ns->ethtool.ring.rx_jumbo_max_pending = 4096;
 	ns->ethtool.ring.rx_mini_max_pending = 4096;
+	ns->ethtool.ring.tx_pending = 512;
 	ns->ethtool.ring.tx_max_pending = 4096;
 }
 
diff --git a/tools/testing/selftests/drivers/net/hds.py b/tools/testing/selftests/drivers/net/hds.py
index 394971b25c0b1..873f5219e41d7 100755
--- a/tools/testing/selftests/drivers/net/hds.py
+++ b/tools/testing/selftests/drivers/net/hds.py
@@ -2,17 +2,54 @@
 # SPDX-License-Identifier: GPL-2.0
 
 import errno
+import os
 from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_raises, KsftSkipEx
-from lib.py import EthtoolFamily, NlError
+from lib.py import CmdExitFailure, EthtoolFamily, NlError
 from lib.py import NetDrvEnv
+from lib.py import defer, ethtool, ip
 
-def get_hds(cfg, netnl) -> None:
+
+def _get_hds_mode(cfg, netnl) -> str:
     try:
         rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}})
     except NlError as e:
         raise KsftSkipEx('ring-get not supported by device')
     if 'tcp-data-split' not in rings:
         raise KsftSkipEx('tcp-data-split not supported by device')
+    return rings['tcp-data-split']
+
+
+def _xdp_onoff(cfg):
+    test_dir = os.path.dirname(os.path.realpath(__file__))
+    prog = test_dir + "/../../net/lib/xdp_dummy.bpf.o"
+    ip("link set dev %s xdp obj %s sec xdp" %
+       (cfg.ifname, prog))
+    ip("link set dev %s xdp off" % cfg.ifname)
+
+
+def _ioctl_ringparam_modify(cfg, netnl) -> None:
+    """
+    Helper for performing a hopefully unimportant IOCTL SET.
+    IOCTL does not support HDS, so it should not affect the HDS config.
+    """
+    try:
+        rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}})
+    except NlError as e:
+        raise KsftSkipEx('ring-get not supported by device')
+
+    if 'tx' not in rings:
+        raise KsftSkipEx('setting Tx ring size not supported')
+
+    try:
+        ethtool(f"--disable-netlink -G {cfg.ifname} tx {rings['tx'] // 2}")
+    except CmdExitFailure as e:
+        ethtool(f"--disable-netlink -G {cfg.ifname} tx {rings['tx'] * 2}")
+    defer(ethtool, f"-G {cfg.ifname} tx {rings['tx']}")
+
+
+def get_hds(cfg, netnl) -> None:
+    _get_hds_mode(cfg, netnl)
+
 
 def get_hds_thresh(cfg, netnl) -> None:
     try:
@@ -104,6 +141,103 @@ def set_hds_thresh_gt(cfg, netnl) -> None:
         netnl.rings_set({'header': {'dev-index': cfg.ifindex}, 'hds-thresh': hds_gt})
     ksft_eq(e.exception.nl_msg.error, -errno.EINVAL)
 
+
+def set_xdp(cfg, netnl) -> None:
+    """
+    Enable single-buffer XDP on the device.
+    When HDS is in "auto" / UNKNOWN mode, XDP installation should work.
+    """
+    mode = _get_hds_mode(cfg, netnl)
+    if mode == 'enabled':
+        netnl.rings_set({'header': {'dev-index': cfg.ifindex},
+                         'tcp-data-split': 'unknown'})
+
+    _xdp_onoff(cfg)
+
+
+def enabled_set_xdp(cfg, netnl) -> None:
+    """
+    Enable single-buffer XDP on the device.
+    When HDS is in "enabled" mode, XDP installation should not work.
+    """
+    _get_hds_mode(cfg, netnl)
+    netnl.rings_set({'header': {'dev-index': cfg.ifindex},
+                     'tcp-data-split': 'enabled'})
+
+    defer(netnl.rings_set, {'header': {'dev-index': cfg.ifindex},
+                            'tcp-data-split': 'unknown'})
+
+    with ksft_raises(CmdExitFailure) as e:
+        _xdp_onoff(cfg)
+
+
+def set_xdp(cfg, netnl) -> None:
+    """
+    Enable single-buffer XDP on the device.
+    When HDS is in "auto" / UNKNOWN mode, XDP installation should work.
+    """
+    mode = _get_hds_mode(cfg, netnl)
+    if mode == 'enabled':
+        netnl.rings_set({'header': {'dev-index': cfg.ifindex},
+                         'tcp-data-split': 'unknown'})
+
+    _xdp_onoff(cfg)
+
+
+def enabled_set_xdp(cfg, netnl) -> None:
+    """
+    Enable single-buffer XDP on the device.
+    When HDS is in "enabled" mode, XDP installation should not work.
+    """
+    _get_hds_mode(cfg, netnl)  # Trigger skip if not supported
+
+    netnl.rings_set({'header': {'dev-index': cfg.ifindex},
+                     'tcp-data-split': 'enabled'})
+    defer(netnl.rings_set, {'header': {'dev-index': cfg.ifindex},
+                            'tcp-data-split': 'unknown'})
+
+    with ksft_raises(CmdExitFailure) as e:
+        _xdp_onoff(cfg)
+
+
+def ioctl(cfg, netnl) -> None:
+    mode1 = _get_hds_mode(cfg, netnl)
+    _ioctl_ringparam_modify(cfg, netnl)
+    mode2 = _get_hds_mode(cfg, netnl)
+
+    ksft_eq(mode1, mode2)
+
+
+def ioctl_set_xdp(cfg, netnl) -> None:
+    """
+    Like set_xdp(), but we perturb the settings via the legacy ioctl.
+    """
+    mode = _get_hds_mode(cfg, netnl)
+    if mode == 'enabled':
+        netnl.rings_set({'header': {'dev-index': cfg.ifindex},
+                         'tcp-data-split': 'unknown'})
+
+    _ioctl_ringparam_modify(cfg, netnl)
+
+    _xdp_onoff(cfg)
+
+
+def ioctl_enabled_set_xdp(cfg, netnl) -> None:
+    """
+    Enable single-buffer XDP on the device.
+    When HDS is in "enabled" mode, XDP installation should not work.
+    """
+    _get_hds_mode(cfg, netnl)  # Trigger skip if not supported
+
+    netnl.rings_set({'header': {'dev-index': cfg.ifindex},
+                     'tcp-data-split': 'enabled'})
+    defer(netnl.rings_set, {'header': {'dev-index': cfg.ifindex},
+                            'tcp-data-split': 'unknown'})
+
+    with ksft_raises(CmdExitFailure) as e:
+        _xdp_onoff(cfg)
+
+
 def main() -> None:
     with NetDrvEnv(__file__, queue_count=3) as cfg:
         ksft_run([get_hds,
@@ -112,7 +246,12 @@ def main() -> None:
                   set_hds_enable,
                   set_hds_thresh_zero,
                   set_hds_thresh_max,
-                  set_hds_thresh_gt],
+                  set_hds_thresh_gt,
+                  set_xdp,
+                  enabled_set_xdp,
+                  ioctl,
+                  ioctl_set_xdp,
+                  ioctl_enabled_set_xdp],
                  args=(cfg, EthtoolFamily()))
     ksft_exit()
 
diff --git a/tools/testing/selftests/net/lib/Makefile b/tools/testing/selftests/net/lib/Makefile
index bc6b6762baf3e..c22623b9a2a5f 100644
--- a/tools/testing/selftests/net/lib/Makefile
+++ b/tools/testing/selftests/net/lib/Makefile
@@ -9,7 +9,10 @@ TEST_FILES := ../../../../../Documentation/netlink/specs
 TEST_FILES += ../../../../net/ynl
 
 TEST_GEN_FILES += csum
+TEST_GEN_FILES += $(patsubst %.c,%.o,$(wildcard *.bpf.c))
 
 TEST_INCLUDES := $(wildcard py/*.py sh/*.sh)
 
 include ../../lib.mk
+
+include ../bpf.mk
diff --git a/tools/testing/selftests/net/lib/xdp_dummy.bpf.c b/tools/testing/selftests/net/lib/xdp_dummy.bpf.c
new file mode 100644
index 0000000000000..d988b2e0cee84
--- /dev/null
+++ b/tools/testing/selftests/net/lib/xdp_dummy.bpf.c
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define KBUILD_MODNAME "xdp_dummy"
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+SEC("xdp")
+int xdp_dummy_prog(struct xdp_md *ctx)
+{
+	return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";

From 8c1624b63a7d24142a2bbc3a5ee7e95f004ea36e Mon Sep 17 00:00:00 2001
From: Sagi Grimberg <sagi@grimberg.me>
Date: Thu, 20 Feb 2025 13:18:30 +0200
Subject: [PATCH 0546/1173] nvme-tcp: fix possible UAF in nvme_tcp_poll

nvme_tcp_poll() may race with the send path error handler because
it may complete the request while it is actively being polled for
completion, resulting in a UAF panic [1]:

We should make sure to stop polling when we see an error when
trying to read from the socket. Hence make sure to propagate the
error so that the block layer breaks the polling cycle.

[1]:
--
[35665.692310] nvme nvme2: failed to send request -13
[35665.702265] nvme nvme2: unsupported pdu type (3)
[35665.702272] BUG: kernel NULL pointer dereference, address: 0000000000000000
[35665.702542] nvme nvme2: queue 1 receive failed:  -22
[35665.703209] #PF: supervisor write access in kernel mode
[35665.703213] #PF: error_code(0x0002) - not-present page
[35665.703214] PGD 8000003801cce067 P4D 8000003801cce067 PUD 37e6f79067 PMD 0
[35665.703220] Oops: 0002 [#1] SMP PTI
[35665.703658] nvme nvme2: starting error recovery
[35665.705809] Hardware name: Inspur aaabbb/YZMB-00882-104, BIOS 4.1.26 09/22/2022
[35665.705812] Workqueue: kblockd blk_mq_requeue_work
[35665.709172] RIP: 0010:_raw_spin_lock+0xc/0x30
[35665.715788] Call Trace:
[35665.716201]  <TASK>
[35665.716613]  ? show_trace_log_lvl+0x1c1/0x2d9
[35665.717049]  ? show_trace_log_lvl+0x1c1/0x2d9
[35665.717457]  ? blk_mq_request_bypass_insert+0x2c/0xb0
[35665.717950]  ? __die_body.cold+0x8/0xd
[35665.718361]  ? page_fault_oops+0xac/0x140
[35665.718749]  ? blk_mq_start_request+0x30/0xf0
[35665.719144]  ? nvme_tcp_queue_rq+0xc7/0x170 [nvme_tcp]
[35665.719547]  ? exc_page_fault+0x62/0x130
[35665.719938]  ? asm_exc_page_fault+0x22/0x30
[35665.720333]  ? _raw_spin_lock+0xc/0x30
[35665.720723]  blk_mq_request_bypass_insert+0x2c/0xb0
[35665.721101]  blk_mq_requeue_work+0xa5/0x180
[35665.721451]  process_one_work+0x1e8/0x390
[35665.721809]  worker_thread+0x53/0x3d0
[35665.722159]  ? process_one_work+0x390/0x390
[35665.722501]  kthread+0x124/0x150
[35665.722849]  ? set_kthread_struct+0x50/0x50
[35665.723182]  ret_from_fork+0x1f/0x30

Reported-by: Zhang Guanghui <zhang.guanghui@cestc.cn>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/tcp.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 8a9131c95a3da..8c14018201dbd 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -2699,6 +2699,7 @@ static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
 {
 	struct nvme_tcp_queue *queue = hctx->driver_data;
 	struct sock *sk = queue->sock->sk;
+	int ret;
 
 	if (!test_bit(NVME_TCP_Q_LIVE, &queue->flags))
 		return 0;
@@ -2706,9 +2707,9 @@ static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
 	set_bit(NVME_TCP_Q_POLLING, &queue->flags);
 	if (sk_can_busy_loop(sk) && skb_queue_empty_lockless(&sk->sk_receive_queue))
 		sk_busy_loop(sk, true);
-	nvme_tcp_try_recv(queue);
+	ret = nvme_tcp_try_recv(queue);
 	clear_bit(NVME_TCP_Q_POLLING, &queue->flags);
-	return queue->nr_cqe;
+	return ret < 0 ? ret : queue->nr_cqe;
 }
 
 static int nvme_tcp_get_address(struct nvme_ctrl *ctrl, char *buf, int size)

From 6a3572e10f740acd48e2713ef37e92186a3ce5e8 Mon Sep 17 00:00:00 2001
From: Icenowy Zheng <uwu@icenowy.me>
Date: Thu, 13 Feb 2025 01:04:43 +0800
Subject: [PATCH 0547/1173] nvme-pci: clean up CMBMSC when registering CMB
 fails

CMB decoding should get disabled when the CMB block isn't successfully
registered to P2P DMA subsystem.

Clean up the CMBMSC register in this error handling codepath to disable
CMB decoding (and CMBLOC/CMBSZ registers).

Signed-off-by: Icenowy Zheng <uwu@icenowy.me>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/pci.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 950289405ef28..218506e3dabea 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2003,6 +2003,7 @@ static void nvme_map_cmb(struct nvme_dev *dev)
 	if (pci_p2pdma_add_resource(pdev, bar, size, offset)) {
 		dev_warn(dev->ctrl.device,
 			 "failed to register the CMB\n");
+		hi_lo_writeq(0, dev->bar + NVME_REG_CMBMSC);
 		return;
 	}
 

From 56cf7ef0d490b28fad8f8629fc135c5ab7c9f54e Mon Sep 17 00:00:00 2001
From: Icenowy Zheng <uwu@icenowy.me>
Date: Thu, 13 Feb 2025 01:04:44 +0800
Subject: [PATCH 0548/1173] nvme-pci: skip CMB blocks incompatible with PCI P2P
 DMA

The PCI P2PDMA code will register the CMB block to the memory
hot-plugging subsystem, which have an alignment requirement. Memory
blocks that do not satisfy this alignment requirement (usually 2MB) will
lead to a WARNING from memory hotplugging.

Verify the CMB block's address and size against the alignment and only
try to send CMB blocks compatible with it to prevent this warning.

Tested on Intel DC D4502 SSD, which has a 512K CMB block that is too
small for memory hotplugging (thus PCI P2PDMA).

Signed-off-by: Icenowy Zheng <uwu@icenowy.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/pci.c | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 218506e3dabea..640590b217282 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1982,6 +1982,18 @@ static void nvme_map_cmb(struct nvme_dev *dev)
 	if (offset > bar_size)
 		return;
 
+	/*
+	 * Controllers may support a CMB size larger than their BAR, for
+	 * example, due to being behind a bridge. Reduce the CMB to the
+	 * reported size of the BAR
+	 */
+	size = min(size, bar_size - offset);
+
+	if (!IS_ALIGNED(size, memremap_compat_align()) ||
+	    !IS_ALIGNED(pci_resource_start(pdev, bar),
+			memremap_compat_align()))
+		return;
+
 	/*
 	 * Tell the controller about the host side address mapping the CMB,
 	 * and enable CMB decoding for the NVMe 1.4+ scheme:
@@ -1992,14 +2004,6 @@ static void nvme_map_cmb(struct nvme_dev *dev)
 			     dev->bar + NVME_REG_CMBMSC);
 	}
 
-	/*
-	 * Controllers may support a CMB size larger than their BAR,
-	 * for example, due to being behind a bridge. Reduce the CMB to
-	 * the reported size of the BAR
-	 */
-	if (size > bar_size - offset)
-		size = bar_size - offset;
-
 	if (pci_p2pdma_add_resource(pdev, bar, size, offset)) {
 		dev_warn(dev->ctrl.device,
 			 "failed to register the CMB\n");

From 5797c04400ee117bfe459ff1e468d0ea38054ab4 Mon Sep 17 00:00:00 2001
From: Paul Fertser <fercerpav@gmail.com>
Date: Thu, 23 Jan 2025 15:20:02 +0300
Subject: [PATCH 0549/1173] hwmon: (peci/dimmtemp) Do not provide fake
 thresholds data

When an Icelake or Sapphire Rapids CPU isn't providing the maximum and
critical thresholds for particular DIMM the driver should return an
error to the userspace instead of giving it stale (best case) or wrong
(the structure contains all zeros after kzalloc() call) data.

The issue can be reproduced by binding the peci driver while the host is
fully booted and idle, this makes PECI interaction unreliable enough.

Fixes: 73bc1b885dae ("hwmon: peci: Add dimmtemp driver")
Fixes: 621995b6d795 ("hwmon: (peci/dimmtemp) Add Sapphire Rapids support")
Cc: stable@vger.kernel.org
Signed-off-by: Paul Fertser <fercerpav@gmail.com>
Reviewed-by: Iwona Winiarska <iwona.winiarska@intel.com>
Link: https://lore.kernel.org/r/20250123122003.6010-1-fercerpav@gmail.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/peci/dimmtemp.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/hwmon/peci/dimmtemp.c b/drivers/hwmon/peci/dimmtemp.c
index d6762259dd69c..fbe82d9852e01 100644
--- a/drivers/hwmon/peci/dimmtemp.c
+++ b/drivers/hwmon/peci/dimmtemp.c
@@ -127,8 +127,6 @@ static int update_thresholds(struct peci_dimmtemp *priv, int dimm_no)
 		return 0;
 
 	ret = priv->gen_info->read_thresholds(priv, dimm_order, chan_rank, &data);
-	if (ret == -ENODATA) /* Use default or previous value */
-		return 0;
 	if (ret)
 		return ret;
 
@@ -509,11 +507,11 @@ read_thresholds_icx(struct peci_dimmtemp *priv, int dimm_order, int chan_rank, u
 
 	ret = peci_ep_pci_local_read(priv->peci_dev, 0, 13, 0, 2, 0xd4, &reg_val);
 	if (ret || !(reg_val & BIT(31)))
-		return -ENODATA; /* Use default or previous value */
+		return -ENODATA;
 
 	ret = peci_ep_pci_local_read(priv->peci_dev, 0, 13, 0, 2, 0xd0, &reg_val);
 	if (ret)
-		return -ENODATA; /* Use default or previous value */
+		return -ENODATA;
 
 	/*
 	 * Device 26, Offset 224e0: IMC 0 channel 0 -> rank 0
@@ -546,11 +544,11 @@ read_thresholds_spr(struct peci_dimmtemp *priv, int dimm_order, int chan_rank, u
 
 	ret = peci_ep_pci_local_read(priv->peci_dev, 0, 30, 0, 2, 0xd4, &reg_val);
 	if (ret || !(reg_val & BIT(31)))
-		return -ENODATA; /* Use default or previous value */
+		return -ENODATA;
 
 	ret = peci_ep_pci_local_read(priv->peci_dev, 0, 30, 0, 2, 0xd0, &reg_val);
 	if (ret)
-		return -ENODATA; /* Use default or previous value */
+		return -ENODATA;
 
 	/*
 	 * Device 26, Offset 219a8: IMC 0 channel 0 -> rank 0

From b5799106b44e1df594f4696500dbbc3b326bba18 Mon Sep 17 00:00:00 2001
From: John Garry <john.g.garry@oracle.com>
Date: Mon, 24 Feb 2025 15:45:38 +0000
Subject: [PATCH 0550/1173] iomap: Minor code simplification in
 iomap_dio_bio_iter()

Combine 'else' and 'if' conditional statements onto a single line and drop
unrequired braces, as is standard coding style.

The code had been like this since commit c3b0e880bbfa ("iomap: support
REQ_OP_ZONE_APPEND").

Signed-off-by: John Garry <john.g.garry@oracle.com>
Link: https://lore.kernel.org/r/20250224154538.548028-1-john.g.garry@oracle.com
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/iomap/direct-io.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index b521eb15759e8..0e47da82b0c24 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -427,12 +427,10 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
 			bio_put(bio);
 			goto zero_tail;
 		}
-		if (dio->flags & IOMAP_DIO_WRITE) {
+		if (dio->flags & IOMAP_DIO_WRITE)
 			task_io_account_write(n);
-		} else {
-			if (dio->flags & IOMAP_DIO_DIRTY)
-				bio_set_pages_dirty(bio);
-		}
+		else if (dio->flags & IOMAP_DIO_DIRTY)
+			bio_set_pages_dirty(bio);
 
 		dio->size += n;
 		copied += n;

From 423de5b5bc5b267586b449abd1c4fde562aa0cf9 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Fri, 21 Feb 2025 17:57:11 +0100
Subject: [PATCH 0551/1173] thermal/of: Fix cdev lookup in
 thermal_of_should_bind()

Since thermal_of_should_bind() terminates the loop after processing
the first child found in cooling-maps, it will never match more than
one cdev to a given trip point which is incorrect, as there may be
cooling-maps associating one trip point with multiple cooling devices.

Address this by letting the loop continue until either all
children have been processed or a matching one has been found.

To avoid adding conditionals or goto statements, put the loop in
question into a separate function and make that function return
right away after finding a matching cooling-maps entry.

Fixes: 94c6110b0b13 ("thermal/of: Use the .should_bind() thermal zone callback")
Link: https://lore.kernel.org/linux-pm/20250219-fix-thermal-of-v1-1-de36e7a590c4@chromium.org/
Reported-by: Yu-Che Cheng <giver@chromium.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Yu-Che Cheng <giver@chromium.org>
Tested-by: Yu-Che Cheng <giver@chromium.org>
Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
Tested-by: Lukasz Luba <lukasz.luba@arm.com>
Link: https://patch.msgid.link/2788228.mvXUDI8C0e@rjwysocki.net
---
 drivers/thermal/thermal_of.c | 50 +++++++++++++++++++++---------------
 1 file changed, 29 insertions(+), 21 deletions(-)

diff --git a/drivers/thermal/thermal_of.c b/drivers/thermal/thermal_of.c
index 5ab4ce4daaebd..5401f03d6b6c1 100644
--- a/drivers/thermal/thermal_of.c
+++ b/drivers/thermal/thermal_of.c
@@ -274,6 +274,34 @@ static bool thermal_of_get_cooling_spec(struct device_node *map_np, int index,
 	return true;
 }
 
+static bool thermal_of_cm_lookup(struct device_node *cm_np,
+				 const struct thermal_trip *trip,
+				 struct thermal_cooling_device *cdev,
+				 struct cooling_spec *c)
+{
+	for_each_child_of_node_scoped(cm_np, child) {
+		struct device_node *tr_np;
+		int count, i;
+
+		tr_np = of_parse_phandle(child, "trip", 0);
+		if (tr_np != trip->priv)
+			continue;
+
+		/* The trip has been found, look up the cdev. */
+		count = of_count_phandle_with_args(child, "cooling-device",
+						   "#cooling-cells");
+		if (count <= 0)
+			pr_err("Add a cooling_device property with at least one device\n");
+
+		for (i = 0; i < count; i++) {
+			if (thermal_of_get_cooling_spec(child, i, cdev, c))
+				return true;
+		}
+	}
+
+	return false;
+}
+
 static bool thermal_of_should_bind(struct thermal_zone_device *tz,
 				   const struct thermal_trip *trip,
 				   struct thermal_cooling_device *cdev,
@@ -293,27 +321,7 @@ static bool thermal_of_should_bind(struct thermal_zone_device *tz,
 		goto out;
 
 	/* Look up the trip and the cdev in the cooling maps. */
-	for_each_child_of_node_scoped(cm_np, child) {
-		struct device_node *tr_np;
-		int count, i;
-
-		tr_np = of_parse_phandle(child, "trip", 0);
-		if (tr_np != trip->priv)
-			continue;
-
-		/* The trip has been found, look up the cdev. */
-		count = of_count_phandle_with_args(child, "cooling-device", "#cooling-cells");
-		if (count <= 0)
-			pr_err("Add a cooling_device property with at least one device\n");
-
-		for (i = 0; i < count; i++) {
-			result = thermal_of_get_cooling_spec(child, i, cdev, c);
-			if (result)
-				break;
-		}
-
-		break;
-	}
+	result = thermal_of_cm_lookup(cm_np, trip, cdev, c);
 
 	of_node_put(cm_np);
 out:

From 0cde378a10c1cbfaa8dd2b89672d42f36c2809c3 Mon Sep 17 00:00:00 2001
From: Yu-Che Cheng <giver@chromium.org>
Date: Sat, 22 Feb 2025 11:20:34 +0800
Subject: [PATCH 0552/1173] thermal: gov_power_allocator: Update total_weight
 on bind and cdev updates

params->total_weight is not initialized during bind and not updated when
the bound cdev changes. The cooling device weight will not be used due
to the uninitialized total_weight, until an update via sysfs is
triggered.

The bound cdevs are updated during thermal zone registration, where each
cooling device will be bound to the thermal zone one by one, but
power_allocator_bind() can be called without an additional cdev update
when manually changing the policy of a thermal zone via sysfs.

Add a new function to handle weight update logic, including updating
total_weight, and call it when bind, weight changes, and cdev updates to
ensure total_weight is always correct.

Fixes: a3cd6db4cc2e ("thermal: gov_power_allocator: Support new update callback of weights")
Signed-off-by: Yu-Che Cheng <giver@chromium.org>
Link: https://patch.msgid.link/20250222-fix-power-allocator-weight-v2-1-a94de86b685a@chromium.org
[ rjw: Changelog edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/thermal/gov_power_allocator.c | 30 ++++++++++++++++++++-------
 1 file changed, 22 insertions(+), 8 deletions(-)

diff --git a/drivers/thermal/gov_power_allocator.c b/drivers/thermal/gov_power_allocator.c
index 3b626db55b2b9..0d9f636c80f4d 100644
--- a/drivers/thermal/gov_power_allocator.c
+++ b/drivers/thermal/gov_power_allocator.c
@@ -641,6 +641,22 @@ static int allocate_actors_buffer(struct power_allocator_params *params,
 	return ret;
 }
 
+static void power_allocator_update_weight(struct power_allocator_params *params)
+{
+	const struct thermal_trip_desc *td;
+	struct thermal_instance *instance;
+
+	if (!params->trip_max)
+		return;
+
+	td = trip_to_trip_desc(params->trip_max);
+
+	params->total_weight = 0;
+	list_for_each_entry(instance, &td->thermal_instances, trip_node)
+		if (power_actor_is_valid(instance))
+			params->total_weight += instance->weight;
+}
+
 static void power_allocator_update_tz(struct thermal_zone_device *tz,
 				      enum thermal_notify_event reason)
 {
@@ -656,16 +672,12 @@ static void power_allocator_update_tz(struct thermal_zone_device *tz,
 			if (power_actor_is_valid(instance))
 				num_actors++;
 
-		if (num_actors == params->num_actors)
-			return;
+		if (num_actors != params->num_actors)
+			allocate_actors_buffer(params, num_actors);
 
-		allocate_actors_buffer(params, num_actors);
-		break;
+		fallthrough;
 	case THERMAL_INSTANCE_WEIGHT_CHANGED:
-		params->total_weight = 0;
-		list_for_each_entry(instance, &td->thermal_instances, trip_node)
-			if (power_actor_is_valid(instance))
-				params->total_weight += instance->weight;
+		power_allocator_update_weight(params);
 		break;
 	default:
 		break;
@@ -731,6 +743,8 @@ static int power_allocator_bind(struct thermal_zone_device *tz)
 
 	tz->governor_data = params;
 
+	power_allocator_update_weight(params);
+
 	return 0;
 
 free_params:

From 4b90de5bc0f5a6d1151acd74c838275f9b7be3a5 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 24 Feb 2025 15:48:52 -0800
Subject: [PATCH 0553/1173] xfs: reduce context switches for synchronous
 buffered I/O

Currently all metadata I/O completions happen in the m_buf_workqueue
workqueue.  But for synchronous I/O (i.e. all buffer reads) there is no
need for that, as there always is a called in process context that is
waiting for the I/O.  Factor out the guts of xfs_buf_ioend into a
separate helper and call it from xfs_buf_iowait to avoid a double
an extra context switch to the workqueue.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_buf.c | 43 +++++++++++++++++++++++++++----------------
 1 file changed, 27 insertions(+), 16 deletions(-)

diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 15bb790359f81..dfc1849b3314b 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1345,6 +1345,7 @@ xfs_buf_ioend_handle_error(
 resubmit:
 	xfs_buf_ioerror(bp, 0);
 	bp->b_flags |= (XBF_DONE | XBF_WRITE_FAIL);
+	reinit_completion(&bp->b_iowait);
 	xfs_buf_submit(bp);
 	return true;
 out_stale:
@@ -1355,8 +1356,9 @@ xfs_buf_ioend_handle_error(
 	return false;
 }
 
-static void
-xfs_buf_ioend(
+/* returns false if the caller needs to resubmit the I/O, else true */
+static bool
+__xfs_buf_ioend(
 	struct xfs_buf	*bp)
 {
 	trace_xfs_buf_iodone(bp, _RET_IP_);
@@ -1376,7 +1378,7 @@ xfs_buf_ioend(
 		}
 
 		if (unlikely(bp->b_error) && xfs_buf_ioend_handle_error(bp))
-			return;
+			return false;
 
 		/* clear the retry state */
 		bp->b_last_error = 0;
@@ -1397,7 +1399,15 @@ xfs_buf_ioend(
 
 	bp->b_flags &= ~(XBF_READ | XBF_WRITE | XBF_READ_AHEAD |
 			 _XBF_LOGRECOVERY);
+	return true;
+}
 
+static void
+xfs_buf_ioend(
+	struct xfs_buf	*bp)
+{
+	if (!__xfs_buf_ioend(bp))
+		return;
 	if (bp->b_flags & XBF_ASYNC)
 		xfs_buf_relse(bp);
 	else
@@ -1411,15 +1421,8 @@ xfs_buf_ioend_work(
 	struct xfs_buf		*bp =
 		container_of(work, struct xfs_buf, b_ioend_work);
 
-	xfs_buf_ioend(bp);
-}
-
-static void
-xfs_buf_ioend_async(
-	struct xfs_buf	*bp)
-{
-	INIT_WORK(&bp->b_ioend_work, xfs_buf_ioend_work);
-	queue_work(bp->b_mount->m_buf_workqueue, &bp->b_ioend_work);
+	if (__xfs_buf_ioend(bp))
+		xfs_buf_relse(bp);
 }
 
 void
@@ -1491,7 +1494,13 @@ xfs_buf_bio_end_io(
 		 XFS_TEST_ERROR(false, bp->b_mount, XFS_ERRTAG_BUF_IOERROR))
 		xfs_buf_ioerror(bp, -EIO);
 
-	xfs_buf_ioend_async(bp);
+	if (bp->b_flags & XBF_ASYNC) {
+		INIT_WORK(&bp->b_ioend_work, xfs_buf_ioend_work);
+		queue_work(bp->b_mount->m_buf_workqueue, &bp->b_ioend_work);
+	} else {
+		complete(&bp->b_iowait);
+	}
+
 	bio_put(bio);
 }
 
@@ -1568,9 +1577,11 @@ xfs_buf_iowait(
 {
 	ASSERT(!(bp->b_flags & XBF_ASYNC));
 
-	trace_xfs_buf_iowait(bp, _RET_IP_);
-	wait_for_completion(&bp->b_iowait);
-	trace_xfs_buf_iowait_done(bp, _RET_IP_);
+	do {
+		trace_xfs_buf_iowait(bp, _RET_IP_);
+		wait_for_completion(&bp->b_iowait);
+		trace_xfs_buf_iowait_done(bp, _RET_IP_);
+	} while (!__xfs_buf_ioend(bp));
 
 	return bp->b_error;
 }

From efc5f7a9f3d887ce44b7610bc39388094b6f97d5 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 24 Feb 2025 15:48:53 -0800
Subject: [PATCH 0554/1173] xfs: decouple buffer readahead from the normal
 buffer read path

xfs_buf_readahead_map is the only caller of xfs_buf_read_map and thus
_xfs_buf_read that is not synchronous.  Split it from xfs_buf_read_map
so that the asynchronous path is self-contained and the now purely
synchronous xfs_buf_read_map / _xfs_buf_read implementation can be
simplified.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_buf.c         | 41 ++++++++++++++++++++--------------------
 fs/xfs/xfs_buf.h         |  2 +-
 fs/xfs/xfs_log_recover.c |  2 +-
 fs/xfs/xfs_trace.h       |  1 +
 4 files changed, 23 insertions(+), 23 deletions(-)

diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index dfc1849b3314b..4ea20483d5213 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -794,18 +794,13 @@ xfs_buf_get_map(
 
 int
 _xfs_buf_read(
-	struct xfs_buf		*bp,
-	xfs_buf_flags_t		flags)
+	struct xfs_buf		*bp)
 {
-	ASSERT(!(flags & XBF_WRITE));
 	ASSERT(bp->b_maps[0].bm_bn != XFS_BUF_DADDR_NULL);
 
 	bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_READ_AHEAD | XBF_DONE);
-	bp->b_flags |= flags & (XBF_READ | XBF_ASYNC | XBF_READ_AHEAD);
-
+	bp->b_flags |= XBF_READ;
 	xfs_buf_submit(bp);
-	if (flags & XBF_ASYNC)
-		return 0;
 	return xfs_buf_iowait(bp);
 }
 
@@ -857,6 +852,8 @@ xfs_buf_read_map(
 	struct xfs_buf		*bp;
 	int			error;
 
+	ASSERT(!(flags & (XBF_WRITE | XBF_ASYNC | XBF_READ_AHEAD)));
+
 	flags |= XBF_READ;
 	*bpp = NULL;
 
@@ -870,21 +867,11 @@ xfs_buf_read_map(
 		/* Initiate the buffer read and wait. */
 		XFS_STATS_INC(target->bt_mount, xb_get_read);
 		bp->b_ops = ops;
-		error = _xfs_buf_read(bp, flags);
-
-		/* Readahead iodone already dropped the buffer, so exit. */
-		if (flags & XBF_ASYNC)
-			return 0;
+		error = _xfs_buf_read(bp);
 	} else {
 		/* Buffer already read; all we need to do is check it. */
 		error = xfs_buf_reverify(bp, ops);
 
-		/* Readahead already finished; drop the buffer and exit. */
-		if (flags & XBF_ASYNC) {
-			xfs_buf_relse(bp);
-			return 0;
-		}
-
 		/* We do not want read in the flags */
 		bp->b_flags &= ~XBF_READ;
 		ASSERT(bp->b_ops != NULL || ops == NULL);
@@ -936,6 +923,7 @@ xfs_buf_readahead_map(
 	int			nmaps,
 	const struct xfs_buf_ops *ops)
 {
+	const xfs_buf_flags_t	flags = XBF_READ | XBF_ASYNC | XBF_READ_AHEAD;
 	struct xfs_buf		*bp;
 
 	/*
@@ -945,9 +933,20 @@ xfs_buf_readahead_map(
 	if (xfs_buftarg_is_mem(target))
 		return;
 
-	xfs_buf_read_map(target, map, nmaps,
-		     XBF_TRYLOCK | XBF_ASYNC | XBF_READ_AHEAD, &bp, ops,
-		     __this_address);
+	if (xfs_buf_get_map(target, map, nmaps, flags | XBF_TRYLOCK, &bp))
+		return;
+	trace_xfs_buf_readahead(bp, 0, _RET_IP_);
+
+	if (bp->b_flags & XBF_DONE) {
+		xfs_buf_reverify(bp, ops);
+		xfs_buf_relse(bp);
+		return;
+	}
+	XFS_STATS_INC(target->bt_mount, xb_get_read);
+	bp->b_ops = ops;
+	bp->b_flags &= ~(XBF_WRITE | XBF_DONE);
+	bp->b_flags |= flags;
+	xfs_buf_submit(bp);
 }
 
 /*
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 3b4ed42e11c01..2e747555ad3fa 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -291,7 +291,7 @@ int xfs_buf_get_uncached(struct xfs_buftarg *target, size_t numblks,
 int xfs_buf_read_uncached(struct xfs_buftarg *target, xfs_daddr_t daddr,
 		size_t numblks, xfs_buf_flags_t flags, struct xfs_buf **bpp,
 		const struct xfs_buf_ops *ops);
-int _xfs_buf_read(struct xfs_buf *bp, xfs_buf_flags_t flags);
+int _xfs_buf_read(struct xfs_buf *bp);
 void xfs_buf_hold(struct xfs_buf *bp);
 
 /* Releasing Buffers */
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index b3c27dbccce86..2f76531842f83 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -3380,7 +3380,7 @@ xlog_do_recover(
 	 */
 	xfs_buf_lock(bp);
 	xfs_buf_hold(bp);
-	error = _xfs_buf_read(bp, XBF_READ);
+	error = _xfs_buf_read(bp);
 	if (error) {
 		if (!xlog_is_shutdown(log)) {
 			xfs_buf_ioerror_alert(bp, __this_address);
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index b29462363b815..bfc2f12490224 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -593,6 +593,7 @@ DEFINE_EVENT(xfs_buf_flags_class, name, \
 DEFINE_BUF_FLAGS_EVENT(xfs_buf_find);
 DEFINE_BUF_FLAGS_EVENT(xfs_buf_get);
 DEFINE_BUF_FLAGS_EVENT(xfs_buf_read);
+DEFINE_BUF_FLAGS_EVENT(xfs_buf_readahead);
 
 TRACE_EVENT(xfs_buf_ioerror,
 	TP_PROTO(struct xfs_buf *bp, int error, xfs_failaddr_t caller_ip),

From 0d1120b9bbe48a2d119afe0dc64f9c0666745bc8 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 24 Feb 2025 15:48:54 -0800
Subject: [PATCH 0555/1173] xfs: remove most in-flight buffer accounting

The buffer cache keeps a bt_io_count per-CPU counter to track all
in-flight I/O, which is used to ensure no I/O is in flight when
unmounting the file system.

For most I/O we already keep track of inflight I/O at higher levels:

 - for synchronous I/O (xfs_buf_read/xfs_bwrite/xfs_buf_delwri_submit),
   the caller has a reference and waits for I/O completions using
   xfs_buf_iowait
 - for xfs_buf_delwri_submit_nowait the only caller (AIL writeback)
   tracks the log items that the buffer attached to

This only leaves only xfs_buf_readahead_map as a submitter of
asynchronous I/O that is not tracked by anything else.  Replace the
bt_io_count per-cpu counter with a more specific bt_readahead_count
counter only tracking readahead I/O.  This allows to simply increment
it when submitting readahead I/O and decrementing it when it completed,
and thus simplify xfs_buf_rele and remove the needed for the
XBF_NO_IOACCT flags and the XFS_BSTATE_IN_FLIGHT buffer state.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_buf.c     | 90 ++++++++------------------------------------
 fs/xfs/xfs_buf.h     |  5 +--
 fs/xfs/xfs_buf_mem.c |  2 +-
 fs/xfs/xfs_mount.c   |  7 +---
 fs/xfs/xfs_rtalloc.c |  2 +-
 5 files changed, 20 insertions(+), 86 deletions(-)

diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 4ea20483d5213..e161f3ab41087 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -29,11 +29,6 @@ struct kmem_cache *xfs_buf_cache;
 /*
  * Locking orders
  *
- * xfs_buf_ioacct_inc:
- * xfs_buf_ioacct_dec:
- *	b_sema (caller holds)
- *	  b_lock
- *
  * xfs_buf_stale:
  *	b_sema (caller holds)
  *	  b_lock
@@ -81,51 +76,6 @@ xfs_buf_vmap_len(
 	return (bp->b_page_count * PAGE_SIZE);
 }
 
-/*
- * Bump the I/O in flight count on the buftarg if we haven't yet done so for
- * this buffer. The count is incremented once per buffer (per hold cycle)
- * because the corresponding decrement is deferred to buffer release. Buffers
- * can undergo I/O multiple times in a hold-release cycle and per buffer I/O
- * tracking adds unnecessary overhead. This is used for sychronization purposes
- * with unmount (see xfs_buftarg_drain()), so all we really need is a count of
- * in-flight buffers.
- *
- * Buffers that are never released (e.g., superblock, iclog buffers) must set
- * the XBF_NO_IOACCT flag before I/O submission. Otherwise, the buftarg count
- * never reaches zero and unmount hangs indefinitely.
- */
-static inline void
-xfs_buf_ioacct_inc(
-	struct xfs_buf	*bp)
-{
-	if (bp->b_flags & XBF_NO_IOACCT)
-		return;
-
-	ASSERT(bp->b_flags & XBF_ASYNC);
-	spin_lock(&bp->b_lock);
-	if (!(bp->b_state & XFS_BSTATE_IN_FLIGHT)) {
-		bp->b_state |= XFS_BSTATE_IN_FLIGHT;
-		percpu_counter_inc(&bp->b_target->bt_io_count);
-	}
-	spin_unlock(&bp->b_lock);
-}
-
-/*
- * Clear the in-flight state on a buffer about to be released to the LRU or
- * freed and unaccount from the buftarg.
- */
-static inline void
-__xfs_buf_ioacct_dec(
-	struct xfs_buf	*bp)
-{
-	lockdep_assert_held(&bp->b_lock);
-
-	if (bp->b_state & XFS_BSTATE_IN_FLIGHT) {
-		bp->b_state &= ~XFS_BSTATE_IN_FLIGHT;
-		percpu_counter_dec(&bp->b_target->bt_io_count);
-	}
-}
-
 /*
  * When we mark a buffer stale, we remove the buffer from the LRU and clear the
  * b_lru_ref count so that the buffer is freed immediately when the buffer
@@ -156,8 +106,6 @@ xfs_buf_stale(
 	 * status now to preserve accounting consistency.
 	 */
 	spin_lock(&bp->b_lock);
-	__xfs_buf_ioacct_dec(bp);
-
 	atomic_set(&bp->b_lru_ref, 0);
 	if (!(bp->b_state & XFS_BSTATE_DISPOSE) &&
 	    (list_lru_del_obj(&bp->b_target->bt_lru, &bp->b_lru)))
@@ -946,6 +894,7 @@ xfs_buf_readahead_map(
 	bp->b_ops = ops;
 	bp->b_flags &= ~(XBF_WRITE | XBF_DONE);
 	bp->b_flags |= flags;
+	percpu_counter_inc(&target->bt_readahead_count);
 	xfs_buf_submit(bp);
 }
 
@@ -1002,10 +951,12 @@ xfs_buf_get_uncached(
 	struct xfs_buf		*bp;
 	DEFINE_SINGLE_BUF_MAP(map, XFS_BUF_DADDR_NULL, numblks);
 
+	/* there are currently no valid flags for xfs_buf_get_uncached */
+	ASSERT(flags == 0);
+
 	*bpp = NULL;
 
-	/* flags might contain irrelevant bits, pass only what we care about */
-	error = _xfs_buf_alloc(target, &map, 1, flags & XBF_NO_IOACCT, &bp);
+	error = _xfs_buf_alloc(target, &map, 1, flags, &bp);
 	if (error)
 		return error;
 
@@ -1059,7 +1010,6 @@ xfs_buf_rele_uncached(
 		spin_unlock(&bp->b_lock);
 		return;
 	}
-	__xfs_buf_ioacct_dec(bp);
 	spin_unlock(&bp->b_lock);
 	xfs_buf_free(bp);
 }
@@ -1078,19 +1028,11 @@ xfs_buf_rele_cached(
 	spin_lock(&bp->b_lock);
 	ASSERT(bp->b_hold >= 1);
 	if (bp->b_hold > 1) {
-		/*
-		 * Drop the in-flight state if the buffer is already on the LRU
-		 * and it holds the only reference. This is racy because we
-		 * haven't acquired the pag lock, but the use of _XBF_IN_FLIGHT
-		 * ensures the decrement occurs only once per-buf.
-		 */
-		if (--bp->b_hold == 1 && !list_empty(&bp->b_lru))
-			__xfs_buf_ioacct_dec(bp);
+		bp->b_hold--;
 		goto out_unlock;
 	}
 
 	/* we are asked to drop the last reference */
-	__xfs_buf_ioacct_dec(bp);
 	if (!(bp->b_flags & XBF_STALE) && atomic_read(&bp->b_lru_ref)) {
 		/*
 		 * If the buffer is added to the LRU, keep the reference to the
@@ -1370,6 +1312,8 @@ __xfs_buf_ioend(
 			bp->b_ops->verify_read(bp);
 		if (!bp->b_error)
 			bp->b_flags |= XBF_DONE;
+		if (bp->b_flags & XBF_READ_AHEAD)
+			percpu_counter_dec(&bp->b_target->bt_readahead_count);
 	} else {
 		if (!bp->b_error) {
 			bp->b_flags &= ~XBF_WRITE_FAIL;
@@ -1658,9 +1602,6 @@ xfs_buf_submit(
 	 */
 	bp->b_error = 0;
 
-	if (bp->b_flags & XBF_ASYNC)
-		xfs_buf_ioacct_inc(bp);
-
 	if ((bp->b_flags & XBF_WRITE) && !xfs_buf_verify_write(bp)) {
 		xfs_force_shutdown(bp->b_mount, SHUTDOWN_CORRUPT_INCORE);
 		xfs_buf_ioend(bp);
@@ -1786,9 +1727,8 @@ xfs_buftarg_wait(
 	struct xfs_buftarg	*btp)
 {
 	/*
-	 * First wait on the buftarg I/O count for all in-flight buffers to be
-	 * released. This is critical as new buffers do not make the LRU until
-	 * they are released.
+	 * First wait for all in-flight readahead buffers to be released.  This is
+	 * critical as new buffers do not make the LRU until they are released.
 	 *
 	 * Next, flush the buffer workqueue to ensure all completion processing
 	 * has finished. Just waiting on buffer locks is not sufficient for
@@ -1797,7 +1737,7 @@ xfs_buftarg_wait(
 	 * all reference counts have been dropped before we start walking the
 	 * LRU list.
 	 */
-	while (percpu_counter_sum(&btp->bt_io_count))
+	while (percpu_counter_sum(&btp->bt_readahead_count))
 		delay(100);
 	flush_workqueue(btp->bt_mount->m_buf_workqueue);
 }
@@ -1914,8 +1854,8 @@ xfs_destroy_buftarg(
 	struct xfs_buftarg	*btp)
 {
 	shrinker_free(btp->bt_shrinker);
-	ASSERT(percpu_counter_sum(&btp->bt_io_count) == 0);
-	percpu_counter_destroy(&btp->bt_io_count);
+	ASSERT(percpu_counter_sum(&btp->bt_readahead_count) == 0);
+	percpu_counter_destroy(&btp->bt_readahead_count);
 	list_lru_destroy(&btp->bt_lru);
 }
 
@@ -1969,7 +1909,7 @@ xfs_init_buftarg(
 
 	if (list_lru_init(&btp->bt_lru))
 		return -ENOMEM;
-	if (percpu_counter_init(&btp->bt_io_count, 0, GFP_KERNEL))
+	if (percpu_counter_init(&btp->bt_readahead_count, 0, GFP_KERNEL))
 		goto out_destroy_lru;
 
 	btp->bt_shrinker =
@@ -1983,7 +1923,7 @@ xfs_init_buftarg(
 	return 0;
 
 out_destroy_io_count:
-	percpu_counter_destroy(&btp->bt_io_count);
+	percpu_counter_destroy(&btp->bt_readahead_count);
 out_destroy_lru:
 	list_lru_destroy(&btp->bt_lru);
 	return -ENOMEM;
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 2e747555ad3fa..80e06eecaf56e 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -27,7 +27,6 @@ struct xfs_buf;
 #define XBF_READ	 (1u << 0) /* buffer intended for reading from device */
 #define XBF_WRITE	 (1u << 1) /* buffer intended for writing to device */
 #define XBF_READ_AHEAD	 (1u << 2) /* asynchronous read-ahead */
-#define XBF_NO_IOACCT	 (1u << 3) /* bypass I/O accounting (non-LRU bufs) */
 #define XBF_ASYNC	 (1u << 4) /* initiator will not wait for completion */
 #define XBF_DONE	 (1u << 5) /* all pages in the buffer uptodate */
 #define XBF_STALE	 (1u << 6) /* buffer has been staled, do not find it */
@@ -58,7 +57,6 @@ typedef unsigned int xfs_buf_flags_t;
 	{ XBF_READ,		"READ" }, \
 	{ XBF_WRITE,		"WRITE" }, \
 	{ XBF_READ_AHEAD,	"READ_AHEAD" }, \
-	{ XBF_NO_IOACCT,	"NO_IOACCT" }, \
 	{ XBF_ASYNC,		"ASYNC" }, \
 	{ XBF_DONE,		"DONE" }, \
 	{ XBF_STALE,		"STALE" }, \
@@ -77,7 +75,6 @@ typedef unsigned int xfs_buf_flags_t;
  * Internal state flags.
  */
 #define XFS_BSTATE_DISPOSE	 (1 << 0)	/* buffer being discarded */
-#define XFS_BSTATE_IN_FLIGHT	 (1 << 1)	/* I/O in flight */
 
 struct xfs_buf_cache {
 	struct rhashtable	bc_hash;
@@ -116,7 +113,7 @@ struct xfs_buftarg {
 	struct shrinker		*bt_shrinker;
 	struct list_lru		bt_lru;
 
-	struct percpu_counter	bt_io_count;
+	struct percpu_counter	bt_readahead_count;
 	struct ratelimit_state	bt_ioerror_rl;
 
 	/* Atomic write unit values */
diff --git a/fs/xfs/xfs_buf_mem.c b/fs/xfs/xfs_buf_mem.c
index 07bebbfb16ee1..5b64a2b3b113f 100644
--- a/fs/xfs/xfs_buf_mem.c
+++ b/fs/xfs/xfs_buf_mem.c
@@ -117,7 +117,7 @@ xmbuf_free(
 	struct xfs_buftarg	*btp)
 {
 	ASSERT(xfs_buftarg_is_mem(btp));
-	ASSERT(percpu_counter_sum(&btp->bt_io_count) == 0);
+	ASSERT(percpu_counter_sum(&btp->bt_readahead_count) == 0);
 
 	trace_xmbuf_free(btp);
 
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 477c5262cf912..b69356582b86f 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -181,14 +181,11 @@ xfs_readsb(
 
 	/*
 	 * Allocate a (locked) buffer to hold the superblock. This will be kept
-	 * around at all times to optimize access to the superblock. Therefore,
-	 * set XBF_NO_IOACCT to make sure it doesn't hold the buftarg count
-	 * elevated.
+	 * around at all times to optimize access to the superblock.
 	 */
 reread:
 	error = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR,
-				      BTOBB(sector_size), XBF_NO_IOACCT, &bp,
-				      buf_ops);
+				      BTOBB(sector_size), 0, &bp, buf_ops);
 	if (error) {
 		if (loud)
 			xfs_warn(mp, "SB validate failed with error %d.", error);
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index d8e6d073d64dc..57bef567e0116 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -1407,7 +1407,7 @@ xfs_rtmount_readsb(
 
 	/* m_blkbb_log is not set up yet */
 	error = xfs_buf_read_uncached(mp->m_rtdev_targp, XFS_RTSB_DADDR,
-			mp->m_sb.sb_blocksize >> BBSHIFT, XBF_NO_IOACCT, &bp,
+			mp->m_sb.sb_blocksize >> BBSHIFT, 0, &bp,
 			&xfs_rtsb_buf_ops);
 	if (error) {
 		xfs_warn(mp, "rt sb validate failed with error %d.", error);

From 9b47d37496e2669078c8616334e5a7200f91681a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 24 Feb 2025 15:48:55 -0800
Subject: [PATCH 0556/1173] xfs: remove the XBF_STALE check from
 xfs_buf_rele_cached

xfs_buf_stale already set b_lru_ref to 0, and thus prevents the buffer
from moving to the LRU.  Remove the duplicate check.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_buf.c | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index e161f3ab41087..5d560e9073f42 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -99,12 +99,6 @@ xfs_buf_stale(
 	 */
 	bp->b_flags &= ~_XBF_DELWRI_Q;
 
-	/*
-	 * Once the buffer is marked stale and unlocked, a subsequent lookup
-	 * could reset b_flags. There is no guarantee that the buffer is
-	 * unaccounted (released to LRU) before that occurs. Drop in-flight
-	 * status now to preserve accounting consistency.
-	 */
 	spin_lock(&bp->b_lock);
 	atomic_set(&bp->b_lru_ref, 0);
 	if (!(bp->b_state & XFS_BSTATE_DISPOSE) &&
@@ -1033,7 +1027,7 @@ xfs_buf_rele_cached(
 	}
 
 	/* we are asked to drop the last reference */
-	if (!(bp->b_flags & XBF_STALE) && atomic_read(&bp->b_lru_ref)) {
+	if (atomic_read(&bp->b_lru_ref)) {
 		/*
 		 * If the buffer is added to the LRU, keep the reference to the
 		 * buffer for the LRU and clear the (now stale) dispose list

From de2c211868b9424f9aa9b3432c4430825bafb41b Mon Sep 17 00:00:00 2001
From: Philo Lu <lulie@linux.alibaba.com>
Date: Sat, 22 Feb 2025 11:35:18 +0800
Subject: [PATCH 0557/1173] ipvs: Always clear ipvs_property flag in
 skb_scrub_packet()

We found an issue when using bpf_redirect with ipvs NAT mode after
commit ff70202b2d1a ("dev_forward_skb: do not scrub skb mark within
the same name space"). Particularly, we use bpf_redirect to return
the skb directly back to the netif it comes from, i.e., xnet is
false in skb_scrub_packet(), and then ipvs_property is preserved
and SNAT is skipped in the rx path.

ipvs_property has been already cleared when netns is changed in
commit 2b5ec1a5f973 ("netfilter/ipvs: clear ipvs_property flag when
SKB net namespace changed"). This patch just clears it in spite of
netns.

Fixes: 2b5ec1a5f973 ("netfilter/ipvs: clear ipvs_property flag when SKB net namespace changed")
Signed-off-by: Philo Lu <lulie@linux.alibaba.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Link: https://patch.msgid.link/20250222033518.126087-1-lulie@linux.alibaba.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/core/skbuff.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 7b03b64fdcb27..b1c81687e9d82 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -6033,11 +6033,11 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet)
 	skb->offload_fwd_mark = 0;
 	skb->offload_l3_fwd_mark = 0;
 #endif
+	ipvs_reset(skb);
 
 	if (!xnet)
 		return;
 
-	ipvs_reset(skb);
 	skb->mark = 0;
 	skb_clear_tstamp(skb);
 }

From bc50682128bde778a1ddc457a02d92a637c20c6f Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Sat, 22 Feb 2025 12:28:04 -0500
Subject: [PATCH 0558/1173] MAINTAINERS: socket timestamping: add Jason Xing as
 reviewer

Jason has been helping as reviewer for this area already, and has
contributed various features directly, notably BPF timestamping.

Also extend coverage to all timestamping tests, including those new
with BPF timestamping.

Link: https://lore.kernel.org/netdev/20250220072940.99994-1-kerneljasonxing@gmail.com/
Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Link: https://patch.msgid.link/20250222172839.642079-1-willemdebruijn.kernel@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 MAINTAINERS | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index ac15093537c6b..c92bcd02049e6 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -21923,10 +21923,13 @@ F:	sound/soc/uniphier/
 
 SOCKET TIMESTAMPING
 M:	Willem de Bruijn <willemdebruijn.kernel@gmail.com>
+R:	Jason Xing <kernelxing@tencent.com>
 S:	Maintained
 F:	Documentation/networking/timestamping.rst
 F:	include/linux/net_tstamp.h
 F:	include/uapi/linux/net_tstamp.h
+F:	tools/testing/selftests/bpf/*/net_timestamping*
+F:	tools/testing/selftests/net/*timestamp*
 F:	tools/testing/selftests/net/so_txtime.c
 
 SOEKRIS NET48XX LED SUPPORT

From 56a677293509b2a0d39ac8d02b583c1ab1fe4d94 Mon Sep 17 00:00:00 2001
From: Bard Liao <yung-chuan.liao@linux.intel.com>
Date: Tue, 25 Feb 2025 17:37:15 +0800
Subject: [PATCH 0559/1173] ASoC: SOF: Intel: don't check number of sdw links
 when set dmic_fixup
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, we assume that the PCH DMIC pins are pin-muxed with SoundWire
links. However, we do see a HW design that use PCH DMIC along with 3
SoundWire links. Remove the check now.
With this change the PCM DMIC will be presented if it is reported by the
BIOS irrespective of whether there are SDW links present or not.

Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Reviewed-by: Péter Ujfalusi <peter.ujfalusi@linux.intel.com>
Link: https://patch.msgid.link/20250225093716.67240-2-yung-chuan.liao@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/intel/hda.c | 18 ++----------------
 1 file changed, 2 insertions(+), 16 deletions(-)

diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c
index be689f6e10c81..a1ccd95da8bb7 100644
--- a/sound/soc/sof/intel/hda.c
+++ b/sound/soc/sof/intel/hda.c
@@ -1312,22 +1312,8 @@ struct snd_soc_acpi_mach *hda_machine_select(struct snd_sof_dev *sdev)
 		/* report to machine driver if any DMICs are found */
 		mach->mach_params.dmic_num = check_dmic_num(sdev);
 
-		if (sdw_mach_found) {
-			/*
-			 * DMICs use up to 4 pins and are typically pin-muxed with SoundWire
-			 * link 2 and 3, or link 1 and 2, thus we only try to enable dmics
-			 * if all conditions are true:
-			 * a) 2 or fewer links are used by SoundWire
-			 * b) the NHLT table reports the presence of microphones
-			 */
-			if (hweight_long(mach->link_mask) <= 2)
-				dmic_fixup = true;
-			else
-				mach->mach_params.dmic_num = 0;
-		} else {
-			if (mach->tplg_quirk_mask & SND_SOC_ACPI_TPLG_INTEL_DMIC_NUMBER)
-				dmic_fixup = true;
-		}
+		if (sdw_mach_found || mach->tplg_quirk_mask & SND_SOC_ACPI_TPLG_INTEL_DMIC_NUMBER)
+			dmic_fixup = true;
 
 		if (tplg_fixup &&
 		    dmic_fixup &&

From 4bcef04ca67fa8c46591a211885bb9c37f25dbbd Mon Sep 17 00:00:00 2001
From: Bard Liao <yung-chuan.liao@linux.intel.com>
Date: Tue, 25 Feb 2025 17:37:16 +0800
Subject: [PATCH 0560/1173] ASoC: Intel: sof_sdw: warn both sdw and pch dmic
 are used
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Typically, SoundWire MIC and PCH DMIC will not coexist. However, we may
want to use both of them in some special cases. Add a warning to let
users know that SoundWire MIC and PCH DMIC are both present and they
could overwrite it with kernel params.

Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Reviewed-by: Péter Ujfalusi <peter.ujfalusi@linux.intel.com>
Link: https://patch.msgid.link/20250225093716.67240-3-yung-chuan.liao@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/sof_sdw.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c
index 203b07d4d833c..c13064c777261 100644
--- a/sound/soc/intel/boards/sof_sdw.c
+++ b/sound/soc/intel/boards/sof_sdw.c
@@ -803,7 +803,9 @@ static int create_sdw_dailink(struct snd_soc_card *card,
 			      int *be_id, struct snd_soc_codec_conf **codec_conf)
 {
 	struct device *dev = card->dev;
+	struct snd_soc_acpi_mach *mach = dev_get_platdata(card->dev);
 	struct asoc_sdw_mc_private *ctx = snd_soc_card_get_drvdata(card);
+	struct snd_soc_acpi_mach_params *mach_params = &mach->mach_params;
 	struct intel_mc_ctx *intel_ctx = (struct intel_mc_ctx *)ctx->private;
 	struct asoc_sdw_endpoint *sof_end;
 	int stream;
@@ -900,6 +902,11 @@ static int create_sdw_dailink(struct snd_soc_card *card,
 
 			codecs[j].name = sof_end->codec_name;
 			codecs[j].dai_name = sof_end->dai_info->dai_name;
+			if (sof_end->dai_info->dai_type == SOC_SDW_DAI_TYPE_MIC &&
+			    mach_params->dmic_num > 0) {
+				dev_warn(dev,
+					 "Both SDW DMIC and PCH DMIC are present, if incorrect, please set kernel params snd_sof_intel_hda_generic dmic_num=0 to disable PCH DMIC\n");
+			}
 			j++;
 		}
 

From fe37c699ae3eed6e02ee55fbf5cb9ceb7fcfd76c Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Thu, 6 Feb 2025 14:18:44 -0500
Subject: [PATCH 0561/1173] x86/nmi: Add an emergency handler in nmi_desc & use
 it in nmi_shootdown_cpus()

Depending on the type of panics, it was found that the
__register_nmi_handler() function can be called in NMI context from
nmi_shootdown_cpus() leading to a lockdep splat:

  WARNING: inconsistent lock state
  inconsistent {INITIAL USE} -> {IN-NMI} usage.

   lock(&nmi_desc[0].lock);
   <Interrupt>
     lock(&nmi_desc[0].lock);

  Call Trace:
    _raw_spin_lock_irqsave
    __register_nmi_handler
    nmi_shootdown_cpus
    kdump_nmi_shootdown_cpus
    native_machine_crash_shutdown
    __crash_kexec

In this particular case, the following panic message was printed before:

  Kernel panic - not syncing: Fatal hardware error!

This message seemed to be given out from __ghes_panic() running in
NMI context.

The __register_nmi_handler() function which takes the nmi_desc lock
with irq disabled shouldn't be called from NMI context as this can
lead to deadlock.

The nmi_shootdown_cpus() function can only be invoked once. After the
first invocation, all other CPUs should be stuck in the newly added
crash_nmi_callback() and cannot respond to a second NMI.

Fix it by adding a new emergency NMI handler to the nmi_desc
structure and provide a new set_emergency_nmi_handler() helper to set
crash_nmi_callback() in any context. The new emergency handler will
preempt other handlers in the linked list. That will eliminate the need
to take any lock and serve the panic in NMI use case.

Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Rik van Riel <riel@surriel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20250206191844.131700-1-longman@redhat.com
---
 arch/x86/include/asm/nmi.h |  2 ++
 arch/x86/kernel/nmi.c      | 42 ++++++++++++++++++++++++++++++++++++++
 arch/x86/kernel/reboot.c   | 10 +++------
 3 files changed, 47 insertions(+), 7 deletions(-)

diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index 41a0ebb699ec6..f677382093f36 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -56,6 +56,8 @@ int __register_nmi_handler(unsigned int, struct nmiaction *);
 
 void unregister_nmi_handler(unsigned int, const char *);
 
+void set_emergency_nmi_handler(unsigned int type, nmi_handler_t handler);
+
 void stop_nmi(void);
 void restart_nmi(void);
 void local_touch_nmi(void);
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index ed163c8c8604e..9a95d00f14233 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -40,8 +40,12 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/nmi.h>
 
+/*
+ * An emergency handler can be set in any context including NMI
+ */
 struct nmi_desc {
 	raw_spinlock_t lock;
+	nmi_handler_t emerg_handler;
 	struct list_head head;
 };
 
@@ -132,9 +136,22 @@ static void nmi_check_duration(struct nmiaction *action, u64 duration)
 static int nmi_handle(unsigned int type, struct pt_regs *regs)
 {
 	struct nmi_desc *desc = nmi_to_desc(type);
+	nmi_handler_t ehandler;
 	struct nmiaction *a;
 	int handled=0;
 
+	/*
+	 * Call the emergency handler, if set
+	 *
+	 * In the case of crash_nmi_callback() emergency handler, it will
+	 * return in the case of the crashing CPU to enable it to complete
+	 * other necessary crashing actions ASAP. Other handlers in the
+	 * linked list won't need to be run.
+	 */
+	ehandler = desc->emerg_handler;
+	if (ehandler)
+		return ehandler(type, regs);
+
 	rcu_read_lock();
 
 	/*
@@ -224,6 +241,31 @@ void unregister_nmi_handler(unsigned int type, const char *name)
 }
 EXPORT_SYMBOL_GPL(unregister_nmi_handler);
 
+/**
+ * set_emergency_nmi_handler - Set emergency handler
+ * @type:    NMI type
+ * @handler: the emergency handler to be stored
+ *
+ * Set an emergency NMI handler which, if set, will preempt all the other
+ * handlers in the linked list. If a NULL handler is passed in, it will clear
+ * it. It is expected that concurrent calls to this function will not happen
+ * or the system is screwed beyond repair.
+ */
+void set_emergency_nmi_handler(unsigned int type, nmi_handler_t handler)
+{
+	struct nmi_desc *desc = nmi_to_desc(type);
+
+	if (WARN_ON_ONCE(desc->emerg_handler == handler))
+		return;
+	desc->emerg_handler = handler;
+
+	/*
+	 * Ensure the emergency handler is visible to other CPUs before
+	 * function return
+	 */
+	smp_wmb();
+}
+
 static void
 pci_serr_error(unsigned char reason, struct pt_regs *regs)
 {
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index dc1dd3f3e67fc..9aaac1f9f45b5 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -926,15 +926,11 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback)
 	shootdown_callback = callback;
 
 	atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
-	/* Would it be better to replace the trap vector here? */
-	if (register_nmi_handler(NMI_LOCAL, crash_nmi_callback,
-				 NMI_FLAG_FIRST, "crash"))
-		return;		/* Return what? */
+
 	/*
-	 * Ensure the new callback function is set before sending
-	 * out the NMI
+	 * Set emergency handler to preempt other handlers.
 	 */
-	wmb();
+	set_emergency_nmi_handler(NMI_LOCAL, crash_nmi_callback);
 
 	apic_send_IPI_allbutself(NMI_VECTOR);
 

From 88ec7eedbbd21cad38707620ad6c48a4e9a87c18 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Fri, 17 Jan 2025 07:19:11 -0800
Subject: [PATCH 0562/1173] perf/x86: Fix low freqency setting issue

Perf doesn't work at low frequencies:

  $ perf record -e cpu_core/instructions/ppp -F 120
  Error:
  The sys_perf_event_open() syscall returned with 22 (Invalid argument)
  for event (cpu_core/instructions/ppp).
  "dmesg | grep -i perf" may provide additional information.

The limit_period() check avoids a low sampling period on a counter. It
doesn't intend to limit the frequency.

The check in the x86_pmu_hw_config() should be limited to non-freq mode.
The attr.sample_period and attr.sample_freq are union. The
attr.sample_period should not be used to indicate the frequency mode.

Fixes: c46e665f0377 ("perf/x86: Add INST_RETIRED.ALL workarounds")
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250117151913.3043942-1-kan.liang@linux.intel.com
Closes: https://lore.kernel.org/lkml/20250115154949.3147-1-ravi.bangoria@amd.com/
---
 arch/x86/events/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 8f218ac0d445c..2092d615333da 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -628,7 +628,7 @@ int x86_pmu_hw_config(struct perf_event *event)
 	if (event->attr.type == event->pmu->type)
 		event->hw.config |= x86_pmu_get_event_config(event);
 
-	if (event->attr.sample_period && x86_pmu.limit_period) {
+	if (!event->attr.freq && x86_pmu.limit_period) {
 		s64 left = event->attr.sample_period;
 		x86_pmu.limit_period(event, &left);
 		if (left > event->attr.sample_period)

From 0d39844150546fa1415127c5fbae26db64070dd3 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Fri, 17 Jan 2025 07:19:12 -0800
Subject: [PATCH 0563/1173] perf/core: Fix low freq setting via IOC_PERIOD

A low attr::freq value cannot be set via IOC_PERIOD on some platforms.

The perf_event_check_period() introduced in:

  81ec3f3c4c4d ("perf/x86: Add check_period PMU callback")

was intended to check the period, rather than the frequency.
A low frequency may be mistakenly rejected by limit_period().

Fix it.

Fixes: 81ec3f3c4c4d ("perf/x86: Add check_period PMU callback")
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250117151913.3043942-2-kan.liang@linux.intel.com
Closes: https://lore.kernel.org/lkml/20250115154949.3147-1-ravi.bangoria@amd.com/
---
 kernel/events/core.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 086d46d096963..6364319e2f888 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5969,14 +5969,15 @@ static int _perf_event_period(struct perf_event *event, u64 value)
 	if (!value)
 		return -EINVAL;
 
-	if (event->attr.freq && value > sysctl_perf_event_sample_rate)
-		return -EINVAL;
-
-	if (perf_event_check_period(event, value))
-		return -EINVAL;
-
-	if (!event->attr.freq && (value & (1ULL << 63)))
-		return -EINVAL;
+	if (event->attr.freq) {
+		if (value > sysctl_perf_event_sample_rate)
+			return -EINVAL;
+	} else {
+		if (perf_event_check_period(event, value))
+			return -EINVAL;
+		if (value & (1ULL << 63))
+			return -EINVAL;
+	}
 
 	event_function_call(event, __perf_event_period, &value);
 

From 5bd566703e16b17d17f4fb648440d54f8967462c Mon Sep 17 00:00:00 2001
From: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Date: Fri, 21 Feb 2025 13:33:52 -0800
Subject: [PATCH 0564/1173] drm/xe/oa: Allow oa_exponent value of 0

OA exponent value of 0 is a valid value for periodic reports. Allow user
to pass 0 for the OA sampling interval since it gets converted to 2 gt
clock ticks.

v2: Update the check in xe_oa_stream_init as well (Ashutosh)
v3: Fix mi-rpc failure by setting default exponent to -1 (CI)
v4: Add the Fixes tag

Fixes: b6fd51c62119 ("drm/xe/oa/uapi: Define and parse OA stream properties")
Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250221213352.1712932-1-umesh.nerlige.ramappa@intel.com
(cherry picked from commit 30341f0b8ea71725cc4ab2c43e3a3b749892fc92)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_oa.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c
index fa873f3d0a9d1..eb6cd91e1e226 100644
--- a/drivers/gpu/drm/xe/xe_oa.c
+++ b/drivers/gpu/drm/xe/xe_oa.c
@@ -1689,7 +1689,7 @@ static int xe_oa_stream_init(struct xe_oa_stream *stream,
 	stream->oa_buffer.format = &stream->oa->oa_formats[param->oa_format];
 
 	stream->sample = param->sample;
-	stream->periodic = param->period_exponent > 0;
+	stream->periodic = param->period_exponent >= 0;
 	stream->period_exponent = param->period_exponent;
 	stream->no_preempt = param->no_preempt;
 	stream->wait_num_reports = param->wait_num_reports;
@@ -1970,6 +1970,7 @@ int xe_oa_stream_open_ioctl(struct drm_device *dev, u64 data, struct drm_file *f
 	}
 
 	param.xef = xef;
+	param.period_exponent = -1;
 	ret = xe_oa_user_extensions(oa, XE_OA_USER_EXTN_FROM_OPEN, data, 0, &param);
 	if (ret)
 		return ret;
@@ -2024,7 +2025,7 @@ int xe_oa_stream_open_ioctl(struct drm_device *dev, u64 data, struct drm_file *f
 		goto err_exec_q;
 	}
 
-	if (param.period_exponent > 0) {
+	if (param.period_exponent >= 0) {
 		u64 oa_period, oa_freq_hz;
 
 		/* Requesting samples from OAG buffer is a privileged operation */

From c4f23a9d6e7314060ccf5f089eda179cdcc3b36a Mon Sep 17 00:00:00 2001
From: liuye <liuye@kylinos.cn>
Date: Tue, 14 Jan 2025 16:26:50 +0800
Subject: [PATCH 0565/1173] selftests/x86/lam: Fix minor memory in do_uring()

Exception branch returns without freeing 'fi'.

Signed-off-by: liuye <liuye@kylinos.cn>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250114082650.113105-1-liuye@kylinos.cn
---
 tools/testing/selftests/x86/lam.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/x86/lam.c b/tools/testing/selftests/x86/lam.c
index 4d4a76532dc9a..309c93e15aba2 100644
--- a/tools/testing/selftests/x86/lam.c
+++ b/tools/testing/selftests/x86/lam.c
@@ -596,8 +596,10 @@ int do_uring(unsigned long lam)
 	fi->file_fd = file_fd;
 
 	ring = malloc(sizeof(*ring));
-	if (!ring)
+	if (!ring) {
+		free(fi);
 		return 1;
+	}
 
 	memset(ring, 0, sizeof(struct io_ring));
 

From fe08b7d5085a9774abc30c26d5aebc5b9cdd6091 Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Tue, 25 Feb 2025 13:18:42 +0000
Subject: [PATCH 0566/1173] firmware: cs_dsp: Remove async regmap writes

Change calls to async regmap write functions to use the normal
blocking writes so that the cs35l56 driver can use spi_bus_lock() to
gain exclusive access to the SPI bus.

As this is part of a fix, it makes only the minimal change to swap the
functions to the blocking equivalents. There's no need to risk
reworking the buffer allocation logic that is now partially redundant.

The async writes are a 12-year-old workaround for inefficiency of
synchronous writes in the SPI subsystem. The SPI subsystem has since
been changed to avoid the overheads, so this workaround should not be
necessary.

The cs35l56 driver needs to use spi_bus_lock() prevent bus activity
while it is soft-resetting the cs35l56. But spi_bus_lock() is
incompatible with spi_async() calls, which will fail with -EBUSY.

Fixes: 8a731fd37f8b ("ASoC: cs35l56: Move utility functions to shared file")
Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://patch.msgid.link/20250225131843.113752-2-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/firmware/cirrus/cs_dsp.c | 24 ++++++------------------
 1 file changed, 6 insertions(+), 18 deletions(-)

diff --git a/drivers/firmware/cirrus/cs_dsp.c b/drivers/firmware/cirrus/cs_dsp.c
index 5365e9a430007..42433c19eb308 100644
--- a/drivers/firmware/cirrus/cs_dsp.c
+++ b/drivers/firmware/cirrus/cs_dsp.c
@@ -1609,8 +1609,8 @@ static int cs_dsp_load(struct cs_dsp *dsp, const struct firmware *firmware,
 				goto out_fw;
 			}
 
-			ret = regmap_raw_write_async(regmap, reg, buf->buf,
-						     le32_to_cpu(region->len));
+			ret = regmap_raw_write(regmap, reg, buf->buf,
+					       le32_to_cpu(region->len));
 			if (ret != 0) {
 				cs_dsp_err(dsp,
 					   "%s.%d: Failed to write %d bytes at %d in %s: %d\n",
@@ -1625,12 +1625,6 @@ static int cs_dsp_load(struct cs_dsp *dsp, const struct firmware *firmware,
 		regions++;
 	}
 
-	ret = regmap_async_complete(regmap);
-	if (ret != 0) {
-		cs_dsp_err(dsp, "Failed to complete async write: %d\n", ret);
-		goto out_fw;
-	}
-
 	if (pos > firmware->size)
 		cs_dsp_warn(dsp, "%s.%d: %zu bytes at end of file\n",
 			    file, regions, pos - firmware->size);
@@ -1638,7 +1632,6 @@ static int cs_dsp_load(struct cs_dsp *dsp, const struct firmware *firmware,
 	cs_dsp_debugfs_save_wmfwname(dsp, file);
 
 out_fw:
-	regmap_async_complete(regmap);
 	cs_dsp_buf_free(&buf_list);
 
 	if (ret == -EOVERFLOW)
@@ -2326,8 +2319,8 @@ static int cs_dsp_load_coeff(struct cs_dsp *dsp, const struct firmware *firmware
 			cs_dsp_dbg(dsp, "%s.%d: Writing %d bytes at %x\n",
 				   file, blocks, le32_to_cpu(blk->len),
 				   reg);
-			ret = regmap_raw_write_async(regmap, reg, buf->buf,
-						     le32_to_cpu(blk->len));
+			ret = regmap_raw_write(regmap, reg, buf->buf,
+					       le32_to_cpu(blk->len));
 			if (ret != 0) {
 				cs_dsp_err(dsp,
 					   "%s.%d: Failed to write to %x in %s: %d\n",
@@ -2339,10 +2332,6 @@ static int cs_dsp_load_coeff(struct cs_dsp *dsp, const struct firmware *firmware
 		blocks++;
 	}
 
-	ret = regmap_async_complete(regmap);
-	if (ret != 0)
-		cs_dsp_err(dsp, "Failed to complete async write: %d\n", ret);
-
 	if (pos > firmware->size)
 		cs_dsp_warn(dsp, "%s.%d: %zu bytes at end of file\n",
 			    file, blocks, pos - firmware->size);
@@ -2350,7 +2339,6 @@ static int cs_dsp_load_coeff(struct cs_dsp *dsp, const struct firmware *firmware
 	cs_dsp_debugfs_save_binname(dsp, file);
 
 out_fw:
-	regmap_async_complete(regmap);
 	cs_dsp_buf_free(&buf_list);
 
 	if (ret == -EOVERFLOW)
@@ -2561,8 +2549,8 @@ static int cs_dsp_adsp2_enable_core(struct cs_dsp *dsp)
 {
 	int ret;
 
-	ret = regmap_update_bits_async(dsp->regmap, dsp->base + ADSP2_CONTROL,
-				       ADSP2_SYS_ENA, ADSP2_SYS_ENA);
+	ret = regmap_update_bits(dsp->regmap, dsp->base + ADSP2_CONTROL,
+				 ADSP2_SYS_ENA, ADSP2_SYS_ENA);
 	if (ret != 0)
 		return ret;
 

From 769c1b79295c38d60fde4c0a8f5f31e01360c54f Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Tue, 25 Feb 2025 13:18:43 +0000
Subject: [PATCH 0567/1173] ASoC: cs35l56: Prevent races when soft-resetting
 using SPI control

When SPI is used for control, the driver must hold the SPI bus lock
while issuing the sequence of writes to perform a soft reset.

>From the time the driver writes the SYSTEM_RESET command until the
driver does a write to terminate the reset, there must not be any
activity on the SPI bus lines. If there is any SPI activity during the
soft-reset, another soft-reset will be triggered. The state of the SPI
chip select is irrelevant.

A repeated soft-reset does not in itself cause any problems, and it is
not an infinite loop. The problem is a race between these resets and
the driver polling for boot completion. There is a time window between
soft resets where the driver could read HALO_STATE as 2 (fully booted)
while the chip is actually soft-resetting. Although this window is
small, it is long enough that it is possible to hit it in normal
operation.

To prevent this race and ensure the chip really is fully booted, the
driver calls spi_bus_lock() to prevent other activity while resetting.
It then issues the SYSTEM_RESET mailbox command. After allowing
sufficient time for reset to take effect, the driver issues a PING
mailbox command, which will force completion of the full soft-reset
sequence. The SPI bus lock can then be released. The mailbox is
checked for any boot or wakeup response from the firmware, before the
value in HALO_STATE will be trusted.

This does not affect SoundWire or I2C control.

Fixes: 8a731fd37f8b ("ASoC: cs35l56: Move utility functions to shared file")
Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://patch.msgid.link/20250225131843.113752-3-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/cs35l56.h           | 31 ++++++++++++
 sound/pci/hda/cs35l56_hda_spi.c   |  3 ++
 sound/soc/codecs/cs35l56-shared.c | 80 +++++++++++++++++++++++++++++++
 sound/soc/codecs/cs35l56-spi.c    |  3 ++
 4 files changed, 117 insertions(+)

diff --git a/include/sound/cs35l56.h b/include/sound/cs35l56.h
index 3dc7a1551ac35..5d653a3491d07 100644
--- a/include/sound/cs35l56.h
+++ b/include/sound/cs35l56.h
@@ -12,6 +12,7 @@
 #include <linux/firmware/cirrus/cs_dsp.h>
 #include <linux/regulator/consumer.h>
 #include <linux/regmap.h>
+#include <linux/spi/spi.h>
 #include <sound/cs-amp-lib.h>
 
 #define CS35L56_DEVID					0x0000000
@@ -61,6 +62,7 @@
 #define CS35L56_IRQ1_MASK_8				0x000E0AC
 #define CS35L56_IRQ1_MASK_18				0x000E0D4
 #define CS35L56_IRQ1_MASK_20				0x000E0DC
+#define CS35L56_DSP_MBOX_1_RAW				0x0011000
 #define CS35L56_DSP_VIRTUAL1_MBOX_1			0x0011020
 #define CS35L56_DSP_VIRTUAL1_MBOX_2			0x0011024
 #define CS35L56_DSP_VIRTUAL1_MBOX_3			0x0011028
@@ -224,6 +226,7 @@
 #define CS35L56_HALO_STATE_SHUTDOWN			1
 #define CS35L56_HALO_STATE_BOOT_DONE			2
 
+#define CS35L56_MBOX_CMD_PING				0x0A000000
 #define CS35L56_MBOX_CMD_AUDIO_PLAY			0x0B000001
 #define CS35L56_MBOX_CMD_AUDIO_PAUSE			0x0B000002
 #define CS35L56_MBOX_CMD_AUDIO_REINIT			0x0B000003
@@ -254,6 +257,16 @@
 #define CS35L56_NUM_BULK_SUPPLIES			3
 #define CS35L56_NUM_DSP_REGIONS				5
 
+/* Additional margin for SYSTEM_RESET to control port ready on SPI */
+#define CS35L56_SPI_RESET_TO_PORT_READY_US (CS35L56_CONTROL_PORT_READY_US + 2500)
+
+struct cs35l56_spi_payload {
+	__be32	addr;
+	__be16	pad;
+	__be32	value;
+} __packed;
+static_assert(sizeof(struct cs35l56_spi_payload) == 10);
+
 struct cs35l56_base {
 	struct device *dev;
 	struct regmap *regmap;
@@ -269,6 +282,7 @@ struct cs35l56_base {
 	s8 cal_index;
 	struct cirrus_amp_cal_data cal_data;
 	struct gpio_desc *reset_gpio;
+	struct cs35l56_spi_payload *spi_payload_buf;
 };
 
 static inline bool cs35l56_is_otp_register(unsigned int reg)
@@ -276,6 +290,23 @@ static inline bool cs35l56_is_otp_register(unsigned int reg)
 	return (reg >> 16) == 3;
 }
 
+static inline int cs35l56_init_config_for_spi(struct cs35l56_base *cs35l56,
+					      struct spi_device *spi)
+{
+	cs35l56->spi_payload_buf = devm_kzalloc(&spi->dev,
+						sizeof(*cs35l56->spi_payload_buf),
+						GFP_KERNEL | GFP_DMA);
+	if (!cs35l56->spi_payload_buf)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static inline bool cs35l56_is_spi(struct cs35l56_base *cs35l56)
+{
+	return IS_ENABLED(CONFIG_SPI_MASTER) && !!cs35l56->spi_payload_buf;
+}
+
 extern const struct regmap_config cs35l56_regmap_i2c;
 extern const struct regmap_config cs35l56_regmap_spi;
 extern const struct regmap_config cs35l56_regmap_sdw;
diff --git a/sound/pci/hda/cs35l56_hda_spi.c b/sound/pci/hda/cs35l56_hda_spi.c
index d4ee5bb7c4866..9035784669053 100644
--- a/sound/pci/hda/cs35l56_hda_spi.c
+++ b/sound/pci/hda/cs35l56_hda_spi.c
@@ -22,6 +22,9 @@ static int cs35l56_hda_spi_probe(struct spi_device *spi)
 		return -ENOMEM;
 
 	cs35l56->base.dev = &spi->dev;
+	ret = cs35l56_init_config_for_spi(&cs35l56->base, spi);
+	if (ret)
+		return ret;
 
 #ifdef CS35L56_WAKE_HOLD_TIME_US
 	cs35l56->base.can_hibernate = true;
diff --git a/sound/soc/codecs/cs35l56-shared.c b/sound/soc/codecs/cs35l56-shared.c
index e0ed4fc11155a..e28bfefa72f33 100644
--- a/sound/soc/codecs/cs35l56-shared.c
+++ b/sound/soc/codecs/cs35l56-shared.c
@@ -10,6 +10,7 @@
 #include <linux/gpio/consumer.h>
 #include <linux/regmap.h>
 #include <linux/regulator/consumer.h>
+#include <linux/spi/spi.h>
 #include <linux/types.h>
 #include <sound/cs-amp-lib.h>
 
@@ -303,6 +304,79 @@ void cs35l56_wait_min_reset_pulse(void)
 }
 EXPORT_SYMBOL_NS_GPL(cs35l56_wait_min_reset_pulse, "SND_SOC_CS35L56_SHARED");
 
+static const struct {
+	u32 addr;
+	u32 value;
+} cs35l56_spi_system_reset_stages[] = {
+	{ .addr = CS35L56_DSP_VIRTUAL1_MBOX_1, .value = CS35L56_MBOX_CMD_SYSTEM_RESET },
+	/* The next write is necessary to delimit the soft reset */
+	{ .addr = CS35L56_DSP_MBOX_1_RAW, .value = CS35L56_MBOX_CMD_PING },
+};
+
+static void cs35l56_spi_issue_bus_locked_reset(struct cs35l56_base *cs35l56_base,
+					       struct spi_device *spi)
+{
+	struct cs35l56_spi_payload *buf = cs35l56_base->spi_payload_buf;
+	struct spi_transfer t = {
+		.tx_buf		= buf,
+		.len		= sizeof(*buf),
+	};
+	struct spi_message m;
+	int i, ret;
+
+	for (i = 0; i < ARRAY_SIZE(cs35l56_spi_system_reset_stages); i++) {
+		buf->addr = cpu_to_be32(cs35l56_spi_system_reset_stages[i].addr);
+		buf->value = cpu_to_be32(cs35l56_spi_system_reset_stages[i].value);
+		spi_message_init_with_transfers(&m, &t, 1);
+		ret = spi_sync_locked(spi, &m);
+		if (ret)
+			dev_warn(cs35l56_base->dev, "spi_sync failed: %d\n", ret);
+
+		usleep_range(CS35L56_SPI_RESET_TO_PORT_READY_US,
+			     2 * CS35L56_SPI_RESET_TO_PORT_READY_US);
+	}
+}
+
+static void cs35l56_spi_system_reset(struct cs35l56_base *cs35l56_base)
+{
+	struct spi_device *spi = to_spi_device(cs35l56_base->dev);
+	unsigned int val;
+	int read_ret, ret;
+
+	/*
+	 * There must not be any other SPI bus activity while the amp is
+	 * soft-resetting.
+	 */
+	ret = spi_bus_lock(spi->controller);
+	if (ret) {
+		dev_warn(cs35l56_base->dev, "spi_bus_lock failed: %d\n", ret);
+		return;
+	}
+
+	cs35l56_spi_issue_bus_locked_reset(cs35l56_base, spi);
+	spi_bus_unlock(spi->controller);
+
+	/*
+	 * Check firmware boot by testing for a response in MBOX_2.
+	 * HALO_STATE cannot be trusted yet because the reset sequence
+	 * can leave it with stale state. But MBOX is reset.
+	 * The regmap must remain in cache-only until the chip has
+	 * booted, so use a bypassed read.
+	 */
+	ret = read_poll_timeout(regmap_read_bypassed, read_ret,
+				(val > 0) && (val < 0xffffffff),
+				CS35L56_HALO_STATE_POLL_US,
+				CS35L56_HALO_STATE_TIMEOUT_US,
+				false,
+				cs35l56_base->regmap,
+				CS35L56_DSP_VIRTUAL1_MBOX_2,
+				&val);
+	if (ret) {
+		dev_err(cs35l56_base->dev, "SPI reboot timed out(%d): MBOX2=%#x\n",
+			read_ret, val);
+	}
+}
+
 static const struct reg_sequence cs35l56_system_reset_seq[] = {
 	REG_SEQ0(CS35L56_DSP1_HALO_STATE, 0),
 	REG_SEQ0(CS35L56_DSP_VIRTUAL1_MBOX_1, CS35L56_MBOX_CMD_SYSTEM_RESET),
@@ -315,6 +389,12 @@ void cs35l56_system_reset(struct cs35l56_base *cs35l56_base, bool is_soundwire)
 	 * accesses other than the controlled system reset sequence below.
 	 */
 	regcache_cache_only(cs35l56_base->regmap, true);
+
+	if (cs35l56_is_spi(cs35l56_base)) {
+		cs35l56_spi_system_reset(cs35l56_base);
+		return;
+	}
+
 	regmap_multi_reg_write_bypassed(cs35l56_base->regmap,
 					cs35l56_system_reset_seq,
 					ARRAY_SIZE(cs35l56_system_reset_seq));
diff --git a/sound/soc/codecs/cs35l56-spi.c b/sound/soc/codecs/cs35l56-spi.c
index c101134e85328..ca6c03a8766d3 100644
--- a/sound/soc/codecs/cs35l56-spi.c
+++ b/sound/soc/codecs/cs35l56-spi.c
@@ -33,6 +33,9 @@ static int cs35l56_spi_probe(struct spi_device *spi)
 
 	cs35l56->base.dev = &spi->dev;
 	cs35l56->base.can_hibernate = true;
+	ret = cs35l56_init_config_for_spi(&cs35l56->base, spi);
+	if (ret)
+		return ret;
 
 	ret = cs35l56_common_probe(cs35l56);
 	if (ret != 0)

From 8ec43c58d3be615a71548bc09148212013fb7e5f Mon Sep 17 00:00:00 2001
From: Harry Wentland <harry.wentland@amd.com>
Date: Thu, 19 Dec 2024 21:33:08 -0700
Subject: [PATCH 0568/1173] drm/vkms: Round fixp2int conversion in lerp_u16

fixp2int always rounds down, fixp2int_ceil rounds up. We need
the new fixp2int_round.

Signed-off-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Louis Chauvet <louis.chauvet@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241220043410.416867-3-alex.hung@amd.com
Signed-off-by: Louis Chauvet <louis.chauvet@bootlin.com>
---
 drivers/gpu/drm/vkms/vkms_composer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/vkms/vkms_composer.c b/drivers/gpu/drm/vkms/vkms_composer.c
index b20ac17057262..fa269d279e257 100644
--- a/drivers/gpu/drm/vkms/vkms_composer.c
+++ b/drivers/gpu/drm/vkms/vkms_composer.c
@@ -67,7 +67,7 @@ static u16 lerp_u16(u16 a, u16 b, s64 t)
 
 	s64 delta = drm_fixp_mul(b_fp - a_fp, t);
 
-	return drm_fixp2int(a_fp + delta);
+	return drm_fixp2int_round(a_fp + delta);
 }
 
 static s64 get_lut_index(const struct vkms_color_lut *lut, u16 channel_value)

From 889c57066ceee5e9172232da0608a8ac053bb6e5 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Tue, 25 Feb 2025 10:21:41 +0800
Subject: [PATCH 0569/1173] block: make segment size limit workable for > 4K
 PAGE_SIZE

Using PAGE_SIZE as a minimum expected DMA segment size in consideration
of devices which have a max DMA segment size of < 64k when used on 64k
PAGE_SIZE systems leads to devices not being able to probe such as
eMMC and Exynos UFS controller [0] [1] you can end up with a probe failure
as follows:

WARNING: CPU: 2 PID: 397 at block/blk-settings.c:339 blk_validate_limits+0x364/0x3c0

Ensure we use min(max_seg_size, seg_boundary_mask + 1) as the new min segment
size when max segment size is < PAGE_SIZE for 16k and 64k base page size systems.

If anyone need to backport this patch, the following commits are depended:

	commit 6aeb4f836480 ("block: remove bio_add_pc_page")
	commit 02ee5d69e3ba ("block: remove blk_rq_bio_prep")
	commit b7175e24d6ac ("block: add a dma mapping iterator")

Link: https://lore.kernel.org/linux-block/20230612203314.17820-1-bvanassche@acm.org/ # [0]
Link: https://lore.kernel.org/linux-block/1d55e942-5150-de4c-3a02-c3d066f87028@acm.org/ # [1]
Cc: Yi Zhang <yi.zhang@redhat.com>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Keith Busch <kbusch@kernel.org>
Tested-by: Paul Bunyan <pbunyan@redhat.com>
Reviewed-by: Daniel Gomez <da.gomez@kernel.org>
Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250225022141.2154581-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-merge.c      |  2 +-
 block/blk-settings.c   | 14 +++++++++++---
 block/blk.h            |  9 +++++++--
 include/linux/blkdev.h |  1 +
 4 files changed, 20 insertions(+), 6 deletions(-)

diff --git a/block/blk-merge.c b/block/blk-merge.c
index c7c85e10cf9cb..1d1589c352976 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -329,7 +329,7 @@ int bio_split_rw_at(struct bio *bio, const struct queue_limits *lim,
 
 		if (nsegs < lim->max_segments &&
 		    bytes + bv.bv_len <= max_bytes &&
-		    bv.bv_offset + bv.bv_len <= PAGE_SIZE) {
+		    bv.bv_offset + bv.bv_len <= lim->min_segment_size) {
 			nsegs++;
 			bytes += bv.bv_len;
 		} else {
diff --git a/block/blk-settings.c b/block/blk-settings.c
index c44dadc35e1ec..b9c6f0ec1c499 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -246,6 +246,7 @@ int blk_validate_limits(struct queue_limits *lim)
 {
 	unsigned int max_hw_sectors;
 	unsigned int logical_block_sectors;
+	unsigned long seg_size;
 	int err;
 
 	/*
@@ -303,7 +304,7 @@ int blk_validate_limits(struct queue_limits *lim)
 	max_hw_sectors = min_not_zero(lim->max_hw_sectors,
 				lim->max_dev_sectors);
 	if (lim->max_user_sectors) {
-		if (lim->max_user_sectors < PAGE_SIZE / SECTOR_SIZE)
+		if (lim->max_user_sectors < BLK_MIN_SEGMENT_SIZE / SECTOR_SIZE)
 			return -EINVAL;
 		lim->max_sectors = min(max_hw_sectors, lim->max_user_sectors);
 	} else if (lim->io_opt > (BLK_DEF_MAX_SECTORS_CAP << SECTOR_SHIFT)) {
@@ -341,7 +342,7 @@ int blk_validate_limits(struct queue_limits *lim)
 	 */
 	if (!lim->seg_boundary_mask)
 		lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
-	if (WARN_ON_ONCE(lim->seg_boundary_mask < PAGE_SIZE - 1))
+	if (WARN_ON_ONCE(lim->seg_boundary_mask < BLK_MIN_SEGMENT_SIZE - 1))
 		return -EINVAL;
 
 	/*
@@ -362,10 +363,17 @@ int blk_validate_limits(struct queue_limits *lim)
 		 */
 		if (!lim->max_segment_size)
 			lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
-		if (WARN_ON_ONCE(lim->max_segment_size < PAGE_SIZE))
+		if (WARN_ON_ONCE(lim->max_segment_size < BLK_MIN_SEGMENT_SIZE))
 			return -EINVAL;
 	}
 
+	/* setup min segment size for building new segment in fast path */
+	if (lim->seg_boundary_mask > lim->max_segment_size - 1)
+		seg_size = lim->max_segment_size;
+	else
+		seg_size = lim->seg_boundary_mask + 1;
+	lim->min_segment_size = min_t(unsigned int, seg_size, PAGE_SIZE);
+
 	/*
 	 * We require drivers to at least do logical block aligned I/O, but
 	 * historically could not check for that due to the separate calls
diff --git a/block/blk.h b/block/blk.h
index 90fa5f28ccabf..9cf9a0099416d 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -14,6 +14,7 @@
 struct elevator_type;
 
 #define	BLK_DEV_MAX_SECTORS	(LLONG_MAX >> 9)
+#define	BLK_MIN_SEGMENT_SIZE	4096
 
 /* Max future timer expiry for timeouts */
 #define BLK_MAX_TIMEOUT		(5 * HZ)
@@ -358,8 +359,12 @@ struct bio *bio_split_zone_append(struct bio *bio,
 static inline bool bio_may_need_split(struct bio *bio,
 		const struct queue_limits *lim)
 {
-	return lim->chunk_sectors || bio->bi_vcnt != 1 ||
-		bio->bi_io_vec->bv_len + bio->bi_io_vec->bv_offset > PAGE_SIZE;
+	if (lim->chunk_sectors)
+		return true;
+	if (bio->bi_vcnt != 1)
+		return true;
+	return bio->bi_io_vec->bv_len + bio->bi_io_vec->bv_offset >
+		lim->min_segment_size;
 }
 
 /**
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 248416ecd01c9..58ff5aca83b67 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -367,6 +367,7 @@ struct queue_limits {
 	unsigned int		max_sectors;
 	unsigned int		max_user_sectors;
 	unsigned int		max_segment_size;
+	unsigned int		min_segment_size;
 	unsigned int		physical_block_size;
 	unsigned int		logical_block_size;
 	unsigned int		alignment_offset;

From 9e7c6779e3530bbdd465214afcd13f19c33e51a2 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 25 Feb 2025 16:45:32 +0100
Subject: [PATCH 0570/1173] ALSA: hda/realtek: Fix wrong mic setup for ASUS
 VivoBook 15

ASUS VivoBook 15 with SSID 1043:1460 took an incorrect quirk via the
pin pattern matching for ASUS (ALC256_FIXUP_ASUS_MIC), resulting in
the two built-in mic pins (0x13 and 0x1b).  This had worked without
problems casually in the past because the right pin (0x1b) was picked
up as the primary device.  But since we fixed the pin enumeration for
other bugs, the bogus one (0x13) is picked up as the primary device,
hence the bug surfaced now.

For addressing the regression, this patch explicitly specifies the
quirk entry with ALC256_FIXUP_ASUS_MIC_NO_PRESENCE, which sets up only
the headset mic pin.

Fixes: 3b4309546b48 ("ALSA: hda: Fix headset detection failure due to unstable sort")
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219807
Link: https://patch.msgid.link/20250225154540.13543-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 224616fbec4fa..e5c80d4be535c 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10623,6 +10623,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x13b0, "ASUS Z550SA", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1427, "Asus Zenbook UX31E", ALC269VB_FIXUP_ASUS_ZENBOOK),
 	SND_PCI_QUIRK(0x1043, 0x1433, "ASUS GX650PY/PZ/PV/PU/PYV/PZV/PIV/PVV", ALC285_FIXUP_ASUS_I2C_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1043, 0x1460, "Asus VivoBook 15", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x1463, "Asus GA402X/GA402N", ALC285_FIXUP_ASUS_I2C_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1473, "ASUS GU604VI/VC/VE/VG/VJ/VQ/VU/VV/VY/VZ", ALC285_FIXUP_ASUS_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1483, "ASUS GU603VQ/VU/VV/VJ/VI", ALC285_FIXUP_ASUS_HEADSET_MIC),

From 6ebf05189dfc6d0d597c99a6448a4d1064439a18 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Tue, 25 Feb 2025 15:59:02 +0000
Subject: [PATCH 0571/1173] io_uring/net: save msg_control for compat

Match the compat part of io_sendmsg_copy_hdr() with its counterpart and
save msg_control.

Fixes: c55978024d123 ("io_uring/net: move receive multishot out of the generic msghdr path")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/2a8418821fe83d3b64350ad2b3c0303e9b732bbd.1740498502.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/net.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/io_uring/net.c b/io_uring/net.c
index 17852a6616ffe..5d0b56ff50eed 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -322,7 +322,9 @@ static int io_sendmsg_copy_hdr(struct io_kiocb *req,
 		if (unlikely(ret))
 			return ret;
 
-		return __get_compat_msghdr(&iomsg->msg, &cmsg, NULL);
+		ret = __get_compat_msghdr(&iomsg->msg, &cmsg, NULL);
+		sr->msg_control = iomsg->msg.msg_control_user;
+		return ret;
 	}
 #endif
 

From 00817f0f1c45b007965f5676b9a2013bb39c7228 Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Mon, 24 Feb 2025 17:13:30 -0800
Subject: [PATCH 0572/1173] nvme-ioctl: fix leaked requests on mapping error

All the callers assume nvme_map_user_request() frees the request on a
failure. This wasn't happening on invalid metadata or io_uring command
flags, so we've been leaking those requests.

Fixes: 23fd22e55b767b ("nvme: wire up fixed buffer support for nvme passthrough")
Fixes: 7c2fd76048e95d ("nvme: fix metadata handling in nvme-passthrough")
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Kanchan Joshi <joshi.k@samsung.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/ioctl.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index b1b46c2713e1c..24e2c702da7a2 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -128,8 +128,10 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer,
 	if (!nvme_ctrl_sgl_supported(ctrl))
 		dev_warn_once(ctrl->device, "using unchecked data buffer\n");
 	if (has_metadata) {
-		if (!supports_metadata)
-			return -EINVAL;
+		if (!supports_metadata) {
+			ret = -EINVAL;
+			goto out;
+		}
 		if (!nvme_ctrl_meta_sgl_supported(ctrl))
 			dev_warn_once(ctrl->device,
 				      "using unchecked metadata buffer\n");
@@ -139,8 +141,10 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer,
 		struct iov_iter iter;
 
 		/* fixedbufs is only for non-vectored io */
-		if (WARN_ON_ONCE(flags & NVME_IOCTL_VEC))
-			return -EINVAL;
+		if (WARN_ON_ONCE(flags & NVME_IOCTL_VEC)) {
+			ret = -EINVAL;
+			goto out;
+		}
 		ret = io_uring_cmd_import_fixed(ubuffer, bufflen,
 				rq_data_dir(req), &iter, ioucmd);
 		if (ret < 0)

From 91dcc66b34beb72dde8412421bdc1b4cd40e4fb8 Mon Sep 17 00:00:00 2001
From: "chr[]" <chris@rudorff.com>
Date: Wed, 12 Feb 2025 16:51:38 +0100
Subject: [PATCH 0573/1173] amdgpu/pm/legacy: fix suspend/resume issues

resume and irq handler happily races in set_power_state()

* amdgpu_legacy_dpm_compute_clocks() needs lock
* protect irq work handler
* fix dpm_enabled usage

v2: fix clang build, integrate Lijo's comments (Alex)

Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/2524
Fixes: 3712e7a49459 ("drm/amd/pm: unified lock protections in amdgpu_dpm.c")
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Tested-by: Maciej S. Szmigiero <mail@maciej.szmigiero.name> # on Oland PRO
Signed-off-by: chr[] <chris@rudorff.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit ee3dc9e204d271c9c7a8d4d38a0bce4745d33e71)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c    | 25 +++++++++++++-----
 .../gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c    |  8 ++++--
 drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c    | 26 ++++++++++++++-----
 3 files changed, 45 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c
index 67a8e22b1126d..e237ea1185a71 100644
--- a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c
+++ b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c
@@ -3042,6 +3042,7 @@ static int kv_dpm_hw_init(struct amdgpu_ip_block *ip_block)
 	if (!amdgpu_dpm)
 		return 0;
 
+	mutex_lock(&adev->pm.mutex);
 	kv_dpm_setup_asic(adev);
 	ret = kv_dpm_enable(adev);
 	if (ret)
@@ -3049,6 +3050,8 @@ static int kv_dpm_hw_init(struct amdgpu_ip_block *ip_block)
 	else
 		adev->pm.dpm_enabled = true;
 	amdgpu_legacy_dpm_compute_clocks(adev);
+	mutex_unlock(&adev->pm.mutex);
+
 	return ret;
 }
 
@@ -3066,32 +3069,42 @@ static int kv_dpm_suspend(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
 
+	cancel_work_sync(&adev->pm.dpm.thermal.work);
+
 	if (adev->pm.dpm_enabled) {
+		mutex_lock(&adev->pm.mutex);
+		adev->pm.dpm_enabled = false;
 		/* disable dpm */
 		kv_dpm_disable(adev);
 		/* reset the power state */
 		adev->pm.dpm.current_ps = adev->pm.dpm.requested_ps = adev->pm.dpm.boot_ps;
+		mutex_unlock(&adev->pm.mutex);
 	}
 	return 0;
 }
 
 static int kv_dpm_resume(struct amdgpu_ip_block *ip_block)
 {
-	int ret;
+	int ret = 0;
 	struct amdgpu_device *adev = ip_block->adev;
 
-	if (adev->pm.dpm_enabled) {
+	if (!amdgpu_dpm)
+		return 0;
+
+	if (!adev->pm.dpm_enabled) {
+		mutex_lock(&adev->pm.mutex);
 		/* asic init will reset to the boot state */
 		kv_dpm_setup_asic(adev);
 		ret = kv_dpm_enable(adev);
-		if (ret)
+		if (ret) {
 			adev->pm.dpm_enabled = false;
-		else
+		} else {
 			adev->pm.dpm_enabled = true;
-		if (adev->pm.dpm_enabled)
 			amdgpu_legacy_dpm_compute_clocks(adev);
+		}
+		mutex_unlock(&adev->pm.mutex);
 	}
-	return 0;
+	return ret;
 }
 
 static bool kv_dpm_is_idle(void *handle)
diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c
index e861355ebd75b..c7518b13e7879 100644
--- a/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c
+++ b/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c
@@ -1009,9 +1009,12 @@ void amdgpu_dpm_thermal_work_handler(struct work_struct *work)
 	enum amd_pm_state_type dpm_state = POWER_STATE_TYPE_INTERNAL_THERMAL;
 	int temp, size = sizeof(temp);
 
-	if (!adev->pm.dpm_enabled)
-		return;
+	mutex_lock(&adev->pm.mutex);
 
+	if (!adev->pm.dpm_enabled) {
+		mutex_unlock(&adev->pm.mutex);
+		return;
+	}
 	if (!pp_funcs->read_sensor(adev->powerplay.pp_handle,
 				   AMDGPU_PP_SENSOR_GPU_TEMP,
 				   (void *)&temp,
@@ -1033,4 +1036,5 @@ void amdgpu_dpm_thermal_work_handler(struct work_struct *work)
 	adev->pm.dpm.state = dpm_state;
 
 	amdgpu_legacy_dpm_compute_clocks(adev->powerplay.pp_handle);
+	mutex_unlock(&adev->pm.mutex);
 }
diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
index a87dcf0974bc1..d6dfe2599ebea 100644
--- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
+++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
@@ -7786,6 +7786,7 @@ static int si_dpm_hw_init(struct amdgpu_ip_block *ip_block)
 	if (!amdgpu_dpm)
 		return 0;
 
+	mutex_lock(&adev->pm.mutex);
 	si_dpm_setup_asic(adev);
 	ret = si_dpm_enable(adev);
 	if (ret)
@@ -7793,6 +7794,7 @@ static int si_dpm_hw_init(struct amdgpu_ip_block *ip_block)
 	else
 		adev->pm.dpm_enabled = true;
 	amdgpu_legacy_dpm_compute_clocks(adev);
+	mutex_unlock(&adev->pm.mutex);
 	return ret;
 }
 
@@ -7810,32 +7812,44 @@ static int si_dpm_suspend(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
 
+	cancel_work_sync(&adev->pm.dpm.thermal.work);
+
 	if (adev->pm.dpm_enabled) {
+		mutex_lock(&adev->pm.mutex);
+		adev->pm.dpm_enabled = false;
 		/* disable dpm */
 		si_dpm_disable(adev);
 		/* reset the power state */
 		adev->pm.dpm.current_ps = adev->pm.dpm.requested_ps = adev->pm.dpm.boot_ps;
+		mutex_unlock(&adev->pm.mutex);
 	}
+
 	return 0;
 }
 
 static int si_dpm_resume(struct amdgpu_ip_block *ip_block)
 {
-	int ret;
+	int ret = 0;
 	struct amdgpu_device *adev = ip_block->adev;
 
-	if (adev->pm.dpm_enabled) {
+	if (!amdgpu_dpm)
+		return 0;
+
+	if (!adev->pm.dpm_enabled) {
 		/* asic init will reset to the boot state */
+		mutex_lock(&adev->pm.mutex);
 		si_dpm_setup_asic(adev);
 		ret = si_dpm_enable(adev);
-		if (ret)
+		if (ret) {
 			adev->pm.dpm_enabled = false;
-		else
+		} else {
 			adev->pm.dpm_enabled = true;
-		if (adev->pm.dpm_enabled)
 			amdgpu_legacy_dpm_compute_clocks(adev);
+		}
+		mutex_unlock(&adev->pm.mutex);
 	}
-	return 0;
+
+	return ret;
 }
 
 static bool si_dpm_is_idle(void *handle)

From 3502ab5022bb5ef1edd063bdb6465a8bf3b46e66 Mon Sep 17 00:00:00 2001
From: David Yat Sin <David.YatSin@amd.com>
Date: Wed, 19 Feb 2025 17:34:38 -0500
Subject: [PATCH 0574/1173] drm/amdkfd: Preserve cp_hqd_pq_control on
 update_mqd

When userspace applications call AMDKFD_IOC_UPDATE_QUEUE. Preserve
bitfields that do not need to be modified as they contain flags to
track queue states that are used by CP FW.

Signed-off-by: David Yat Sin <David.YatSin@amd.com>
Reviewed-by: Jay Cornwall <jay.cornwall@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 8150827990b709ab5a40c46c30d21b7f7b9e9440)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c | 6 ++++--
 drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c | 5 +++--
 drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c | 5 +++--
 drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c  | 5 ++++-
 4 files changed, 14 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
index 2eff37aaf8273..1695dd78ede8e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
@@ -107,6 +107,8 @@ static void init_mqd(struct mqd_manager *mm, void **mqd,
 	m->cp_hqd_persistent_state = CP_HQD_PERSISTENT_STATE__PRELOAD_REQ_MASK |
 			0x53 << CP_HQD_PERSISTENT_STATE__PRELOAD_SIZE__SHIFT;
 
+	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+	m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
 	m->cp_mqd_control = 1 << CP_MQD_CONTROL__PRIV_STATE__SHIFT;
 
 	m->cp_mqd_base_addr_lo        = lower_32_bits(addr);
@@ -167,10 +169,10 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
 
 	m = get_mqd(mqd);
 
-	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+	m->cp_hqd_pq_control &= ~CP_HQD_PQ_CONTROL__QUEUE_SIZE_MASK;
 	m->cp_hqd_pq_control |=
 			ffs(q->queue_size / sizeof(unsigned int)) - 1 - 1;
-	m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
+
 	pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control);
 
 	m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
index 68dbc0399c87a..3c0ae28c5923b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
@@ -154,6 +154,8 @@ static void init_mqd(struct mqd_manager *mm, void **mqd,
 	m->cp_hqd_persistent_state = CP_HQD_PERSISTENT_STATE__PRELOAD_REQ_MASK |
 			0x55 << CP_HQD_PERSISTENT_STATE__PRELOAD_SIZE__SHIFT;
 
+	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+	m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
 	m->cp_mqd_control = 1 << CP_MQD_CONTROL__PRIV_STATE__SHIFT;
 
 	m->cp_mqd_base_addr_lo        = lower_32_bits(addr);
@@ -221,10 +223,9 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
 
 	m = get_mqd(mqd);
 
-	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+	m->cp_hqd_pq_control &= ~CP_HQD_PQ_CONTROL__QUEUE_SIZE_MASK;
 	m->cp_hqd_pq_control |=
 			ffs(q->queue_size / sizeof(unsigned int)) - 1 - 1;
-	m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
 	pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control);
 
 	m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c
index 2b72d5b4949b6..565858b9044d4 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c
@@ -121,6 +121,8 @@ static void init_mqd(struct mqd_manager *mm, void **mqd,
 	m->cp_hqd_persistent_state = CP_HQD_PERSISTENT_STATE__PRELOAD_REQ_MASK |
 			0x55 << CP_HQD_PERSISTENT_STATE__PRELOAD_SIZE__SHIFT;
 
+	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+	m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
 	m->cp_mqd_control = 1 << CP_MQD_CONTROL__PRIV_STATE__SHIFT;
 
 	m->cp_mqd_base_addr_lo        = lower_32_bits(addr);
@@ -184,10 +186,9 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
 
 	m = get_mqd(mqd);
 
-	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+	m->cp_hqd_pq_control &= ~CP_HQD_PQ_CONTROL__QUEUE_SIZE_MASK;
 	m->cp_hqd_pq_control |=
 			ffs(q->queue_size / sizeof(unsigned int)) - 1 - 1;
-	m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
 	pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control);
 
 	m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
index ff417d5361c42..3014925d95ffc 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
@@ -183,6 +183,9 @@ static void init_mqd(struct mqd_manager *mm, void **mqd,
 	m->cp_hqd_persistent_state = CP_HQD_PERSISTENT_STATE__PRELOAD_REQ_MASK |
 			0x53 << CP_HQD_PERSISTENT_STATE__PRELOAD_SIZE__SHIFT;
 
+	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+	m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
+
 	m->cp_mqd_control = 1 << CP_MQD_CONTROL__PRIV_STATE__SHIFT;
 
 	m->cp_mqd_base_addr_lo        = lower_32_bits(addr);
@@ -245,7 +248,7 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
 
 	m = get_mqd(mqd);
 
-	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+	m->cp_hqd_pq_control &= ~CP_HQD_PQ_CONTROL__QUEUE_SIZE_MASK;
 	m->cp_hqd_pq_control |= order_base_2(q->queue_size / 4) - 1;
 	pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control);
 

From 099bffc7cadff40bfab1517c3461c53a7a38a0d7 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Mon, 17 Feb 2025 10:55:05 -0500
Subject: [PATCH 0575/1173] drm/amdgpu: disable BAR resize on Dell G5 SE

There was a quirk added to add a workaround for a Sapphire
RX 5600 XT Pulse that didn't allow BAR resizing.  However,
the quirk caused a regression with runtime pm on Dell laptops
using those chips, rather than narrowing the scope of the
resizing quirk, add a quirk to prevent amdgpu from resizing
the BAR on those Dell platforms unless runtime pm is disabled.

v2: update commit message, add runpm check

Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/1707
Fixes: 907830b0fc9e ("PCI: Add a REBAR size quirk for Sapphire RX 5600 XT Pulse")
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 5235053f443cef4210606e5fb71f99b915a9723d)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index d100bb7a137cd..018dfccd771ba 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1638,6 +1638,13 @@ int amdgpu_device_resize_fb_bar(struct amdgpu_device *adev)
 	if (amdgpu_sriov_vf(adev))
 		return 0;
 
+	/* resizing on Dell G5 SE platforms causes problems with runtime pm */
+	if ((amdgpu_runtime_pm != 0) &&
+	    adev->pdev->vendor == PCI_VENDOR_ID_ATI &&
+	    adev->pdev->device == 0x731f &&
+	    adev->pdev->subsystem_vendor == PCI_VENDOR_ID_DELL)
+		return 0;
+
 	/* PCI_EXT_CAP_ID_VNDR extended capability is located at 0x100 */
 	if (!pci_find_ext_capability(adev->pdev, PCI_EXT_CAP_ID_VNDR))
 		DRM_WARN("System can't access extended configuration space, please check!!\n");

From 8005351c7d53c31fb7eb5a423da7ab4bc3ad7639 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Tue, 11 Feb 2025 15:38:20 -0500
Subject: [PATCH 0576/1173] MAINTAINERS: update amdgpu maintainers list
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Xinhui's email is no longer valid.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit c19390ca9094dfcbc16d96b233a409c01e21d85b)
Cc: stable@vger.kernel.org
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 4ff26fa94895d..d6ea828345fdb 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -19657,7 +19657,6 @@ F:	drivers/net/wireless/quantenna
 RADEON and AMDGPU DRM DRIVERS
 M:	Alex Deucher <alexander.deucher@amd.com>
 M:	Christian König <christian.koenig@amd.com>
-M:	Xinhui Pan <Xinhui.Pan@amd.com>
 L:	amd-gfx@lists.freedesktop.org
 S:	Supported
 B:	https://gitlab.freedesktop.org/drm/amd/-/issues

From e7ea88207cef513514e706aacc534527ac88b9b8 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 13 Feb 2025 13:37:01 -0500
Subject: [PATCH 0577/1173] drm/amdgpu/gfx: only call mes for enforce isolation
 if supported

This should not be called on chips without MES so check if
MES is enabled and if the cleaner shader is supported.

Fixes: 8521e3c5f058 ("drm/amd/amdgpu: limit single process inside MES")
Reviewed-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: Shaoyun Liu <shaoyun.liu@amd.com>
Cc: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
(cherry picked from commit 80513e389765c8f9543b26d8fa4bbdf0e59ff8bc)
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index 784b03abb3a43..c6aff3ddb42d7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -1643,11 +1643,13 @@ static ssize_t amdgpu_gfx_set_enforce_isolation(struct device *dev,
 		if (adev->enforce_isolation[i] && !partition_values[i]) {
 			/* Going from enabled to disabled */
 			amdgpu_vmid_free_reserved(adev, AMDGPU_GFXHUB(i));
-			amdgpu_mes_set_enforce_isolation(adev, i, false);
+			if (adev->enable_mes && adev->gfx.enable_cleaner_shader)
+				amdgpu_mes_set_enforce_isolation(adev, i, false);
 		} else if (!adev->enforce_isolation[i] && partition_values[i]) {
 			/* Going from disabled to enabled */
 			amdgpu_vmid_alloc_reserved(adev, AMDGPU_GFXHUB(i));
-			amdgpu_mes_set_enforce_isolation(adev, i, true);
+			if (adev->enable_mes && adev->gfx.enable_cleaner_shader)
+				amdgpu_mes_set_enforce_isolation(adev, i, true);
 		}
 		adev->enforce_isolation[i] = partition_values[i];
 	}

From 748a1f51bb74453f1fe22d3ca68a717cb31f02e5 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 14 Feb 2025 12:32:30 -0500
Subject: [PATCH 0578/1173] drm/amdgpu/mes: keep enforce isolation up to date

Re-send the mes message on resume to make sure the
mes state is up to date.

Fixes: 8521e3c5f058 ("drm/amd/amdgpu: limit single process inside MES")
Acked-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: Shaoyun Liu <shaoyun.liu@amd.com>
Cc: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 27b791514789844e80da990c456c2465325e0851)
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c | 13 ++++---------
 drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c | 20 +++++++++++++++++++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h |  2 +-
 drivers/gpu/drm/amd/amdgpu/mes_v11_0.c  |  4 ++++
 drivers/gpu/drm/amd/amdgpu/mes_v12_0.c  |  4 ++++
 5 files changed, 32 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index c6aff3ddb42d7..c1f35ded684e8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -1638,24 +1638,19 @@ static ssize_t amdgpu_gfx_set_enforce_isolation(struct device *dev,
 	}
 
 	mutex_lock(&adev->enforce_isolation_mutex);
-
 	for (i = 0; i < num_partitions; i++) {
-		if (adev->enforce_isolation[i] && !partition_values[i]) {
+		if (adev->enforce_isolation[i] && !partition_values[i])
 			/* Going from enabled to disabled */
 			amdgpu_vmid_free_reserved(adev, AMDGPU_GFXHUB(i));
-			if (adev->enable_mes && adev->gfx.enable_cleaner_shader)
-				amdgpu_mes_set_enforce_isolation(adev, i, false);
-		} else if (!adev->enforce_isolation[i] && partition_values[i]) {
+		else if (!adev->enforce_isolation[i] && partition_values[i])
 			/* Going from disabled to enabled */
 			amdgpu_vmid_alloc_reserved(adev, AMDGPU_GFXHUB(i));
-			if (adev->enable_mes && adev->gfx.enable_cleaner_shader)
-				amdgpu_mes_set_enforce_isolation(adev, i, true);
-		}
 		adev->enforce_isolation[i] = partition_values[i];
 	}
-
 	mutex_unlock(&adev->enforce_isolation_mutex);
 
+	amdgpu_mes_update_enforce_isolation(adev);
+
 	return count;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
index 32b27a1658e78..709c11cbeabd8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
@@ -1681,7 +1681,8 @@ bool amdgpu_mes_suspend_resume_all_supported(struct amdgpu_device *adev)
 }
 
 /* Fix me -- node_id is used to identify the correct MES instances in the future */
-int amdgpu_mes_set_enforce_isolation(struct amdgpu_device *adev, uint32_t node_id, bool enable)
+static int amdgpu_mes_set_enforce_isolation(struct amdgpu_device *adev,
+					    uint32_t node_id, bool enable)
 {
 	struct mes_misc_op_input op_input = {0};
 	int r;
@@ -1703,6 +1704,23 @@ int amdgpu_mes_set_enforce_isolation(struct amdgpu_device *adev, uint32_t node_i
 	return r;
 }
 
+int amdgpu_mes_update_enforce_isolation(struct amdgpu_device *adev)
+{
+	int i, r = 0;
+
+	if (adev->enable_mes && adev->gfx.enable_cleaner_shader) {
+		mutex_lock(&adev->enforce_isolation_mutex);
+		for (i = 0; i < (adev->xcp_mgr ? adev->xcp_mgr->num_xcps : 1); i++) {
+			if (adev->enforce_isolation[i])
+				r |= amdgpu_mes_set_enforce_isolation(adev, i, true);
+			else
+				r |= amdgpu_mes_set_enforce_isolation(adev, i, false);
+		}
+		mutex_unlock(&adev->enforce_isolation_mutex);
+	}
+	return r;
+}
+
 #if defined(CONFIG_DEBUG_FS)
 
 static int amdgpu_debugfs_mes_event_log_show(struct seq_file *m, void *unused)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
index 2df2444ee892c..e98ea7ede1bab 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
@@ -534,6 +534,6 @@ static inline void amdgpu_mes_unlock(struct amdgpu_mes *mes)
 
 bool amdgpu_mes_suspend_resume_all_supported(struct amdgpu_device *adev);
 
-int amdgpu_mes_set_enforce_isolation(struct amdgpu_device *adev, uint32_t node_id, bool enable);
+int amdgpu_mes_update_enforce_isolation(struct amdgpu_device *adev);
 
 #endif /* __AMDGPU_MES_H__ */
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index 65f389eb65e5f..f9a4d08eef925 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -1633,6 +1633,10 @@ static int mes_v11_0_hw_init(struct amdgpu_ip_block *ip_block)
 		goto failure;
 	}
 
+	r = amdgpu_mes_update_enforce_isolation(adev);
+	if (r)
+		goto failure;
+
 out:
 	/*
 	 * Disable KIQ ring usage from the driver once MES is enabled.
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
index 901e924e69ad9..0fd0fa6ed5184 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
@@ -1743,6 +1743,10 @@ static int mes_v12_0_hw_init(struct amdgpu_ip_block *ip_block)
 		goto failure;
 	}
 
+	r = amdgpu_mes_update_enforce_isolation(adev);
+	if (r)
+		goto failure;
+
 out:
 	/*
 	 * Disable KIQ ring usage from the driver once MES is enabled.

From 733d675c2a436b416107893db87eb182585c1b39 Mon Sep 17 00:00:00 2001
From: Rodrigo Siqueira <siqueira@igalia.com>
Date: Wed, 19 Feb 2025 11:46:19 -0700
Subject: [PATCH 0579/1173] MAINTAINERS: Change my role from Maintainer to
 Reviewer

Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Rodrigo Siqueira <siqueira@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 9b3ef540397cfc356f10f504841b2e9d16e31286)
Cc: stable@vger.kernel.org
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index d6ea828345fdb..f3fdc43bdd497 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1046,7 +1046,7 @@ F:	drivers/crypto/ccp/hsti.*
 AMD DISPLAY CORE
 M:	Harry Wentland <harry.wentland@amd.com>
 M:	Leo Li <sunpeng.li@amd.com>
-M:	Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
+R:	Rodrigo Siqueira <siqueira@igalia.com>
 L:	amd-gfx@lists.freedesktop.org
 S:	Supported
 T:	git https://gitlab.freedesktop.org/agd5f/linux.git

From 96989f3dca6f51f202b6dbc92c37e17df6ca12f4 Mon Sep 17 00:00:00 2001
From: Rodrigo Siqueira <siqueira@igalia.com>
Date: Wed, 19 Feb 2025 11:46:20 -0700
Subject: [PATCH 0580/1173] mailmap: Add entry for Rodrigo Siqueira

Map all of my previously used email addresses to my @igalia.com address.

Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Rodrigo Siqueira <siqueira@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 289387d0dbf806bd59063ab93d94f48cd4c75c7c)
Cc: stable@vger.kernel.org
---
 .mailmap | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/.mailmap b/.mailmap
index a897c16d3baef..ec18b01f0be2a 100644
--- a/.mailmap
+++ b/.mailmap
@@ -613,6 +613,8 @@ Richard Leitner <richard.leitner@linux.dev> <me@g0hl1n.net>
 Richard Leitner <richard.leitner@linux.dev> <richard.leitner@skidata.com>
 Robert Foss <rfoss@kernel.org> <robert.foss@linaro.org>
 Rocky Liao <quic_rjliao@quicinc.com> <rjliao@codeaurora.org>
+Rodrigo Siqueira <siqueira@igalia.com> <rodrigosiqueiramelo@gmail.com>
+Rodrigo Siqueira <siqueira@igalia.com> <Rodrigo.Siqueira@amd.com>
 Roman Gushchin <roman.gushchin@linux.dev> <guro@fb.com>
 Roman Gushchin <roman.gushchin@linux.dev> <guroan@gmail.com>
 Roman Gushchin <roman.gushchin@linux.dev> <klamm@yandex-team.ru>

From 12f3b92d1cfa5526715fff93a6d6fe29300d5e2a Mon Sep 17 00:00:00 2001
From: Melissa Wen <mwen@igalia.com>
Date: Sat, 15 Feb 2025 18:15:47 -0300
Subject: [PATCH 0581/1173] drm/amd/display: restore edid reading from a given
 i2c adapter

When switching to drm_edid, we slightly changed how to get edid by
removing the possibility of getting them from dc_link when in aux
transaction mode. As MST doesn't initialize the connector with
`drm_connector_init_with_ddc()`, restore the original behavior to avoid
functional changes.

v2:
- Fix build warning of unchecked dereference (kernel test bot)

CC: Alex Hung <alex.hung@amd.com>
CC: Mario Limonciello <mario.limonciello@amd.com>
CC: Roman Li <Roman.Li@amd.com>
CC: Aurabindo Pillai <Aurabindo.Pillai@amd.com>
Fixes: 48edb2a4256e ("drm/amd/display: switch amdgpu_dm_connector to use struct drm_edid")
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Melissa Wen <mwen@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 81262b1656feb3813e3d917ab78824df6831e69e)
---
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c   | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index ac3fd81fecef2..5ddd21466e22f 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -7240,8 +7240,14 @@ static void amdgpu_dm_connector_funcs_force(struct drm_connector *connector)
 	struct dc_link *dc_link = aconnector->dc_link;
 	struct dc_sink *dc_em_sink = aconnector->dc_em_sink;
 	const struct drm_edid *drm_edid;
+	struct i2c_adapter *ddc;
 
-	drm_edid = drm_edid_read(connector);
+	if (dc_link && dc_link->aux_mode)
+		ddc = &aconnector->dm_dp_aux.aux.ddc;
+	else
+		ddc = &aconnector->i2c->base;
+
+	drm_edid = drm_edid_read_ddc(connector, ddc);
 	drm_edid_connector_update(connector, drm_edid);
 	if (!drm_edid) {
 		DRM_ERROR("No EDID found on connector: %s.\n", connector->name);
@@ -7286,14 +7292,21 @@ static int get_modes(struct drm_connector *connector)
 static void create_eml_sink(struct amdgpu_dm_connector *aconnector)
 {
 	struct drm_connector *connector = &aconnector->base;
+	struct dc_link *dc_link = aconnector->dc_link;
 	struct dc_sink_init_data init_params = {
 			.link = aconnector->dc_link,
 			.sink_signal = SIGNAL_TYPE_VIRTUAL
 	};
 	const struct drm_edid *drm_edid;
 	const struct edid *edid;
+	struct i2c_adapter *ddc;
+
+	if (dc_link && dc_link->aux_mode)
+		ddc = &aconnector->dm_dp_aux.aux.ddc;
+	else
+		ddc = &aconnector->i2c->base;
 
-	drm_edid = drm_edid_read(connector);
+	drm_edid = drm_edid_read_ddc(connector, ddc);
 	drm_edid_connector_update(connector, drm_edid);
 	if (!drm_edid) {
 		DRM_ERROR("No EDID found on connector: %s.\n", connector->name);

From a04bf34e0829f2c5d5f1ea7317daae2efa560fd1 Mon Sep 17 00:00:00 2001
From: Aurabindo Pillai <aurabindo.pillai@amd.com>
Date: Fri, 21 Feb 2025 14:19:12 -0500
Subject: [PATCH 0582/1173] MAINTAINERS: Update AMDGPU DML maintainers info

Chaitanya is no longer with AMD, and the responsibility has been
taken over by Austin.

Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit a101fa705d016d46463dd4ce488671369c922bc2)
Cc: stable@vger.kernel.org
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index f3fdc43bdd497..95bce73f3ef44 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1053,7 +1053,7 @@ T:	git https://gitlab.freedesktop.org/agd5f/linux.git
 F:	drivers/gpu/drm/amd/display/
 
 AMD DISPLAY CORE - DML
-M:	Chaitanya Dhere <chaitanya.dhere@amd.com>
+M:	Austin Zheng <austin.zheng@amd.com>
 M:	Jun Lei <jun.lei@amd.com>
 S:	Supported
 F:	drivers/gpu/drm/amd/display/dc/dml/

From e8863f8b0316d8ee1e7e5291e8f2f72c91ac967d Mon Sep 17 00:00:00 2001
From: Tom Chung <chiahsuan.chung@amd.com>
Date: Thu, 6 Feb 2025 11:31:23 +0800
Subject: [PATCH 0583/1173] drm/amd/display: Disable PSR-SU on eDP panels

[Why]
PSR-SU may cause some glitching randomly on several panels.

[How]
Temporarily disable the PSR-SU and fallback to PSR1 for
all eDP panels.

Link: https://gitlab.freedesktop.org/drm/amd/-/issues/3388
Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Sun peng Li <sunpeng.li@amd.com>
Signed-off-by: Tom Chung <chiahsuan.chung@amd.com>
Signed-off-by: Roman Li <roman.li@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 6deeefb820d0efb0b36753622fb982d03b37b3ad)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
index 45858bf1523d8..e140b7a04d724 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
@@ -54,7 +54,8 @@ static bool link_supports_psrsu(struct dc_link *link)
 	if (amdgpu_dc_debug_mask & DC_DISABLE_PSR_SU)
 		return false;
 
-	return dc_dmub_check_min_version(dc->ctx->dmub_srv->dmub);
+	/* Temporarily disable PSR-SU to avoid glitches */
+	return false;
 }
 
 /*

From b5f7242e49b927cfe488b369fa552f2eff579ef1 Mon Sep 17 00:00:00 2001
From: Yilin Chen <Yilin.Chen@amd.com>
Date: Fri, 7 Feb 2025 15:26:19 -0500
Subject: [PATCH 0584/1173] drm/amd/display: add a quirk to enable eDP0 on DP1

[why]
some board designs have eDP0 connected to DP1, need a way to enable
support_edp0_on_dp1 flag, otherwise edp related features cannot work

[how]
do a dmi check during dm initialization to identify systems that
require support_edp0_on_dp1. Optimize quirk table with callback
functions to set quirk entries, retrieve_dmi_info can set quirks
according to quirk entries

Cc: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Yilin Chen <Yilin.Chen@amd.com>
Signed-off-by: Zaeem Mohamed <zaeem.mohamed@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit f6d17270d18a6a6753fff046330483d43f8405e4)
Cc: stable@vger.kernel.org
---
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 69 +++++++++++++++++--
 1 file changed, 62 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 5ddd21466e22f..9d9645a2d18ef 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -1618,75 +1618,130 @@ static bool dm_should_disable_stutter(struct pci_dev *pdev)
 	return false;
 }
 
-static const struct dmi_system_id hpd_disconnect_quirk_table[] = {
+struct amdgpu_dm_quirks {
+	bool aux_hpd_discon;
+	bool support_edp0_on_dp1;
+};
+
+static struct amdgpu_dm_quirks quirk_entries = {
+	.aux_hpd_discon = false,
+	.support_edp0_on_dp1 = false
+};
+
+static int edp0_on_dp1_callback(const struct dmi_system_id *id)
+{
+	quirk_entries.support_edp0_on_dp1 = true;
+	return 0;
+}
+
+static int aux_hpd_discon_callback(const struct dmi_system_id *id)
+{
+	quirk_entries.aux_hpd_discon = true;
+	return 0;
+}
+
+static const struct dmi_system_id dmi_quirk_table[] = {
 	{
+		.callback = aux_hpd_discon_callback,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "Precision 3660"),
 		},
 	},
 	{
+		.callback = aux_hpd_discon_callback,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "Precision 3260"),
 		},
 	},
 	{
+		.callback = aux_hpd_discon_callback,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "Precision 3460"),
 		},
 	},
 	{
+		.callback = aux_hpd_discon_callback,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex Tower Plus 7010"),
 		},
 	},
 	{
+		.callback = aux_hpd_discon_callback,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex Tower 7010"),
 		},
 	},
 	{
+		.callback = aux_hpd_discon_callback,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex SFF Plus 7010"),
 		},
 	},
 	{
+		.callback = aux_hpd_discon_callback,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex SFF 7010"),
 		},
 	},
 	{
+		.callback = aux_hpd_discon_callback,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex Micro Plus 7010"),
 		},
 	},
 	{
+		.callback = aux_hpd_discon_callback,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex Micro 7010"),
 		},
 	},
+	{
+		.callback = edp0_on_dp1_callback,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "HP Elite mt645 G8 Mobile Thin Client"),
+		},
+	},
+	{
+		.callback = edp0_on_dp1_callback,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook 665 16 inch G11 Notebook PC"),
+		},
+	},
 	{}
 	/* TODO: refactor this from a fixed table to a dynamic option */
 };
 
-static void retrieve_dmi_info(struct amdgpu_display_manager *dm)
+static void retrieve_dmi_info(struct amdgpu_display_manager *dm, struct dc_init_data *init_data)
 {
-	const struct dmi_system_id *dmi_id;
+	int dmi_id;
+	struct drm_device *dev = dm->ddev;
 
 	dm->aux_hpd_discon_quirk = false;
+	init_data->flags.support_edp0_on_dp1 = false;
+
+	dmi_id = dmi_check_system(dmi_quirk_table);
 
-	dmi_id = dmi_first_match(hpd_disconnect_quirk_table);
-	if (dmi_id) {
+	if (!dmi_id)
+		return;
+
+	if (quirk_entries.aux_hpd_discon) {
 		dm->aux_hpd_discon_quirk = true;
-		DRM_INFO("aux_hpd_discon_quirk attached\n");
+		drm_info(dev, "aux_hpd_discon_quirk attached\n");
+	}
+	if (quirk_entries.support_edp0_on_dp1) {
+		init_data->flags.support_edp0_on_dp1 = true;
+		drm_info(dev, "aux_hpd_discon_quirk attached\n");
 	}
 }
 
@@ -1994,7 +2049,7 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 	if (amdgpu_ip_version(adev, DCE_HWIP, 0) >= IP_VERSION(3, 0, 0))
 		init_data.num_virtual_links = 1;
 
-	retrieve_dmi_info(&adev->dm);
+	retrieve_dmi_info(&adev->dm, &init_data);
 
 	if (adev->dm.bb_from_dmub)
 		init_data.bb_from_dmub = adev->dm.bb_from_dmub;

From 4de141b8b1b7991b607f77e5f4580e1c67c24717 Mon Sep 17 00:00:00 2001
From: Roman Li <Roman.Li@amd.com>
Date: Wed, 12 Feb 2025 14:49:36 -0500
Subject: [PATCH 0585/1173] drm/amd/display: Fix HPD after gpu reset

[Why]
DC is not using amdgpu_irq_get/put to manage the HPD interrupt refcounts.
So when amdgpu_irq_gpu_reset_resume_helper() reprograms all of the IRQs,
HPD gets disabled.

[How]
Use amdgpu_irq_get/put() for HPD init/fini in DM in order to sync refcounts

Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Roman Li <Roman.Li@amd.com>
Signed-off-by: Zaeem Mohamed <zaeem.mohamed@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit f3dde2ff7fcaacd77884502e8f572f2328e9c745)
Cc: stable@vger.kernel.org
---
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c  | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
index 3390f0d8420a0..c4a7fd453e5fc 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
@@ -894,6 +894,7 @@ void amdgpu_dm_hpd_init(struct amdgpu_device *adev)
 	struct drm_device *dev = adev_to_drm(adev);
 	struct drm_connector *connector;
 	struct drm_connector_list_iter iter;
+	int i;
 
 	drm_connector_list_iter_begin(dev, &iter);
 	drm_for_each_connector_iter(connector, &iter) {
@@ -920,6 +921,12 @@ void amdgpu_dm_hpd_init(struct amdgpu_device *adev)
 		}
 	}
 	drm_connector_list_iter_end(&iter);
+
+	/* Update reference counts for HPDs */
+	for (i = DC_IRQ_SOURCE_HPD1; i <= adev->mode_info.num_hpd; i++) {
+		if (amdgpu_irq_get(adev, &adev->hpd_irq, i - DC_IRQ_SOURCE_HPD1))
+			drm_err(dev, "DM_IRQ: Failed get HPD for source=%d)!\n", i);
+	}
 }
 
 /**
@@ -935,6 +942,7 @@ void amdgpu_dm_hpd_fini(struct amdgpu_device *adev)
 	struct drm_device *dev = adev_to_drm(adev);
 	struct drm_connector *connector;
 	struct drm_connector_list_iter iter;
+	int i;
 
 	drm_connector_list_iter_begin(dev, &iter);
 	drm_for_each_connector_iter(connector, &iter) {
@@ -960,4 +968,10 @@ void amdgpu_dm_hpd_fini(struct amdgpu_device *adev)
 		}
 	}
 	drm_connector_list_iter_end(&iter);
+
+	/* Update reference counts for HPDs */
+	for (i = DC_IRQ_SOURCE_HPD1; i <= adev->mode_info.num_hpd; i++) {
+		if (amdgpu_irq_put(adev, &adev->hpd_irq, i - DC_IRQ_SOURCE_HPD1))
+			drm_err(dev, "DM_IRQ: Failed put HPD for source=%d!\n", i);
+	}
 }

From d3c7059b6a8600fc62cd863f1ea203b8675e63e1 Mon Sep 17 00:00:00 2001
From: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Date: Thu, 20 Feb 2025 14:41:59 +0100
Subject: [PATCH 0586/1173] drm/amdgpu: init return value in
 amdgpu_ttm_clear_buffer
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Otherwise an uninitialized value can be returned if
amdgpu_res_cleared returns true for all regions.

Possibly closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3812

Fixes: a68c7eaa7a8f ("drm/amdgpu: Enable clear page functionality")
Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 7c62aacc3b452f73a1284198c81551035fac6d71)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 01ae2f88dec8c..262bd010a283d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -2281,7 +2281,7 @@ int amdgpu_ttm_clear_buffer(struct amdgpu_bo *bo,
 	struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring;
 	struct amdgpu_res_cursor cursor;
 	u64 addr;
-	int r;
+	int r = 0;
 
 	if (!adev->mman.buffer_funcs_enabled)
 		return -EINVAL;

From 68f3ea7ee199ef77551e090dfef5a49046ea8443 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Fri, 21 Feb 2025 14:57:06 +0100
Subject: [PATCH 0587/1173] vmlinux.lds: Ensure that const vars with
 relocations are mapped R/O

In the kernel, there are architectures (x86, arm64) that perform
boot-time relocation (for KASLR) without relying on PIE codegen. In this
case, all const global objects are emitted into .rodata, including const
objects with fields that will be fixed up by the boot-time relocation
code.  This implies that .rodata (and .text in some cases) need to be
writable at boot, but they will usually be mapped read-only as soon as
the boot completes.

When using PIE codegen, the compiler will emit const global objects into
.data.rel.ro rather than .rodata if the object contains fields that need
such fixups at boot-time. This permits the linker to annotate such
regions as requiring read-write access only at load time, but not at
execution time (in user space), while keeping .rodata truly const (in
user space, this is important for reducing the CoW footprint of dynamic
executables).

This distinction does not matter for the kernel, but it does imply that
const data will end up in writable memory if the .data.rel.ro sections
are not treated in a special way, as they will end up in the writable
.data segment by default.

So emit .data.rel.ro into the .rodata segment.

Cc: stable@vger.kernel.org
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lore.kernel.org/r/20250221135704.431269-5-ardb+git@google.com
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
---
 include/asm-generic/vmlinux.lds.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 54504013c7491..337d3336e1756 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -457,7 +457,7 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
 	. = ALIGN((align));						\
 	.rodata           : AT(ADDR(.rodata) - LOAD_OFFSET) {		\
 		__start_rodata = .;					\
-		*(.rodata) *(.rodata.*)					\
+		*(.rodata) *(.rodata.*) *(.data.rel.ro*)		\
 		SCHED_DATA						\
 		RO_AFTER_INIT_DATA	/* Read only after init */	\
 		. = ALIGN(8);						\

From 73cfc53cc3b6380eccf013049574485f64cb83ca Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Fri, 21 Feb 2025 14:57:07 +0100
Subject: [PATCH 0588/1173] objtool: Fix C jump table annotations for Clang

A C jump table (such as the one used by the BPF interpreter) is a const
global array of absolute code addresses, and this means that the actual
values in the table may not be known until the kernel is booted (e.g.,
when using KASLR or when the kernel VA space is sized dynamically).

When using PIE codegen, the compiler will default to placing such const
global objects in .data.rel.ro (which is annotated as writable), rather
than .rodata (which is annotated as read-only). As C jump tables are
explicitly emitted into .rodata, this used to result in warnings for
LoongArch builds (which uses PIE codegen for the entire kernel) like

  Warning: setting incorrect section attributes for .rodata..c_jump_table

due to the fact that the explicitly specified .rodata section inherited
the read-write annotation that the compiler uses for such objects when
using PIE codegen.

This warning was suppressed by explicitly adding the read-only
annotation to the __attribute__((section(""))) string, by commit

  c5b1184decc8 ("compiler.h: specify correct attribute for .rodata..c_jump_table")

Unfortunately, this hack does not work on Clang's integrated assembler,
which happily interprets the appended section type and permission
specifiers as part of the section name, which therefore no longer
matches the hard-coded pattern '.rodata..c_jump_table' that objtool
expects, causing it to emit a warning

  kernel/bpf/core.o: warning: objtool: ___bpf_prog_run+0x20: sibling call from callable instruction with modified stack frame

Work around this, by emitting C jump tables into .data.rel.ro instead,
which is treated as .rodata by the linker script for all builds, not
just PIE based ones.

Fixes: c5b1184decc8 ("compiler.h: specify correct attribute for .rodata..c_jump_table")
Tested-by: Tiezhu Yang <yangtiezhu@loongson.cn> # on LoongArch
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lore.kernel.org/r/20250221135704.431269-6-ardb+git@google.com
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
---
 include/linux/compiler.h                | 2 +-
 tools/objtool/check.c                   | 7 ++++---
 tools/objtool/include/objtool/special.h | 2 +-
 3 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index b087de2f3e94b..0c25f3e429bba 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -110,7 +110,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 /* Unreachable code */
 #ifdef CONFIG_OBJTOOL
 /* Annotate a C jump table to allow objtool to follow the code flow */
-#define __annotate_jump_table __section(".rodata..c_jump_table,\"a\",@progbits #")
+#define __annotate_jump_table __section(".data.rel.ro.c_jump_table")
 #else /* !CONFIG_OBJTOOL */
 #define __annotate_jump_table
 #endif /* CONFIG_OBJTOOL */
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 497cb8dfb3eb3..1b5a1b3ea7a9f 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -2471,13 +2471,14 @@ static void mark_rodata(struct objtool_file *file)
 	 *
 	 * - .rodata: can contain GCC switch tables
 	 * - .rodata.<func>: same, if -fdata-sections is being used
-	 * - .rodata..c_jump_table: contains C annotated jump tables
+	 * - .data.rel.ro.c_jump_table: contains C annotated jump tables
 	 *
 	 * .rodata.str1.* sections are ignored; they don't contain jump tables.
 	 */
 	for_each_sec(file, sec) {
-		if (!strncmp(sec->name, ".rodata", 7) &&
-		    !strstr(sec->name, ".str1.")) {
+		if ((!strncmp(sec->name, ".rodata", 7) &&
+		     !strstr(sec->name, ".str1.")) ||
+		    !strncmp(sec->name, ".data.rel.ro", 12)) {
 			sec->rodata = true;
 			found = true;
 		}
diff --git a/tools/objtool/include/objtool/special.h b/tools/objtool/include/objtool/special.h
index e7ee7ffccefd4..e049679bb17b2 100644
--- a/tools/objtool/include/objtool/special.h
+++ b/tools/objtool/include/objtool/special.h
@@ -10,7 +10,7 @@
 #include <objtool/check.h>
 #include <objtool/elf.h>
 
-#define C_JUMP_TABLE_SECTION ".rodata..c_jump_table"
+#define C_JUMP_TABLE_SECTION ".data.rel.ro.c_jump_table"
 
 struct special_alt {
 	struct list_head list;

From b4ae43b053537ec28f430c0ddb9b916ab296dbe5 Mon Sep 17 00:00:00 2001
From: Youling Tang <tangyouling@kylinos.cn>
Date: Tue, 18 Feb 2025 14:42:30 +0800
Subject: [PATCH 0589/1173] objtool: Add
 bch2_trans_unlocked_or_in_restart_error() to bcachefs noreturns

Fix the following objtool warning during build time:

  fs/bcachefs/btree_cache.o: warning: objtool: btree_node_lock.constprop.0() falls through to next function bch2_recalc_btree_reserve()
  fs/bcachefs/btree_update.o: warning: objtool: bch2_trans_update_get_key_cache() falls through to next function need_whiteout_for_snapshot()

bch2_trans_unlocked_or_in_restart_error() is an Obviously Correct (tm)
panic() wrapper, add it to the list of known noreturns.

Fixes: b318882022a8 ("bcachefs: bch2_trans_verify_not_unlocked_or_in_restart()")
Reported-by: k2ci <kernel-bot@kylinos.cn>
Signed-off-by: Youling Tang <tangyouling@kylinos.cn>
Reviewed-by: Kent Overstreet <kent.overstreet@linux.dev>
Link: https://lore.kernel.org/r/20250218064230.219997-1-youling.tang@linux.dev
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
---
 tools/objtool/noreturns.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/objtool/noreturns.h b/tools/objtool/noreturns.h
index b2174894f9f71..6bb7edda3094d 100644
--- a/tools/objtool/noreturns.h
+++ b/tools/objtool/noreturns.h
@@ -19,7 +19,7 @@ NORETURN(__x64_sys_exit_group)
 NORETURN(arch_cpu_idle_dead)
 NORETURN(bch2_trans_in_restart_error)
 NORETURN(bch2_trans_restart_error)
-NORETURN(bch2_trans_unlocked_error)
+NORETURN(bch2_trans_unlocked_or_in_restart_error)
 NORETURN(cpu_bringup_and_idle)
 NORETURN(cpu_startup_entry)
 NORETURN(do_exit)

From 8fef0a3b17bb258130a4fcbcb5addf94b25e9ec5 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 25 Feb 2025 06:02:23 -1000
Subject: [PATCH 0590/1173] sched_ext: Fix pick_task_scx() picking non-queued
 tasks when it's called without balance()

a6250aa251ea ("sched_ext: Handle cases where pick_task_scx() is called
without preceding balance_scx()") added a workaround to handle the cases
where pick_task_scx() is called without prececing balance_scx() which is due
to a fair class bug where pick_taks_fair() may return NULL after a true
return from balance_fair().

The workaround detects when pick_task_scx() is called without preceding
balance_scx() and emulates SCX_RQ_BAL_KEEP and triggers kicking to avoid
stalling. Unfortunately, the workaround code was testing whether @prev was
on SCX to decide whether to keep the task running. This is incorrect as the
task may be on SCX but no longer runnable.

This could lead to a non-runnable task to be returned from pick_task_scx()
which cause interesting confusions and failures. e.g. A common failure mode
is the task ending up with (!on_rq && on_cpu) state which can cause
potential wakers to busy loop, which can easily lead to deadlocks.

Fix it by testing whether @prev has SCX_TASK_QUEUED set. This makes
@prev_on_scx only used in one place. Open code the usage and improve the
comment while at it.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Pat Cody <patcody@meta.com>
Fixes: a6250aa251ea ("sched_ext: Handle cases where pick_task_scx() is called without preceding balance_scx()")
Cc: stable@vger.kernel.org # v6.12+
Acked-by: Andrea Righi <arighi@nvidia.com>
---
 kernel/sched/ext.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 5a81d9a1e31f2..0f1da199cfc7c 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -3117,7 +3117,6 @@ static struct task_struct *pick_task_scx(struct rq *rq)
 {
 	struct task_struct *prev = rq->curr;
 	struct task_struct *p;
-	bool prev_on_scx = prev->sched_class == &ext_sched_class;
 	bool keep_prev = rq->scx.flags & SCX_RQ_BAL_KEEP;
 	bool kick_idle = false;
 
@@ -3137,14 +3136,18 @@ static struct task_struct *pick_task_scx(struct rq *rq)
 	 * if pick_task_scx() is called without preceding balance_scx().
 	 */
 	if (unlikely(rq->scx.flags & SCX_RQ_BAL_PENDING)) {
-		if (prev_on_scx) {
+		if (prev->scx.flags & SCX_TASK_QUEUED) {
 			keep_prev = true;
 		} else {
 			keep_prev = false;
 			kick_idle = true;
 		}
-	} else if (unlikely(keep_prev && !prev_on_scx)) {
-		/* only allowed during transitions */
+	} else if (unlikely(keep_prev &&
+			    prev->sched_class != &ext_sched_class)) {
+		/*
+		 * Can happen while enabling as SCX_RQ_BAL_PENDING assertion is
+		 * conditional on scx_enabled() and may have been skipped.
+		 */
 		WARN_ON_ONCE(scx_ops_enable_state() == SCX_OPS_ENABLED);
 		keep_prev = false;
 	}

From a26b24b2e21f6222635a95426b9ef9eec63d69b1 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Fri, 17 Jan 2025 07:19:13 -0800
Subject: [PATCH 0591/1173] perf/x86/intel: Use better start period for
 frequency mode

Freqency mode is the current default mode of Linux perf. A period of 1 is
used as a starting period. The period is auto-adjusted on each tick or an
overflow, to meet the frequency target.

The start period of 1 is too low and may trigger some issues:

- Many HWs do not support period 1 well.
  https://lore.kernel.org/lkml/875xs2oh69.ffs@tglx/

- For an event that occurs frequently, period 1 is too far away from the
  real period. Lots of samples are generated at the beginning.
  The distribution of samples may not be even.

- A low starting period for frequently occurring events also challenges
  virtualization, which has a longer path to handle a PMI.

The limit_period value only checks the minimum acceptable value for HW.
It cannot be used to set the start period, because some events may
need a very low period. The limit_period cannot be set too high. It
doesn't help with the events that occur frequently.

It's hard to find a universal starting period for all events. The idea
implemented by this patch is to only give an estimate for the popular
HW and HW cache events. For the rest of the events, start from the lowest
possible recommended value.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250117151913.3043942-3-kan.liang@linux.intel.com
---
 arch/x86/events/intel/core.c | 85 ++++++++++++++++++++++++++++++++++++
 1 file changed, 85 insertions(+)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index cdcebf30468a0..cdb19e3ba3aa3 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3952,6 +3952,85 @@ static inline bool intel_pmu_has_cap(struct perf_event *event, int idx)
 	return test_bit(idx, (unsigned long *)&intel_cap->capabilities);
 }
 
+static u64 intel_pmu_freq_start_period(struct perf_event *event)
+{
+	int type = event->attr.type;
+	u64 config, factor;
+	s64 start;
+
+	/*
+	 * The 127 is the lowest possible recommended SAV (sample after value)
+	 * for a 4000 freq (default freq), according to the event list JSON file.
+	 * Also, assume the workload is idle 50% time.
+	 */
+	factor = 64 * 4000;
+	if (type != PERF_TYPE_HARDWARE && type != PERF_TYPE_HW_CACHE)
+		goto end;
+
+	/*
+	 * The estimation of the start period in the freq mode is
+	 * based on the below assumption.
+	 *
+	 * For a cycles or an instructions event, 1GHZ of the
+	 * underlying platform, 1 IPC. The workload is idle 50% time.
+	 * The start period = 1,000,000,000 * 1 / freq / 2.
+	 *		    = 500,000,000 / freq
+	 *
+	 * Usually, the branch-related events occur less than the
+	 * instructions event. According to the Intel event list JSON
+	 * file, the SAV (sample after value) of a branch-related event
+	 * is usually 1/4 of an instruction event.
+	 * The start period of branch-related events = 125,000,000 / freq.
+	 *
+	 * The cache-related events occurs even less. The SAV is usually
+	 * 1/20 of an instruction event.
+	 * The start period of cache-related events = 25,000,000 / freq.
+	 */
+	config = event->attr.config & PERF_HW_EVENT_MASK;
+	if (type == PERF_TYPE_HARDWARE) {
+		switch (config) {
+		case PERF_COUNT_HW_CPU_CYCLES:
+		case PERF_COUNT_HW_INSTRUCTIONS:
+		case PERF_COUNT_HW_BUS_CYCLES:
+		case PERF_COUNT_HW_STALLED_CYCLES_FRONTEND:
+		case PERF_COUNT_HW_STALLED_CYCLES_BACKEND:
+		case PERF_COUNT_HW_REF_CPU_CYCLES:
+			factor = 500000000;
+			break;
+		case PERF_COUNT_HW_BRANCH_INSTRUCTIONS:
+		case PERF_COUNT_HW_BRANCH_MISSES:
+			factor = 125000000;
+			break;
+		case PERF_COUNT_HW_CACHE_REFERENCES:
+		case PERF_COUNT_HW_CACHE_MISSES:
+			factor = 25000000;
+			break;
+		default:
+			goto end;
+		}
+	}
+
+	if (type == PERF_TYPE_HW_CACHE)
+		factor = 25000000;
+end:
+	/*
+	 * Usually, a prime or a number with less factors (close to prime)
+	 * is chosen as an SAV, which makes it less likely that the sampling
+	 * period synchronizes with some periodic event in the workload.
+	 * Minus 1 to make it at least avoiding values near power of twos
+	 * for the default freq.
+	 */
+	start = DIV_ROUND_UP_ULL(factor, event->attr.sample_freq) - 1;
+
+	if (start > x86_pmu.max_period)
+		start = x86_pmu.max_period;
+
+	if (x86_pmu.limit_period)
+		x86_pmu.limit_period(event, &start);
+
+	return start;
+}
+
 static int intel_pmu_hw_config(struct perf_event *event)
 {
 	int ret = x86_pmu_hw_config(event);
@@ -3963,6 +4042,12 @@ static int intel_pmu_hw_config(struct perf_event *event)
 	if (ret)
 		return ret;
 
+	if (event->attr.freq && event->attr.sample_freq) {
+		event->hw.sample_period = intel_pmu_freq_start_period(event);
+		event->hw.last_period = event->hw.sample_period;
+		local64_set(&event->hw.period_left, event->hw.sample_period);
+	}
+
 	if (event->attr.precise_ip) {
 		if ((event->attr.config & INTEL_ARCH_EVENT_MASK) == INTEL_FIXED_VLBR_EVENT)
 			return -EINVAL;

From 8e8f0306497dea58fb4e8e2558949daae5eeac5c Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Tue, 25 Feb 2025 14:16:19 +0100
Subject: [PATCH 0592/1173] x86/mtrr: Remove unnecessary strlen() in
 mtrr_write()

The local variable length already holds the string length after calling
strncpy_from_user(). Using another local variable linlen and calling
strlen() is therefore unnecessary and can be removed. Remove linlen
and strlen() and use length instead.

No change in functionality intended.

Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250225131621.329699-2-thorsten.blum@linux.dev
---
 arch/x86/kernel/cpu/mtrr/if.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c
index a5c506f6da7fa..4049235b1bfe4 100644
--- a/arch/x86/kernel/cpu/mtrr/if.c
+++ b/arch/x86/kernel/cpu/mtrr/if.c
@@ -99,7 +99,6 @@ mtrr_write(struct file *file, const char __user *buf, size_t len, loff_t * ppos)
 	char *ptr;
 	char line[LINE_SIZE];
 	int length;
-	size_t linelen;
 
 	memset(line, 0, LINE_SIZE);
 
@@ -108,9 +107,8 @@ mtrr_write(struct file *file, const char __user *buf, size_t len, loff_t * ppos)
 	if (length < 0)
 		return length;
 
-	linelen = strlen(line);
-	ptr = line + linelen - 1;
-	if (linelen && *ptr == '\n')
+	ptr = line + length - 1;
+	if (length && *ptr == '\n')
 		*ptr = '\0';
 
 	if (!strncmp(line, "disable=", 8)) {

From 1f7a4f98c11fbeb18ed21f3b3a497e90a50ad2e0 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 25 Feb 2025 15:52:21 +0100
Subject: [PATCH 0593/1173] sunrpc: suppress warnings for unused procfs
 functions

There is a warning about unused variables when building with W=1 and no procfs:

net/sunrpc/cache.c:1660:30: error: 'cache_flush_proc_ops' defined but not used [-Werror=unused-const-variable=]
 1660 | static const struct proc_ops cache_flush_proc_ops = {
      |                              ^~~~~~~~~~~~~~~~~~~~
net/sunrpc/cache.c:1622:30: error: 'content_proc_ops' defined but not used [-Werror=unused-const-variable=]
 1622 | static const struct proc_ops content_proc_ops = {
      |                              ^~~~~~~~~~~~~~~~
net/sunrpc/cache.c:1598:30: error: 'cache_channel_proc_ops' defined but not used [-Werror=unused-const-variable=]
 1598 | static const struct proc_ops cache_channel_proc_ops = {
      |                              ^~~~~~~~~~~~~~~~~~~~~~

These are used inside of an #ifdef, so replacing that with an
IS_ENABLED() check lets the compiler see how they are used while
still dropping them during dead code elimination.

Fixes: dbf847ecb631 ("knfsd: allow cache_register to return error on failure")
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Acked-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>
---
 net/sunrpc/cache.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index cb279eb9ac4ba..7ce5e28a6c031 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -1674,12 +1674,14 @@ static void remove_cache_proc_entries(struct cache_detail *cd)
 	}
 }
 
-#ifdef CONFIG_PROC_FS
 static int create_cache_proc_entries(struct cache_detail *cd, struct net *net)
 {
 	struct proc_dir_entry *p;
 	struct sunrpc_net *sn;
 
+	if (!IS_ENABLED(CONFIG_PROC_FS))
+		return 0;
+
 	sn = net_generic(net, sunrpc_net_id);
 	cd->procfs = proc_mkdir(cd->name, sn->proc_net_rpc);
 	if (cd->procfs == NULL)
@@ -1707,12 +1709,6 @@ static int create_cache_proc_entries(struct cache_detail *cd, struct net *net)
 	remove_cache_proc_entries(cd);
 	return -ENOMEM;
 }
-#else /* CONFIG_PROC_FS */
-static int create_cache_proc_entries(struct cache_detail *cd, struct net *net)
-{
-	return 0;
-}
-#endif
 
 void __init cache_initialize(void)
 {

From 9084ed79ddaaaa1ec01cd304af9fb532c26252db Mon Sep 17 00:00:00 2001
From: Stephen Smalley <stephen.smalley.work@gmail.com>
Date: Thu, 20 Feb 2025 14:29:36 -0500
Subject: [PATCH 0594/1173] lsm,nfs: fix memory leak of lsm_context

commit b530104f50e8 ("lsm: lsm_context in security_dentry_init_security")
did not preserve the lsm id for subsequent release calls, which results
in a memory leak. Fix it by saving the lsm id in the nfs4_label and
providing it on the subsequent release call.

Fixes: b530104f50e8 ("lsm: lsm_context in security_dentry_init_security")
Signed-off-by: Stephen Smalley <stephen.smalley.work@gmail.com>
Acked-by: Paul Moore <paul@paul-moore.com>
Acked-by: Casey Schaufler <casey@schaufler-ca.com>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>
---
 fs/nfs/nfs4proc.c    | 7 ++++---
 include/linux/nfs4.h | 1 +
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index c25ecdb76d304..6e95db6c17e92 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -133,6 +133,7 @@ nfs4_label_init_security(struct inode *dir, struct dentry *dentry,
 	if (err)
 		return NULL;
 
+	label->lsmid = shim.id;
 	label->label = shim.context;
 	label->len = shim.len;
 	return label;
@@ -145,7 +146,7 @@ nfs4_label_release_security(struct nfs4_label *label)
 	if (label) {
 		shim.context = label->label;
 		shim.len = label->len;
-		shim.id = LSM_ID_UNDEF;
+		shim.id = label->lsmid;
 		security_release_secctx(&shim);
 	}
 }
@@ -6272,7 +6273,7 @@ static int _nfs4_get_security_label(struct inode *inode, void *buf,
 					size_t buflen)
 {
 	struct nfs_server *server = NFS_SERVER(inode);
-	struct nfs4_label label = {0, 0, buflen, buf};
+	struct nfs4_label label = {0, 0, 0, buflen, buf};
 
 	u32 bitmask[3] = { 0, 0, FATTR4_WORD2_SECURITY_LABEL };
 	struct nfs_fattr fattr = {
@@ -6377,7 +6378,7 @@ static int nfs4_do_set_security_label(struct inode *inode,
 static int
 nfs4_set_security_label(struct inode *inode, const void *buf, size_t buflen)
 {
-	struct nfs4_label ilabel = {0, 0, buflen, (char *)buf };
+	struct nfs4_label ilabel = {0, 0, 0, buflen, (char *)buf };
 	struct nfs_fattr *fattr;
 	int status;
 
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 71fbebfa43c7e..9ac83ca883266 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -47,6 +47,7 @@ struct nfs4_acl {
 struct nfs4_label {
 	uint32_t	lfs;
 	uint32_t	pi;
+	u32		lsmid;
 	u32		len;
 	char	*label;
 };

From 79165720f31868d9a9f7e5a50a09d5fe510d1822 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Tue, 25 Feb 2025 21:02:20 +0100
Subject: [PATCH 0595/1173] x86/percpu: Construct __percpu_seg_override from
 __percpu_seg

Construct __percpu_seg_override macro from __percpu_seg by
concatenating the later with __seg_ prefix to reduce ifdeffery.

No functional change intended.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250225200235.48007-1-ubizjak@gmail.com
---
 arch/x86/include/asm/percpu.h | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index c2a9dfce36a57..7cb4f64b2e601 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -22,6 +22,7 @@
 
 #else /* !__ASSEMBLY__: */
 
+#include <linux/args.h>
 #include <linux/build_bug.h>
 #include <linux/stringify.h>
 #include <asm/asm.h>
@@ -35,12 +36,7 @@
 # define __seg_fs		__attribute__((address_space(__seg_fs)))
 #endif
 
-#ifdef CONFIG_X86_64
-# define __percpu_seg_override	__seg_gs
-#else
-# define __percpu_seg_override	__seg_fs
-#endif
-
+#define __percpu_seg_override	CONCATENATE(__seg_, __percpu_seg)
 #define __percpu_prefix		""
 
 #else /* !CONFIG_CC_HAS_NAMED_AS: */

From e451630226bd09dc730eedb4e32cab1cc7155ae8 Mon Sep 17 00:00:00 2001
From: Nir Lichtman <nir@lichtman.org>
Date: Fri, 10 Jan 2025 12:05:00 +0000
Subject: [PATCH 0596/1173] x86/build: Fix broken copy command in genimage.sh
 when making isoimage

Problem: Currently when running the "make isoimage" command there is an
error related to wrong parameters passed to the cp command:

  "cp: missing destination file operand after 'arch/x86/boot/isoimage/'"

This is caused because FDINITRDS is an empty array.

Solution: Check if FDINITRDS is empty before executing the "cp" command,
similar to how it is done in the case of hdimage.

Signed-off-by: Nir Lichtman <nir@lichtman.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: Michal Marek <michal.lkml@markovi.net>
Link: https://lore.kernel.org/r/20250110120500.GA923218@lichtman.org
---
 arch/x86/boot/genimage.sh | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/x86/boot/genimage.sh b/arch/x86/boot/genimage.sh
index c9299aeb7333e..3882ead513f74 100644
--- a/arch/x86/boot/genimage.sh
+++ b/arch/x86/boot/genimage.sh
@@ -22,6 +22,7 @@
 # This script requires:
 #   bash
 #   syslinux
+#   genisoimage
 #   mtools (for fdimage* and hdimage)
 #   edk2/OVMF (for hdimage)
 #
@@ -251,7 +252,9 @@ geniso() {
 	cp "$isolinux" "$ldlinux" "$tmp_dir"
 	cp "$FBZIMAGE" "$tmp_dir"/linux
 	echo default linux "$KCMDLINE" > "$tmp_dir"/isolinux.cfg
-	cp "${FDINITRDS[@]}" "$tmp_dir"/
+	if [ ${#FDINITRDS[@]} -gt 0 ]; then
+		cp "${FDINITRDS[@]}" "$tmp_dir"/
+	fi
 	genisoimage -J -r -appid 'LINUX_BOOT' -input-charset=utf-8 \
 		    -quiet -o "$FIMAGE" -b isolinux.bin \
 		    -c boot.cat -no-emul-boot -boot-load-size 4 \

From 96f41f644c4885761b0d117fc36dc5dcf92e15ec Mon Sep 17 00:00:00 2001
From: Dmytro Maluka <dmaluka@chromium.org>
Date: Sun, 5 Jan 2025 17:27:40 +0000
Subject: [PATCH 0597/1173] x86/of: Don't use DTB for SMP setup if ACPI is
 enabled

There are cases when it is useful to use both ACPI and DTB provided by
the bootloader, however in such cases we should make sure to prevent
conflicts between the two. Namely, don't try to use DTB for SMP setup
if ACPI is enabled.

Precisely, this prevents at least:

- incorrectly calling register_lapic_address(APIC_DEFAULT_PHYS_BASE)
  after the LAPIC was already successfully enumerated via ACPI, causing
  noisy kernel warnings and probably potential real issues as well

- failed IOAPIC setup in the case when IOAPIC is enumerated via mptable
  instead of ACPI (e.g. with acpi=noirq), due to
  mpparse_parse_smp_config() overridden by x86_dtb_parse_smp_config()

Signed-off-by: Dmytro Maluka <dmaluka@chromium.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250105172741.3476758-2-dmaluka@chromium.org
---
 arch/x86/kernel/devicetree.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 59d23cdf4ed0f..dd8748c45529a 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -2,6 +2,7 @@
 /*
  * Architecture specific OF callbacks.
  */
+#include <linux/acpi.h>
 #include <linux/export.h>
 #include <linux/io.h>
 #include <linux/interrupt.h>
@@ -313,6 +314,6 @@ void __init x86_flattree_get_config(void)
 	if (initial_dtb)
 		early_memunmap(dt, map_len);
 #endif
-	if (of_have_populated_dt())
+	if (acpi_disabled && of_have_populated_dt())
 		x86_init.mpparse.parse_smp_cfg = x86_dtb_parse_smp_config;
 }

From bebe35bb738b573c32a5033499cd59f20293f2a3 Mon Sep 17 00:00:00 2001
From: Russell Senior <russell@personaltelco.net>
Date: Tue, 25 Feb 2025 22:31:20 +0100
Subject: [PATCH 0598/1173] x86/CPU: Fix warm boot hang regression on AMD
 SC1100 SoC systems

I still have some Soekris net4826 in a Community Wireless Network I
volunteer with. These devices use an AMD SC1100 SoC. I am running
OpenWrt on them, which uses a patched kernel, that naturally has
evolved over time.  I haven't updated the ones in the field in a
number of years (circa 2017), but have one in a test bed, where I have
intermittently tried out test builds.

A few years ago, I noticed some trouble, particularly when "warm
booting", that is, doing a reboot without removing power, and noticed
the device was hanging after the kernel message:

  [    0.081615] Working around Cyrix MediaGX virtual DMA bugs.

If I removed power and then restarted, it would boot fine, continuing
through the message above, thusly:

  [    0.081615] Working around Cyrix MediaGX virtual DMA bugs.
  [    0.090076] Enable Memory-Write-back mode on Cyrix/NSC processor.
  [    0.100000] Enable Memory access reorder on Cyrix/NSC processor.
  [    0.100070] Last level iTLB entries: 4KB 0, 2MB 0, 4MB 0
  [    0.110058] Last level dTLB entries: 4KB 0, 2MB 0, 4MB 0, 1GB 0
  [    0.120037] CPU: NSC Geode(TM) Integrated Processor by National Semi (family: 0x5, model: 0x9, stepping: 0x1)
  [...]

In order to continue using modern tools, like ssh, to interact with
the software on these old devices, I need modern builds of the OpenWrt
firmware on the devices. I confirmed that the warm boot hang was still
an issue in modern OpenWrt builds (currently using a patched linux
v6.6.65).

Last night, I decided it was time to get to the bottom of the warm
boot hang, and began bisecting. From preserved builds, I narrowed down
the bisection window from late February to late May 2019. During this
period, the OpenWrt builds were using 4.14.x. I was able to build
using period-correct Ubuntu 18.04.6. After a number of bisection
iterations, I identified a kernel bump from 4.14.112 to 4.14.113 as
the commit that introduced the warm boot hang.

  https://github.com/openwrt/openwrt/commit/07aaa7e3d62ad32767d7067107db64b6ade81537

Looking at the upstream changes in the stable kernel between 4.14.112
and 4.14.113 (tig v4.14.112..v4.14.113), I spotted a likely suspect:

  https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=20afb90f730982882e65b01fb8bdfe83914339c5

So, I tried reverting just that kernel change on top of the breaking
OpenWrt commit, and my warm boot hang went away.

Presumably, the warm boot hang is due to some register not getting
cleared in the same way that a loss of power does. That is
approximately as much as I understand about the problem.

More poking/prodding and coaching from Jonas Gorski, it looks
like this test patch fixes the problem on my board: Tested against
v6.6.67 and v4.14.113.

Fixes: 18fb053f9b82 ("x86/cpu/cyrix: Use correct macros for Cyrix calls on Geode processors")
Debugged-by: Jonas Gorski <jonas.gorski@gmail.com>
Signed-off-by: Russell Senior <russell@personaltelco.net>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/CAHP3WfOgs3Ms4Z+L9i0-iBOE21sdMk5erAiJurPjnrL9LSsgRA@mail.gmail.com
Cc: Matthew Whitehead <tedheadster@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/cpu/cyrix.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index 9651275aecd1b..dfec2c61e3547 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -153,8 +153,8 @@ static void geode_configure(void)
 	u8 ccr3;
 	local_irq_save(flags);
 
-	/* Suspend on halt power saving and enable #SUSP pin */
-	setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x88);
+	/* Suspend on halt power saving */
+	setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x08);
 
 	ccr3 = getCx86(CX86_CCR3);
 	setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10);	/* enable MAPEN */

From 9de7695925d5d2d2085681ba935857246eb2817d Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 25 Feb 2025 22:32:33 +0100
Subject: [PATCH 0599/1173] x86/irq: Define trace events conditionally

When both of X86_LOCAL_APIC and X86_THERMAL_VECTOR are disabled,
the irq tracing produces a W=1 build warning for the tracing
definitions:

  In file included from include/trace/trace_events.h:27,
                 from include/trace/define_trace.h:113,
                 from arch/x86/include/asm/trace/irq_vectors.h:383,
                 from arch/x86/kernel/irq.c:29:
  include/trace/stages/init.h:2:23: error: 'str__irq_vectors__trace_system_name' defined but not used [-Werror=unused-const-variable=]

Make the tracepoints conditional on the same symbosl that guard
their usage.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250225213236.3141752-1-arnd@kernel.org
---
 arch/x86/kernel/irq.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 385e3a5fc3045..feca4f20b06aa 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -25,8 +25,10 @@
 #include <asm/posted_intr.h>
 #include <asm/irq_remapping.h>
 
+#if defined(CONFIG_X86_LOCAL_APIC) || defined(CONFIG_X86_THERMAL_VECTOR)
 #define CREATE_TRACE_POINTS
 #include <asm/trace/irq_vectors.h>
+#endif
 
 DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
 EXPORT_PER_CPU_SYMBOL(irq_stat);

From 68a9b0e313302451468c0b0eda53c383fa51a8f4 Mon Sep 17 00:00:00 2001
From: Aaron Ma <aaron.ma@canonical.com>
Date: Tue, 24 Dec 2024 22:55:16 +0800
Subject: [PATCH 0600/1173] perf/x86/rapl: Add support for Intel Arrow Lake U

Add Arrow Lake U model for RAPL:

  $ ls -1 /sys/devices/power/events/
  energy-cores
  energy-cores.scale
  energy-cores.unit
  energy-gpu
  energy-gpu.scale
  energy-gpu.unit
  energy-pkg
  energy-pkg.scale
  energy-pkg.unit
  energy-psys
  energy-psys.scale
  energy-psys.unit

The same output as ArrowLake:

  $ perf stat -a -I 1000 --per-socket -e power/energy-pkg/

Signed-off-by: Aaron Ma <aaron.ma@canonical.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Zhang Rui <rui.zhang@intel.com>
Link: https://lore.kernel.org/r/20241224145516.349028-1-aaron.ma@canonical.com
---
 arch/x86/events/rapl.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index 4952faf03e82d..6941f4811bec1 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -879,6 +879,7 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = {
 	X86_MATCH_VFM(INTEL_METEORLAKE_L,	&model_skl),
 	X86_MATCH_VFM(INTEL_ARROWLAKE_H,	&model_skl),
 	X86_MATCH_VFM(INTEL_ARROWLAKE,		&model_skl),
+	X86_MATCH_VFM(INTEL_ARROWLAKE_U,	&model_skl),
 	X86_MATCH_VFM(INTEL_LUNARLAKE_M,	&model_skl),
 	{},
 };

From 0f6750b15ffdf274668b12824b09bd49ea854e18 Mon Sep 17 00:00:00 2001
From: Daniel Sneddon <daniel.sneddon@linux.intel.com>
Date: Thu, 19 Dec 2024 08:52:27 -0700
Subject: [PATCH 0601/1173] x86/entry: Fix kernel-doc warning

The do_int80_emulation() function is missing a kernel-doc formatted
description of its argument. This is causing a warning when building
with W=1. Add a brief description of the argument to satisfy
kernel-doc.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Daniel Sneddon <daniel.sneddon@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20241219155227.685692-1-daniel.sneddon@linux.intel.com
Closes: https://lore.kernel.org/oe-kbuild-all/202412131236.a5HhOqXo-lkp@intel.com/
---
 arch/x86/entry/common.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 94941c5a10ac1..14db5b85114c1 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -190,6 +190,7 @@ static __always_inline bool int80_is_external(void)
 
 /**
  * do_int80_emulation - 32-bit legacy syscall C entry from asm
+ * @regs: syscall arguments in struct pt_args on the stack.
  *
  * This entry point can be used by 32-bit and 64-bit programs to perform
  * 32-bit system calls.  Instances of INT $0x80 can be found inline in

From f8c857238a392f21d5726d07966f6061007c8d4f Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 25 Feb 2025 14:32:14 -0800
Subject: [PATCH 0602/1173] uprobes: Remove too strict lockdep_assert()
 condition in hprobe_expire()

hprobe_expire() is used to atomically switch pending uretprobe instance
(struct return_instance) from being SRCU protected to be refcounted.
This can be done from background timer thread, or synchronously within
current thread when task is forked.

In the former case, return_instance has to be protected through RCU read
lock, and that's what hprobe_expire() used to check with
lockdep_assert(rcu_read_lock_held()).

But in the latter case (hprobe_expire() called from dup_utask()) there
is no RCU lock being held, and it's both unnecessary and incovenient.
Inconvenient due to the intervening memory allocations inside
dup_return_instance()'s loop. Unnecessary because dup_utask() is called
synchronously in current thread, and no uretprobe can run at that point,
so return_instance can't be freed either.

So drop rcu_read_lock_held() condition, and expand corresponding comment
to explain necessary lifetime guarantees. lockdep_assert()-detected
issue is a false positive.

Fixes: dd1a7567784e ("uprobes: SRCU-protect uretprobe lifetime (with timeout)")
Reported-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250225223214.2970740-1-andrii@kernel.org
---
 kernel/events/uprobes.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index af53fbd2d12c4..b4ca8898fe178 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -767,10 +767,14 @@ static struct uprobe *hprobe_expire(struct hprobe *hprobe, bool get)
 	enum hprobe_state hstate;
 
 	/*
-	 * return_instance's hprobe is protected by RCU.
-	 * Underlying uprobe is itself protected from reuse by SRCU.
+	 * Caller should guarantee that return_instance is not going to be
+	 * freed from under us. This can be achieved either through holding
+	 * rcu_read_lock() or by owning return_instance in the first place.
+	 *
+	 * Underlying uprobe is itself protected from reuse by SRCU, so ensure
+	 * SRCU lock is held properly.
 	 */
-	lockdep_assert(rcu_read_lock_held() && srcu_read_lock_held(&uretprobes_srcu));
+	lockdep_assert(srcu_read_lock_held(&uretprobes_srcu));
 
 	hstate = READ_ONCE(hprobe->state);
 	switch (hstate) {

From 66cb85c441cd9c44b193ff75b4d0358fccdc6b9c Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 25 Feb 2025 22:25:00 +0000
Subject: [PATCH 0603/1173] cifs: Fix the smb1 readv callback to correctly call
 netfs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix cifs_readv_callback() to call netfs_read_subreq_terminated() rather
than queuing the subrequest work item (which is unset).  Also call the
I/O progress tracepoint.

cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cifs@vger.kernel.org
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Fixes: e2d46f2ec332 ("netfs: Change the read result collector to only use one work item")
Reported-by: Jean-Christophe Guillain <jean-christophe@guillain.net>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219793
Tested-by: Jean-Christophe Guillain <jean-christophe@guillain.net>
Tested-by: Pali Rohár <pali@kernel.org>
Reviewed-by: Paulo Alcantara (Red Hat) <pc@manguebit.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifssmb.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c
index 3feaa0f681699..d07682020c645 100644
--- a/fs/smb/client/cifssmb.c
+++ b/fs/smb/client/cifssmb.c
@@ -1338,7 +1338,8 @@ cifs_readv_callback(struct mid_q_entry *mid)
 	rdata->credits.value = 0;
 	rdata->subreq.error = rdata->result;
 	rdata->subreq.transferred += rdata->got_bytes;
-	queue_work(cifsiod_wq, &rdata->subreq.work);
+	trace_netfs_sreq(&rdata->subreq, netfs_sreq_trace_io_progress);
+	netfs_read_subreq_terminated(&rdata->subreq);
 	release_mid(mid);
 	add_credits(server, &credits, 0);
 }

From bab3a6e9ffd600f9db0ebaf8f45e1c6111cf314c Mon Sep 17 00:00:00 2001
From: Sascha Hauer <s.hauer@pengutronix.de>
Date: Mon, 24 Feb 2025 06:17:16 +0100
Subject: [PATCH 0604/1173] net: ethernet: ti: am65-cpsw: select PAGE_POOL

am65-cpsw uses page_pool_dev_alloc_pages(), thus needs PAGE_POOL
selected to avoid linker errors. This is missing since the driver
started to use page_pool helpers in 8acacc40f733 ("net: ethernet:
ti: am65-cpsw: Add minimal XDP support")

Fixes: 8acacc40f733 ("net: ethernet: ti: am65-cpsw: Add minimal XDP support")
Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Link: https://patch.msgid.link/20250224-net-am654-nuss-kconfig-v2-1-c124f4915c92@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ti/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig
index 0d5a862cd78a6..3a13d60a947a8 100644
--- a/drivers/net/ethernet/ti/Kconfig
+++ b/drivers/net/ethernet/ti/Kconfig
@@ -99,6 +99,7 @@ config TI_K3_AM65_CPSW_NUSS
 	select NET_DEVLINK
 	select TI_DAVINCI_MDIO
 	select PHYLINK
+	select PAGE_POOL
 	select TI_K3_CPPI_DESC_POOL
 	imply PHY_TI_GMII_SEL
 	depends on TI_K3_AM65_CPTS || !TI_K3_AM65_CPTS

From 18912c520674ec4d920fe3826e7e4fefeecdf5ae Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Mon, 24 Feb 2025 09:44:01 -0800
Subject: [PATCH 0605/1173] tcp: devmem: don't write truncated dmabuf CMSGs to
 userspace

Currently, we report -ETOOSMALL (err) only on the first iteration
(!sent). When we get put_cmsg error after a bunch of successful
put_cmsg calls, we don't signal the error at all. This might be
confusing on the userspace side which will see truncated CMSGs
but no MSG_CTRUNC signal.

Consider the following case:
- sizeof(struct cmsghdr) = 16
- sizeof(struct dmabuf_cmsg) = 24
- total cmsg size (CMSG_LEN) = 40 (16+24)

When calling recvmsg with msg_controllen=60, the userspace
will receive two(!) dmabuf_cmsg(s), the first one will
be a valid one and the second one will be silently truncated. There is no
easy way to discover the truncation besides doing something like
"cm->cmsg_len != CMSG_LEN(sizeof(dmabuf_cmsg))".

Introduce new put_devmem_cmsg wrapper that reports an error instead
of doing the truncation. Mina suggests that it's the intended way
this API should work.

Note that we might now report MSG_CTRUNC when the users (incorrectly)
call us with msg_control == NULL.

Fixes: 8f0b3cc9a4c1 ("tcp: RX path for devmem TCP")
Reviewed-by: Mina Almasry <almasrymina@google.com>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250224174401.3582695-1-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/socket.h |  2 ++
 net/core/scm.c         | 10 ++++++++++
 net/ipv4/tcp.c         | 26 ++++++++++----------------
 3 files changed, 22 insertions(+), 16 deletions(-)

diff --git a/include/linux/socket.h b/include/linux/socket.h
index d18cc47e89bd0..c3322eb3d6865 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -392,6 +392,8 @@ struct ucred {
 
 extern int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr_storage *kaddr);
 extern int put_cmsg(struct msghdr*, int level, int type, int len, void *data);
+extern int put_cmsg_notrunc(struct msghdr *msg, int level, int type, int len,
+			    void *data);
 
 struct timespec64;
 struct __kernel_timespec;
diff --git a/net/core/scm.c b/net/core/scm.c
index 4f6a14babe5ae..733c0cbd393d2 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -282,6 +282,16 @@ int put_cmsg(struct msghdr * msg, int level, int type, int len, void *data)
 }
 EXPORT_SYMBOL(put_cmsg);
 
+int put_cmsg_notrunc(struct msghdr *msg, int level, int type, int len,
+		     void *data)
+{
+	/* Don't produce truncated CMSGs */
+	if (!msg->msg_control || msg->msg_controllen < CMSG_LEN(len))
+		return -ETOOSMALL;
+
+	return put_cmsg(msg, level, type, len, data);
+}
+
 void put_cmsg_scm_timestamping64(struct msghdr *msg, struct scm_timestamping_internal *tss_internal)
 {
 	struct scm_timestamping64 tss;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 0d704bda6c416..d74281eca14f0 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2438,14 +2438,12 @@ static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb,
 			 */
 			memset(&dmabuf_cmsg, 0, sizeof(dmabuf_cmsg));
 			dmabuf_cmsg.frag_size = copy;
-			err = put_cmsg(msg, SOL_SOCKET, SO_DEVMEM_LINEAR,
-				       sizeof(dmabuf_cmsg), &dmabuf_cmsg);
-			if (err || msg->msg_flags & MSG_CTRUNC) {
-				msg->msg_flags &= ~MSG_CTRUNC;
-				if (!err)
-					err = -ETOOSMALL;
+			err = put_cmsg_notrunc(msg, SOL_SOCKET,
+					       SO_DEVMEM_LINEAR,
+					       sizeof(dmabuf_cmsg),
+					       &dmabuf_cmsg);
+			if (err)
 				goto out;
-			}
 
 			sent += copy;
 
@@ -2499,16 +2497,12 @@ static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb,
 				offset += copy;
 				remaining_len -= copy;
 
-				err = put_cmsg(msg, SOL_SOCKET,
-					       SO_DEVMEM_DMABUF,
-					       sizeof(dmabuf_cmsg),
-					       &dmabuf_cmsg);
-				if (err || msg->msg_flags & MSG_CTRUNC) {
-					msg->msg_flags &= ~MSG_CTRUNC;
-					if (!err)
-						err = -ETOOSMALL;
+				err = put_cmsg_notrunc(msg, SOL_SOCKET,
+						       SO_DEVMEM_DMABUF,
+						       sizeof(dmabuf_cmsg),
+						       &dmabuf_cmsg);
+				if (err)
 					goto out;
-				}
 
 				atomic_long_inc(&niov->pp_ref_count);
 				tcp_xa_pool.netmems[tcp_xa_pool.idx++] = skb_frag_netmem(frag);

From f865c24bc55158313d5779fc81116023a6940ca3 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 24 Feb 2025 19:11:50 +0100
Subject: [PATCH 0606/1173] mptcp: always handle address removal under msk
 socket lock

Syzkaller reported a lockdep splat in the PM control path:

  WARNING: CPU: 0 PID: 6693 at ./include/net/sock.h:1711 sock_owned_by_me include/net/sock.h:1711 [inline]
  WARNING: CPU: 0 PID: 6693 at ./include/net/sock.h:1711 msk_owned_by_me net/mptcp/protocol.h:363 [inline]
  WARNING: CPU: 0 PID: 6693 at ./include/net/sock.h:1711 mptcp_pm_nl_addr_send_ack+0x57c/0x610 net/mptcp/pm_netlink.c:788
  Modules linked in:
  CPU: 0 UID: 0 PID: 6693 Comm: syz.0.205 Not tainted 6.14.0-rc2-syzkaller-00303-gad1b832bf1cf #0
  Hardware name: Google Compute Engine/Google Compute Engine, BIOS Google 12/27/2024
  RIP: 0010:sock_owned_by_me include/net/sock.h:1711 [inline]
  RIP: 0010:msk_owned_by_me net/mptcp/protocol.h:363 [inline]
  RIP: 0010:mptcp_pm_nl_addr_send_ack+0x57c/0x610 net/mptcp/pm_netlink.c:788
  Code: 5b 41 5c 41 5d 41 5e 41 5f 5d c3 cc cc cc cc e8 ca 7b d3 f5 eb b9 e8 c3 7b d3 f5 90 0f 0b 90 e9 dd fb ff ff e8 b5 7b d3 f5 90 <0f> 0b 90 e9 3e fb ff ff 44 89 f1 80 e1 07 38 c1 0f 8c eb fb ff ff
  RSP: 0000:ffffc900034f6f60 EFLAGS: 00010283
  RAX: ffffffff8bee3c2b RBX: 0000000000000001 RCX: 0000000000080000
  RDX: ffffc90004d42000 RSI: 000000000000a407 RDI: 000000000000a408
  RBP: ffffc900034f7030 R08: ffffffff8bee37f6 R09: 0100000000000000
  R10: dffffc0000000000 R11: ffffed100bcc62e4 R12: ffff88805e6316e0
  R13: ffff88805e630c00 R14: dffffc0000000000 R15: ffff88805e630c00
  FS:  00007f7e9a7e96c0(0000) GS:ffff8880b8600000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 0000001b2fd18ff8 CR3: 0000000032c24000 CR4: 00000000003526f0
  DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
  DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
  Call Trace:
   <TASK>
   mptcp_pm_remove_addr+0x103/0x1d0 net/mptcp/pm.c:59
   mptcp_pm_remove_anno_addr+0x1f4/0x2f0 net/mptcp/pm_netlink.c:1486
   mptcp_nl_remove_subflow_and_signal_addr net/mptcp/pm_netlink.c:1518 [inline]
   mptcp_pm_nl_del_addr_doit+0x118d/0x1af0 net/mptcp/pm_netlink.c:1629
   genl_family_rcv_msg_doit net/netlink/genetlink.c:1115 [inline]
   genl_family_rcv_msg net/netlink/genetlink.c:1195 [inline]
   genl_rcv_msg+0xb1f/0xec0 net/netlink/genetlink.c:1210
   netlink_rcv_skb+0x206/0x480 net/netlink/af_netlink.c:2543
   genl_rcv+0x28/0x40 net/netlink/genetlink.c:1219
   netlink_unicast_kernel net/netlink/af_netlink.c:1322 [inline]
   netlink_unicast+0x7f6/0x990 net/netlink/af_netlink.c:1348
   netlink_sendmsg+0x8de/0xcb0 net/netlink/af_netlink.c:1892
   sock_sendmsg_nosec net/socket.c:718 [inline]
   __sock_sendmsg+0x221/0x270 net/socket.c:733
   ____sys_sendmsg+0x53a/0x860 net/socket.c:2573
   ___sys_sendmsg net/socket.c:2627 [inline]
   __sys_sendmsg+0x269/0x350 net/socket.c:2659
   do_syscall_x64 arch/x86/entry/common.c:52 [inline]
   do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83
   entry_SYSCALL_64_after_hwframe+0x77/0x7f
  RIP: 0033:0x7f7e9998cde9
  Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48
  RSP: 002b:00007f7e9a7e9038 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
  RAX: ffffffffffffffda RBX: 00007f7e99ba5fa0 RCX: 00007f7e9998cde9
  RDX: 000000002000c094 RSI: 0000400000000000 RDI: 0000000000000007
  RBP: 00007f7e99a0e2a0 R08: 0000000000000000 R09: 0000000000000000
  R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
  R13: 0000000000000000 R14: 00007f7e99ba5fa0 R15: 00007fff49231088

Indeed the PM can try to send a RM_ADDR over a msk without acquiring
first the msk socket lock.

The bugged code-path comes from an early optimization: when there
are no subflows, the PM should (usually) not send RM_ADDR
notifications.

The above statement is incorrect, as without locks another process
could concurrent create a new subflow and cause the RM_ADDR generation.

Additionally the supposed optimization is not very effective even
performance-wise, as most mptcp sockets should have at least one
subflow: the MPC one.

Address the issue removing the buggy code path, the existing "slow-path"
will handle correctly even the edge case.

Fixes: b6c08380860b ("mptcp: remove addr and subflow in PM netlink")
Cc: stable@vger.kernel.org
Reported-by: syzbot+cd3ce3d03a3393ae9700@syzkaller.appspotmail.com
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/546
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250224-net-mptcp-misc-fixes-v1-1-f550f636b435@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm_netlink.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 572d160edca33..c0e47f4f7b1aa 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1514,11 +1514,6 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net,
 		if (mptcp_pm_is_userspace(msk))
 			goto next;
 
-		if (list_empty(&msk->conn_list)) {
-			mptcp_pm_remove_anno_addr(msk, addr, false);
-			goto next;
-		}
-
 		lock_sock(sk);
 		remove_subflow = mptcp_lookup_subflow_by_saddr(&msk->conn_list, addr);
 		mptcp_pm_remove_anno_addr(msk, addr, remove_subflow &&

From 8668860b0ad32a13fcd6c94a0995b7aa7638c9ef Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 24 Feb 2025 19:11:51 +0100
Subject: [PATCH 0607/1173] mptcp: reset when MPTCP opts are dropped after join

Before this patch, if the checksum was not used, the subflow was only
reset if map_data_len was != 0. If there were no MPTCP options or an
invalid mapping, map_data_len was not set to the data len, and then the
subflow was not reset as it should have been, leaving the MPTCP
connection in a wrong fallback mode.

This map_data_len condition has been introduced to handle the reception
of the infinite mapping. Instead, a new dedicated mapping error could
have been returned and treated as a special case. However, the commit
31bf11de146c ("mptcp: introduce MAPPING_BAD_CSUM") has been introduced
by Paolo Abeni soon after, and backported later on to stable. It better
handle the csum case, and it means the exception for valid_csum_seen in
subflow_can_fallback(), plus this one for the infinite mapping in
subflow_check_data_avail(), are no longer needed.

In other words, the code can be simplified there: a fallback should only
be done if msk->allow_infinite_fallback is set. This boolean is set to
false once MPTCP-specific operations acting on the whole MPTCP
connection vs the initial path have been done, e.g. a second path has
been created, or an MPTCP re-injection -- yes, possible even with a
single subflow. The subflow_can_fallback() helper can then be dropped,
and replaced by this single condition.

This also makes the code clearer: a fallback should only be done if it
is possible to do so.

While at it, no need to set map_data_len to 0 in get_mapping_status()
for the infinite mapping case: it will be set to skb->len just after, at
the end of subflow_check_data_avail(), and not read in between.

Fixes: f8d4bcacff3b ("mptcp: infinite mapping receiving")
Cc: stable@vger.kernel.org
Reported-by: Chester A. Unal <chester.a.unal@xpedite-tech.com>
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/544
Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Tested-by: Chester A. Unal <chester.a.unal@xpedite-tech.com>
Link: https://patch.msgid.link/20250224-net-mptcp-misc-fixes-v1-2-f550f636b435@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/subflow.c | 15 +--------------
 1 file changed, 1 insertion(+), 14 deletions(-)

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index dfcbef9c46246..9f18217dddc86 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -1142,7 +1142,6 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
 	if (data_len == 0) {
 		pr_debug("infinite mapping received\n");
 		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPRX);
-		subflow->map_data_len = 0;
 		return MAPPING_INVALID;
 	}
 
@@ -1286,18 +1285,6 @@ static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ss
 		mptcp_schedule_work(sk);
 }
 
-static bool subflow_can_fallback(struct mptcp_subflow_context *subflow)
-{
-	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
-
-	if (subflow->mp_join)
-		return false;
-	else if (READ_ONCE(msk->csum_enabled))
-		return !subflow->valid_csum_seen;
-	else
-		return READ_ONCE(msk->allow_infinite_fallback);
-}
-
 static void mptcp_subflow_fail(struct mptcp_sock *msk, struct sock *ssk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
@@ -1393,7 +1380,7 @@ static bool subflow_check_data_avail(struct sock *ssk)
 			return true;
 		}
 
-		if (!subflow_can_fallback(subflow) && subflow->map_data_len) {
+		if (!READ_ONCE(msk->allow_infinite_fallback)) {
 			/* fatal protocol error, close the socket.
 			 * subflow_error_report() will introduce the appropriate barriers
 			 */

From db75a16813aabae3b78c06b1b99f5e314c1f55d3 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 24 Feb 2025 19:11:52 +0100
Subject: [PATCH 0608/1173] mptcp: safety check before fallback

Recently, some fallback have been initiated, while the connection was
not supposed to fallback.

Add a safety check with a warning to detect when an wrong attempt to
fallback is being done. This should help detecting any future issues
quicker.

Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250224-net-mptcp-misc-fixes-v1-3-f550f636b435@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/protocol.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index f6a207958459d..ad21925af0612 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -1199,6 +1199,8 @@ static inline void __mptcp_do_fallback(struct mptcp_sock *msk)
 		pr_debug("TCP fallback already done (msk=%p)\n", msk);
 		return;
 	}
+	if (WARN_ON_ONCE(!READ_ONCE(msk->allow_infinite_fallback)))
+		return;
 	set_bit(MPTCP_FALLBACK_DONE, &msk->flags);
 }
 

From a6aa36e957a1bfb5341986dec32d013d23228fe1 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Fri, 14 Feb 2025 13:14:34 +0900
Subject: [PATCH 0609/1173] block: Remove zone write plugs when handling native
 zone append writes

For devices that natively support zone append operations,
REQ_OP_ZONE_APPEND BIOs are not processed through zone write plugging
and are immediately issued to the zoned device. This means that there is
no write pointer offset tracking done for these operations and that a
zone write plug is not necessary.

However, when receiving a zone append BIO, we may already have a zone
write plug for the target zone if that zone was previously partially
written using regular write operations. In such case, since the write
pointer offset of the zone write plug is not incremented by the amount
of sectors appended to the zone, 2 issues arise:
1) we risk leaving the plug in the disk hash table if the zone is fully
   written using zone append or regular write operations, because the
   write pointer offset will never reach the "zone full" state.
2) Regular write operations that are issued after zone append operations
   will always be failed by blk_zone_wplug_prepare_bio() as the write
   pointer alignment check will fail, even if the user correctly
   accounted for the zone append operations and issued the regular
   writes with a correct sector.

Avoid these issues by immediately removing the zone write plug of zones
that are the target of zone append operations when blk_zone_plug_bio()
is called. The new function blk_zone_wplug_handle_native_zone_append()
implements this for devices that natively support zone append. The
removal of the zone write plug using disk_remove_zone_wplug() requires
aborting all plugged regular write using disk_zone_wplug_abort() as
otherwise the plugged write BIOs would never be executed (with the plug
removed, the completion path will never see again the zone write plug as
disk_get_zone_wplug() will return NULL). Rate-limited warnings are added
to blk_zone_wplug_handle_native_zone_append() and to
disk_zone_wplug_abort() to signal this.

Since blk_zone_wplug_handle_native_zone_append() is called in the hot
path for operations that will not be plugged, disk_get_zone_wplug() is
optimized under the assumption that a user issuing zone append
operations is not at the same time issuing regular writes and that there
are no hashed zone write plugs. The struct gendisk atomic counter
nr_zone_wplugs is added to check this, with this counter incremented in
disk_insert_zone_wplug() and decremented in disk_remove_zone_wplug().

To be consistent with this fix, we do not need to fill the zone write
plug hash table with zone write plugs for zones that are partially
written for a device that supports native zone append operations.
So modify blk_revalidate_seq_zone() to return early to avoid allocating
and inserting a zone write plug for partially written sequential zones
if the device natively supports zone append.

Reported-by: Jorgen Hansen <Jorgen.Hansen@wdc.com>
Fixes: 9b1ce7f0c6f8 ("block: Implement zone append emulation")
Cc: stable@vger.kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Tested-by: Jorgen Hansen <Jorgen.Hansen@wdc.com>
Link: https://lore.kernel.org/r/20250214041434.82564-1-dlemoal@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-zoned.c      | 76 ++++++++++++++++++++++++++++++++++++++----
 include/linux/blkdev.h |  7 ++--
 2 files changed, 73 insertions(+), 10 deletions(-)

diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 761ea662ddc34..0c77244a35c92 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -410,13 +410,14 @@ static bool disk_insert_zone_wplug(struct gendisk *disk,
 		}
 	}
 	hlist_add_head_rcu(&zwplug->node, &disk->zone_wplugs_hash[idx]);
+	atomic_inc(&disk->nr_zone_wplugs);
 	spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags);
 
 	return true;
 }
 
-static struct blk_zone_wplug *disk_get_zone_wplug(struct gendisk *disk,
-						  sector_t sector)
+static struct blk_zone_wplug *disk_get_hashed_zone_wplug(struct gendisk *disk,
+							 sector_t sector)
 {
 	unsigned int zno = disk_zone_no(disk, sector);
 	unsigned int idx = hash_32(zno, disk->zone_wplugs_hash_bits);
@@ -437,6 +438,15 @@ static struct blk_zone_wplug *disk_get_zone_wplug(struct gendisk *disk,
 	return NULL;
 }
 
+static inline struct blk_zone_wplug *disk_get_zone_wplug(struct gendisk *disk,
+							 sector_t sector)
+{
+	if (!atomic_read(&disk->nr_zone_wplugs))
+		return NULL;
+
+	return disk_get_hashed_zone_wplug(disk, sector);
+}
+
 static void disk_free_zone_wplug_rcu(struct rcu_head *rcu_head)
 {
 	struct blk_zone_wplug *zwplug =
@@ -503,6 +513,7 @@ static void disk_remove_zone_wplug(struct gendisk *disk,
 	zwplug->flags |= BLK_ZONE_WPLUG_UNHASHED;
 	spin_lock_irqsave(&disk->zone_wplugs_lock, flags);
 	hlist_del_init_rcu(&zwplug->node);
+	atomic_dec(&disk->nr_zone_wplugs);
 	spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags);
 	disk_put_zone_wplug(zwplug);
 }
@@ -593,6 +604,11 @@ static void disk_zone_wplug_abort(struct blk_zone_wplug *zwplug)
 {
 	struct bio *bio;
 
+	if (bio_list_empty(&zwplug->bio_list))
+		return;
+
+	pr_warn_ratelimited("%s: zone %u: Aborting plugged BIOs\n",
+			    zwplug->disk->disk_name, zwplug->zone_no);
 	while ((bio = bio_list_pop(&zwplug->bio_list)))
 		blk_zone_wplug_bio_io_error(zwplug, bio);
 }
@@ -1040,6 +1056,47 @@ static bool blk_zone_wplug_handle_write(struct bio *bio, unsigned int nr_segs)
 	return true;
 }
 
+static void blk_zone_wplug_handle_native_zone_append(struct bio *bio)
+{
+	struct gendisk *disk = bio->bi_bdev->bd_disk;
+	struct blk_zone_wplug *zwplug;
+	unsigned long flags;
+
+	/*
+	 * We have native support for zone append operations, so we are not
+	 * going to handle @bio through plugging. However, we may already have a
+	 * zone write plug for the target zone if that zone was previously
+	 * partially written using regular writes. In such case, we risk leaving
+	 * the plug in the disk hash table if the zone is fully written using
+	 * zone append operations. Avoid this by removing the zone write plug.
+	 */
+	zwplug = disk_get_zone_wplug(disk, bio->bi_iter.bi_sector);
+	if (likely(!zwplug))
+		return;
+
+	spin_lock_irqsave(&zwplug->lock, flags);
+
+	/*
+	 * We are about to remove the zone write plug. But if the user
+	 * (mistakenly) has issued regular writes together with native zone
+	 * append, we must aborts the writes as otherwise the plugged BIOs would
+	 * not be executed by the plug BIO work as disk_get_zone_wplug() will
+	 * return NULL after the plug is removed. Aborting the plugged write
+	 * BIOs is consistent with the fact that these writes will most likely
+	 * fail anyway as there is no ordering guarantees between zone append
+	 * operations and regular write operations.
+	 */
+	if (!bio_list_empty(&zwplug->bio_list)) {
+		pr_warn_ratelimited("%s: zone %u: Invalid mix of zone append and regular writes\n",
+				    disk->disk_name, zwplug->zone_no);
+		disk_zone_wplug_abort(zwplug);
+	}
+	disk_remove_zone_wplug(disk, zwplug);
+	spin_unlock_irqrestore(&zwplug->lock, flags);
+
+	disk_put_zone_wplug(zwplug);
+}
+
 /**
  * blk_zone_plug_bio - Handle a zone write BIO with zone write plugging
  * @bio: The BIO being submitted
@@ -1096,8 +1153,10 @@ bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs)
 	 */
 	switch (bio_op(bio)) {
 	case REQ_OP_ZONE_APPEND:
-		if (!bdev_emulates_zone_append(bdev))
+		if (!bdev_emulates_zone_append(bdev)) {
+			blk_zone_wplug_handle_native_zone_append(bio);
 			return false;
+		}
 		fallthrough;
 	case REQ_OP_WRITE:
 	case REQ_OP_WRITE_ZEROES:
@@ -1284,6 +1343,7 @@ static int disk_alloc_zone_resources(struct gendisk *disk,
 {
 	unsigned int i;
 
+	atomic_set(&disk->nr_zone_wplugs, 0);
 	disk->zone_wplugs_hash_bits =
 		min(ilog2(pool_size) + 1, BLK_ZONE_WPLUG_MAX_HASH_BITS);
 
@@ -1338,6 +1398,7 @@ static void disk_destroy_zone_wplugs_hash_table(struct gendisk *disk)
 		}
 	}
 
+	WARN_ON_ONCE(atomic_read(&disk->nr_zone_wplugs));
 	kfree(disk->zone_wplugs_hash);
 	disk->zone_wplugs_hash = NULL;
 	disk->zone_wplugs_hash_bits = 0;
@@ -1550,11 +1611,12 @@ static int blk_revalidate_seq_zone(struct blk_zone *zone, unsigned int idx,
 	}
 
 	/*
-	 * We need to track the write pointer of all zones that are not
-	 * empty nor full. So make sure we have a zone write plug for
-	 * such zone if the device has a zone write plug hash table.
+	 * If the device needs zone append emulation, we need to track the
+	 * write pointer of all zones that are not empty nor full. So make sure
+	 * we have a zone write plug for such zone if the device has a zone
+	 * write plug hash table.
 	 */
-	if (!disk->zone_wplugs_hash)
+	if (!queue_emulates_zone_append(disk->queue) || !disk->zone_wplugs_hash)
 		return 0;
 
 	disk_zone_wplug_sync_wp_offset(disk, zone);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 58ff5aca83b67..d37751789bf58 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -196,10 +196,11 @@ struct gendisk {
 	unsigned int		zone_capacity;
 	unsigned int		last_zone_capacity;
 	unsigned long __rcu	*conv_zones_bitmap;
-	unsigned int            zone_wplugs_hash_bits;
-	spinlock_t              zone_wplugs_lock;
+	unsigned int		zone_wplugs_hash_bits;
+	atomic_t		nr_zone_wplugs;
+	spinlock_t		zone_wplugs_lock;
 	struct mempool_s	*zone_wplugs_pool;
-	struct hlist_head       *zone_wplugs_hash;
+	struct hlist_head	*zone_wplugs_hash;
 	struct workqueue_struct *zone_wplugs_wq;
 #endif /* CONFIG_BLK_DEV_ZONED */
 

From 79990cf5e7aded76d0c092c9f5ed31eb1c75e02c Mon Sep 17 00:00:00 2001
From: Marcin Szycik <marcin.szycik@linux.intel.com>
Date: Mon, 24 Feb 2025 11:06:41 -0800
Subject: [PATCH 0610/1173] ice: Fix deinitializing VF in error path

If ice_ena_vfs() fails after calling ice_create_vf_entries(), it frees
all VFs without removing them from snapshot PF-VF mailbox list, leading
to list corruption.

Reproducer:
  devlink dev eswitch set $PF1_PCI mode switchdev
  ip l s $PF1 up
  ip l s $PF1 promisc on
  sleep 1
  echo 1 > /sys/class/net/$PF1/device/sriov_numvfs
  sleep 1
  echo 1 > /sys/class/net/$PF1/device/sriov_numvfs

Trace (minimized):
  list_add corruption. next->prev should be prev (ffff8882e241c6f0), but was 0000000000000000. (next=ffff888455da1330).
  kernel BUG at lib/list_debug.c:29!
  RIP: 0010:__list_add_valid_or_report+0xa6/0x100
   ice_mbx_init_vf_info+0xa7/0x180 [ice]
   ice_initialize_vf_entry+0x1fa/0x250 [ice]
   ice_sriov_configure+0x8d7/0x1520 [ice]
   ? __percpu_ref_switch_mode+0x1b1/0x5d0
   ? __pfx_ice_sriov_configure+0x10/0x10 [ice]

Sometimes a KASAN report can be seen instead with a similar stack trace:
  BUG: KASAN: use-after-free in __list_add_valid_or_report+0xf1/0x100

VFs are added to this list in ice_mbx_init_vf_info(), but only removed
in ice_free_vfs(). Move the removing to ice_free_vf_entries(), which is
also being called in other places where VFs are being removed (including
ice_free_vfs() itself).

Fixes: 8cd8a6b17d27 ("ice: move VF overflow message count into struct ice_mbx_vf_info")
Reported-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Closes: https://lore.kernel.org/intel-wired-lan/PH0PR11MB50138B635F2E5CEB7075325D961F2@PH0PR11MB5013.namprd11.prod.outlook.com
Reviewed-by: Martyna Szapar-Mudlaw <martyna.szapar-mudlaw@linux.intel.com>
Signed-off-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://patch.msgid.link/20250224190647.3601930-2-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_sriov.c          | 5 +----
 drivers/net/ethernet/intel/ice/ice_vf_lib.c         | 8 ++++++++
 drivers/net/ethernet/intel/ice/ice_vf_lib_private.h | 1 +
 3 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c
index b83f99c01d91b..8aabf7749aa5e 100644
--- a/drivers/net/ethernet/intel/ice/ice_sriov.c
+++ b/drivers/net/ethernet/intel/ice/ice_sriov.c
@@ -36,6 +36,7 @@ static void ice_free_vf_entries(struct ice_pf *pf)
 
 	hash_for_each_safe(vfs->table, bkt, tmp, vf, entry) {
 		hash_del_rcu(&vf->entry);
+		ice_deinitialize_vf_entry(vf);
 		ice_put_vf(vf);
 	}
 }
@@ -193,10 +194,6 @@ void ice_free_vfs(struct ice_pf *pf)
 			wr32(hw, GLGEN_VFLRSTAT(reg_idx), BIT(bit_idx));
 		}
 
-		/* clear malicious info since the VF is getting released */
-		if (!ice_is_feature_supported(pf, ICE_F_MBX_LIMIT))
-			list_del(&vf->mbx_info.list_entry);
-
 		mutex_unlock(&vf->cfg_lock);
 	}
 
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
index c7c0c2f50c265..815ad0bfe8326 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
@@ -1036,6 +1036,14 @@ void ice_initialize_vf_entry(struct ice_vf *vf)
 	mutex_init(&vf->cfg_lock);
 }
 
+void ice_deinitialize_vf_entry(struct ice_vf *vf)
+{
+	struct ice_pf *pf = vf->pf;
+
+	if (!ice_is_feature_supported(pf, ICE_F_MBX_LIMIT))
+		list_del(&vf->mbx_info.list_entry);
+}
+
 /**
  * ice_dis_vf_qs - Disable the VF queues
  * @vf: pointer to the VF structure
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h
index 0c7e77c0a09fa..5392b04049862 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h
@@ -24,6 +24,7 @@
 #endif
 
 void ice_initialize_vf_entry(struct ice_vf *vf);
+void ice_deinitialize_vf_entry(struct ice_vf *vf);
 void ice_dis_vf_qs(struct ice_vf *vf);
 int ice_check_vf_init(struct ice_vf *vf);
 enum virtchnl_status_code ice_err_to_virt_err(int err);

From 5c07be96d8b3f8447e980f29b967bf2e1d7ac732 Mon Sep 17 00:00:00 2001
From: Marcin Szycik <marcin.szycik@linux.intel.com>
Date: Mon, 24 Feb 2025 11:06:42 -0800
Subject: [PATCH 0611/1173] ice: Avoid setting default Rx VSI twice in
 switchdev setup

As part of switchdev environment setup, uplink VSI is configured as
default for both Tx and Rx. Default Rx VSI is also used by promiscuous
mode. If promisc mode is enabled and an attempt to enter switchdev mode
is made, the setup will fail because Rx VSI is already configured as
default (rule exists).

Reproducer:
  devlink dev eswitch set $PF1_PCI mode switchdev
  ip l s $PF1 up
  ip l s $PF1 promisc on
  echo 1 > /sys/class/net/$PF1/device/sriov_numvfs

In switchdev setup, use ice_set_dflt_vsi() instead of plain
ice_cfg_dflt_vsi(), which avoids repeating setting default VSI for Rx if
it's already configured.

Fixes: 50d62022f455 ("ice: default Tx rule instead of to queue")
Reported-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Closes: https://lore.kernel.org/intel-wired-lan/PH0PR11MB50138B635F2E5CEB7075325D961F2@PH0PR11MB5013.namprd11.prod.outlook.com
Reviewed-by: Martyna Szapar-Mudlaw <martyna.szapar-mudlaw@linux.intel.com>
Signed-off-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://patch.msgid.link/20250224190647.3601930-3-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_eswitch.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c
index fb527434b58b1..d649c197cf673 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch.c
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c
@@ -38,8 +38,7 @@ static int ice_eswitch_setup_env(struct ice_pf *pf)
 	if (ice_vsi_add_vlan_zero(uplink_vsi))
 		goto err_vlan_zero;
 
-	if (ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, true,
-			     ICE_FLTR_RX))
+	if (ice_set_dflt_vsi(uplink_vsi))
 		goto err_def_rx;
 
 	if (ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, true,

From c6124f6fd3ca37d53ec5cbf62f9d9130ef439eca Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Mon, 24 Feb 2025 11:06:44 -0800
Subject: [PATCH 0612/1173] iavf: fix circular lock dependency with netdev_lock

We have recently seen reports of lockdep circular lock dependency warnings
when loading the iAVF driver:

[ 1504.790308] ======================================================
[ 1504.790309] WARNING: possible circular locking dependency detected
[ 1504.790310] 6.13.0 #net_next_rt.c2933b2befe2.el9 Not tainted
[ 1504.790311] ------------------------------------------------------
[ 1504.790312] kworker/u128:0/13566 is trying to acquire lock:
[ 1504.790313] ffff97d0e4738f18 (&dev->lock){+.+.}-{4:4}, at: register_netdevice+0x52c/0x710
[ 1504.790320]
[ 1504.790320] but task is already holding lock:
[ 1504.790321] ffff97d0e47392e8 (&adapter->crit_lock){+.+.}-{4:4}, at: iavf_finish_config+0x37/0x240 [iavf]
[ 1504.790330]
[ 1504.790330] which lock already depends on the new lock.
[ 1504.790330]
[ 1504.790330]
[ 1504.790330] the existing dependency chain (in reverse order) is:
[ 1504.790331]
[ 1504.790331] -> #1 (&adapter->crit_lock){+.+.}-{4:4}:
[ 1504.790333]        __lock_acquire+0x52d/0xbb0
[ 1504.790337]        lock_acquire+0xd9/0x330
[ 1504.790338]        mutex_lock_nested+0x4b/0xb0
[ 1504.790341]        iavf_finish_config+0x37/0x240 [iavf]
[ 1504.790347]        process_one_work+0x248/0x6d0
[ 1504.790350]        worker_thread+0x18d/0x330
[ 1504.790352]        kthread+0x10e/0x250
[ 1504.790354]        ret_from_fork+0x30/0x50
[ 1504.790357]        ret_from_fork_asm+0x1a/0x30
[ 1504.790361]
[ 1504.790361] -> #0 (&dev->lock){+.+.}-{4:4}:
[ 1504.790364]        check_prev_add+0xf1/0xce0
[ 1504.790366]        validate_chain+0x46a/0x570
[ 1504.790368]        __lock_acquire+0x52d/0xbb0
[ 1504.790370]        lock_acquire+0xd9/0x330
[ 1504.790371]        mutex_lock_nested+0x4b/0xb0
[ 1504.790372]        register_netdevice+0x52c/0x710
[ 1504.790374]        iavf_finish_config+0xfa/0x240 [iavf]
[ 1504.790379]        process_one_work+0x248/0x6d0
[ 1504.790381]        worker_thread+0x18d/0x330
[ 1504.790383]        kthread+0x10e/0x250
[ 1504.790385]        ret_from_fork+0x30/0x50
[ 1504.790387]        ret_from_fork_asm+0x1a/0x30
[ 1504.790389]
[ 1504.790389] other info that might help us debug this:
[ 1504.790389]
[ 1504.790389]  Possible unsafe locking scenario:
[ 1504.790389]
[ 1504.790390]        CPU0                    CPU1
[ 1504.790391]        ----                    ----
[ 1504.790391]   lock(&adapter->crit_lock);
[ 1504.790393]                                lock(&dev->lock);
[ 1504.790394]                                lock(&adapter->crit_lock);
[ 1504.790395]   lock(&dev->lock);
[ 1504.790397]
[ 1504.790397]  *** DEADLOCK ***

This appears to be caused by the change in commit 5fda3f35349b ("net: make
netdev_lock() protect netdev->reg_state"), which added a netdev_lock() in
register_netdevice.

The iAVF driver calls register_netdevice() from iavf_finish_config(), as a
final stage of its state machine post-probe. It currently takes the RTNL
lock, then the netdev lock, and then the device critical lock. This pattern
is used throughout the driver. Thus there is a strong dependency that the
crit_lock should not be acquired before the net device lock. The change to
register_netdevice creates an ABBA lock order violation because the iAVF
driver is holding the crit_lock while calling register_netdevice, which
then takes the netdev_lock.

It seems likely that future refactors could result in netdev APIs which
hold the netdev_lock while calling into the driver. This means that we
should not re-order the locks so that netdev_lock is acquired after the
device private crit_lock.

Instead, notice that we already release the netdev_lock prior to calling
the register_netdevice. This flow only happens during the early driver
initialization as we transition through the __IAVF_STARTUP,
__IAVF_INIT_VERSION_CHECK, __IAVF_INIT_GET_RESOURCES, etc.

Analyzing the places where we take crit_lock in the driver there are two
sources:

a) several of the work queue tasks including adminq_task, watchdog_task,
reset_task, and the finish_config task.

b) various callbacks which ultimately stem back to .ndo operations or
ethtool operations.

The latter cannot be triggered until after the netdevice registration is
completed successfully.

The iAVF driver uses alloc_ordered_workqueue, which is an unbound workqueue
that has a max limit of 1, and thus guarantees that only a single work item
on the queue is executing at any given time, so none of the other work
threads could be executing due to the ordered workqueue guarantees.

The iavf_finish_config() function also does not do anything else after
register_netdevice, unless it fails. It seems unlikely that the driver
private crit_lock is protecting anything that register_netdevice() itself
touches.

Thus, to fix this ABBA lock violation, lets simply release the
adapter->crit_lock as well as netdev_lock prior to calling
register_netdevice(). We do still keep holding the RTNL lock as required by
the function. If we do fail to register the netdevice, then we re-acquire
the adapter critical lock to finish the transition back to
__IAVF_INIT_CONFIG_ADAPTER.

This ensures every call where both netdev_lock and the adapter->crit_lock
are acquired under the same ordering.

Fixes: afc664987ab3 ("eth: iavf: extend the netdev_lock usage")
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://patch.msgid.link/20250224190647.3601930-5-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/iavf/iavf_main.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 852e5b62f0a5d..6faa62bced3a2 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -1983,7 +1983,7 @@ static int iavf_reinit_interrupt_scheme(struct iavf_adapter *adapter, bool runni
 static void iavf_finish_config(struct work_struct *work)
 {
 	struct iavf_adapter *adapter;
-	bool netdev_released = false;
+	bool locks_released = false;
 	int pairs, err;
 
 	adapter = container_of(work, struct iavf_adapter, finish_config);
@@ -2012,19 +2012,22 @@ static void iavf_finish_config(struct work_struct *work)
 		netif_set_real_num_tx_queues(adapter->netdev, pairs);
 
 		if (adapter->netdev->reg_state != NETREG_REGISTERED) {
+			mutex_unlock(&adapter->crit_lock);
 			netdev_unlock(adapter->netdev);
-			netdev_released = true;
+			locks_released = true;
 			err = register_netdevice(adapter->netdev);
 			if (err) {
 				dev_err(&adapter->pdev->dev, "Unable to register netdev (%d)\n",
 					err);
 
 				/* go back and try again.*/
+				mutex_lock(&adapter->crit_lock);
 				iavf_free_rss(adapter);
 				iavf_free_misc_irq(adapter);
 				iavf_reset_interrupt_capability(adapter);
 				iavf_change_state(adapter,
 						  __IAVF_INIT_CONFIG_ADAPTER);
+				mutex_unlock(&adapter->crit_lock);
 				goto out;
 			}
 		}
@@ -2040,9 +2043,10 @@ static void iavf_finish_config(struct work_struct *work)
 	}
 
 out:
-	mutex_unlock(&adapter->crit_lock);
-	if (!netdev_released)
+	if (!locks_released) {
+		mutex_unlock(&adapter->crit_lock);
 		netdev_unlock(adapter->netdev);
+	}
 	rtnl_unlock();
 }
 

From b1e44b4aecb551727a368df5b85c535f2ce932ea Mon Sep 17 00:00:00 2001
From: Piotr Kwapulinski <piotr.kwapulinski@intel.com>
Date: Mon, 24 Feb 2025 11:06:45 -0800
Subject: [PATCH 0613/1173] ixgbe: fix media cage present detection for E610
 device

The commit 23c0e5a16bcc ("ixgbe: Add link management support for E610
device") introduced incorrect checking of media cage presence for E610
device. Fix it.

Fixes: 23c0e5a16bcc ("ixgbe: Add link management support for E610 device")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/all/e7d73b32-f12a-49d1-8b60-1ef83359ec13@stanley.mountain/
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Piotr Kwapulinski <piotr.kwapulinski@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Bharath R <bharath.r@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://patch.msgid.link/20250224190647.3601930-6-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c
index 683c668672d65..cb07ecd8937d3 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c
@@ -1122,7 +1122,7 @@ static bool ixgbe_is_media_cage_present(struct ixgbe_hw *hw)
 	 * returns error (ENOENT), then no cage present. If no cage present then
 	 * connection type is backplane or BASE-T.
 	 */
-	return ixgbe_aci_get_netlist_node(hw, cmd, NULL, NULL);
+	return !ixgbe_aci_get_netlist_node(hw, cmd, NULL, NULL);
 }
 
 /**

From 39ab773e4c120f7f98d759415ccc2aca706bbc10 Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Mon, 24 Feb 2025 19:12:44 +0800
Subject: [PATCH 0614/1173] net: enetc: fix the off-by-one issue in
 enetc_map_tx_buffs()

When a DMA mapping error occurs while processing skb frags, it will free
one more tx_swbd than expected, so fix this off-by-one issue.

Fixes: d4fd0404c1c9 ("enetc: Introduce basic PF and VF ENETC ethernet drivers")
Cc: stable@vger.kernel.org
Suggested-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Suggested-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Link: https://patch.msgid.link/20250224111251.1061098-2-wei.fang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/enetc/enetc.c | 26 ++++++++++++++------
 1 file changed, 19 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 6a6fc819dfdee..55ad31a5073e7 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -167,6 +167,24 @@ static bool enetc_skb_is_tcp(struct sk_buff *skb)
 	return skb->csum_offset == offsetof(struct tcphdr, check);
 }
 
+/**
+ * enetc_unwind_tx_frame() - Unwind the DMA mappings of a multi-buffer Tx frame
+ * @tx_ring: Pointer to the Tx ring on which the buffer descriptors are located
+ * @count: Number of Tx buffer descriptors which need to be unmapped
+ * @i: Index of the last successfully mapped Tx buffer descriptor
+ */
+static void enetc_unwind_tx_frame(struct enetc_bdr *tx_ring, int count, int i)
+{
+	while (count--) {
+		struct enetc_tx_swbd *tx_swbd = &tx_ring->tx_swbd[i];
+
+		enetc_free_tx_frame(tx_ring, tx_swbd);
+		if (i == 0)
+			i = tx_ring->bd_count;
+		i--;
+	}
+}
+
 static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
 {
 	bool do_vlan, do_onestep_tstamp = false, do_twostep_tstamp = false;
@@ -372,13 +390,7 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
 dma_err:
 	dev_err(tx_ring->dev, "DMA map error");
 
-	do {
-		tx_swbd = &tx_ring->tx_swbd[i];
-		enetc_free_tx_frame(tx_ring, tx_swbd);
-		if (i == 0)
-			i = tx_ring->bd_count;
-		i--;
-	} while (count--);
+	enetc_unwind_tx_frame(tx_ring, count, i);
 
 	return 0;
 }

From da291996b16ebd10626d4b20288327b743aff110 Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Mon, 24 Feb 2025 19:12:45 +0800
Subject: [PATCH 0615/1173] net: enetc: keep track of correct Tx BD count in
 enetc_map_tx_tso_buffs()

When creating a TSO header, if the skb is VLAN tagged, the extended BD
will be used and the 'count' should be increased by 2 instead of 1.
Otherwise, when an error occurs, less tx_swbd will be freed than the
actual number.

Fixes: fb8629e2cbfc ("net: enetc: add support for software TSO")
Cc: stable@vger.kernel.org
Suggested-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Link: https://patch.msgid.link/20250224111251.1061098-3-wei.fang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/enetc/enetc.c | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 55ad31a5073e7..174db9e2ce813 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -395,14 +395,15 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
 	return 0;
 }
 
-static void enetc_map_tx_tso_hdr(struct enetc_bdr *tx_ring, struct sk_buff *skb,
-				 struct enetc_tx_swbd *tx_swbd,
-				 union enetc_tx_bd *txbd, int *i, int hdr_len,
-				 int data_len)
+static int enetc_map_tx_tso_hdr(struct enetc_bdr *tx_ring, struct sk_buff *skb,
+				struct enetc_tx_swbd *tx_swbd,
+				union enetc_tx_bd *txbd, int *i, int hdr_len,
+				int data_len)
 {
 	union enetc_tx_bd txbd_tmp;
 	u8 flags = 0, e_flags = 0;
 	dma_addr_t addr;
+	int count = 1;
 
 	enetc_clear_tx_bd(&txbd_tmp);
 	addr = tx_ring->tso_headers_dma + *i * TSO_HEADER_SIZE;
@@ -445,7 +446,10 @@ static void enetc_map_tx_tso_hdr(struct enetc_bdr *tx_ring, struct sk_buff *skb,
 		/* Write the BD */
 		txbd_tmp.ext.e_flags = e_flags;
 		*txbd = txbd_tmp;
+		count++;
 	}
+
+	return count;
 }
 
 static int enetc_map_tx_tso_data(struct enetc_bdr *tx_ring, struct sk_buff *skb,
@@ -802,9 +806,9 @@ static int enetc_map_tx_tso_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb
 
 		/* compute the csum over the L4 header */
 		csum = enetc_tso_hdr_csum(&tso, skb, hdr, hdr_len, &pos);
-		enetc_map_tx_tso_hdr(tx_ring, skb, tx_swbd, txbd, &i, hdr_len, data_len);
+		count += enetc_map_tx_tso_hdr(tx_ring, skb, tx_swbd, txbd,
+					      &i, hdr_len, data_len);
 		bd_data_num = 0;
-		count++;
 
 		while (data_len > 0) {
 			int size;

From 432a2cb3ee97a7c6ea578888fe81baad035b9307 Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Mon, 24 Feb 2025 19:12:46 +0800
Subject: [PATCH 0616/1173] net: enetc: correct the xdp_tx statistics

The 'xdp_tx' is used to count the number of XDP_TX frames sent, not the
number of Tx BDs.

Fixes: 7ed2bc80074e ("net: enetc: add support for XDP_TX")
Cc: stable@vger.kernel.org
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://patch.msgid.link/20250224111251.1061098-4-wei.fang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/enetc/enetc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 174db9e2ce813..3cb9ebb13b19b 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -1917,7 +1917,7 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
 				enetc_xdp_drop(rx_ring, orig_i, i);
 				tx_ring->stats.xdp_tx_drops++;
 			} else {
-				tx_ring->stats.xdp_tx += xdp_tx_bd_cnt;
+				tx_ring->stats.xdp_tx++;
 				rx_ring->xdp.xdp_tx_in_flight += xdp_tx_bd_cnt;
 				xdp_tx_frm_cnt++;
 				/* The XDP_TX enqueue was successful, so we

From a562d0c4a893eae3ea51d512c4d90ab858a6b7ec Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Mon, 24 Feb 2025 19:12:47 +0800
Subject: [PATCH 0617/1173] net: enetc: VFs do not support
 HWTSTAMP_TX_ONESTEP_SYNC

Actually ENETC VFs do not support HWTSTAMP_TX_ONESTEP_SYNC because only
ENETC PF can access PMa_SINGLE_STEP registers. And there will be a crash
if VFs are used to test one-step timestamp, the crash log as follows.

[  129.110909] Unable to handle kernel paging request at virtual address 00000000000080c0
[  129.287769] Call trace:
[  129.290219]  enetc_port_mac_wr+0x30/0xec (P)
[  129.294504]  enetc_start_xmit+0xda4/0xe74
[  129.298525]  enetc_xmit+0x70/0xec
[  129.301848]  dev_hard_start_xmit+0x98/0x118

Fixes: 41514737ecaa ("enetc: add get_ts_info interface for ethtool")
Cc: stable@vger.kernel.org
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Tested-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://patch.msgid.link/20250224111251.1061098-5-wei.fang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/enetc/enetc.c         | 3 +++
 drivers/net/ethernet/freescale/enetc/enetc_ethtool.c | 7 +++++--
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 3cb9ebb13b19b..e946d86527904 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -3244,6 +3244,9 @@ static int enetc_hwtstamp_set(struct net_device *ndev, struct ifreq *ifr)
 		new_offloads |= ENETC_F_TX_TSTAMP;
 		break;
 	case HWTSTAMP_TX_ONESTEP_SYNC:
+		if (!enetc_si_is_pf(priv->si))
+			return -EOPNOTSUPP;
+
 		new_offloads &= ~ENETC_F_TX_TSTAMP_MASK;
 		new_offloads |= ENETC_F_TX_ONESTEP_SYNC_TSTAMP;
 		break;
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
index bf34b5bb1e358..ece3ae28ba827 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
@@ -832,6 +832,7 @@ static int enetc_set_coalesce(struct net_device *ndev,
 static int enetc_get_ts_info(struct net_device *ndev,
 			     struct kernel_ethtool_ts_info *info)
 {
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
 	int *phc_idx;
 
 	phc_idx = symbol_get(enetc_phc_index);
@@ -852,8 +853,10 @@ static int enetc_get_ts_info(struct net_device *ndev,
 				SOF_TIMESTAMPING_TX_SOFTWARE;
 
 	info->tx_types = (1 << HWTSTAMP_TX_OFF) |
-			 (1 << HWTSTAMP_TX_ON) |
-			 (1 << HWTSTAMP_TX_ONESTEP_SYNC);
+			 (1 << HWTSTAMP_TX_ON);
+
+	if (enetc_si_is_pf(priv->si))
+		info->tx_types |= (1 << HWTSTAMP_TX_ONESTEP_SYNC);
 
 	info->rx_filters = (1 << HWTSTAMP_FILTER_NONE) |
 			   (1 << HWTSTAMP_FILTER_ALL);

From bbcbc906ab7b5834c1219cd17a38d78dba904aa0 Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Mon, 24 Feb 2025 19:12:48 +0800
Subject: [PATCH 0618/1173] net: enetc: update UDP checksum when updating
 originTimestamp field

There is an issue with one-step timestamp based on UDP/IP. The peer will
discard the sync packet because of the wrong UDP checksum. For ENETC v1,
the software needs to update the UDP checksum when updating the
originTimestamp field, so that the hardware can correctly update the UDP
checksum when updating the correction field. Otherwise, the UDP checksum
in the sync packet will be wrong.

Fixes: 7294380c5211 ("enetc: support PTP Sync packet one-step timestamping")
Cc: stable@vger.kernel.org
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Tested-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://patch.msgid.link/20250224111251.1061098-6-wei.fang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/enetc/enetc.c | 41 ++++++++++++++++----
 1 file changed, 34 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index e946d86527904..9801c51b6a590 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -297,9 +297,11 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
 		}
 
 		if (do_onestep_tstamp) {
-			u32 lo, hi, val;
-			u64 sec, nsec;
+			__be32 new_sec_l, new_nsec;
+			u32 lo, hi, nsec, val;
+			__be16 new_sec_h;
 			u8 *data;
+			u64 sec;
 
 			lo = enetc_rd_hot(hw, ENETC_SICTR0);
 			hi = enetc_rd_hot(hw, ENETC_SICTR1);
@@ -313,13 +315,38 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
 			/* Update originTimestamp field of Sync packet
 			 * - 48 bits seconds field
 			 * - 32 bits nanseconds field
+			 *
+			 * In addition, the UDP checksum needs to be updated
+			 * by software after updating originTimestamp field,
+			 * otherwise the hardware will calculate the wrong
+			 * checksum when updating the correction field and
+			 * update it to the packet.
 			 */
 			data = skb_mac_header(skb);
-			*(__be16 *)(data + offset2) =
-				htons((sec >> 32) & 0xffff);
-			*(__be32 *)(data + offset2 + 2) =
-				htonl(sec & 0xffffffff);
-			*(__be32 *)(data + offset2 + 6) = htonl(nsec);
+			new_sec_h = htons((sec >> 32) & 0xffff);
+			new_sec_l = htonl(sec & 0xffffffff);
+			new_nsec = htonl(nsec);
+			if (udp) {
+				struct udphdr *uh = udp_hdr(skb);
+				__be32 old_sec_l, old_nsec;
+				__be16 old_sec_h;
+
+				old_sec_h = *(__be16 *)(data + offset2);
+				inet_proto_csum_replace2(&uh->check, skb, old_sec_h,
+							 new_sec_h, false);
+
+				old_sec_l = *(__be32 *)(data + offset2 + 2);
+				inet_proto_csum_replace4(&uh->check, skb, old_sec_l,
+							 new_sec_l, false);
+
+				old_nsec = *(__be32 *)(data + offset2 + 6);
+				inet_proto_csum_replace4(&uh->check, skb, old_nsec,
+							 new_nsec, false);
+			}
+
+			*(__be16 *)(data + offset2) = new_sec_h;
+			*(__be32 *)(data + offset2 + 2) = new_sec_l;
+			*(__be32 *)(data + offset2 + 6) = new_nsec;
 
 			/* Configure single-step register */
 			val = ENETC_PM0_SINGLE_STEP_EN;

From 8e43decdfbb477dd7800e3902d2d2f105d22ef5f Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Mon, 24 Feb 2025 19:12:49 +0800
Subject: [PATCH 0619/1173] net: enetc: add missing enetc4_link_deinit()

The enetc4_link_init() is called when the PF driver probes to create
phylink and MDIO bus, but we forgot to call enetc4_link_deinit() to
free the phylink and MDIO bus when the driver was unbound. so add
missing enetc4_link_deinit() to enetc4_pf_netdev_destroy().

Fixes: 99100d0d9922 ("net: enetc: add preliminary support for i.MX95 ENETC PF")
Cc: stable@vger.kernel.org
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://patch.msgid.link/20250224111251.1061098-7-wei.fang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/enetc/enetc4_pf.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
index fc41078c4f5da..48861c8b499a0 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
@@ -684,6 +684,7 @@ static void enetc4_pf_netdev_destroy(struct enetc_si *si)
 	struct net_device *ndev = si->ndev;
 
 	unregister_netdev(ndev);
+	enetc4_link_deinit(priv);
 	enetc_free_msix(priv);
 	free_netdev(ndev);
 }

From 119049b66b883c7e7e575a0b69dc6e3d211662cc Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Mon, 24 Feb 2025 19:12:50 +0800
Subject: [PATCH 0620/1173] net: enetc: remove the mm_lock from the ENETC v4
 driver

Currently, the ENETC v4 driver has not added the MAC merge layer support
in the upstream, so the mm_lock is not initialized and used, so remove
the mm_lock from the driver.

Fixes: 99100d0d9922 ("net: enetc: add preliminary support for i.MX95 ENETC PF")
Cc: stable@vger.kernel.org
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://patch.msgid.link/20250224111251.1061098-8-wei.fang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/enetc/enetc4_pf.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
index 48861c8b499a0..73ac8c6afb3ad 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
@@ -672,7 +672,6 @@ static int enetc4_pf_netdev_create(struct enetc_si *si)
 err_alloc_msix:
 err_config_si:
 err_clk_get:
-	mutex_destroy(&priv->mm_lock);
 	free_netdev(ndev);
 
 	return err;

From 249df695c3ffe8c8d36d46c2580ce72410976f96 Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Mon, 24 Feb 2025 19:12:51 +0800
Subject: [PATCH 0621/1173] net: enetc: fix the off-by-one issue in
 enetc_map_tx_tso_buffs()

There is an off-by-one issue for the err_chained_bd path, it will free
one more tx_swbd than expected. But there is no such issue for the
err_map_data path. To fix this off-by-one issue and make the two error
handling consistent, the increment of 'i' and 'count' remain in sync
and enetc_unwind_tx_frame() is called for error handling.

Fixes: fb8629e2cbfc ("net: enetc: add support for software TSO")
Cc: stable@vger.kernel.org
Suggested-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Link: https://patch.msgid.link/20250224111251.1061098-9-wei.fang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/enetc/enetc.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 9801c51b6a590..2106861463e40 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -859,8 +859,13 @@ static int enetc_map_tx_tso_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb
 			err = enetc_map_tx_tso_data(tx_ring, skb, tx_swbd, txbd,
 						    tso.data, size,
 						    size == data_len);
-			if (err)
+			if (err) {
+				if (i == 0)
+					i = tx_ring->bd_count;
+				i--;
+
 				goto err_map_data;
+			}
 
 			data_len -= size;
 			count++;
@@ -889,13 +894,7 @@ static int enetc_map_tx_tso_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb
 	dev_err(tx_ring->dev, "DMA map error");
 
 err_chained_bd:
-	do {
-		tx_swbd = &tx_ring->tx_swbd[i];
-		enetc_free_tx_frame(tx_ring, tx_swbd);
-		if (i == 0)
-			i = tx_ring->bd_count;
-		i--;
-	} while (count--);
+	enetc_unwind_tx_frame(tx_ring, count, i);
 
 	return 0;
 }

From a41d042757fb36f982413622e890a1c41e043000 Mon Sep 17 00:00:00 2001
From: Chen Wang <unicorn_wang@outlook.com>
Date: Wed, 26 Feb 2025 10:15:01 +0800
Subject: [PATCH 0622/1173] dt-bindings: interrupt-controller: Add Sophgo
 SG2042 MSI

Add binding for Sophgo SG2042 MSI controller.

Signed-off-by: Chen Wang <unicorn_wang@outlook.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://lore.kernel.org/all/44de02977624be334ba6328acfdbb2a375f2071f.1740535748.git.unicorn_wang@outlook.com
---
 .../sophgo,sg2042-msi.yaml                    | 61 +++++++++++++++++++
 1 file changed, 61 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/interrupt-controller/sophgo,sg2042-msi.yaml

diff --git a/Documentation/devicetree/bindings/interrupt-controller/sophgo,sg2042-msi.yaml b/Documentation/devicetree/bindings/interrupt-controller/sophgo,sg2042-msi.yaml
new file mode 100644
index 0000000000000..e1ffd55fa7bf8
--- /dev/null
+++ b/Documentation/devicetree/bindings/interrupt-controller/sophgo,sg2042-msi.yaml
@@ -0,0 +1,61 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/interrupt-controller/sophgo,sg2042-msi.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Sophgo SG2042 MSI Controller
+
+maintainers:
+  - Chen Wang <unicorn_wang@outlook.com>
+
+description:
+  This interrupt controller is in Sophgo SG2042 for transforming interrupts from
+  PCIe MSI to PLIC interrupts.
+
+allOf:
+  - $ref: /schemas/interrupt-controller/msi-controller.yaml#
+
+properties:
+  compatible:
+    const: sophgo,sg2042-msi
+
+  reg:
+    items:
+      - description: clear register
+      - description: msi doorbell address
+
+  reg-names:
+    items:
+      - const: clr
+      - const: doorbell
+
+  msi-controller: true
+
+  msi-ranges:
+    maxItems: 1
+
+  "#msi-cells":
+    const: 0
+
+required:
+  - compatible
+  - reg
+  - reg-names
+  - msi-controller
+  - msi-ranges
+  - "#msi-cells"
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+    msi-controller@30000000 {
+      compatible = "sophgo,sg2042-msi";
+      reg = <0x30000000 0x4>, <0x30000008 0x4>;
+      reg-names = "clr", "doorbell";
+      msi-controller;
+      #msi-cells = <0>;
+      msi-ranges = <&plic 64 IRQ_TYPE_LEVEL_HIGH 32>;
+    };

From c66741549424ca67453885f8b3a5aa81d9abfb34 Mon Sep 17 00:00:00 2001
From: Chen Wang <unicorn_wang@outlook.com>
Date: Wed, 26 Feb 2025 10:15:19 +0800
Subject: [PATCH 0623/1173] irqchip: Add the Sophgo SG2042 MSI interrupt
 controller

Add driver for Sophgo SG2042 MSI interrupt controller.

Signed-off-by: Chen Wang <unicorn_wang@outlook.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Inochi Amaoto <inochiama@gmail.com>
Link: https://lore.kernel.org/all/3104216ca90a5f532bafb676c1c5b1efb19e94d1.1740535748.git.unicorn_wang@outlook.com
---
 drivers/irqchip/Kconfig          |  12 ++
 drivers/irqchip/Makefile         |   1 +
 drivers/irqchip/irq-sg2042-msi.c | 249 +++++++++++++++++++++++++++++++
 3 files changed, 262 insertions(+)
 create mode 100644 drivers/irqchip/irq-sg2042-msi.c

diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index bc3f12af2dc78..441f107116950 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -745,6 +745,18 @@ config MCHP_EIC
 	help
 	  Support for Microchip External Interrupt Controller.
 
+config SOPHGO_SG2042_MSI
+	bool "Sophgo SG2042 MSI Controller"
+	depends on ARCH_SOPHGO || COMPILE_TEST
+	depends on PCI
+	select IRQ_DOMAIN_HIERARCHY
+	select IRQ_MSI_LIB
+	select PCI_MSI
+	help
+	  Support for the Sophgo SG2042 MSI Controller.
+	  This on-chip interrupt controller enables MSI sources to be
+	  routed to the primary PLIC controller on SoC.
+
 config SUNPLUS_SP7021_INTC
 	bool "Sunplus SP7021 interrupt controller" if COMPILE_TEST
 	default SOC_SP7021
diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index 25e9ad29b8c4a..dd60e597491d9 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -128,4 +128,5 @@ obj-$(CONFIG_WPCM450_AIC)		+= irq-wpcm450-aic.o
 obj-$(CONFIG_IRQ_IDT3243X)		+= irq-idt3243x.o
 obj-$(CONFIG_APPLE_AIC)			+= irq-apple-aic.o
 obj-$(CONFIG_MCHP_EIC)			+= irq-mchp-eic.o
+obj-$(CONFIG_SOPHGO_SG2042_MSI)		+= irq-sg2042-msi.o
 obj-$(CONFIG_SUNPLUS_SP7021_INTC)	+= irq-sp7021-intc.o
diff --git a/drivers/irqchip/irq-sg2042-msi.c b/drivers/irqchip/irq-sg2042-msi.c
new file mode 100644
index 0000000000000..ee682e87eb8be
--- /dev/null
+++ b/drivers/irqchip/irq-sg2042-msi.c
@@ -0,0 +1,249 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * SG2042 MSI Controller
+ *
+ * Copyright (C) 2024 Sophgo Technology Inc.
+ * Copyright (C) 2024 Chen Wang <unicorn_wang@outlook.com>
+ */
+
+#include <linux/cleanup.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/msi.h>
+#include <linux/platform_device.h>
+#include <linux/property.h>
+#include <linux/slab.h>
+
+#include "irq-msi-lib.h"
+
+#define SG2042_MAX_MSI_VECTOR	32
+
+struct sg2042_msi_chipdata {
+	void __iomem	*reg_clr;	// clear reg, see TRM, 10.1.33, GP_INTR0_CLR
+
+	phys_addr_t	doorbell_addr;	// see TRM, 10.1.32, GP_INTR0_SET
+
+	u32		irq_first;	// The vector number that MSIs starts
+	u32		num_irqs;	// The number of vectors for MSIs
+
+	DECLARE_BITMAP(msi_map, SG2042_MAX_MSI_VECTOR);
+	struct mutex	msi_map_lock;	// lock for msi_map
+};
+
+static int sg2042_msi_allocate_hwirq(struct sg2042_msi_chipdata *data, int num_req)
+{
+	int first;
+
+	guard(mutex)(&data->msi_map_lock);
+	first = bitmap_find_free_region(data->msi_map, data->num_irqs,
+					get_count_order(num_req));
+	return first >= 0 ? first : -ENOSPC;
+}
+
+static void sg2042_msi_free_hwirq(struct sg2042_msi_chipdata *data, int hwirq, int num_req)
+{
+	guard(mutex)(&data->msi_map_lock);
+	bitmap_release_region(data->msi_map, hwirq, get_count_order(num_req));
+}
+
+static void sg2042_msi_irq_ack(struct irq_data *d)
+{
+	struct sg2042_msi_chipdata *data  = irq_data_get_irq_chip_data(d);
+	int bit_off = d->hwirq;
+
+	writel(1 << bit_off, data->reg_clr);
+
+	irq_chip_ack_parent(d);
+}
+
+static void sg2042_msi_irq_compose_msi_msg(struct irq_data *d, struct msi_msg *msg)
+{
+	struct sg2042_msi_chipdata *data = irq_data_get_irq_chip_data(d);
+
+	msg->address_hi = upper_32_bits(data->doorbell_addr);
+	msg->address_lo = lower_32_bits(data->doorbell_addr);
+	msg->data = 1 << d->hwirq;
+}
+
+static const struct irq_chip sg2042_msi_middle_irq_chip = {
+	.name			= "SG2042 MSI",
+	.irq_ack		= sg2042_msi_irq_ack,
+	.irq_mask		= irq_chip_mask_parent,
+	.irq_unmask		= irq_chip_unmask_parent,
+#ifdef CONFIG_SMP
+	.irq_set_affinity	= irq_chip_set_affinity_parent,
+#endif
+	.irq_compose_msi_msg	= sg2042_msi_irq_compose_msi_msg,
+};
+
+static int sg2042_msi_parent_domain_alloc(struct irq_domain *domain, unsigned int virq, int hwirq)
+{
+	struct sg2042_msi_chipdata *data = domain->host_data;
+	struct irq_fwspec fwspec;
+	struct irq_data *d;
+	int ret;
+
+	fwspec.fwnode = domain->parent->fwnode;
+	fwspec.param_count = 2;
+	fwspec.param[0] = data->irq_first + hwirq;
+	fwspec.param[1] = IRQ_TYPE_EDGE_RISING;
+
+	ret = irq_domain_alloc_irqs_parent(domain, virq, 1, &fwspec);
+	if (ret)
+		return ret;
+
+	d = irq_domain_get_irq_data(domain->parent, virq);
+	return d->chip->irq_set_type(d, IRQ_TYPE_EDGE_RISING);
+}
+
+static int sg2042_msi_middle_domain_alloc(struct irq_domain *domain, unsigned int virq,
+					  unsigned int nr_irqs, void *args)
+{
+	struct sg2042_msi_chipdata *data = domain->host_data;
+	int hwirq, err, i;
+
+	hwirq = sg2042_msi_allocate_hwirq(data, nr_irqs);
+	if (hwirq < 0)
+		return hwirq;
+
+	for (i = 0; i < nr_irqs; i++) {
+		err = sg2042_msi_parent_domain_alloc(domain, virq + i, hwirq + i);
+		if (err)
+			goto err_hwirq;
+
+		irq_domain_set_hwirq_and_chip(domain, virq + i, hwirq + i,
+					      &sg2042_msi_middle_irq_chip, data);
+	}
+
+	return 0;
+
+err_hwirq:
+	sg2042_msi_free_hwirq(data, hwirq, nr_irqs);
+	irq_domain_free_irqs_parent(domain, virq, i);
+
+	return err;
+}
+
+static void sg2042_msi_middle_domain_free(struct irq_domain *domain, unsigned int virq,
+					  unsigned int nr_irqs)
+{
+	struct irq_data *d = irq_domain_get_irq_data(domain, virq);
+	struct sg2042_msi_chipdata *data = irq_data_get_irq_chip_data(d);
+
+	irq_domain_free_irqs_parent(domain, virq, nr_irqs);
+	sg2042_msi_free_hwirq(data, d->hwirq, nr_irqs);
+}
+
+static const struct irq_domain_ops sg2042_msi_middle_domain_ops = {
+	.alloc	= sg2042_msi_middle_domain_alloc,
+	.free	= sg2042_msi_middle_domain_free,
+	.select	= msi_lib_irq_domain_select,
+};
+
+#define SG2042_MSI_FLAGS_REQUIRED (MSI_FLAG_USE_DEF_DOM_OPS |	\
+				   MSI_FLAG_USE_DEF_CHIP_OPS)
+
+#define SG2042_MSI_FLAGS_SUPPORTED MSI_GENERIC_FLAGS_MASK
+
+static const struct msi_parent_ops sg2042_msi_parent_ops = {
+	.required_flags		= SG2042_MSI_FLAGS_REQUIRED,
+	.supported_flags	= SG2042_MSI_FLAGS_SUPPORTED,
+	.bus_select_mask	= MATCH_PCI_MSI,
+	.bus_select_token	= DOMAIN_BUS_NEXUS,
+	.prefix			= "SG2042-",
+	.init_dev_msi_info	= msi_lib_init_dev_msi_info,
+};
+
+static int sg2042_msi_init_domains(struct sg2042_msi_chipdata *data,
+				   struct irq_domain *plic_domain, struct device *dev)
+{
+	struct fwnode_handle *fwnode = dev_fwnode(dev);
+	struct irq_domain *middle_domain;
+
+	middle_domain = irq_domain_create_hierarchy(plic_domain, 0, data->num_irqs, fwnode,
+						    &sg2042_msi_middle_domain_ops, data);
+	if (!middle_domain) {
+		pr_err("Failed to create the MSI middle domain\n");
+		return -ENOMEM;
+	}
+
+	irq_domain_update_bus_token(middle_domain, DOMAIN_BUS_NEXUS);
+
+	middle_domain->flags |= IRQ_DOMAIN_FLAG_MSI_PARENT;
+	middle_domain->msi_parent_ops = &sg2042_msi_parent_ops;
+
+	return 0;
+}
+
+static int sg2042_msi_probe(struct platform_device *pdev)
+{
+	struct fwnode_reference_args args = { };
+	struct sg2042_msi_chipdata *data;
+	struct device *dev = &pdev->dev;
+	struct irq_domain *plic_domain;
+	struct resource *res;
+	int ret;
+
+	data = devm_kzalloc(dev, sizeof(struct sg2042_msi_chipdata), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->reg_clr = devm_platform_ioremap_resource_byname(pdev, "clr");
+	if (IS_ERR(data->reg_clr)) {
+		dev_err(dev, "Failed to map clear register\n");
+		return PTR_ERR(data->reg_clr);
+	}
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "doorbell");
+	if (!res) {
+		dev_err(dev, "Failed get resource from set\n");
+		return -EINVAL;
+	}
+	data->doorbell_addr = res->start;
+
+	ret = fwnode_property_get_reference_args(dev_fwnode(dev), "msi-ranges",
+						 "#interrupt-cells", 0, 0, &args);
+	if (ret) {
+		dev_err(dev, "Unable to parse MSI vec base\n");
+		return ret;
+	}
+	fwnode_handle_put(args.fwnode);
+
+	ret = fwnode_property_get_reference_args(dev_fwnode(dev), "msi-ranges", NULL,
+						 args.nargs + 1, 0, &args);
+	if (ret) {
+		dev_err(dev, "Unable to parse MSI vec number\n");
+		return ret;
+	}
+
+	plic_domain = irq_find_matching_fwnode(args.fwnode, DOMAIN_BUS_ANY);
+	fwnode_handle_put(args.fwnode);
+	if (!plic_domain) {
+		pr_err("Failed to find the PLIC domain\n");
+		return -ENXIO;
+	}
+
+	data->irq_first = (u32)args.args[0];
+	data->num_irqs = (u32)args.args[args.nargs - 1];
+
+	mutex_init(&data->msi_map_lock);
+
+	return sg2042_msi_init_domains(data, plic_domain, dev);
+}
+
+static const struct of_device_id sg2042_msi_of_match[] = {
+	{ .compatible	= "sophgo,sg2042-msi" },
+	{ }
+};
+
+static struct platform_driver sg2042_msi_driver = {
+	.driver = {
+		.name		= "sg2042-msi",
+		.of_match_table	= sg2042_msi_of_match,
+	},
+	.probe = sg2042_msi_probe,
+};
+builtin_platform_driver(sg2042_msi_driver);

From 0edaa4593efe9377b4536211f9bc3812e3e53315 Mon Sep 17 00:00:00 2001
From: Chen Wang <unicorn_wang@outlook.com>
Date: Wed, 26 Feb 2025 10:15:37 +0800
Subject: [PATCH 0624/1173] riscv: sophgo: dts: Add msi controller for SG2042

Add msi-controller node to dts for SG2042.

Signed-off-by: Chen Wang <unicorn_wang@outlook.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/f47c6c3f0309a543d495cb088d6c8c5750bb5647.1740535748.git.unicorn_wang@outlook.com
---
 arch/riscv/boot/dts/sophgo/sg2042.dtsi | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/arch/riscv/boot/dts/sophgo/sg2042.dtsi b/arch/riscv/boot/dts/sophgo/sg2042.dtsi
index e62ac51ac55ab..fef2a0e0f7a3f 100644
--- a/arch/riscv/boot/dts/sophgo/sg2042.dtsi
+++ b/arch/riscv/boot/dts/sophgo/sg2042.dtsi
@@ -173,6 +173,16 @@
 			#clock-cells = <1>;
 		};
 
+		msi: msi-controller@7030010304 {
+			compatible = "sophgo,sg2042-msi";
+			reg = <0x70 0x30010304 0x0 0x4>,
+			      <0x70 0x30010300 0x0 0x4>;
+			reg-names = "clr", "doorbell";
+			msi-controller;
+			#msi-cells = <0>;
+			msi-ranges = <&intc 64 IRQ_TYPE_LEVEL_HIGH 32>;
+		};
+
 		rpgate: clock-controller@7030010368 {
 			compatible = "sophgo,sg2042-rpgate";
 			reg = <0x70 0x30010368 0x0 0x98>;

From 5a4041f2c47247575a6c2e53ce14f7b0ac946c33 Mon Sep 17 00:00:00 2001
From: Naohiro Aota <naohiro.aota@wdc.com>
Date: Wed, 19 Feb 2025 16:02:11 +0900
Subject: [PATCH 0625/1173] btrfs: zoned: fix extent range end unlock in
 cow_file_range()

Running generic/751 on the for-next branch often results in a hang like
below. They are both stack by locking an extent. This suggests someone
forget to unlock an extent.

  INFO: task kworker/u128:1:12 blocked for more than 323 seconds.
        Not tainted 6.13.0-BTRFS-ZNS+ #503
  "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
  task:kworker/u128:1  state:D stack:0     pid:12    tgid:12    ppid:2      flags:0x00004000
  Workqueue: btrfs-fixup btrfs_work_helper [btrfs]
  Call Trace:
   <TASK>
   __schedule+0x534/0xdd0
   schedule+0x39/0x140
   __lock_extent+0x31b/0x380 [btrfs]
   ? __pfx_autoremove_wake_function+0x10/0x10
   btrfs_writepage_fixup_worker+0xf1/0x3a0 [btrfs]
   btrfs_work_helper+0xff/0x480 [btrfs]
   ? lock_release+0x178/0x2c0
   process_one_work+0x1ee/0x570
   ? srso_return_thunk+0x5/0x5f
   worker_thread+0x1d1/0x3b0
   ? __pfx_worker_thread+0x10/0x10
   kthread+0x10b/0x230
   ? __pfx_kthread+0x10/0x10
   ret_from_fork+0x30/0x50
   ? __pfx_kthread+0x10/0x10
   ret_from_fork_asm+0x1a/0x30
   </TASK>
  INFO: task kworker/u134:0:184 blocked for more than 323 seconds.
        Not tainted 6.13.0-BTRFS-ZNS+ #503
  "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
  task:kworker/u134:0  state:D stack:0     pid:184   tgid:184   ppid:2      flags:0x00004000
  Workqueue: writeback wb_workfn (flush-btrfs-4)
  Call Trace:
   <TASK>
   __schedule+0x534/0xdd0
   schedule+0x39/0x140
   __lock_extent+0x31b/0x380 [btrfs]
   ? __pfx_autoremove_wake_function+0x10/0x10
   find_lock_delalloc_range+0xdb/0x260 [btrfs]
   writepage_delalloc+0x12f/0x500 [btrfs]
   ? srso_return_thunk+0x5/0x5f
   extent_write_cache_pages+0x232/0x840 [btrfs]
   btrfs_writepages+0x72/0x130 [btrfs]
   do_writepages+0xe7/0x260
   ? srso_return_thunk+0x5/0x5f
   ? lock_acquire+0xd2/0x300
   ? srso_return_thunk+0x5/0x5f
   ? find_held_lock+0x2b/0x80
   ? wbc_attach_and_unlock_inode.part.0+0x102/0x250
   ? wbc_attach_and_unlock_inode.part.0+0x102/0x250
   __writeback_single_inode+0x5c/0x4b0
   writeback_sb_inodes+0x22d/0x550
   __writeback_inodes_wb+0x4c/0xe0
   wb_writeback+0x2f6/0x3f0
   wb_workfn+0x32a/0x510
   process_one_work+0x1ee/0x570
   ? srso_return_thunk+0x5/0x5f
   worker_thread+0x1d1/0x3b0
   ? __pfx_worker_thread+0x10/0x10
   kthread+0x10b/0x230
   ? __pfx_kthread+0x10/0x10
   ret_from_fork+0x30/0x50
   ? __pfx_kthread+0x10/0x10
   ret_from_fork_asm+0x1a/0x30
   </TASK>

This happens because we have another success path for the zoned mode. When
there is no active zone available, btrfs_reserve_extent() returns
-EAGAIN. In this case, we have two reactions.

(1) If the given range is never allocated, we can only wait for someone
    to finish a zone, so wait on BTRFS_FS_NEED_ZONE_FINISH bit and retry
    afterward.

(2) Or, if some allocations are already done, we must bail out and let
    the caller to send IOs for the allocation. This is because these IOs
    may be necessary to finish a zone.

The commit 06f364284794 ("btrfs: do proper folio cleanup when
cow_file_range() failed") moved the unlock code from the inside of the
loop to the outside. So, previously, the allocated extents are unlocked
just after the allocation and so before returning from the function.
However, they are no longer unlocked on the case (2) above. That caused
the hang issue.

Fix the issue by modifying the 'end' to the end of the allocated
range. Then, we can exit the loop and the same unlock code can properly
handle the case.

Reported-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Tested-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Fixes: 06f364284794 ("btrfs: do proper folio cleanup when cow_file_range() failed")
CC: stable@vger.kernel.org
Reviewed-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index fe2c810335ff0..69e90ed33cfe5 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1382,8 +1382,13 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
 				continue;
 			}
 			if (done_offset) {
-				*done_offset = start - 1;
-				return 0;
+				/*
+				 * Move @end to the end of the processed range,
+				 * and exit the loop to unlock the processed extents.
+				 */
+				end = start - 1;
+				ret = 0;
+				break;
 			}
 			ret = -ENOSPC;
 		}

From 2df2c6ed89600a02e1c7a581a6a55e53c38ce0f5 Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Tue, 25 Feb 2025 20:26:14 +0100
Subject: [PATCH 0626/1173] btrfs: replace deprecated strncpy() with strscpy()

strncpy() is deprecated for NUL-terminated destination buffers. Use
strscpy() instead and don't zero-initialize the param array.

Link: https://github.com/KSPP/linux/issues/90
Cc: linux-hardening@vger.kernel.org
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/sysfs.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 53b846d99ecea..14f53f7575553 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -1330,13 +1330,13 @@ MODULE_PARM_DESC(read_policy,
 
 int btrfs_read_policy_to_enum(const char *str, s64 *value_ret)
 {
-	char param[32] = { 0 };
+	char param[32];
 	char __maybe_unused *value_str;
 
 	if (!str || strlen(str) == 0)
 		return 0;
 
-	strncpy(param, str, sizeof(param) - 1);
+	strscpy(param, str);
 
 #ifdef CONFIG_BTRFS_EXPERIMENTAL
 	/* Separate value from input in policy:value format. */

From 8d52da23b6c68a0f6bad83959ebb61a2cf623c4e Mon Sep 17 00:00:00 2001
From: Wang Hai <wanghai38@huawei.com>
Date: Mon, 24 Feb 2025 17:00:47 +0800
Subject: [PATCH 0627/1173] tcp: Defer ts_recent changes until req is owned

Recently a bug was discovered where the server had entered TCP_ESTABLISHED
state, but the upper layers were not notified.

The same 5-tuple packet may be processed by different CPUSs, so two
CPUs may receive different ack packets at the same time when the
state is TCP_NEW_SYN_RECV.

In that case, req->ts_recent in tcp_check_req may be changed concurrently,
which will probably cause the newsk's ts_recent to be incorrectly large.
So that tcp_validate_incoming will fail. At this point, newsk will not be
able to enter the TCP_ESTABLISHED.

cpu1                                    cpu2
tcp_check_req
                                        tcp_check_req
 req->ts_recent = rcv_tsval = t1
                                         req->ts_recent = rcv_tsval = t2

 syn_recv_sock
  tcp_sk(child)->rx_opt.ts_recent = req->ts_recent = t2 // t1 < t2
tcp_child_process
 tcp_rcv_state_process
  tcp_validate_incoming
   tcp_paws_check
    if ((s32)(rx_opt->ts_recent - rx_opt->rcv_tsval) <= paws_win)
        // t2 - t1 > paws_win, failed
                                        tcp_v4_do_rcv
                                         tcp_rcv_state_process
                                         // TCP_ESTABLISHED

The cpu2's skb or a newly received skb will call tcp_v4_do_rcv to get
the newsk into the TCP_ESTABLISHED state, but at this point it is no
longer possible to notify the upper layer application. A notification
mechanism could be added here, but the fix is more complex, so the
current fix is used.

In tcp_check_req, req->ts_recent is used to assign a value to
tcp_sk(child)->rx_opt.ts_recent, so removing the change in req->ts_recent
and changing tcp_sk(child)->rx_opt.ts_recent directly after owning the
req fixes this bug.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Wang Hai <wanghai38@huawei.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_minisocks.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index b089b08e96178..dfdb7a4608a85 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -815,12 +815,6 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 
 	/* In sequence, PAWS is OK. */
 
-	/* TODO: We probably should defer ts_recent change once
-	 * we take ownership of @req.
-	 */
-	if (tmp_opt.saw_tstamp && !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_nxt))
-		WRITE_ONCE(req->ts_recent, tmp_opt.rcv_tsval);
-
 	if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn) {
 		/* Truncate SYN, it is out of window starting
 		   at tcp_rsk(req)->rcv_isn + 1. */
@@ -869,6 +863,10 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 	if (!child)
 		goto listen_overflow;
 
+	if (own_req && tmp_opt.saw_tstamp &&
+	    !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_nxt))
+		tcp_sk(child)->rx_opt.ts_recent = tmp_opt.rcv_tsval;
+
 	if (own_req && rsk_drop_req(req)) {
 		reqsk_queue_removed(&inet_csk(req->rsk_listener)->icsk_accept_queue, req);
 		inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, req);

From 17bcd714426386fda741a4bccd96a2870179344b Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Mon, 24 Feb 2025 15:55:36 -0800
Subject: [PATCH 0628/1173] KVM: x86: Free vCPUs before freeing VM state

Free vCPUs before freeing any VM state, as both SVM and VMX may access
VM state when "freeing" a vCPU that is currently "in" L2, i.e. that needs
to be kicked out of nested guest mode.

Commit 6fcee03df6a1 ("KVM: x86: avoid loading a vCPU after .vm_destroy was
called") partially fixed the issue, but for unknown reasons only moved the
MMU unloading before VM destruction.  Complete the change, and free all
vCPU state prior to destroying VM state, as nVMX accesses even more state
than nSVM.

In addition to the AVIC, KVM can hit a use-after-free on MSR filters:

  kvm_msr_allowed+0x4c/0xd0
  __kvm_set_msr+0x12d/0x1e0
  kvm_set_msr+0x19/0x40
  load_vmcs12_host_state+0x2d8/0x6e0 [kvm_intel]
  nested_vmx_vmexit+0x715/0xbd0 [kvm_intel]
  nested_vmx_free_vcpu+0x33/0x50 [kvm_intel]
  vmx_free_vcpu+0x54/0xc0 [kvm_intel]
  kvm_arch_vcpu_destroy+0x28/0xf0
  kvm_vcpu_destroy+0x12/0x50
  kvm_arch_destroy_vm+0x12c/0x1c0
  kvm_put_kvm+0x263/0x3c0
  kvm_vm_release+0x21/0x30

and an upcoming fix to process injectable interrupts on nested VM-Exit
will access the PIC:

  BUG: kernel NULL pointer dereference, address: 0000000000000090
  #PF: supervisor read access in kernel mode
  #PF: error_code(0x0000) - not-present page
  CPU: 23 UID: 1000 PID: 2658 Comm: kvm-nx-lpage-re
  RIP: 0010:kvm_cpu_has_extint+0x2f/0x60 [kvm]
  Call Trace:
   <TASK>
   kvm_cpu_has_injectable_intr+0xe/0x60 [kvm]
   nested_vmx_vmexit+0x2d7/0xdf0 [kvm_intel]
   nested_vmx_free_vcpu+0x40/0x50 [kvm_intel]
   vmx_vcpu_free+0x2d/0x80 [kvm_intel]
   kvm_arch_vcpu_destroy+0x2d/0x130 [kvm]
   kvm_destroy_vcpus+0x8a/0x100 [kvm]
   kvm_arch_destroy_vm+0xa7/0x1d0 [kvm]
   kvm_destroy_vm+0x172/0x300 [kvm]
   kvm_vcpu_release+0x31/0x50 [kvm]

Inarguably, both nSVM and nVMX need to be fixed, but punt on those
cleanups for the moment.  Conceptually, vCPUs should be freed before VM
state.  Assets like the I/O APIC and PIC _must_ be allocated before vCPUs
are created, so it stands to reason that they must be freed _after_ vCPUs
are destroyed.

Reported-by: Aaron Lewis <aaronlewis@google.com>
Closes: https://lore.kernel.org/all/20240703175618.2304869-2-aaronlewis@google.com
Cc: Jim Mattson <jmattson@google.com>
Cc: Yan Zhao <yan.y.zhao@intel.com>
Cc: Rick P Edgecombe <rick.p.edgecombe@intel.com>
Cc: Kai Huang <kai.huang@intel.com>
Cc: Isaku Yamahata <isaku.yamahata@intel.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-ID: <20250224235542.2562848-2-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/x86.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 02159c967d29e..6fc4ddc606bd4 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -12877,11 +12877,11 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 		mutex_unlock(&kvm->slots_lock);
 	}
 	kvm_unload_vcpu_mmus(kvm);
+	kvm_destroy_vcpus(kvm);
 	kvm_x86_call(vm_destroy)(kvm);
 	kvm_free_msr_filter(srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1));
 	kvm_pic_destroy(kvm);
 	kvm_ioapic_destroy(kvm);
-	kvm_destroy_vcpus(kvm);
 	kvfree(rcu_dereference_check(kvm->arch.apic_map, 1));
 	kfree(srcu_dereference_check(kvm->arch.pmu_event_filter, &kvm->srcu, 1));
 	kvm_mmu_uninit_vm(kvm);

From 982caaa1150479f022003390cd72a1941663d211 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Mon, 24 Feb 2025 15:55:37 -0800
Subject: [PATCH 0629/1173] KVM: nVMX: Process events on nested VM-Exit if
 injectable IRQ or NMI is pending

Process pending events on nested VM-Exit if the vCPU has an injectable IRQ
or NMI, as the event may have become pending while L2 was active, i.e. may
not be tracked in the context of vmcs01.  E.g. if L1 has passed its APIC
through to L2 and an IRQ arrives while L2 is active, then KVM needs to
request an IRQ window prior to running L1, otherwise delivery of the IRQ
will be delayed until KVM happens to process events for some other reason.

The missed failure is detected by vmx_apic_passthrough_tpr_threshold_test
in KVM-Unit-Tests, but has effectively been masked due to a flaw in KVM's
PIC emulation that causes KVM to make spurious KVM_REQ_EVENT requests (and
apparently no one ever ran the test with split IRQ chips).

Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-ID: <20250224235542.2562848-3-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/vmx/nested.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 8a7af02d466e9..ed8a3cb539612 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -5084,6 +5084,17 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 
 		load_vmcs12_host_state(vcpu, vmcs12);
 
+		/*
+		 * Process events if an injectable IRQ or NMI is pending, even
+		 * if the event is blocked (RFLAGS.IF is cleared on VM-Exit).
+		 * If an event became pending while L2 was active, KVM needs to
+		 * either inject the event or request an IRQ/NMI window.  SMIs
+		 * don't need to be processed as SMM is mutually exclusive with
+		 * non-root mode.  INIT/SIPI don't need to be checked as INIT
+		 * is blocked post-VMXON, and SIPIs are ignored.
+		 */
+		if (kvm_cpu_has_injectable_intr(vcpu) || vcpu->arch.nmi_pending)
+			kvm_make_request(KVM_REQ_EVENT, vcpu);
 		return;
 	}
 

From 2e064e3f3282ec016d80cb7b1fadff0d8e2014ca Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Mon, 10 Feb 2025 19:23:50 +0900
Subject: [PATCH 0630/1173] drm/imagination: remove unnecessary header include
 path

drivers/gpu/drm/imagination/ includes local headers with the double-quote
form (#include "...").

Hence, the header search path addition is unneeded.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Matt Coster <matt.coster@imgtec.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250210102352.1517115-1-masahiroy@kernel.org
Signed-off-by: Matt Coster <matt.coster@imgtec.com>
---
 drivers/gpu/drm/imagination/Makefile | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/gpu/drm/imagination/Makefile b/drivers/gpu/drm/imagination/Makefile
index 9bc6a3884c223..3d9d4d40fb806 100644
--- a/drivers/gpu/drm/imagination/Makefile
+++ b/drivers/gpu/drm/imagination/Makefile
@@ -1,8 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only OR MIT
 # Copyright (c) 2023 Imagination Technologies Ltd.
 
-subdir-ccflags-y := -I$(src)
-
 powervr-y := \
 	pvr_ccb.o \
 	pvr_cccb.o \

From 130ff5c8b78e6fd05270a04985c50bce6a3de6c1 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <cassel@kernel.org>
Date: Tue, 25 Feb 2025 15:16:12 +0100
Subject: [PATCH 0631/1173] ata: ahci: Make ahci_ignore_port() handle empty
 mask_port_map
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 8c87215dd3a2 ("ata: libahci_platform: support non-consecutive port
numbers") added a skip to ahci_platform_enable_phys() for ports that are
not in mask_port_map.

The code in ahci_platform_get_resources(), will currently set mask_port_map
for each child "port" node it finds in the device tree.

However, device trees that do not have any child "port" nodes will not have
mask_port_map set, and for non-device tree platforms mask_port_map will
only exist as a quirk for specific PCI device + vendor IDs, or as a kernel
module parameter, but will not be set by default.

Therefore, the common thing is that mask_port_map is only set if you do not
want to use all ports (as defined by Offset 0Ch: PI – Ports Implemented
register), but instead only want to use the ports in mask_port_map. If
mask_port_map is not set, all ports are available.

Thus, ahci_ignore_port() must be able to handle an empty mask_port_map.

Fixes: 8c87215dd3a2 ("ata: libahci_platform: support non-consecutive port numbers")
Fixes: 2c202e6c4f4d ("ata: libahci_platform: Do not set mask_port_map when not needed")
Fixes: c9b5be909e65 ("ahci: Introduce ahci_ignore_port() helper")
Reported-by: Marek Szyprowski <m.szyprowski@samsung.com>
Closes: https://lore.kernel.org/linux-ide/10b31dd0-d0bb-4f76-9305-2195c3e17670@samsung.com/
Tested-by: Marek Szyprowski <m.szyprowski@samsung.com>
Co-developed-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Link: https://lore.kernel.org/r/20250225141612.942170-2-cassel@kernel.org
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/ahci.h    | 8 ++++++--
 drivers/ata/libahci.c | 1 +
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h
index aea30df50c581..b2e0ef4efbdc3 100644
--- a/drivers/ata/ahci.h
+++ b/drivers/ata/ahci.h
@@ -386,8 +386,12 @@ struct ahci_host_priv {
 static inline bool ahci_ignore_port(struct ahci_host_priv *hpriv,
 				    unsigned int portid)
 {
-	return portid >= hpriv->nports ||
-		!(hpriv->mask_port_map & (1 << portid));
+	if (portid >= hpriv->nports)
+		return true;
+	/* mask_port_map not set means that all ports are available */
+	if (!hpriv->mask_port_map)
+		return false;
+	return !(hpriv->mask_port_map & (1 << portid));
 }
 
 extern int ahci_ignore_sss;
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index fdfa7b2662180..e7ace4b10f15b 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -541,6 +541,7 @@ void ahci_save_initial_config(struct device *dev, struct ahci_host_priv *hpriv)
 		hpriv->saved_port_map = port_map;
 	}
 
+	/* mask_port_map not set means that all ports are available */
 	if (hpriv->mask_port_map) {
 		dev_warn(dev, "masking port_map 0x%lx -> 0x%lx\n",
 			port_map,

From 9d245214b683e9e4fe2d5c588691337b22c48841 Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Mon, 24 Feb 2025 13:11:17 +0000
Subject: [PATCH 0632/1173] dt-bindings: interrupt-controller:
 renesas,rzv2h-icu: Document RZ/G3E SoC

Document RZ/G3E (R9A09G047) ICU bindings. The ICU block on the RZ/G3E
SoC is almost identical to the one found on the RZ/V2H SoC, with the
following differences:
 - The TINT register base offset is 0x800 instead of zero.
 - The number of supported GPIO interrupts for TINT selection is 141
   instead of 86.
 - The pin index and TINT selection index are not in the 1:1 map
 - The number of TSSR registers is 16 instead of 8
 - Each TSSR register can program 2 TINTs instead of 4 TINTs

Hence add the new compatible string "renesas,r9a09g047-icu" for RZ/G3E SoC.

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Fabrizio Castro <fabrizio.castro.jz@renesas.com>
Reviewed-by: Tommaso Merciai <tommaso.merciai.xr@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://lore.kernel.org/all/20250224131253.134199-2-biju.das.jz@bp.renesas.com
---
 .../bindings/interrupt-controller/renesas,rzv2h-icu.yaml    | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/interrupt-controller/renesas,rzv2h-icu.yaml b/Documentation/devicetree/bindings/interrupt-controller/renesas,rzv2h-icu.yaml
index d7ef4f1323a7a..3f99c8645767c 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/renesas,rzv2h-icu.yaml
+++ b/Documentation/devicetree/bindings/interrupt-controller/renesas,rzv2h-icu.yaml
@@ -4,7 +4,7 @@
 $id: http://devicetree.org/schemas/interrupt-controller/renesas,rzv2h-icu.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
-title: Renesas RZ/V2H(P) Interrupt Control Unit
+title: Renesas RZ/{G3E,V2H(P)} Interrupt Control Unit
 
 maintainers:
   - Fabrizio Castro <fabrizio.castro.jz@renesas.com>
@@ -20,7 +20,9 @@ description:
 
 properties:
   compatible:
-    const: renesas,r9a09g057-icu # RZ/V2H(P)
+    enum:
+      - renesas,r9a09g047-icu # RZ/G3E
+      - renesas,r9a09g057-icu # RZ/V2H(P)
 
   '#interrupt-cells':
     description: The first cell is the SPI number of the NMI or the

From 72310650788ad3d3afe3810735656dd291fea885 Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Mon, 24 Feb 2025 13:11:18 +0000
Subject: [PATCH 0633/1173] irqchip/renesas-rzv2h: Fix wrong variable usage in
 rzv2h_tint_set_type()

The variable tssel_n is used for selecting TINT source and titsel_n for
setting the interrupt type. The variable titsel_n is wrongly used for
enabling the TINT interrupt in rzv2h_tint_set_type(). Fix this issue by
using the correct variable tssel_n.

While at it, move the tien variable assignment near to tssr.

Fixes: 0d7605e75ac2 ("irqchip: Add RZ/V2H(P) Interrupt Control Unit (ICU) driver")
Reported-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/all/20250224131253.134199-3-biju.das.jz@bp.renesas.com
Closes: https://lore.kernel.org/CAMuHMdU3xJpz-jh=j7t4JreBat2of2ksP_OR3+nKAoZBr4pSxg@mail.gmail.com
---
 drivers/irqchip/irq-renesas-rzv2h.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/irqchip/irq-renesas-rzv2h.c b/drivers/irqchip/irq-renesas-rzv2h.c
index fe2d29e910261..f6363246a71a0 100644
--- a/drivers/irqchip/irq-renesas-rzv2h.c
+++ b/drivers/irqchip/irq-renesas-rzv2h.c
@@ -301,10 +301,10 @@ static int rzv2h_tint_set_type(struct irq_data *d, unsigned int type)
 
 	tssr_k = ICU_TSSR_K(tint_nr);
 	tssel_n = ICU_TSSR_TSSEL_N(tint_nr);
+	tien = ICU_TSSR_TIEN(tssel_n);
 
 	titsr_k = ICU_TITSR_K(tint_nr);
 	titsel_n = ICU_TITSR_TITSEL_N(tint_nr);
-	tien = ICU_TSSR_TIEN(titsel_n);
 
 	guard(raw_spinlock)(&priv->lock);
 

From c56cab0c3ee063f30d1e53cca7614574e3c2cbd5 Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Mon, 24 Feb 2025 13:11:19 +0000
Subject: [PATCH 0634/1173] irqchip/renesas-rzv2h: Drop irqchip from struct
 rzv2h_icu_priv

Use rzv2h_icu_chip directly on irq_domain_set_hwirq_and_chip() and drop
the global variable irqchip from struct rzv2h_icu_priv.

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Fabrizio Castro <fabrizio.castro.jz@renesas.com>
Reviewed-by: Tommaso Merciai <tommaso.merciai.xr@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/all/20250224131253.134199-4-biju.das.jz@bp.renesas.com
---
 drivers/irqchip/irq-renesas-rzv2h.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/irqchip/irq-renesas-rzv2h.c b/drivers/irqchip/irq-renesas-rzv2h.c
index f6363246a71a0..0573062c89c45 100644
--- a/drivers/irqchip/irq-renesas-rzv2h.c
+++ b/drivers/irqchip/irq-renesas-rzv2h.c
@@ -83,13 +83,11 @@
 /**
  * struct rzv2h_icu_priv - Interrupt Control Unit controller private data structure.
  * @base:	Controller's base address
- * @irqchip:	Pointer to struct irq_chip
  * @fwspec:	IRQ firmware specific data
  * @lock:	Lock to serialize access to hardware registers
  */
 struct rzv2h_icu_priv {
 	void __iomem			*base;
-	const struct irq_chip		*irqchip;
 	struct irq_fwspec		fwspec[ICU_NUM_IRQ];
 	raw_spinlock_t			lock;
 };
@@ -390,7 +388,7 @@ static int rzv2h_icu_alloc(struct irq_domain *domain, unsigned int virq, unsigne
 	if (hwirq > (ICU_NUM_IRQ - 1))
 		return -EINVAL;
 
-	ret = irq_domain_set_hwirq_and_chip(domain, virq, hwirq, priv->irqchip,
+	ret = irq_domain_set_hwirq_and_chip(domain, virq, hwirq, &rzv2h_icu_chip,
 					    (void *)(uintptr_t)tint);
 	if (ret)
 		return ret;
@@ -446,8 +444,6 @@ static int rzv2h_icu_init(struct device_node *node, struct device_node *parent)
 		goto put_dev;
 	}
 
-	rzv2h_icu_data->irqchip = &rzv2h_icu_chip;
-
 	rzv2h_icu_data->base = devm_of_iomap(&pdev->dev, pdev->dev.of_node, 0, NULL);
 	if (IS_ERR(rzv2h_icu_data->base)) {
 		ret = PTR_ERR(rzv2h_icu_data->base);

From f5de95438834a3bc3ad747f67c9da93cd08e5008 Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Mon, 24 Feb 2025 13:11:20 +0000
Subject: [PATCH 0635/1173] irqchip/renesas-rzv2h: Simplify rzv2h_icu_init()

Use devm_add_action_or_reset() for calling put_device in error path of
rzv2h_icu_init() to simplify the code by using the recently added devm_*
helpers.

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de>
Link: https://lore.kernel.org/all/20250224131253.134199-5-biju.das.jz@bp.renesas.com
---
 drivers/irqchip/irq-renesas-rzv2h.c | 37 +++++++++++++++--------------
 1 file changed, 19 insertions(+), 18 deletions(-)

diff --git a/drivers/irqchip/irq-renesas-rzv2h.c b/drivers/irqchip/irq-renesas-rzv2h.c
index 0573062c89c45..d724f32dde8f2 100644
--- a/drivers/irqchip/irq-renesas-rzv2h.c
+++ b/drivers/irqchip/irq-renesas-rzv2h.c
@@ -419,6 +419,11 @@ static int rzv2h_icu_parse_interrupts(struct rzv2h_icu_priv *priv, struct device
 	return 0;
 }
 
+static void rzv2h_icu_put_device(void *data)
+{
+	put_device(data);
+}
+
 static int rzv2h_icu_init(struct device_node *node, struct device_node *parent)
 {
 	struct irq_domain *irq_domain, *parent_domain;
@@ -431,41 +436,39 @@ static int rzv2h_icu_init(struct device_node *node, struct device_node *parent)
 	if (!pdev)
 		return -ENODEV;
 
+	ret = devm_add_action_or_reset(&pdev->dev, rzv2h_icu_put_device,
+				       &pdev->dev);
+	if (ret < 0)
+		return ret;
+
 	parent_domain = irq_find_host(parent);
 	if (!parent_domain) {
 		dev_err(&pdev->dev, "cannot find parent domain\n");
-		ret = -ENODEV;
-		goto put_dev;
+		return -ENODEV;
 	}
 
 	rzv2h_icu_data = devm_kzalloc(&pdev->dev, sizeof(*rzv2h_icu_data), GFP_KERNEL);
-	if (!rzv2h_icu_data) {
-		ret = -ENOMEM;
-		goto put_dev;
-	}
+	if (!rzv2h_icu_data)
+		return -ENOMEM;
 
 	rzv2h_icu_data->base = devm_of_iomap(&pdev->dev, pdev->dev.of_node, 0, NULL);
-	if (IS_ERR(rzv2h_icu_data->base)) {
-		ret = PTR_ERR(rzv2h_icu_data->base);
-		goto put_dev;
-	}
+	if (IS_ERR(rzv2h_icu_data->base))
+		return PTR_ERR(rzv2h_icu_data->base);
 
 	ret = rzv2h_icu_parse_interrupts(rzv2h_icu_data, node);
 	if (ret) {
 		dev_err(&pdev->dev, "cannot parse interrupts: %d\n", ret);
-		goto put_dev;
+		return ret;
 	}
 
 	resetn = devm_reset_control_get_exclusive(&pdev->dev, NULL);
-	if (IS_ERR(resetn)) {
-		ret = PTR_ERR(resetn);
-		goto put_dev;
-	}
+	if (IS_ERR(resetn))
+		return PTR_ERR(resetn);
 
 	ret = reset_control_deassert(resetn);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to deassert resetn pin, %d\n", ret);
-		goto put_dev;
+		return ret;
 	}
 
 	pm_runtime_enable(&pdev->dev);
@@ -496,8 +499,6 @@ static int rzv2h_icu_init(struct device_node *node, struct device_node *parent)
 pm_disable:
 	pm_runtime_disable(&pdev->dev);
 	reset_control_assert(resetn);
-put_dev:
-	put_device(&pdev->dev);
 
 	return ret;
 }

From ad773ebc6e41f0004487726e432b86795ae426d9 Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Mon, 24 Feb 2025 13:11:21 +0000
Subject: [PATCH 0636/1173] irqchip/renesas-rzv2h: Use
 devm_reset_control_get_exclusive_deasserted()

Use devm_reset_control_get_exclusive_deasserted() to simplify
rzv2h_icu_init().

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Tommaso Merciai <tommaso.merciai.xr@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de>
Link: https://lore.kernel.org/all/20250224131253.134199-6-biju.das.jz@bp.renesas.com
---
 drivers/irqchip/irq-renesas-rzv2h.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/irqchip/irq-renesas-rzv2h.c b/drivers/irqchip/irq-renesas-rzv2h.c
index d724f32dde8f2..edae54f9f5da5 100644
--- a/drivers/irqchip/irq-renesas-rzv2h.c
+++ b/drivers/irqchip/irq-renesas-rzv2h.c
@@ -461,13 +461,10 @@ static int rzv2h_icu_init(struct device_node *node, struct device_node *parent)
 		return ret;
 	}
 
-	resetn = devm_reset_control_get_exclusive(&pdev->dev, NULL);
-	if (IS_ERR(resetn))
-		return PTR_ERR(resetn);
-
-	ret = reset_control_deassert(resetn);
-	if (ret) {
-		dev_err(&pdev->dev, "failed to deassert resetn pin, %d\n", ret);
+	resetn = devm_reset_control_get_exclusive_deasserted(&pdev->dev, NULL);
+	if (IS_ERR(resetn)) {
+		ret = PTR_ERR(resetn);
+		dev_err(&pdev->dev, "failed to acquire deasserted reset: %d\n", ret);
 		return ret;
 	}
 
@@ -498,7 +495,6 @@ static int rzv2h_icu_init(struct device_node *node, struct device_node *parent)
 	pm_runtime_put(&pdev->dev);
 pm_disable:
 	pm_runtime_disable(&pdev->dev);
-	reset_control_assert(resetn);
 
 	return ret;
 }

From 5ec8cabc3b8622f95de973c1a245245c65e3337b Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Mon, 24 Feb 2025 13:11:22 +0000
Subject: [PATCH 0637/1173] irqchip/renesas-rzv2h: Use devm_pm_runtime_enable()

Simplify rzv2h_icu_init() by using devm_pm_runtime_enable().

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/all/20250224131253.134199-7-biju.das.jz@bp.renesas.com
---
 drivers/irqchip/irq-renesas-rzv2h.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/irqchip/irq-renesas-rzv2h.c b/drivers/irqchip/irq-renesas-rzv2h.c
index edae54f9f5da5..10b9b63a1f092 100644
--- a/drivers/irqchip/irq-renesas-rzv2h.c
+++ b/drivers/irqchip/irq-renesas-rzv2h.c
@@ -468,11 +468,16 @@ static int rzv2h_icu_init(struct device_node *node, struct device_node *parent)
 		return ret;
 	}
 
-	pm_runtime_enable(&pdev->dev);
+	ret = devm_pm_runtime_enable(&pdev->dev);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "devm_pm_runtime_enable failed, %d\n", ret);
+		return ret;
+	}
+
 	ret = pm_runtime_resume_and_get(&pdev->dev);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "pm_runtime_resume_and_get failed: %d\n", ret);
-		goto pm_disable;
+		return ret;
 	}
 
 	raw_spin_lock_init(&rzv2h_icu_data->lock);
@@ -493,8 +498,6 @@ static int rzv2h_icu_init(struct device_node *node, struct device_node *parent)
 
 pm_put:
 	pm_runtime_put(&pdev->dev);
-pm_disable:
-	pm_runtime_disable(&pdev->dev);
 
 	return ret;
 }

From 0a9d6ef64e5e917f93db98935cd09bac38507ebf Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Mon, 24 Feb 2025 13:11:23 +0000
Subject: [PATCH 0638/1173] irqchip/renesas-rzv2h: Add struct rzv2h_hw_info
 with t_offs variable

The ICU block on the RZ/G3E SoC is almost identical to the one found on
the RZ/V2H SoC, with the following differences:

 - The TINT register base offset is 0x800 instead of zero.
 - The number of GPIO interrupts for TINT selection is 141 instead of 86.
 - The pin index and TINT selection index are not in the 1:1 map
 - The number of TSSR registers is 16 instead of 8
 - Each TSSR register can program 2 TINTs instead of 4 TINTs

Introduce struct rzv2h_hw_info to describe the SoC properties and refactor
the code by moving rzv2h_icu_init() into rzv2h_icu_init_common() and pass
the variable containing hw difference to support both these SoCs.

As a first step add t_offs to the new struct and replace the hardcoded
constants in the code.

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Fabrizio Castro <fabrizio.castro.jz@renesas.com>
Reviewed-by: Tommaso Merciai <tommaso.merciai.xr@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/all/20250224131253.134199-8-biju.das.jz@bp.renesas.com
---
 drivers/irqchip/irq-renesas-rzv2h.c | 46 +++++++++++++++++++++--------
 1 file changed, 34 insertions(+), 12 deletions(-)

diff --git a/drivers/irqchip/irq-renesas-rzv2h.c b/drivers/irqchip/irq-renesas-rzv2h.c
index 10b9b63a1f092..43b805b6df94a 100644
--- a/drivers/irqchip/irq-renesas-rzv2h.c
+++ b/drivers/irqchip/irq-renesas-rzv2h.c
@@ -80,16 +80,26 @@
 #define ICU_TINT_EXTRACT_GPIOINT(x)		FIELD_GET(GENMASK(31, 16), (x))
 #define ICU_PB5_TINT				0x55
 
+/**
+ * struct rzv2h_hw_info - Interrupt Control Unit controller hardware info structure.
+ * @t_offs:		TINT offset
+ */
+struct rzv2h_hw_info {
+	u16		t_offs;
+};
+
 /**
  * struct rzv2h_icu_priv - Interrupt Control Unit controller private data structure.
  * @base:	Controller's base address
  * @fwspec:	IRQ firmware specific data
  * @lock:	Lock to serialize access to hardware registers
+ * @info:	Pointer to struct rzv2h_hw_info
  */
 struct rzv2h_icu_priv {
 	void __iomem			*base;
 	struct irq_fwspec		fwspec[ICU_NUM_IRQ];
 	raw_spinlock_t			lock;
+	const struct rzv2h_hw_info	*info;
 };
 
 static inline struct rzv2h_icu_priv *irq_data_to_priv(struct irq_data *data)
@@ -109,7 +119,7 @@ static void rzv2h_icu_eoi(struct irq_data *d)
 			tintirq_nr = hw_irq - ICU_TINT_START;
 			bit = BIT(tintirq_nr);
 			if (!irqd_is_level_type(d))
-				writel_relaxed(bit, priv->base + ICU_TSCLR);
+				writel_relaxed(bit, priv->base + priv->info->t_offs + ICU_TSCLR);
 		} else if (hw_irq >= ICU_IRQ_START) {
 			tintirq_nr = hw_irq - ICU_IRQ_START;
 			bit = BIT(tintirq_nr);
@@ -137,12 +147,12 @@ static void rzv2h_tint_irq_endisable(struct irq_data *d, bool enable)
 	tssel_n = ICU_TSSR_TSSEL_N(tint_nr);
 
 	guard(raw_spinlock)(&priv->lock);
-	tssr = readl_relaxed(priv->base + ICU_TSSR(k));
+	tssr = readl_relaxed(priv->base + priv->info->t_offs + ICU_TSSR(k));
 	if (enable)
 		tssr |= ICU_TSSR_TIEN(tssel_n);
 	else
 		tssr &= ~ICU_TSSR_TIEN(tssel_n);
-	writel_relaxed(tssr, priv->base + ICU_TSSR(k));
+	writel_relaxed(tssr, priv->base + priv->info->t_offs + ICU_TSSR(k));
 }
 
 static void rzv2h_icu_irq_disable(struct irq_data *d)
@@ -245,8 +255,8 @@ static void rzv2h_clear_tint_int(struct rzv2h_icu_priv *priv, unsigned int hwirq
 	u32 bit = BIT(tint_nr);
 	int k = tint_nr / 16;
 
-	tsctr = readl_relaxed(priv->base + ICU_TSCTR);
-	titsr = readl_relaxed(priv->base + ICU_TITSR(k));
+	tsctr = readl_relaxed(priv->base + priv->info->t_offs + ICU_TSCTR);
+	titsr = readl_relaxed(priv->base + priv->info->t_offs + ICU_TITSR(k));
 	titsel = ICU_TITSR_TITSEL_GET(titsr, titsel_n);
 
 	/*
@@ -255,7 +265,7 @@ static void rzv2h_clear_tint_int(struct rzv2h_icu_priv *priv, unsigned int hwirq
 	 */
 	if ((tsctr & bit) && ((titsel == ICU_TINT_EDGE_RISING) ||
 			      (titsel == ICU_TINT_EDGE_FALLING)))
-		writel_relaxed(bit, priv->base + ICU_TSCLR);
+		writel_relaxed(bit, priv->base + priv->info->t_offs + ICU_TSCLR);
 }
 
 static int rzv2h_tint_set_type(struct irq_data *d, unsigned int type)
@@ -306,21 +316,21 @@ static int rzv2h_tint_set_type(struct irq_data *d, unsigned int type)
 
 	guard(raw_spinlock)(&priv->lock);
 
-	tssr = readl_relaxed(priv->base + ICU_TSSR(tssr_k));
+	tssr = readl_relaxed(priv->base + priv->info->t_offs + ICU_TSSR(tssr_k));
 	tssr &= ~(ICU_TSSR_TSSEL_MASK(tssel_n) | tien);
 	tssr |= ICU_TSSR_TSSEL_PREP(tint, tssel_n);
 
-	writel_relaxed(tssr, priv->base + ICU_TSSR(tssr_k));
+	writel_relaxed(tssr, priv->base + priv->info->t_offs + ICU_TSSR(tssr_k));
 
-	titsr = readl_relaxed(priv->base + ICU_TITSR(titsr_k));
+	titsr = readl_relaxed(priv->base + priv->info->t_offs + ICU_TITSR(titsr_k));
 	titsr &= ~ICU_TITSR_TITSEL_MASK(titsel_n);
 	titsr |= ICU_TITSR_TITSEL_PREP(sense, titsel_n);
 
-	writel_relaxed(titsr, priv->base + ICU_TITSR(titsr_k));
+	writel_relaxed(titsr, priv->base + priv->info->t_offs + ICU_TITSR(titsr_k));
 
 	rzv2h_clear_tint_int(priv, hwirq);
 
-	writel_relaxed(tssr | tien, priv->base + ICU_TSSR(tssr_k));
+	writel_relaxed(tssr | tien, priv->base + priv->info->t_offs + ICU_TSSR(tssr_k));
 
 	return 0;
 }
@@ -424,7 +434,8 @@ static void rzv2h_icu_put_device(void *data)
 	put_device(data);
 }
 
-static int rzv2h_icu_init(struct device_node *node, struct device_node *parent)
+static int rzv2h_icu_init_common(struct device_node *node, struct device_node *parent,
+				 const struct rzv2h_hw_info *hw_info)
 {
 	struct irq_domain *irq_domain, *parent_domain;
 	struct rzv2h_icu_priv *rzv2h_icu_data;
@@ -490,6 +501,8 @@ static int rzv2h_icu_init(struct device_node *node, struct device_node *parent)
 		goto pm_put;
 	}
 
+	rzv2h_icu_data->info = hw_info;
+
 	/*
 	 * coccicheck complains about a missing put_device call before returning, but it's a false
 	 * positive. We still need &pdev->dev after successfully returning from this function.
@@ -502,6 +515,15 @@ static int rzv2h_icu_init(struct device_node *node, struct device_node *parent)
 	return ret;
 }
 
+static const struct rzv2h_hw_info rzv2h_hw_params = {
+	.t_offs		= 0,
+};
+
+static int rzv2h_icu_init(struct device_node *node, struct device_node *parent)
+{
+	return rzv2h_icu_init_common(node, parent, &rzv2h_hw_params);
+}
+
 IRQCHIP_PLATFORM_DRIVER_BEGIN(rzv2h_icu)
 IRQCHIP_MATCH("renesas,r9a09g057-icu", rzv2h_icu_init)
 IRQCHIP_PLATFORM_DRIVER_END(rzv2h_icu)

From eb23d23d082d097e2a8154a57da72061cb7e33b3 Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Mon, 24 Feb 2025 13:11:24 +0000
Subject: [PATCH 0639/1173] irqchip/renesas-rzv2h: Add max_tssel to struct
 rzv2h_hw_info

The number of GPIO interrupts on RZ/G3E for TINT selection is 141 compared
to 86 on RZ/V2H. Rename the macro ICU_PB5_TINT->ICU_RZV2H_TSSEL_MAX_VAL to
hold this difference for RZ/V2H.

Add max_tssel to struct rzv2h_hw_info and replace the hardcoded constants
in the code.

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Fabrizio Castro <fabrizio.castro.jz@renesas.com>
Reviewed-by: Tommaso Merciai <tommaso.merciai.xr@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/all/20250224131253.134199-9-biju.das.jz@bp.renesas.com
---
 drivers/irqchip/irq-renesas-rzv2h.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/irqchip/irq-renesas-rzv2h.c b/drivers/irqchip/irq-renesas-rzv2h.c
index 43b805b6df94a..2fae3274c015e 100644
--- a/drivers/irqchip/irq-renesas-rzv2h.c
+++ b/drivers/irqchip/irq-renesas-rzv2h.c
@@ -78,14 +78,16 @@
 
 #define ICU_TINT_EXTRACT_HWIRQ(x)		FIELD_GET(GENMASK(15, 0), (x))
 #define ICU_TINT_EXTRACT_GPIOINT(x)		FIELD_GET(GENMASK(31, 16), (x))
-#define ICU_PB5_TINT				0x55
+#define ICU_RZV2H_TSSEL_MAX_VAL			0x55
 
 /**
  * struct rzv2h_hw_info - Interrupt Control Unit controller hardware info structure.
  * @t_offs:		TINT offset
+ * @max_tssel:		TSSEL max value
  */
 struct rzv2h_hw_info {
 	u16		t_offs;
+	u8		max_tssel;
 };
 
 /**
@@ -298,13 +300,12 @@ static int rzv2h_tint_set_type(struct irq_data *d, unsigned int type)
 		return -EINVAL;
 	}
 
+	priv = irq_data_to_priv(d);
 	tint = (u32)(uintptr_t)irq_data_get_irq_chip_data(d);
-	if (tint > ICU_PB5_TINT)
+	if (tint > priv->info->max_tssel)
 		return -EINVAL;
 
-	priv = irq_data_to_priv(d);
 	hwirq = irqd_to_hwirq(d);
-
 	tint_nr = hwirq - ICU_TINT_START;
 
 	tssr_k = ICU_TSSR_K(tint_nr);
@@ -517,6 +518,7 @@ static int rzv2h_icu_init_common(struct device_node *node, struct device_node *p
 
 static const struct rzv2h_hw_info rzv2h_hw_params = {
 	.t_offs		= 0,
+	.max_tssel	= ICU_RZV2H_TSSEL_MAX_VAL,
 };
 
 static int rzv2h_icu_init(struct device_node *node, struct device_node *parent)

From 1a6ebcc10b138a6c55f8df2cf6cc630ddabe3cab Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Mon, 24 Feb 2025 13:11:25 +0000
Subject: [PATCH 0640/1173] irqchip/renesas-rzv2h: Add field_width to struct
 rzv2h_hw_info

On RZ/G3E the field width for TSSR register for a TINT is 16 compared to 8
on the RZ/V2H.

Add field_width to struct rzv2h_hw_info and replace the macros ICU_TSSR_K
and ICU_TSSR_TSSEL_N by a runtime evaluation:

    (32 / field_width) provides the number of tints in the TSSR register.

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/all/20250224131253.134199-10-biju.das.jz@bp.renesas.com
---
 drivers/irqchip/irq-renesas-rzv2h.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/irqchip/irq-renesas-rzv2h.c b/drivers/irqchip/irq-renesas-rzv2h.c
index 2fae3274c015e..98a6a7cd36117 100644
--- a/drivers/irqchip/irq-renesas-rzv2h.c
+++ b/drivers/irqchip/irq-renesas-rzv2h.c
@@ -64,8 +64,6 @@
 #define ICU_TINT_LEVEL_HIGH			2
 #define ICU_TINT_LEVEL_LOW			3
 
-#define ICU_TSSR_K(tint_nr)			((tint_nr) / 4)
-#define ICU_TSSR_TSSEL_N(tint_nr)		((tint_nr) % 4)
 #define ICU_TSSR_TSSEL_PREP(tssel, n)		((tssel) << ((n) * 8))
 #define ICU_TSSR_TSSEL_MASK(n)			ICU_TSSR_TSSEL_PREP(0x7F, n)
 #define ICU_TSSR_TIEN(n)			(BIT(7) << ((n) * 8))
@@ -84,10 +82,12 @@
  * struct rzv2h_hw_info - Interrupt Control Unit controller hardware info structure.
  * @t_offs:		TINT offset
  * @max_tssel:		TSSEL max value
+ * @field_width:	TSSR field width
  */
 struct rzv2h_hw_info {
 	u16		t_offs;
 	u8		max_tssel;
+	u8		field_width;
 };
 
 /**
@@ -140,13 +140,15 @@ static void rzv2h_tint_irq_endisable(struct irq_data *d, bool enable)
 	struct rzv2h_icu_priv *priv = irq_data_to_priv(d);
 	unsigned int hw_irq = irqd_to_hwirq(d);
 	u32 tint_nr, tssel_n, k, tssr;
+	u8 nr_tint;
 
 	if (hw_irq < ICU_TINT_START)
 		return;
 
 	tint_nr = hw_irq - ICU_TINT_START;
-	k = ICU_TSSR_K(tint_nr);
-	tssel_n = ICU_TSSR_TSSEL_N(tint_nr);
+	nr_tint = 32 / priv->info->field_width;
+	k = tint_nr / nr_tint;
+	tssel_n = tint_nr % nr_tint;
 
 	guard(raw_spinlock)(&priv->lock);
 	tssr = readl_relaxed(priv->base + priv->info->t_offs + ICU_TSSR(k));
@@ -278,6 +280,7 @@ static int rzv2h_tint_set_type(struct irq_data *d, unsigned int type)
 	unsigned int hwirq;
 	u32 tint, sense;
 	int tint_nr;
+	u8 nr_tint;
 
 	switch (type & IRQ_TYPE_SENSE_MASK) {
 	case IRQ_TYPE_LEVEL_LOW:
@@ -308,8 +311,9 @@ static int rzv2h_tint_set_type(struct irq_data *d, unsigned int type)
 	hwirq = irqd_to_hwirq(d);
 	tint_nr = hwirq - ICU_TINT_START;
 
-	tssr_k = ICU_TSSR_K(tint_nr);
-	tssel_n = ICU_TSSR_TSSEL_N(tint_nr);
+	nr_tint = 32 / priv->info->field_width;
+	tssr_k = tint_nr / nr_tint;
+	tssel_n = tint_nr % nr_tint;
 	tien = ICU_TSSR_TIEN(tssel_n);
 
 	titsr_k = ICU_TITSR_K(tint_nr);
@@ -519,6 +523,7 @@ static int rzv2h_icu_init_common(struct device_node *node, struct device_node *p
 static const struct rzv2h_hw_info rzv2h_hw_params = {
 	.t_offs		= 0,
 	.max_tssel	= ICU_RZV2H_TSSEL_MAX_VAL,
+	.field_width	= 8,
 };
 
 static int rzv2h_icu_init(struct device_node *node, struct device_node *parent)

From 76c3b774734feb8224b78721e0c67a54760a75c5 Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Mon, 24 Feb 2025 13:11:26 +0000
Subject: [PATCH 0641/1173] irqchip/renesas-rzv2h: Update TSSR_TIEN macro

On RZ/G3E, TIEN bit position is at 15 compared to 7 on RZ/V2H. Replace the
macro ICU_TSSR_TIEN(n)->ICU_TSSR_TIEN(n, _field_width) for supporting both
these SoCs.

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/all/20250224131253.134199-11-biju.das.jz@bp.renesas.com
---
 drivers/irqchip/irq-renesas-rzv2h.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/irqchip/irq-renesas-rzv2h.c b/drivers/irqchip/irq-renesas-rzv2h.c
index 98a6a7cd36117..8d0bd4d69de2a 100644
--- a/drivers/irqchip/irq-renesas-rzv2h.c
+++ b/drivers/irqchip/irq-renesas-rzv2h.c
@@ -66,7 +66,11 @@
 
 #define ICU_TSSR_TSSEL_PREP(tssel, n)		((tssel) << ((n) * 8))
 #define ICU_TSSR_TSSEL_MASK(n)			ICU_TSSR_TSSEL_PREP(0x7F, n)
-#define ICU_TSSR_TIEN(n)			(BIT(7) << ((n) * 8))
+#define ICU_TSSR_TIEN(n, field_width)	\
+({\
+		typeof(field_width) (_field_width) = (field_width); \
+		BIT((_field_width) - 1) << ((n) * (_field_width)); \
+})
 
 #define ICU_TITSR_K(tint_nr)			((tint_nr) / 16)
 #define ICU_TITSR_TITSEL_N(tint_nr)		((tint_nr) % 16)
@@ -153,9 +157,9 @@ static void rzv2h_tint_irq_endisable(struct irq_data *d, bool enable)
 	guard(raw_spinlock)(&priv->lock);
 	tssr = readl_relaxed(priv->base + priv->info->t_offs + ICU_TSSR(k));
 	if (enable)
-		tssr |= ICU_TSSR_TIEN(tssel_n);
+		tssr |= ICU_TSSR_TIEN(tssel_n, priv->info->field_width);
 	else
-		tssr &= ~ICU_TSSR_TIEN(tssel_n);
+		tssr &= ~ICU_TSSR_TIEN(tssel_n, priv->info->field_width);
 	writel_relaxed(tssr, priv->base + priv->info->t_offs + ICU_TSSR(k));
 }
 
@@ -314,7 +318,7 @@ static int rzv2h_tint_set_type(struct irq_data *d, unsigned int type)
 	nr_tint = 32 / priv->info->field_width;
 	tssr_k = tint_nr / nr_tint;
 	tssel_n = tint_nr % nr_tint;
-	tien = ICU_TSSR_TIEN(tssel_n);
+	tien = ICU_TSSR_TIEN(tssel_n, priv->info->field_width);
 
 	titsr_k = ICU_TITSR_K(tint_nr);
 	titsel_n = ICU_TITSR_TITSEL_N(tint_nr);

From e3a16c33db69ffd1369ebfdf93f93a93a785896a Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Mon, 24 Feb 2025 13:11:27 +0000
Subject: [PATCH 0642/1173] irqchip/renesas-rzv2h: Update macros
 ICU_TSSR_TSSEL_{MASK,PREP}

On RZ/G3E, TSSEL register field is 8 bits wide compared to 7 on RZ/V2H.
Also bits 8..14 is reserved on RZ/G3E and any writes on these reserved
bits is ignored.

Use bitmask GENMASK(field_width - 2, 0) on both SoCs for extracting TSSEL
and then update the macros ICU_TSSR_TSSEL_PREP and ICU_TSSR_TSSEL_MASK for
supporting both SoCs.

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/all/20250224131253.134199-12-biju.das.jz@bp.renesas.com
---
 drivers/irqchip/irq-renesas-rzv2h.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/irqchip/irq-renesas-rzv2h.c b/drivers/irqchip/irq-renesas-rzv2h.c
index 8d0bd4d69de2a..7bc4397ec1490 100644
--- a/drivers/irqchip/irq-renesas-rzv2h.c
+++ b/drivers/irqchip/irq-renesas-rzv2h.c
@@ -64,8 +64,13 @@
 #define ICU_TINT_LEVEL_HIGH			2
 #define ICU_TINT_LEVEL_LOW			3
 
-#define ICU_TSSR_TSSEL_PREP(tssel, n)		((tssel) << ((n) * 8))
-#define ICU_TSSR_TSSEL_MASK(n)			ICU_TSSR_TSSEL_PREP(0x7F, n)
+#define ICU_TSSR_TSSEL_PREP(tssel, n, field_width)	((tssel) << ((n) * (field_width)))
+#define ICU_TSSR_TSSEL_MASK(n, field_width)	\
+({\
+		typeof(field_width) (_field_width) = (field_width); \
+		ICU_TSSR_TSSEL_PREP((GENMASK(((_field_width) - 2), 0)), (n), _field_width); \
+})
+
 #define ICU_TSSR_TIEN(n, field_width)	\
 ({\
 		typeof(field_width) (_field_width) = (field_width); \
@@ -326,8 +331,8 @@ static int rzv2h_tint_set_type(struct irq_data *d, unsigned int type)
 	guard(raw_spinlock)(&priv->lock);
 
 	tssr = readl_relaxed(priv->base + priv->info->t_offs + ICU_TSSR(tssr_k));
-	tssr &= ~(ICU_TSSR_TSSEL_MASK(tssel_n) | tien);
-	tssr |= ICU_TSSR_TSSEL_PREP(tint, tssel_n);
+	tssr &= ~(ICU_TSSR_TSSEL_MASK(tssel_n, priv->info->field_width) | tien);
+	tssr |= ICU_TSSR_TSSEL_PREP(tint, tssel_n, priv->info->field_width);
 
 	writel_relaxed(tssr, priv->base + priv->info->t_offs + ICU_TSSR(tssr_k));
 

From 399b2799985237cf5c3656b7cfc87cdaa489efd1 Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Mon, 24 Feb 2025 13:11:28 +0000
Subject: [PATCH 0643/1173] irqchip/renesas-rzv2h: Add RZ/G3E support

The ICU block on the RZ/G3E SoC is almost identical to the one found on
the RZ/V2H SoC, with the following differences:

 - The TINT register base offset is 0x800 instead of zero.
 - The number of GPIO interrupts for TINT selection is 141 instead of 86.
 - The pin index and TINT selection index are not in the 1:1 map.
 - The number of TSSR registers is 16 instead of 8.
 - Each TSSR register can program 2 TINTs instead of 4 TINTs.

Add support for the RZ/G3E driver by filling the rzv2h_hw_info table and
adding LUT for mapping between pin index and TINT selection index.

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Fabrizio Castro <fabrizio.castro.jz@renesas.com>
Reviewed-by: Tommaso Merciai <tommaso.merciai.xr@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/all/20250224131253.134199-13-biju.das.jz@bp.renesas.com
---
 drivers/irqchip/irq-renesas-rzv2h.c | 46 +++++++++++++++++++++++++++++
 1 file changed, 46 insertions(+)

diff --git a/drivers/irqchip/irq-renesas-rzv2h.c b/drivers/irqchip/irq-renesas-rzv2h.c
index 7bc4397ec1490..3d5b5fdf9bde8 100644
--- a/drivers/irqchip/irq-renesas-rzv2h.c
+++ b/drivers/irqchip/irq-renesas-rzv2h.c
@@ -85,15 +85,19 @@
 
 #define ICU_TINT_EXTRACT_HWIRQ(x)		FIELD_GET(GENMASK(15, 0), (x))
 #define ICU_TINT_EXTRACT_GPIOINT(x)		FIELD_GET(GENMASK(31, 16), (x))
+#define ICU_RZG3E_TINT_OFFSET			0x800
+#define ICU_RZG3E_TSSEL_MAX_VAL			0x8c
 #define ICU_RZV2H_TSSEL_MAX_VAL			0x55
 
 /**
  * struct rzv2h_hw_info - Interrupt Control Unit controller hardware info structure.
+ * @tssel_lut:		TINT lookup table
  * @t_offs:		TINT offset
  * @max_tssel:		TSSEL max value
  * @field_width:	TSSR field width
  */
 struct rzv2h_hw_info {
+	const u8	*tssel_lut;
 	u16		t_offs;
 	u8		max_tssel;
 	u8		field_width;
@@ -317,6 +321,9 @@ static int rzv2h_tint_set_type(struct irq_data *d, unsigned int type)
 	if (tint > priv->info->max_tssel)
 		return -EINVAL;
 
+	if (priv->info->tssel_lut)
+		tint = priv->info->tssel_lut[tint];
+
 	hwirq = irqd_to_hwirq(d);
 	tint_nr = hwirq - ICU_TINT_START;
 
@@ -529,18 +536,57 @@ static int rzv2h_icu_init_common(struct device_node *node, struct device_node *p
 	return ret;
 }
 
+/* Mapping based on port index on Table 4.2-6 and TSSEL bits on Table 4.6-4 */
+static const u8 rzg3e_tssel_lut[] = {
+	81, 82, 83, 84, 85, 86, 87, 88,		/* P00-P07 */
+	89, 90, 91, 92, 93, 94, 95, 96,		/* P10-P17 */
+	111, 112,				/* P20-P21 */
+	97, 98, 99, 100, 101, 102, 103, 104,	/* P30-P37 */
+	105, 106, 107, 108, 109, 110,		/* P40-P45 */
+	113, 114, 115, 116, 117, 118, 119,	/* P50-P56 */
+	120, 121, 122, 123, 124, 125, 126,	/* P60-P66 */
+	127, 128, 129, 130, 131, 132, 133, 134,	/* P70-P77 */
+	135, 136, 137, 138, 139, 140,		/* P80-P85 */
+	43, 44, 45, 46, 47, 48, 49, 50,		/* PA0-PA7 */
+	51, 52, 53, 54, 55, 56, 57, 58,		/* PB0-PB7 */
+	59, 60,	61,				/* PC0-PC2 */
+	62, 63, 64, 65, 66, 67, 68, 69,		/* PD0-PD7 */
+	70, 71, 72, 73, 74, 75, 76, 77,		/* PE0-PE7 */
+	78, 79, 80,				/* PF0-PF2 */
+	25, 26, 27, 28, 29, 30, 31, 32,		/* PG0-PG7 */
+	33, 34, 35, 36, 37, 38,			/* PH0-PH5 */
+	4, 5, 6, 7, 8,				/* PJ0-PJ4 */
+	39, 40, 41, 42,				/* PK0-PK3 */
+	9, 10, 11, 12, 21, 22, 23, 24,		/* PL0-PL7 */
+	13, 14, 15, 16, 17, 18, 19, 20,		/* PM0-PM7 */
+	0, 1, 2, 3				/* PS0-PS3 */
+};
+
+static const struct rzv2h_hw_info rzg3e_hw_params = {
+	.tssel_lut	= rzg3e_tssel_lut,
+	.t_offs		= ICU_RZG3E_TINT_OFFSET,
+	.max_tssel	= ICU_RZG3E_TSSEL_MAX_VAL,
+	.field_width	= 16,
+};
+
 static const struct rzv2h_hw_info rzv2h_hw_params = {
 	.t_offs		= 0,
 	.max_tssel	= ICU_RZV2H_TSSEL_MAX_VAL,
 	.field_width	= 8,
 };
 
+static int rzg3e_icu_init(struct device_node *node, struct device_node *parent)
+{
+	return rzv2h_icu_init_common(node, parent, &rzg3e_hw_params);
+}
+
 static int rzv2h_icu_init(struct device_node *node, struct device_node *parent)
 {
 	return rzv2h_icu_init_common(node, parent, &rzv2h_hw_params);
 }
 
 IRQCHIP_PLATFORM_DRIVER_BEGIN(rzv2h_icu)
+IRQCHIP_MATCH("renesas,r9a09g047-icu", rzg3e_icu_init)
 IRQCHIP_MATCH("renesas,r9a09g057-icu", rzv2h_icu_init)
 IRQCHIP_PLATFORM_DRIVER_END(rzv2h_icu)
 MODULE_AUTHOR("Fabrizio Castro <fabrizio.castro.jz@renesas.com>");

From 9a54fb31343362f93680543e37afc14484c185d9 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 24 Feb 2025 13:37:04 +0100
Subject: [PATCH 0644/1173] x86/cfi: Add 'cfi=warn' boot option

Rebuilding with CONFIG_CFI_PERMISSIVE=y enabled is such a pain, esp. since
clang is so slow.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Kees Cook <kees@kernel.org>
Link: https://lore.kernel.org/r/20250224124159.924496481@infradead.org
---
 arch/x86/kernel/alternative.c | 3 +++
 include/linux/cfi.h           | 2 ++
 kernel/cfi.c                  | 4 +++-
 3 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 247ee5ffbff47..1142ebd3bb49c 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -1022,6 +1022,9 @@ static __init int cfi_parse_cmdline(char *str)
 			cfi_mode = CFI_FINEIBT;
 		} else if (!strcmp(str, "norand")) {
 			cfi_rand = false;
+		} else if (!strcmp(str, "warn")) {
+			pr_alert("CFI mismatch non-fatal!\n");
+			cfi_warn = true;
 		} else {
 			pr_err("Ignoring unknown cfi option (%s).", str);
 		}
diff --git a/include/linux/cfi.h b/include/linux/cfi.h
index f0df518e11dd1..1db17ecbb86c6 100644
--- a/include/linux/cfi.h
+++ b/include/linux/cfi.h
@@ -11,6 +11,8 @@
 #include <linux/module.h>
 #include <asm/cfi.h>
 
+extern bool cfi_warn;
+
 #ifndef cfi_get_offset
 static inline int cfi_get_offset(void)
 {
diff --git a/kernel/cfi.c b/kernel/cfi.c
index 08caad7767176..19be796395420 100644
--- a/kernel/cfi.c
+++ b/kernel/cfi.c
@@ -7,6 +7,8 @@
 
 #include <linux/cfi.h>
 
+bool cfi_warn __ro_after_init = IS_ENABLED(CONFIG_CFI_PERMISSIVE);
+
 enum bug_trap_type report_cfi_failure(struct pt_regs *regs, unsigned long addr,
 				      unsigned long *target, u32 type)
 {
@@ -17,7 +19,7 @@ enum bug_trap_type report_cfi_failure(struct pt_regs *regs, unsigned long addr,
 		pr_err("CFI failure at %pS (no target information)\n",
 		       (void *)addr);
 
-	if (IS_ENABLED(CONFIG_CFI_PERMISSIVE)) {
+	if (cfi_warn) {
 		__warn(NULL, 0, (void *)addr, 0, regs, NULL);
 		return BUG_TRAP_TYPE_WARN;
 	}

From 500a41acb05a973cb6826ee56df082a97e210a95 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 24 Feb 2025 13:37:05 +0100
Subject: [PATCH 0645/1173] x86/ibt: Add exact_endbr() helper

For when we want to exactly match ENDBR, and not everything that we
can scribble it with.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Kees Cook <kees@kernel.org>
Link: https://lore.kernel.org/r/20250224124200.059556588@infradead.org
---
 arch/x86/kernel/alternative.c | 20 +++++++++++++++++---
 1 file changed, 17 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 1142ebd3bb49c..83316ea470b2b 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -863,6 +863,21 @@ __noendbr bool is_endbr(u32 *val)
 	return false;
 }
 
+#ifdef CONFIG_FINEIBT
+
+static __noendbr bool exact_endbr(u32 *val)
+{
+	u32 endbr;
+
+	__get_kernel_nofault(&endbr, val, u32, Efault);
+	return endbr == gen_endbr();
+
+Efault:
+	return false;
+}
+
+#endif
+
 static void poison_cfi(void *addr);
 
 static void __init_or_module poison_endbr(void *addr)
@@ -1426,10 +1441,9 @@ static void poison_cfi(void *addr)
 bool decode_fineibt_insn(struct pt_regs *regs, unsigned long *target, u32 *type)
 {
 	unsigned long addr = regs->ip - fineibt_preamble_ud2;
-	u32 endbr, hash;
+	u32 hash;
 
-	__get_kernel_nofault(&endbr, addr, u32, Efault);
-	if (endbr != gen_endbr())
+	if (!exact_endbr((void *)addr))
 		return false;
 
 	*target = addr + fineibt_preamble_size;

From 5d703825fde301677e8a79b0738927490407f435 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 26 Feb 2025 12:15:15 +0100
Subject: [PATCH 0646/1173] x86/alternatives: Clean up preprocessor conditional
 block comments

When in the middle of a kernel source code file a kernel developer
sees a lone #else or #endif:

   ...

   #else

   ...

It's not obvious at a glance what those preprocessor blocks are
conditional on, if the starting #ifdef is outside visible range.

So apply the standard pattern we use in such cases elsewhere in
the kernel for large preprocessor blocks:

  #ifdef CONFIG_XXX
  ...
  ...
  ...
  #endif /* CONFIG_XXX */

  ...

  #ifdef CONFIG_XXX
  ...
  ...
  ...
  #else /* !CONFIG_XXX: */
  ...
  ...
  ...
  #endif /* !CONFIG_XXX */

( Note that in the  #else case we use the /* !CONFIG_XXX */ marker
  in the final #endif, not /* CONFIG_XXX */, which serves as an easy
  visual marker to differentiate #else or #elif related #endif closures
  from singular #ifdef/#endif blocks. )

Also clean up __CFI_DEFAULT definition with a bit more vertical alignment
applied, and a pointless tab converted to the standard space we use in
such definitions.

Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: linux-kernel@vger.kernel.org
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 arch/x86/kernel/alternative.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 83316ea470b2b..ea68f0e59cecb 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -839,16 +839,16 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end)
 		}
 	}
 }
-#else
+#else /* !CONFIG_MITIGATION_RETHUNK: */
 void __init_or_module noinline apply_returns(s32 *start, s32 *end) { }
-#endif /* CONFIG_MITIGATION_RETHUNK */
+#endif /* !CONFIG_MITIGATION_RETHUNK */
 
 #else /* !CONFIG_MITIGATION_RETPOLINE || !CONFIG_OBJTOOL */
 
 void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) { }
 void __init_or_module noinline apply_returns(s32 *start, s32 *end) { }
 
-#endif /* CONFIG_MITIGATION_RETPOLINE && CONFIG_OBJTOOL */
+#endif /* !CONFIG_MITIGATION_RETPOLINE || !CONFIG_OBJTOOL */
 
 #ifdef CONFIG_X86_KERNEL_IBT
 
@@ -916,18 +916,18 @@ void __init_or_module noinline apply_seal_endbr(s32 *start, s32 *end)
 	}
 }
 
-#else
+#else /* !CONFIG_X86_KERNEL_IBT: */
 
 void __init_or_module apply_seal_endbr(s32 *start, s32 *end) { }
 
-#endif /* CONFIG_X86_KERNEL_IBT */
+#endif /* !CONFIG_X86_KERNEL_IBT */
 
 #ifdef CONFIG_CFI_AUTO_DEFAULT
-#define __CFI_DEFAULT	CFI_AUTO
+# define __CFI_DEFAULT CFI_AUTO
 #elif defined(CONFIG_CFI_CLANG)
-#define __CFI_DEFAULT	CFI_KCFI
+# define __CFI_DEFAULT CFI_KCFI
 #else
-#define __CFI_DEFAULT	CFI_OFF
+# define __CFI_DEFAULT CFI_OFF
 #endif
 
 enum cfi_mode cfi_mode __ro_after_init = __CFI_DEFAULT;
@@ -1457,7 +1457,7 @@ bool decode_fineibt_insn(struct pt_regs *regs, unsigned long *target, u32 *type)
 	return false;
 }
 
-#else
+#else /* !CONFIG_FINEIBT: */
 
 static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 			    s32 *start_cfi, s32 *end_cfi, bool builtin)
@@ -1468,7 +1468,7 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 static void poison_cfi(void *addr) { }
 #endif
 
-#endif
+#endif /* !CONFIG_FINEIBT */
 
 void apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 		   s32 *start_cfi, s32 *end_cfi)

From 6447828875b7d768e4ef0f58765b4bd4e16bcf18 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nik.borisov@suse.com>
Date: Tue, 25 Feb 2025 16:33:48 +0200
Subject: [PATCH 0647/1173] x86/mce/inject: Remove call to mce_notify_irq()

The call to mce_notify_irq() has been there since the initial version of
the soft inject mce machinery, introduced in

  ea149b36c7f5 ("x86, mce: add basic error injection infrastructure").

At that time it was functional since injecting an MCE resulted in the
following call chain:

  raise_mce()
    ->machine_check_poll()
        ->mce_log() - sets notfiy_user_bit
  ->mce_notify_user() (current mce_notify_irq) consumed the bit and called the
  usermode helper.

However, with the introduction of

  011d82611172 ("RAS: Add a Corrected Errors Collector")

the code got moved around and the usermode helper began to be called via the
early notifier mce_first_notifier() rendering the call in raise_local()
defunct as the mce_need_notify bit (ex notify_user) is only being set from the
early notifier.

Remove the noop call and make mce_notify_irq() static.

No functional changes.

Signed-off-by: Nikolay Borisov <nik.borisov@suse.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20250225143348.268469-1-nik.borisov@suse.com
---
 arch/x86/include/asm/mce.h       |  2 --
 arch/x86/kernel/cpu/mce/core.c   | 44 ++++++++++++++++----------------
 arch/x86/kernel/cpu/mce/inject.c |  1 -
 3 files changed, 22 insertions(+), 25 deletions(-)

diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index eb2db07ef39c8..6c77c03139f7f 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -296,8 +296,6 @@ enum mcp_flags {
 
 void machine_check_poll(enum mcp_flags flags, mce_banks_t *b);
 
-bool mce_notify_irq(void);
-
 DECLARE_PER_CPU(struct mce, injectm);
 
 /* Disable CMCI/polling for MCA bank claimed by firmware */
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 0dc00c9894c7c..1f14c3308b6b4 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -584,6 +584,28 @@ bool mce_is_correctable(struct mce *m)
 }
 EXPORT_SYMBOL_GPL(mce_is_correctable);
 
+/*
+ * Notify the user(s) about new machine check events.
+ * Can be called from interrupt context, but not from machine check/NMI
+ * context.
+ */
+static bool mce_notify_irq(void)
+{
+	/* Not more than two messages every minute */
+	static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2);
+
+	if (test_and_clear_bit(0, &mce_need_notify)) {
+		mce_work_trigger();
+
+		if (__ratelimit(&ratelimit))
+			pr_info(HW_ERR "Machine check events logged\n");
+
+		return true;
+	}
+
+	return false;
+}
+
 static int mce_early_notifier(struct notifier_block *nb, unsigned long val,
 			      void *data)
 {
@@ -1773,28 +1795,6 @@ static void mce_timer_delete_all(void)
 		del_timer_sync(&per_cpu(mce_timer, cpu));
 }
 
-/*
- * Notify the user(s) about new machine check events.
- * Can be called from interrupt context, but not from machine check/NMI
- * context.
- */
-bool mce_notify_irq(void)
-{
-	/* Not more than two messages every minute */
-	static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2);
-
-	if (test_and_clear_bit(0, &mce_need_notify)) {
-		mce_work_trigger();
-
-		if (__ratelimit(&ratelimit))
-			pr_info(HW_ERR "Machine check events logged\n");
-
-		return true;
-	}
-	return false;
-}
-EXPORT_SYMBOL_GPL(mce_notify_irq);
-
 static void __mcheck_cpu_mce_banks_init(void)
 {
 	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c
index 313fe682db339..06e3cf7229ce9 100644
--- a/arch/x86/kernel/cpu/mce/inject.c
+++ b/arch/x86/kernel/cpu/mce/inject.c
@@ -229,7 +229,6 @@ static int raise_local(void)
 	} else if (m->status) {
 		pr_info("Starting machine check poll CPU %d\n", cpu);
 		raise_poll(m);
-		mce_notify_irq();
 		pr_info("Machine check poll done on CPU %d\n", cpu);
 	} else
 		m->finished = 0;

From 2e044911be75ce3321c5b3d10205ac0b54f8cb92 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 24 Feb 2025 13:37:06 +0100
Subject: [PATCH 0648/1173] x86/traps: Decode 0xEA instructions as #UD

FineIBT will start using 0xEA as #UD. Normally '0xEA' is a 'bad',
invalid instruction for the CPU.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Kees Cook <kees@kernel.org>
Link: https://lore.kernel.org/r/20250224124200.166774696@infradead.org
---
 arch/x86/include/asm/bug.h |  1 +
 arch/x86/kernel/traps.c    | 20 +++++++++++++++++---
 2 files changed, 18 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index 1a5e4b3726940..bc8a2ca3c82ef 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -25,6 +25,7 @@
 #define BUG_UD2			0xfffe
 #define BUG_UD1			0xfffd
 #define BUG_UD1_UBSAN		0xfffc
+#define BUG_EA			0xffea
 
 #ifdef CONFIG_GENERIC_BUG
 
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 05b86c05e446c..a02a51bf433fa 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -96,6 +96,7 @@ __always_inline int is_valid_bugaddr(unsigned long addr)
  * Check for UD1 or UD2, accounting for Address Size Override Prefixes.
  * If it's a UD1, further decode to determine its use:
  *
+ * FineIBT:      ea                      (bad)
  * UBSan{0}:     67 0f b9 00             ud1    (%eax),%eax
  * UBSan{10}:    67 0f b9 40 10          ud1    0x10(%eax),%eax
  * static_call:  0f b9 cc                ud1    %esp,%ecx
@@ -113,6 +114,10 @@ __always_inline int decode_bug(unsigned long addr, s32 *imm, int *len)
 	v = *(u8 *)(addr++);
 	if (v == INSN_ASOP)
 		v = *(u8 *)(addr++);
+	if (v == 0xea) {
+		*len = addr - start;
+		return BUG_EA;
+	}
 	if (v != OPCODE_ESCAPE)
 		return BUG_NONE;
 
@@ -309,10 +314,16 @@ static noinstr bool handle_bug(struct pt_regs *regs)
 
 	switch (ud_type) {
 	case BUG_UD2:
-		if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN ||
-		    handle_cfi_failure(regs) == BUG_TRAP_TYPE_WARN) {
-			regs->ip += ud_len;
+		if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN) {
+			handled = true;
+			break;
+		}
+		fallthrough;
+
+	case BUG_EA:
+		if (handle_cfi_failure(regs) == BUG_TRAP_TYPE_WARN) {
 			handled = true;
+			break;
 		}
 		break;
 
@@ -328,6 +339,9 @@ static noinstr bool handle_bug(struct pt_regs *regs)
 		break;
 	}
 
+	if (handled)
+		regs->ip += ud_len;
+
 	if (regs->flags & X86_EFLAGS_IF)
 		raw_local_irq_disable();
 	instrumentation_end();

From e33d805a1005bf7b8a5a53559c81a8e17f0b981b Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 24 Feb 2025 13:37:07 +0100
Subject: [PATCH 0649/1173] x86/traps: Allow custom fixups in handle_bug()

The normal fixup in handle_bug() is simply continuing at the next
instruction. However upcoming patches make this the wrong thing, so
allow handlers (specifically handle_cfi_failure()) to over-ride
regs->ip.

The callchain is such that the fixup needs to be done before it is
determined if the exception is fatal, as such, revert any changes in
that case.

Additionally, have handle_cfi_failure() remember the regs->ip value it
starts with for reporting.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Kees Cook <kees@kernel.org>
Link: https://lore.kernel.org/r/20250224124200.275223080@infradead.org
---
 arch/x86/kernel/cfi.c   |  8 ++++----
 arch/x86/kernel/traps.c | 16 +++++++++++++---
 2 files changed, 17 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kernel/cfi.c b/arch/x86/kernel/cfi.c
index f6905bef0af84..77086cf565ec1 100644
--- a/arch/x86/kernel/cfi.c
+++ b/arch/x86/kernel/cfi.c
@@ -67,16 +67,16 @@ static bool decode_cfi_insn(struct pt_regs *regs, unsigned long *target,
  */
 enum bug_trap_type handle_cfi_failure(struct pt_regs *regs)
 {
-	unsigned long target;
+	unsigned long target, addr = regs->ip;
 	u32 type;
 
 	switch (cfi_mode) {
 	case CFI_KCFI:
-		if (!is_cfi_trap(regs->ip))
+		if (!is_cfi_trap(addr))
 			return BUG_TRAP_TYPE_NONE;
 
 		if (!decode_cfi_insn(regs, &target, &type))
-			return report_cfi_failure_noaddr(regs, regs->ip);
+			return report_cfi_failure_noaddr(regs, addr);
 
 		break;
 
@@ -90,7 +90,7 @@ enum bug_trap_type handle_cfi_failure(struct pt_regs *regs)
 		return BUG_TRAP_TYPE_NONE;
 	}
 
-	return report_cfi_failure(regs, regs->ip, &target, type);
+	return report_cfi_failure(regs, addr, &target, type);
 }
 
 /*
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index a02a51bf433fa..c169f3bd3c6c0 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -287,11 +287,12 @@ static inline void handle_invalid_op(struct pt_regs *regs)
 
 static noinstr bool handle_bug(struct pt_regs *regs)
 {
+	unsigned long addr = regs->ip;
 	bool handled = false;
 	int ud_type, ud_len;
 	s32 ud_imm;
 
-	ud_type = decode_bug(regs->ip, &ud_imm, &ud_len);
+	ud_type = decode_bug(addr, &ud_imm, &ud_len);
 	if (ud_type == BUG_NONE)
 		return handled;
 
@@ -339,8 +340,17 @@ static noinstr bool handle_bug(struct pt_regs *regs)
 		break;
 	}
 
-	if (handled)
-		regs->ip += ud_len;
+	/*
+	 * When continuing, and regs->ip hasn't changed, move it to the next
+	 * instruction. When not continuing execution, restore the instruction
+	 * pointer.
+	 */
+	if (handled) {
+		if (regs->ip == addr)
+			regs->ip += ud_len;
+	} else {
+		regs->ip = addr;
+	}
 
 	if (regs->flags & X86_EFLAGS_IF)
 		raw_local_irq_disable();

From 06926c6cdb955bf24521d4e13af95b4d062d02d0 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 24 Feb 2025 13:37:08 +0100
Subject: [PATCH 0650/1173] x86/ibt: Optimize the FineIBT instruction sequence

Scott notes that non-taken branches are faster. Abuse overlapping code
that traps instead of explicit UD2 instructions.

And LEA does not modify flags and will have less dependencies.

Suggested-by: Scott Constable <scott.d.constable@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Kees Cook <kees@kernel.org>
Link: https://lore.kernel.org/r/20250224124200.371942555@infradead.org
---
 arch/x86/kernel/alternative.c | 61 +++++++++++++++++++++++------------
 arch/x86/net/bpf_jit_comp.c   |  5 ++-
 2 files changed, 42 insertions(+), 24 deletions(-)

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index ea68f0e59cecb..a2e8ee8029eb8 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -1057,9 +1057,9 @@ early_param("cfi", cfi_parse_cmdline);
  * __cfi_\func:					__cfi_\func:
  *	movl   $0x12345678,%eax		// 5	     endbr64			// 4
  *	nop					     subl   $0x12345678,%r10d   // 7
- *	nop					     jz     1f			// 2
- *	nop					     ud2			// 2
- *	nop					1:   nop			// 1
+ *	nop					     jne    __cfi_\func+6	// 2
+ *	nop					     nop3			// 3
+ *	nop
  *	nop
  *	nop
  *	nop
@@ -1071,37 +1071,50 @@ early_param("cfi", cfi_parse_cmdline);
  *
  * caller:					caller:
  *	movl	$(-0x12345678),%r10d	 // 6	     movl   $0x12345678,%r10d	// 6
- *	addl	$-15(%r11),%r10d	 // 4	     sub    $16,%r11		// 4
+ *	addl	$-15(%r11),%r10d	 // 4	     lea    -0x10(%r11),%r11	// 4
  *	je	1f			 // 2	     nop4			// 4
  *	ud2				 // 2
- * 1:	call	__x86_indirect_thunk_r11 // 5	     call   *%r11; nop2;	// 5
+ * 1:	cs call	__x86_indirect_thunk_r11 // 6	     call   *%r11; nop3;	// 6
  *
  */
 
-asm(	".pushsection .rodata			\n"
-	"fineibt_preamble_start:		\n"
-	"	endbr64				\n"
-	"	subl	$0x12345678, %r10d	\n"
-	"	je	fineibt_preamble_end	\n"
-	"fineibt_preamble_ud2:			\n"
-	"	ud2				\n"
-	"	nop				\n"
-	"fineibt_preamble_end:			\n"
+/*
+ * <fineibt_preamble_start>:
+ *  0:   f3 0f 1e fa             endbr64
+ *  4:   41 81 <ea> 78 56 34 12  sub    $0x12345678, %r10d
+ *  b:   75 f9                   jne    6 <fineibt_preamble_start+0x6>
+ *  d:   0f 1f 00                nopl   (%rax)
+ *
+ * Note that the JNE target is the 0xEA byte inside the SUB, this decodes as
+ * (bad) on x86_64 and raises #UD.
+ */
+asm(	".pushsection .rodata				\n"
+	"fineibt_preamble_start:			\n"
+	"	endbr64					\n"
+	"	subl	$0x12345678, %r10d		\n"
+	"	jne	fineibt_preamble_start+6	\n"
+	ASM_NOP3
+	"fineibt_preamble_end:				\n"
 	".popsection\n"
 );
 
 extern u8 fineibt_preamble_start[];
-extern u8 fineibt_preamble_ud2[];
 extern u8 fineibt_preamble_end[];
 
 #define fineibt_preamble_size (fineibt_preamble_end - fineibt_preamble_start)
-#define fineibt_preamble_ud2  (fineibt_preamble_ud2 - fineibt_preamble_start)
+#define fineibt_preamble_ud   6
 #define fineibt_preamble_hash 7
 
+/*
+ * <fineibt_caller_start>:
+ *  0:   41 ba 78 56 34 12       mov    $0x12345678, %r10d
+ *  6:   4d 8d 5b f0             lea    -0x10(%r11), %r11
+ *  a:   0f 1f 40 00             nopl   0x0(%rax)
+ */
 asm(	".pushsection .rodata			\n"
 	"fineibt_caller_start:			\n"
 	"	movl	$0x12345678, %r10d	\n"
-	"	sub	$16, %r11		\n"
+	"	lea	-0x10(%r11), %r11	\n"
 	ASM_NOP4
 	"fineibt_caller_end:			\n"
 	".popsection				\n"
@@ -1432,15 +1445,15 @@ static void poison_cfi(void *addr)
 }
 
 /*
- * regs->ip points to a UD2 instruction, return true and fill out target and
- * type when this UD2 is from a FineIBT preamble.
+ * When regs->ip points to a 0xEA byte in the FineIBT preamble,
+ * return true and fill out target and type.
  *
  * We check the preamble by checking for the ENDBR instruction relative to the
- * UD2 instruction.
+ * 0xEA instruction.
  */
 bool decode_fineibt_insn(struct pt_regs *regs, unsigned long *target, u32 *type)
 {
-	unsigned long addr = regs->ip - fineibt_preamble_ud2;
+	unsigned long addr = regs->ip - fineibt_preamble_ud;
 	u32 hash;
 
 	if (!exact_endbr((void *)addr))
@@ -1451,6 +1464,12 @@ bool decode_fineibt_insn(struct pt_regs *regs, unsigned long *target, u32 *type)
 	__get_kernel_nofault(&hash, addr + fineibt_preamble_hash, u32, Efault);
 	*type = (u32)regs->r10 + hash;
 
+	/*
+	 * Since regs->ip points to the middle of an instruction; it cannot
+	 * continue with the normal fixup.
+	 */
+	regs->ip = *target;
+
 	return true;
 
 Efault:
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index f36508b67278a..ce033e63bc27b 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -417,9 +417,8 @@ static void emit_fineibt(u8 **pprog, u32 hash)
 
 	EMIT_ENDBR();
 	EMIT3_off32(0x41, 0x81, 0xea, hash);		/* subl $hash, %r10d	*/
-	EMIT2(0x74, 0x07);				/* jz.d8 +7		*/
-	EMIT2(0x0f, 0x0b);				/* ud2			*/
-	EMIT1(0x90);					/* nop			*/
+	EMIT2(0x75, 0xf9);				/* jne.d8 .-7		*/
+	EMIT3(0x0f, 0x1f, 0x00);			/* nop3			*/
 	EMIT_ENDBR_POISON();
 
 	*pprog = prog;

From 029f718fedd72872f7475604fe71b2a841108834 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 24 Feb 2025 13:37:09 +0100
Subject: [PATCH 0651/1173] x86/traps: Decode LOCK Jcc.d8 as #UD

Because overlapping code sequences are all the rage.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Kees Cook <kees@kernel.org>
Link: https://lore.kernel.org/r/20250224124200.486463917@infradead.org
---
 arch/x86/include/asm/bug.h |  2 ++
 arch/x86/kernel/traps.c    | 26 +++++++++++++++++++++++---
 2 files changed, 25 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index bc8a2ca3c82ef..f0e9acf725471 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -17,6 +17,7 @@
  * In clang we have UD1s reporting UBSAN failures on X86, 64 and 32bit.
  */
 #define INSN_ASOP		0x67
+#define INSN_LOCK		0xf0
 #define OPCODE_ESCAPE		0x0f
 #define SECOND_BYTE_OPCODE_UD1	0xb9
 #define SECOND_BYTE_OPCODE_UD2	0x0b
@@ -26,6 +27,7 @@
 #define BUG_UD1			0xfffd
 #define BUG_UD1_UBSAN		0xfffc
 #define BUG_EA			0xffea
+#define BUG_LOCK		0xfff0
 
 #ifdef CONFIG_GENERIC_BUG
 
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index c169f3bd3c6c0..f4263cb3d21e6 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -97,6 +97,7 @@ __always_inline int is_valid_bugaddr(unsigned long addr)
  * If it's a UD1, further decode to determine its use:
  *
  * FineIBT:      ea                      (bad)
+ * FineIBT:      f0 75 f9                lock jne . - 6
  * UBSan{0}:     67 0f b9 00             ud1    (%eax),%eax
  * UBSan{10}:    67 0f b9 40 10          ud1    0x10(%eax),%eax
  * static_call:  0f b9 cc                ud1    %esp,%ecx
@@ -106,6 +107,7 @@ __always_inline int is_valid_bugaddr(unsigned long addr)
 __always_inline int decode_bug(unsigned long addr, s32 *imm, int *len)
 {
 	unsigned long start = addr;
+	bool lock = false;
 	u8 v;
 
 	if (addr < TASK_SIZE_MAX)
@@ -114,12 +116,29 @@ __always_inline int decode_bug(unsigned long addr, s32 *imm, int *len)
 	v = *(u8 *)(addr++);
 	if (v == INSN_ASOP)
 		v = *(u8 *)(addr++);
-	if (v == 0xea) {
+
+	if (v == INSN_LOCK) {
+		lock = true;
+		v = *(u8 *)(addr++);
+	}
+
+	switch (v) {
+	case 0x70 ... 0x7f: /* Jcc.d8 */
+		addr += 1; /* d8 */
+		*len = addr - start;
+		WARN_ON_ONCE(!lock);
+		return BUG_LOCK;
+
+	case 0xea:
 		*len = addr - start;
 		return BUG_EA;
-	}
-	if (v != OPCODE_ESCAPE)
+
+	case OPCODE_ESCAPE:
+		break;
+
+	default:
 		return BUG_NONE;
+	}
 
 	v = *(u8 *)(addr++);
 	if (v == SECOND_BYTE_OPCODE_UD2) {
@@ -322,6 +341,7 @@ static noinstr bool handle_bug(struct pt_regs *regs)
 		fallthrough;
 
 	case BUG_EA:
+	case BUG_LOCK:
 		if (handle_cfi_failure(regs) == BUG_TRAP_TYPE_WARN) {
 			handled = true;
 			break;

From 97e59672a9d2aec0c27f6cd6a6b0edfdd6e5a85c Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 26 Feb 2025 12:25:17 +0100
Subject: [PATCH 0652/1173] x86/ibt: Add paranoid FineIBT mode

Due to concerns about circumvention attacks against FineIBT on 'naked'
ENDBR, add an additional caller side hash check to FineIBT. This
should make it impossible to pivot over such a 'naked' ENDBR
instruction at the cost of an additional load.

The specific pivot reported was against the SYSCALL entry site and
FRED will have all those holes fixed up.

  https://lore.kernel.org/linux-hardening/Z60NwR4w%2F28Z7XUa@ubun/

This specific fineibt_paranoid_start[] sequence was concocted by
Scott.

Suggested-by: Scott Constable <scott.d.constable@intel.com>
Reported-by: Jennifer Miller <jmill@asu.edu>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Kees Cook <kees@kernel.org>
Link: https://lore.kernel.org/r/20250224124200.598033084@infradead.org
---
 arch/x86/kernel/alternative.c | 144 ++++++++++++++++++++++++++++++++--
 1 file changed, 138 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index a2e8ee8029eb8..c698c9e27ce37 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -741,6 +741,11 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end)
 		op2 = insn.opcode.bytes[1];
 
 		switch (op1) {
+		case 0x70 ... 0x7f:	/* Jcc.d8 */
+			/* See cfi_paranoid. */
+			WARN_ON_ONCE(cfi_mode != CFI_FINEIBT);
+			continue;
+
 		case CALL_INSN_OPCODE:
 		case JMP32_INSN_OPCODE:
 			break;
@@ -998,6 +1003,8 @@ u32 cfi_get_func_hash(void *func)
 static bool cfi_rand __ro_after_init = true;
 static u32  cfi_seed __ro_after_init;
 
+static bool cfi_paranoid __ro_after_init = false;
+
 /*
  * Re-hash the CFI hash with a boot-time seed while making sure the result is
  * not a valid ENDBR instruction.
@@ -1040,6 +1047,12 @@ static __init int cfi_parse_cmdline(char *str)
 		} else if (!strcmp(str, "warn")) {
 			pr_alert("CFI mismatch non-fatal!\n");
 			cfi_warn = true;
+		} else if (!strcmp(str, "paranoid")) {
+			if (cfi_mode == CFI_FINEIBT) {
+				cfi_paranoid = true;
+			} else {
+				pr_err("Ignoring paranoid; depends on fineibt.\n");
+			}
 		} else {
 			pr_err("Ignoring unknown cfi option (%s).", str);
 		}
@@ -1128,6 +1141,52 @@ extern u8 fineibt_caller_end[];
 
 #define fineibt_caller_jmp (fineibt_caller_size - 2)
 
+/*
+ * Since FineIBT does hash validation on the callee side it is prone to
+ * circumvention attacks where a 'naked' ENDBR instruction exists that
+ * is not part of the fineibt_preamble sequence.
+ *
+ * Notably the x86 entry points must be ENDBR and equally cannot be
+ * fineibt_preamble.
+ *
+ * The fineibt_paranoid caller sequence adds additional caller side
+ * hash validation. This stops such circumvention attacks dead, but at the cost
+ * of adding a load.
+ *
+ * <fineibt_paranoid_start>:
+ *  0:   41 ba 78 56 34 12       mov    $0x12345678, %r10d
+ *  6:   45 3b 53 f7             cmp    -0x9(%r11), %r10d
+ *  a:   4d 8d 5b <f0>           lea    -0x10(%r11), %r11
+ *  e:   75 fd                   jne    d <fineibt_paranoid_start+0xd>
+ * 10:   41 ff d3                call   *%r11
+ * 13:   90                      nop
+ *
+ * Notably LEA does not modify flags and can be reordered with the CMP,
+ * avoiding a dependency. Again, using a non-taken (backwards) branch
+ * for the failure case, abusing LEA's immediate 0xf0 as LOCK prefix for the
+ * Jcc.d8, causing #UD.
+ */
+asm(	".pushsection .rodata				\n"
+	"fineibt_paranoid_start:			\n"
+	"	movl	$0x12345678, %r10d		\n"
+	"	cmpl	-9(%r11), %r10d			\n"
+	"	lea	-0x10(%r11), %r11		\n"
+	"	jne	fineibt_paranoid_start+0xd	\n"
+	"fineibt_paranoid_ind:				\n"
+	"	call	*%r11				\n"
+	"	nop					\n"
+	"fineibt_paranoid_end:				\n"
+	".popsection					\n"
+);
+
+extern u8 fineibt_paranoid_start[];
+extern u8 fineibt_paranoid_ind[];
+extern u8 fineibt_paranoid_end[];
+
+#define fineibt_paranoid_size (fineibt_paranoid_end - fineibt_paranoid_start)
+#define fineibt_paranoid_ind  (fineibt_paranoid_ind - fineibt_paranoid_start)
+#define fineibt_paranoid_ud   0xd
+
 static u32 decode_preamble_hash(void *addr)
 {
 	u8 *p = addr;
@@ -1291,18 +1350,48 @@ static int cfi_rewrite_callers(s32 *start, s32 *end)
 {
 	s32 *s;
 
+	BUG_ON(fineibt_paranoid_size != 20);
+
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
+		struct insn insn;
+		u8 bytes[20];
 		u32 hash;
+		int ret;
+		u8 op;
 
 		addr -= fineibt_caller_size;
 		hash = decode_caller_hash(addr);
-		if (hash) {
+		if (!hash)
+			continue;
+
+		if (!cfi_paranoid) {
 			text_poke_early(addr, fineibt_caller_start, fineibt_caller_size);
 			WARN_ON(*(u32 *)(addr + fineibt_caller_hash) != 0x12345678);
 			text_poke_early(addr + fineibt_caller_hash, &hash, 4);
+			/* rely on apply_retpolines() */
+			continue;
+		}
+
+		/* cfi_paranoid */
+		ret = insn_decode_kernel(&insn, addr + fineibt_caller_size);
+		if (WARN_ON_ONCE(ret < 0))
+			continue;
+
+		op = insn.opcode.bytes[0];
+		if (op != CALL_INSN_OPCODE && op != JMP32_INSN_OPCODE) {
+			WARN_ON_ONCE(1);
+			continue;
 		}
-		/* rely on apply_retpolines() */
+
+		memcpy(bytes, fineibt_paranoid_start, fineibt_paranoid_size);
+		memcpy(bytes + fineibt_caller_hash, &hash, 4);
+
+		ret = emit_indirect(op, 11, bytes + fineibt_paranoid_ind);
+		if (WARN_ON_ONCE(ret != 3))
+			continue;
+
+		text_poke_early(addr, bytes, fineibt_paranoid_size);
 	}
 
 	return 0;
@@ -1319,8 +1408,15 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 
 	if (cfi_mode == CFI_AUTO) {
 		cfi_mode = CFI_KCFI;
-		if (HAS_KERNEL_IBT && cpu_feature_enabled(X86_FEATURE_IBT))
+		if (HAS_KERNEL_IBT && cpu_feature_enabled(X86_FEATURE_IBT)) {
+			/*
+			 * FRED has much saner context on exception entry and
+			 * is less easy to take advantage of.
+			 */
+			if (!cpu_feature_enabled(X86_FEATURE_FRED))
+				cfi_paranoid = true;
 			cfi_mode = CFI_FINEIBT;
+		}
 	}
 
 	/*
@@ -1377,8 +1473,10 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 		/* now that nobody targets func()+0, remove ENDBR there */
 		cfi_rewrite_endbr(start_cfi, end_cfi);
 
-		if (builtin)
-			pr_info("Using FineIBT CFI\n");
+		if (builtin) {
+			pr_info("Using %sFineIBT CFI\n",
+				cfi_paranoid ? "paranoid " : "");
+		}
 		return;
 
 	default:
@@ -1451,7 +1549,7 @@ static void poison_cfi(void *addr)
  * We check the preamble by checking for the ENDBR instruction relative to the
  * 0xEA instruction.
  */
-bool decode_fineibt_insn(struct pt_regs *regs, unsigned long *target, u32 *type)
+static bool decode_fineibt_preamble(struct pt_regs *regs, unsigned long *target, u32 *type)
 {
 	unsigned long addr = regs->ip - fineibt_preamble_ud;
 	u32 hash;
@@ -1476,6 +1574,40 @@ bool decode_fineibt_insn(struct pt_regs *regs, unsigned long *target, u32 *type)
 	return false;
 }
 
+/*
+ * regs->ip points to a LOCK Jcc.d8 instruction from the fineibt_paranoid_start[]
+ * sequence.
+ */
+static bool decode_fineibt_paranoid(struct pt_regs *regs, unsigned long *target, u32 *type)
+{
+	unsigned long addr = regs->ip - fineibt_paranoid_ud;
+	u32 hash;
+
+	if (!cfi_paranoid || !is_cfi_trap(addr + fineibt_caller_size - LEN_UD2))
+		return false;
+
+	__get_kernel_nofault(&hash, addr + fineibt_caller_hash, u32, Efault);
+	*target = regs->r11 + fineibt_preamble_size;
+	*type = regs->r10;
+
+	/*
+	 * Since the trapping instruction is the exact, but LOCK prefixed,
+	 * Jcc.d8 that got us here, the normal fixup will work.
+	 */
+	return true;
+
+Efault:
+	return false;
+}
+
+bool decode_fineibt_insn(struct pt_regs *regs, unsigned long *target, u32 *type)
+{
+	if (decode_fineibt_paranoid(regs, target, type))
+		return true;
+
+	return decode_fineibt_preamble(regs, target, type);
+}
+
 #else /* !CONFIG_FINEIBT: */
 
 static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,

From dbd6b649e7d5b66c7fa95a65d67b59cf5b45f0ac Mon Sep 17 00:00:00 2001
From: "Chang S. Bae" <chang.seok.bae@intel.com>
Date: Tue, 25 Feb 2025 17:07:21 -0800
Subject: [PATCH 0653/1173] selftests/x86: Consolidate redundant signal helper
 functions

The x86 selftests frequently register and clean up signal handlers, but
the sethandler() and clearhandler() functions have been redundantly
copied across multiple .c files.

Move these functions to helpers.h to enable reuse across tests,
eliminating around 250 lines of duplicate code.

Converge the error handling by using ksft_exit_fail_msg(), which is
functionally equivalent with err() within the selftest framework.

This change is a prerequisite for the upcoming xstate selftest, which
requires signal handling for registering and cleaning up handlers.

Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250226010731.2456-2-chang.seok.bae@intel.com
---
 tools/testing/selftests/x86/amx.c             | 25 +----------------
 .../selftests/x86/corrupt_xstate_header.c     | 14 +---------
 tools/testing/selftests/x86/entry_from_vm86.c | 24 ++--------------
 tools/testing/selftests/x86/fsgsbase.c        | 24 ++--------------
 tools/testing/selftests/x86/helpers.h         | 28 +++++++++++++++++++
 tools/testing/selftests/x86/ioperm.c          | 25 ++---------------
 tools/testing/selftests/x86/iopl.c            | 25 ++---------------
 tools/testing/selftests/x86/ldt_gdt.c         | 18 +++---------
 tools/testing/selftests/x86/mov_ss_trap.c     | 14 +---------
 tools/testing/selftests/x86/ptrace_syscall.c  | 24 ++--------------
 tools/testing/selftests/x86/sigaltstack.c     | 26 ++---------------
 tools/testing/selftests/x86/sigreturn.c       | 24 ++--------------
 .../selftests/x86/single_step_syscall.c       | 22 ---------------
 .../testing/selftests/x86/syscall_arg_fault.c | 12 --------
 tools/testing/selftests/x86/syscall_nt.c      | 12 --------
 tools/testing/selftests/x86/sysret_rip.c      | 24 ++--------------
 tools/testing/selftests/x86/test_vsyscall.c   | 13 ---------
 tools/testing/selftests/x86/unwind_vdso.c     | 12 --------
 18 files changed, 51 insertions(+), 315 deletions(-)

diff --git a/tools/testing/selftests/x86/amx.c b/tools/testing/selftests/x86/amx.c
index 1fdf35a4d7f63..0f355f331f41c 100644
--- a/tools/testing/selftests/x86/amx.c
+++ b/tools/testing/selftests/x86/amx.c
@@ -20,6 +20,7 @@
 #include <sys/uio.h>
 
 #include "../kselftest.h" /* For __cpuid_count() */
+#include "helpers.h"
 
 #ifndef __x86_64__
 # error This test is 64-bit only
@@ -61,30 +62,6 @@ static inline void xrstor(struct xsave_buffer *xbuf, uint64_t rfbm)
 /* err() exits and will not return */
 #define fatal_error(msg, ...)	err(1, "[FAIL]\t" msg, ##__VA_ARGS__)
 
-static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
-		       int flags)
-{
-	struct sigaction sa;
-
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handler;
-	sa.sa_flags = SA_SIGINFO | flags;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		fatal_error("sigaction");
-}
-
-static void clearhandler(int sig)
-{
-	struct sigaction sa;
-
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_handler = SIG_DFL;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		fatal_error("sigaction");
-}
-
 #define XFEATURE_XTILECFG	17
 #define XFEATURE_XTILEDATA	18
 #define XFEATURE_MASK_XTILECFG	(1 << XFEATURE_XTILECFG)
diff --git a/tools/testing/selftests/x86/corrupt_xstate_header.c b/tools/testing/selftests/x86/corrupt_xstate_header.c
index cf9ce8fbb656c..93a89a5997ca8 100644
--- a/tools/testing/selftests/x86/corrupt_xstate_header.c
+++ b/tools/testing/selftests/x86/corrupt_xstate_header.c
@@ -18,6 +18,7 @@
 #include <sys/wait.h>
 
 #include "../kselftest.h" /* For __cpuid_count() */
+#include "helpers.h"
 
 static inline int xsave_enabled(void)
 {
@@ -29,19 +30,6 @@ static inline int xsave_enabled(void)
 	return ecx & (1U << 27);
 }
 
-static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
-		       int flags)
-{
-	struct sigaction sa;
-
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handler;
-	sa.sa_flags = SA_SIGINFO | flags;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
 static void sigusr1(int sig, siginfo_t *info, void *uc_void)
 {
 	ucontext_t *uc = uc_void;
diff --git a/tools/testing/selftests/x86/entry_from_vm86.c b/tools/testing/selftests/x86/entry_from_vm86.c
index d1e919b0c1dc8..5cb8393737d05 100644
--- a/tools/testing/selftests/x86/entry_from_vm86.c
+++ b/tools/testing/selftests/x86/entry_from_vm86.c
@@ -24,31 +24,11 @@
 #include <errno.h>
 #include <sys/vm86.h>
 
+#include "helpers.h"
+
 static unsigned long load_addr = 0x10000;
 static int nerrs = 0;
 
-static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
-		       int flags)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handler;
-	sa.sa_flags = SA_SIGINFO | flags;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
-static void clearhandler(int sig)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_handler = SIG_DFL;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
 static sig_atomic_t got_signal;
 
 static void sighandler(int sig, siginfo_t *info, void *ctx_void)
diff --git a/tools/testing/selftests/x86/fsgsbase.c b/tools/testing/selftests/x86/fsgsbase.c
index 50cf32de63139..0a75252d31b6a 100644
--- a/tools/testing/selftests/x86/fsgsbase.c
+++ b/tools/testing/selftests/x86/fsgsbase.c
@@ -28,6 +28,8 @@
 #include <sys/wait.h>
 #include <setjmp.h>
 
+#include "helpers.h"
+
 #ifndef __x86_64__
 # error This test is 64-bit only
 #endif
@@ -39,28 +41,6 @@ static unsigned short *shared_scratch;
 
 static int nerrs;
 
-static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
-		       int flags)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handler;
-	sa.sa_flags = SA_SIGINFO | flags;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
-static void clearhandler(int sig)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_handler = SIG_DFL;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
 static void sigsegv(int sig, siginfo_t *si, void *ctx_void)
 {
 	ucontext_t *ctx = (ucontext_t*)ctx_void;
diff --git a/tools/testing/selftests/x86/helpers.h b/tools/testing/selftests/x86/helpers.h
index 4ef42c4559a9e..6deaad035161a 100644
--- a/tools/testing/selftests/x86/helpers.h
+++ b/tools/testing/selftests/x86/helpers.h
@@ -2,8 +2,13 @@
 #ifndef __SELFTESTS_X86_HELPERS_H
 #define __SELFTESTS_X86_HELPERS_H
 
+#include <signal.h>
+#include <string.h>
+
 #include <asm/processor-flags.h>
 
+#include "../kselftest.h"
+
 static inline unsigned long get_eflags(void)
 {
 #ifdef __x86_64__
@@ -22,4 +27,27 @@ static inline void set_eflags(unsigned long eflags)
 #endif
 }
 
+static inline void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), int flags)
+{
+	struct sigaction sa;
+
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_sigaction = handler;
+	sa.sa_flags = SA_SIGINFO | flags;
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(sig, &sa, 0))
+		ksft_exit_fail_msg("sigaction failed");
+}
+
+static inline void clearhandler(int sig)
+{
+	struct sigaction sa;
+
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_handler = SIG_DFL;
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(sig, &sa, 0))
+		ksft_exit_fail_msg("sigaction failed");
+}
+
 #endif /* __SELFTESTS_X86_HELPERS_H */
diff --git a/tools/testing/selftests/x86/ioperm.c b/tools/testing/selftests/x86/ioperm.c
index 57ec5e99edb93..69d5fb7050c25 100644
--- a/tools/testing/selftests/x86/ioperm.c
+++ b/tools/testing/selftests/x86/ioperm.c
@@ -20,30 +20,9 @@
 #include <sched.h>
 #include <sys/io.h>
 
-static int nerrs = 0;
-
-static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
-		       int flags)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handler;
-	sa.sa_flags = SA_SIGINFO | flags;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-
-}
+#include "helpers.h"
 
-static void clearhandler(int sig)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_handler = SIG_DFL;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
+static int nerrs = 0;
 
 static jmp_buf jmpbuf;
 
diff --git a/tools/testing/selftests/x86/iopl.c b/tools/testing/selftests/x86/iopl.c
index 7e3e09c1abac6..457b6715542bd 100644
--- a/tools/testing/selftests/x86/iopl.c
+++ b/tools/testing/selftests/x86/iopl.c
@@ -20,30 +20,9 @@
 #include <sched.h>
 #include <sys/io.h>
 
-static int nerrs = 0;
-
-static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
-		       int flags)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handler;
-	sa.sa_flags = SA_SIGINFO | flags;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-
-}
+#include "helpers.h"
 
-static void clearhandler(int sig)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_handler = SIG_DFL;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
+static int nerrs = 0;
 
 static jmp_buf jmpbuf;
 
diff --git a/tools/testing/selftests/x86/ldt_gdt.c b/tools/testing/selftests/x86/ldt_gdt.c
index 3a29346e1452d..bb99a71380a5f 100644
--- a/tools/testing/selftests/x86/ldt_gdt.c
+++ b/tools/testing/selftests/x86/ldt_gdt.c
@@ -26,6 +26,8 @@
 #include <asm/prctl.h>
 #include <sys/prctl.h>
 
+#include "helpers.h"
+
 #define AR_ACCESSED		(1<<8)
 
 #define AR_TYPE_RODATA		(0 * (1<<9))
@@ -506,20 +508,6 @@ static void fix_sa_restorer(int sig)
 }
 #endif
 
-static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
-		       int flags)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handler;
-	sa.sa_flags = SA_SIGINFO | flags;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-
-	fix_sa_restorer(sig);
-}
-
 static jmp_buf jmpbuf;
 
 static void sigsegv(int sig, siginfo_t *info, void *ctx_void)
@@ -549,9 +537,11 @@ static void do_multicpu_tests(void)
 	}
 
 	sethandler(SIGSEGV, sigsegv, 0);
+	fix_sa_restorer(SIGSEGV);
 #ifdef __i386__
 	/* True 32-bit kernels send SIGILL instead of SIGSEGV on IRET faults. */
 	sethandler(SIGILL, sigsegv, 0);
+	fix_sa_restorer(SIGILL);
 #endif
 
 	printf("[RUN]\tCross-CPU LDT invalidation\n");
diff --git a/tools/testing/selftests/x86/mov_ss_trap.c b/tools/testing/selftests/x86/mov_ss_trap.c
index cc3de6ff9fba1..f22cb6b382f9c 100644
--- a/tools/testing/selftests/x86/mov_ss_trap.c
+++ b/tools/testing/selftests/x86/mov_ss_trap.c
@@ -36,7 +36,7 @@
 #include <setjmp.h>
 #include <sys/prctl.h>
 
-#define X86_EFLAGS_RF (1UL << 16)
+#include "helpers.h"
 
 #if __x86_64__
 # define REG_IP REG_RIP
@@ -94,18 +94,6 @@ static void enable_watchpoint(void)
 	}
 }
 
-static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
-		       int flags)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handler;
-	sa.sa_flags = SA_SIGINFO | flags;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
 static char const * const signames[] = {
 	[SIGSEGV] = "SIGSEGV",
 	[SIGBUS] = "SIBGUS",
diff --git a/tools/testing/selftests/x86/ptrace_syscall.c b/tools/testing/selftests/x86/ptrace_syscall.c
index 12aaa063196e7..360ec88d5432c 100644
--- a/tools/testing/selftests/x86/ptrace_syscall.c
+++ b/tools/testing/selftests/x86/ptrace_syscall.c
@@ -15,6 +15,8 @@
 #include <asm/ptrace-abi.h>
 #include <sys/auxv.h>
 
+#include "helpers.h"
+
 /* Bitness-agnostic defines for user_regs_struct fields. */
 #ifdef __x86_64__
 # define user_syscall_nr	orig_rax
@@ -93,18 +95,6 @@ static siginfo_t wait_trap(pid_t chld)
 	return si;
 }
 
-static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
-		       int flags)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handler;
-	sa.sa_flags = SA_SIGINFO | flags;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
 static void setsigign(int sig, int flags)
 {
 	struct sigaction sa;
@@ -116,16 +106,6 @@ static void setsigign(int sig, int flags)
 		err(1, "sigaction");
 }
 
-static void clearhandler(int sig)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_handler = SIG_DFL;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
 #ifdef __x86_64__
 # define REG_BP REG_RBP
 #else
diff --git a/tools/testing/selftests/x86/sigaltstack.c b/tools/testing/selftests/x86/sigaltstack.c
index f689af75e979e..0ae1b784498cc 100644
--- a/tools/testing/selftests/x86/sigaltstack.c
+++ b/tools/testing/selftests/x86/sigaltstack.c
@@ -14,6 +14,8 @@
 #include <sys/resource.h>
 #include <setjmp.h>
 
+#include "helpers.h"
+
 /* sigaltstack()-enforced minimum stack */
 #define ENFORCED_MINSIGSTKSZ	2048
 
@@ -27,30 +29,6 @@ static bool sigalrm_expected;
 
 static unsigned long at_minstack_size;
 
-static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
-		       int flags)
-{
-	struct sigaction sa;
-
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handler;
-	sa.sa_flags = SA_SIGINFO | flags;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
-static void clearhandler(int sig)
-{
-	struct sigaction sa;
-
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_handler = SIG_DFL;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
 static int setup_altstack(void *start, unsigned long size)
 {
 	stack_t ss;
diff --git a/tools/testing/selftests/x86/sigreturn.c b/tools/testing/selftests/x86/sigreturn.c
index 0b75b29f794b7..26ef562f4232a 100644
--- a/tools/testing/selftests/x86/sigreturn.c
+++ b/tools/testing/selftests/x86/sigreturn.c
@@ -46,6 +46,8 @@
 #include <sys/ptrace.h>
 #include <sys/user.h>
 
+#include "helpers.h"
+
 /* Pull in AR_xyz defines. */
 typedef unsigned int u32;
 typedef unsigned short u16;
@@ -138,28 +140,6 @@ static unsigned short LDT3(int idx)
 	return (idx << 3) | 7;
 }
 
-static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
-		       int flags)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handler;
-	sa.sa_flags = SA_SIGINFO | flags;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
-static void clearhandler(int sig)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_handler = SIG_DFL;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
 static void add_ldt(const struct user_desc *desc, unsigned short *var,
 		    const char *name)
 {
diff --git a/tools/testing/selftests/x86/single_step_syscall.c b/tools/testing/selftests/x86/single_step_syscall.c
index 9a30f443e9286..280d7a22b9c9b 100644
--- a/tools/testing/selftests/x86/single_step_syscall.c
+++ b/tools/testing/selftests/x86/single_step_syscall.c
@@ -33,28 +33,6 @@
 
 #include "helpers.h"
 
-static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
-		       int flags)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handler;
-	sa.sa_flags = SA_SIGINFO | flags;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
-static void clearhandler(int sig)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_handler = SIG_DFL;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
 static volatile sig_atomic_t sig_traps, sig_eflags;
 sigjmp_buf jmpbuf;
 
diff --git a/tools/testing/selftests/x86/syscall_arg_fault.c b/tools/testing/selftests/x86/syscall_arg_fault.c
index 48ab065a76f9b..f67a2df335ba0 100644
--- a/tools/testing/selftests/x86/syscall_arg_fault.c
+++ b/tools/testing/selftests/x86/syscall_arg_fault.c
@@ -17,18 +17,6 @@
 
 #include "helpers.h"
 
-static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
-		       int flags)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handler;
-	sa.sa_flags = SA_SIGINFO | flags;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
 static sigjmp_buf jmpbuf;
 
 static volatile sig_atomic_t n_errs;
diff --git a/tools/testing/selftests/x86/syscall_nt.c b/tools/testing/selftests/x86/syscall_nt.c
index a108b80dd0823..f9c9814160f09 100644
--- a/tools/testing/selftests/x86/syscall_nt.c
+++ b/tools/testing/selftests/x86/syscall_nt.c
@@ -18,18 +18,6 @@
 
 static unsigned int nerrs;
 
-static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
-		       int flags)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handler;
-	sa.sa_flags = SA_SIGINFO | flags;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
 static void sigtrap(int sig, siginfo_t *si, void *ctx_void)
 {
 }
diff --git a/tools/testing/selftests/x86/sysret_rip.c b/tools/testing/selftests/x86/sysret_rip.c
index b30de9aaa6d41..5fb531e3ad7c3 100644
--- a/tools/testing/selftests/x86/sysret_rip.c
+++ b/tools/testing/selftests/x86/sysret_rip.c
@@ -22,6 +22,8 @@
 #include <sys/mman.h>
 #include <assert.h>
 
+#include "helpers.h"
+
 /*
  * These items are in clang_helpers_64.S, in order to avoid clang inline asm
  * limitations:
@@ -31,28 +33,6 @@ extern const char test_page[];
 
 static void const *current_test_page_addr = test_page;
 
-static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
-		       int flags)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handler;
-	sa.sa_flags = SA_SIGINFO | flags;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
-static void clearhandler(int sig)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_handler = SIG_DFL;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
 /* State used by our signal handlers. */
 static gregset_t initial_regs;
 
diff --git a/tools/testing/selftests/x86/test_vsyscall.c b/tools/testing/selftests/x86/test_vsyscall.c
index 6de11b4df4583..05e1e6774fba3 100644
--- a/tools/testing/selftests/x86/test_vsyscall.c
+++ b/tools/testing/selftests/x86/test_vsyscall.c
@@ -310,19 +310,6 @@ static void test_getcpu(int cpu)
 static jmp_buf jmpbuf;
 static volatile unsigned long segv_err;
 
-static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
-		       int flags)
-{
-	struct sigaction sa;
-
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handler;
-	sa.sa_flags = SA_SIGINFO | flags;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		ksft_exit_fail_msg("sigaction failed\n");
-}
-
 static void sigsegv(int sig, siginfo_t *info, void *ctx_void)
 {
 	ucontext_t *ctx = (ucontext_t *)ctx_void;
diff --git a/tools/testing/selftests/x86/unwind_vdso.c b/tools/testing/selftests/x86/unwind_vdso.c
index 4c311e1af4c7a..9cc17588d8189 100644
--- a/tools/testing/selftests/x86/unwind_vdso.c
+++ b/tools/testing/selftests/x86/unwind_vdso.c
@@ -43,18 +43,6 @@ int main()
 #include <dlfcn.h>
 #include <unwind.h>
 
-static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
-		       int flags)
-{
-	struct sigaction sa;
-	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handler;
-	sa.sa_flags = SA_SIGINFO | flags;
-	sigemptyset(&sa.sa_mask);
-	if (sigaction(sig, &sa, 0))
-		err(1, "sigaction");
-}
-
 static volatile sig_atomic_t nerrs;
 static unsigned long sysinfo;
 static bool got_sysinfo = false;

From 0f6d91a327db4a36d6febb74d833cdc668c8661b Mon Sep 17 00:00:00 2001
From: "Chang S. Bae" <chang.seok.bae@intel.com>
Date: Tue, 25 Feb 2025 17:07:22 -0800
Subject: [PATCH 0654/1173] selftests/x86/xstate: Refactor XSAVE helpers for
 general use

The AMX test introduced several XSAVE-related helper functions, but so
far, it has been the only user of them. These helpers can be generalized
for broader test of multiple xstate features.

Move most XSAVE-related code into xsave.h, making it shareable. The
restructuring includes:

 * Establishing low-level XSAVE helpers for saving and restoring register
  states, as well as handling XSAVE buffers.

 * Generalizing state data manipuldations: set_rand_data()

 * Introducing a generic feature query helper: get_xstate_info()

While doing so, remove unused defines in amx.c.

Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250226010731.2456-3-chang.seok.bae@intel.com
---
 tools/testing/selftests/x86/amx.c    | 142 ++-------------------------
 tools/testing/selftests/x86/xstate.h | 132 +++++++++++++++++++++++++
 2 files changed, 142 insertions(+), 132 deletions(-)
 create mode 100644 tools/testing/selftests/x86/xstate.h

diff --git a/tools/testing/selftests/x86/amx.c b/tools/testing/selftests/x86/amx.c
index 0f355f331f41c..366cfec221e48 100644
--- a/tools/testing/selftests/x86/amx.c
+++ b/tools/testing/selftests/x86/amx.c
@@ -19,46 +19,13 @@
 #include <sys/wait.h>
 #include <sys/uio.h>
 
-#include "../kselftest.h" /* For __cpuid_count() */
 #include "helpers.h"
+#include "xstate.h"
 
 #ifndef __x86_64__
 # error This test is 64-bit only
 #endif
 
-#define XSAVE_HDR_OFFSET	512
-#define XSAVE_HDR_SIZE		64
-
-struct xsave_buffer {
-	union {
-		struct {
-			char legacy[XSAVE_HDR_OFFSET];
-			char header[XSAVE_HDR_SIZE];
-			char extended[0];
-		};
-		char bytes[0];
-	};
-};
-
-static inline void xsave(struct xsave_buffer *xbuf, uint64_t rfbm)
-{
-	uint32_t rfbm_lo = rfbm;
-	uint32_t rfbm_hi = rfbm >> 32;
-
-	asm volatile("xsave (%%rdi)"
-		     : : "D" (xbuf), "a" (rfbm_lo), "d" (rfbm_hi)
-		     : "memory");
-}
-
-static inline void xrstor(struct xsave_buffer *xbuf, uint64_t rfbm)
-{
-	uint32_t rfbm_lo = rfbm;
-	uint32_t rfbm_hi = rfbm >> 32;
-
-	asm volatile("xrstor (%%rdi)"
-		     : : "D" (xbuf), "a" (rfbm_lo), "d" (rfbm_hi));
-}
-
 /* err() exits and will not return */
 #define fatal_error(msg, ...)	err(1, "[FAIL]\t" msg, ##__VA_ARGS__)
 
@@ -68,92 +35,12 @@ static inline void xrstor(struct xsave_buffer *xbuf, uint64_t rfbm)
 #define XFEATURE_MASK_XTILEDATA	(1 << XFEATURE_XTILEDATA)
 #define XFEATURE_MASK_XTILE	(XFEATURE_MASK_XTILECFG | XFEATURE_MASK_XTILEDATA)
 
-#define CPUID_LEAF1_ECX_XSAVE_MASK	(1 << 26)
-#define CPUID_LEAF1_ECX_OSXSAVE_MASK	(1 << 27)
-
 static uint32_t xbuf_size;
 
-static struct {
-	uint32_t xbuf_offset;
-	uint32_t size;
-} xtiledata;
-
-#define CPUID_LEAF_XSTATE		0xd
-#define CPUID_SUBLEAF_XSTATE_USER	0x0
-#define TILE_CPUID			0x1d
-#define TILE_PALETTE_ID			0x1
-
-static void check_cpuid_xtiledata(void)
-{
-	uint32_t eax, ebx, ecx, edx;
-
-	__cpuid_count(CPUID_LEAF_XSTATE, CPUID_SUBLEAF_XSTATE_USER,
-		      eax, ebx, ecx, edx);
-
-	/*
-	 * EBX enumerates the size (in bytes) required by the XSAVE
-	 * instruction for an XSAVE area containing all the user state
-	 * components corresponding to bits currently set in XCR0.
-	 *
-	 * Stash that off so it can be used to allocate buffers later.
-	 */
-	xbuf_size = ebx;
-
-	__cpuid_count(CPUID_LEAF_XSTATE, XFEATURE_XTILEDATA,
-		      eax, ebx, ecx, edx);
-	/*
-	 * eax: XTILEDATA state component size
-	 * ebx: XTILEDATA state component offset in user buffer
-	 */
-	if (!eax || !ebx)
-		fatal_error("xstate cpuid: invalid tile data size/offset: %d/%d",
-				eax, ebx);
-
-	xtiledata.size	      = eax;
-	xtiledata.xbuf_offset = ebx;
-}
+struct xstate_info xtiledata;
 
 /* The helpers for managing XSAVE buffer and tile states: */
 
-struct xsave_buffer *alloc_xbuf(void)
-{
-	struct xsave_buffer *xbuf;
-
-	/* XSAVE buffer should be 64B-aligned. */
-	xbuf = aligned_alloc(64, xbuf_size);
-	if (!xbuf)
-		fatal_error("aligned_alloc()");
-	return xbuf;
-}
-
-static inline void clear_xstate_header(struct xsave_buffer *buffer)
-{
-	memset(&buffer->header, 0, sizeof(buffer->header));
-}
-
-static inline void set_xstatebv(struct xsave_buffer *buffer, uint64_t bv)
-{
-	/* XSTATE_BV is at the beginning of the header: */
-	*(uint64_t *)(&buffer->header) = bv;
-}
-
-static void set_rand_tiledata(struct xsave_buffer *xbuf)
-{
-	int *ptr = (int *)&xbuf->bytes[xtiledata.xbuf_offset];
-	int data;
-	int i;
-
-	/*
-	 * Ensure that 'data' is never 0.  This ensures that
-	 * the registers are never in their initial configuration
-	 * and thus never tracked as being in the init state.
-	 */
-	data = rand() | 1;
-
-	for (i = 0; i < xtiledata.size / sizeof(int); i++, ptr++)
-		*ptr = data;
-}
-
 struct xsave_buffer *stashed_xsave;
 
 static void init_stashed_xsave(void)
@@ -169,21 +56,6 @@ static void free_stashed_xsave(void)
 	free(stashed_xsave);
 }
 
-/* See 'struct _fpx_sw_bytes' at sigcontext.h */
-#define SW_BYTES_OFFSET		464
-/* N.B. The struct's field name varies so read from the offset. */
-#define SW_BYTES_BV_OFFSET	(SW_BYTES_OFFSET + 8)
-
-static inline struct _fpx_sw_bytes *get_fpx_sw_bytes(void *buffer)
-{
-	return (struct _fpx_sw_bytes *)(buffer + SW_BYTES_OFFSET);
-}
-
-static inline uint64_t get_fpx_sw_bytes_features(void *buffer)
-{
-	return *(uint64_t *)(buffer + SW_BYTES_BV_OFFSET);
-}
-
 /* Work around printf() being unsafe in signals: */
 #define SIGNAL_BUF_LEN 1000
 char signal_message_buffer[SIGNAL_BUF_LEN];
@@ -281,7 +153,7 @@ static inline bool load_rand_tiledata(struct xsave_buffer *xbuf)
 {
 	clear_xstate_header(xbuf);
 	set_xstatebv(xbuf, XFEATURE_MASK_XTILEDATA);
-	set_rand_tiledata(xbuf);
+	set_rand_data(&xtiledata, xbuf);
 	return xrstor_safe(xbuf, XFEATURE_MASK_XTILEDATA);
 }
 
@@ -884,7 +756,13 @@ int main(void)
 		return KSFT_SKIP;
 	}
 
-	check_cpuid_xtiledata();
+	xbuf_size = get_xbuf_size();
+
+	xtiledata = get_xstate_info(XFEATURE_XTILEDATA);
+	if (!xtiledata.size || !xtiledata.xbuf_offset) {
+		fatal_error("xstate cpuid: invalid tile data size/offset: %d/%d",
+			    xtiledata.size, xtiledata.xbuf_offset);
+	}
 
 	init_stashed_xsave();
 	sethandler(SIGILL, handle_noperm, 0);
diff --git a/tools/testing/selftests/x86/xstate.h b/tools/testing/selftests/x86/xstate.h
new file mode 100644
index 0000000000000..6729ffde6cc49
--- /dev/null
+++ b/tools/testing/selftests/x86/xstate.h
@@ -0,0 +1,132 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#ifndef __SELFTESTS_X86_XSTATE_H
+#define __SELFTESTS_X86_XSTATE_H
+
+#include <stdint.h>
+
+#include "../kselftest.h"
+
+#define XSAVE_HDR_OFFSET	512
+#define XSAVE_HDR_SIZE		64
+
+struct xsave_buffer {
+	union {
+		struct {
+			char legacy[XSAVE_HDR_OFFSET];
+			char header[XSAVE_HDR_SIZE];
+			char extended[0];
+		};
+		char bytes[0];
+	};
+};
+
+static inline void xsave(struct xsave_buffer *xbuf, uint64_t rfbm)
+{
+	uint32_t rfbm_hi = rfbm >> 32;
+	uint32_t rfbm_lo = rfbm;
+
+	asm volatile("xsave (%%rdi)"
+		     : : "D" (xbuf), "a" (rfbm_lo), "d" (rfbm_hi)
+		     : "memory");
+}
+
+static inline void xrstor(struct xsave_buffer *xbuf, uint64_t rfbm)
+{
+	uint32_t rfbm_hi = rfbm >> 32;
+	uint32_t rfbm_lo = rfbm;
+
+	asm volatile("xrstor (%%rdi)"
+		     : : "D" (xbuf), "a" (rfbm_lo), "d" (rfbm_hi));
+}
+
+#define CPUID_LEAF_XSTATE		0xd
+#define CPUID_SUBLEAF_XSTATE_USER	0x0
+
+static inline uint32_t get_xbuf_size(void)
+{
+	uint32_t eax, ebx, ecx, edx;
+
+	__cpuid_count(CPUID_LEAF_XSTATE, CPUID_SUBLEAF_XSTATE_USER,
+		      eax, ebx, ecx, edx);
+
+	/*
+	 * EBX enumerates the size (in bytes) required by the XSAVE
+	 * instruction for an XSAVE area containing all the user state
+	 * components corresponding to bits currently set in XCR0.
+	 */
+	return ebx;
+}
+
+struct xstate_info {
+	uint32_t num;
+	uint32_t mask;
+	uint32_t xbuf_offset;
+	uint32_t size;
+};
+
+static inline struct xstate_info get_xstate_info(uint32_t xfeature_num)
+{
+	struct xstate_info xstate = { };
+	uint32_t eax, ebx, ecx, edx;
+
+	xstate.num  = xfeature_num;
+	xstate.mask = 1 << xfeature_num;
+
+	__cpuid_count(CPUID_LEAF_XSTATE, xfeature_num,
+		      eax, ebx, ecx, edx);
+	xstate.size        = eax;
+	xstate.xbuf_offset = ebx;
+	return xstate;
+}
+
+static inline struct xsave_buffer *alloc_xbuf(void)
+{
+	uint32_t xbuf_size = get_xbuf_size();
+
+	/* XSAVE buffer should be 64B-aligned. */
+	return aligned_alloc(64, xbuf_size);
+}
+
+static inline void clear_xstate_header(struct xsave_buffer *xbuf)
+{
+	memset(&xbuf->header, 0, sizeof(xbuf->header));
+}
+
+static inline void set_xstatebv(struct xsave_buffer *xbuf, uint64_t bv)
+{
+	/* XSTATE_BV is at the beginning of the header: */
+	*(uint64_t *)(&xbuf->header) = bv;
+}
+
+/* See 'struct _fpx_sw_bytes' at sigcontext.h */
+#define SW_BYTES_OFFSET		464
+/* N.B. The struct's field name varies so read from the offset. */
+#define SW_BYTES_BV_OFFSET	(SW_BYTES_OFFSET + 8)
+
+static inline struct _fpx_sw_bytes *get_fpx_sw_bytes(void *xbuf)
+{
+	return xbuf + SW_BYTES_OFFSET;
+}
+
+static inline uint64_t get_fpx_sw_bytes_features(void *buffer)
+{
+	return *(uint64_t *)(buffer + SW_BYTES_BV_OFFSET);
+}
+
+static inline void set_rand_data(struct xstate_info *xstate, struct xsave_buffer *xbuf)
+{
+	int *ptr = (int *)&xbuf->bytes[xstate->xbuf_offset];
+	int data, i;
+
+	/*
+	 * Ensure that 'data' is never 0.  This ensures that
+	 * the registers are never in their initial configuration
+	 * and thus never tracked as being in the init state.
+	 */
+	data = rand() | 1;
+
+	for (i = 0; i < xstate->size / sizeof(int); i++, ptr++)
+		*ptr = data;
+}
+
+#endif /* __SELFTESTS_X86_XSTATE_H */

From 3fcb4d61465613aee76ebd5d86b488778657dda7 Mon Sep 17 00:00:00 2001
From: "Chang S. Bae" <chang.seok.bae@intel.com>
Date: Tue, 25 Feb 2025 17:07:23 -0800
Subject: [PATCH 0655/1173] selftests/x86/xstate: Enumerate and name xstate
 components

After moving essential helpers from amx.c, the code remains neutral
regarding which xstate components it handles. However, explicitly listing
known components helps users identify which features are ready for
testing.

Enumerate xstate components to facilitate identification. Extend struct
xstate_info to include a name field, providing a human-readable
identifier.

Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250226010731.2456-4-chang.seok.bae@intel.com
---
 tools/testing/selftests/x86/amx.c    |  2 -
 tools/testing/selftests/x86/xstate.h | 60 ++++++++++++++++++++++++++++
 2 files changed, 60 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/x86/amx.c b/tools/testing/selftests/x86/amx.c
index 366cfec221e48..cde22f3039056 100644
--- a/tools/testing/selftests/x86/amx.c
+++ b/tools/testing/selftests/x86/amx.c
@@ -29,8 +29,6 @@
 /* err() exits and will not return */
 #define fatal_error(msg, ...)	err(1, "[FAIL]\t" msg, ##__VA_ARGS__)
 
-#define XFEATURE_XTILECFG	17
-#define XFEATURE_XTILEDATA	18
 #define XFEATURE_MASK_XTILECFG	(1 << XFEATURE_XTILECFG)
 #define XFEATURE_MASK_XTILEDATA	(1 << XFEATURE_XTILEDATA)
 #define XFEATURE_MASK_XTILE	(XFEATURE_MASK_XTILECFG | XFEATURE_MASK_XTILEDATA)
diff --git a/tools/testing/selftests/x86/xstate.h b/tools/testing/selftests/x86/xstate.h
index 6729ffde6cc49..d3461c4384614 100644
--- a/tools/testing/selftests/x86/xstate.h
+++ b/tools/testing/selftests/x86/xstate.h
@@ -9,6 +9,59 @@
 #define XSAVE_HDR_OFFSET	512
 #define XSAVE_HDR_SIZE		64
 
+/*
+ * List of XSAVE features Linux knows about. Copied from
+ * arch/x86/include/asm/fpu/types.h
+ */
+enum xfeature {
+	XFEATURE_FP,
+	XFEATURE_SSE,
+	XFEATURE_YMM,
+	XFEATURE_BNDREGS,
+	XFEATURE_BNDCSR,
+	XFEATURE_OPMASK,
+	XFEATURE_ZMM_Hi256,
+	XFEATURE_Hi16_ZMM,
+	XFEATURE_PT_UNIMPLEMENTED_SO_FAR,
+	XFEATURE_PKRU,
+	XFEATURE_PASID,
+	XFEATURE_CET_USER,
+	XFEATURE_CET_KERNEL_UNUSED,
+	XFEATURE_RSRVD_COMP_13,
+	XFEATURE_RSRVD_COMP_14,
+	XFEATURE_LBR,
+	XFEATURE_RSRVD_COMP_16,
+	XFEATURE_XTILECFG,
+	XFEATURE_XTILEDATA,
+
+	XFEATURE_MAX,
+};
+
+/* Copied from arch/x86/kernel/fpu/xstate.c */
+static const char *xfeature_names[] =
+{
+	"x87 floating point registers",
+	"SSE registers",
+	"AVX registers",
+	"MPX bounds registers",
+	"MPX CSR",
+	"AVX-512 opmask",
+	"AVX-512 Hi256",
+	"AVX-512 ZMM_Hi256",
+	"Processor Trace (unused)",
+	"Protection Keys User registers",
+	"PASID state",
+	"Control-flow User registers",
+	"Control-flow Kernel registers (unused)",
+	"unknown xstate feature",
+	"unknown xstate feature",
+	"unknown xstate feature",
+	"unknown xstate feature",
+	"AMX Tile config",
+	"AMX Tile data",
+	"unknown xstate feature",
+};
+
 struct xsave_buffer {
 	union {
 		struct {
@@ -58,6 +111,7 @@ static inline uint32_t get_xbuf_size(void)
 }
 
 struct xstate_info {
+	const char *name;
 	uint32_t num;
 	uint32_t mask;
 	uint32_t xbuf_offset;
@@ -69,6 +123,12 @@ static inline struct xstate_info get_xstate_info(uint32_t xfeature_num)
 	struct xstate_info xstate = { };
 	uint32_t eax, ebx, ecx, edx;
 
+	if (xfeature_num >= XFEATURE_MAX) {
+		ksft_print_msg("unknown state\n");
+		return xstate;
+	}
+
+	xstate.name = xfeature_names[xfeature_num];
 	xstate.num  = xfeature_num;
 	xstate.mask = 1 << xfeature_num;
 

From 40f6852ef2bffcd6fb3634cf71e6fbc2d1d6b768 Mon Sep 17 00:00:00 2001
From: "Chang S. Bae" <chang.seok.bae@intel.com>
Date: Tue, 25 Feb 2025 17:07:24 -0800
Subject: [PATCH 0656/1173] selftests/x86/xstate: Refactor context switching
 test

The existing context switching and ptrace tests in amx.c are not specific
to dynamic states, making them reusable for general xstate testing.

As a first step, move the context switching test to xstate.c. Refactor
the test code to allow specifying which xstate component being tested.

To decouple the test from dynamic states, remove the permission request
code. In fact, The permission request inside the test wrapper was
redundant.

Additionally, replace fatal_error() with ksft_exit_fail_msg() for
consistency in error handling.

  Expected output:
  $ amx_64
  ...
  [RUN]   AMX Tile data: check context switches, 10 iterations, 5 threads.
  [OK]    No incorrect case was found.

Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250226010731.2456-5-chang.seok.bae@intel.com
---
 tools/testing/selftests/x86/Makefile |   2 +
 tools/testing/selftests/x86/amx.c    | 166 +---------------------
 tools/testing/selftests/x86/xstate.c | 198 +++++++++++++++++++++++++++
 tools/testing/selftests/x86/xstate.h |   2 +
 4 files changed, 204 insertions(+), 164 deletions(-)
 create mode 100644 tools/testing/selftests/x86/xstate.c

diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index d51249f14e2fe..f15efdc6aef73 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -132,3 +132,5 @@ $(OUTPUT)/check_initial_reg_state_64: CFLAGS += -Wl,-ereal_start -static
 
 $(OUTPUT)/nx_stack_32: CFLAGS += -Wl,-z,noexecstack
 $(OUTPUT)/nx_stack_64: CFLAGS += -Wl,-z,noexecstack
+
+$(OUTPUT)/amx_64: EXTRA_FILES += xstate.c
diff --git a/tools/testing/selftests/x86/amx.c b/tools/testing/selftests/x86/amx.c
index cde22f3039056..b3c51dd25abca 100644
--- a/tools/testing/selftests/x86/amx.c
+++ b/tools/testing/selftests/x86/amx.c
@@ -3,7 +3,6 @@
 #define _GNU_SOURCE
 #include <err.h>
 #include <errno.h>
-#include <pthread.h>
 #include <setjmp.h>
 #include <stdio.h>
 #include <string.h>
@@ -434,14 +433,6 @@ static inline bool __validate_tiledata_regs(struct xsave_buffer *xbuf1)
 	return true;
 }
 
-static inline void validate_tiledata_regs_same(struct xsave_buffer *xbuf)
-{
-	int ret = __validate_tiledata_regs(xbuf);
-
-	if (ret != 0)
-		fatal_error("TILEDATA registers changed");
-}
-
 static inline void validate_tiledata_regs_changed(struct xsave_buffer *xbuf)
 {
 	int ret = __validate_tiledata_regs(xbuf);
@@ -498,158 +489,6 @@ static void test_fork(void)
 	_exit(0);
 }
 
-/* Context switching test */
-
-static struct _ctxtswtest_cfg {
-	unsigned int iterations;
-	unsigned int num_threads;
-} ctxtswtest_config;
-
-struct futex_info {
-	pthread_t thread;
-	int nr;
-	pthread_mutex_t mutex;
-	struct futex_info *next;
-};
-
-static void *check_tiledata(void *info)
-{
-	struct futex_info *finfo = (struct futex_info *)info;
-	struct xsave_buffer *xbuf;
-	int i;
-
-	xbuf = alloc_xbuf();
-	if (!xbuf)
-		fatal_error("unable to allocate XSAVE buffer");
-
-	/*
-	 * Load random data into 'xbuf' and then restore
-	 * it to the tile registers themselves.
-	 */
-	load_rand_tiledata(xbuf);
-	for (i = 0; i < ctxtswtest_config.iterations; i++) {
-		pthread_mutex_lock(&finfo->mutex);
-
-		/*
-		 * Ensure the register values have not
-		 * diverged from those recorded in 'xbuf'.
-		 */
-		validate_tiledata_regs_same(xbuf);
-
-		/* Load new, random values into xbuf and registers */
-		load_rand_tiledata(xbuf);
-
-		/*
-		 * The last thread's last unlock will be for
-		 * thread 0's mutex.  However, thread 0 will
-		 * have already exited the loop and the mutex
-		 * will already be unlocked.
-		 *
-		 * Because this is not an ERRORCHECK mutex,
-		 * that inconsistency will be silently ignored.
-		 */
-		pthread_mutex_unlock(&finfo->next->mutex);
-	}
-
-	free(xbuf);
-	/*
-	 * Return this thread's finfo, which is
-	 * a unique value for this thread.
-	 */
-	return finfo;
-}
-
-static int create_threads(int num, struct futex_info *finfo)
-{
-	int i;
-
-	for (i = 0; i < num; i++) {
-		int next_nr;
-
-		finfo[i].nr = i;
-		/*
-		 * Thread 'i' will wait on this mutex to
-		 * be unlocked.  Lock it immediately after
-		 * initialization:
-		 */
-		pthread_mutex_init(&finfo[i].mutex, NULL);
-		pthread_mutex_lock(&finfo[i].mutex);
-
-		next_nr = (i + 1) % num;
-		finfo[i].next = &finfo[next_nr];
-
-		if (pthread_create(&finfo[i].thread, NULL, check_tiledata, &finfo[i]))
-			fatal_error("pthread_create()");
-	}
-	return 0;
-}
-
-static void affinitize_cpu0(void)
-{
-	cpu_set_t cpuset;
-
-	CPU_ZERO(&cpuset);
-	CPU_SET(0, &cpuset);
-
-	if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0)
-		fatal_error("sched_setaffinity to CPU 0");
-}
-
-static void test_context_switch(void)
-{
-	struct futex_info *finfo;
-	int i;
-
-	/* Affinitize to one CPU to force context switches */
-	affinitize_cpu0();
-
-	req_xtiledata_perm();
-
-	printf("[RUN]\tCheck tiledata context switches, %d iterations, %d threads.\n",
-	       ctxtswtest_config.iterations,
-	       ctxtswtest_config.num_threads);
-
-
-	finfo = malloc(sizeof(*finfo) * ctxtswtest_config.num_threads);
-	if (!finfo)
-		fatal_error("malloc()");
-
-	create_threads(ctxtswtest_config.num_threads, finfo);
-
-	/*
-	 * This thread wakes up thread 0
-	 * Thread 0 will wake up 1
-	 * Thread 1 will wake up 2
-	 * ...
-	 * the last thread will wake up 0
-	 *
-	 * ... this will repeat for the configured
-	 * number of iterations.
-	 */
-	pthread_mutex_unlock(&finfo[0].mutex);
-
-	/* Wait for all the threads to finish: */
-	for (i = 0; i < ctxtswtest_config.num_threads; i++) {
-		void *thread_retval;
-		int rc;
-
-		rc = pthread_join(finfo[i].thread, &thread_retval);
-
-		if (rc)
-			fatal_error("pthread_join() failed for thread %d err: %d\n",
-					i, rc);
-
-		if (thread_retval != &finfo[i])
-			fatal_error("unexpected thread retval for thread %d: %p\n",
-					i, thread_retval);
-
-	}
-
-	printf("[OK]\tNo incorrect case was found.\n");
-
-	free(finfo);
-}
-
 /* Ptrace test */
 
 /*
@@ -745,6 +584,7 @@ static void test_ptrace(void)
 
 int main(void)
 {
+	const unsigned int ctxtsw_num_threads = 5, ctxtsw_iterations = 10;
 	unsigned long features;
 	long rc;
 
@@ -772,9 +612,7 @@ int main(void)
 
 	test_fork();
 
-	ctxtswtest_config.iterations = 10;
-	ctxtswtest_config.num_threads = 5;
-	test_context_switch();
+	test_context_switch(XFEATURE_XTILEDATA, ctxtsw_num_threads, ctxtsw_iterations);
 
 	test_ptrace();
 
diff --git a/tools/testing/selftests/x86/xstate.c b/tools/testing/selftests/x86/xstate.c
new file mode 100644
index 0000000000000..e5b51e7d13e15
--- /dev/null
+++ b/tools/testing/selftests/x86/xstate.c
@@ -0,0 +1,198 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <pthread.h>
+#include <stdbool.h>
+
+#include "helpers.h"
+#include "xstate.h"
+
+static struct xstate_info xstate;
+
+struct futex_info {
+	unsigned int iterations;
+	struct futex_info *next;
+	pthread_mutex_t mutex;
+	pthread_t thread;
+	bool valid;
+	int nr;
+};
+
+static inline void load_rand_xstate(struct xstate_info *xstate, struct xsave_buffer *xbuf)
+{
+	clear_xstate_header(xbuf);
+	set_xstatebv(xbuf, xstate->mask);
+	set_rand_data(xstate, xbuf);
+	xrstor(xbuf, xstate->mask);
+}
+
+static inline bool validate_xstate_same(struct xsave_buffer *xbuf1, struct xsave_buffer *xbuf2)
+{
+	int ret;
+
+	ret = memcmp(&xbuf1->bytes[xstate.xbuf_offset],
+		     &xbuf2->bytes[xstate.xbuf_offset],
+		     xstate.size);
+	return ret == 0;
+}
+
+static inline bool validate_xregs_same(struct xsave_buffer *xbuf1)
+{
+	struct xsave_buffer *xbuf2;
+	bool ret;
+
+	xbuf2 = alloc_xbuf();
+	if (!xbuf2)
+		ksft_exit_fail_msg("failed to allocate XSAVE buffer\n");
+
+	xsave(xbuf2, xstate.mask);
+	ret = validate_xstate_same(xbuf1, xbuf2);
+
+	free(xbuf2);
+	return ret;
+}
+
+/* Context switching test */
+
+static void *check_xstate(void *info)
+{
+	struct futex_info *finfo = (struct futex_info *)info;
+	struct xsave_buffer *xbuf;
+	int i;
+
+	xbuf = alloc_xbuf();
+	if (!xbuf)
+		ksft_exit_fail_msg("unable to allocate XSAVE buffer\n");
+
+	/*
+	 * Load random data into 'xbuf' and then restore it to the xstate
+	 * registers.
+	 */
+	load_rand_xstate(&xstate, xbuf);
+	finfo->valid = true;
+
+	for (i = 0; i < finfo->iterations; i++) {
+		pthread_mutex_lock(&finfo->mutex);
+
+		/*
+		 * Ensure the register values have not diverged from the
+		 * record. Then reload a new random value.  If it failed
+		 * ever before, skip it.
+		 */
+		if (finfo->valid) {
+			finfo->valid = validate_xregs_same(xbuf);
+			load_rand_xstate(&xstate, xbuf);
+		}
+
+		/*
+		 * The last thread's last unlock will be for thread 0's
+		 * mutex. However, thread 0 will have already exited the
+		 * loop and the mutex will already be unlocked.
+		 *
+		 * Because this is not an ERRORCHECK mutex, that
+		 * inconsistency will be silently ignored.
+		 */
+		pthread_mutex_unlock(&finfo->next->mutex);
+	}
+
+	free(xbuf);
+	return finfo;
+}
+
+static void create_threads(uint32_t num_threads, uint32_t iterations, struct futex_info *finfo)
+{
+	int i;
+
+	for (i = 0; i < num_threads; i++) {
+		int next_nr;
+
+		finfo[i].nr = i;
+		finfo[i].iterations = iterations;
+
+		/*
+		 * Thread 'i' will wait on this mutex to be unlocked.
+		 * Lock it immediately after initialization:
+		 */
+		pthread_mutex_init(&finfo[i].mutex, NULL);
+		pthread_mutex_lock(&finfo[i].mutex);
+
+		next_nr = (i + 1) % num_threads;
+		finfo[i].next = &finfo[next_nr];
+
+		if (pthread_create(&finfo[i].thread, NULL, check_xstate, &finfo[i]))
+			ksft_exit_fail_msg("pthread_create() failed\n");
+	}
+}
+
+static bool checkout_threads(uint32_t num_threads, struct futex_info *finfo)
+{
+	void *thread_retval;
+	bool valid = true;
+	int err, i;
+
+	for (i = 0; i < num_threads; i++) {
+		err = pthread_join(finfo[i].thread, &thread_retval);
+		if (err)
+			ksft_exit_fail_msg("pthread_join() failed for thread %d err: %d\n", i, err);
+
+		if (thread_retval != &finfo[i]) {
+			ksft_exit_fail_msg("unexpected thread retval for thread %d: %p\n",
+					   i, thread_retval);
+		}
+
+		valid &= finfo[i].valid;
+	}
+
+	return valid;
+}
+
+static void affinitize_cpu0(void)
+{
+	cpu_set_t cpuset;
+
+	CPU_ZERO(&cpuset);
+	CPU_SET(0, &cpuset);
+
+	if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0)
+		ksft_exit_fail_msg("sched_setaffinity to CPU 0 failed\n");
+}
+
+void test_context_switch(uint32_t feature_num, uint32_t num_threads, uint32_t iterations)
+{
+	struct futex_info *finfo;
+
+	/* Affinitize to one CPU to force context switches */
+	affinitize_cpu0();
+
+	xstate = get_xstate_info(feature_num);
+
+	printf("[RUN]\t%s: check context switches, %d iterations, %d threads.\n",
+	       xstate.name, iterations, num_threads);
+
+	finfo = malloc(sizeof(*finfo) * num_threads);
+	if (!finfo)
+		ksft_exit_fail_msg("unable allocate memory\n");
+
+	create_threads(num_threads, iterations, finfo);
+
+	/*
+	 * This thread wakes up thread 0
+	 * Thread 0 will wake up 1
+	 * Thread 1 will wake up 2
+	 * ...
+	 * The last thread will wake up 0
+	 *
+	 * This will repeat for the configured
+	 * number of iterations.
+	 */
+	pthread_mutex_unlock(&finfo[0].mutex);
+
+	/* Wait for all the threads to finish: */
+	if (checkout_threads(num_threads, finfo))
+		printf("[OK]\tNo incorrect case was found.\n");
+	else
+		printf("[FAIL]\tFailed with context switching test.\n");
+
+	free(finfo);
+}
diff --git a/tools/testing/selftests/x86/xstate.h b/tools/testing/selftests/x86/xstate.h
index d3461c4384614..5ef66f247eb92 100644
--- a/tools/testing/selftests/x86/xstate.h
+++ b/tools/testing/selftests/x86/xstate.h
@@ -189,4 +189,6 @@ static inline void set_rand_data(struct xstate_info *xstate, struct xsave_buffer
 		*ptr = data;
 }
 
+void test_context_switch(uint32_t feature_num, uint32_t num_threads, uint32_t iterations);
+
 #endif /* __SELFTESTS_X86_XSTATE_H */

From 7cb2fbe41949caa35ef1805323b8fc011fac2537 Mon Sep 17 00:00:00 2001
From: "Chang S. Bae" <chang.seok.bae@intel.com>
Date: Tue, 25 Feb 2025 17:07:25 -0800
Subject: [PATCH 0657/1173] selftests/x86/xstate: Refactor ptrace ABI test

Following the refactoring of the context switching test, the ptrace test is
another component reusable for other xstate features. As part of this
restructuring, add a missing check to validate the
user_xstateregs->xstate_fx_sw field in the ABI.

Also, replace err() and fatal_error() with ksft_exit_fail_msg() for
consistency in error handling.

  Expected output:
  $ amx_64
  ...
  [RUN]   AMX Tile data: inject xstate via ptrace().
  [OK]    'xfeatures' in SW reserved area was correctly written
  [OK]    xstate was correctly updated.

Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250226010731.2456-6-chang.seok.bae@intel.com
---
 tools/testing/selftests/x86/amx.c    | 108 +---------------------
 tools/testing/selftests/x86/xstate.c | 129 +++++++++++++++++++++++++++
 tools/testing/selftests/x86/xstate.h |   1 +
 3 files changed, 131 insertions(+), 107 deletions(-)

diff --git a/tools/testing/selftests/x86/amx.c b/tools/testing/selftests/x86/amx.c
index b3c51dd25abca..4bafbb72aa1b8 100644
--- a/tools/testing/selftests/x86/amx.c
+++ b/tools/testing/selftests/x86/amx.c
@@ -13,10 +13,8 @@
 #include <sys/auxv.h>
 #include <sys/mman.h>
 #include <sys/shm.h>
-#include <sys/ptrace.h>
 #include <sys/syscall.h>
 #include <sys/wait.h>
-#include <sys/uio.h>
 
 #include "helpers.h"
 #include "xstate.h"
@@ -32,8 +30,6 @@
 #define XFEATURE_MASK_XTILEDATA	(1 << XFEATURE_XTILEDATA)
 #define XFEATURE_MASK_XTILE	(XFEATURE_MASK_XTILECFG | XFEATURE_MASK_XTILEDATA)
 
-static uint32_t xbuf_size;
-
 struct xstate_info xtiledata;
 
 /* The helpers for managing XSAVE buffer and tile states: */
@@ -154,13 +150,6 @@ static inline bool load_rand_tiledata(struct xsave_buffer *xbuf)
 	return xrstor_safe(xbuf, XFEATURE_MASK_XTILEDATA);
 }
 
-/* Return XTILEDATA to its initial configuration. */
-static inline void init_xtiledata(void)
-{
-	clear_xstate_header(stashed_xsave);
-	xrstor_safe(stashed_xsave, XFEATURE_MASK_XTILEDATA);
-}
-
 enum expected_result { FAIL_EXPECTED, SUCCESS_EXPECTED };
 
 /* arch_prctl() and sigaltstack() test */
@@ -489,99 +478,6 @@ static void test_fork(void)
 	_exit(0);
 }
 
-/* Ptrace test */
-
-/*
- * Make sure the ptracee has the expanded kernel buffer on the first
- * use. Then, initialize the state before performing the state
- * injection from the ptracer.
- */
-static inline void ptracee_firstuse_tiledata(void)
-{
-	load_rand_tiledata(stashed_xsave);
-	init_xtiledata();
-}
-
-/*
- * Ptracer injects the randomized tile data state. It also reads
- * before and after that, which will execute the kernel's state copy
- * functions. So, the tester is advised to double-check any emitted
- * kernel messages.
- */
-static void ptracer_inject_tiledata(pid_t target)
-{
-	struct xsave_buffer *xbuf;
-	struct iovec iov;
-
-	xbuf = alloc_xbuf();
-	if (!xbuf)
-		fatal_error("unable to allocate XSAVE buffer");
-
-	printf("\tRead the init'ed tiledata via ptrace().\n");
-
-	iov.iov_base = xbuf;
-	iov.iov_len = xbuf_size;
-
-	memset(stashed_xsave, 0, xbuf_size);
-
-	if (ptrace(PTRACE_GETREGSET, target, (uint32_t)NT_X86_XSTATE, &iov))
-		fatal_error("PTRACE_GETREGSET");
-
-	if (!__compare_tiledata_state(stashed_xsave, xbuf))
-		printf("[OK]\tThe init'ed tiledata was read from ptracee.\n");
-	else
-		printf("[FAIL]\tThe init'ed tiledata was not read from ptracee.\n");
-
-	printf("\tInject tiledata via ptrace().\n");
-
-	load_rand_tiledata(xbuf);
-
-	memcpy(&stashed_xsave->bytes[xtiledata.xbuf_offset],
-	       &xbuf->bytes[xtiledata.xbuf_offset],
-	       xtiledata.size);
-
-	if (ptrace(PTRACE_SETREGSET, target, (uint32_t)NT_X86_XSTATE, &iov))
-		fatal_error("PTRACE_SETREGSET");
-
-	if (ptrace(PTRACE_GETREGSET, target, (uint32_t)NT_X86_XSTATE, &iov))
-		fatal_error("PTRACE_GETREGSET");
-
-	if (!__compare_tiledata_state(stashed_xsave, xbuf))
-		printf("[OK]\tTiledata was correctly written to ptracee.\n");
-	else
-		printf("[FAIL]\tTiledata was not correctly written to ptracee.\n");
-}
-
-static void test_ptrace(void)
-{
-	pid_t child;
-	int status;
-
-	child = fork();
-	if (child < 0) {
-		err(1, "fork");
-	} else if (!child) {
-		if (ptrace(PTRACE_TRACEME, 0, NULL, NULL))
-			err(1, "PTRACE_TRACEME");
-
-		ptracee_firstuse_tiledata();
-
-		raise(SIGTRAP);
-		_exit(0);
-	}
-
-	do {
-		wait(&status);
-	} while (WSTOPSIG(status) != SIGTRAP);
-
-	ptracer_inject_tiledata(child);
-
-	ptrace(PTRACE_DETACH, child, NULL, NULL);
-	wait(&status);
-	if (!WIFEXITED(status) || WEXITSTATUS(status))
-		err(1, "ptrace test");
-}
-
 int main(void)
 {
 	const unsigned int ctxtsw_num_threads = 5, ctxtsw_iterations = 10;
@@ -594,8 +490,6 @@ int main(void)
 		return KSFT_SKIP;
 	}
 
-	xbuf_size = get_xbuf_size();
-
 	xtiledata = get_xstate_info(XFEATURE_XTILEDATA);
 	if (!xtiledata.size || !xtiledata.xbuf_offset) {
 		fatal_error("xstate cpuid: invalid tile data size/offset: %d/%d",
@@ -614,7 +508,7 @@ int main(void)
 
 	test_context_switch(XFEATURE_XTILEDATA, ctxtsw_num_threads, ctxtsw_iterations);
 
-	test_ptrace();
+	test_ptrace(XFEATURE_XTILEDATA);
 
 	clearhandler(SIGILL);
 	free_stashed_xsave();
diff --git a/tools/testing/selftests/x86/xstate.c b/tools/testing/selftests/x86/xstate.c
index e5b51e7d13e15..d318b35ba547c 100644
--- a/tools/testing/selftests/x86/xstate.c
+++ b/tools/testing/selftests/x86/xstate.c
@@ -2,12 +2,25 @@
 
 #define _GNU_SOURCE
 
+#include <elf.h>
 #include <pthread.h>
 #include <stdbool.h>
 
+#include <sys/ptrace.h>
+#include <sys/uio.h>
+#include <sys/wait.h>
+
 #include "helpers.h"
 #include "xstate.h"
 
+static inline uint64_t xgetbv(uint32_t index)
+{
+	uint32_t eax, edx;
+
+	asm volatile("xgetbv" : "=a" (eax), "=d" (edx) : "c" (index));
+	return eax + ((uint64_t)edx << 32);
+}
+
 static struct xstate_info xstate;
 
 struct futex_info {
@@ -27,6 +40,19 @@ static inline void load_rand_xstate(struct xstate_info *xstate, struct xsave_buf
 	xrstor(xbuf, xstate->mask);
 }
 
+static inline void load_init_xstate(struct xstate_info *xstate, struct xsave_buffer *xbuf)
+{
+	clear_xstate_header(xbuf);
+	xrstor(xbuf, xstate->mask);
+}
+
+static inline void copy_xstate(struct xsave_buffer *xbuf_dst, struct xsave_buffer *xbuf_src)
+{
+	memcpy(&xbuf_dst->bytes[xstate.xbuf_offset],
+	       &xbuf_src->bytes[xstate.xbuf_offset],
+	       xstate.size);
+}
+
 static inline bool validate_xstate_same(struct xsave_buffer *xbuf1, struct xsave_buffer *xbuf2)
 {
 	int ret;
@@ -196,3 +222,106 @@ void test_context_switch(uint32_t feature_num, uint32_t num_threads, uint32_t it
 
 	free(finfo);
 }
+
+/*
+ * Ptrace test for the ABI format as described in arch/x86/include/asm/user.h
+ */
+
+/*
+ * Make sure the ptracee has the expanded kernel buffer on the first use.
+ * Then, initialize the state before performing the state injection from
+ * the ptracer. For non-dynamic states, this is benign.
+ */
+static inline void ptracee_touch_xstate(void)
+{
+	struct xsave_buffer *xbuf;
+
+	xbuf = alloc_xbuf();
+
+	load_rand_xstate(&xstate, xbuf);
+	load_init_xstate(&xstate, xbuf);
+
+	free(xbuf);
+}
+
+/*
+ * Ptracer injects the randomized xstate data. It also reads before and
+ * after that, which will execute the kernel's state copy functions.
+ */
+static void ptracer_inject_xstate(pid_t target)
+{
+	uint32_t xbuf_size = get_xbuf_size();
+	struct xsave_buffer *xbuf1, *xbuf2;
+	struct iovec iov;
+
+	/*
+	 * Allocate buffers to keep data while ptracer can write the
+	 * other buffer
+	 */
+	xbuf1 = alloc_xbuf();
+	xbuf2 = alloc_xbuf();
+	if (!xbuf1 || !xbuf2)
+		ksft_exit_fail_msg("unable to allocate XSAVE buffer\n");
+
+	iov.iov_base = xbuf1;
+	iov.iov_len  = xbuf_size;
+
+	if (ptrace(PTRACE_GETREGSET, target, (uint32_t)NT_X86_XSTATE, &iov))
+		ksft_exit_fail_msg("PTRACE_GETREGSET failed\n");
+
+	printf("[RUN]\t%s: inject xstate via ptrace().\n", xstate.name);
+
+	load_rand_xstate(&xstate, xbuf1);
+	copy_xstate(xbuf2, xbuf1);
+
+	if (ptrace(PTRACE_SETREGSET, target, (uint32_t)NT_X86_XSTATE, &iov))
+		ksft_exit_fail_msg("PTRACE_SETREGSET failed\n");
+
+	if (ptrace(PTRACE_GETREGSET, target, (uint32_t)NT_X86_XSTATE, &iov))
+		ksft_exit_fail_msg("PTRACE_GETREGSET failed\n");
+
+	if (*(uint64_t *)get_fpx_sw_bytes(xbuf1) == xgetbv(0))
+		printf("[OK]\t'xfeatures' in SW reserved area was correctly written\n");
+	else
+		printf("[FAIL]\t'xfeatures' in SW reserved area was not correctly written\n");
+
+	if (validate_xstate_same(xbuf2, xbuf1))
+		printf("[OK]\txstate was correctly updated.\n");
+	else
+		printf("[FAIL]\txstate was not correctly updated.\n");
+
+	free(xbuf1);
+	free(xbuf2);
+}
+
+void test_ptrace(uint32_t feature_num)
+{
+	pid_t child;
+	int status;
+
+	xstate = get_xstate_info(feature_num);
+
+	child = fork();
+	if (child < 0) {
+		ksft_exit_fail_msg("fork() failed\n");
+	} else if (!child) {
+		if (ptrace(PTRACE_TRACEME, 0, NULL, NULL))
+			ksft_exit_fail_msg("PTRACE_TRACEME failed\n");
+
+		ptracee_touch_xstate();
+
+		raise(SIGTRAP);
+		_exit(0);
+	}
+
+	do {
+		wait(&status);
+	} while (WSTOPSIG(status) != SIGTRAP);
+
+	ptracer_inject_xstate(child);
+
+	ptrace(PTRACE_DETACH, child, NULL, NULL);
+	wait(&status);
+	if (!WIFEXITED(status) || WEXITSTATUS(status))
+		ksft_exit_fail_msg("ptracee exit error\n");
+}
diff --git a/tools/testing/selftests/x86/xstate.h b/tools/testing/selftests/x86/xstate.h
index 5ef66f247eb92..2bf11d3a3ce93 100644
--- a/tools/testing/selftests/x86/xstate.h
+++ b/tools/testing/selftests/x86/xstate.h
@@ -190,5 +190,6 @@ static inline void set_rand_data(struct xstate_info *xstate, struct xsave_buffer
 }
 
 void test_context_switch(uint32_t feature_num, uint32_t num_threads, uint32_t iterations);
+void test_ptrace(uint32_t feature_num);
 
 #endif /* __SELFTESTS_X86_XSTATE_H */

From e075d9fa16b3681b8a375cb47f4b5a1901e93530 Mon Sep 17 00:00:00 2001
From: "Chang S. Bae" <chang.seok.bae@intel.com>
Date: Tue, 25 Feb 2025 17:07:26 -0800
Subject: [PATCH 0658/1173] selftests/x86/xstate: Introduce signal ABI test

With the refactored test cases, another xstate exposure to userspace is
through signal delivery. While amx.c includes signal-related scenarios,
its primary focus is on xstate permission management, which is largely
specific to dynamic states.

The remaining gap is testing xstate preservation and restoration across
signal delivery. The kernel defines an ABI for presenting xstate in the
signal frame, closely resembling the hardware XSAVE format, where xstate
modification is also possible.

Introduce a new test case to verify xstate preservation across signal
delivery and return, that is ensuring ABI compatibility by:

 - Loading xstate before raising a signal.

 - Verifying correct exposure in the signal frame

 - Modifying xstate in the signal frame before returning.

 - Checking the state restoration upon signal return.

Integrate this test into the AMX test suite as an initial usage site.

  Expected output:
  $ amx_64
  ...
  [RUN]   AMX Tile data: load xstate and raise SIGUSR1
  [OK]    'magic1' is valid
  [OK]    'xfeatures' in SW reserved area is valid
  [OK]    'xfeatures' in XSAVE header is valid
  [OK]    xstate delivery was successful
  [OK]    'magic2' is valid
  [RUN]   AMX Tile data: load new xstate from sighandler and check it after sigreturn
  [OK]    xstate was restored correctly

Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250226010731.2456-7-chang.seok.bae@intel.com
---
 tools/testing/selftests/x86/amx.c    |   2 +
 tools/testing/selftests/x86/xstate.c | 108 +++++++++++++++++++++++++++
 tools/testing/selftests/x86/xstate.h |   1 +
 3 files changed, 111 insertions(+)

diff --git a/tools/testing/selftests/x86/amx.c b/tools/testing/selftests/x86/amx.c
index 4bafbb72aa1b8..9cb691d67ef49 100644
--- a/tools/testing/selftests/x86/amx.c
+++ b/tools/testing/selftests/x86/amx.c
@@ -510,6 +510,8 @@ int main(void)
 
 	test_ptrace(XFEATURE_XTILEDATA);
 
+	test_signal(XFEATURE_XTILEDATA);
+
 	clearhandler(SIGILL);
 	free_stashed_xsave();
 
diff --git a/tools/testing/selftests/x86/xstate.c b/tools/testing/selftests/x86/xstate.c
index d318b35ba547c..b5600f492632e 100644
--- a/tools/testing/selftests/x86/xstate.c
+++ b/tools/testing/selftests/x86/xstate.c
@@ -21,6 +21,11 @@ static inline uint64_t xgetbv(uint32_t index)
 	return eax + ((uint64_t)edx << 32);
 }
 
+static inline uint64_t get_xstatebv(struct xsave_buffer *xbuf)
+{
+	return *(uint64_t *)(&xbuf->header);
+}
+
 static struct xstate_info xstate;
 
 struct futex_info {
@@ -325,3 +330,106 @@ void test_ptrace(uint32_t feature_num)
 	if (!WIFEXITED(status) || WEXITSTATUS(status))
 		ksft_exit_fail_msg("ptracee exit error\n");
 }
+
+/*
+ * Test signal delivery for the ABI compatibility.
+ * See the ABI format: arch/x86/include/uapi/asm/sigcontext.h
+ */
+
+/*
+ * Avoid using printf() in signal handlers as it is not
+ * async-signal-safe.
+ */
+#define SIGNAL_BUF_LEN 1000
+static char signal_message_buffer[SIGNAL_BUF_LEN];
+static void sig_print(char *msg)
+{
+	int left = SIGNAL_BUF_LEN - strlen(signal_message_buffer) - 1;
+
+	strncat(signal_message_buffer, msg, left);
+}
+
+static struct xsave_buffer *stashed_xbuf;
+
+static void validate_sigfpstate(int sig, siginfo_t *si, void *ctx_void)
+{
+	ucontext_t *ctx = (ucontext_t *)ctx_void;
+	void *xbuf = ctx->uc_mcontext.fpregs;
+	struct _fpx_sw_bytes *sw_bytes;
+	uint32_t magic2;
+
+	/* Reset the signal message buffer: */
+	signal_message_buffer[0] = '\0';
+
+	sw_bytes = get_fpx_sw_bytes(xbuf);
+	if (sw_bytes->magic1 == FP_XSTATE_MAGIC1)
+		sig_print("[OK]\t'magic1' is valid\n");
+	else
+		sig_print("[FAIL]\t'magic1' is not valid\n");
+
+	if (get_fpx_sw_bytes_features(xbuf) & xstate.mask)
+		sig_print("[OK]\t'xfeatures' in SW reserved area is valid\n");
+	else
+		sig_print("[FAIL]\t'xfeatures' in SW reserved area is not valid\n");
+
+	if (get_xstatebv(xbuf) & xstate.mask)
+		sig_print("[OK]\t'xfeatures' in XSAVE header is valid\n");
+	else
+		sig_print("[FAIL]\t'xfeatures' in XSAVE hader is not valid\n");
+
+	if (validate_xstate_same(stashed_xbuf, xbuf))
+		sig_print("[OK]\txstate delivery was successful\n");
+	else
+		sig_print("[FAIL]\txstate delivery was not successful\n");
+
+	magic2 = *(uint32_t *)(xbuf + sw_bytes->xstate_size);
+	if (magic2 == FP_XSTATE_MAGIC2)
+		sig_print("[OK]\t'magic2' is valid\n");
+	else
+		sig_print("[FAIL]\t'magic2' is not valid\n");
+
+	set_rand_data(&xstate, xbuf);
+	copy_xstate(stashed_xbuf, xbuf);
+}
+
+void test_signal(uint32_t feature_num)
+{
+	bool valid_xstate;
+
+	xstate = get_xstate_info(feature_num);
+
+	/*
+	 * The signal handler will access this to verify xstate context
+	 * preservation.
+	 */
+
+	stashed_xbuf = alloc_xbuf();
+	if (!stashed_xbuf)
+		ksft_exit_fail_msg("unable to allocate XSAVE buffer\n");
+
+	printf("[RUN]\t%s: load xstate and raise SIGUSR1\n", xstate.name);
+
+	sethandler(SIGUSR1, validate_sigfpstate, 0);
+
+	load_rand_xstate(&xstate, stashed_xbuf);
+
+	raise(SIGUSR1);
+
+	/*
+	 * Immediately record the test result, deferring printf() to
+	 * prevent unintended state contamination by that.
+	 */
+	valid_xstate = validate_xregs_same(stashed_xbuf);
+	printf("%s", signal_message_buffer);
+
+	printf("[RUN]\t%s: load new xstate from sighandler and check it after sigreturn\n",
+	       xstate.name);
+
+	if (valid_xstate)
+		printf("[OK]\txstate was restored correctly\n");
+	else
+		printf("[FAIL]\txstate restoration failed\n");
+
+	clearhandler(SIGUSR1);
+	free(stashed_xbuf);
+}
diff --git a/tools/testing/selftests/x86/xstate.h b/tools/testing/selftests/x86/xstate.h
index 2bf11d3a3ce93..4d0ffe9609f8b 100644
--- a/tools/testing/selftests/x86/xstate.h
+++ b/tools/testing/selftests/x86/xstate.h
@@ -191,5 +191,6 @@ static inline void set_rand_data(struct xstate_info *xstate, struct xsave_buffer
 
 void test_context_switch(uint32_t feature_num, uint32_t num_threads, uint32_t iterations);
 void test_ptrace(uint32_t feature_num);
+void test_signal(uint32_t feature_num);
 
 #endif /* __SELFTESTS_X86_XSTATE_H */

From 10d8a204c5009fb8a6cb2790d17b5611b795c349 Mon Sep 17 00:00:00 2001
From: "Chang S. Bae" <chang.seok.bae@intel.com>
Date: Tue, 25 Feb 2025 17:07:27 -0800
Subject: [PATCH 0659/1173] selftests/x86/xstate: Consolidate test invocations
 into a single entry

Currently, each of the three xstate tests runs as a separate invocation,
requiring the xstate number to be passed and state information to be
reconstructed repeatedly. This approach arose from their individual and
isolated development, but now it makes sense to unify them.

Introduce a wrapper function that first verifies feature availability
from the kernel and constructs the necessary state information once. The
wrapper then sequentially invokes all tests to ensure consistent
execution.

Update the AMX test to use this unified invocation.

Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250226010731.2456-8-chang.seok.bae@intel.com
---
 tools/testing/selftests/x86/amx.c    | 11 ++++----
 tools/testing/selftests/x86/xstate.c | 38 ++++++++++++++++++++--------
 tools/testing/selftests/x86/xstate.h |  5 ++--
 3 files changed, 35 insertions(+), 19 deletions(-)

diff --git a/tools/testing/selftests/x86/amx.c b/tools/testing/selftests/x86/amx.c
index 9cb691d67ef49..40769c16de1bb 100644
--- a/tools/testing/selftests/x86/amx.c
+++ b/tools/testing/selftests/x86/amx.c
@@ -480,7 +480,6 @@ static void test_fork(void)
 
 int main(void)
 {
-	const unsigned int ctxtsw_num_threads = 5, ctxtsw_iterations = 10;
 	unsigned long features;
 	long rc;
 
@@ -506,11 +505,11 @@ int main(void)
 
 	test_fork();
 
-	test_context_switch(XFEATURE_XTILEDATA, ctxtsw_num_threads, ctxtsw_iterations);
-
-	test_ptrace(XFEATURE_XTILEDATA);
-
-	test_signal(XFEATURE_XTILEDATA);
+	/*
+	 * Perform generic xstate tests for context switching, ptrace,
+	 * and signal.
+	 */
+	test_xstate(XFEATURE_XTILEDATA);
 
 	clearhandler(SIGILL);
 	free_stashed_xsave();
diff --git a/tools/testing/selftests/x86/xstate.c b/tools/testing/selftests/x86/xstate.c
index b5600f492632e..fd8451e55f3f1 100644
--- a/tools/testing/selftests/x86/xstate.c
+++ b/tools/testing/selftests/x86/xstate.c
@@ -6,7 +6,9 @@
 #include <pthread.h>
 #include <stdbool.h>
 
+#include <asm/prctl.h>
 #include <sys/ptrace.h>
+#include <sys/syscall.h>
 #include <sys/uio.h>
 #include <sys/wait.h>
 
@@ -189,15 +191,13 @@ static void affinitize_cpu0(void)
 		ksft_exit_fail_msg("sched_setaffinity to CPU 0 failed\n");
 }
 
-void test_context_switch(uint32_t feature_num, uint32_t num_threads, uint32_t iterations)
+static void test_context_switch(uint32_t num_threads, uint32_t iterations)
 {
 	struct futex_info *finfo;
 
 	/* Affinitize to one CPU to force context switches */
 	affinitize_cpu0();
 
-	xstate = get_xstate_info(feature_num);
-
 	printf("[RUN]\t%s: check context switches, %d iterations, %d threads.\n",
 	       xstate.name, iterations, num_threads);
 
@@ -299,13 +299,11 @@ static void ptracer_inject_xstate(pid_t target)
 	free(xbuf2);
 }
 
-void test_ptrace(uint32_t feature_num)
+static void test_ptrace(void)
 {
 	pid_t child;
 	int status;
 
-	xstate = get_xstate_info(feature_num);
-
 	child = fork();
 	if (child < 0) {
 		ksft_exit_fail_msg("fork() failed\n");
@@ -392,17 +390,14 @@ static void validate_sigfpstate(int sig, siginfo_t *si, void *ctx_void)
 	copy_xstate(stashed_xbuf, xbuf);
 }
 
-void test_signal(uint32_t feature_num)
+static void test_signal(void)
 {
 	bool valid_xstate;
 
-	xstate = get_xstate_info(feature_num);
-
 	/*
 	 * The signal handler will access this to verify xstate context
 	 * preservation.
 	 */
-
 	stashed_xbuf = alloc_xbuf();
 	if (!stashed_xbuf)
 		ksft_exit_fail_msg("unable to allocate XSAVE buffer\n");
@@ -433,3 +428,26 @@ void test_signal(uint32_t feature_num)
 	clearhandler(SIGUSR1);
 	free(stashed_xbuf);
 }
+
+void test_xstate(uint32_t feature_num)
+{
+	const unsigned int ctxtsw_num_threads = 5, ctxtsw_iterations = 10;
+	unsigned long features;
+	long rc;
+
+	rc = syscall(SYS_arch_prctl, ARCH_GET_XCOMP_SUPP, &features);
+	if (rc || !(features & (1 << feature_num))) {
+		ksft_print_msg("The kernel does not support feature number: %u\n", feature_num);
+		return;
+	}
+
+	xstate = get_xstate_info(feature_num);
+	if (!xstate.size || !xstate.xbuf_offset) {
+		ksft_exit_fail_msg("invalid state size/offset (%d/%d)\n",
+				   xstate.size, xstate.xbuf_offset);
+	}
+
+	test_context_switch(ctxtsw_num_threads, ctxtsw_iterations);
+	test_ptrace();
+	test_signal();
+}
diff --git a/tools/testing/selftests/x86/xstate.h b/tools/testing/selftests/x86/xstate.h
index 4d0ffe9609f8b..42af36ec852f4 100644
--- a/tools/testing/selftests/x86/xstate.h
+++ b/tools/testing/selftests/x86/xstate.h
@@ -189,8 +189,7 @@ static inline void set_rand_data(struct xstate_info *xstate, struct xsave_buffer
 		*ptr = data;
 }
 
-void test_context_switch(uint32_t feature_num, uint32_t num_threads, uint32_t iterations);
-void test_ptrace(uint32_t feature_num);
-void test_signal(uint32_t feature_num);
+/* Testing kernel's context switching and ABI support for the xstate. */
+void test_xstate(uint32_t feature_num);
 
 #endif /* __SELFTESTS_X86_XSTATE_H */

From fa826c1f2cc92db44c207d323d2568e3f04c1257 Mon Sep 17 00:00:00 2001
From: "Chang S. Bae" <chang.seok.bae@intel.com>
Date: Tue, 25 Feb 2025 17:07:28 -0800
Subject: [PATCH 0660/1173] selftests/x86/xstate: Clarify supported xstates

The established xstate test code is designed to be generic, but certain
xstates require special handling and cannot be tested without additional
adjustments.

Clarify which xstates are currently supported, and enforce testing only
for them.

Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250226010731.2456-9-chang.seok.bae@intel.com
---
 tools/testing/selftests/x86/xstate.c | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/tools/testing/selftests/x86/xstate.c b/tools/testing/selftests/x86/xstate.c
index fd8451e55f3f1..875777911d826 100644
--- a/tools/testing/selftests/x86/xstate.c
+++ b/tools/testing/selftests/x86/xstate.c
@@ -15,6 +15,24 @@
 #include "helpers.h"
 #include "xstate.h"
 
+/*
+ * The userspace xstate test suite is designed to be generic and operates
+ * with randomized xstate data. However, some states require special handling:
+ *
+ * - PKRU and XTILECFG need specific adjustments, such as modifying
+ *   randomization behavior or using fixed values.
+ * - But, PKRU already has a dedicated test suite in /tools/selftests/mm.
+ * - Legacy states (FP and SSE) are excluded, as they are not considered
+ *   part of extended states (xstates) and their usage is already deeply
+ *   integrated into user-space libraries.
+ */
+#define XFEATURE_MASK_TEST_SUPPORTED	\
+	((1 << XFEATURE_YMM) |		\
+	 (1 << XFEATURE_OPMASK)	|	\
+	 (1 << XFEATURE_ZMM_Hi256) |	\
+	 (1 << XFEATURE_Hi16_ZMM) |	\
+	 (1 << XFEATURE_XTILEDATA))
+
 static inline uint64_t xgetbv(uint32_t index)
 {
 	uint32_t eax, edx;
@@ -435,6 +453,12 @@ void test_xstate(uint32_t feature_num)
 	unsigned long features;
 	long rc;
 
+	if (!(XFEATURE_MASK_TEST_SUPPORTED & (1 << feature_num))) {
+		ksft_print_msg("The xstate test does not fully support the component %u, yet.\n",
+			       feature_num);
+		return;
+	}
+
 	rc = syscall(SYS_arch_prctl, ARCH_GET_XCOMP_SUPP, &features);
 	if (rc || !(features & (1 << feature_num))) {
 		ksft_print_msg("The kernel does not support feature number: %u\n", feature_num);

From bfc98dbcb3c75c6e2eb1dcf389d02a8c2419c41c Mon Sep 17 00:00:00 2001
From: "Chang S. Bae" <chang.seok.bae@intel.com>
Date: Tue, 25 Feb 2025 17:07:29 -0800
Subject: [PATCH 0661/1173] selftests/x86/avx: Add AVX tests

Add xstate testing specifically for those vector register states,
validating kernel's context switching and ensuring ABI compliance.
Use the established xstate testing framework.

Alternatively, this invocation could be placed directly in
xstate.c::main(). However, the current test file naming convention, which
clearly specifies the tested area, seems reasonable. Adding avx.c
considerably aligns with that convention.

The test output should be like this for ZMM_Hi256 as an example:

  $ avx_64
  ...
  [RUN]   AVX-512 ZMM_Hi256: check context switches, 10 iterations, 5 threads.
  [OK]    No incorrect case was found.
  [RUN]   AVX-512 ZMM_Hi256: inject xstate via ptrace().
  [OK]    'xfeatures' in SW reserved area was correctly written
  [OK]    xstate was correctly updated.
  [RUN]   AVX-512 ZMM_Hi256: load xstate and raise SIGUSR1
  [OK]    'magic1' is valid
  [OK]    'xfeatures' in SW reserved area is valid
  [OK]    'xfeatures' in XSAVE header is valid
  [OK]    xstate delivery was successful
  [OK]    'magic2' is valid
  [RUN]   AVX-512 ZMM_Hi256: load new xstate from sighandler and check it after sigreturn
  [OK]    xstate was restored correctly

But systems without AVX-512 will look like:
  ...
  The kernel does not support feature number: 5
  The kernel does not support feature number: 6
  The kernel does not support feature number: 7

Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250226010731.2456-10-chang.seok.bae@intel.com
---
 tools/testing/selftests/x86/Makefile |  4 +++-
 tools/testing/selftests/x86/avx.c    | 12 ++++++++++++
 2 files changed, 15 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/x86/avx.c

diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index f15efdc6aef73..28422c32cc8ff 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -19,7 +19,7 @@ TARGETS_C_32BIT_ONLY := entry_from_vm86 test_syscall_vdso unwind_vdso \
 			test_FCMOV test_FCOMI test_FISTTP \
 			vdso_restorer
 TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip syscall_numbering \
-			corrupt_xstate_header amx lam test_shadow_stack
+			corrupt_xstate_header amx lam test_shadow_stack avx
 # Some selftests require 32bit support enabled also on 64bit systems
 TARGETS_C_32BIT_NEEDED := ldt_gdt ptrace_syscall
 
@@ -133,4 +133,6 @@ $(OUTPUT)/check_initial_reg_state_64: CFLAGS += -Wl,-ereal_start -static
 $(OUTPUT)/nx_stack_32: CFLAGS += -Wl,-z,noexecstack
 $(OUTPUT)/nx_stack_64: CFLAGS += -Wl,-z,noexecstack
 
+$(OUTPUT)/avx_64: CFLAGS += -mno-avx -mno-avx512f
 $(OUTPUT)/amx_64: EXTRA_FILES += xstate.c
+$(OUTPUT)/avx_64: EXTRA_FILES += xstate.c
diff --git a/tools/testing/selftests/x86/avx.c b/tools/testing/selftests/x86/avx.c
new file mode 100644
index 0000000000000..11d5367c235fc
--- /dev/null
+++ b/tools/testing/selftests/x86/avx.c
@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE /* Required for inline xstate helpers */
+#include "xstate.h"
+
+int main(void)
+{
+	test_xstate(XFEATURE_YMM);
+	test_xstate(XFEATURE_OPMASK);
+	test_xstate(XFEATURE_ZMM_Hi256);
+	test_xstate(XFEATURE_Hi16_ZMM);
+}

From b815f6877d8063482fe745f098eeef632679aa8a Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 24 Feb 2025 13:37:11 +0100
Subject: [PATCH 0662/1173] x86/bhi: Add BHI stubs

Add an array of code thunks, to be called from the FineIBT preamble,
clobbering the first 'n' argument registers for speculative execution.

Notably the 0th entry will clobber no argument registers and will never
be used, it exists so the array can be naturally indexed, while the 7th
entry will clobber all the 6 argument registers and also RSP in order to
mess up stack based arguments.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Kees Cook <kees@kernel.org>
Link: https://lore.kernel.org/r/20250224124200.717378681@infradead.org
---
 arch/x86/include/asm/cfi.h |   4 +
 arch/x86/lib/Makefile      |   3 +-
 arch/x86/lib/bhi.S         | 147 +++++++++++++++++++++++++++++++++++++
 3 files changed, 153 insertions(+), 1 deletion(-)
 create mode 100644 arch/x86/lib/bhi.S

diff --git a/arch/x86/include/asm/cfi.h b/arch/x86/include/asm/cfi.h
index 7dd5ab239c87b..7c15c4bfe65f2 100644
--- a/arch/x86/include/asm/cfi.h
+++ b/arch/x86/include/asm/cfi.h
@@ -101,6 +101,10 @@ enum cfi_mode {
 
 extern enum cfi_mode cfi_mode;
 
+typedef u8 bhi_thunk[32];
+extern bhi_thunk __bhi_args[];
+extern bhi_thunk __bhi_args_end[];
+
 struct pt_regs;
 
 #ifdef CONFIG_CFI_CLANG
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 8a59c61624c2f..f453507649d48 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -66,5 +66,6 @@ endif
         lib-y += clear_page_64.o copy_page_64.o
         lib-y += memmove_64.o memset_64.o
         lib-y += copy_user_64.o copy_user_uncached_64.o
-	lib-y += cmpxchg16b_emu.o
+        lib-y += cmpxchg16b_emu.o
+        lib-y += bhi.o
 endif
diff --git a/arch/x86/lib/bhi.S b/arch/x86/lib/bhi.S
new file mode 100644
index 0000000000000..58891681261b0
--- /dev/null
+++ b/arch/x86/lib/bhi.S
@@ -0,0 +1,147 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <linux/linkage.h>
+#include <asm/unwind_hints.h>
+#include <asm/nospec-branch.h>
+
+/*
+ * Notably, the FineIBT preamble calling these will have ZF set and r10 zero.
+ *
+ * The very last element is in fact larger than 32 bytes, but since its the
+ * last element, this does not matter,
+ *
+ * There are 2 #UD sites, located between 0,1-2,3 and 4,5-6,7 such that they
+ * can be reached using Jcc.d8, these elements (1 and 5) have sufficiently
+ * big alignment holes for this to not stagger the array.
+ */
+
+.pushsection .noinstr.text, "ax"
+
+	.align 32
+SYM_CODE_START(__bhi_args)
+
+#ifdef CONFIG_FINEIBT_BHI
+
+	.align 32
+SYM_INNER_LABEL(__bhi_args_0, SYM_L_LOCAL)
+	ANNOTATE_NOENDBR
+	UNWIND_HINT_FUNC
+	jne .Lud_1
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+
+	.align 32
+SYM_INNER_LABEL(__bhi_args_1, SYM_L_LOCAL)
+	ANNOTATE_NOENDBR
+	UNWIND_HINT_FUNC
+	jne .Lud_1
+	cmovne %r10, %rdi
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+
+	.align 8
+	ANNOTATE_REACHABLE
+.Lud_1:	ud2
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+
+	.align 32
+SYM_INNER_LABEL(__bhi_args_2, SYM_L_LOCAL)
+	ANNOTATE_NOENDBR
+	UNWIND_HINT_FUNC
+	jne .Lud_1
+	cmovne %r10, %rdi
+	cmovne %r10, %rsi
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+
+	.align 32
+SYM_INNER_LABEL(__bhi_args_3, SYM_L_LOCAL)
+	ANNOTATE_NOENDBR
+	UNWIND_HINT_FUNC
+	jne .Lud_1
+	cmovne %r10, %rdi
+	cmovne %r10, %rsi
+	cmovne %r10, %rdx
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+
+	.align 32
+SYM_INNER_LABEL(__bhi_args_4, SYM_L_LOCAL)
+	ANNOTATE_NOENDBR
+	UNWIND_HINT_FUNC
+	jne .Lud_2
+	cmovne %r10, %rdi
+	cmovne %r10, %rsi
+	cmovne %r10, %rdx
+	cmovne %r10, %rcx
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+
+	.align 32
+SYM_INNER_LABEL(__bhi_args_5, SYM_L_LOCAL)
+	ANNOTATE_NOENDBR
+	UNWIND_HINT_FUNC
+	jne .Lud_2
+	cmovne %r10, %rdi
+	cmovne %r10, %rsi
+	cmovne %r10, %rdx
+	cmovne %r10, %rcx
+	cmovne %r10, %r8
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+
+	.align 8
+	ANNOTATE_REACHABLE
+.Lud_2:	ud2
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+
+	.align 32
+SYM_INNER_LABEL(__bhi_args_6, SYM_L_LOCAL)
+	ANNOTATE_NOENDBR
+	UNWIND_HINT_FUNC
+	jne .Lud_2
+	cmovne %r10, %rdi
+	cmovne %r10, %rsi
+	cmovne %r10, %rdx
+	cmovne %r10, %rcx
+	cmovne %r10, %r8
+	cmovne %r10, %r9
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+
+	.align 32
+SYM_INNER_LABEL(__bhi_args_7, SYM_L_LOCAL)
+	ANNOTATE_NOENDBR
+	UNWIND_HINT_FUNC
+	jne .Lud_2
+	cmovne %r10, %rdi
+	cmovne %r10, %rsi
+	cmovne %r10, %rdx
+	cmovne %r10, %rcx
+	cmovne %r10, %r8
+	cmovne %r10, %r9
+	cmovne %r10, %rsp
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+
+#endif /* CONFIG_FINEIBT_BHI */
+
+	.align 32
+SYM_INNER_LABEL(__bhi_args_end, SYM_L_GLOBAL)
+	ANNOTATE_NOENDBR
+	nop /* Work around toolchain+objtool quirk */
+SYM_CODE_END(__bhi_args)
+
+.popsection

From 0c92385dc05ee9637c04372ea95a11bbf6e010ff Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 24 Feb 2025 13:37:12 +0100
Subject: [PATCH 0663/1173] x86/ibt: Implement FineIBT-BHI mitigation

While WAIT_FOR_ENDBR is specified to be a full speculation stop; it
has been shown that some implementations are 'leaky' to such an extend
that speculation can escape even the FineIBT preamble.

To deal with this, add additional hardening to the FineIBT preamble.

Notably, using a new LLVM feature:

  https://github.com/llvm/llvm-project/commit/e223485c9b38a5579991b8cebb6a200153eee245

which encodes the number of arguments in the kCFI preamble's register.

Using this register<->arity mapping, have the FineIBT preamble CALL
into a stub clobbering the relevant argument registers in the
speculative case.

Scott sayeth thusly:

Microarchitectural attacks such as Branch History Injection (BHI) and
Intra-mode Branch Target Injection (IMBTI) [1] can cause an indirect
call to mispredict to an adversary-influenced target within the same
hardware domain (e.g., within the kernel). Instructions at the
mispredicted target may execute speculatively and potentially expose
kernel data (e.g., to a user-mode adversary) through a
microarchitectural covert channel such as CPU cache state.

CET-IBT [2] is a coarse-grained control-flow integrity (CFI) ISA
extension that enforces that each indirect call (or indirect jump)
must land on an ENDBR (end branch) instruction, even speculatively*.
FineIBT is a software technique that refines CET-IBT by associating
each function type with a 32-bit hash and enforcing (at the callee)
that the hash of the caller's function pointer type matches the hash
of the callee's function type. However, recent research [3] has
demonstrated that the conditional branch that enforces FineIBT's hash
check can be coerced to mispredict, potentially allowing an adversary
to speculatively bypass the hash check:

__cfi_foo:
  ENDBR64
  SUB R10d, 0x01234567
  JZ foo    # Even if the hash check fails and ZF=0, this branch could still mispredict as taken
  UD2
foo:
  ...

The techniques demonstrated in [3] require the attacker to be able to
control the contents of at least one live register at the mispredicted
target. Therefore, this patch set introduces a sequence of CMOV
instructions at each indirect-callable target that poisons every live
register with data that the attacker cannot control whenever the
FineIBT hash check fails, thus mitigating any potential attack.

The security provided by this scheme has been discussed in detail on
an earlier thread [4].

 [1] https://www.intel.com/content/www/us/en/developer/articles/technical/software-security-guidance/technical-documentation/branch-history-injection.html
 [2] Intel Software Developer's Manual, Volume 1, Chapter 18
 [3] https://www.vusec.net/projects/native-bhi/
 [4] https://lore.kernel.org/lkml/20240927194925.707462984@infradead.org/
 *There are some caveats for certain processors, see [1] for more info

Suggested-by: Scott Constable <scott.d.constable@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Kees Cook <kees@kernel.org>
Link: https://lore.kernel.org/r/20250224124200.820402212@infradead.org
---
 Makefile                      |   3 +
 arch/x86/Kconfig              |   8 +++
 arch/x86/include/asm/cfi.h    |   6 ++
 arch/x86/kernel/alternative.c | 107 ++++++++++++++++++++++++++++++----
 arch/x86/net/bpf_jit_comp.c   |  29 ++++++---
 5 files changed, 134 insertions(+), 19 deletions(-)

diff --git a/Makefile b/Makefile
index 96407c1d6be16..f19431f25ed77 100644
--- a/Makefile
+++ b/Makefile
@@ -1014,6 +1014,9 @@ CC_FLAGS_CFI	:= -fsanitize=kcfi
 ifdef CONFIG_CFI_ICALL_NORMALIZE_INTEGERS
 	CC_FLAGS_CFI	+= -fsanitize-cfi-icall-experimental-normalize-integers
 endif
+ifdef CONFIG_FINEIBT_BHI
+	CC_FLAGS_CFI	+= -fsanitize-kcfi-arity
+endif
 ifdef CONFIG_RUST
 	# Always pass -Zsanitizer-cfi-normalize-integers as CONFIG_RUST selects
 	# CONFIG_CFI_ICALL_NORMALIZE_INTEGERS.
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index c4175f4635eea..5c277261507ed 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2473,6 +2473,10 @@ config CC_HAS_RETURN_THUNK
 config CC_HAS_ENTRY_PADDING
 	def_bool $(cc-option,-fpatchable-function-entry=16,16)
 
+config CC_HAS_KCFI_ARITY
+	def_bool $(cc-option,-fsanitize=kcfi -fsanitize-kcfi-arity)
+	depends on CC_IS_CLANG && !RUST
+
 config FUNCTION_PADDING_CFI
 	int
 	default 59 if FUNCTION_ALIGNMENT_64B
@@ -2498,6 +2502,10 @@ config FINEIBT
 	depends on X86_KERNEL_IBT && CFI_CLANG && MITIGATION_RETPOLINE
 	select CALL_PADDING
 
+config FINEIBT_BHI
+	def_bool y
+	depends on FINEIBT && CC_HAS_KCFI_ARITY
+
 config HAVE_CALL_THUNKS
 	def_bool y
 	depends on CC_HAS_ENTRY_PADDING && MITIGATION_RETHUNK && OBJTOOL
diff --git a/arch/x86/include/asm/cfi.h b/arch/x86/include/asm/cfi.h
index 7c15c4bfe65f2..2f6a01f098b5c 100644
--- a/arch/x86/include/asm/cfi.h
+++ b/arch/x86/include/asm/cfi.h
@@ -100,6 +100,7 @@ enum cfi_mode {
 };
 
 extern enum cfi_mode cfi_mode;
+extern bool cfi_bhi;
 
 typedef u8 bhi_thunk[32];
 extern bhi_thunk __bhi_args[];
@@ -129,6 +130,7 @@ static inline int cfi_get_offset(void)
 #define cfi_get_offset cfi_get_offset
 
 extern u32 cfi_get_func_hash(void *func);
+extern int cfi_get_func_arity(void *func);
 
 #ifdef CONFIG_FINEIBT
 extern bool decode_fineibt_insn(struct pt_regs *regs, unsigned long *target, u32 *type);
@@ -152,6 +154,10 @@ static inline u32 cfi_get_func_hash(void *func)
 {
 	return 0;
 }
+static inline int cfi_get_func_arity(void *func)
+{
+	return 0;
+}
 #endif /* CONFIG_CFI_CLANG */
 
 #if HAS_KERNEL_IBT == 1
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index c698c9e27ce37..b8d65d5120665 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -936,6 +936,7 @@ void __init_or_module apply_seal_endbr(s32 *start, s32 *end) { }
 #endif
 
 enum cfi_mode cfi_mode __ro_after_init = __CFI_DEFAULT;
+bool cfi_bhi __ro_after_init = false;
 
 #ifdef CONFIG_CFI_CLANG
 struct bpf_insn;
@@ -996,6 +997,21 @@ u32 cfi_get_func_hash(void *func)
 
 	return hash;
 }
+
+int cfi_get_func_arity(void *func)
+{
+	bhi_thunk *target;
+	s32 disp;
+
+	if (cfi_mode != CFI_FINEIBT && !cfi_bhi)
+		return 0;
+
+	if (get_kernel_nofault(disp, func - 4))
+		return 0;
+
+	target = func + disp;
+	return target - __bhi_args;
+}
 #endif
 
 #ifdef CONFIG_FINEIBT
@@ -1053,6 +1069,12 @@ static __init int cfi_parse_cmdline(char *str)
 			} else {
 				pr_err("Ignoring paranoid; depends on fineibt.\n");
 			}
+		} else if (!strcmp(str, "bhi")) {
+			if (cfi_mode == CFI_FINEIBT) {
+				cfi_bhi = true;
+			} else {
+				pr_err("Ignoring bhi; depends on fineibt.\n");
+			}
 		} else {
 			pr_err("Ignoring unknown cfi option (%s).", str);
 		}
@@ -1105,6 +1127,7 @@ asm(	".pushsection .rodata				\n"
 	"fineibt_preamble_start:			\n"
 	"	endbr64					\n"
 	"	subl	$0x12345678, %r10d		\n"
+	"fineibt_preamble_bhi:				\n"
 	"	jne	fineibt_preamble_start+6	\n"
 	ASM_NOP3
 	"fineibt_preamble_end:				\n"
@@ -1112,9 +1135,11 @@ asm(	".pushsection .rodata				\n"
 );
 
 extern u8 fineibt_preamble_start[];
+extern u8 fineibt_preamble_bhi[];
 extern u8 fineibt_preamble_end[];
 
 #define fineibt_preamble_size (fineibt_preamble_end - fineibt_preamble_start)
+#define fineibt_preamble_bhi  (fineibt_preamble_bhi - fineibt_preamble_start)
 #define fineibt_preamble_ud   6
 #define fineibt_preamble_hash 7
 
@@ -1187,13 +1212,16 @@ extern u8 fineibt_paranoid_end[];
 #define fineibt_paranoid_ind  (fineibt_paranoid_ind - fineibt_paranoid_start)
 #define fineibt_paranoid_ud   0xd
 
-static u32 decode_preamble_hash(void *addr)
+static u32 decode_preamble_hash(void *addr, int *reg)
 {
 	u8 *p = addr;
 
-	/* b8 78 56 34 12          mov    $0x12345678,%eax */
-	if (p[0] == 0xb8)
+	/* b8+reg 78 56 34 12          movl    $0x12345678,\reg */
+	if (p[0] >= 0xb8 && p[0] < 0xc0) {
+		if (reg)
+			*reg = p[0] - 0xb8;
 		return *(u32 *)(addr + 1);
+	}
 
 	return 0; /* invalid hash value */
 }
@@ -1202,11 +1230,11 @@ static u32 decode_caller_hash(void *addr)
 {
 	u8 *p = addr;
 
-	/* 41 ba 78 56 34 12       mov    $0x12345678,%r10d */
+	/* 41 ba 88 a9 cb ed       mov    $(-0x12345678),%r10d */
 	if (p[0] == 0x41 && p[1] == 0xba)
 		return -*(u32 *)(addr + 2);
 
-	/* e8 0c 78 56 34 12	   jmp.d8  +12 */
+	/* e8 0c 88 a9 cb ed	   jmp.d8  +12 */
 	if (p[0] == JMP8_INSN_OPCODE && p[1] == fineibt_caller_jmp)
 		return -*(u32 *)(addr + 2);
 
@@ -1271,7 +1299,7 @@ static int cfi_rand_preamble(s32 *start, s32 *end)
 		void *addr = (void *)s + *s;
 		u32 hash;
 
-		hash = decode_preamble_hash(addr);
+		hash = decode_preamble_hash(addr, NULL);
 		if (WARN(!hash, "no CFI hash found at: %pS %px %*ph\n",
 			 addr, addr, 5, addr))
 			return -EINVAL;
@@ -1289,6 +1317,7 @@ static int cfi_rewrite_preamble(s32 *start, s32 *end)
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
+		int arity;
 		u32 hash;
 
 		/*
@@ -1299,7 +1328,7 @@ static int cfi_rewrite_preamble(s32 *start, s32 *end)
 		if (!is_endbr(addr + 16))
 			continue;
 
-		hash = decode_preamble_hash(addr);
+		hash = decode_preamble_hash(addr, &arity);
 		if (WARN(!hash, "no CFI hash found at: %pS %px %*ph\n",
 			 addr, addr, 5, addr))
 			return -EINVAL;
@@ -1307,6 +1336,19 @@ static int cfi_rewrite_preamble(s32 *start, s32 *end)
 		text_poke_early(addr, fineibt_preamble_start, fineibt_preamble_size);
 		WARN_ON(*(u32 *)(addr + fineibt_preamble_hash) != 0x12345678);
 		text_poke_early(addr + fineibt_preamble_hash, &hash, 4);
+
+		WARN_ONCE(!IS_ENABLED(CONFIG_FINEIBT_BHI) && arity,
+			  "kCFI preamble has wrong register at: %pS %*ph\n",
+			  addr, 5, addr);
+
+		if (!cfi_bhi || !arity)
+			continue;
+
+		text_poke_early(addr + fineibt_preamble_bhi,
+				text_gen_insn(CALL_INSN_OPCODE,
+					      addr + fineibt_preamble_bhi,
+					      __bhi_args[arity]),
+				CALL_INSN_SIZE);
 	}
 
 	return 0;
@@ -1474,8 +1516,9 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 		cfi_rewrite_endbr(start_cfi, end_cfi);
 
 		if (builtin) {
-			pr_info("Using %sFineIBT CFI\n",
-				cfi_paranoid ? "paranoid " : "");
+			pr_info("Using %sFineIBT%s CFI\n",
+				cfi_paranoid ? "paranoid " : "",
+				cfi_bhi ? "+BHI" : "");
 		}
 		return;
 
@@ -1526,7 +1569,7 @@ static void poison_cfi(void *addr)
 		/*
 		 * kCFI prefix should start with a valid hash.
 		 */
-		if (!decode_preamble_hash(addr))
+		if (!decode_preamble_hash(addr, NULL))
 			break;
 
 		/*
@@ -1574,6 +1617,47 @@ static bool decode_fineibt_preamble(struct pt_regs *regs, unsigned long *target,
 	return false;
 }
 
+/*
+ * regs->ip points to one of the UD2 in __bhi_args[].
+ */
+static bool decode_fineibt_bhi(struct pt_regs *regs, unsigned long *target, u32 *type)
+{
+	unsigned long addr;
+	u32 hash;
+
+	if (!cfi_bhi)
+		return false;
+
+	if (regs->ip < (unsigned long)__bhi_args ||
+	    regs->ip >= (unsigned long)__bhi_args_end)
+		return false;
+
+	/*
+	 * Fetch the return address from the stack, this points to the
+	 * FineIBT preamble. Since the CALL instruction is in the 5 last
+	 * bytes of the preamble, the return address is in fact the target
+	 * address.
+	 */
+	__get_kernel_nofault(&addr, regs->sp, unsigned long, Efault);
+	*target = addr;
+
+	addr -= fineibt_preamble_size;
+	if (!exact_endbr((void *)addr))
+		return false;
+
+	__get_kernel_nofault(&hash, addr + fineibt_preamble_hash, u32, Efault);
+	*type = (u32)regs->r10 + hash;
+
+	/*
+	 * The UD2 sites are constructed with a RET immediately following,
+	 * as such the non-fatal case can use the regular fixup.
+	 */
+	return true;
+
+Efault:
+	return false;
+}
+
 /*
  * regs->ip points to a LOCK Jcc.d8 instruction from the fineibt_paranoid_start[]
  * sequence.
@@ -1605,6 +1689,9 @@ bool decode_fineibt_insn(struct pt_regs *regs, unsigned long *target, u32 *type)
 	if (decode_fineibt_paranoid(regs, target, type))
 		return true;
 
+	if (decode_fineibt_bhi(regs, target, type))
+		return true;
+
 	return decode_fineibt_preamble(regs, target, type);
 }
 
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index ce033e63bc27b..72776dcb75aa6 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -410,15 +410,20 @@ static void emit_nops(u8 **pprog, int len)
  * Emit the various CFI preambles, see asm/cfi.h and the comments about FineIBT
  * in arch/x86/kernel/alternative.c
  */
+static int emit_call(u8 **prog, void *func, void *ip);
 
-static void emit_fineibt(u8 **pprog, u32 hash)
+static void emit_fineibt(u8 **pprog, u8 *ip, u32 hash, int arity)
 {
 	u8 *prog = *pprog;
 
 	EMIT_ENDBR();
 	EMIT3_off32(0x41, 0x81, 0xea, hash);		/* subl $hash, %r10d	*/
-	EMIT2(0x75, 0xf9);				/* jne.d8 .-7		*/
-	EMIT3(0x0f, 0x1f, 0x00);			/* nop3			*/
+	if (cfi_bhi) {
+		emit_call(&prog, __bhi_args[arity], ip + 11);
+	} else {
+		EMIT2(0x75, 0xf9);			/* jne.d8 .-7		*/
+		EMIT3(0x0f, 0x1f, 0x00);		/* nop3			*/
+	}
 	EMIT_ENDBR_POISON();
 
 	*pprog = prog;
@@ -447,13 +452,13 @@ static void emit_kcfi(u8 **pprog, u32 hash)
 	*pprog = prog;
 }
 
-static void emit_cfi(u8 **pprog, u32 hash)
+static void emit_cfi(u8 **pprog, u8 *ip, u32 hash, int arity)
 {
 	u8 *prog = *pprog;
 
 	switch (cfi_mode) {
 	case CFI_FINEIBT:
-		emit_fineibt(&prog, hash);
+		emit_fineibt(&prog, ip, hash, arity);
 		break;
 
 	case CFI_KCFI:
@@ -504,13 +509,17 @@ static void emit_prologue_tail_call(u8 **pprog, bool is_subprog)
  * bpf_tail_call helper will skip the first X86_TAIL_CALL_OFFSET bytes
  * while jumping to another program
  */
-static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf,
+static void emit_prologue(u8 **pprog, u8 *ip, u32 stack_depth, bool ebpf_from_cbpf,
 			  bool tail_call_reachable, bool is_subprog,
 			  bool is_exception_cb)
 {
 	u8 *prog = *pprog;
 
-	emit_cfi(&prog, is_subprog ? cfi_bpf_subprog_hash : cfi_bpf_hash);
+	if (is_subprog) {
+		emit_cfi(&prog, ip, cfi_bpf_subprog_hash, 5);
+	} else {
+		emit_cfi(&prog, ip, cfi_bpf_hash, 1);
+	}
 	/* BPF trampoline can be made to work without these nops,
 	 * but let's waste 5 bytes for now and optimize later
 	 */
@@ -1479,7 +1488,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
 
 	detect_reg_usage(insn, insn_cnt, callee_regs_used);
 
-	emit_prologue(&prog, stack_depth,
+	emit_prologue(&prog, image, stack_depth,
 		      bpf_prog_was_classic(bpf_prog), tail_call_reachable,
 		      bpf_is_subprog(bpf_prog), bpf_prog->aux->exception_cb);
 	/* Exception callback will clobber callee regs for its own use, and
@@ -3046,7 +3055,9 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 		/*
 		 * Indirect call for bpf_struct_ops
 		 */
-		emit_cfi(&prog, cfi_get_func_hash(func_addr));
+		emit_cfi(&prog, image,
+			 cfi_get_func_hash(func_addr),
+			 cfi_get_func_arity(func_addr));
 	} else {
 		/*
 		 * Direct-call fentry stub, as such it needs accounting for the

From dfebe7362f6f461d771cdb9ac2c5172a4721f064 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 24 Feb 2025 13:37:13 +0100
Subject: [PATCH 0664/1173] x86/ibt: Optimize the fineibt-bhi arity 1 case

Saves a CALL to an out-of-line thunk for the common case of 1
argument.

Suggested-by: Scott Constable <scott.d.constable@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Kees Cook <kees@kernel.org>
Link: https://lore.kernel.org/r/20250224124200.927885784@infradead.org
---
 arch/x86/include/asm/ibt.h    |  4 +++
 arch/x86/kernel/alternative.c | 59 +++++++++++++++++++++++++++++------
 2 files changed, 54 insertions(+), 9 deletions(-)

diff --git a/arch/x86/include/asm/ibt.h b/arch/x86/include/asm/ibt.h
index f0ca5c0b1a6b2..9423a2967f506 100644
--- a/arch/x86/include/asm/ibt.h
+++ b/arch/x86/include/asm/ibt.h
@@ -70,6 +70,10 @@ static inline bool __is_endbr(u32 val)
 	if (val == gen_endbr_poison())
 		return true;
 
+	/* See cfi_fineibt_bhi_preamble() */
+	if (IS_ENABLED(CONFIG_FINEIBT_BHI) && val == 0x001f0ff5)
+		return true;
+
 	val &= ~0x01000000U; /* ENDBR32 -> ENDBR64 */
 	return val == gen_endbr();
 }
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index b8d65d5120665..32e4b801db991 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -1311,6 +1311,53 @@ static int cfi_rand_preamble(s32 *start, s32 *end)
 	return 0;
 }
 
+static void cfi_fineibt_bhi_preamble(void *addr, int arity)
+{
+	if (!arity)
+		return;
+
+	if (!cfi_warn && arity == 1) {
+		/*
+		 * Crazy scheme to allow arity-1 inline:
+		 *
+		 * __cfi_foo:
+		 *  0: f3 0f 1e fa             endbr64
+		 *  4: 41 81 <ea> 78 56 34 12  sub     0x12345678, %r10d
+		 *  b: 49 0f 45 fa             cmovne  %r10, %rdi
+		 *  f: 75 f5                   jne     __cfi_foo+6
+		 * 11: 0f 1f 00                nopl    (%rax)
+		 *
+		 * Code that direct calls to foo()+0, decodes the tail end as:
+		 *
+		 * foo:
+		 *  0: f5                      cmc
+		 *  1: 0f 1f 00                nopl    (%rax)
+		 *
+		 * which clobbers CF, but does not affect anything ABI
+		 * wise.
+		 *
+		 * Notably, this scheme is incompatible with permissive CFI
+		 * because the CMOVcc is unconditional and RDI will have been
+		 * clobbered.
+		 */
+		const u8 magic[9] = {
+			0x49, 0x0f, 0x45, 0xfa,
+			0x75, 0xf5,
+			BYTES_NOP3,
+		};
+
+		text_poke_early(addr + fineibt_preamble_bhi, magic, 9);
+
+		return;
+	}
+
+	text_poke_early(addr + fineibt_preamble_bhi,
+			text_gen_insn(CALL_INSN_OPCODE,
+				      addr + fineibt_preamble_bhi,
+				      __bhi_args[arity]),
+			CALL_INSN_SIZE);
+}
+
 static int cfi_rewrite_preamble(s32 *start, s32 *end)
 {
 	s32 *s;
@@ -1341,14 +1388,8 @@ static int cfi_rewrite_preamble(s32 *start, s32 *end)
 			  "kCFI preamble has wrong register at: %pS %*ph\n",
 			  addr, 5, addr);
 
-		if (!cfi_bhi || !arity)
-			continue;
-
-		text_poke_early(addr + fineibt_preamble_bhi,
-				text_gen_insn(CALL_INSN_OPCODE,
-					      addr + fineibt_preamble_bhi,
-					      __bhi_args[arity]),
-				CALL_INSN_SIZE);
+		if (cfi_bhi)
+			cfi_fineibt_bhi_preamble(addr, arity);
 	}
 
 	return 0;
@@ -1361,7 +1402,7 @@ static void cfi_rewrite_endbr(s32 *start, s32 *end)
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
 
-		if (!is_endbr(addr + 16))
+		if (!exact_endbr(addr + 16))
 			continue;
 
 		poison_endbr(addr + 16);

From 2ec01bd7152f80795eab7b48706aa5db8d4a286a Mon Sep 17 00:00:00 2001
From: Benjamin Berg <benjamin.berg@intel.com>
Date: Tue, 17 Dec 2024 21:27:43 +0100
Subject: [PATCH 0665/1173] vmlinux.lds.h: Remove entry to place init_task onto
 init_stack

Since commit 0eb5085c3874 ("arch: remove ARCH_TASK_STRUCT_ON_STACK")
there is no option that would allow placing task_struct on the stack.
Remove the unused linker script entry.

Signed-off-by: Benjamin Berg <benjamin.berg@intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20241217202745.1402932-2-benjamin@sipsolutions.net
---
 include/asm-generic/vmlinux.lds.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 02a4adb4a9999..a1b04694a2cdf 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -404,7 +404,6 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
 	__start_init_stack = .;						\
 	init_thread_union = .;						\
 	init_stack = .;							\
-	KEEP(*(.data..init_task))					\
 	KEEP(*(.data..init_thread_info))				\
 	. = __start_init_stack + THREAD_SIZE;				\
 	__end_init_stack = .;

From f2ba0cf1ca32e075617813de98c826ab55d57f11 Mon Sep 17 00:00:00 2001
From: Mingcong Bai <jeffbai@aosc.io>
Date: Tue, 25 Feb 2025 15:31:01 +0800
Subject: [PATCH 0666/1173] drm/xe/regs: remove a duplicate definition for
 RING_CTL_SIZE(size)

Commit b79e8fd954c4 ("drm/xe: Remove dependency on intel_engine_regs.h")
introduced an internal set of engine registers, however, as part of this
change, it has also introduced two duplicate `define' lines for
`RING_CTL_SIZE(size)'. This commit was introduced to the tree in v6.8-rc1.

While this is harmless as the definitions did not change, so no compiler
warning was observed.

Drop this line anyway for the sake of correctness.

Cc: stable@vger.kernel.org # v6.8-rc1+
Fixes: b79e8fd954c4 ("drm/xe: Remove dependency on intel_engine_regs.h")
Signed-off-by: Mingcong Bai <jeffbai@aosc.io>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250225073104.865230-1-jeffbai@aosc.io
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
(cherry picked from commit 6b68c4542ffecc36087a9e14db8fc990c88bb01b)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/regs/xe_engine_regs.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/regs/xe_engine_regs.h b/drivers/gpu/drm/xe/regs/xe_engine_regs.h
index d86219dedde2a..b732c89816dff 100644
--- a/drivers/gpu/drm/xe/regs/xe_engine_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_engine_regs.h
@@ -53,7 +53,6 @@
 
 #define RING_CTL(base)				XE_REG((base) + 0x3c)
 #define   RING_CTL_SIZE(size)			((size) - PAGE_SIZE) /* in bytes -> pages */
-#define   RING_CTL_SIZE(size)			((size) - PAGE_SIZE) /* in bytes -> pages */
 
 #define RING_START_UDW(base)			XE_REG((base) + 0x48)
 

From 12c2f962fe71f390951d9242725bc7e608f55927 Mon Sep 17 00:00:00 2001
From: Tejas Upadhyay <tejas.upadhyay@intel.com>
Date: Tue, 25 Feb 2025 10:27:54 +0530
Subject: [PATCH 0667/1173] drm/xe: cancel pending job timer before freeing
 scheduler

The async call to __guc_exec_queue_fini_async frees the scheduler
while a submission may time out and restart. To prevent this race
condition, the pending job timer should be canceled before freeing
the scheduler.

V3(MattB):
 - Adjust position of cancel pending job
 - Remove gitlab issue# from commit message
V2(MattB):
 - Cancel pending jobs before scheduler finish

Fixes: a20c75dba192 ("drm/xe: Call __guc_exec_queue_fini_async direct for KERNEL exec_queues")
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250225045754.600905-1-tejas.upadhyay@intel.com
Signed-off-by: Tejas Upadhyay <tejas.upadhyay@intel.com>
(cherry picked from commit 18fbd567e75f9b97b699b2ab4f1fa76b7cf268f6)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_guc_submit.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 913c74d6e2aeb..b6a2dd742ebdc 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1248,6 +1248,8 @@ static void __guc_exec_queue_fini_async(struct work_struct *w)
 
 	if (xe_exec_queue_is_lr(q))
 		cancel_work_sync(&ge->lr_tdr);
+	/* Confirm no work left behind accessing device structures */
+	cancel_delayed_work_sync(&ge->sched.base.work_tdr);
 	release_guc_id(guc, q);
 	xe_sched_entity_fini(&ge->entity);
 	xe_sched_fini(&ge->sched);

From 16fef33fdb1e2269c20697d9b61ae8022bc92665 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Mon, 24 Feb 2025 11:32:42 +0200
Subject: [PATCH 0668/1173] drm/i915/dp_mst: Fix encoder HW state readout for
 UHBR MST

The encoder HW/SW state verification should use a SW state which stays
unchanged while the encoder/output is active. The intel_dp::is_mst flag
used during state computation to choose between the DP SST/MST modes can
change while the output is active, if the sink gets disconnected or the
MST topology is removed for another reason. A subsequent state
verification using intel_dp::is_mst leads then to a mismatch if the
output is disabled/re-enabled without recomputing its state.

Use the encoder's active MST link count instead, which will be always
non-zero for an active MST output and will be zero for SST.

Fixes: 35d2e4b75649 ("drm/i915/ddi: start distinguishing 128b/132b SST and MST at state readout")
Fixes: 40d489fac0e8 ("drm/i915/ddi: handle 128b/132b SST in intel_ddi_read_func_ctl()")
Cc: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250224093242.1859583-1-imre.deak@intel.com
(cherry picked from commit 0159e311772af9d6598aafe072c020687720f1d7)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/display/intel_ddi.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 18c66992aa1d8..ff2cf3daa7a2b 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -866,7 +866,7 @@ static void intel_ddi_get_encoder_pipes(struct intel_encoder *encoder,
 			    encoder->base.base.id, encoder->base.name);
 
 	if (!mst_pipe_mask && dp128b132b_pipe_mask) {
-		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+		struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
 
 		/*
 		 * If we don't have 8b/10b MST, but have more than one
@@ -878,7 +878,8 @@ static void intel_ddi_get_encoder_pipes(struct intel_encoder *encoder,
 		 * we don't expect MST to have been enabled at that point, and
 		 * can assume it's SST.
 		 */
-		if (hweight8(dp128b132b_pipe_mask) > 1 || intel_dp->is_mst)
+		if (hweight8(dp128b132b_pipe_mask) > 1 ||
+		    intel_dp_mst_encoder_active_links(dig_port))
 			mst_pipe_mask = dp128b132b_pipe_mask;
 	}
 
@@ -4151,13 +4152,13 @@ static void intel_ddi_read_func_ctl(struct intel_encoder *encoder,
 	} else if (ddi_mode == TRANS_DDI_MODE_SELECT_DP_MST) {
 		intel_ddi_read_func_ctl_dp_mst(encoder, pipe_config, ddi_func_ctl);
 	} else if (ddi_mode == TRANS_DDI_MODE_SELECT_FDI_OR_128B132B && HAS_DP20(display)) {
-		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+		struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
 
 		/*
 		 * If this is true, we know we're being called from mst stream
 		 * encoder's ->get_config().
 		 */
-		if (intel_dp->is_mst)
+		if (intel_dp_mst_encoder_active_links(dig_port))
 			intel_ddi_read_func_ctl_dp_mst(encoder, pipe_config, ddi_func_ctl);
 		else
 			intel_ddi_read_func_ctl_dp_sst(encoder, pipe_config, ddi_func_ctl);

From c6557ccf8094ce2e1142c6e49cd47f5d5e2933a8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Adrien=20Verg=C3=A9?= <adrienverge@gmail.com>
Date: Wed, 26 Feb 2025 14:55:15 +0100
Subject: [PATCH 0669/1173] ALSA: hda/realtek: Fix microphone regression on
 ASUS N705UD
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This fixes a regression introduced a few weeks ago in stable kernels
6.12.14 and 6.13.3. The internal microphone on ASUS Vivobook N705UD /
X705UD laptops is broken: the microphone appears in userspace (e.g.
Gnome settings) but no sound is detected.
I bisected it to commit 3b4309546b48 ("ALSA: hda: Fix headset detection
failure due to unstable sort").

I figured out the cause:
1. The initial pins enabled for the ALC256 driver are:
       cfg->inputs == {
         { pin=0x19, type=AUTO_PIN_MIC,
           is_headset_mic=1, is_headphone_mic=0, has_boost_on_pin=1 },
         { pin=0x1a, type=AUTO_PIN_MIC,
           is_headset_mic=0, is_headphone_mic=0, has_boost_on_pin=1 } }
2. Since 2017 and commits c1732ede5e8 ("ALSA: hda/realtek - Fix headset
   and mic on several ASUS laptops with ALC256") and 28e8af8a163 ("ALSA:
   hda/realtek: Fix mic and headset jack sense on ASUS X705UD"), the
   quirk ALC256_FIXUP_ASUS_MIC is also applied to ASUS X705UD / N705UD
   laptops.
   This added another internal microphone on pin 0x13:
       cfg->inputs == {
         { pin=0x13, type=AUTO_PIN_MIC,
           is_headset_mic=0, is_headphone_mic=0, has_boost_on_pin=1 },
         { pin=0x19, type=AUTO_PIN_MIC,
           is_headset_mic=1, is_headphone_mic=0, has_boost_on_pin=1 },
         { pin=0x1a, type=AUTO_PIN_MIC,
           is_headset_mic=0, is_headphone_mic=0, has_boost_on_pin=1 } }
   I don't know what this pin 0x13 corresponds to. To the best of my
   knowledge, these laptops have only one internal microphone.
3. Before 2025 and commit 3b4309546b48 ("ALSA: hda: Fix headset
   detection failure due to unstable sort"), the sort function would let
   the microphone of pin 0x1a (the working one) *before* the microphone
   of pin 0x13 (the phantom one).
4. After this commit 3b4309546b48, the fixed sort function puts the
   working microphone (pin 0x1a) *after* the phantom one (pin 0x13). As
   a result, no sound is detected anymore.

It looks like the quirk ALC256_FIXUP_ASUS_MIC is not needed anymore for
ASUS Vivobook X705UD / N705UD laptops. Without it, everything works
fine:
- the internal microphone is detected and records actual sound,
- plugging in a jack headset is detected and can record actual sound
  with it,
- unplugging the jack headset makes the system go back to internal
  microphone and can record actual sound.

Cc: stable@vger.kernel.org
Cc: Kuan-Wei Chiu <visitorckw@gmail.com>
Cc: Chris Chiu <chris.chiu@canonical.com>
Fixes: 3b4309546b48 ("ALSA: hda: Fix headset detection failure due to unstable sort")
Tested-by: Adrien Vergé <adrienverge@gmail.com>
Signed-off-by: Adrien Vergé <adrienverge@gmail.com>
Link: https://patch.msgid.link/20250226135515.24219-1-adrienverge@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index e5c80d4be535c..c735f630ecb5a 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10657,7 +10657,6 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x19ce, "ASUS B9450FA", ALC294_FIXUP_ASUS_HPE),
 	SND_PCI_QUIRK(0x1043, 0x19e1, "ASUS UX581LV", ALC295_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x1a13, "Asus G73Jw", ALC269_FIXUP_ASUS_G73JW),
-	SND_PCI_QUIRK(0x1043, 0x1a30, "ASUS X705UD", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1a63, "ASUS UX3405MA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1a83, "ASUS UM5302LA", ALC294_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x1a8f, "ASUS UX582ZS", ALC245_FIXUP_CS35L41_SPI_2),

From 99ca2c28e6b68084a0fb65585df09b9e28c3ec16 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 21 Feb 2025 11:24:50 +0100
Subject: [PATCH 0670/1173] wifi: mac80211: fix MLE non-inheritance parsing

The code is erroneously applying the non-inheritance element
to the inner elements rather than the outer, which is clearly
completely wrong. Fix it by finding the MLE basic element at
the beginning, and then applying the non-inheritance for the
outer parsing.

While at it, do some general cleanups such as not allowing
callers to try looking for a specific non-transmitted BSS
and link at the same time.

Fixes: 45ebac4f059b ("wifi: mac80211: Parse station profile from association response")
Reviewed-by: Ilan Peer <ilan.peer@intel.com>
Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250221112451.b46d42f45b66.If5b95dc3c80208e0c62d8895fb6152aa54b6620b@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c  |   1 +
 net/mac80211/parse.c | 127 ++++++++++++++++++++++++++++---------------
 2 files changed, 83 insertions(+), 45 deletions(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index f8d52b3b0d0e4..36a9be9a66c8e 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -4959,6 +4959,7 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link,
 		parse_params.start = bss_ies->data;
 		parse_params.len = bss_ies->len;
 		parse_params.bss = cbss;
+		parse_params.link_id = -1;
 		bss_elems = ieee802_11_parse_elems_full(&parse_params);
 		if (!bss_elems) {
 			ret = false;
diff --git a/net/mac80211/parse.c b/net/mac80211/parse.c
index cd318c1c67bec..3d5d6658fe8d5 100644
--- a/net/mac80211/parse.c
+++ b/net/mac80211/parse.c
@@ -47,6 +47,8 @@ struct ieee80211_elems_parse {
 	/* The EPCS Multi-Link element in the original elements */
 	const struct element *ml_epcs_elem;
 
+	bool multi_link_inner;
+
 	/*
 	 * scratch buffer that can be used for various element parsing related
 	 * tasks, e.g., element de-fragmentation etc.
@@ -152,12 +154,11 @@ ieee80211_parse_extension_element(u32 *crc,
 			switch (le16_get_bits(mle->control,
 					      IEEE80211_ML_CONTROL_TYPE)) {
 			case IEEE80211_ML_CONTROL_TYPE_BASIC:
-				if (elems_parse->ml_basic_elem) {
+				if (elems_parse->multi_link_inner) {
 					elems->parse_error |=
 						IEEE80211_PARSE_ERR_DUP_NEST_ML_BASIC;
 					break;
 				}
-				elems_parse->ml_basic_elem = elem;
 				break;
 			case IEEE80211_ML_CONTROL_TYPE_RECONF:
 				elems_parse->ml_reconf_elem = elem;
@@ -866,21 +867,36 @@ ieee80211_mle_get_sta_prof(struct ieee80211_elems_parse *elems_parse,
 	}
 }
 
-static void ieee80211_mle_parse_link(struct ieee80211_elems_parse *elems_parse,
-				     struct ieee80211_elems_parse_params *params)
+static const struct element *
+ieee80211_prep_mle_link_parse(struct ieee80211_elems_parse *elems_parse,
+			      struct ieee80211_elems_parse_params *params,
+			      struct ieee80211_elems_parse_params *sub)
 {
 	struct ieee802_11_elems *elems = &elems_parse->elems;
 	struct ieee80211_mle_per_sta_profile *prof;
-	struct ieee80211_elems_parse_params sub = {
-		.mode = params->mode,
-		.action = params->action,
-		.from_ap = params->from_ap,
-		.link_id = -1,
-	};
-	ssize_t ml_len = elems->ml_basic_len;
-	const struct element *non_inherit = NULL;
+	const struct element *tmp;
+	ssize_t ml_len;
 	const u8 *end;
 
+	if (params->mode < IEEE80211_CONN_MODE_EHT)
+		return NULL;
+
+	for_each_element_extid(tmp, WLAN_EID_EXT_EHT_MULTI_LINK,
+			       elems->ie_start, elems->total_len) {
+		const struct ieee80211_multi_link_elem *mle =
+			(void *)tmp->data + 1;
+
+		if (!ieee80211_mle_size_ok(tmp->data + 1, tmp->datalen - 1))
+			continue;
+
+		if (le16_get_bits(mle->control, IEEE80211_ML_CONTROL_TYPE) !=
+		    IEEE80211_ML_CONTROL_TYPE_BASIC)
+			continue;
+
+		elems_parse->ml_basic_elem = tmp;
+		break;
+	}
+
 	ml_len = cfg80211_defragment_element(elems_parse->ml_basic_elem,
 					     elems->ie_start,
 					     elems->total_len,
@@ -891,26 +907,26 @@ static void ieee80211_mle_parse_link(struct ieee80211_elems_parse *elems_parse,
 					     WLAN_EID_FRAGMENT);
 
 	if (ml_len < 0)
-		return;
+		return NULL;
 
 	elems->ml_basic = (const void *)elems_parse->scratch_pos;
 	elems->ml_basic_len = ml_len;
 	elems_parse->scratch_pos += ml_len;
 
 	if (params->link_id == -1)
-		return;
+		return NULL;
 
 	ieee80211_mle_get_sta_prof(elems_parse, params->link_id);
 	prof = elems->prof;
 
 	if (!prof)
-		return;
+		return NULL;
 
 	/* check if we have the 4 bytes for the fixed part in assoc response */
 	if (elems->sta_prof_len < sizeof(*prof) + prof->sta_info_len - 1 + 4) {
 		elems->prof = NULL;
 		elems->sta_prof_len = 0;
-		return;
+		return NULL;
 	}
 
 	/*
@@ -919,13 +935,17 @@ static void ieee80211_mle_parse_link(struct ieee80211_elems_parse *elems_parse,
 	 * the -1 is because the 'sta_info_len' is accounted to as part of the
 	 * per-STA profile, but not part of the 'u8 variable[]' portion.
 	 */
-	sub.start = prof->variable + prof->sta_info_len - 1 + 4;
+	sub->start = prof->variable + prof->sta_info_len - 1 + 4;
 	end = (const u8 *)prof + elems->sta_prof_len;
-	sub.len = end - sub.start;
+	sub->len = end - sub->start;
 
-	non_inherit = cfg80211_find_ext_elem(WLAN_EID_EXT_NON_INHERITANCE,
-					     sub.start, sub.len);
-	_ieee802_11_parse_elems_full(&sub, elems_parse, non_inherit);
+	sub->mode = params->mode;
+	sub->action = params->action;
+	sub->from_ap = params->from_ap;
+	sub->link_id = -1;
+
+	return cfg80211_find_ext_elem(WLAN_EID_EXT_NON_INHERITANCE,
+				      sub->start, sub->len);
 }
 
 static void
@@ -973,15 +993,19 @@ ieee80211_mle_defrag_epcs(struct ieee80211_elems_parse *elems_parse)
 struct ieee802_11_elems *
 ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params)
 {
+	struct ieee80211_elems_parse_params sub = {};
 	struct ieee80211_elems_parse *elems_parse;
-	struct ieee802_11_elems *elems;
 	const struct element *non_inherit = NULL;
-	u8 *nontransmitted_profile;
-	int nontransmitted_profile_len = 0;
+	struct ieee802_11_elems *elems;
 	size_t scratch_len = 3 * params->len;
+	bool multi_link_inner = false;
 
 	BUILD_BUG_ON(offsetof(typeof(*elems_parse), elems) != 0);
 
+	/* cannot parse for both a specific link and non-transmitted BSS */
+	if (WARN_ON(params->link_id >= 0 && params->bss))
+		return NULL;
+
 	elems_parse = kzalloc(struct_size(elems_parse, scratch, scratch_len),
 			      GFP_ATOMIC);
 	if (!elems_parse)
@@ -998,34 +1022,47 @@ ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params)
 	ieee80211_clear_tpe(&elems->tpe);
 	ieee80211_clear_tpe(&elems->csa_tpe);
 
-	nontransmitted_profile = elems_parse->scratch_pos;
-	nontransmitted_profile_len =
-		ieee802_11_find_bssid_profile(params->start, params->len,
-					      elems, params->bss,
-					      nontransmitted_profile);
-	elems_parse->scratch_pos += nontransmitted_profile_len;
-	non_inherit = cfg80211_find_ext_elem(WLAN_EID_EXT_NON_INHERITANCE,
-					     nontransmitted_profile,
-					     nontransmitted_profile_len);
+	/*
+	 * If we're looking for a non-transmitted BSS then we cannot at
+	 * the same time be looking for a second link as the two can only
+	 * appear in the same frame carrying info for different BSSes.
+	 *
+	 * In any case, we only look for one at a time, as encoded by
+	 * the WARN_ON above.
+	 */
+	if (params->bss) {
+		int nontx_len =
+			ieee802_11_find_bssid_profile(params->start,
+						      params->len,
+						      elems, params->bss,
+						      elems_parse->scratch_pos);
+		sub.start = elems_parse->scratch_pos;
+		sub.mode = params->mode;
+		sub.len = nontx_len;
+		sub.action = params->action;
+		sub.link_id = params->link_id;
+
+		/* consume the space used for non-transmitted profile */
+		elems_parse->scratch_pos += nontx_len;
+
+		non_inherit = cfg80211_find_ext_elem(WLAN_EID_EXT_NON_INHERITANCE,
+						     sub.start, nontx_len);
+	} else {
+		/* must always parse to get elems_parse->ml_basic_elem */
+		non_inherit = ieee80211_prep_mle_link_parse(elems_parse, params,
+							    &sub);
+		multi_link_inner = true;
+	}
 
 	elems->crc = _ieee802_11_parse_elems_full(params, elems_parse,
 						  non_inherit);
 
-	/* Override with nontransmitted profile, if found */
-	if (nontransmitted_profile_len) {
-		struct ieee80211_elems_parse_params sub = {
-			.mode = params->mode,
-			.start = nontransmitted_profile,
-			.len = nontransmitted_profile_len,
-			.action = params->action,
-			.link_id = params->link_id,
-		};
-
+	/* Override with nontransmitted/per-STA profile if found */
+	if (sub.len) {
+		elems_parse->multi_link_inner = multi_link_inner;
 		_ieee802_11_parse_elems_full(&sub, elems_parse, NULL);
 	}
 
-	ieee80211_mle_parse_link(elems_parse, params);
-
 	ieee80211_mle_defrag_reconf(elems_parse);
 
 	ieee80211_mle_defrag_epcs(elems_parse);

From 130067e9c13bdc4820748ef16076a6972364745f Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 21 Feb 2025 11:24:51 +0100
Subject: [PATCH 0671/1173] wifi: mac80211: fix vendor-specific inheritance

If there's any vendor-specific element in the subelements
then the outer element parsing must not parse any vendor
element at all. This isn't implemented correctly now due
to parsing into the pointers and then overriding them, so
explicitly skip vendor elements if any exist in the sub-
elements (non-transmitted profile or per-STA profile).

Fixes: 671042a4fb77 ("mac80211: support non-inheritance element")
Reviewed-by: Ilan Peer <ilan.peer@intel.com>
Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250221112451.fd71e5268840.I9db3e6a3367e6ff38d052d07dc07005f0dd3bd5c@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/parse.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/net/mac80211/parse.c b/net/mac80211/parse.c
index 3d5d6658fe8d5..6da39c864f45b 100644
--- a/net/mac80211/parse.c
+++ b/net/mac80211/parse.c
@@ -48,6 +48,7 @@ struct ieee80211_elems_parse {
 	const struct element *ml_epcs_elem;
 
 	bool multi_link_inner;
+	bool skip_vendor;
 
 	/*
 	 * scratch buffer that can be used for various element parsing related
@@ -400,6 +401,9 @@ _ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params,
 					IEEE80211_PARSE_ERR_BAD_ELEM_SIZE;
 			break;
 		case WLAN_EID_VENDOR_SPECIFIC:
+			if (elems_parse->skip_vendor)
+				break;
+
 			if (elen >= 4 && pos[0] == 0x00 && pos[1] == 0x50 &&
 			    pos[2] == 0xf2) {
 				/* Microsoft OUI (00:50:F2) */
@@ -1054,12 +1058,16 @@ ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params)
 		multi_link_inner = true;
 	}
 
+	elems_parse->skip_vendor =
+		cfg80211_find_elem(WLAN_EID_VENDOR_SPECIFIC,
+				   sub.start, sub.len);
 	elems->crc = _ieee802_11_parse_elems_full(params, elems_parse,
 						  non_inherit);
 
 	/* Override with nontransmitted/per-STA profile if found */
 	if (sub.len) {
 		elems_parse->multi_link_inner = multi_link_inner;
+		elems_parse->skip_vendor = false;
 		_ieee802_11_parse_elems_full(&sub, elems_parse, NULL);
 	}
 

From 861d0445e72e9e33797f2ceef882c74decb16a87 Mon Sep 17 00:00:00 2001
From: Alexander Wetzel <Alexander@wetzel-home.de>
Date: Thu, 13 Feb 2025 22:43:30 +0100
Subject: [PATCH 0672/1173] wifi: mac80211: Fix sparse warning for
 monitor_sdata

Use rcu_access_pointer() to avoid sparse warning in
drv_remove_interface().

Signed-off-by: Alexander Wetzel <Alexander@wetzel-home.de>
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202502130534.bVrZZBK0-lkp@intel.com/
Fixes: 646262c71aca ("wifi: mac80211: remove debugfs dir for virtual monitor")
Link: https://patch.msgid.link/20250213214330.6113-1-Alexander@wetzel-home.de
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/driver-ops.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c
index 2fc60e1e77a55..35349a7f16cb4 100644
--- a/net/mac80211/driver-ops.c
+++ b/net/mac80211/driver-ops.c
@@ -121,7 +121,7 @@ void drv_remove_interface(struct ieee80211_local *local,
 	 * The virtual monitor interface doesn't get a debugfs
 	 * entry, so it's exempt here.
 	 */
-	if (sdata != local->monitor_sdata)
+	if (sdata != rcu_access_pointer(local->monitor_sdata))
 		ieee80211_debugfs_recreate_netdev(sdata,
 						  sdata->vif.valid_links);
 

From 8c3170628a9ce24a59647bd24f897e666af919b8 Mon Sep 17 00:00:00 2001
From: Matthias Proske <email@matthias-proske.de>
Date: Wed, 12 Feb 2025 19:59:35 +0100
Subject: [PATCH 0673/1173] wifi: brcmfmac: keep power during suspend if board
 requires it

After commit 92cadedd9d5f ("brcmfmac: Avoid keeping power to SDIO card
unless WOWL is used"), the wifi adapter by default is turned off on
suspend and then re-probed on resume.

This conflicts with some embedded boards that require to remain powered.
They will fail on resume with:

brcmfmac: brcmf_sdio_bus_rxctl: resumed on timeout
ieee80211 phy1: brcmf_bus_started: failed: -110
ieee80211 phy1: brcmf_attach: dongle is not responding: err=-110
brcmfmac: brcmf_sdio_firmware_callback: brcmf_attach failed

This commit checks for the Device Tree property 'cap-power-off-cards'.
If this property is not set, it means that we do not have the capability
to power off and should therefore remain powered.

Signed-off-by: Matthias Proske <email@matthias-proske.de>
Acked-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Link: https://patch.msgid.link/20250212185941.146958-2-email@matthias-proske.de
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../broadcom/brcm80211/brcmfmac/bcmsdh.c      | 20 ++++++++++++-------
 1 file changed, 13 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
index 60eb95fc19a5a..6bc107476a2a3 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
@@ -1172,6 +1172,7 @@ static int brcmf_ops_sdio_suspend(struct device *dev)
 	struct brcmf_bus *bus_if;
 	struct brcmf_sdio_dev *sdiodev;
 	mmc_pm_flag_t sdio_flags;
+	bool cap_power_off;
 	int ret = 0;
 
 	func = container_of(dev, struct sdio_func, dev);
@@ -1179,19 +1180,23 @@ static int brcmf_ops_sdio_suspend(struct device *dev)
 	if (func->num != 1)
 		return 0;
 
+	cap_power_off = !!(func->card->host->caps & MMC_CAP_POWER_OFF_CARD);
 
 	bus_if = dev_get_drvdata(dev);
 	sdiodev = bus_if->bus_priv.sdio;
 
-	if (sdiodev->wowl_enabled) {
+	if (sdiodev->wowl_enabled || !cap_power_off) {
 		brcmf_sdiod_freezer_on(sdiodev);
 		brcmf_sdio_wd_timer(sdiodev->bus, 0);
 
 		sdio_flags = MMC_PM_KEEP_POWER;
-		if (sdiodev->settings->bus.sdio.oob_irq_supported)
-			enable_irq_wake(sdiodev->settings->bus.sdio.oob_irq_nr);
-		else
-			sdio_flags |= MMC_PM_WAKE_SDIO_IRQ;
+
+		if (sdiodev->wowl_enabled) {
+			if (sdiodev->settings->bus.sdio.oob_irq_supported)
+				enable_irq_wake(sdiodev->settings->bus.sdio.oob_irq_nr);
+			else
+				sdio_flags |= MMC_PM_WAKE_SDIO_IRQ;
+		}
 
 		if (sdio_set_host_pm_flags(sdiodev->func1, sdio_flags))
 			brcmf_err("Failed to set pm_flags %x\n", sdio_flags);
@@ -1213,18 +1218,19 @@ static int brcmf_ops_sdio_resume(struct device *dev)
 	struct brcmf_sdio_dev *sdiodev = bus_if->bus_priv.sdio;
 	struct sdio_func *func = container_of(dev, struct sdio_func, dev);
 	int ret = 0;
+	bool cap_power_off = !!(func->card->host->caps & MMC_CAP_POWER_OFF_CARD);
 
 	brcmf_dbg(SDIO, "Enter: F%d\n", func->num);
 	if (func->num != 2)
 		return 0;
 
-	if (!sdiodev->wowl_enabled) {
+	if (!sdiodev->wowl_enabled && cap_power_off) {
 		/* bus was powered off and device removed, probe again */
 		ret = brcmf_sdiod_probe(sdiodev);
 		if (ret)
 			brcmf_err("Failed to probe device on resume\n");
 	} else {
-		if (sdiodev->settings->bus.sdio.oob_irq_supported)
+		if (sdiodev->wowl_enabled && sdiodev->settings->bus.sdio.oob_irq_supported)
 			disable_irq_wake(sdiodev->settings->bus.sdio.oob_irq_nr);
 
 		brcmf_sdiod_freezer_off(sdiodev);

From 8442df2b49ed9bcd67833ad4f091d15ac91efd00 Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@alien8.de>
Date: Tue, 18 Feb 2025 12:13:33 +0100
Subject: [PATCH 0674/1173] x86/bugs: KVM: Add support for SRSO_MSR_FIX

Add support for

  CPUID Fn8000_0021_EAX[31] (SRSO_MSR_FIX). If this bit is 1, it
  indicates that software may use MSR BP_CFG[BpSpecReduce] to mitigate
  SRSO.

Enable BpSpecReduce to mitigate SRSO across guest/host boundaries.

Switch back to enabling the bit when virtualization is enabled and to
clear the bit when virtualization is disabled because using a MSR slot
would clear the bit when the guest is exited and any training the guest
has done, would potentially influence the host kernel when execution
enters the kernel and hasn't VMRUN the guest yet.

More detail on the public thread in Link below.

Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20241202120416.6054-1-bp@kernel.org
---
 Documentation/admin-guide/hw-vuln/srso.rst | 13 ++++++++++++
 arch/x86/include/asm/cpufeatures.h         |  4 ++++
 arch/x86/include/asm/msr-index.h           |  1 +
 arch/x86/kernel/cpu/bugs.c                 | 24 ++++++++++++++++++----
 arch/x86/kvm/svm/svm.c                     |  6 ++++++
 arch/x86/lib/msr.c                         |  2 ++
 6 files changed, 46 insertions(+), 4 deletions(-)

diff --git a/Documentation/admin-guide/hw-vuln/srso.rst b/Documentation/admin-guide/hw-vuln/srso.rst
index 2ad1c05b8c883..66af95251a3d1 100644
--- a/Documentation/admin-guide/hw-vuln/srso.rst
+++ b/Documentation/admin-guide/hw-vuln/srso.rst
@@ -104,7 +104,20 @@ The possible values in this file are:
 
    (spec_rstack_overflow=ibpb-vmexit)
 
+ * 'Mitigation: Reduced Speculation':
 
+   This mitigation gets automatically enabled when the above one "IBPB on
+   VMEXIT" has been selected and the CPU supports the BpSpecReduce bit.
+
+   It gets automatically enabled on machines which have the
+   SRSO_USER_KERNEL_NO=1 CPUID bit. In that case, the code logic is to switch
+   to the above =ibpb-vmexit mitigation because the user/kernel boundary is
+   not affected anymore and thus "safe RET" is not needed.
+
+   After enabling the IBPB on VMEXIT mitigation option, the BpSpecReduce bit
+   is detected (functionality present on all such machines) and that
+   practically overrides IBPB on VMEXIT as it has a lot less performance
+   impact and takes care of the guest->host attack vector too.
 
 In order to exploit vulnerability, an attacker needs to:
 
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 508c0dad116bc..43653f2704c93 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -468,6 +468,10 @@
 #define X86_FEATURE_IBPB_BRTYPE		(20*32+28) /* MSR_PRED_CMD[IBPB] flushes all branch type predictions */
 #define X86_FEATURE_SRSO_NO		(20*32+29) /* CPU is not affected by SRSO */
 #define X86_FEATURE_SRSO_USER_KERNEL_NO	(20*32+30) /* CPU is not affected by SRSO across user/kernel boundaries */
+#define X86_FEATURE_SRSO_BP_SPEC_REDUCE	(20*32+31) /*
+						    * BP_CFG[BpSpecReduce] can be used to mitigate SRSO for VMs.
+						    * (SRSO_MSR_FIX in the official doc).
+						    */
 
 /*
  * Extended auxiliary flags: Linux defined - for features scattered in various
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 72765b2fe0d87..d35519b337ba2 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -721,6 +721,7 @@
 
 /* Zen4 */
 #define MSR_ZEN4_BP_CFG                 0xc001102e
+#define MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT 4
 #define MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT 5
 
 /* Fam 19h MSRs */
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index a5d0998d76049..1d7afc40f2272 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -2522,6 +2522,7 @@ enum srso_mitigation {
 	SRSO_MITIGATION_SAFE_RET,
 	SRSO_MITIGATION_IBPB,
 	SRSO_MITIGATION_IBPB_ON_VMEXIT,
+	SRSO_MITIGATION_BP_SPEC_REDUCE,
 };
 
 enum srso_mitigation_cmd {
@@ -2539,7 +2540,8 @@ static const char * const srso_strings[] = {
 	[SRSO_MITIGATION_MICROCODE]		= "Vulnerable: Microcode, no safe RET",
 	[SRSO_MITIGATION_SAFE_RET]		= "Mitigation: Safe RET",
 	[SRSO_MITIGATION_IBPB]			= "Mitigation: IBPB",
-	[SRSO_MITIGATION_IBPB_ON_VMEXIT]	= "Mitigation: IBPB on VMEXIT only"
+	[SRSO_MITIGATION_IBPB_ON_VMEXIT]	= "Mitigation: IBPB on VMEXIT only",
+	[SRSO_MITIGATION_BP_SPEC_REDUCE]	= "Mitigation: Reduced Speculation"
 };
 
 static enum srso_mitigation srso_mitigation __ro_after_init = SRSO_MITIGATION_NONE;
@@ -2578,7 +2580,7 @@ static void __init srso_select_mitigation(void)
 	    srso_cmd == SRSO_CMD_OFF) {
 		if (boot_cpu_has(X86_FEATURE_SBPB))
 			x86_pred_cmd = PRED_CMD_SBPB;
-		return;
+		goto out;
 	}
 
 	if (has_microcode) {
@@ -2590,7 +2592,7 @@ static void __init srso_select_mitigation(void)
 		 */
 		if (boot_cpu_data.x86 < 0x19 && !cpu_smt_possible()) {
 			setup_force_cpu_cap(X86_FEATURE_SRSO_NO);
-			return;
+			goto out;
 		}
 
 		if (retbleed_mitigation == RETBLEED_MITIGATION_IBPB) {
@@ -2670,6 +2672,12 @@ static void __init srso_select_mitigation(void)
 
 ibpb_on_vmexit:
 	case SRSO_CMD_IBPB_ON_VMEXIT:
+		if (boot_cpu_has(X86_FEATURE_SRSO_BP_SPEC_REDUCE)) {
+			pr_notice("Reducing speculation to address VM/HV SRSO attack vector.\n");
+			srso_mitigation = SRSO_MITIGATION_BP_SPEC_REDUCE;
+			break;
+		}
+
 		if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY)) {
 			if (has_microcode) {
 				setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT);
@@ -2691,7 +2699,15 @@ static void __init srso_select_mitigation(void)
 	}
 
 out:
-	pr_info("%s\n", srso_strings[srso_mitigation]);
+	/*
+	 * Clear the feature flag if this mitigation is not selected as that
+	 * feature flag controls the BpSpecReduce MSR bit toggling in KVM.
+	 */
+	if (srso_mitigation != SRSO_MITIGATION_BP_SPEC_REDUCE)
+		setup_clear_cpu_cap(X86_FEATURE_SRSO_BP_SPEC_REDUCE);
+
+	if (srso_mitigation != SRSO_MITIGATION_NONE)
+		pr_info("%s\n", srso_strings[srso_mitigation]);
 }
 
 #undef pr_fmt
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index a713c803a3a37..77ab66c5bb962 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -607,6 +607,9 @@ static void svm_disable_virtualization_cpu(void)
 	kvm_cpu_svm_disable();
 
 	amd_pmu_disable_virt();
+
+	if (cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE))
+		msr_clear_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT);
 }
 
 static int svm_enable_virtualization_cpu(void)
@@ -684,6 +687,9 @@ static int svm_enable_virtualization_cpu(void)
 		rdmsr(MSR_TSC_AUX, sev_es_host_save_area(sd)->tsc_aux, msr_hi);
 	}
 
+	if (cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE))
+		msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT);
+
 	return 0;
 }
 
diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c
index 4bf4fad5b148e..5a18ecc04a6c3 100644
--- a/arch/x86/lib/msr.c
+++ b/arch/x86/lib/msr.c
@@ -103,6 +103,7 @@ int msr_set_bit(u32 msr, u8 bit)
 {
 	return __flip_bit(msr, bit, true);
 }
+EXPORT_SYMBOL_GPL(msr_set_bit);
 
 /**
  * msr_clear_bit - Clear @bit in a MSR @msr.
@@ -118,6 +119,7 @@ int msr_clear_bit(u32 msr, u8 bit)
 {
 	return __flip_bit(msr, bit, false);
 }
+EXPORT_SYMBOL_GPL(msr_clear_bit);
 
 #ifdef CONFIG_TRACEPOINTS
 void do_trace_write_msr(unsigned int msr, u64 val, int failed)

From e4cf8ec4de4e13f156c1d61977d282d90c221085 Mon Sep 17 00:00:00 2001
From: Simon Tatham <anakin@pobox.com>
Date: Thu, 20 Feb 2025 08:14:43 +0000
Subject: [PATCH 0675/1173] affs: generate OFS sequence numbers starting at 1

If I write a file to an OFS floppy image, and try to read it back on
an emulated Amiga running Workbench 1.3, the Amiga reports a disk
error trying to read the file. (That is, it's unable to read it _at
all_, even to copy it to the NIL: device. It isn't a matter of getting
the wrong data and being unable to parse the file format.)

This is because the 'sequence number' field in the OFS data block
header is supposed to be based at 1, but affs writes it based at 0.
All three locations changed by this patch were setting the sequence
number to a variable 'bidx' which was previously obtained by dividing
a file position by bsize, so bidx will naturally use 0 for the first
block. Therefore all three should add 1 to that value before writing
it into the sequence number field.

With this change, the Amiga successfully reads the file.

For data block reference: https://wiki.osdev.org/FFS_(Amiga)

Signed-off-by: Simon Tatham <anakin@pobox.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/affs/file.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/affs/file.c b/fs/affs/file.c
index a5a861dd52230..226308f8627e7 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -596,7 +596,7 @@ affs_extent_file_ofs(struct inode *inode, u32 newsize)
 		BUG_ON(tmp > bsize);
 		AFFS_DATA_HEAD(bh)->ptype = cpu_to_be32(T_DATA);
 		AFFS_DATA_HEAD(bh)->key = cpu_to_be32(inode->i_ino);
-		AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx);
+		AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx + 1);
 		AFFS_DATA_HEAD(bh)->size = cpu_to_be32(tmp);
 		affs_fix_checksum(sb, bh);
 		bh->b_state &= ~(1UL << BH_New);
@@ -746,7 +746,7 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
 		if (buffer_new(bh)) {
 			AFFS_DATA_HEAD(bh)->ptype = cpu_to_be32(T_DATA);
 			AFFS_DATA_HEAD(bh)->key = cpu_to_be32(inode->i_ino);
-			AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx);
+			AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx + 1);
 			AFFS_DATA_HEAD(bh)->size = cpu_to_be32(bsize);
 			AFFS_DATA_HEAD(bh)->next = 0;
 			bh->b_state &= ~(1UL << BH_New);
@@ -780,7 +780,7 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
 		if (buffer_new(bh)) {
 			AFFS_DATA_HEAD(bh)->ptype = cpu_to_be32(T_DATA);
 			AFFS_DATA_HEAD(bh)->key = cpu_to_be32(inode->i_ino);
-			AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx);
+			AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx + 1);
 			AFFS_DATA_HEAD(bh)->size = cpu_to_be32(tmp);
 			AFFS_DATA_HEAD(bh)->next = 0;
 			bh->b_state &= ~(1UL << BH_New);

From 011ea742a25a77bac3d995f457886a67d178c6f0 Mon Sep 17 00:00:00 2001
From: Simon Tatham <anakin@pobox.com>
Date: Thu, 20 Feb 2025 08:14:44 +0000
Subject: [PATCH 0676/1173] affs: don't write overlarge OFS data block size
 fields

If a data sector on an OFS floppy contains a value > 0x1e8 (the
largest amount of data that fits in the sector after its header), then
an Amiga reading the file can return corrupt data, by taking the
overlarge size at its word and reading past the end of the buffer it
read the disk sector into!

The cause: when affs_write_end_ofs() writes data to an OFS filesystem,
the new size field for a data block was computed by adding the amount
of data currently being written (into the block) to the existing value
of the size field. This is correct if you're extending the file at the
end, but if you seek backwards in the file and overwrite _existing_
data, it can lead to the size field being larger than the maximum
legal value.

This commit changes the calculation so that it sets the size field to
the max of its previous size and the position within the block that we
just wrote up to.

Signed-off-by: Simon Tatham <anakin@pobox.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/affs/file.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/affs/file.c b/fs/affs/file.c
index 226308f8627e7..7a71018e3f675 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -724,7 +724,8 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
 		tmp = min(bsize - boff, to - from);
 		BUG_ON(boff + tmp > bsize || tmp > bsize);
 		memcpy(AFFS_DATA(bh) + boff, data + from, tmp);
-		be32_add_cpu(&AFFS_DATA_HEAD(bh)->size, tmp);
+		AFFS_DATA_HEAD(bh)->size = cpu_to_be32(
+			max(boff + tmp, be32_to_cpu(AFFS_DATA_HEAD(bh)->size)));
 		affs_fix_checksum(sb, bh);
 		mark_buffer_dirty_inode(bh, inode);
 		written += tmp;

From 5d3b81d4d8520efe888536b6906dc10fd1a228a8 Mon Sep 17 00:00:00 2001
From: Benjamin Berg <benjamin.berg@intel.com>
Date: Wed, 26 Feb 2025 14:31:36 +0100
Subject: [PATCH 0677/1173] x86/fpu: Avoid copying dynamic FP state from
 init_task in arch_dup_task_struct()

The init_task instance of struct task_struct is statically allocated and
may not contain the full FP state for userspace. As such, limit the copy
to the valid area of both init_task and 'dst' and ensure all memory is
initialized.

Note that the FP state is only needed for userspace, and as such it is
entirely reasonable for init_task to not contain parts of it.

Fixes: 5aaeb5c01c5b ("x86/fpu, sched: Introduce CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT and use it on x86")
Signed-off-by: Benjamin Berg <benjamin.berg@intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Link: https://lore.kernel.org/r/20250226133136.816901-1-benjamin@sipsolutions.net
----

v2:
- Fix code if arch_task_struct_size < sizeof(init_task) by using
  memcpy_and_pad.
---
 arch/x86/kernel/process.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 6da6769d7254a..7cb52f84cb0c2 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -93,7 +93,12 @@ EXPORT_PER_CPU_SYMBOL_GPL(__tss_limit_invalid);
  */
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
-	memcpy(dst, src, arch_task_struct_size);
+	/* init_task is not dynamically sized (incomplete FPU state) */
+	if (unlikely(src == &init_task))
+		memcpy_and_pad(dst, arch_task_struct_size, src, sizeof(init_task), 0);
+	else
+		memcpy(dst, src, arch_task_struct_size);
+
 #ifdef CONFIG_VM86
 	dst->thread.vm86 = NULL;
 #endif

From 7d8f03f7dd9f7d108b8d5af12fdc57e10555981f Mon Sep 17 00:00:00 2001
From: Zhou Ding <zhouding@cmss.chinamobile.com>
Date: Wed, 18 Dec 2024 00:28:59 +0800
Subject: [PATCH 0678/1173] x86/boot: Add missing has_cpuflag() prototype
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We get a warning when building the kernel with W=1:

  arch/x86/boot/compressed/cpuflags.c:4:6: warning: no previous prototype for ‘has_cpuflag’ [-Werror=missing-prototypes]
      4 | bool has_cpuflag(int flag)
        |      ^~~~~~~~~~~

Add a function declaration to cpuflags.h

Signed-off-by: Zhou Ding <zhouding@cmss.chinamobile.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20241217162859.1167889-1-zhouding@cmss.chinamobile.com
---
 arch/x86/boot/cpuflags.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/boot/cpuflags.h b/arch/x86/boot/cpuflags.h
index 475b8fde90f7d..fdcc2aa4c3c4a 100644
--- a/arch/x86/boot/cpuflags.h
+++ b/arch/x86/boot/cpuflags.h
@@ -18,5 +18,6 @@ extern u32 cpu_vendor[3];
 int has_eflag(unsigned long mask);
 void get_cpuflags(void);
 void cpuid_count(u32 id, u32 count, u32 *a, u32 *b, u32 *c, u32 *d);
+bool has_cpuflag(int flag);
 
 #endif

From e3924279e5164d821fa2cbcf0c15e7345cb3508e Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Wed, 26 Feb 2025 10:10:57 +0100
Subject: [PATCH 0679/1173] futex: Use a hashmask instead of hashsize

The global hash uses futex_hashsize to save the amount of the hash
buckets that have been allocated during system boot. On each
futex_hash() invocation this number is substracted by one to get the
mask. This can be optimized by saving directly the mask avoiding the
substraction on each futex_hash() invocation.

Rename futex_hashsize to futex_hashmask and save the mask of the
allocated hash map.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Waiman Long <longman@redhat.com>
Link: https://lore.kernel.org/all/20250226091057.bX8vObR4@linutronix.de
---
 kernel/futex/core.c | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index 3db8567f5a44e..cca15859a50be 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -50,10 +50,10 @@
  */
 static struct {
 	struct futex_hash_bucket *queues;
-	unsigned long            hashsize;
+	unsigned long            hashmask;
 } __futex_data __read_mostly __aligned(2*sizeof(long));
 #define futex_queues   (__futex_data.queues)
-#define futex_hashsize (__futex_data.hashsize)
+#define futex_hashmask (__futex_data.hashmask)
 
 
 /*
@@ -119,7 +119,7 @@ struct futex_hash_bucket *futex_hash(union futex_key *key)
 	u32 hash = jhash2((u32 *)key, offsetof(typeof(*key), both.offset) / 4,
 			  key->both.offset);
 
-	return &futex_queues[hash & (futex_hashsize - 1)];
+	return &futex_queues[hash & futex_hashmask];
 }
 
 
@@ -1127,27 +1127,28 @@ void futex_exit_release(struct task_struct *tsk)
 
 static int __init futex_init(void)
 {
+	unsigned long hashsize, i;
 	unsigned int futex_shift;
-	unsigned long i;
 
 #ifdef CONFIG_BASE_SMALL
-	futex_hashsize = 16;
+	hashsize = 16;
 #else
-	futex_hashsize = roundup_pow_of_two(256 * num_possible_cpus());
+	hashsize = roundup_pow_of_two(256 * num_possible_cpus());
 #endif
 
 	futex_queues = alloc_large_system_hash("futex", sizeof(*futex_queues),
-					       futex_hashsize, 0, 0,
+					       hashsize, 0, 0,
 					       &futex_shift, NULL,
-					       futex_hashsize, futex_hashsize);
-	futex_hashsize = 1UL << futex_shift;
+					       hashsize, hashsize);
+	hashsize = 1UL << futex_shift;
 
-	for (i = 0; i < futex_hashsize; i++) {
+	for (i = 0; i < hashsize; i++) {
 		atomic_set(&futex_queues[i].waiters, 0);
 		plist_head_init(&futex_queues[i].chain);
 		spin_lock_init(&futex_queues[i].lock);
 	}
 
+	futex_hashmask = hashsize - 1;
 	return 0;
 }
 core_initcall(futex_init);

From 79e10dad1ce3feac7937bedf911d92f486a9e76a Mon Sep 17 00:00:00 2001
From: Michael Jeanson <mjeanson@efficios.com>
Date: Tue, 25 Feb 2025 15:24:46 -0500
Subject: [PATCH 0680/1173] rseq: Update kernel fields in lockstep with
 CONFIG_DEBUG_RSEQ=y

With CONFIG_DEBUG_RSEQ=y, an in-kernel copy of the read-only fields is
kept synchronized with the user-space fields. Ensure the updates are
done in lockstep in case we error out on a write to user-space.

Fixes: 7d5265ffcd8b ("rseq: Validate read-only fields under DEBUG_RSEQ config")
Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/r/20250225202500.731245-1-mjeanson@efficios.com
---
 kernel/rseq.c | 80 +++++++++++++++++++++++++--------------------------
 1 file changed, 40 insertions(+), 40 deletions(-)

diff --git a/kernel/rseq.c b/kernel/rseq.c
index 442aba29bc4cf..3d136c48cff7f 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -78,24 +78,24 @@ static int rseq_validate_ro_fields(struct task_struct *t)
 	return -EFAULT;
 }
 
-static void rseq_set_ro_fields(struct task_struct *t, u32 cpu_id_start, u32 cpu_id,
-			       u32 node_id, u32 mm_cid)
-{
-	rseq_kernel_fields(t)->cpu_id_start = cpu_id;
-	rseq_kernel_fields(t)->cpu_id = cpu_id;
-	rseq_kernel_fields(t)->node_id = node_id;
-	rseq_kernel_fields(t)->mm_cid = mm_cid;
-}
+/*
+ * Update an rseq field and its in-kernel copy in lock-step to keep a coherent
+ * state.
+ */
+#define rseq_unsafe_put_user(t, value, field, error_label)		\
+	do {								\
+		unsafe_put_user(value, &t->rseq->field, error_label);	\
+		rseq_kernel_fields(t)->field = value;			\
+	} while (0)
+
 #else
 static int rseq_validate_ro_fields(struct task_struct *t)
 {
 	return 0;
 }
 
-static void rseq_set_ro_fields(struct task_struct *t, u32 cpu_id_start, u32 cpu_id,
-			       u32 node_id, u32 mm_cid)
-{
-}
+#define rseq_unsafe_put_user(t, value, field, error_label)		\
+	unsafe_put_user(value, &t->rseq->field, error_label)
 #endif
 
 /*
@@ -173,17 +173,18 @@ static int rseq_update_cpu_node_id(struct task_struct *t)
 	WARN_ON_ONCE((int) mm_cid < 0);
 	if (!user_write_access_begin(rseq, t->rseq_len))
 		goto efault;
-	unsafe_put_user(cpu_id, &rseq->cpu_id_start, efault_end);
-	unsafe_put_user(cpu_id, &rseq->cpu_id, efault_end);
-	unsafe_put_user(node_id, &rseq->node_id, efault_end);
-	unsafe_put_user(mm_cid, &rseq->mm_cid, efault_end);
+
+	rseq_unsafe_put_user(t, cpu_id, cpu_id_start, efault_end);
+	rseq_unsafe_put_user(t, cpu_id, cpu_id, efault_end);
+	rseq_unsafe_put_user(t, node_id, node_id, efault_end);
+	rseq_unsafe_put_user(t, mm_cid, mm_cid, efault_end);
+
 	/*
 	 * Additional feature fields added after ORIG_RSEQ_SIZE
 	 * need to be conditionally updated only if
 	 * t->rseq_len != ORIG_RSEQ_SIZE.
 	 */
 	user_write_access_end();
-	rseq_set_ro_fields(t, cpu_id, cpu_id, node_id, mm_cid);
 	trace_rseq_update(t);
 	return 0;
 
@@ -195,6 +196,7 @@ static int rseq_update_cpu_node_id(struct task_struct *t)
 
 static int rseq_reset_rseq_cpu_node_id(struct task_struct *t)
 {
+	struct rseq __user *rseq = t->rseq;
 	u32 cpu_id_start = 0, cpu_id = RSEQ_CPU_ID_UNINITIALIZED, node_id = 0,
 	    mm_cid = 0;
 
@@ -202,38 +204,36 @@ static int rseq_reset_rseq_cpu_node_id(struct task_struct *t)
 	 * Validate read-only rseq fields.
 	 */
 	if (rseq_validate_ro_fields(t))
-		return -EFAULT;
-	/*
-	 * Reset cpu_id_start to its initial state (0).
-	 */
-	if (put_user(cpu_id_start, &t->rseq->cpu_id_start))
-		return -EFAULT;
-	/*
-	 * Reset cpu_id to RSEQ_CPU_ID_UNINITIALIZED, so any user coming
-	 * in after unregistration can figure out that rseq needs to be
-	 * registered again.
-	 */
-	if (put_user(cpu_id, &t->rseq->cpu_id))
-		return -EFAULT;
-	/*
-	 * Reset node_id to its initial state (0).
-	 */
-	if (put_user(node_id, &t->rseq->node_id))
-		return -EFAULT;
+		goto efault;
+
+	if (!user_write_access_begin(rseq, t->rseq_len))
+		goto efault;
+
 	/*
-	 * Reset mm_cid to its initial state (0).
+	 * Reset all fields to their initial state.
+	 *
+	 * All fields have an initial state of 0 except cpu_id which is set to
+	 * RSEQ_CPU_ID_UNINITIALIZED, so that any user coming in after
+	 * unregistration can figure out that rseq needs to be registered
+	 * again.
 	 */
-	if (put_user(mm_cid, &t->rseq->mm_cid))
-		return -EFAULT;
-
-	rseq_set_ro_fields(t, cpu_id_start, cpu_id, node_id, mm_cid);
+	rseq_unsafe_put_user(t, cpu_id_start, cpu_id_start, efault_end);
+	rseq_unsafe_put_user(t, cpu_id, cpu_id, efault_end);
+	rseq_unsafe_put_user(t, node_id, node_id, efault_end);
+	rseq_unsafe_put_user(t, mm_cid, mm_cid, efault_end);
 
 	/*
 	 * Additional feature fields added after ORIG_RSEQ_SIZE
 	 * need to be conditionally reset only if
 	 * t->rseq_len != ORIG_RSEQ_SIZE.
 	 */
+	user_write_access_end();
 	return 0;
+
+efault_end:
+	user_write_access_end();
+efault:
+	return -EFAULT;
 }
 
 static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs)

From 7a6b158e00c862ccfa7fe447682bd0bf5c229c73 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Tue, 25 Feb 2025 18:00:47 +0100
Subject: [PATCH 0681/1173] posix-clock: Remove duplicate compat ioctl()
 handler
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The normal and compat ioctl handlers are identical,
which is fine as compat ioctls are detected and handled dynamically
inside the underlying clock implementation.
The duplicate definition however is unnecessary.

Just reuse the regular ioctl handler also for compat ioctls.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Cyrill Gorcunov <gorcunov@gmail.com>
Link: https://lore.kernel.org/all/20250225-posix-clock-compat-cleanup-v2-1-30de86457a2b@weissschuh.net
---
 kernel/time/posix-clock.c | 24 +-----------------------
 1 file changed, 1 insertion(+), 23 deletions(-)

diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c
index 1af0bb2cc45c0..7f4e4fb7381ef 100644
--- a/kernel/time/posix-clock.c
+++ b/kernel/time/posix-clock.c
@@ -90,26 +90,6 @@ static long posix_clock_ioctl(struct file *fp,
 	return err;
 }
 
-#ifdef CONFIG_COMPAT
-static long posix_clock_compat_ioctl(struct file *fp,
-				     unsigned int cmd, unsigned long arg)
-{
-	struct posix_clock_context *pccontext = fp->private_data;
-	struct posix_clock *clk = get_posix_clock(fp);
-	int err = -ENOTTY;
-
-	if (!clk)
-		return -ENODEV;
-
-	if (clk->ops.ioctl)
-		err = clk->ops.ioctl(pccontext, cmd, arg);
-
-	put_posix_clock(clk);
-
-	return err;
-}
-#endif
-
 static int posix_clock_open(struct inode *inode, struct file *fp)
 {
 	int err;
@@ -171,11 +151,9 @@ static const struct file_operations posix_clock_file_operations = {
 	.read		= posix_clock_read,
 	.poll		= posix_clock_poll,
 	.unlocked_ioctl	= posix_clock_ioctl,
+	.compat_ioctl	= posix_clock_ioctl,
 	.open		= posix_clock_open,
 	.release	= posix_clock_release,
-#ifdef CONFIG_COMPAT
-	.compat_ioctl	= posix_clock_compat_ioctl,
-#endif
 };
 
 int posix_clock_register(struct posix_clock *clk, struct device *dev)

From 01f1d77a2630e774ce33233c4e6723bca3ae9daa Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Tue, 14 Jan 2025 10:57:25 +0100
Subject: [PATCH 0682/1173] drm/nouveau: Do not override forced connector
 status

Keep user-forced connector status even if it cannot be programmed. Same
behavior as for the rest of the drivers.

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Lyude Paul <lyude@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250114100214.195386-1-tzimmermann@suse.de
---
 drivers/gpu/drm/nouveau/nouveau_connector.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c
index 8d5c9c74cbb90..eac0d1d2dbda2 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.c
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.c
@@ -775,7 +775,6 @@ nouveau_connector_force(struct drm_connector *connector)
 	if (!nv_encoder) {
 		NV_ERROR(drm, "can't find encoder to force %s on!\n",
 			 connector->name);
-		connector->status = connector_status_disconnected;
 		return;
 	}
 

From 75f1f311d883dfaffb98be3c1da208d6ed5d4df9 Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Wed, 26 Feb 2025 13:38:19 -0600
Subject: [PATCH 0683/1173] Revert "of: reserved-memory: Fix using wrong number
 of cells to get property 'alignment'"

This reverts commit 267b21d0bef8e67dbe6c591c9991444e58237ec9.

Turns out some DTs do depend on this behavior. Specifically, a
downstream Pixel 6 DT. Revert the change at least until we can decide if
the DT spec can be changed instead.

Cc: stable@vger.kernel.org
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
---
 drivers/of/of_reserved_mem.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c
index 75e819f66a561..ee2e31522d7ef 100644
--- a/drivers/of/of_reserved_mem.c
+++ b/drivers/of/of_reserved_mem.c
@@ -415,12 +415,12 @@ static int __init __reserved_mem_alloc_size(unsigned long node, const char *unam
 
 	prop = of_get_flat_dt_prop(node, "alignment", &len);
 	if (prop) {
-		if (len != dt_root_size_cells * sizeof(__be32)) {
+		if (len != dt_root_addr_cells * sizeof(__be32)) {
 			pr_err("invalid alignment property in '%s' node.\n",
 				uname);
 			return -EINVAL;
 		}
-		align = dt_mem_next_cell(dt_root_size_cells, &prop);
+		align = dt_mem_next_cell(dt_root_addr_cells, &prop);
 	}
 
 	nomap = of_get_flat_dt_prop(node, "no-map", NULL) != NULL;

From dd1998e243f5fa25d348a384ba0b6c84d980f2b2 Mon Sep 17 00:00:00 2001
From: Tyrone Ting <kfting@nuvoton.com>
Date: Thu, 20 Feb 2025 12:00:29 +0800
Subject: [PATCH 0684/1173] i2c: npcm: disable interrupt enable bit before
 devm_request_irq

The customer reports that there is a soft lockup issue related to
the i2c driver. After checking, the i2c module was doing a tx transfer
and the bmc machine reboots in the middle of the i2c transaction, the i2c
module keeps the status without being reset.

Due to such an i2c module status, the i2c irq handler keeps getting
triggered since the i2c irq handler is registered in the kernel booting
process after the bmc machine is doing a warm rebooting.
The continuous triggering is stopped by the soft lockup watchdog timer.

Disable the interrupt enable bit in the i2c module before calling
devm_request_irq to fix this issue since the i2c relative status bit
is read-only.

Here is the soft lockup log.
[   28.176395] watchdog: BUG: soft lockup - CPU#0 stuck for 26s! [swapper/0:1]
[   28.183351] Modules linked in:
[   28.186407] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.15.120-yocto-s-dirty-bbebc78 #1
[   28.201174] pstate: 40000005 (nZcv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[   28.208128] pc : __do_softirq+0xb0/0x368
[   28.212055] lr : __do_softirq+0x70/0x368
[   28.215972] sp : ffffff8035ebca00
[   28.219278] x29: ffffff8035ebca00 x28: 0000000000000002 x27: ffffff80071a3780
[   28.226412] x26: ffffffc008bdc000 x25: ffffffc008bcc640 x24: ffffffc008be50c0
[   28.233546] x23: ffffffc00800200c x22: 0000000000000000 x21: 000000000000001b
[   28.240679] x20: 0000000000000000 x19: ffffff80001c3200 x18: ffffffffffffffff
[   28.247812] x17: ffffffc02d2e0000 x16: ffffff8035eb8b40 x15: 00001e8480000000
[   28.254945] x14: 02c3647e37dbfcb6 x13: 02c364f2ab14200c x12: 0000000002c364f2
[   28.262078] x11: 00000000fa83b2da x10: 000000000000b67e x9 : ffffffc008010250
[   28.269211] x8 : 000000009d983d00 x7 : 7fffffffffffffff x6 : 0000036d74732434
[   28.276344] x5 : 00ffffffffffffff x4 : 0000000000000015 x3 : 0000000000000198
[   28.283476] x2 : ffffffc02d2e0000 x1 : 00000000000000e0 x0 : ffffffc008bdcb40
[   28.290611] Call trace:
[   28.293052]  __do_softirq+0xb0/0x368
[   28.296625]  __irq_exit_rcu+0xe0/0x100
[   28.300374]  irq_exit+0x14/0x20
[   28.303513]  handle_domain_irq+0x68/0x90
[   28.307440]  gic_handle_irq+0x78/0xb0
[   28.311098]  call_on_irq_stack+0x20/0x38
[   28.315019]  do_interrupt_handler+0x54/0x5c
[   28.319199]  el1_interrupt+0x2c/0x4c
[   28.322777]  el1h_64_irq_handler+0x14/0x20
[   28.326872]  el1h_64_irq+0x74/0x78
[   28.330269]  __setup_irq+0x454/0x780
[   28.333841]  request_threaded_irq+0xd0/0x1b4
[   28.338107]  devm_request_threaded_irq+0x84/0x100
[   28.342809]  npcm_i2c_probe_bus+0x188/0x3d0
[   28.346990]  platform_probe+0x6c/0xc4
[   28.350653]  really_probe+0xcc/0x45c
[   28.354227]  __driver_probe_device+0x8c/0x160
[   28.358578]  driver_probe_device+0x44/0xe0
[   28.362670]  __driver_attach+0x124/0x1d0
[   28.366589]  bus_for_each_dev+0x7c/0xe0
[   28.370426]  driver_attach+0x28/0x30
[   28.373997]  bus_add_driver+0x124/0x240
[   28.377830]  driver_register+0x7c/0x124
[   28.381662]  __platform_driver_register+0x2c/0x34
[   28.386362]  npcm_i2c_init+0x3c/0x5c
[   28.389937]  do_one_initcall+0x74/0x230
[   28.393768]  kernel_init_freeable+0x24c/0x2b4
[   28.398126]  kernel_init+0x28/0x130
[   28.401614]  ret_from_fork+0x10/0x20
[   28.405189] Kernel panic - not syncing: softlockup: hung tasks
[   28.411011] SMP: stopping secondary CPUs
[   28.414933] Kernel Offset: disabled
[   28.418412] CPU features: 0x00000000,00000802
[   28.427644] Rebooting in 20 seconds..

Fixes: 56a1485b102e ("i2c: npcm7xx: Add Nuvoton NPCM I2C controller driver")
Signed-off-by: Tyrone Ting <kfting@nuvoton.com>
Cc: <stable@vger.kernel.org> # v5.8+
Reviewed-by: Tali Perry <tali.perry1@gmail.com>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20250220040029.27596-2-kfting@nuvoton.com
---
 drivers/i2c/busses/i2c-npcm7xx.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/i2c/busses/i2c-npcm7xx.c b/drivers/i2c/busses/i2c-npcm7xx.c
index 3ca08b8ef8af3..de713b5747fe5 100644
--- a/drivers/i2c/busses/i2c-npcm7xx.c
+++ b/drivers/i2c/busses/i2c-npcm7xx.c
@@ -2554,6 +2554,13 @@ static int npcm_i2c_probe_bus(struct platform_device *pdev)
 	if (irq < 0)
 		return irq;
 
+	/*
+	 * Disable the interrupt to avoid the interrupt handler being triggered
+	 * incorrectly by the asynchronous interrupt status since the machine
+	 * might do a warm reset during the last smbus/i2c transfer session.
+	 */
+	npcm_i2c_int_enable(bus, false);
+
 	ret = devm_request_irq(bus->dev, irq, npcm_i2c_bus_irq, 0,
 			       dev_name(bus->dev), bus);
 	if (ret)

From 71c49ee9bb41e1709abac7e2eb05f9193222e580 Mon Sep 17 00:00:00 2001
From: Binbin Zhou <zhoubinbin@loongson.cn>
Date: Thu, 20 Feb 2025 20:56:12 +0800
Subject: [PATCH 0685/1173] i2c: ls2x: Fix frequency division register access

According to the chip manual, the I2C register access type of
Loongson-2K2000/LS7A is "B", so we can only access registers in byte
form (readb()/writeb()).

Although Loongson-2K0500/Loongson-2K1000 do not have similar
constraints, register accesses in byte form also behave correctly.

Also, in hardware, the frequency division registers are defined as two
separate registers (high 8-bit and low 8-bit), so we just access them
directly as bytes.

Fixes: 015e61f0bffd ("i2c: ls2x: Add driver for Loongson-2K/LS7A I2C controller")
Co-developed-by: Hongliang Wang <wanghongliang@loongson.cn>
Signed-off-by: Hongliang Wang <wanghongliang@loongson.cn>
Signed-off-by: Binbin Zhou <zhoubinbin@loongson.cn>
Cc: stable@vger.kernel.org # v6.3+
Reviewed-by: Andy Shevchenko <andy@kernel.org>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20250220125612.1910990-1-zhoubinbin@loongson.cn
---
 drivers/i2c/busses/i2c-ls2x.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/drivers/i2c/busses/i2c-ls2x.c b/drivers/i2c/busses/i2c-ls2x.c
index 8821cac3897b6..b475dd27b7af9 100644
--- a/drivers/i2c/busses/i2c-ls2x.c
+++ b/drivers/i2c/busses/i2c-ls2x.c
@@ -10,6 +10,7 @@
  * Rewritten for mainline by Binbin Zhou <zhoubinbin@loongson.cn>
  */
 
+#include <linux/bitfield.h>
 #include <linux/bits.h>
 #include <linux/completion.h>
 #include <linux/device.h>
@@ -26,7 +27,8 @@
 #include <linux/units.h>
 
 /* I2C Registers */
-#define I2C_LS2X_PRER		0x0 /* Freq Division Register(16 bits) */
+#define I2C_LS2X_PRER_LO	0x0 /* Freq Division Low Byte Register */
+#define I2C_LS2X_PRER_HI	0x1 /* Freq Division High Byte Register */
 #define I2C_LS2X_CTR		0x2 /* Control Register */
 #define I2C_LS2X_TXR		0x3 /* Transport Data Register */
 #define I2C_LS2X_RXR		0x3 /* Receive Data Register */
@@ -93,6 +95,7 @@ static irqreturn_t ls2x_i2c_isr(int this_irq, void *dev_id)
  */
 static void ls2x_i2c_adjust_bus_speed(struct ls2x_i2c_priv *priv)
 {
+	u16 val;
 	struct i2c_timings *t = &priv->i2c_t;
 	struct device *dev = priv->adapter.dev.parent;
 	u32 acpi_speed = i2c_acpi_find_bus_speed(dev);
@@ -104,9 +107,14 @@ static void ls2x_i2c_adjust_bus_speed(struct ls2x_i2c_priv *priv)
 	else
 		t->bus_freq_hz = LS2X_I2C_FREQ_STD;
 
-	/* Calculate and set i2c frequency. */
-	writew(LS2X_I2C_PCLK_FREQ / (5 * t->bus_freq_hz) - 1,
-	       priv->base + I2C_LS2X_PRER);
+	/*
+	 * According to the chip manual, we can only access the registers as bytes,
+	 * otherwise the high bits will be truncated.
+	 * So set the I2C frequency with a sequential writeb() instead of writew().
+	 */
+	val = LS2X_I2C_PCLK_FREQ / (5 * t->bus_freq_hz) - 1;
+	writeb(FIELD_GET(GENMASK(7, 0), val), priv->base + I2C_LS2X_PRER_LO);
+	writeb(FIELD_GET(GENMASK(15, 8), val), priv->base + I2C_LS2X_PRER_HI);
 }
 
 static void ls2x_i2c_init(struct ls2x_i2c_priv *priv)

From 9f3c507cb44498067c980674139bcad56e582ee6 Mon Sep 17 00:00:00 2001
From: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Date: Wed, 19 Feb 2025 19:27:47 +0530
Subject: [PATCH 0686/1173] i2c: amd-asf: Fix EOI register write to enable
 successive interrupts

The commit b1f8921dfbaa
("i2c: amd-asf: Clear remote IRR bit to get successive interrupt")
introduced a method to enable successive interrupts but inadvertently
omitted the necessary write to the EOI register, resulting in a failure to
receive successive interrupts.

Fix this by adding the required write to the EOI register.

Fixes: b1f8921dfbaa ("i2c: amd-asf: Clear remote IRR bit to get successive interrupt")
Cc: stable@vger.kernel.org # v6.13+
Co-developed-by: Sanket Goswami <Sanket.Goswami@amd.com>
Signed-off-by: Sanket Goswami <Sanket.Goswami@amd.com>
Signed-off-by: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Fixes: 9b25419ad397 ("i2c: amd-asf: Add routine to handle the ASF slave process")
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20250219135747.3251182-1-Shyam-sundar.S-k@amd.com
---
 drivers/i2c/busses/i2c-amd-asf-plat.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/i2c/busses/i2c-amd-asf-plat.c b/drivers/i2c/busses/i2c-amd-asf-plat.c
index 7512614bf4b73..93ebec162c6dd 100644
--- a/drivers/i2c/busses/i2c-amd-asf-plat.c
+++ b/drivers/i2c/busses/i2c-amd-asf-plat.c
@@ -293,6 +293,7 @@ static irqreturn_t amd_asf_irq_handler(int irq, void *ptr)
 		amd_asf_update_ioport_target(piix4_smba, ASF_SLV_INTR, SMBHSTSTS, true);
 	}
 
+	iowrite32(irq, dev->eoi_base);
 	return IRQ_HANDLED;
 }
 

From ac965d7d88fc36fb42e3d50225c0a44dd8326da4 Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Wed, 26 Feb 2025 15:18:46 +0900
Subject: [PATCH 0687/1173] tracing: tprobe-events: Fix a memory leak when
 tprobe with $retval

Fix a memory leak when a tprobe is defined with $retval. This
combination is not allowed, but the parse_symbol_and_return() does
not free the *symbol which should not be used if it returns the error.
Thus, it leaks the *symbol memory in that error path.

Link: https://lore.kernel.org/all/174055072650.4079315.3063014346697447838.stgit@mhiramat.tok.corp.google.com/

Fixes: ce51e6153f77 ("tracing: fprobe-event: Fix to check tracepoint event and return")
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Cc: stable@vger.kernel.org
---
 kernel/trace/trace_fprobe.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c
index b8f3c4ba309b6..8826f44f69a44 100644
--- a/kernel/trace/trace_fprobe.c
+++ b/kernel/trace/trace_fprobe.c
@@ -1056,6 +1056,8 @@ static int parse_symbol_and_return(int argc, const char *argv[],
 			if (is_tracepoint) {
 				trace_probe_log_set_index(i);
 				trace_probe_log_err(tmp - argv[i], RETVAL_ON_PROBE);
+				kfree(*symbol);
+				*symbol = NULL;
 				return -EINVAL;
 			}
 			*is_return = true;

From d0453655b6ddc685a4837f3cc0776ae8eef62d01 Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Wed, 26 Feb 2025 15:18:54 +0900
Subject: [PATCH 0688/1173] tracing: tprobe-events: Reject invalid tracepoint
 name

Commit 57a7e6de9e30 ("tracing/fprobe: Support raw tracepoints on
future loaded modules") allows user to set a tprobe on non-exist
tracepoint but it does not check the tracepoint name is acceptable.
So it leads tprobe has a wrong character for events (e.g. with
subsystem prefix). In this case, the event is not shown in the
events directory.

Reject such invalid tracepoint name.

The tracepoint name must consist of alphabet or digit or '_'.

Link: https://lore.kernel.org/all/174055073461.4079315.15875502830565214255.stgit@mhiramat.tok.corp.google.com/

Fixes: 57a7e6de9e30 ("tracing/fprobe: Support raw tracepoints on future loaded modules")
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Cc: stable@vger.kernel.org
---
 kernel/trace/trace_fprobe.c | 13 +++++++++++++
 kernel/trace/trace_probe.h  |  1 +
 2 files changed, 14 insertions(+)

diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c
index 8826f44f69a44..85f037dc14623 100644
--- a/kernel/trace/trace_fprobe.c
+++ b/kernel/trace/trace_fprobe.c
@@ -1049,6 +1049,19 @@ static int parse_symbol_and_return(int argc, const char *argv[],
 	if (*is_return)
 		return 0;
 
+	if (is_tracepoint) {
+		tmp = *symbol;
+		while (*tmp && (isalnum(*tmp) || *tmp == '_'))
+			tmp++;
+		if (*tmp) {
+			/* find a wrong character. */
+			trace_probe_log_err(tmp - *symbol, BAD_TP_NAME);
+			kfree(*symbol);
+			*symbol = NULL;
+			return -EINVAL;
+		}
+	}
+
 	/* If there is $retval, this should be a return fprobe. */
 	for (i = 2; i < argc; i++) {
 		tmp = strstr(argv[i], "$retval");
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 5803e6a415705..fba3ede870541 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -481,6 +481,7 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
 	C(NON_UNIQ_SYMBOL,	"The symbol is not unique"),		\
 	C(BAD_RETPROBE,		"Retprobe address must be an function entry"), \
 	C(NO_TRACEPOINT,	"Tracepoint is not found"),		\
+	C(BAD_TP_NAME,		"Invalid character in tracepoint name"),\
 	C(BAD_ADDR_SUFFIX,	"Invalid probed address suffix"), \
 	C(NO_GROUP_NAME,	"Group name is not specified"),		\
 	C(GROUP_TOO_LONG,	"Group name is too long"),		\

From db5e228611b118cf7b1f8084063feda5c037f4a7 Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Wed, 26 Feb 2025 15:19:02 +0900
Subject: [PATCH 0689/1173] tracing: fprobe-events: Log error for exceeding the
 number of entry args

Add error message when the number of entry argument exceeds the
maximum size of entry data.
This is currently checked when registering fprobe, but in this case
no error message is shown in the error_log file.

Link: https://lore.kernel.org/all/174055074269.4079315.17809232650360988538.stgit@mhiramat.tok.corp.google.com/

Fixes: 25f00e40ce79 ("tracing/probes: Support $argN in return probe (kprobe and fprobe)")
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_fprobe.c | 5 +++++
 kernel/trace/trace_probe.h  | 3 ++-
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c
index 85f037dc14623..e27305d31fc57 100644
--- a/kernel/trace/trace_fprobe.c
+++ b/kernel/trace/trace_fprobe.c
@@ -1230,6 +1230,11 @@ static int trace_fprobe_create_internal(int argc, const char *argv[],
 	if (is_return && tf->tp.entry_arg) {
 		tf->fp.entry_handler = trace_fprobe_entry_handler;
 		tf->fp.entry_data_size = traceprobe_get_entry_data_size(&tf->tp);
+		if (ALIGN(tf->fp.entry_data_size, sizeof(long)) > MAX_FPROBE_DATA_SIZE) {
+			trace_probe_log_set_index(2);
+			trace_probe_log_err(0, TOO_MANY_EARGS);
+			return -E2BIG;
+		}
 	}
 
 	ret = traceprobe_set_print_fmt(&tf->tp,
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index fba3ede870541..c47ca002347a7 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -545,7 +545,8 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
 	C(NO_BTF_FIELD,		"This field is not found."),	\
 	C(BAD_BTF_TID,		"Failed to get BTF type info."),\
 	C(BAD_TYPE4STR,		"This type does not fit for string."),\
-	C(NEED_STRING_TYPE,	"$comm and immediate-string only accepts string type"),
+	C(NEED_STRING_TYPE,	"$comm and immediate-string only accepts string type"),\
+	C(TOO_MANY_EARGS,	"Too many entry arguments specified"),
 
 #undef C
 #define C(a, b)		TP_ERR_##a

From 2b1283e1ea9b5e0b06f075f79391a51d9f70749b Mon Sep 17 00:00:00 2001
From: Ryan Roberts <ryan.roberts@arm.com>
Date: Tue, 25 Feb 2025 11:46:36 +0000
Subject: [PATCH 0690/1173] arm64/mm: Fix Boot panic on Ampere Altra

When the range of present physical memory is sufficiently small enough
and the reserved address space for the linear map is sufficiently large
enough, The linear map base address is randomized in
arm64_memblock_init().

Prior to commit 62cffa496aac ("arm64/mm: Override PARange for !LPA2 and
use it consistently"), we decided if the sizes were suitable with the
help of the raw mmfr0.parange. But the commit changed this to use the
sanitized version instead. But the function runs before the register has
been sanitized so this returns 0, interpreted as a parange of 32 bits.
Some fun wrapping occurs and the logic concludes that there is enough
room to randomize the linear map base address, when really there isn't.
So the top of the linear map ends up outside the reserved address space.

Since the PA range cannot be overridden in the first place, restore the
mmfr0 reading logic to its state prior to 62cffa496aac, where the raw
register value is used.

Reported-by: Luiz Capitulino <luizcap@redhat.com>
Suggested-by: Ard Biesheuvel <ardb@kernel.org>
Closes: https://lore.kernel.org/all/a3d9acbe-07c2-43b6-9ba9-a7585f770e83@redhat.com/
Fixes: 62cffa496aac ("arm64/mm: Override PARange for !LPA2 and use it consistently")
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Link: https://lore.kernel.org/r/20250225114638.2038006-1-ryan.roberts@arm.com
Cc: stable@vger.kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/mm/init.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 9c0b8d9558fc4..ccdef53872a0b 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -279,12 +279,7 @@ void __init arm64_memblock_init(void)
 
 	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
 		extern u16 memstart_offset_seed;
-
-		/*
-		 * Use the sanitised version of id_aa64mmfr0_el1 so that linear
-		 * map randomization can be enabled by shrinking the IPA space.
-		 */
-		u64 mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
+		u64 mmfr0 = read_cpuid(ID_AA64MMFR0_EL1);
 		int parange = cpuid_feature_extract_unsigned_field(
 					mmfr0, ID_AA64MMFR0_EL1_PARANGE_SHIFT);
 		s64 range = linear_region_size -

From 4804f3ac2649475509b1836a4d252c04de143249 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Wed, 26 Feb 2025 19:30:38 -0500
Subject: [PATCH 0691/1173] bcachefs: Revert directory i_size

This turned out to have several bugs, which were missed because the fsck
code wasn't properly reporting errors - whoops.

Kicking it out for now, hopefully it can make 6.15.

Cc: Hongbo Li <lihongbo22@huawei.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/dirent.h       |  5 -----
 fs/bcachefs/fs-common.c    | 11 -----------
 fs/bcachefs/fsck.c         | 21 ---------------------
 fs/bcachefs/sb-downgrade.c |  5 +----
 4 files changed, 1 insertion(+), 41 deletions(-)

diff --git a/fs/bcachefs/dirent.h b/fs/bcachefs/dirent.h
index a633f83c1ac78..362b3b2f2f2e3 100644
--- a/fs/bcachefs/dirent.h
+++ b/fs/bcachefs/dirent.h
@@ -31,11 +31,6 @@ static inline unsigned dirent_val_u64s(unsigned len)
 			    sizeof(u64));
 }
 
-static inline unsigned int dirent_occupied_size(const struct qstr *name)
-{
-	return (BKEY_U64s + dirent_val_u64s(name->len)) * sizeof(u64);
-}
-
 int bch2_dirent_read_target(struct btree_trans *, subvol_inum,
 			    struct bkey_s_c_dirent, subvol_inum *);
 
diff --git a/fs/bcachefs/fs-common.c b/fs/bcachefs/fs-common.c
index d70d9f634cea9..2c3d46ac70c61 100644
--- a/fs/bcachefs/fs-common.c
+++ b/fs/bcachefs/fs-common.c
@@ -152,7 +152,6 @@ int bch2_create_trans(struct btree_trans *trans,
 		if (is_subdir_for_nlink(new_inode))
 			dir_u->bi_nlink++;
 		dir_u->bi_mtime = dir_u->bi_ctime = now;
-		dir_u->bi_size += dirent_occupied_size(name);
 
 		ret = bch2_inode_write(trans, &dir_iter, dir_u);
 		if (ret)
@@ -221,7 +220,6 @@ int bch2_link_trans(struct btree_trans *trans,
 	}
 
 	dir_u->bi_mtime = dir_u->bi_ctime = now;
-	dir_u->bi_size += dirent_occupied_size(name);
 
 	dir_hash = bch2_hash_info_init(c, dir_u);
 
@@ -324,7 +322,6 @@ int bch2_unlink_trans(struct btree_trans *trans,
 
 	dir_u->bi_mtime = dir_u->bi_ctime = inode_u->bi_ctime = now;
 	dir_u->bi_nlink -= is_subdir_for_nlink(inode_u);
-	dir_u->bi_size	-= dirent_occupied_size(name);
 
 	ret =   bch2_hash_delete_at(trans, bch2_dirent_hash_desc,
 				    &dir_hash, &dirent_iter,
@@ -463,14 +460,6 @@ int bch2_rename_trans(struct btree_trans *trans,
 		goto err;
 	}
 
-	if (mode == BCH_RENAME) {
-		src_dir_u->bi_size -= dirent_occupied_size(src_name);
-		dst_dir_u->bi_size += dirent_occupied_size(dst_name);
-	}
-
-	if (mode == BCH_RENAME_OVERWRITE)
-		src_dir_u->bi_size -= dirent_occupied_size(src_name);
-
 	if (src_inode_u->bi_parent_subvol)
 		src_inode_u->bi_parent_subvol = dst_dir.subvol;
 
diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c
index 9bf316e7b845d..0e85131d0af88 100644
--- a/fs/bcachefs/fsck.c
+++ b/fs/bcachefs/fsck.c
@@ -1978,31 +1978,10 @@ static int check_subdir_count_notnested(struct btree_trans *trans, struct inode_
 	return ret;
 }
 
-static int check_dir_i_size_notnested(struct btree_trans *trans, struct inode_walker *w)
-{
-	struct bch_fs *c = trans->c;
-	int ret = 0;
-
-	darray_for_each(w->inodes, i)
-		if (fsck_err_on(i->inode.bi_size != i->i_size,
-				trans, inode_dir_wrong_nlink,
-				"directory %llu:%u with wrong i_size: got %llu, should be %llu",
-				w->last_pos.inode, i->snapshot, i->inode.bi_size, i->i_size)) {
-			i->inode.bi_size = i->i_size;
-			ret = bch2_fsck_write_inode(trans, &i->inode);
-			if (ret)
-				break;
-		}
-fsck_err:
-	bch_err_fn(c, ret);
-	return ret;
-}
-
 static int check_subdir_dirents_count(struct btree_trans *trans, struct inode_walker *w)
 {
 	u32 restart_count = trans->restart_count;
 	return check_subdir_count_notnested(trans, w) ?:
-		check_dir_i_size_notnested(trans, w) ?:
 		trans_was_restarted(trans, restart_count);
 }
 
diff --git a/fs/bcachefs/sb-downgrade.c b/fs/bcachefs/sb-downgrade.c
index 35e07bc8fbd34..051214fdc7352 100644
--- a/fs/bcachefs/sb-downgrade.c
+++ b/fs/bcachefs/sb-downgrade.c
@@ -90,10 +90,7 @@
 	  BIT_ULL(BCH_RECOVERY_PASS_check_allocations),		\
 	  BCH_FSCK_ERR_accounting_mismatch,			\
 	  BCH_FSCK_ERR_accounting_key_replicas_nr_devs_0,	\
-	  BCH_FSCK_ERR_accounting_key_junk_at_end)		\
-	x(directory_size,					\
-	  BIT_ULL(BCH_RECOVERY_PASS_check_dirents),		\
-	  BCH_FSCK_ERR_directory_size_mismatch)			\
+	  BCH_FSCK_ERR_accounting_key_junk_at_end)
 
 #define DOWNGRADE_TABLE()					\
 	x(bucket_stripe_sectors,				\

From 7909d1fb90e290ffd7b8570f4e2f97fe2fb381d0 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Tue, 25 Feb 2025 22:35:28 -0500
Subject: [PATCH 0692/1173] bcachefs: Check for -BCH_ERR_open_buckets_empty in
 journal resize

This fixes occasional failures from journal resize.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/journal.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/bcachefs/journal.c b/fs/bcachefs/journal.c
index 24c294d4634e0..5dabbf3c0965c 100644
--- a/fs/bcachefs/journal.c
+++ b/fs/bcachefs/journal.c
@@ -1194,7 +1194,9 @@ int bch2_set_nr_journal_buckets(struct bch_fs *c, struct bch_dev *ca,
 
 		closure_sync(&cl);
 
-		if (ret && ret != -BCH_ERR_bucket_alloc_blocked)
+		if (ret &&
+		    ret != -BCH_ERR_bucket_alloc_blocked &&
+		    ret != -BCH_ERR_open_buckets_empty)
 			break;
 	}
 

From 677bdb7346b6fd806ea45b11cbfe36de0b0cd644 Mon Sep 17 00:00:00 2001
From: Alan Huang <mmpgouride@gmail.com>
Date: Wed, 26 Feb 2025 17:33:22 +0800
Subject: [PATCH 0693/1173] bcachefs: Fix deadlock

This fixes two deadlocks:

1.pcpu_alloc_mutex involved one as pointed by syzbot[1]
2.recursion deadlock.

The root cause is that we hold the bc lock during alloc_percpu, fix it
by following the pattern used by __btree_node_mem_alloc().

[1] https://lore.kernel.org/all/66f97d9a.050a0220.6bad9.001d.GAE@google.com/T/

Reported-by: syzbot+fe63f377148a6371a9db@syzkaller.appspotmail.com
Tested-by: syzbot+fe63f377148a6371a9db@syzkaller.appspotmail.com
Signed-off-by: Alan Huang <mmpgouride@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_cache.c     | 9 +++++----
 fs/bcachefs/btree_key_cache.c | 2 +-
 fs/bcachefs/btree_locking.c   | 5 +++--
 fs/bcachefs/btree_locking.h   | 2 +-
 fs/bcachefs/six.c             | 5 +++--
 fs/bcachefs/six.h             | 7 ++++---
 6 files changed, 17 insertions(+), 13 deletions(-)

diff --git a/fs/bcachefs/btree_cache.c b/fs/bcachefs/btree_cache.c
index ca755e8d1a372..1ec1f90e0eb38 100644
--- a/fs/bcachefs/btree_cache.c
+++ b/fs/bcachefs/btree_cache.c
@@ -203,7 +203,7 @@ struct btree *__bch2_btree_node_mem_alloc(struct bch_fs *c)
 		return NULL;
 	}
 
-	bch2_btree_lock_init(&b->c, 0);
+	bch2_btree_lock_init(&b->c, 0, GFP_KERNEL);
 
 	__bch2_btree_node_to_freelist(bc, b);
 	return b;
@@ -795,17 +795,18 @@ struct btree *bch2_btree_node_mem_alloc(struct btree_trans *trans, bool pcpu_rea
 		}
 
 	b = __btree_node_mem_alloc(c, GFP_NOWAIT|__GFP_NOWARN);
-	if (!b) {
+	if (b) {
+		bch2_btree_lock_init(&b->c, pcpu_read_locks ? SIX_LOCK_INIT_PCPU : 0, GFP_NOWAIT);
+	} else {
 		mutex_unlock(&bc->lock);
 		bch2_trans_unlock(trans);
 		b = __btree_node_mem_alloc(c, GFP_KERNEL);
 		if (!b)
 			goto err;
+		bch2_btree_lock_init(&b->c, pcpu_read_locks ? SIX_LOCK_INIT_PCPU : 0, GFP_KERNEL);
 		mutex_lock(&bc->lock);
 	}
 
-	bch2_btree_lock_init(&b->c, pcpu_read_locks ? SIX_LOCK_INIT_PCPU : 0);
-
 	BUG_ON(!six_trylock_intent(&b->c.lock));
 	BUG_ON(!six_trylock_write(&b->c.lock));
 
diff --git a/fs/bcachefs/btree_key_cache.c b/fs/bcachefs/btree_key_cache.c
index 1821f40c161a1..edce594333756 100644
--- a/fs/bcachefs/btree_key_cache.c
+++ b/fs/bcachefs/btree_key_cache.c
@@ -156,7 +156,7 @@ bkey_cached_alloc(struct btree_trans *trans, struct btree_path *path, unsigned k
 	}
 
 	if (ck) {
-		bch2_btree_lock_init(&ck->c, pcpu_readers ? SIX_LOCK_INIT_PCPU : 0);
+		bch2_btree_lock_init(&ck->c, pcpu_readers ? SIX_LOCK_INIT_PCPU : 0, GFP_KERNEL);
 		ck->c.cached = true;
 		goto lock;
 	}
diff --git a/fs/bcachefs/btree_locking.c b/fs/bcachefs/btree_locking.c
index 10b805a60f526..caef65adeae49 100644
--- a/fs/bcachefs/btree_locking.c
+++ b/fs/bcachefs/btree_locking.c
@@ -7,9 +7,10 @@
 static struct lock_class_key bch2_btree_node_lock_key;
 
 void bch2_btree_lock_init(struct btree_bkey_cached_common *b,
-			  enum six_lock_init_flags flags)
+			  enum six_lock_init_flags flags,
+			  gfp_t gfp)
 {
-	__six_lock_init(&b->lock, "b->c.lock", &bch2_btree_node_lock_key, flags);
+	__six_lock_init(&b->lock, "b->c.lock", &bch2_btree_node_lock_key, flags, gfp);
 	lockdep_set_notrack_class(&b->lock);
 }
 
diff --git a/fs/bcachefs/btree_locking.h b/fs/bcachefs/btree_locking.h
index b54ef48eb8cc2..b33ab7af84402 100644
--- a/fs/bcachefs/btree_locking.h
+++ b/fs/bcachefs/btree_locking.h
@@ -13,7 +13,7 @@
 #include "btree_iter.h"
 #include "six.h"
 
-void bch2_btree_lock_init(struct btree_bkey_cached_common *, enum six_lock_init_flags);
+void bch2_btree_lock_init(struct btree_bkey_cached_common *, enum six_lock_init_flags, gfp_t gfp);
 
 void bch2_trans_unlock_noassert(struct btree_trans *);
 void bch2_trans_unlock_write(struct btree_trans *);
diff --git a/fs/bcachefs/six.c b/fs/bcachefs/six.c
index 7e7c66a1e1a6b..7c403427fbdb8 100644
--- a/fs/bcachefs/six.c
+++ b/fs/bcachefs/six.c
@@ -850,7 +850,8 @@ void six_lock_exit(struct six_lock *lock)
 EXPORT_SYMBOL_GPL(six_lock_exit);
 
 void __six_lock_init(struct six_lock *lock, const char *name,
-		     struct lock_class_key *key, enum six_lock_init_flags flags)
+		     struct lock_class_key *key, enum six_lock_init_flags flags,
+		     gfp_t gfp)
 {
 	atomic_set(&lock->state, 0);
 	raw_spin_lock_init(&lock->wait_lock);
@@ -873,7 +874,7 @@ void __six_lock_init(struct six_lock *lock, const char *name,
 		 * failure if they wish by checking lock->readers, but generally
 		 * will not want to treat it as an error.
 		 */
-		lock->readers = alloc_percpu(unsigned);
+		lock->readers = alloc_percpu_gfp(unsigned, gfp);
 	}
 #endif
 }
diff --git a/fs/bcachefs/six.h b/fs/bcachefs/six.h
index c142e06b7a3a7..59b851cf8bacc 100644
--- a/fs/bcachefs/six.h
+++ b/fs/bcachefs/six.h
@@ -164,18 +164,19 @@ enum six_lock_init_flags {
 };
 
 void __six_lock_init(struct six_lock *lock, const char *name,
-		     struct lock_class_key *key, enum six_lock_init_flags flags);
+		     struct lock_class_key *key, enum six_lock_init_flags flags,
+		     gfp_t gfp);
 
 /**
  * six_lock_init - initialize a six lock
  * @lock:	lock to initialize
  * @flags:	optional flags, i.e. SIX_LOCK_INIT_PCPU
  */
-#define six_lock_init(lock, flags)					\
+#define six_lock_init(lock, flags, gfp)					\
 do {									\
 	static struct lock_class_key __key;				\
 									\
-	__six_lock_init((lock), #lock, &__key, flags);			\
+	__six_lock_init((lock), #lock, &__key, flags, gfp);			\
 } while (0)
 
 /**

From eb54d2695b57426638fed0ec066ae17a18c4426c Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Wed, 26 Feb 2025 10:57:26 -0500
Subject: [PATCH 0694/1173] bcachefs: Fix truncate sometimes failing and
 returning 1

__bch_truncate_folio() may return 1 to indicate dirtyness of the folio
being truncated, needed for fpunch to get the i_size writes correct.

But truncate was forgetting to clear ret, and sometimes returning it as
an error.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/fs-io.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/bcachefs/fs-io.c b/fs/bcachefs/fs-io.c
index 94bf34b9b65f0..717e7b94c66f8 100644
--- a/fs/bcachefs/fs-io.c
+++ b/fs/bcachefs/fs-io.c
@@ -466,6 +466,7 @@ int bchfs_truncate(struct mnt_idmap *idmap,
 	ret = bch2_truncate_folio(inode, iattr->ia_size);
 	if (unlikely(ret < 0))
 		goto err;
+	ret = 0;
 
 	truncate_setsize(&inode->v, iattr->ia_size);
 

From 01c9c123db76357d4373b2e97b760a856d6fe822 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Tue, 25 Feb 2025 13:10:23 -0800
Subject: [PATCH 0695/1173] net: Use rtnl_net_dev_lock() in
 register_netdevice_notifier_dev_net().

Breno Leitao reported the splat below. [0]

Commit 65161fb544aa ("net: Fix dev_net(dev) race in
unregister_netdevice_notifier_dev_net().") added the
DEBUG_NET_WARN_ON_ONCE(), assuming that the netdev is not
registered before register_netdevice_notifier_dev_net().

But the assumption was simply wrong.

Let's use rtnl_net_dev_lock() in register_netdevice_notifier_dev_net().

[0]:
WARNING: CPU: 25 PID: 849 at net/core/dev.c:2150 register_netdevice_notifier_dev_net (net/core/dev.c:2150)
 <TASK>
 ? __warn (kernel/panic.c:242 kernel/panic.c:748)
 ? register_netdevice_notifier_dev_net (net/core/dev.c:2150)
 ? register_netdevice_notifier_dev_net (net/core/dev.c:2150)
 ? report_bug (lib/bug.c:? lib/bug.c:219)
 ? handle_bug (arch/x86/kernel/traps.c:285)
 ? exc_invalid_op (arch/x86/kernel/traps.c:309)
 ? asm_exc_invalid_op (./arch/x86/include/asm/idtentry.h:621)
 ? register_netdevice_notifier_dev_net (net/core/dev.c:2150)
 ? register_netdevice_notifier_dev_net (./include/net/net_namespace.h:406 ./include/linux/netdevice.h:2663 net/core/dev.c:2144)
 mlx5e_mdev_notifier_event+0x9f/0xf0 mlx5_ib
 notifier_call_chain.llvm.12241336988804114627 (kernel/notifier.c:85)
 blocking_notifier_call_chain (kernel/notifier.c:380)
 mlx5_core_uplink_netdev_event_replay (drivers/net/ethernet/mellanox/mlx5/core/main.c:352)
 mlx5_ib_roce_init.llvm.12447516292400117075+0x1c6/0x550 mlx5_ib
 mlx5r_probe+0x375/0x6a0 mlx5_ib
 ? kernfs_put (./include/linux/instrumented.h:96 ./include/linux/atomic/atomic-arch-fallback.h:2278 ./include/linux/atomic/atomic-instrumented.h:1384 fs/kernfs/dir.c:557)
 ? auxiliary_match_id (drivers/base/auxiliary.c:174)
 ? mlx5r_mp_remove+0x160/0x160 mlx5_ib
 really_probe (drivers/base/dd.c:? drivers/base/dd.c:658)
 driver_probe_device (drivers/base/dd.c:830)
 __driver_attach (drivers/base/dd.c:1217)
 bus_for_each_dev (drivers/base/bus.c:369)
 ? driver_attach (drivers/base/dd.c:1157)
 bus_add_driver (drivers/base/bus.c:679)
 driver_register (drivers/base/driver.c:249)

Fixes: 7fb1073300a2 ("net: Hold rtnl_net_lock() in (un)?register_netdevice_notifier_dev_net().")
Reported-by: Breno Leitao <leitao@debian.org>
Closes: https://lore.kernel.org/netdev/20250224-noisy-cordial-roadrunner-fad40c@leitao/
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Tested-by: Breno Leitao <leitao@debian.org>
Link: https://patch.msgid.link/20250225211023.96448-1-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/dev.c | 12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 1b252e9459fdb..70c01bd1799e5 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2141,21 +2141,15 @@ int register_netdevice_notifier_dev_net(struct net_device *dev,
 					struct notifier_block *nb,
 					struct netdev_net_notifier *nn)
 {
-	struct net *net = dev_net(dev);
 	int err;
 
-	/* rtnl_net_lock() assumes dev is not yet published by
-	 * register_netdevice().
-	 */
-	DEBUG_NET_WARN_ON_ONCE(!list_empty(&dev->dev_list));
-
-	rtnl_net_lock(net);
-	err = __register_netdevice_notifier_net(net, nb, false);
+	rtnl_net_dev_lock(dev);
+	err = __register_netdevice_notifier_net(dev_net(dev), nb, false);
 	if (!err) {
 		nn->nb = nb;
 		list_add(&nn->list, &dev->net_notifier_list);
 	}
-	rtnl_net_unlock(net);
+	rtnl_net_dev_unlock(dev);
 
 	return err;
 }

From de70981f295e7eab86325db3bf349fa676f16c42 Mon Sep 17 00:00:00 2001
From: Harshitha Ramamurthy <hramamurthy@google.com>
Date: Wed, 26 Feb 2025 00:35:26 +0000
Subject: [PATCH 0696/1173] gve: unlink old napi when stopping a queue using
 queue API

When a queue is stopped using the ndo queue API, before
destroying its page pool, the associated NAPI instance
needs to be unlinked to avoid warnings.

Handle this by calling page_pool_disable_direct_recycling()
when stopping a queue.

Cc: stable@vger.kernel.org
Fixes: ebdfae0d377b ("gve: adopt page pool for DQ RDA mode")
Reviewed-by: Praveen Kaligineedi <pkaligineedi@google.com>
Signed-off-by: Harshitha Ramamurthy <hramamurthy@google.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20250226003526.1546854-1-hramamurthy@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/google/gve/gve_rx_dqo.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
index 8ac0047f1ada1..f0674a4435670 100644
--- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
@@ -109,10 +109,12 @@ static void gve_rx_reset_ring_dqo(struct gve_priv *priv, int idx)
 void gve_rx_stop_ring_dqo(struct gve_priv *priv, int idx)
 {
 	int ntfy_idx = gve_rx_idx_to_ntfy(priv, idx);
+	struct gve_rx_ring *rx = &priv->rx[idx];
 
 	if (!gve_rx_was_added_to_block(priv, idx))
 		return;
 
+	page_pool_disable_direct_recycling(rx->dqo.page_pool);
 	gve_remove_napi(priv, ntfy_idx);
 	gve_rx_remove_from_block(priv, idx);
 	gve_rx_reset_ring_dqo(priv, idx);

From 49806fe6e61b045b5be8610e08b5a3083c109aa0 Mon Sep 17 00:00:00 2001
From: Mohammad Heib <mheib@redhat.com>
Date: Tue, 25 Feb 2025 13:28:52 +0200
Subject: [PATCH 0697/1173] net: Clear old fragment checksum value in
 napi_reuse_skb

In certain cases, napi_get_frags() returns an skb that points to an old
received fragment, This skb may have its skb->ip_summed, csum, and other
fields set from previous fragment handling.

Some network drivers set skb->ip_summed to either CHECKSUM_COMPLETE or
CHECKSUM_UNNECESSARY when getting skb from napi_get_frags(), while
others only set skb->ip_summed when RX checksum offload is enabled on
the device, and do not set any value for skb->ip_summed when hardware
checksum offload is disabled, assuming that the skb->ip_summed
initiated to zero by napi_reuse_skb, ionic driver for example will
ignore/unset any value for the ip_summed filed if HW checksum offload is
disabled, and if we have a situation where the user disables the
checksum offload during a traffic that could lead to the following
errors shown in the kernel logs:
<IRQ>
dump_stack_lvl+0x34/0x48
 __skb_gro_checksum_complete+0x7e/0x90
tcp6_gro_receive+0xc6/0x190
ipv6_gro_receive+0x1ec/0x430
dev_gro_receive+0x188/0x360
? ionic_rx_clean+0x25a/0x460 [ionic]
napi_gro_frags+0x13c/0x300
? __pfx_ionic_rx_service+0x10/0x10 [ionic]
ionic_rx_service+0x67/0x80 [ionic]
ionic_cq_service+0x58/0x90 [ionic]
ionic_txrx_napi+0x64/0x1b0 [ionic]
 __napi_poll+0x27/0x170
net_rx_action+0x29c/0x370
handle_softirqs+0xce/0x270
__irq_exit_rcu+0xa3/0xc0
common_interrupt+0x80/0xa0
</IRQ>

This inconsistency sometimes leads to checksum validation issues in the
upper layers of the network stack.

To resolve this, this patch clears the skb->ip_summed value for each
reused skb in by napi_reuse_skb(), ensuring that the caller is responsible
for setting the correct checksum status. This eliminates potential
checksum validation issues caused by improper handling of
skb->ip_summed.

Fixes: 76620aafd66f ("gro: New frags interface to avoid copying shinfo")
Signed-off-by: Mohammad Heib <mheib@redhat.com>
Reviewed-by: Shannon Nelson <shannon.nelson@amd.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250225112852.2507709-1-mheib@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/gro.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/core/gro.c b/net/core/gro.c
index 78b320b631744..0ad549b07e039 100644
--- a/net/core/gro.c
+++ b/net/core/gro.c
@@ -653,6 +653,7 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
 	skb->pkt_type = PACKET_HOST;
 
 	skb->encapsulation = 0;
+	skb->ip_summed = CHECKSUM_NONE;
 	skb_shinfo(skb)->gso_type = 0;
 	skb_shinfo(skb)->gso_size = 0;
 	if (unlikely(skb->slow_gro)) {

From 77e45145e3039a0fb212556ab3f8c87f54771757 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <frederic@kernel.org>
Date: Sun, 23 Feb 2025 23:17:08 +0100
Subject: [PATCH 0698/1173] net: Handle napi_schedule() calls from
 non-interrupt

napi_schedule() is expected to be called either:

* From an interrupt, where raised softirqs are handled on IRQ exit

* From a softirq disabled section, where raised softirqs are handled on
  the next call to local_bh_enable().

* From a softirq handler, where raised softirqs are handled on the next
  round in do_softirq(), or further deferred to a dedicated kthread.

Other bare tasks context may end up ignoring the raised NET_RX vector
until the next random softirq handling opportunity, which may not
happen before a while if the CPU goes idle afterwards with the tick
stopped.

Such "misuses" have been detected on several places thanks to messages
of the kind:

	"NOHZ tick-stop error: local softirq work is pending, handler #08!!!"

For example:

       __raise_softirq_irqoff
        __napi_schedule
        rtl8152_runtime_resume.isra.0
        rtl8152_resume
        usb_resume_interface.isra.0
        usb_resume_both
        __rpm_callback
        rpm_callback
        rpm_resume
        __pm_runtime_resume
        usb_autoresume_device
        usb_remote_wakeup
        hub_event
        process_one_work
        worker_thread
        kthread
        ret_from_fork
        ret_from_fork_asm

And also:

* drivers/net/usb/r8152.c::rtl_work_func_t
* drivers/net/netdevsim/netdev.c::nsim_start_xmit

There is a long history of issues of this kind:

	019edd01d174 ("ath10k: sdio: Add missing BH locking around napi_schdule()")
	330068589389 ("idpf: disable local BH when scheduling napi for marker packets")
	e3d5d70cb483 ("net: lan78xx: fix "softirq work is pending" error")
	e55c27ed9ccf ("mt76: mt7615: add missing bh-disable around rx napi schedule")
	c0182aa98570 ("mt76: mt7915: add missing bh-disable around tx napi enable/schedule")
	970be1dff26d ("mt76: disable BH around napi_schedule() calls")
	019edd01d174 ("ath10k: sdio: Add missing BH locking around napi_schdule()")
	30bfec4fec59 ("can: rx-offload: can_rx_offload_threaded_irq_finish(): add new  function to be called from threaded interrupt")
	e63052a5dd3c ("mlx5e: add add missing BH locking around napi_schdule()")
	83a0c6e58901 ("i40e: Invoke softirqs after napi_reschedule")
	bd4ce941c8d5 ("mlx4: Invoke softirqs after napi_reschedule")
	8cf699ec849f ("mlx4: do not call napi_schedule() without care")
	ec13ee80145c ("virtio_net: invoke softirqs after __napi_schedule")

This shows that relying on the caller to arrange a proper context for
the softirqs to be handled while calling napi_schedule() is very fragile
and error prone. Also fixing them can also prove challenging if the
caller may be called from different kinds of contexts.

Therefore fix this from napi_schedule() itself with waking up ksoftirqd
when softirqs are raised from task contexts.

Reported-by: Paul Menzel <pmenzel@molgen.mpg.de>
Reported-by: Jakub Kicinski <kuba@kernel.org>
Reported-by: Francois Romieu <romieu@fr.zoreil.com>
Closes: https://lore.kernel.org/lkml/354a2690-9bbf-4ccb-8769-fa94707a9340@molgen.mpg.de/
Cc: Breno Leitao <leitao@debian.org>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250223221708.27130-1-frederic@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 70c01bd1799e5..30da277c5a6f8 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4757,7 +4757,7 @@ static inline void ____napi_schedule(struct softnet_data *sd,
 	 * we have to raise NET_RX_SOFTIRQ.
 	 */
 	if (!sd->in_net_rx_action)
-		__raise_softirq_irqoff(NET_RX_SOFTIRQ);
+		raise_softirq_irqoff(NET_RX_SOFTIRQ);
 }
 
 #ifdef CONFIG_RPS

From bc23d4e30866011700787bab8563de45d5bf8431 Mon Sep 17 00:00:00 2001
From: Adrian Huang <ahuang12@lenovo.com>
Date: Tue, 25 Feb 2025 10:14:57 +0800
Subject: [PATCH 0699/1173] af_unix: Fix memory leak in unix_dgram_sendmsg()

After running the 'sendmsg02' program of Linux Test Project (LTP),
kmemleak reports the following memory leak:

  # cat /sys/kernel/debug/kmemleak
  unreferenced object 0xffff888243866800 (size 2048):
    comm "sendmsg02", pid 67, jiffies 4294903166
    hex dump (first 32 bytes):
      00 00 00 00 00 00 00 00 5e 00 00 00 00 00 00 00  ........^.......
      01 00 07 40 00 00 00 00 00 00 00 00 00 00 00 00  ...@............
    backtrace (crc 7e96a3f2):
      kmemleak_alloc+0x56/0x90
      kmem_cache_alloc_noprof+0x209/0x450
      sk_prot_alloc.constprop.0+0x60/0x160
      sk_alloc+0x32/0xc0
      unix_create1+0x67/0x2b0
      unix_create+0x47/0xa0
      __sock_create+0x12e/0x200
      __sys_socket+0x6d/0x100
      __x64_sys_socket+0x1b/0x30
      x64_sys_call+0x7e1/0x2140
      do_syscall_64+0x54/0x110
      entry_SYSCALL_64_after_hwframe+0x76/0x7e

Commit 689c398885cc ("af_unix: Defer sock_put() to clean up path in
unix_dgram_sendmsg().") defers sock_put() in the error handling path.
However, it fails to account for the condition 'msg->msg_namelen != 0',
resulting in a memory leak when the code jumps to the 'lookup' label.

Fix issue by calling sock_put() if 'msg->msg_namelen != 0' is met.

Fixes: 689c398885cc ("af_unix: Defer sock_put() to clean up path in unix_dgram_sendmsg().")
Signed-off-by: Adrian Huang <ahuang12@lenovo.com>
Acked-by: Joe Damato <jdamato@fastly.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250225021457.1824-1-ahuang12@lenovo.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/unix/af_unix.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 34945de1fb1fa..f0e613d976640 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2102,6 +2102,7 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 			goto out_sock_put;
 		}
 
+		sock_put(other);
 		goto lookup;
 	}
 

From 2d253726ff7106b39a44483b6864398bba8a2f74 Mon Sep 17 00:00:00 2001
From: Harshal Chaudhari <hchaudhari@marvell.com>
Date: Mon, 24 Feb 2025 20:20:58 -0800
Subject: [PATCH 0700/1173] net: mvpp2: cls: Fixed Non IP flow, with vlan tag
 flow defination.

Non IP flow, with vlan tag not working as expected while
running below command for vlan-priority. fixed that.

ethtool -N eth1 flow-type ether vlan 0x8000 vlan-mask 0x1fff action 0 loc 0

Fixes: 1274daede3ef ("net: mvpp2: cls: Add steering based on vlan Id and priority.")
Signed-off-by: Harshal Chaudhari <hchaudhari@marvell.com>
Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Link: https://patch.msgid.link/20250225042058.2643838-1-hchaudhari@marvell.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
index 1641791a2d5b4..8ed83fb988624 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
@@ -324,7 +324,7 @@ static const struct mvpp2_cls_flow cls_flows[MVPP2_N_PRS_FLOWS] = {
 		       MVPP2_PRS_RI_VLAN_MASK),
 	/* Non IP flow, with vlan tag */
 	MVPP2_DEF_FLOW(MVPP22_FLOW_ETHERNET, MVPP2_FL_NON_IP_TAG,
-		       MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP22_CLS_HEK_TAGGED,
 		       0, 0),
 };
 

From 7f3528f7d2f98b70e19a6bb7b130fc82c079ac54 Mon Sep 17 00:00:00 2001
From: Carolina Jubran <cjubran@nvidia.com>
Date: Tue, 25 Feb 2025 09:26:06 +0200
Subject: [PATCH 0701/1173] net/mlx5: Fix vport QoS cleanup on error

When enabling vport QoS fails, the scheduling node was never freed,
causing a leak.

Add the missing free and reset the vport scheduling node pointer to
NULL.

Fixes: be034baba83e ("net/mlx5: Make vport QoS enablement more flexible for future extensions")
Signed-off-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250225072608.526866-2-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
index 8b7c843446e11..07a28073a49ea 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
@@ -591,8 +591,11 @@ static int mlx5_esw_qos_vport_enable(struct mlx5_vport *vport, enum sched_node_t
 	sched_node->vport = vport;
 	vport->qos.sched_node = sched_node;
 	err = esw_qos_vport_enable(vport, parent, extack);
-	if (err)
+	if (err) {
+		__esw_qos_free_node(sched_node);
 		esw_qos_put(esw);
+		vport->qos.sched_node = NULL;
+	}
 
 	return err;
 }

From 47bcd9bf3d231bfd4698d7d3013597490fd5e2d6 Mon Sep 17 00:00:00 2001
From: Carolina Jubran <cjubran@nvidia.com>
Date: Tue, 25 Feb 2025 09:26:07 +0200
Subject: [PATCH 0702/1173] net/mlx5: Restore missing trace event when enabling
 vport QoS

Restore the `trace_mlx5_esw_vport_qos_create` event when creating
the vport scheduling element. This trace event was lost during
refactoring.

Fixes: be034baba83e ("net/mlx5: Make vport QoS enablement more flexible for future extensions")
Signed-off-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250225072608.526866-3-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
index 07a28073a49ea..823c1ba456cd1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
@@ -564,6 +564,9 @@ static int esw_qos_vport_enable(struct mlx5_vport *vport, struct mlx5_esw_sched_
 		return err;
 
 	esw_qos_normalize_min_rate(parent->esw, parent, extack);
+	trace_mlx5_esw_vport_qos_create(vport->dev, vport,
+					vport->qos.sched_node->max_rate,
+					vport->qos.sched_node->bw_share);
 
 	return 0;
 }

From 2f5a6014eb168a97b24153adccfa663d3b282767 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Tue, 25 Feb 2025 09:26:08 +0200
Subject: [PATCH 0703/1173] net/mlx5: IRQ, Fix null string in debug print

irq_pool_alloc() debug print can print a null string.
Fix it by providing a default string to print.

Fixes: 71e084e26414 ("net/mlx5: Allocating a pool of MSI-X vectors for SFs")
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202501141055.SwfIphN0-lkp@intel.com/
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Link: https://patch.msgid.link/20250225072608.526866-4-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
index 7db9cab9bedf6..d9362eabc6a1c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
@@ -572,7 +572,7 @@ irq_pool_alloc(struct mlx5_core_dev *dev, int start, int size, char *name,
 	pool->min_threshold = min_threshold * MLX5_EQ_REFS_PER_IRQ;
 	pool->max_threshold = max_threshold * MLX5_EQ_REFS_PER_IRQ;
 	mlx5_core_dbg(dev, "pool->name = %s, pool->size = %d, pool->start = %d",
-		      name, size, start);
+		      name ? name : "mlx5_pcif_pool", size, start);
 	return pool;
 }
 

From e521f516716de7895acd1b5b7fac788214a390b9 Mon Sep 17 00:00:00 2001
From: Caleb Connolly <caleb.connolly@linaro.org>
Date: Sat, 8 Feb 2025 22:30:54 +0000
Subject: [PATCH 0704/1173] dmaengine: Revert "dmaengine: qcom: bam_dma: Avoid
 writing unavailable register"

This commit causes a hard crash on sdm845 and likely other platforms.
Revert it until a proper fix is found.

This reverts commit 57a7138d0627: ("dmaengine: qcom: bam_dma: Avoid writing
unavailable register")

Signed-off-by: Caleb Connolly <caleb.connolly@linaro.org>
Fixes: 57a7138d0627 ("dmaengine: qcom: bam_dma: Avoid writing unavailable register")
Tested-by: Neil Armstrong <neil.armstrong@linaro.org> # on sdm845-DB845c
Tested-by: David Heidelberg <david@ixit.cz>
Link: https://lore.kernel.org/r/20250208223112.142567-1-caleb.connolly@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/qcom/bam_dma.c | 24 ++++++++----------------
 1 file changed, 8 insertions(+), 16 deletions(-)

diff --git a/drivers/dma/qcom/bam_dma.c b/drivers/dma/qcom/bam_dma.c
index c14557efd5770..bbc3276992bb0 100644
--- a/drivers/dma/qcom/bam_dma.c
+++ b/drivers/dma/qcom/bam_dma.c
@@ -59,9 +59,6 @@ struct bam_desc_hw {
 #define DESC_FLAG_NWD BIT(12)
 #define DESC_FLAG_CMD BIT(11)
 
-#define BAM_NDP_REVISION_START	0x20
-#define BAM_NDP_REVISION_END	0x27
-
 struct bam_async_desc {
 	struct virt_dma_desc vd;
 
@@ -401,7 +398,6 @@ struct bam_device {
 
 	/* dma start transaction tasklet */
 	struct tasklet_struct task;
-	u32 bam_revision;
 };
 
 /**
@@ -445,10 +441,8 @@ static void bam_reset(struct bam_device *bdev)
 	writel_relaxed(val, bam_addr(bdev, 0, BAM_CTRL));
 
 	/* set descriptor threshold, start with 4 bytes */
-	if (in_range(bdev->bam_revision, BAM_NDP_REVISION_START,
-		     BAM_NDP_REVISION_END))
-		writel_relaxed(DEFAULT_CNT_THRSHLD,
-			       bam_addr(bdev, 0, BAM_DESC_CNT_TRSHLD));
+	writel_relaxed(DEFAULT_CNT_THRSHLD,
+			bam_addr(bdev, 0, BAM_DESC_CNT_TRSHLD));
 
 	/* Enable default set of h/w workarounds, ie all except BAM_FULL_PIPE */
 	writel_relaxed(BAM_CNFG_BITS_DEFAULT, bam_addr(bdev, 0, BAM_CNFG_BITS));
@@ -1006,10 +1000,9 @@ static void bam_apply_new_config(struct bam_chan *bchan,
 			maxburst = bchan->slave.src_maxburst;
 		else
 			maxburst = bchan->slave.dst_maxburst;
-		if (in_range(bdev->bam_revision, BAM_NDP_REVISION_START,
-			     BAM_NDP_REVISION_END))
-			writel_relaxed(maxburst,
-				       bam_addr(bdev, 0, BAM_DESC_CNT_TRSHLD));
+
+		writel_relaxed(maxburst,
+			       bam_addr(bdev, 0, BAM_DESC_CNT_TRSHLD));
 	}
 
 	bchan->reconfigure = 0;
@@ -1199,11 +1192,10 @@ static int bam_init(struct bam_device *bdev)
 	u32 val;
 
 	/* read revision and configuration information */
-	val = readl_relaxed(bam_addr(bdev, 0, BAM_REVISION));
-	if (!bdev->num_ees)
+	if (!bdev->num_ees) {
+		val = readl_relaxed(bam_addr(bdev, 0, BAM_REVISION));
 		bdev->num_ees = (val >> NUM_EES_SHIFT) & NUM_EES_MASK;
-
-	bdev->bam_revision = val & REVISION_MASK;
+	}
 
 	/* check that configured EE is within range */
 	if (bdev->ee >= bdev->num_ees)

From 3603996432997f7c88da37a97062a46cda01ac9d Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Wed, 11 Dec 2024 10:06:28 +0100
Subject: [PATCH 0705/1173] drm/fbdev-dma: Add shadow buffering for deferred
 I/O
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

DMA areas are not necessarily backed by struct page, so we cannot
rely on it for deferred I/O. Allocate a shadow buffer for drivers
that require deferred I/O and use it as framebuffer memory.

Fixes driver errors about being "Unable to handle kernel NULL pointer
dereference at virtual address" or "Unable to handle kernel paging
request at virtual address".

The patch splits drm_fbdev_dma_driver_fbdev_probe() in an initial
allocation, which creates the DMA-backed buffer object, and a tail
that sets up the fbdev data structures. There is a tail function for
direct memory mappings and a tail function for deferred I/O with
the shadow buffer.

It is no longer possible to use deferred I/O without shadow buffer.
It can be re-added if there exists a reliably test for usable struct
page in the allocated DMA-backed buffer object.

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Reported-by: Nuno Gonçalves <nunojpg@gmail.com>
CLoses: https://lore.kernel.org/dri-devel/CAEXMXLR55DziAMbv_+2hmLeH-jP96pmit6nhs6siB22cpQFr9w@mail.gmail.com/
Tested-by: Nuno Gonçalves <nunojpg@gmail.com>
Fixes: 5ab91447aa13 ("drm/tiny/ili9225: Use fbdev-dma")
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Cc: <stable@vger.kernel.org> # v6.11+
Reviewed-by: Simona Vetter <simona.vetter@ffwll.ch>
Reviewed-by: Javier Martinez Canillas <javierm@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241211090643.74250-1-tzimmermann@suse.de
---
 drivers/gpu/drm/drm_fbdev_dma.c | 217 +++++++++++++++++++++++---------
 1 file changed, 155 insertions(+), 62 deletions(-)

diff --git a/drivers/gpu/drm/drm_fbdev_dma.c b/drivers/gpu/drm/drm_fbdev_dma.c
index b14b581c059d3..02a516e771927 100644
--- a/drivers/gpu/drm/drm_fbdev_dma.c
+++ b/drivers/gpu/drm/drm_fbdev_dma.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: MIT
 
 #include <linux/fb.h>
+#include <linux/vmalloc.h>
 
 #include <drm/drm_drv.h>
 #include <drm/drm_fbdev_dma.h>
@@ -70,37 +71,102 @@ static const struct fb_ops drm_fbdev_dma_fb_ops = {
 	.fb_destroy = drm_fbdev_dma_fb_destroy,
 };
 
-FB_GEN_DEFAULT_DEFERRED_DMAMEM_OPS(drm_fbdev_dma,
+FB_GEN_DEFAULT_DEFERRED_DMAMEM_OPS(drm_fbdev_dma_shadowed,
 				   drm_fb_helper_damage_range,
 				   drm_fb_helper_damage_area);
 
-static int drm_fbdev_dma_deferred_fb_mmap(struct fb_info *info, struct vm_area_struct *vma)
+static void drm_fbdev_dma_shadowed_fb_destroy(struct fb_info *info)
 {
 	struct drm_fb_helper *fb_helper = info->par;
-	struct drm_framebuffer *fb = fb_helper->fb;
-	struct drm_gem_dma_object *dma = drm_fb_dma_get_gem_obj(fb, 0);
+	void *shadow = info->screen_buffer;
+
+	if (!fb_helper->dev)
+		return;
 
-	if (!dma->map_noncoherent)
-		vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
+	if (info->fbdefio)
+		fb_deferred_io_cleanup(info);
+	drm_fb_helper_fini(fb_helper);
+	vfree(shadow);
 
-	return fb_deferred_io_mmap(info, vma);
+	drm_client_buffer_vunmap(fb_helper->buffer);
+	drm_client_framebuffer_delete(fb_helper->buffer);
+	drm_client_release(&fb_helper->client);
+	drm_fb_helper_unprepare(fb_helper);
+	kfree(fb_helper);
 }
 
-static const struct fb_ops drm_fbdev_dma_deferred_fb_ops = {
+static const struct fb_ops drm_fbdev_dma_shadowed_fb_ops = {
 	.owner = THIS_MODULE,
 	.fb_open = drm_fbdev_dma_fb_open,
 	.fb_release = drm_fbdev_dma_fb_release,
-	__FB_DEFAULT_DEFERRED_OPS_RDWR(drm_fbdev_dma),
+	FB_DEFAULT_DEFERRED_OPS(drm_fbdev_dma_shadowed),
 	DRM_FB_HELPER_DEFAULT_OPS,
-	__FB_DEFAULT_DEFERRED_OPS_DRAW(drm_fbdev_dma),
-	.fb_mmap = drm_fbdev_dma_deferred_fb_mmap,
-	.fb_destroy = drm_fbdev_dma_fb_destroy,
+	.fb_destroy = drm_fbdev_dma_shadowed_fb_destroy,
 };
 
 /*
  * struct drm_fb_helper
  */
 
+static void drm_fbdev_dma_damage_blit_real(struct drm_fb_helper *fb_helper,
+					   struct drm_clip_rect *clip,
+					   struct iosys_map *dst)
+{
+	struct drm_framebuffer *fb = fb_helper->fb;
+	size_t offset = clip->y1 * fb->pitches[0];
+	size_t len = clip->x2 - clip->x1;
+	unsigned int y;
+	void *src;
+
+	switch (drm_format_info_bpp(fb->format, 0)) {
+	case 1:
+		offset += clip->x1 / 8;
+		len = DIV_ROUND_UP(len + clip->x1 % 8, 8);
+		break;
+	case 2:
+		offset += clip->x1 / 4;
+		len = DIV_ROUND_UP(len + clip->x1 % 4, 4);
+		break;
+	case 4:
+		offset += clip->x1 / 2;
+		len = DIV_ROUND_UP(len + clip->x1 % 2, 2);
+		break;
+	default:
+		offset += clip->x1 * fb->format->cpp[0];
+		len *= fb->format->cpp[0];
+		break;
+	}
+
+	src = fb_helper->info->screen_buffer + offset;
+	iosys_map_incr(dst, offset); /* go to first pixel within clip rect */
+
+	for (y = clip->y1; y < clip->y2; y++) {
+		iosys_map_memcpy_to(dst, 0, src, len);
+		iosys_map_incr(dst, fb->pitches[0]);
+		src += fb->pitches[0];
+	}
+}
+
+static int drm_fbdev_dma_damage_blit(struct drm_fb_helper *fb_helper,
+				     struct drm_clip_rect *clip)
+{
+	struct drm_client_buffer *buffer = fb_helper->buffer;
+	struct iosys_map dst;
+
+	/*
+	 * For fbdev emulation, we only have to protect against fbdev modeset
+	 * operations. Nothing else will involve the client buffer's BO. So it
+	 * is sufficient to acquire struct drm_fb_helper.lock here.
+	 */
+	mutex_lock(&fb_helper->lock);
+
+	dst = buffer->map;
+	drm_fbdev_dma_damage_blit_real(fb_helper, clip, &dst);
+
+	mutex_unlock(&fb_helper->lock);
+
+	return 0;
+}
 static int drm_fbdev_dma_helper_fb_dirty(struct drm_fb_helper *helper,
 					 struct drm_clip_rect *clip)
 {
@@ -112,6 +178,10 @@ static int drm_fbdev_dma_helper_fb_dirty(struct drm_fb_helper *helper,
 		return 0;
 
 	if (helper->fb->funcs->dirty) {
+		ret = drm_fbdev_dma_damage_blit(helper, clip);
+		if (drm_WARN_ONCE(dev, ret, "Damage blitter failed: ret=%d\n", ret))
+			return ret;
+
 		ret = helper->fb->funcs->dirty(helper->fb, NULL, 0, 0, clip, 1);
 		if (drm_WARN_ONCE(dev, ret, "Dirty helper failed: ret=%d\n", ret))
 			return ret;
@@ -128,14 +198,80 @@ static const struct drm_fb_helper_funcs drm_fbdev_dma_helper_funcs = {
  * struct drm_fb_helper
  */
 
+static int drm_fbdev_dma_driver_fbdev_probe_tail(struct drm_fb_helper *fb_helper,
+						 struct drm_fb_helper_surface_size *sizes)
+{
+	struct drm_device *dev = fb_helper->dev;
+	struct drm_client_buffer *buffer = fb_helper->buffer;
+	struct drm_gem_dma_object *dma_obj = to_drm_gem_dma_obj(buffer->gem);
+	struct drm_framebuffer *fb = fb_helper->fb;
+	struct fb_info *info = fb_helper->info;
+	struct iosys_map map = buffer->map;
+
+	info->fbops = &drm_fbdev_dma_fb_ops;
+
+	/* screen */
+	info->flags |= FBINFO_VIRTFB; /* system memory */
+	if (dma_obj->map_noncoherent)
+		info->flags |= FBINFO_READS_FAST; /* signal caching */
+	info->screen_size = sizes->surface_height * fb->pitches[0];
+	info->screen_buffer = map.vaddr;
+	if (!(info->flags & FBINFO_HIDE_SMEM_START)) {
+		if (!drm_WARN_ON(dev, is_vmalloc_addr(info->screen_buffer)))
+			info->fix.smem_start = page_to_phys(virt_to_page(info->screen_buffer));
+	}
+	info->fix.smem_len = info->screen_size;
+
+	return 0;
+}
+
+static int drm_fbdev_dma_driver_fbdev_probe_tail_shadowed(struct drm_fb_helper *fb_helper,
+							  struct drm_fb_helper_surface_size *sizes)
+{
+	struct drm_client_buffer *buffer = fb_helper->buffer;
+	struct fb_info *info = fb_helper->info;
+	size_t screen_size = buffer->gem->size;
+	void *screen_buffer;
+	int ret;
+
+	/*
+	 * Deferred I/O requires struct page for framebuffer memory,
+	 * which is not guaranteed for all DMA ranges. We thus create
+	 * a shadow buffer in system memory.
+	 */
+	screen_buffer = vzalloc(screen_size);
+	if (!screen_buffer)
+		return -ENOMEM;
+
+	info->fbops = &drm_fbdev_dma_shadowed_fb_ops;
+
+	/* screen */
+	info->flags |= FBINFO_VIRTFB; /* system memory */
+	info->flags |= FBINFO_READS_FAST; /* signal caching */
+	info->screen_buffer = screen_buffer;
+	info->fix.smem_len = screen_size;
+
+	fb_helper->fbdefio.delay = HZ / 20;
+	fb_helper->fbdefio.deferred_io = drm_fb_helper_deferred_io;
+
+	info->fbdefio = &fb_helper->fbdefio;
+	ret = fb_deferred_io_init(info);
+	if (ret)
+		goto err_vfree;
+
+	return 0;
+
+err_vfree:
+	vfree(screen_buffer);
+	return ret;
+}
+
 int drm_fbdev_dma_driver_fbdev_probe(struct drm_fb_helper *fb_helper,
 				     struct drm_fb_helper_surface_size *sizes)
 {
 	struct drm_client_dev *client = &fb_helper->client;
 	struct drm_device *dev = fb_helper->dev;
-	bool use_deferred_io = false;
 	struct drm_client_buffer *buffer;
-	struct drm_gem_dma_object *dma_obj;
 	struct drm_framebuffer *fb;
 	struct fb_info *info;
 	u32 format;
@@ -152,19 +288,9 @@ int drm_fbdev_dma_driver_fbdev_probe(struct drm_fb_helper *fb_helper,
 					       sizes->surface_height, format);
 	if (IS_ERR(buffer))
 		return PTR_ERR(buffer);
-	dma_obj = to_drm_gem_dma_obj(buffer->gem);
 
 	fb = buffer->fb;
 
-	/*
-	 * Deferred I/O requires struct page for framebuffer memory,
-	 * which is not guaranteed for all DMA ranges. We thus only
-	 * install deferred I/O if we have a framebuffer that requires
-	 * it.
-	 */
-	if (fb->funcs->dirty)
-		use_deferred_io = true;
-
 	ret = drm_client_buffer_vmap(buffer, &map);
 	if (ret) {
 		goto err_drm_client_buffer_delete;
@@ -185,45 +311,12 @@ int drm_fbdev_dma_driver_fbdev_probe(struct drm_fb_helper *fb_helper,
 
 	drm_fb_helper_fill_info(info, fb_helper, sizes);
 
-	if (use_deferred_io)
-		info->fbops = &drm_fbdev_dma_deferred_fb_ops;
+	if (fb->funcs->dirty)
+		ret = drm_fbdev_dma_driver_fbdev_probe_tail_shadowed(fb_helper, sizes);
 	else
-		info->fbops = &drm_fbdev_dma_fb_ops;
-
-	/* screen */
-	info->flags |= FBINFO_VIRTFB; /* system memory */
-	if (dma_obj->map_noncoherent)
-		info->flags |= FBINFO_READS_FAST; /* signal caching */
-	info->screen_size = sizes->surface_height * fb->pitches[0];
-	info->screen_buffer = map.vaddr;
-	if (!(info->flags & FBINFO_HIDE_SMEM_START)) {
-		if (!drm_WARN_ON(dev, is_vmalloc_addr(info->screen_buffer)))
-			info->fix.smem_start = page_to_phys(virt_to_page(info->screen_buffer));
-	}
-	info->fix.smem_len = info->screen_size;
-
-	/*
-	 * Only set up deferred I/O if the screen buffer supports
-	 * it. If this disagrees with the previous test for ->dirty,
-	 * mmap on the /dev/fb file might not work correctly.
-	 */
-	if (!is_vmalloc_addr(info->screen_buffer) && info->fix.smem_start) {
-		unsigned long pfn = info->fix.smem_start >> PAGE_SHIFT;
-
-		if (drm_WARN_ON(dev, !pfn_to_page(pfn)))
-			use_deferred_io = false;
-	}
-
-	/* deferred I/O */
-	if (use_deferred_io) {
-		fb_helper->fbdefio.delay = HZ / 20;
-		fb_helper->fbdefio.deferred_io = drm_fb_helper_deferred_io;
-
-		info->fbdefio = &fb_helper->fbdefio;
-		ret = fb_deferred_io_init(info);
-		if (ret)
-			goto err_drm_fb_helper_release_info;
-	}
+		ret = drm_fbdev_dma_driver_fbdev_probe_tail(fb_helper, sizes);
+	if (ret)
+		goto err_drm_fb_helper_release_info;
 
 	return 0;
 

From c1fcf41cf37f7a3fd3bbf6f0c04aba3ea4258888 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 25 Feb 2025 19:37:32 +0000
Subject: [PATCH 0706/1173] x86/mm: Clear _PAGE_DIRTY for kernel mappings when
 we clear _PAGE_RW

The bit pattern of _PAGE_DIRTY set and _PAGE_RW clear is used to mark
shadow stacks.  This is currently checked for in mk_pte() but not
pfn_pte().  If we add the check to pfn_pte(), it catches vfree()
calling set_direct_map_invalid_noflush() which calls
__change_page_attr() which loads the old protection bits from the
PTE, clears the specified bits and uses pfn_pte() to construct the
new PTE.

We should, therefore, for kernel mappings, clear the _PAGE_DIRTY bit
consistently whenever we clear _PAGE_RW.  I opted to do it in the
callers in case we want to use __change_page_attr() to create shadow
stacks inside the kernel at some point in the future.  Arguably, we
might also want to clear _PAGE_ACCESSED here.

Note that the 3 functions involved:

  __set_pages_np()
  kernel_map_pages_in_pgd()
  kernel_unmap_pages_in_pgd()

Only ever manipulate non-swappable kernel mappings, so maintaining
the DIRTY:1|RW:0 special pattern for shadow stacks and DIRTY:0
pattern for non-shadow-stack entries can be maintained consistently
and doesn't result in the unintended clearing of a live dirty bit
that could corrupt (destroy) dirty bit information for user mappings.

Reported-by: kernel test robot <oliver.sang@intel.com>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/174051422675.10177.13226545170101706336.tip-bot2@tip-bot2
Closes: https://lore.kernel.org/oe-lkp/202502241646.719f4651-lkp@intel.com
---
 arch/x86/mm/pat/set_memory.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index 84d0bca3be285..d1740159029e8 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -2628,7 +2628,7 @@ static int __set_pages_np(struct page *page, int numpages)
 				.pgd = NULL,
 				.numpages = numpages,
 				.mask_set = __pgprot(0),
-				.mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW),
+				.mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY),
 				.flags = CPA_NO_CHECK_ALIAS };
 
 	/*
@@ -2715,7 +2715,7 @@ int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
 		.pgd = pgd,
 		.numpages = numpages,
 		.mask_set = __pgprot(0),
-		.mask_clr = __pgprot(~page_flags & (_PAGE_NX|_PAGE_RW)),
+		.mask_clr = __pgprot(~page_flags & (_PAGE_NX|_PAGE_RW|_PAGE_DIRTY)),
 		.flags = CPA_NO_CHECK_ALIAS,
 	};
 
@@ -2758,7 +2758,7 @@ int __init kernel_unmap_pages_in_pgd(pgd_t *pgd, unsigned long address,
 		.pgd		= pgd,
 		.numpages	= numpages,
 		.mask_set	= __pgprot(0),
-		.mask_clr	= __pgprot(_PAGE_PRESENT | _PAGE_RW),
+		.mask_clr	= __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY),
 		.flags		= CPA_NO_CHECK_ALIAS,
 	};
 

From adf6819278ba34be1d29ffcdca5c2ccd2123f667 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Wed, 26 Feb 2025 16:36:56 +0100
Subject: [PATCH 0707/1173] x86/bootflag: Micro-optimize sbf_write()

Change parity bit with XOR when !parity instead of masking bit out
and conditionally setting it when !parity.

Saves a couple of bytes in the object file.

Co-developed-by: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250226153709.6370-1-ubizjak@gmail.com
---
 arch/x86/kernel/bootflag.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/x86/kernel/bootflag.c b/arch/x86/kernel/bootflag.c
index 4d89a2d80d0f3..b935c3e42bfdf 100644
--- a/arch/x86/kernel/bootflag.c
+++ b/arch/x86/kernel/bootflag.c
@@ -38,9 +38,8 @@ static void __init sbf_write(u8 v)
 	unsigned long flags;
 
 	if (sbf_port != -1) {
-		v &= ~SBF_PARITY;
 		if (!parity(v))
-			v |= SBF_PARITY;
+			v ^= SBF_PARITY;
 
 		printk(KERN_INFO "Simple Boot Flag at 0x%x set to 0x%x\n",
 			sbf_port, v);

From bd64e9d6aafd12e5437685d2a06360f86418d277 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Thu, 27 Feb 2025 09:15:33 +0000
Subject: [PATCH 0708/1173] selftests/x86/xstate: Fix spelling mistake "hader"
 -> "header"

There is a spelling mistake in a sig_print() message. Fix it.

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250227091533.599213-1-colin.i.king@gmail.com
---
 tools/testing/selftests/x86/xstate.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/x86/xstate.c b/tools/testing/selftests/x86/xstate.c
index 875777911d826..23c1d6c964eae 100644
--- a/tools/testing/selftests/x86/xstate.c
+++ b/tools/testing/selftests/x86/xstate.c
@@ -391,7 +391,7 @@ static void validate_sigfpstate(int sig, siginfo_t *si, void *ctx_void)
 	if (get_xstatebv(xbuf) & xstate.mask)
 		sig_print("[OK]\t'xfeatures' in XSAVE header is valid\n");
 	else
-		sig_print("[FAIL]\t'xfeatures' in XSAVE hader is not valid\n");
+		sig_print("[FAIL]\t'xfeatures' in XSAVE header is not valid\n");
 
 	if (validate_xstate_same(stashed_xbuf, xbuf))
 		sig_print("[OK]\txstate delivery was successful\n");

From 549435aab49ae83d60a08795de6cf0e866f3b2ec Mon Sep 17 00:00:00 2001
From: Yosry Ahmed <yosry.ahmed@linux.dev>
Date: Thu, 27 Feb 2025 01:27:07 +0000
Subject: [PATCH 0709/1173] x86/bugs: Move the X86_FEATURE_USE_IBPB check into
 callers

indirect_branch_prediction_barrier() only performs the MSR write if
X86_FEATURE_USE_IBPB is set, using alternative_msr_write(). In
preparation for removing X86_FEATURE_USE_IBPB, move the feature check
into the callers so that they can be addressed one-by-one, and use
X86_FEATURE_IBPB instead to guard the MSR write.

Signed-off-by: Yosry Ahmed <yosry.ahmed@linux.dev>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Josh Poimboeuf <jpoimboe@kernel.org>
Acked-by: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/r/20250227012712.3193063-2-yosry.ahmed@linux.dev
---
 arch/x86/include/asm/nospec-branch.h | 2 +-
 arch/x86/kernel/cpu/bugs.c           | 2 +-
 arch/x86/kvm/svm/svm.c               | 3 ++-
 arch/x86/kvm/vmx/nested.c            | 3 ++-
 arch/x86/kvm/vmx/vmx.c               | 3 ++-
 arch/x86/mm/tlb.c                    | 7 ++++---
 6 files changed, 12 insertions(+), 8 deletions(-)

diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 7e8bf78c03d5d..7cbb76a2434b9 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -515,7 +515,7 @@ extern u64 x86_pred_cmd;
 
 static inline void indirect_branch_prediction_barrier(void)
 {
-	alternative_msr_write(MSR_IA32_PRED_CMD, x86_pred_cmd, X86_FEATURE_USE_IBPB);
+	alternative_msr_write(MSR_IA32_PRED_CMD, x86_pred_cmd, X86_FEATURE_IBPB);
 }
 
 /* The Intel SPEC CTRL MSR base value cache */
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 1d7afc40f2272..754150fc05784 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -2272,7 +2272,7 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl)
 		if (ctrl == PR_SPEC_FORCE_DISABLE)
 			task_set_spec_ib_force_disable(task);
 		task_update_spec_tif(task);
-		if (task == current)
+		if (task == current && cpu_feature_enabled(X86_FEATURE_USE_IBPB))
 			indirect_branch_prediction_barrier();
 		break;
 	default:
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 77ab66c5bb962..57222c3b56592 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1565,7 +1565,8 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	if (sd->current_vmcb != svm->vmcb) {
 		sd->current_vmcb = svm->vmcb;
 
-		if (!cpu_feature_enabled(X86_FEATURE_IBPB_ON_VMEXIT))
+		if (!cpu_feature_enabled(X86_FEATURE_IBPB_ON_VMEXIT) &&
+		    cpu_feature_enabled(X86_FEATURE_USE_IBPB))
 			indirect_branch_prediction_barrier();
 	}
 	if (kvm_vcpu_apicv_active(vcpu))
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 8a7af02d466e9..1df427a822dd7 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -5026,7 +5026,8 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 	 * doesn't isolate different VMCSs, i.e. in this case, doesn't provide
 	 * separate modes for L2 vs L1.
 	 */
-	if (guest_cpu_cap_has(vcpu, X86_FEATURE_SPEC_CTRL))
+	if (guest_cpu_cap_has(vcpu, X86_FEATURE_SPEC_CTRL) &&
+	    cpu_feature_enabled(X86_FEATURE_USE_IBPB))
 		indirect_branch_prediction_barrier();
 
 	/* Update any VMCS fields that might have changed while L2 ran */
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 6c56d5235f0f3..042b7a88157b0 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1477,7 +1477,8 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
 		 * performs IBPB on nested VM-Exit (a single nested transition
 		 * may switch the active VMCS multiple times).
 		 */
-		if (!buddy || WARN_ON_ONCE(buddy->vmcs != prev))
+		if (cpu_feature_enabled(X86_FEATURE_USE_IBPB) &&
+		    (!buddy || WARN_ON_ONCE(buddy->vmcs != prev)))
 			indirect_branch_prediction_barrier();
 	}
 
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 6cf881a942bbe..4f61d11de041c 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -437,7 +437,8 @@ static void cond_mitigation(struct task_struct *next)
 		 * both have the IBPB bit set.
 		 */
 		if (next_mm != prev_mm &&
-		    (next_mm | prev_mm) & LAST_USER_MM_IBPB)
+		    (next_mm | prev_mm) & LAST_USER_MM_IBPB &&
+		    cpu_feature_enabled(X86_FEATURE_USE_IBPB))
 			indirect_branch_prediction_barrier();
 	}
 
@@ -447,8 +448,8 @@ static void cond_mitigation(struct task_struct *next)
 		 * different context than the user space task which ran
 		 * last on this CPU.
 		 */
-		if ((prev_mm & ~LAST_USER_MM_SPEC_MASK) !=
-					(unsigned long)next->mm)
+		if ((prev_mm & ~LAST_USER_MM_SPEC_MASK) != (unsigned long)next->mm &&
+		    cpu_feature_enabled(X86_FEATURE_USE_IBPB))
 			indirect_branch_prediction_barrier();
 	}
 

From a48dc42614cad39fac1ef55d690847fd07f0e3c6 Mon Sep 17 00:00:00 2001
From: Yosry Ahmed <yosry.ahmed@linux.dev>
Date: Thu, 27 Feb 2025 01:27:08 +0000
Subject: [PATCH 0710/1173] x86/mm: Remove X86_FEATURE_USE_IBPB checks in
 cond_mitigation()

The check is performed when either switch_mm_cond_ibpb or
switch_mm_always_ibpb is set. In both cases, X86_FEATURE_USE_IBPB is
always set. Remove the redundant check.

Signed-off-by: Yosry Ahmed <yosry.ahmed@linux.dev>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Josh Poimboeuf <jpoimboe@kernel.org>
Link: https://lore.kernel.org/r/20250227012712.3193063-3-yosry.ahmed@linux.dev
---
 arch/x86/mm/tlb.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 4f61d11de041c..30708076abfa6 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -437,8 +437,7 @@ static void cond_mitigation(struct task_struct *next)
 		 * both have the IBPB bit set.
 		 */
 		if (next_mm != prev_mm &&
-		    (next_mm | prev_mm) & LAST_USER_MM_IBPB &&
-		    cpu_feature_enabled(X86_FEATURE_USE_IBPB))
+		    (next_mm | prev_mm) & LAST_USER_MM_IBPB)
 			indirect_branch_prediction_barrier();
 	}
 
@@ -448,8 +447,7 @@ static void cond_mitigation(struct task_struct *next)
 		 * different context than the user space task which ran
 		 * last on this CPU.
 		 */
-		if ((prev_mm & ~LAST_USER_MM_SPEC_MASK) != (unsigned long)next->mm &&
-		    cpu_feature_enabled(X86_FEATURE_USE_IBPB))
+		if ((prev_mm & ~LAST_USER_MM_SPEC_MASK) != (unsigned long)next->mm)
 			indirect_branch_prediction_barrier();
 	}
 

From bd9a8542ceccce1b1d5d5fd5e47be57fe42f9bb9 Mon Sep 17 00:00:00 2001
From: Yosry Ahmed <yosry.ahmed@linux.dev>
Date: Thu, 27 Feb 2025 01:27:09 +0000
Subject: [PATCH 0711/1173] x86/bugs: Remove the X86_FEATURE_USE_IBPB check in
 ib_prctl_set()

If X86_FEATURE_USE_IBPB is not set, then both spectre_v2_user_ibpb and
spectre_v2_user_stibp are set to SPECTRE_V2_USER_NONE in
spectre_v2_user_select_mitigation(). Since ib_prctl_set() already checks
for this before performing the IBPB, the X86_FEATURE_USE_IBPB check is
redundant. Remove it.

Signed-off-by: Yosry Ahmed <yosry.ahmed@linux.dev>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Josh Poimboeuf <jpoimboe@kernel.org>
Link: https://lore.kernel.org/r/20250227012712.3193063-4-yosry.ahmed@linux.dev
---
 arch/x86/kernel/cpu/bugs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 754150fc05784..1d7afc40f2272 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -2272,7 +2272,7 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl)
 		if (ctrl == PR_SPEC_FORCE_DISABLE)
 			task_set_spec_ib_force_disable(task);
 		task_update_spec_tif(task);
-		if (task == current && cpu_feature_enabled(X86_FEATURE_USE_IBPB))
+		if (task == current)
 			indirect_branch_prediction_barrier();
 		break;
 	default:

From 80dacb080461edfc1d854721ee6933a4cfa3b602 Mon Sep 17 00:00:00 2001
From: Yosry Ahmed <yosry.ahmed@linux.dev>
Date: Thu, 27 Feb 2025 01:27:10 +0000
Subject: [PATCH 0712/1173] x86/bugs: Use a static branch to guard IBPB on vCPU
 switch

Instead of using X86_FEATURE_USE_IBPB to guard the IBPB execution in KVM
when a new vCPU is loaded, introduce a static branch, similar to
switch_mm_*_ibpb.

This makes it obvious in spectre_v2_user_select_mitigation() what
exactly is being toggled, instead of the unclear X86_FEATURE_USE_IBPB
(which will be shortly removed). It also provides more fine-grained
control, making it simpler to change/add paths that control the IBPB in
the vCPU switch path without affecting other IBPBs.

Signed-off-by: Yosry Ahmed <yosry.ahmed@linux.dev>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Josh Poimboeuf <jpoimboe@kernel.org>
Acked-by: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/r/20250227012712.3193063-5-yosry.ahmed@linux.dev
---
 arch/x86/include/asm/nospec-branch.h | 2 ++
 arch/x86/kernel/cpu/bugs.c           | 5 +++++
 arch/x86/kvm/svm/svm.c               | 2 +-
 arch/x86/kvm/vmx/vmx.c               | 2 +-
 4 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 7cbb76a2434b9..36bc395bdef32 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -552,6 +552,8 @@ DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp);
 DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb);
 DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
 
+DECLARE_STATIC_KEY_FALSE(switch_vcpu_ibpb);
+
 DECLARE_STATIC_KEY_FALSE(mds_idle_clear);
 
 DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush);
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 1d7afc40f2272..7f904d0b0b04f 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -113,6 +113,10 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_ibpb);
 /* Control unconditional IBPB in switch_mm() */
 DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
 
+/* Control IBPB on vCPU load */
+DEFINE_STATIC_KEY_FALSE(switch_vcpu_ibpb);
+EXPORT_SYMBOL_GPL(switch_vcpu_ibpb);
+
 /* Control MDS CPU buffer clear before idling (halt, mwait) */
 DEFINE_STATIC_KEY_FALSE(mds_idle_clear);
 EXPORT_SYMBOL_GPL(mds_idle_clear);
@@ -1365,6 +1369,7 @@ spectre_v2_user_select_mitigation(void)
 	/* Initialize Indirect Branch Prediction Barrier */
 	if (boot_cpu_has(X86_FEATURE_IBPB)) {
 		setup_force_cpu_cap(X86_FEATURE_USE_IBPB);
+		static_branch_enable(&switch_vcpu_ibpb);
 
 		spectre_v2_user_ibpb = mode;
 		switch (cmd) {
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 57222c3b56592..a73875ffbc3df 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1566,7 +1566,7 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		sd->current_vmcb = svm->vmcb;
 
 		if (!cpu_feature_enabled(X86_FEATURE_IBPB_ON_VMEXIT) &&
-		    cpu_feature_enabled(X86_FEATURE_USE_IBPB))
+		    static_branch_likely(&switch_vcpu_ibpb))
 			indirect_branch_prediction_barrier();
 	}
 	if (kvm_vcpu_apicv_active(vcpu))
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 042b7a88157b0..956f9143a3c4c 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1477,7 +1477,7 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
 		 * performs IBPB on nested VM-Exit (a single nested transition
 		 * may switch the active VMCS multiple times).
 		 */
-		if (cpu_feature_enabled(X86_FEATURE_USE_IBPB) &&
+		if (static_branch_likely(&switch_vcpu_ibpb) &&
 		    (!buddy || WARN_ON_ONCE(buddy->vmcs != prev)))
 			indirect_branch_prediction_barrier();
 	}

From 8c4f28cd81fe86033918eec69d5280b532c05842 Mon Sep 17 00:00:00 2001
From: Yosry Ahmed <yosry.ahmed@linux.dev>
Date: Thu, 27 Feb 2025 01:27:11 +0000
Subject: [PATCH 0713/1173] KVM: nVMX: Always use IBPB to properly virtualize
 IBRS

On synthesized nested VM-exits in VMX, an IBPB is performed if IBRS is
advertised to the guest to properly provide separate prediction domains
for L1 and L2. However, this is currently conditional on
X86_FEATURE_USE_IBPB, which depends on the host spectre_v2_user
mitigation.

In short, if spectre_v2_user=no, IBRS is not virtualized correctly and
L1 becomes susceptible to attacks from L2. Fix this by performing the
IBPB regardless of X86_FEATURE_USE_IBPB.

Fixes: 2e7eab81425a ("KVM: VMX: Execute IBPB on emulated VM-exit when guest has IBRS")
Signed-off-by: Yosry Ahmed <yosry.ahmed@linux.dev>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Jim Mattson <jmattson@google.com>
Acked-by: Josh Poimboeuf <jpoimboe@kernel.org>
Acked-by: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/r/20250227012712.3193063-6-yosry.ahmed@linux.dev
---
 arch/x86/kvm/vmx/nested.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 1df427a822dd7..8a7af02d466e9 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -5026,8 +5026,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 	 * doesn't isolate different VMCSs, i.e. in this case, doesn't provide
 	 * separate modes for L2 vs L1.
 	 */
-	if (guest_cpu_cap_has(vcpu, X86_FEATURE_SPEC_CTRL) &&
-	    cpu_feature_enabled(X86_FEATURE_USE_IBPB))
+	if (guest_cpu_cap_has(vcpu, X86_FEATURE_SPEC_CTRL))
 		indirect_branch_prediction_barrier();
 
 	/* Update any VMCS fields that might have changed while L2 ran */

From 8f64eee70cdd3bb8c3ec7d30f0d1f52922aaef7c Mon Sep 17 00:00:00 2001
From: Yosry Ahmed <yosry.ahmed@linux.dev>
Date: Thu, 27 Feb 2025 01:27:12 +0000
Subject: [PATCH 0714/1173] x86/bugs: Remove X86_FEATURE_USE_IBPB

X86_FEATURE_USE_IBPB was introduced in:

  2961298efe1e ("x86/cpufeatures: Clean up Spectre v2 related CPUID flags")

to have separate flags for when the CPU supports IBPB (i.e. X86_FEATURE_IBPB)
and when an IBPB is actually used to mitigate Spectre v2.

Ever since then, the uses of IBPB expanded. The name became confusing
because it does not control all IBPB executions in the kernel.
Furthermore, because its name is generic and it's buried within
indirect_branch_prediction_barrier(), it's easy to use it not knowing
that it is specific to Spectre v2.

X86_FEATURE_USE_IBPB is no longer needed because all the IBPB executions
it used to control are now controlled through other means (e.g.
switch_mm_*_ibpb static branches).

Remove the unused feature bit.

Signed-off-by: Yosry Ahmed <yosry.ahmed@linux.dev>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Josh Poimboeuf <jpoimboe@kernel.org>
Link: https://lore.kernel.org/r/20250227012712.3193063-7-yosry.ahmed@linux.dev
---
 arch/x86/include/asm/cpufeatures.h       | 1 -
 arch/x86/kernel/cpu/bugs.c               | 1 -
 tools/arch/x86/include/asm/cpufeatures.h | 1 -
 3 files changed, 3 deletions(-)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 43653f2704c93..c8701abb77524 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -210,7 +210,6 @@
 #define X86_FEATURE_MBA			( 7*32+18) /* "mba" Memory Bandwidth Allocation */
 #define X86_FEATURE_RSB_CTXSW		( 7*32+19) /* Fill RSB on context switches */
 #define X86_FEATURE_PERFMON_V2		( 7*32+20) /* "perfmon_v2" AMD Performance Monitoring Version 2 */
-#define X86_FEATURE_USE_IBPB		( 7*32+21) /* Indirect Branch Prediction Barrier enabled */
 #define X86_FEATURE_USE_IBRS_FW		( 7*32+22) /* Use IBRS during runtime firmware calls */
 #define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE	( 7*32+23) /* Disable Speculative Store Bypass. */
 #define X86_FEATURE_LS_CFG_SSBD		( 7*32+24)  /* AMD SSBD implementation via LS_CFG MSR */
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 7f904d0b0b04f..5397d0afac089 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -1368,7 +1368,6 @@ spectre_v2_user_select_mitigation(void)
 
 	/* Initialize Indirect Branch Prediction Barrier */
 	if (boot_cpu_has(X86_FEATURE_IBPB)) {
-		setup_force_cpu_cap(X86_FEATURE_USE_IBPB);
 		static_branch_enable(&switch_vcpu_ibpb);
 
 		spectre_v2_user_ibpb = mode;
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 17b6590748c00..ec9911379c617 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -210,7 +210,6 @@
 #define X86_FEATURE_MBA			( 7*32+18) /* "mba" Memory Bandwidth Allocation */
 #define X86_FEATURE_RSB_CTXSW		( 7*32+19) /* Fill RSB on context switches */
 #define X86_FEATURE_PERFMON_V2		( 7*32+20) /* "perfmon_v2" AMD Performance Monitoring Version 2 */
-#define X86_FEATURE_USE_IBPB		( 7*32+21) /* Indirect Branch Prediction Barrier enabled */
 #define X86_FEATURE_USE_IBRS_FW		( 7*32+22) /* Use IBRS during runtime firmware calls */
 #define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE	( 7*32+23) /* Disable Speculative Store Bypass. */
 #define X86_FEATURE_LS_CFG_SSBD		( 7*32+24)  /* AMD SSBD implementation via LS_CFG MSR */

From 6d48ad04075729519f6baaa1dc9e5a3a39d05f53 Mon Sep 17 00:00:00 2001
From: Xi Ruoyao <xry111@xry111.site>
Date: Wed, 26 Feb 2025 21:28:41 +0800
Subject: [PATCH 0715/1173] MIPS: Ignore relocs against __ex_table for
 relocatable kernel

Since commit 6f2c2f93a190 ("scripts/sorttable: Remove unneeded
Elf_Rel"), sorttable no longer clears relocs against __ex_table,
claiming "it was never used."  But in fact MIPS relocatable kernel had
been implicitly depending on this behavior, so after this commit the
MIPS relocatable kernel has started to spit oops like:

	CPU 1 Unable to handle kernel paging request at virtual address 000000fffbbdbff8, epc == ffffffff818f9a6c, ra == ffffffff813ad7d0
	... ...
	Call Trace:
	[<ffffffff818f9a6c>] __raw_copy_from_user+0x48/0x2fc
	[<ffffffff813ad7d0>] cp_statx+0x1a0/0x1e0
	[<ffffffff813ae528>] do_statx_fd+0xa8/0x118
	[<ffffffff813ae670>] sys_statx+0xd8/0xf8
	[<ffffffff81156cc8>] syscall_common+0x34/0x58

So ignore those relocs on our own to fix the issue.

Fixes: 6f2c2f93a190 ("scripts/sorttable: Remove unneeded Elf_Rel")
Signed-off-by: Xi Ruoyao <xry111@xry111.site>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/boot/tools/relocs.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/mips/boot/tools/relocs.c b/arch/mips/boot/tools/relocs.c
index a88d66c46d7f7..9863e1d5c62e3 100644
--- a/arch/mips/boot/tools/relocs.c
+++ b/arch/mips/boot/tools/relocs.c
@@ -468,6 +468,8 @@ static void walk_relocs(int (*process)(struct section *sec, Elf_Rel *rel,
 			Elf_Sym *sym, const char *symname))
 {
 	int i;
+	struct section *extab_sec = sec_lookup("__ex_table");
+	int extab_index = extab_sec ? extab_sec - secs : -1;
 
 	/* Walk through the relocations */
 	for (i = 0; i < ehdr.e_shnum; i++) {
@@ -480,6 +482,9 @@ static void walk_relocs(int (*process)(struct section *sec, Elf_Rel *rel,
 		if (sec->shdr.sh_type != SHT_REL_TYPE)
 			continue;
 
+		if (sec->shdr.sh_info == extab_index)
+			continue;
+
 		sec_symtab  = sec->link;
 		sec_applies = &secs[sec->shdr.sh_info];
 		if (!(sec_applies->shdr.sh_flags & SHF_ALLOC))

From 6ac43f2be982ea54b75206dccd33f4cf81bfdc39 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 26 Feb 2025 22:37:05 +0100
Subject: [PATCH 0716/1173] x86/Kconfig: Add cmpxchg8b support back to Geode
 CPUs

An older cleanup of mine inadvertently removed geode-gx1 and geode-lx
from the list of CPUs that are known to support a working cmpxchg8b.

Fixes: 88a2b4edda3d ("x86/Kconfig: Rework CONFIG_X86_PAE dependency")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250226213714.4040853-2-arnd@kernel.org
---
 arch/x86/Kconfig.cpu | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 2a7279d80460a..42e6a40876ea4 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -368,7 +368,7 @@ config X86_HAVE_PAE
 
 config X86_CMPXCHG64
 	def_bool y
-	depends on X86_HAVE_PAE || M586TSC || M586MMX || MK6 || MK7
+	depends on X86_HAVE_PAE || M586TSC || M586MMX || MK6 || MK7 || MGEODEGX1 || MGEODE_LX
 
 # this should be set for all -march=.. options where the compiler
 # generates cmov.

From 0abf508675c0dbbca6a387842f90db60756c4af5 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 26 Feb 2025 22:37:06 +0100
Subject: [PATCH 0717/1173] x86/smp: Drop 32-bit "bigsmp" machine support

The x86-32 kernel used to support multiple platforms with more than eight
logical CPUs, from the 1999-2003 timeframe: Sequent NUMA-Q, IBM Summit,
Unisys ES7000 and HP F8. Support for all except the latter was dropped
back in 2014, leaving only the F8 based DL740 and DL760 G2 machines in
this catery, with up to eight single-core Socket-603 Xeon-MP processors
with hyperthreading.

Like the already removed machines, the HP F8 servers at the time cost
upwards of $100k in typical configurations, but were quickly obsoleted
by their 64-bit Socket-604 cousins and the AMD Opteron.

Earlier servers with up to 8 Pentium Pro or Xeon processors remain
fully supported as they had no hyperthreading. Similarly, the more
common 4-socket Xeon-MP machines with hyperthreading using Intel
or ServerWorks chipsets continue to work without this, and all the
multi-core Xeon processors also run 64-bit kernels.

While the "bigsmp" support can also be used to run on later 64-bit
machines (including VM guests), it seems best to discourage that
and get any remaining users to update their kernels to 64-bit builds
on these. As a side-effect of this, there is also no more need to
support NUMA configurations on 32-bit x86, as all true 32-bit
NUMA platforms are already gone.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250226213714.4040853-3-arnd@kernel.org
---
 .../admin-guide/kernel-parameters.txt         |   4 -
 arch/x86/Kconfig                              |  20 +---
 arch/x86/kernel/apic/Makefile                 |   3 -
 arch/x86/kernel/apic/apic.c                   |   3 -
 arch/x86/kernel/apic/bigsmp_32.c              | 105 ------------------
 arch/x86/kernel/apic/local.h                  |  13 ---
 arch/x86/kernel/apic/probe_32.c               |  29 -----
 7 files changed, 4 insertions(+), 173 deletions(-)
 delete mode 100644 arch/x86/kernel/apic/bigsmp_32.c

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index fb8752b42ec85..8f923770a566d 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -416,10 +416,6 @@
 			Format: { quiet (default) | verbose | debug }
 			Change the amount of debugging information output
 			when initialising the APIC and IO-APIC components.
-			For X86-32, this can also be used to specify an APIC
-			driver name.
-			Format: apic=driver_name
-			Examples: apic=bigsmp
 
 	apic_extnmi=	[APIC,X86,EARLY] External NMI delivery setting
 			Format: { bsp (default) | all | none }
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index d581634c6a59e..887b77bdeb064 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -531,12 +531,6 @@ config X86_FRED
 	  ring transitions and exception/interrupt handling if the
 	  system supports it.
 
-config X86_BIGSMP
-	bool "Support for big SMP systems with more than 8 CPUs"
-	depends on SMP && X86_32
-	help
-	  This option is needed for the systems that have more than 8 CPUs.
-
 config X86_EXTENDED_PLATFORM
 	bool "Support for extended (non-PC) x86 platforms"
 	default y
@@ -735,8 +729,8 @@ config X86_32_NON_STANDARD
 	depends on X86_32 && SMP
 	depends on X86_EXTENDED_PLATFORM
 	help
-	  This option compiles in the bigsmp and STA2X11 default
-	  subarchitectures.  It is intended for a generic binary
+	  This option compiles in the STA2X11 default
+	  subarchitecture.  It is intended for a generic binary
 	  kernel. If you select them all, kernel will probe it one by
 	  one and will fallback to default.
 
@@ -1013,8 +1007,7 @@ config NR_CPUS_RANGE_BEGIN
 config NR_CPUS_RANGE_END
 	int
 	depends on X86_32
-	default   64 if  SMP &&  X86_BIGSMP
-	default    8 if  SMP && !X86_BIGSMP
+	default    8 if  SMP
 	default    1 if !SMP
 
 config NR_CPUS_RANGE_END
@@ -1027,7 +1020,6 @@ config NR_CPUS_RANGE_END
 config NR_CPUS_DEFAULT
 	int
 	depends on X86_32
-	default   32 if  X86_BIGSMP
 	default    8 if  SMP
 	default    1 if !SMP
 
@@ -1574,8 +1566,7 @@ config AMD_MEM_ENCRYPT
 config NUMA
 	bool "NUMA Memory Allocation and Scheduler Support"
 	depends on SMP
-	depends on X86_64 || (X86_32 && HIGHMEM64G && X86_BIGSMP)
-	default y if X86_BIGSMP
+	depends on X86_64
 	select USE_PERCPU_NUMA_NODE_ID
 	select OF_NUMA if OF
 	help
@@ -1588,9 +1579,6 @@ config NUMA
 	  For 64-bit this is recommended if the system is Intel Core i7
 	  (or later), AMD Opteron, or EM64T NUMA.
 
-	  For 32-bit this is only needed if you boot a 32-bit
-	  kernel on a 64-bit NUMA platform.
-
 	  Otherwise, you should say N.
 
 config AMD_NUMA
diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile
index 3bf0487cf3b73..52d1808ee360b 100644
--- a/arch/x86/kernel/apic/Makefile
+++ b/arch/x86/kernel/apic/Makefile
@@ -23,8 +23,5 @@ obj-$(CONFIG_X86_X2APIC)	+= x2apic_cluster.o
 obj-y				+= apic_flat_64.o
 endif
 
-# APIC probe will depend on the listing order here
-obj-$(CONFIG_X86_BIGSMP)	+= bigsmp_32.o
-
 # For 32bit, probe_32 need to be listed last
 obj-$(CONFIG_X86_LOCAL_APIC)	+= probe_$(BITS).o
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index e893dc6f11c13..ddca8da6d4680 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1371,8 +1371,6 @@ void __init apic_intr_mode_init(void)
 
 	x86_64_probe_apic();
 
-	x86_32_install_bigsmp();
-
 	if (x86_platform.apic_post_init)
 		x86_platform.apic_post_init();
 
@@ -1674,7 +1672,6 @@ static __init void apic_read_boot_cpu_id(bool x2apic)
 		boot_cpu_apic_version = GET_APIC_VERSION(apic_read(APIC_LVR));
 	}
 	topology_register_boot_apic(boot_cpu_physical_apicid);
-	x86_32_probe_bigsmp_early();
 }
 
 #ifdef CONFIG_X86_X2APIC
diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c
deleted file mode 100644
index 9285d500d5b44..0000000000000
--- a/arch/x86/kernel/apic/bigsmp_32.c
+++ /dev/null
@@ -1,105 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * APIC driver for "bigsmp" xAPIC machines with more than 8 virtual CPUs.
- *
- * Drives the local APIC in "clustered mode".
- */
-#include <linux/cpumask.h>
-#include <linux/dmi.h>
-#include <linux/smp.h>
-
-#include <asm/apic.h>
-#include <asm/io_apic.h>
-
-#include "local.h"
-
-static u32 bigsmp_get_apic_id(u32 x)
-{
-	return (x >> 24) & 0xFF;
-}
-
-static void bigsmp_send_IPI_allbutself(int vector)
-{
-	default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector);
-}
-
-static void bigsmp_send_IPI_all(int vector)
-{
-	default_send_IPI_mask_sequence_phys(cpu_online_mask, vector);
-}
-
-static int dmi_bigsmp; /* can be set by dmi scanners */
-
-static int hp_ht_bigsmp(const struct dmi_system_id *d)
-{
-	printk(KERN_NOTICE "%s detected: force use of apic=bigsmp\n", d->ident);
-	dmi_bigsmp = 1;
-
-	return 0;
-}
-
-
-static const struct dmi_system_id bigsmp_dmi_table[] = {
-	{ hp_ht_bigsmp, "HP ProLiant DL760 G2",
-		{	DMI_MATCH(DMI_BIOS_VENDOR, "HP"),
-			DMI_MATCH(DMI_BIOS_VERSION, "P44-"),
-		}
-	},
-
-	{ hp_ht_bigsmp, "HP ProLiant DL740",
-		{	DMI_MATCH(DMI_BIOS_VENDOR, "HP"),
-			DMI_MATCH(DMI_BIOS_VERSION, "P47-"),
-		}
-	},
-	{ } /* NULL entry stops DMI scanning */
-};
-
-static int probe_bigsmp(void)
-{
-	return dmi_check_system(bigsmp_dmi_table);
-}
-
-static struct apic apic_bigsmp __ro_after_init = {
-
-	.name				= "bigsmp",
-	.probe				= probe_bigsmp,
-
-	.dest_mode_logical		= false,
-
-	.disable_esr			= 1,
-
-	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
-
-	.max_apic_id			= 0xFE,
-	.get_apic_id			= bigsmp_get_apic_id,
-
-	.calc_dest_apicid		= apic_default_calc_apicid,
-
-	.send_IPI			= default_send_IPI_single_phys,
-	.send_IPI_mask			= default_send_IPI_mask_sequence_phys,
-	.send_IPI_mask_allbutself	= NULL,
-	.send_IPI_allbutself		= bigsmp_send_IPI_allbutself,
-	.send_IPI_all			= bigsmp_send_IPI_all,
-	.send_IPI_self			= default_send_IPI_self,
-
-	.read				= native_apic_mem_read,
-	.write				= native_apic_mem_write,
-	.eoi				= native_apic_mem_eoi,
-	.icr_read			= native_apic_icr_read,
-	.icr_write			= native_apic_icr_write,
-	.wait_icr_idle			= apic_mem_wait_icr_idle,
-	.safe_wait_icr_idle		= apic_mem_wait_icr_idle_timeout,
-};
-
-bool __init apic_bigsmp_possible(bool cmdline_override)
-{
-	return apic == &apic_bigsmp || !cmdline_override;
-}
-
-void __init apic_bigsmp_force(void)
-{
-	if (apic != &apic_bigsmp)
-		apic_install_driver(&apic_bigsmp);
-}
-
-apic_driver(apic_bigsmp);
diff --git a/arch/x86/kernel/apic/local.h b/arch/x86/kernel/apic/local.h
index 842fe28496bee..bdcf609eb2835 100644
--- a/arch/x86/kernel/apic/local.h
+++ b/arch/x86/kernel/apic/local.h
@@ -65,17 +65,4 @@ void default_send_IPI_self(int vector);
 void default_send_IPI_mask_sequence_logical(const struct cpumask *mask, int vector);
 void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask, int vector);
 void default_send_IPI_mask_logical(const struct cpumask *mask, int vector);
-void x86_32_probe_bigsmp_early(void);
-void x86_32_install_bigsmp(void);
-#else
-static inline void x86_32_probe_bigsmp_early(void) { }
-static inline void x86_32_install_bigsmp(void) { }
-#endif
-
-#ifdef CONFIG_X86_BIGSMP
-bool apic_bigsmp_possible(bool cmdline_selected);
-void apic_bigsmp_force(void);
-#else
-static inline bool apic_bigsmp_possible(bool cmdline_selected) { return false; };
-static inline void apic_bigsmp_force(void) { }
 #endif
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index f75ee345c02d0..87bc9e7ca5d60 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -93,35 +93,6 @@ static int __init parse_apic(char *arg)
 }
 early_param("apic", parse_apic);
 
-void __init x86_32_probe_bigsmp_early(void)
-{
-	if (nr_cpu_ids <= 8 || xen_pv_domain())
-		return;
-
-	if (IS_ENABLED(CONFIG_X86_BIGSMP)) {
-		switch (boot_cpu_data.x86_vendor) {
-		case X86_VENDOR_INTEL:
-			if (!APIC_XAPIC(boot_cpu_apic_version))
-				break;
-			/* P4 and above */
-			fallthrough;
-		case X86_VENDOR_HYGON:
-		case X86_VENDOR_AMD:
-			if (apic_bigsmp_possible(cmdline_apic))
-				return;
-			break;
-		}
-	}
-	pr_info("Limiting to 8 possible CPUs\n");
-	set_nr_cpu_ids(8);
-}
-
-void __init x86_32_install_bigsmp(void)
-{
-	if (nr_cpu_ids > 8 && !xen_pv_domain())
-		apic_bigsmp_force();
-}
-
 void __init x86_32_probe_apic(void)
 {
 	if (!cmdline_apic) {

From fc2d5cbe541032e74a66599ba843803cebbfed0e Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 26 Feb 2025 22:37:07 +0100
Subject: [PATCH 0718/1173] x86/build: Rework CONFIG_GENERIC_CPU compiler flags

Building an x86-64 kernel with CONFIG_GENERIC_CPU is documented to
run on all CPUs, but the Makefile does not actually pass an -march=
argument, instead relying on the default that was used to configure
the toolchain.

In many cases, gcc will be configured to -march=x86-64 or -march=k8
for maximum compatibility, but in other cases a distribution default
may be either raised to a more recent ISA, or set to -march=native
to build for the CPU used for compilation. This still works in the
case of building a custom kernel for the local machine.

The point where it breaks down is building a kernel for another
machine that is older the the default target. Changing the default
to -march=x86-64 would make it work reliable, but possibly produce
worse code on distros that intentionally default to a newer ISA.

To allow reliably building a kernel for either the oldest x86-64
CPUs, pass the -march=x86-64 flag to the compiler. This was not
possible in early versions of x86-64 gcc, but works on all currently
supported versions down to at least gcc-5.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250226213714.4040853-4-arnd@kernel.org
---
 arch/x86/Makefile | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 5b773b34768d1..5af3172fd51cd 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -183,14 +183,14 @@ else
         cflags-$(CONFIG_MPSC)		+= -march=nocona
         cflags-$(CONFIG_MCORE2)		+= -march=core2
         cflags-$(CONFIG_MATOM)		+= -march=atom
-        cflags-$(CONFIG_GENERIC_CPU)	+= -mtune=generic
+        cflags-$(CONFIG_GENERIC_CPU)	+= -march=x86-64 -mtune=generic
         KBUILD_CFLAGS += $(cflags-y)
 
         rustflags-$(CONFIG_MK8)		+= -Ctarget-cpu=k8
         rustflags-$(CONFIG_MPSC)	+= -Ctarget-cpu=nocona
         rustflags-$(CONFIG_MCORE2)	+= -Ctarget-cpu=core2
         rustflags-$(CONFIG_MATOM)	+= -Ctarget-cpu=atom
-        rustflags-$(CONFIG_GENERIC_CPU)	+= -Ztune-cpu=generic
+        rustflags-$(CONFIG_GENERIC_CPU)	+= -Ctarget-cpu=x86-64 -Ztune-cpu=generic
         KBUILD_RUSTFLAGS += $(rustflags-y)
 
         KBUILD_CFLAGS += -mno-red-zone

From f388f60ca9041a95c9b3f157d316ed7c8f297e44 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 26 Feb 2025 22:37:08 +0100
Subject: [PATCH 0719/1173] x86/cpu: Drop configuration options for early
 64-bit CPUs

The x86 CPU selection menu is confusing for a number of reasons:

When configuring 32-bit kernels, it shows a small number of early 64-bit
microarchitectures (K8, Core 2) but not the regular generic 64-bit target
that is the normal default.  There is no longer a reason to run 32-bit
kernels on production 64-bit systems, so only actual 32-bit CPUs need
to be shown here.

When configuring 64-bit kernels, the options also pointless as there is
no way to pick any CPU from the past 15 years, leaving GENERIC_CPU as
the only sensible choice.

Address both of the above by removing the obsolete options and making
all 64-bit kernels run on both Intel and AMD CPUs from any generation.
Testing generic 32-bit kernels on 64-bit hardware remains possible,
just not building a 32-bit kernel that requires a 64-bit CPU.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250226213714.4040853-5-arnd@kernel.org
---
 arch/x86/Kconfig.cpu            | 95 +++++----------------------------
 arch/x86/Makefile               | 16 +-----
 arch/x86/Makefile_32.cpu        |  5 +-
 arch/x86/include/asm/vermagic.h |  4 --
 drivers/misc/mei/Kconfig        |  2 +-
 5 files changed, 18 insertions(+), 104 deletions(-)

diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 42e6a40876ea4..8fcb8ccee44b2 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -1,9 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0
 # Put here option for CPU selection and depending optimization
 choice
-	prompt "Processor family"
-	default M686 if X86_32
-	default GENERIC_CPU if X86_64
+	prompt "x86-32 Processor family"
+	depends on X86_32
+	default M686
 	help
 	  This is the processor type of your CPU. This information is
 	  used for optimizing purposes. In order to compile a kernel
@@ -31,7 +31,6 @@ choice
 	  - "Pentium-4" for the Intel Pentium 4 or P4-based Celeron.
 	  - "K6" for the AMD K6, K6-II and K6-III (aka K6-3D).
 	  - "Athlon" for the AMD K7 family (Athlon/Duron/Thunderbird).
-	  - "Opteron/Athlon64/Hammer/K8" for all K8 and newer AMD CPUs.
 	  - "Crusoe" for the Transmeta Crusoe series.
 	  - "Efficeon" for the Transmeta Efficeon series.
 	  - "Winchip-C6" for original IDT Winchip.
@@ -42,13 +41,10 @@ choice
 	  - "CyrixIII/VIA C3" for VIA Cyrix III or VIA C3.
 	  - "VIA C3-2" for VIA C3-2 "Nehemiah" (model 9 and above).
 	  - "VIA C7" for VIA C7.
-	  - "Intel P4" for the Pentium 4/Netburst microarchitecture.
-	  - "Core 2/newer Xeon" for all core2 and newer Intel CPUs.
 	  - "Intel Atom" for the Atom-microarchitecture CPUs.
-	  - "Generic-x86-64" for a kernel which runs on any x86-64 CPU.
 
 	  See each option's help text for additional details. If you don't know
-	  what to do, choose "486".
+	  what to do, choose "Pentium-Pro".
 
 config M486SX
 	bool "486SX"
@@ -114,11 +110,11 @@ config MPENTIUMIII
 	  extensions.
 
 config MPENTIUMM
-	bool "Pentium M"
+	bool "Pentium M/Pentium Dual Core/Core Solo/Core Duo"
 	depends on X86_32
 	help
 	  Select this for Intel Pentium M (not Pentium-4 M)
-	  notebook chips.
+	  "Merom" Core Solo/Duo notebook chips
 
 config MPENTIUM4
 	bool "Pentium-4/Celeron(P4-based)/Pentium-4 M/older Xeon"
@@ -139,22 +135,10 @@ config MPENTIUM4
 		-Mobile Pentium 4
 		-Mobile Pentium 4 M
 		-Extreme Edition (Gallatin)
-		-Prescott
-		-Prescott 2M
-		-Cedar Mill
-		-Presler
-		-Smithfiled
 	    Xeons (Intel Xeon, Xeon MP, Xeon LV, Xeon MV) corename:
 		-Foster
 		-Prestonia
 		-Gallatin
-		-Nocona
-		-Irwindale
-		-Cranford
-		-Potomac
-		-Paxville
-		-Dempsey
-
 
 config MK6
 	bool "K6/K6-II/K6-III"
@@ -172,13 +156,6 @@ config MK7
 	  some extended instructions, and passes appropriate optimization
 	  flags to GCC.
 
-config MK8
-	bool "Opteron/Athlon64/Hammer/K8"
-	help
-	  Select this for an AMD Opteron or Athlon64 Hammer-family processor.
-	  Enables use of some extended instructions, and passes appropriate
-	  optimization flags to GCC.
-
 config MCRUSOE
 	bool "Crusoe"
 	depends on X86_32
@@ -258,42 +235,14 @@ config MVIAC7
 	  Select this for a VIA C7.  Selecting this uses the correct cache
 	  shift and tells gcc to treat the CPU as a 686.
 
-config MPSC
-	bool "Intel P4 / older Netburst based Xeon"
-	depends on X86_64
-	help
-	  Optimize for Intel Pentium 4, Pentium D and older Nocona/Dempsey
-	  Xeon CPUs with Intel 64bit which is compatible with x86-64.
-	  Note that the latest Xeons (Xeon 51xx and 53xx) are not based on the
-	  Netburst core and shouldn't use this option. You can distinguish them
-	  using the cpu family field
-	  in /proc/cpuinfo. Family 15 is an older Xeon, Family 6 a newer one.
-
-config MCORE2
-	bool "Core 2/newer Xeon"
-	help
-
-	  Select this for Intel Core 2 and newer Core 2 Xeons (Xeon 51xx and
-	  53xx) CPUs. You can distinguish newer from older Xeons by the CPU
-	  family in /proc/cpuinfo. Newer ones have 6 and older ones 15
-	  (not a typo)
-
 config MATOM
 	bool "Intel Atom"
 	help
-
 	  Select this for the Intel Atom platform. Intel Atom CPUs have an
 	  in-order pipelining architecture and thus can benefit from
 	  accordingly optimized code. Use a recent GCC with specific Atom
 	  support in order to fully benefit from selecting this option.
 
-config GENERIC_CPU
-	bool "Generic-x86-64"
-	depends on X86_64
-	help
-	  Generic x86-64 CPU.
-	  Run equally well on all x86-64 CPUs.
-
 endchoice
 
 config X86_GENERIC
@@ -317,8 +266,8 @@ config X86_INTERNODE_CACHE_SHIFT
 
 config X86_L1_CACHE_SHIFT
 	int
-	default "7" if MPENTIUM4 || MPSC
-	default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU
+	default "7" if MPENTIUM4
+	default "6" if MK7 || MPENTIUMM || MATOM || MVIAC7 || X86_GENERIC || X86_64
 	default "4" if MELAN || M486SX || M486 || MGEODEGX1
 	default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX
 
@@ -336,35 +285,19 @@ config X86_ALIGNMENT_16
 
 config X86_INTEL_USERCOPY
 	def_bool y
-	depends on MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M586MMX || X86_GENERIC || MK8 || MK7 || MEFFICEON || MCORE2
+	depends on MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M586MMX || X86_GENERIC || MK7 || MEFFICEON
 
 config X86_USE_PPRO_CHECKSUM
 	def_bool y
-	depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MVIAC7 || MEFFICEON || MGEODE_LX || MCORE2 || MATOM
-
-#
-# P6_NOPs are a relatively minor optimization that require a family >=
-# 6 processor, except that it is broken on certain VIA chips.
-# Furthermore, AMD chips prefer a totally different sequence of NOPs
-# (which work on all CPUs).  In addition, it looks like Virtual PC
-# does not understand them.
-#
-# As a result, disallow these if we're not compiling for X86_64 (these
-# NOPs do work on all x86-64 capable chips); the list of processors in
-# the right-hand clause are the cores that benefit from this optimization.
-#
-config X86_P6_NOP
-	def_bool y
-	depends on X86_64
-	depends on (MCORE2 || MPENTIUM4 || MPSC)
+	depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MGEODE_LX || MATOM
 
 config X86_TSC
 	def_bool y
-	depends on (MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2 || MATOM) || X86_64
+	depends on (MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MATOM) || X86_64
 
 config X86_HAVE_PAE
 	def_bool y
-	depends on MCRUSOE || MEFFICEON || MCYRIXIII || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC7 || MCORE2 || MATOM || X86_64
+	depends on MCRUSOE || MEFFICEON || MCYRIXIII || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC7 || MATOM || X86_64
 
 config X86_CMPXCHG64
 	def_bool y
@@ -374,12 +307,12 @@ config X86_CMPXCHG64
 # generates cmov.
 config X86_CMOV
 	def_bool y
-	depends on (MK8 || MK7 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || X86_64 || MATOM || MGEODE_LX)
+	depends on (MK7 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || MATOM || MGEODE_LX || X86_64)
 
 config X86_MINIMUM_CPU_FAMILY
 	int
 	default "64" if X86_64
-	default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCORE2 || MK7 || MK8)
+	default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MK7)
 	default "5" if X86_32 && X86_CMPXCHG64
 	default "4"
 
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 5af3172fd51cd..8120085b00a4a 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -178,20 +178,8 @@ else
 	# Use -mskip-rax-setup if supported.
 	KBUILD_CFLAGS += $(call cc-option,-mskip-rax-setup)
 
-        # FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu)
-        cflags-$(CONFIG_MK8)		+= -march=k8
-        cflags-$(CONFIG_MPSC)		+= -march=nocona
-        cflags-$(CONFIG_MCORE2)		+= -march=core2
-        cflags-$(CONFIG_MATOM)		+= -march=atom
-        cflags-$(CONFIG_GENERIC_CPU)	+= -march=x86-64 -mtune=generic
-        KBUILD_CFLAGS += $(cflags-y)
-
-        rustflags-$(CONFIG_MK8)		+= -Ctarget-cpu=k8
-        rustflags-$(CONFIG_MPSC)	+= -Ctarget-cpu=nocona
-        rustflags-$(CONFIG_MCORE2)	+= -Ctarget-cpu=core2
-        rustflags-$(CONFIG_MATOM)	+= -Ctarget-cpu=atom
-        rustflags-$(CONFIG_GENERIC_CPU)	+= -Ctarget-cpu=x86-64 -Ztune-cpu=generic
-        KBUILD_RUSTFLAGS += $(rustflags-y)
+        KBUILD_CFLAGS += -march=x86-64 -mtune=generic
+        KBUILD_RUSTFLAGS += -Ctarget-cpu=x86-64 -Ztune-cpu=generic
 
         KBUILD_CFLAGS += -mno-red-zone
         KBUILD_CFLAGS += -mcmodel=kernel
diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu
index 94834c4b5e5ef..af7de9a427523 100644
--- a/arch/x86/Makefile_32.cpu
+++ b/arch/x86/Makefile_32.cpu
@@ -24,7 +24,6 @@ cflags-$(CONFIG_MK6)		+= -march=k6
 # Please note, that patches that add -march=athlon-xp and friends are pointless.
 # They make zero difference whatsosever to performance at this time.
 cflags-$(CONFIG_MK7)		+= -march=athlon
-cflags-$(CONFIG_MK8)		+= $(call cc-option,-march=k8,-march=athlon)
 cflags-$(CONFIG_MCRUSOE)	+= -march=i686 $(align)
 cflags-$(CONFIG_MEFFICEON)	+= -march=i686 $(call tune,pentium3) $(align)
 cflags-$(CONFIG_MWINCHIPC6)	+= $(call cc-option,-march=winchip-c6,-march=i586)
@@ -32,9 +31,7 @@ cflags-$(CONFIG_MWINCHIP3D)	+= $(call cc-option,-march=winchip2,-march=i586)
 cflags-$(CONFIG_MCYRIXIII)	+= $(call cc-option,-march=c3,-march=i486) $(align)
 cflags-$(CONFIG_MVIAC3_2)	+= $(call cc-option,-march=c3-2,-march=i686)
 cflags-$(CONFIG_MVIAC7)		+= -march=i686
-cflags-$(CONFIG_MCORE2)		+= -march=i686 $(call tune,core2)
-cflags-$(CONFIG_MATOM)		+= $(call cc-option,-march=atom,$(call cc-option,-march=core2,-march=i686)) \
-	$(call cc-option,-mtune=atom,$(call cc-option,-mtune=generic))
+cflags-$(CONFIG_MATOM)		+= -march=atom
 
 # AMD Elan support
 cflags-$(CONFIG_MELAN)		+= -march=i486
diff --git a/arch/x86/include/asm/vermagic.h b/arch/x86/include/asm/vermagic.h
index 75884d2cdec37..5d471253c7554 100644
--- a/arch/x86/include/asm/vermagic.h
+++ b/arch/x86/include/asm/vermagic.h
@@ -15,8 +15,6 @@
 #define MODULE_PROC_FAMILY "586TSC "
 #elif defined CONFIG_M586MMX
 #define MODULE_PROC_FAMILY "586MMX "
-#elif defined CONFIG_MCORE2
-#define MODULE_PROC_FAMILY "CORE2 "
 #elif defined CONFIG_MATOM
 #define MODULE_PROC_FAMILY "ATOM "
 #elif defined CONFIG_M686
@@ -33,8 +31,6 @@
 #define MODULE_PROC_FAMILY "K6 "
 #elif defined CONFIG_MK7
 #define MODULE_PROC_FAMILY "K7 "
-#elif defined CONFIG_MK8
-#define MODULE_PROC_FAMILY "K8 "
 #elif defined CONFIG_MELAN
 #define MODULE_PROC_FAMILY "ELAN "
 #elif defined CONFIG_MCRUSOE
diff --git a/drivers/misc/mei/Kconfig b/drivers/misc/mei/Kconfig
index 67d9391f18550..7575fee96cc6a 100644
--- a/drivers/misc/mei/Kconfig
+++ b/drivers/misc/mei/Kconfig
@@ -3,7 +3,7 @@
 config INTEL_MEI
 	tristate "Intel Management Engine Interface"
 	depends on X86 && PCI
-	default GENERIC_CPU || MCORE2 || MATOM || X86_GENERIC
+	default X86_64 || MATOM
 	help
 	  The Intel Management Engine (Intel ME) provides Manageability,
 	  Security and Media services for system containing Intel chipsets.

From bbeb69ce301323e84f1677484eb8e4cd8fb1f9f8 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 26 Feb 2025 22:37:09 +0100
Subject: [PATCH 0720/1173] x86/mm: Remove CONFIG_HIGHMEM64G support

HIGHMEM64G support was added in linux-2.3.25 to support (then)
high-end Pentium Pro and Pentium III Xeon servers with more than 4GB of
addressing, NUMA and PCI-X slots started appearing.

I have found no evidence of this ever being used in regular dual-socket
servers or consumer devices, all the users seem obsolete these days,
even by i386 standards:

 - Support for NUMA servers (NUMA-Q, IBM x440, unisys) was already
   removed ten years ago.

 - 4+ socket non-NUMA servers based on Intel 450GX/450NX, HP F8 and
   ServerWorks ServerSet/GrandChampion could theoretically still work
   with 8GB, but these were exceptionally rare even 20 years ago and
   would have usually been equipped with than the maximum amount of
   RAM.

 - Some SKUs of the Celeron D from 2004 had 64-bit mode fused off but
   could still work in a Socket 775 mainboard designed for the later
   Core 2 Duo and 8GB. Apparently most BIOSes at the time only allowed
   64-bit CPUs.

 - The rare Xeon LV "Sossaman" came on a few motherboards with
   registered DDR2 memory support up to 16GB.

 - In the early days of x86-64 hardware, there was sometimes the need
   to run a 32-bit kernel to work around bugs in the hardware drivers,
   or in the syscall emulation for 32-bit userspace. This likely still
   works but there should never be a need for this any more.

PAE mode is still required to get access to the 'NX' bit on Atom
'Pentium M' and 'Core Duo' CPUs.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250226213714.4040853-6-arnd@kernel.org
---
 Documentation/admin-guide/kdump/kdump.rst     |  4 --
 Documentation/arch/x86/usb-legacy-support.rst | 11 +----
 arch/x86/Kconfig                              | 46 +++----------------
 arch/x86/configs/xen.config                   |  2 -
 arch/x86/include/asm/page_32_types.h          |  4 +-
 arch/x86/mm/init_32.c                         |  9 +---
 6 files changed, 11 insertions(+), 65 deletions(-)

diff --git a/Documentation/admin-guide/kdump/kdump.rst b/Documentation/admin-guide/kdump/kdump.rst
index 5376890adbeb0..1f7f14c6e184c 100644
--- a/Documentation/admin-guide/kdump/kdump.rst
+++ b/Documentation/admin-guide/kdump/kdump.rst
@@ -180,10 +180,6 @@ Dump-capture kernel config options (Arch Dependent, i386 and x86_64)
 1) On i386, enable high memory support under "Processor type and
    features"::
 
-	CONFIG_HIGHMEM64G=y
-
-   or::
-
 	CONFIG_HIGHMEM4G
 
 2) With CONFIG_SMP=y, usually nr_cpus=1 need specified on the kernel
diff --git a/Documentation/arch/x86/usb-legacy-support.rst b/Documentation/arch/x86/usb-legacy-support.rst
index e01c08b7c981c..b17bf122270aa 100644
--- a/Documentation/arch/x86/usb-legacy-support.rst
+++ b/Documentation/arch/x86/usb-legacy-support.rst
@@ -20,11 +20,7 @@ It has several drawbacks, though:
    features (wheel, extra buttons, touchpad mode) of the real PS/2 mouse may
    not be available.
 
-2) If CONFIG_HIGHMEM64G is enabled, the PS/2 mouse emulation can cause
-   system crashes, because the SMM BIOS is not expecting to be in PAE mode.
-   The Intel E7505 is a typical machine where this happens.
-
-3) If AMD64 64-bit mode is enabled, again system crashes often happen,
+2) If AMD64 64-bit mode is enabled, again system crashes often happen,
    because the SMM BIOS isn't expecting the CPU to be in 64-bit mode.  The
    BIOS manufacturers only test with Windows, and Windows doesn't do 64-bit
    yet.
@@ -38,11 +34,6 @@ Problem 1)
   compiled-in, too.
 
 Problem 2)
-  can currently only be solved by either disabling HIGHMEM64G
-  in the kernel config or USB Legacy support in the BIOS. A BIOS update
-  could help, but so far no such update exists.
-
-Problem 3)
   is usually fixed by a BIOS update. Check the board
   manufacturers web site. If an update is not available, disable USB
   Legacy support in the BIOS. If this alone doesn't help, try also adding
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 887b77bdeb064..737a0c6305271 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1388,15 +1388,11 @@ config X86_CPUID
 	  with major 203 and minors 0 to 31 for /dev/cpu/0/cpuid to
 	  /dev/cpu/31/cpuid.
 
-choice
-	prompt "High Memory Support"
-	default HIGHMEM4G
+config HIGHMEM4G
+	bool "High Memory Support"
 	depends on X86_32
-
-config NOHIGHMEM
-	bool "off"
 	help
-	  Linux can use up to 64 Gigabytes of physical memory on x86 systems.
+	  Linux can use up to 4 Gigabytes of physical memory on x86 systems.
 	  However, the address space of 32-bit x86 processors is only 4
 	  Gigabytes large. That means that, if you have a large amount of
 	  physical memory, not all of it can be "permanently mapped" by the
@@ -1412,38 +1408,9 @@ config NOHIGHMEM
 	  possible.
 
 	  If the machine has between 1 and 4 Gigabytes physical RAM, then
-	  answer "4GB" here.
+	  answer "Y" here.
 
-	  If more than 4 Gigabytes is used then answer "64GB" here. This
-	  selection turns Intel PAE (Physical Address Extension) mode on.
-	  PAE implements 3-level paging on IA32 processors. PAE is fully
-	  supported by Linux, PAE mode is implemented on all recent Intel
-	  processors (Pentium Pro and better). NOTE: If you say "64GB" here,
-	  then the kernel will not boot on CPUs that don't support PAE!
-
-	  The actual amount of total physical memory will either be
-	  auto detected or can be forced by using a kernel command line option
-	  such as "mem=256M". (Try "man bootparam" or see the documentation of
-	  your boot loader (lilo or loadlin) about how to pass options to the
-	  kernel at boot time.)
-
-	  If unsure, say "off".
-
-config HIGHMEM4G
-	bool "4GB"
-	help
-	  Select this if you have a 32-bit processor and between 1 and 4
-	  gigabytes of physical RAM.
-
-config HIGHMEM64G
-	bool "64GB"
-	depends on X86_HAVE_PAE
-	select X86_PAE
-	help
-	  Select this if you have a 32-bit processor and more than 4
-	  gigabytes of physical RAM.
-
-endchoice
+	  If unsure, say N.
 
 choice
 	prompt "Memory split" if EXPERT
@@ -1489,8 +1456,7 @@ config PAGE_OFFSET
 	depends on X86_32
 
 config HIGHMEM
-	def_bool y
-	depends on X86_32 && (HIGHMEM64G || HIGHMEM4G)
+	def_bool HIGHMEM4G
 
 config X86_PAE
 	bool "PAE (Physical Address Extension) Support"
diff --git a/arch/x86/configs/xen.config b/arch/x86/configs/xen.config
index 581296255b39e..d5d091e03bd34 100644
--- a/arch/x86/configs/xen.config
+++ b/arch/x86/configs/xen.config
@@ -1,6 +1,4 @@
 # global x86 required specific stuff
-# On 32-bit HIGHMEM4G is not allowed
-CONFIG_HIGHMEM64G=y
 CONFIG_64BIT=y
 
 # These enable us to allow some of the
diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index faf9cc1c14bb6..25c32652f4042 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -11,8 +11,8 @@
  * a virtual address space of one gigabyte, which limits the
  * amount of physical memory you can use to about 950MB.
  *
- * If you want more physical memory than this then see the CONFIG_HIGHMEM4G
- * and CONFIG_HIGHMEM64G options in the kernel configuration.
+ * If you want more physical memory than this then see the CONFIG_VMSPLIT_2G
+ * and CONFIG_HIGHMEM4G options in the kernel configuration.
  */
 #define __PAGE_OFFSET_BASE	_AC(CONFIG_PAGE_OFFSET, UL)
 #define __PAGE_OFFSET		__PAGE_OFFSET_BASE
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index ac41b1e0940d4..f288aad8dc74e 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -582,7 +582,7 @@ static void __init lowmem_pfn_init(void)
 	"only %luMB highmem pages available, ignoring highmem size of %luMB!\n"
 
 #define MSG_HIGHMEM_TRIMMED \
-	"Warning: only 4GB will be used. Use a HIGHMEM64G enabled kernel!\n"
+	"Warning: only 4GB will be used. Support for for CONFIG_HIGHMEM64G was removed!\n"
 /*
  * We have more RAM than fits into lowmem - we try to put it into
  * highmem, also taking the highmem=x boot parameter into account:
@@ -606,18 +606,13 @@ static void __init highmem_pfn_init(void)
 #ifndef CONFIG_HIGHMEM
 	/* Maximum memory usable is what is directly addressable */
 	printk(KERN_WARNING "Warning only %ldMB will be used.\n", MAXMEM>>20);
-	if (max_pfn > MAX_NONPAE_PFN)
-		printk(KERN_WARNING "Use a HIGHMEM64G enabled kernel.\n");
-	else
-		printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n");
+	printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n");
 	max_pfn = MAXMEM_PFN;
 #else /* !CONFIG_HIGHMEM */
-#ifndef CONFIG_HIGHMEM64G
 	if (max_pfn > MAX_NONPAE_PFN) {
 		max_pfn = MAX_NONPAE_PFN;
 		printk(KERN_WARNING MSG_HIGHMEM_TRIMMED);
 	}
-#endif /* !CONFIG_HIGHMEM64G */
 #endif /* !CONFIG_HIGHMEM */
 }
 

From a8331594036f22dcf037f1a75358bd0985c84cd9 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 26 Feb 2025 22:37:10 +0100
Subject: [PATCH 0721/1173] x86/mm: Drop CONFIG_SWIOTLB for PAE

Since kernels with and without CONFIG_X86_PAE are now limited
to the low 4GB of physical address space, there is no need to
use swiotlb any more, so stop selecting this.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250226213714.4040853-7-arnd@kernel.org
---
 arch/x86/Kconfig | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 737a0c6305271..0e0ec2c8ef753 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1462,7 +1462,6 @@ config X86_PAE
 	bool "PAE (Physical Address Extension) Support"
 	depends on X86_32 && X86_HAVE_PAE
 	select PHYS_ADDR_T_64BIT
-	select SWIOTLB
 	help
 	  PAE is required for NX support, and furthermore enables
 	  larger swapspace support for non-overcommit purposes. It

From 0081fdeccbf610499b79784998b1fd36783209dd Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 26 Feb 2025 22:37:11 +0100
Subject: [PATCH 0722/1173] x86/mm: Drop support for CONFIG_HIGHPTE

With the maximum amount of RAM now 4GB, there is very little point
to still have PTE pages in highmem. Drop this for simplification.

The only other architecture supporting HIGHPTE is 32-bit arm, and
once that feature is removed as well, the highpte logic can be
dropped from common code as well.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250226213714.4040853-8-arnd@kernel.org
---
 .../admin-guide/kernel-parameters.txt         |  7 -----
 arch/x86/Kconfig                              |  9 -------
 arch/x86/include/asm/pgalloc.h                |  5 ----
 arch/x86/mm/pgtable.c                         | 27 +------------------
 4 files changed, 1 insertion(+), 47 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 8f923770a566d..93177630cefb9 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -7668,13 +7668,6 @@
 				16 - SIGBUS faults
 			Example: user_debug=31
 
-	userpte=
-			[X86,EARLY] Flags controlling user PTE allocations.
-
-				nohigh = do not allocate PTE pages in
-					HIGHMEM regardless of setting
-					of CONFIG_HIGHPTE.
-
 	vdso=		[X86,SH,SPARC]
 			On X86_32, this is an alias for vdso32=.  Otherwise:
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 0e0ec2c8ef753..73eeaf295b742 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1628,15 +1628,6 @@ config X86_PMEM_LEGACY
 
 	  Say Y if unsure.
 
-config HIGHPTE
-	bool "Allocate 3rd-level pagetables from highmem"
-	depends on HIGHMEM
-	help
-	  The VM uses one page table entry for each page of physical memory.
-	  For systems with a lot of RAM, this can be wasteful of precious
-	  low memory.  Setting this option will put user-space page table
-	  entries in high memory.
-
 config X86_CHECK_BIOS_CORRUPTION
 	bool "Check for low memory corruption"
 	help
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index dd4841231bb9f..a33147520044b 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -29,11 +29,6 @@ static inline void paravirt_release_pud(unsigned long pfn) {}
 static inline void paravirt_release_p4d(unsigned long pfn) {}
 #endif
 
-/*
- * Flags to use when allocating a user page table page.
- */
-extern gfp_t __userpte_alloc_gfp;
-
 #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 /*
  * Instead of one PGD, we acquire two PGDs.  Being order-1, it is
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index b1c1f72c1fd1b..cec321fb74f21 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -12,35 +12,10 @@ phys_addr_t physical_mask __ro_after_init = (1ULL << __PHYSICAL_MASK_SHIFT) - 1;
 EXPORT_SYMBOL(physical_mask);
 #endif
 
-#ifdef CONFIG_HIGHPTE
-#define PGTABLE_HIGHMEM __GFP_HIGHMEM
-#else
-#define PGTABLE_HIGHMEM 0
-#endif
-
-gfp_t __userpte_alloc_gfp = GFP_PGTABLE_USER | PGTABLE_HIGHMEM;
-
 pgtable_t pte_alloc_one(struct mm_struct *mm)
 {
-	return __pte_alloc_one(mm, __userpte_alloc_gfp);
-}
-
-static int __init setup_userpte(char *arg)
-{
-	if (!arg)
-		return -EINVAL;
-
-	/*
-	 * "userpte=nohigh" disables allocation of user pagetables in
-	 * high memory.
-	 */
-	if (strcmp(arg, "nohigh") == 0)
-		__userpte_alloc_gfp &= ~__GFP_HIGHMEM;
-	else
-		return -EINVAL;
-	return 0;
+	return __pte_alloc_one(mm, GFP_PGTABLE_USER);
 }
-early_param("userpte", setup_userpte);
 
 void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte)
 {

From ca5955dd5f08727605723b60767fbf2cc3d54046 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 26 Feb 2025 22:37:12 +0100
Subject: [PATCH 0723/1173] x86/cpu: Document CONFIG_X86_INTEL_MID as
 64-bit-only

The X86_INTEL_MID code was originally introduced for the 32-bit
Moorestown/Medfield/Clovertrail platform, later the 64-bit
Merrifield/Moorefield variants were added, but the final Morganfield
14nm platform was canceled before it hit the market.

To help users understand what the option actually refers to, update the
help text, and add a dependency on 64-bit kernels.

Ferry confirmed that all the hardware can run 64-bit kernels these days,
but is still testing 32-bit kernels on the Intel Edison board, so this
remains possible, but is guarded by a CONFIG_EXPERT dependency now,
to gently push remaining users towards using CONFIG_64BIT.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Andy Shevchenko <andy@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250226213714.4040853-9-arnd@kernel.org
---
 arch/x86/Kconfig | 50 ++++++++++++++++++++++++++++--------------------
 1 file changed, 29 insertions(+), 21 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 73eeaf295b742..acd4d73502d60 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -549,12 +549,12 @@ config X86_EXTENDED_PLATFORM
 		RDC R-321x SoC
 		SGI 320/540 (Visual Workstation)
 		STA2X11-based (e.g. Northville)
-		Moorestown MID devices
 
 	  64-bit platforms (CONFIG_64BIT=y):
 		Numascale NumaChip
 		ScaleMP vSMP
 		SGI Ultraviolet
+		Merrifield/Moorefield MID devices
 
 	  If you have one of these systems, or if you want to build a
 	  generic distribution kernel, say Y here - otherwise say N.
@@ -599,8 +599,31 @@ config X86_UV
 	  This option is needed in order to support SGI Ultraviolet systems.
 	  If you don't have one of these, you should say N here.
 
-# Following is an alphabetically sorted list of 32 bit extended platforms
-# Please maintain the alphabetic order if and when there are additions
+config X86_INTEL_MID
+	bool "Intel Z34xx/Z35xx MID platform support"
+	depends on X86_EXTENDED_PLATFORM
+	depends on X86_PLATFORM_DEVICES
+	depends on PCI
+	depends on X86_64 || (EXPERT && PCI_GOANY)
+	depends on X86_IO_APIC
+	select I2C
+	select DW_APB_TIMER
+	select INTEL_SCU_PCI
+	help
+	  Select to build a kernel capable of supporting 64-bit Intel MID
+	  (Mobile Internet Device) platform systems which do not have
+	  the PCI legacy interfaces.
+
+	  The only supported devices are the 22nm Merrified (Z34xx)
+	  and Moorefield (Z35xx) SoC used in the Intel Edison board and
+	  a small number of Android devices such as the Asus Zenfone 2,
+	  Asus FonePad 8 and Dell Venue 7.
+
+	  If you are building for a PC class system or non-MID tablet
+	  SoCs like Bay Trail (Z36xx/Z37xx), say N here.
+
+	  Intel MID platforms are based on an Intel processor and chipset which
+	  consume less power than most of the x86 derivatives.
 
 config X86_GOLDFISH
 	bool "Goldfish (Virtual Platform)"
@@ -610,6 +633,9 @@ config X86_GOLDFISH
 	  for Android development. Unless you are building for the Android
 	  Goldfish emulator say N here.
 
+# Following is an alphabetically sorted list of 32 bit extended platforms
+# Please maintain the alphabetic order if and when there are additions
+
 config X86_INTEL_CE
 	bool "CE4100 TV platform"
 	depends on PCI
@@ -625,24 +651,6 @@ config X86_INTEL_CE
 	  This option compiles in support for the CE4100 SOC for settop
 	  boxes and media devices.
 
-config X86_INTEL_MID
-	bool "Intel MID platform support"
-	depends on X86_EXTENDED_PLATFORM
-	depends on X86_PLATFORM_DEVICES
-	depends on PCI
-	depends on X86_64 || (PCI_GOANY && X86_32)
-	depends on X86_IO_APIC
-	select I2C
-	select DW_APB_TIMER
-	select INTEL_SCU_PCI
-	help
-	  Select to build a kernel capable of supporting Intel MID (Mobile
-	  Internet Device) platform systems which do not have the PCI legacy
-	  interfaces. If you are building for a PC class system say N here.
-
-	  Intel MID platforms are based on an Intel processor and chipset which
-	  consume less power than most of the x86 derivatives.
-
 config X86_INTEL_QUARK
 	bool "Intel Quark platform support"
 	depends on X86_32

From dcbb01fbb7aeed0fae4dc1389a36842c77f4f381 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 26 Feb 2025 22:37:13 +0100
Subject: [PATCH 0724/1173] x86/pci: Remove old STA2x11 support

ST ConneXt STA2x11 was an interface chip for Atom E6xx processors,
using a number of components usually found on Arm SoCs. Most of this
was merged upstream, but it was never complete enough to actually work
and has been abandoned for many years.

We already had an agreement on removing it in 2022, but nobody ever
submitted the patch to do it.

Without STA2x11, CONFIG_X86_32_NON_STANDARD no longer has any
use - remove it.

Suggested-by: Davide Ciminaghi <ciminaghi@gnudd.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250226213714.4040853-10-arnd@kernel.org
---
 arch/x86/Kconfig               |  32 +----
 arch/x86/include/asm/sta2x11.h |  13 --
 arch/x86/pci/Makefile          |   2 -
 arch/x86/pci/sta2x11-fixup.c   | 233 ---------------------------------
 4 files changed, 3 insertions(+), 277 deletions(-)
 delete mode 100644 arch/x86/include/asm/sta2x11.h
 delete mode 100644 arch/x86/pci/sta2x11-fixup.c

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index acd4d73502d60..383b145ffe9fc 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -548,7 +548,6 @@ config X86_EXTENDED_PLATFORM
 		AMD Elan
 		RDC R-321x SoC
 		SGI 320/540 (Visual Workstation)
-		STA2X11-based (e.g. Northville)
 
 	  64-bit platforms (CONFIG_64BIT=y):
 		Numascale NumaChip
@@ -732,18 +731,6 @@ config X86_RDC321X
 	  as R-8610-(G).
 	  If you don't have one of these chips, you should say N here.
 
-config X86_32_NON_STANDARD
-	bool "Support non-standard 32-bit SMP architectures"
-	depends on X86_32 && SMP
-	depends on X86_EXTENDED_PLATFORM
-	help
-	  This option compiles in the STA2X11 default
-	  subarchitecture.  It is intended for a generic binary
-	  kernel. If you select them all, kernel will probe it one by
-	  one and will fallback to default.
-
-# Alphabetically sorted list of Non standard 32 bit platforms
-
 config X86_SUPPORTS_MEMORY_FAILURE
 	def_bool y
 	# MCE code calls memory_failure():
@@ -753,19 +740,6 @@ config X86_SUPPORTS_MEMORY_FAILURE
 	depends on X86_64 || !SPARSEMEM
 	select ARCH_SUPPORTS_MEMORY_FAILURE
 
-config STA2X11
-	bool "STA2X11 Companion Chip Support"
-	depends on X86_32_NON_STANDARD && PCI
-	select SWIOTLB
-	select MFD_STA2X11
-	select GPIOLIB
-	help
-	  This adds support for boards based on the STA2X11 IO-Hub,
-	  a.k.a. "ConneXt". The chip is used in place of the standard
-	  PC chipset, so all "standard" peripherals are missing. If this
-	  option is selected the kernel will still be able to boot on
-	  standard PC machines.
-
 config X86_32_IRIS
 	tristate "Eurobraille/Iris poweroff module"
 	depends on X86_32
@@ -1103,7 +1077,7 @@ config UP_LATE_INIT
 config X86_UP_APIC
 	bool "Local APIC support on uniprocessors" if !PCI_MSI
 	default PCI_MSI
-	depends on X86_32 && !SMP && !X86_32_NON_STANDARD
+	depends on X86_32 && !SMP
 	help
 	  A local APIC (Advanced Programmable Interrupt Controller) is an
 	  integrated interrupt controller in the CPU. If you have a single-CPU
@@ -1128,7 +1102,7 @@ config X86_UP_IOAPIC
 
 config X86_LOCAL_APIC
 	def_bool y
-	depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC || PCI_MSI
+	depends on X86_64 || SMP || X86_UP_APIC || PCI_MSI
 	select IRQ_DOMAIN_HIERARCHY
 
 config ACPI_MADT_WAKEUP
@@ -1590,7 +1564,7 @@ config ARCH_FLATMEM_ENABLE
 
 config ARCH_SPARSEMEM_ENABLE
 	def_bool y
-	depends on X86_64 || NUMA || X86_32 || X86_32_NON_STANDARD
+	depends on X86_64 || NUMA || X86_32
 	select SPARSEMEM_STATIC if X86_32
 	select SPARSEMEM_VMEMMAP_ENABLE if X86_64
 
diff --git a/arch/x86/include/asm/sta2x11.h b/arch/x86/include/asm/sta2x11.h
deleted file mode 100644
index e0975e9c4f477..0000000000000
--- a/arch/x86/include/asm/sta2x11.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Header file for STMicroelectronics ConneXt (STA2X11) IOHub
- */
-#ifndef __ASM_STA2X11_H
-#define __ASM_STA2X11_H
-
-#include <linux/pci.h>
-
-/* This needs to be called from the MFD to configure its sub-devices */
-struct sta2x11_instance *sta2x11_get_instance(struct pci_dev *pdev);
-
-#endif /* __ASM_STA2X11_H */
diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile
index 48bcada5cabe5..4933fb3379832 100644
--- a/arch/x86/pci/Makefile
+++ b/arch/x86/pci/Makefile
@@ -12,8 +12,6 @@ obj-$(CONFIG_X86_INTEL_CE)      += ce4100.o
 obj-$(CONFIG_ACPI)		+= acpi.o
 obj-y				+= legacy.o irq.o
 
-obj-$(CONFIG_STA2X11)           += sta2x11-fixup.o
-
 obj-$(CONFIG_X86_NUMACHIP)	+= numachip.o
 
 obj-$(CONFIG_X86_INTEL_MID)	+= intel_mid_pci.o
diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c
deleted file mode 100644
index 8c8ddc4dcc08d..0000000000000
--- a/arch/x86/pci/sta2x11-fixup.c
+++ /dev/null
@@ -1,233 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * DMA translation between STA2x11 AMBA memory mapping and the x86 memory mapping
- *
- * ST Microelectronics ConneXt (STA2X11/STA2X10)
- *
- * Copyright (c) 2010-2011 Wind River Systems, Inc.
- */
-
-#include <linux/pci.h>
-#include <linux/pci_ids.h>
-#include <linux/export.h>
-#include <linux/list.h>
-#include <linux/dma-map-ops.h>
-#include <linux/swiotlb.h>
-#include <asm/iommu.h>
-#include <asm/sta2x11.h>
-
-#define STA2X11_SWIOTLB_SIZE (4*1024*1024)
-
-/*
- * We build a list of bus numbers that are under the ConneXt. The
- * main bridge hosts 4 busses, which are the 4 endpoints, in order.
- */
-#define STA2X11_NR_EP		4	/* 0..3 included */
-#define STA2X11_NR_FUNCS	8	/* 0..7 included */
-#define STA2X11_AMBA_SIZE	(512 << 20)
-
-struct sta2x11_ahb_regs { /* saved during suspend */
-	u32 base, pexlbase, pexhbase, crw;
-};
-
-struct sta2x11_mapping {
-	int is_suspended;
-	struct sta2x11_ahb_regs regs[STA2X11_NR_FUNCS];
-};
-
-struct sta2x11_instance {
-	struct list_head list;
-	int bus0;
-	struct sta2x11_mapping map[STA2X11_NR_EP];
-};
-
-static LIST_HEAD(sta2x11_instance_list);
-
-/* At probe time, record new instances of this bridge (likely one only) */
-static void sta2x11_new_instance(struct pci_dev *pdev)
-{
-	struct sta2x11_instance *instance;
-
-	instance = kzalloc(sizeof(*instance), GFP_ATOMIC);
-	if (!instance)
-		return;
-	/* This has a subordinate bridge, with 4 more-subordinate ones */
-	instance->bus0 = pdev->subordinate->number + 1;
-
-	if (list_empty(&sta2x11_instance_list)) {
-		int size = STA2X11_SWIOTLB_SIZE;
-		/* First instance: register your own swiotlb area */
-		dev_info(&pdev->dev, "Using SWIOTLB (size %i)\n", size);
-		if (swiotlb_init_late(size, GFP_DMA, NULL))
-			dev_emerg(&pdev->dev, "init swiotlb failed\n");
-	}
-	list_add(&instance->list, &sta2x11_instance_list);
-}
-DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_STMICRO, 0xcc17, sta2x11_new_instance);
-
-/*
- * Utility functions used in this file from below
- */
-static struct sta2x11_instance *sta2x11_pdev_to_instance(struct pci_dev *pdev)
-{
-	struct sta2x11_instance *instance;
-	int ep;
-
-	list_for_each_entry(instance, &sta2x11_instance_list, list) {
-		ep = pdev->bus->number - instance->bus0;
-		if (ep >= 0 && ep < STA2X11_NR_EP)
-			return instance;
-	}
-	return NULL;
-}
-
-static int sta2x11_pdev_to_ep(struct pci_dev *pdev)
-{
-	struct sta2x11_instance *instance;
-
-	instance = sta2x11_pdev_to_instance(pdev);
-	if (!instance)
-		return -1;
-
-	return pdev->bus->number - instance->bus0;
-}
-
-/* This is exported, as some devices need to access the MFD registers */
-struct sta2x11_instance *sta2x11_get_instance(struct pci_dev *pdev)
-{
-	return sta2x11_pdev_to_instance(pdev);
-}
-EXPORT_SYMBOL(sta2x11_get_instance);
-
-/* At setup time, we use our own ops if the device is a ConneXt one */
-static void sta2x11_setup_pdev(struct pci_dev *pdev)
-{
-	struct sta2x11_instance *instance = sta2x11_pdev_to_instance(pdev);
-
-	if (!instance) /* either a sta2x11 bridge or another ST device */
-		return;
-
-	/* We must enable all devices as master, for audio DMA to work */
-	pci_set_master(pdev);
-}
-DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_STMICRO, PCI_ANY_ID, sta2x11_setup_pdev);
-
-/*
- * At boot we must set up the mappings for the pcie-to-amba bridge.
- * It involves device access, and the same happens at suspend/resume time
- */
-
-#define AHB_MAPB		0xCA4
-#define AHB_CRW(i)		(AHB_MAPB + 0  + (i) * 0x10)
-#define AHB_CRW_SZMASK			0xfffffc00UL
-#define AHB_CRW_ENABLE			(1 << 0)
-#define AHB_CRW_WTYPE_MEM		(2 << 1)
-#define AHB_CRW_ROE			(1UL << 3)	/* Relax Order Ena */
-#define AHB_CRW_NSE			(1UL << 4)	/* No Snoop Enable */
-#define AHB_BASE(i)		(AHB_MAPB + 4  + (i) * 0x10)
-#define AHB_PEXLBASE(i)		(AHB_MAPB + 8  + (i) * 0x10)
-#define AHB_PEXHBASE(i)		(AHB_MAPB + 12 + (i) * 0x10)
-
-/* At probe time, enable mapping for each endpoint, using the pdev */
-static void sta2x11_map_ep(struct pci_dev *pdev)
-{
-	struct sta2x11_instance *instance = sta2x11_pdev_to_instance(pdev);
-	struct device *dev = &pdev->dev;
-	u32 amba_base, max_amba_addr;
-	int i, ret;
-
-	if (!instance)
-		return;
-
-	pci_read_config_dword(pdev, AHB_BASE(0), &amba_base);
-	max_amba_addr = amba_base + STA2X11_AMBA_SIZE - 1;
-
-	ret = dma_direct_set_offset(dev, 0, amba_base, STA2X11_AMBA_SIZE);
-	if (ret)
-		dev_err(dev, "sta2x11: could not set DMA offset\n");
-
-	dev->bus_dma_limit = max_amba_addr;
-	dma_set_mask_and_coherent(&pdev->dev, max_amba_addr);
-
-	/* Configure AHB mapping */
-	pci_write_config_dword(pdev, AHB_PEXLBASE(0), 0);
-	pci_write_config_dword(pdev, AHB_PEXHBASE(0), 0);
-	pci_write_config_dword(pdev, AHB_CRW(0), STA2X11_AMBA_SIZE |
-			       AHB_CRW_WTYPE_MEM | AHB_CRW_ENABLE);
-
-	/* Disable all the other windows */
-	for (i = 1; i < STA2X11_NR_FUNCS; i++)
-		pci_write_config_dword(pdev, AHB_CRW(i), 0);
-
-	dev_info(&pdev->dev,
-		 "sta2x11: Map EP %i: AMBA address %#8x-%#8x\n",
-		 sta2x11_pdev_to_ep(pdev), amba_base, max_amba_addr);
-}
-DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_STMICRO, PCI_ANY_ID, sta2x11_map_ep);
-
-#ifdef CONFIG_PM /* Some register values must be saved and restored */
-
-static struct sta2x11_mapping *sta2x11_pdev_to_mapping(struct pci_dev *pdev)
-{
-	struct sta2x11_instance *instance;
-	int ep;
-
-	instance = sta2x11_pdev_to_instance(pdev);
-	if (!instance)
-		return NULL;
-	ep = sta2x11_pdev_to_ep(pdev);
-	return instance->map + ep;
-}
-
-static void suspend_mapping(struct pci_dev *pdev)
-{
-	struct sta2x11_mapping *map = sta2x11_pdev_to_mapping(pdev);
-	int i;
-
-	if (!map)
-		return;
-
-	if (map->is_suspended)
-		return;
-	map->is_suspended = 1;
-
-	/* Save all window configs */
-	for (i = 0; i < STA2X11_NR_FUNCS; i++) {
-		struct sta2x11_ahb_regs *regs = map->regs + i;
-
-		pci_read_config_dword(pdev, AHB_BASE(i), &regs->base);
-		pci_read_config_dword(pdev, AHB_PEXLBASE(i), &regs->pexlbase);
-		pci_read_config_dword(pdev, AHB_PEXHBASE(i), &regs->pexhbase);
-		pci_read_config_dword(pdev, AHB_CRW(i), &regs->crw);
-	}
-}
-DECLARE_PCI_FIXUP_SUSPEND(PCI_VENDOR_ID_STMICRO, PCI_ANY_ID, suspend_mapping);
-
-static void resume_mapping(struct pci_dev *pdev)
-{
-	struct sta2x11_mapping *map = sta2x11_pdev_to_mapping(pdev);
-	int i;
-
-	if (!map)
-		return;
-
-
-	if (!map->is_suspended)
-		goto out;
-	map->is_suspended = 0;
-
-	/* Restore all window configs */
-	for (i = 0; i < STA2X11_NR_FUNCS; i++) {
-		struct sta2x11_ahb_regs *regs = map->regs + i;
-
-		pci_write_config_dword(pdev, AHB_BASE(i), regs->base);
-		pci_write_config_dword(pdev, AHB_PEXLBASE(i), regs->pexlbase);
-		pci_write_config_dword(pdev, AHB_PEXHBASE(i), regs->pexhbase);
-		pci_write_config_dword(pdev, AHB_CRW(i), regs->crw);
-	}
-out:
-	pci_set_master(pdev); /* Like at boot, enable master on all devices */
-}
-DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_STMICRO, PCI_ANY_ID, resume_mapping);
-
-#endif /* CONFIG_PM */

From 976ba8da2f3c2f1e997f4f620da83ae65c0e3728 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 26 Feb 2025 22:37:14 +0100
Subject: [PATCH 0725/1173] x86/platform: Only allow CONFIG_EISA for 32-bit

The CONFIG_EISA menu was cleaned up in 2018, but this inadvertently
brought the option back on 64-bit machines: ISA remains guarded by
a CONFIG_X86_32 check, but EISA no longer depends on ISA.

The last Intel machines ith EISA support used a 82375EB PCI/EISA bridge
from 1993 that could be paired with the 440FX chipset on early Pentium-II
CPUs, long before the first x86-64 products.

Fixes: 6630a8e50105 ("eisa: consolidate EISA Kconfig entry in drivers/eisa")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250226213714.4040853-11-arnd@kernel.org
---
 arch/x86/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 383b145ffe9fc..aa90f0355be11 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -233,7 +233,7 @@ config X86
 	select HAVE_SAMPLE_FTRACE_DIRECT_MULTI	if X86_64
 	select HAVE_EBPF_JIT
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
-	select HAVE_EISA
+	select HAVE_EISA			if X86_32
 	select HAVE_EXIT_THREAD
 	select HAVE_GUP_FAST
 	select HAVE_FENTRY			if X86_64 || DYNAMIC_FTRACE

From fc20737d8b85691ecabab3739ed7d06c9b7bc00f Mon Sep 17 00:00:00 2001
From: James Bottomley <James.Bottomley@HansenPartnership.com>
Date: Wed, 26 Feb 2025 16:48:26 -0500
Subject: [PATCH 0726/1173] efivarfs: allow creation of zero length files

Temporarily allow the creation of zero length files in efivarfs so the
'fwupd' user space firmware update tool can continue to operate. This
hack should be reverted as soon as the fwupd mechanisms for updating
firmware have been fixed.

fwupd has been coded to open a firmware file, close it, remove the
immutable bit and write to it.  Since commit 908af31f4896 ("efivarfs:
fix error on write to new variable leaving remnants") this behaviour
results in the first close removing the file which causes the second
write to fail.  To allow fwupd to keep working code up an indicator of
size 1 if a write fails and only remove the file on that condition (so
create at zero size is allowed).

Tested-by: Richard Hughes <richard@hughsie.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
[ardb: replace LVFS with fwupd, as suggested by Richard]
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 fs/efivarfs/file.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c
index cb1b6d0c34545..c294a8fc566da 100644
--- a/fs/efivarfs/file.c
+++ b/fs/efivarfs/file.c
@@ -57,10 +57,11 @@ static ssize_t efivarfs_file_write(struct file *file,
 
 	if (bytes == -ENOENT) {
 		/*
-		 * zero size signals to release that the write deleted
-		 * the variable
+		 * FIXME: temporary workaround for fwupdate, signal
+		 * failed write with a 1 to keep created but not
+		 * written files
 		 */
-		i_size_write(inode, 0);
+		i_size_write(inode, 1);
 	} else {
 		i_size_write(inode, datasize + sizeof(attributes));
 		inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
@@ -124,7 +125,8 @@ static int efivarfs_file_release(struct inode *inode, struct file *file)
 	struct efivar_entry *var = inode->i_private;
 
 	inode_lock(inode);
-	var->removed = (--var->open_count == 0 && i_size_read(inode) == 0);
+	/* FIXME: temporary work around for fwupdate */
+	var->removed = (--var->open_count == 0 && i_size_read(inode) == 1);
 	inode_unlock(inode);
 
 	if (var->removed)

From 1cf9631d836b289bd5490776551961c883ae8a4f Mon Sep 17 00:00:00 2001
From: Nikita Zhandarovich <n.zhandarovich@fintech.ru>
Date: Mon, 24 Feb 2025 20:29:17 +0300
Subject: [PATCH 0727/1173] usbnet: gl620a: fix endpoint checking in
 genelink_bind()

Syzbot reports [1] a warning in usb_submit_urb() triggered by
inconsistencies between expected and actually present endpoints
in gl620a driver. Since genelink_bind() does not properly
verify whether specified eps are in fact provided by the device,
in this case, an artificially manufactured one, one may get a
mismatch.

Fix the issue by resorting to a usbnet utility function
usbnet_get_endpoints(), usually reserved for this very problem.
Check for endpoints and return early before proceeding further if
any are missing.

[1] Syzbot report:
usb 5-1: Manufacturer: syz
usb 5-1: SerialNumber: syz
usb 5-1: config 0 descriptor??
gl620a 5-1:0.23 usb0: register 'gl620a' at usb-dummy_hcd.0-1, ...
------------[ cut here ]------------
usb 5-1: BOGUS urb xfer, pipe 3 != type 1
WARNING: CPU: 2 PID: 1841 at drivers/usb/core/urb.c:503 usb_submit_urb+0xe4b/0x1730 drivers/usb/core/urb.c:503
Modules linked in:
CPU: 2 UID: 0 PID: 1841 Comm: kworker/2:2 Not tainted 6.12.0-syzkaller-07834-g06afb0f36106 #0
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014
Workqueue: mld mld_ifc_work
RIP: 0010:usb_submit_urb+0xe4b/0x1730 drivers/usb/core/urb.c:503
...
Call Trace:
 <TASK>
 usbnet_start_xmit+0x6be/0x2780 drivers/net/usb/usbnet.c:1467
 __netdev_start_xmit include/linux/netdevice.h:5002 [inline]
 netdev_start_xmit include/linux/netdevice.h:5011 [inline]
 xmit_one net/core/dev.c:3590 [inline]
 dev_hard_start_xmit+0x9a/0x7b0 net/core/dev.c:3606
 sch_direct_xmit+0x1ae/0xc30 net/sched/sch_generic.c:343
 __dev_xmit_skb net/core/dev.c:3827 [inline]
 __dev_queue_xmit+0x13d4/0x43e0 net/core/dev.c:4400
 dev_queue_xmit include/linux/netdevice.h:3168 [inline]
 neigh_resolve_output net/core/neighbour.c:1514 [inline]
 neigh_resolve_output+0x5bc/0x950 net/core/neighbour.c:1494
 neigh_output include/net/neighbour.h:539 [inline]
 ip6_finish_output2+0xb1b/0x2070 net/ipv6/ip6_output.c:141
 __ip6_finish_output net/ipv6/ip6_output.c:215 [inline]
 ip6_finish_output+0x3f9/0x1360 net/ipv6/ip6_output.c:226
 NF_HOOK_COND include/linux/netfilter.h:303 [inline]
 ip6_output+0x1f8/0x540 net/ipv6/ip6_output.c:247
 dst_output include/net/dst.h:450 [inline]
 NF_HOOK include/linux/netfilter.h:314 [inline]
 NF_HOOK include/linux/netfilter.h:308 [inline]
 mld_sendpack+0x9f0/0x11d0 net/ipv6/mcast.c:1819
 mld_send_cr net/ipv6/mcast.c:2120 [inline]
 mld_ifc_work+0x740/0xca0 net/ipv6/mcast.c:2651
 process_one_work+0x9c5/0x1ba0 kernel/workqueue.c:3229
 process_scheduled_works kernel/workqueue.c:3310 [inline]
 worker_thread+0x6c8/0xf00 kernel/workqueue.c:3391
 kthread+0x2c1/0x3a0 kernel/kthread.c:389
 ret_from_fork+0x45/0x80 arch/x86/kernel/process.c:147
 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244
 </TASK>

Reported-by: syzbot+d693c07c6f647e0388d3@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=d693c07c6f647e0388d3
Fixes: 47ee3051c856 ("[PATCH] USB: usbnet (5/9) module for genesys gl620a cables")
Cc: stable@vger.kernel.org
Signed-off-by: Nikita Zhandarovich <n.zhandarovich@fintech.ru>
Link: https://patch.msgid.link/20250224172919.1220522-1-n.zhandarovich@fintech.ru
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/usb/gl620a.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/usb/gl620a.c b/drivers/net/usb/gl620a.c
index 46af78caf457a..0bfa37c140591 100644
--- a/drivers/net/usb/gl620a.c
+++ b/drivers/net/usb/gl620a.c
@@ -179,9 +179,7 @@ static int genelink_bind(struct usbnet *dev, struct usb_interface *intf)
 {
 	dev->hard_mtu = GL_RCV_BUF_SIZE;
 	dev->net->hard_header_len += 4;
-	dev->in = usb_rcvbulkpipe(dev->udev, dev->driver_info->in);
-	dev->out = usb_sndbulkpipe(dev->udev, dev->driver_info->out);
-	return 0;
+	return usbnet_get_endpoints(dev, intf);
 }
 
 static const struct driver_info	genelink_info = {

From 4a412c70af674198749fd16be695d53e1c41b5f9 Mon Sep 17 00:00:00 2001
From: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Date: Wed, 11 Dec 2024 22:57:24 -0800
Subject: [PATCH 0728/1173] x86/cpu: Prefix hexadecimal values with 0x in
 cpu_debug_show()

The hex values in CPU debug interface are not prefixed with 0x. This may
cause misinterpretation of values. Fix it.

[ mingo: Restore previous vertical alignment of the output. ]

Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/r/20241211-add-cpu-type-v5-1-2ae010f50370@linux.intel.com
---
 arch/x86/kernel/cpu/debugfs.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/debugfs.c b/arch/x86/kernel/cpu/debugfs.c
index cacfd3f6abeff..1976fef2dfe51 100644
--- a/arch/x86/kernel/cpu/debugfs.c
+++ b/arch/x86/kernel/cpu/debugfs.c
@@ -16,8 +16,8 @@ static int cpu_debug_show(struct seq_file *m, void *p)
 	if (!c->initialized)
 		return 0;
 
-	seq_printf(m, "initial_apicid:      %x\n", c->topo.initial_apicid);
-	seq_printf(m, "apicid:              %x\n", c->topo.apicid);
+	seq_printf(m, "initial_apicid:	    0x%x\n", c->topo.initial_apicid);
+	seq_printf(m, "apicid:		    0x%x\n", c->topo.apicid);
 	seq_printf(m, "pkg_id:              %u\n", c->topo.pkg_id);
 	seq_printf(m, "die_id:              %u\n", c->topo.die_id);
 	seq_printf(m, "cu_id:               %u\n", c->topo.cu_id);

From b52aaeeadfac54c91005e044b72b62616a5864a9 Mon Sep 17 00:00:00 2001
From: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Date: Wed, 11 Dec 2024 22:57:30 -0800
Subject: [PATCH 0729/1173] cpufreq: intel_pstate: Avoid SMP calls to get
 cpu-type

Intel pstate driver relies on SMP calls to get the cpu-type of a given CPU.
Remove the SMP calls and instead use the cached value of cpu-type which is
more efficient.

[ mingo: Forward ported it. ]

Suggested-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/r/20241211-add-cpu-type-v5-2-2ae010f50370@linux.intel.com
---
 drivers/cpufreq/intel_pstate.c | 16 ++++------------
 1 file changed, 4 insertions(+), 12 deletions(-)

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 9c4cc01fd51aa..f06b9bc999456 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -2200,28 +2200,20 @@ static int knl_get_turbo_pstate(int cpu)
 	return ret;
 }
 
-static void hybrid_get_type(void *data)
-{
-	u8 *cpu_type = data;
-
-	*cpu_type = get_this_hybrid_cpu_type();
-}
-
 static int hwp_get_cpu_scaling(int cpu)
 {
 	if (hybrid_scaling_factor) {
-		u8 cpu_type = 0;
-
-		smp_call_function_single(cpu, hybrid_get_type, &cpu_type, 1);
+		struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
+		u8 cpu_type = c->topo.intel_type;
 
 		/*
 		 * Return the hybrid scaling factor for P-cores and use the
 		 * default core scaling for E-cores.
 		 */
-		if (cpu_type == 0x40)
+		if (cpu_type == INTEL_CPU_TYPE_CORE)
 			return hybrid_scaling_factor;
 
-		if (cpu_type == 0x20)
+		if (cpu_type == INTEL_CPU_TYPE_ATOM)
 			return core_get_scaling();
 	}
 

From c4a8b7116b9927f7b00bd68140e285662a03068e Mon Sep 17 00:00:00 2001
From: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Date: Wed, 11 Dec 2024 22:57:36 -0800
Subject: [PATCH 0730/1173] perf/x86/intel: Use cache cpu-type for hybrid PMU
 selection

get_this_hybrid_cpu_type() misses a case when cpu-type is populated
regardless of X86_FEATURE_HYBRID_CPU. This is particularly true for hybrid
variants that have P or E cores fused off.

Instead use the cpu-type cached in struct x86_topology, as it does not rely
on hybrid feature to enumerate cpu-type. This can also help avoid the
model-specific fixup get_hybrid_cpu_type(). Also replace the
get_this_hybrid_cpu_native_id() with its cached value in struct
x86_topology.

While at it, remove enum hybrid_cpu_type as it serves no purpose when we
have the exact cpu-types defined in enum intel_cpu_type. Also rename
atom_native_id to intel_native_id and move it to intel-family.h where
intel_cpu_type lives.

Suggested-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/r/20241211-add-cpu-type-v5-3-2ae010f50370@linux.intel.com
---
 arch/x86/events/intel/core.c        | 19 ++++++++++---------
 arch/x86/events/perf_event.h        | 19 +------------------
 arch/x86/include/asm/intel-family.h | 15 ++++++++++++++-
 3 files changed, 25 insertions(+), 28 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 3cf65e93a03fd..397c545b86105 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -4606,9 +4606,9 @@ static int adl_hw_config(struct perf_event *event)
 	return -EOPNOTSUPP;
 }
 
-static enum hybrid_cpu_type adl_get_hybrid_cpu_type(void)
+static enum intel_cpu_type adl_get_hybrid_cpu_type(void)
 {
-	return HYBRID_INTEL_CORE;
+	return INTEL_CPU_TYPE_CORE;
 }
 
 static inline bool erratum_hsw11(struct perf_event *event)
@@ -4953,7 +4953,8 @@ static void intel_pmu_check_hybrid_pmus(struct x86_hybrid_pmu *pmu)
 
 static struct x86_hybrid_pmu *find_hybrid_pmu_for_cpu(void)
 {
-	u8 cpu_type = get_this_hybrid_cpu_type();
+	struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
+	enum intel_cpu_type cpu_type = c->topo.intel_type;
 	int i;
 
 	/*
@@ -4962,7 +4963,7 @@ static struct x86_hybrid_pmu *find_hybrid_pmu_for_cpu(void)
 	 * on it. There should be a fixup function provided for these
 	 * troublesome CPUs (->get_hybrid_cpu_type).
 	 */
-	if (cpu_type == HYBRID_INTEL_NONE) {
+	if (cpu_type == INTEL_CPU_TYPE_UNKNOWN) {
 		if (x86_pmu.get_hybrid_cpu_type)
 			cpu_type = x86_pmu.get_hybrid_cpu_type();
 		else
@@ -4979,16 +4980,16 @@ static struct x86_hybrid_pmu *find_hybrid_pmu_for_cpu(void)
 		enum hybrid_pmu_type pmu_type = x86_pmu.hybrid_pmu[i].pmu_type;
 		u32 native_id;
 
-		if (cpu_type == HYBRID_INTEL_CORE && pmu_type == hybrid_big)
+		if (cpu_type == INTEL_CPU_TYPE_CORE && pmu_type == hybrid_big)
 			return &x86_pmu.hybrid_pmu[i];
-		if (cpu_type == HYBRID_INTEL_ATOM) {
+		if (cpu_type == INTEL_CPU_TYPE_ATOM) {
 			if (x86_pmu.num_hybrid_pmus == 2 && pmu_type == hybrid_small)
 				return &x86_pmu.hybrid_pmu[i];
 
-			native_id = get_this_hybrid_cpu_native_id();
-			if (native_id == skt_native_id && pmu_type == hybrid_small)
+			native_id = c->topo.intel_native_model_id;
+			if (native_id == INTEL_ATOM_SKT_NATIVE_ID && pmu_type == hybrid_small)
 				return &x86_pmu.hybrid_pmu[i];
-			if (native_id == cmt_native_id && pmu_type == hybrid_tiny)
+			if (native_id == INTEL_ATOM_CMT_NATIVE_ID && pmu_type == hybrid_tiny)
 				return &x86_pmu.hybrid_pmu[i];
 		}
 	}
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 31c2771545a6c..7b18754084a6e 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -669,18 +669,6 @@ enum {
 #define PERF_PEBS_DATA_SOURCE_GRT_MAX	0x10
 #define PERF_PEBS_DATA_SOURCE_GRT_MASK	(PERF_PEBS_DATA_SOURCE_GRT_MAX - 1)
 
-/*
- * CPUID.1AH.EAX[31:0] uniquely identifies the microarchitecture
- * of the core. Bits 31-24 indicates its core type (Core or Atom)
- * and Bits [23:0] indicates the native model ID of the core.
- * Core type and native model ID are defined in below enumerations.
- */
-enum hybrid_cpu_type {
-	HYBRID_INTEL_NONE,
-	HYBRID_INTEL_ATOM	= 0x20,
-	HYBRID_INTEL_CORE	= 0x40,
-};
-
 #define X86_HYBRID_PMU_ATOM_IDX		0
 #define X86_HYBRID_PMU_CORE_IDX		1
 #define X86_HYBRID_PMU_TINY_IDX		2
@@ -697,11 +685,6 @@ enum hybrid_pmu_type {
 	hybrid_big_small_tiny	= hybrid_big   | hybrid_small_tiny,
 };
 
-enum atom_native_id {
-	cmt_native_id           = 0x2,  /* Crestmont */
-	skt_native_id           = 0x3,  /* Skymont */
-};
-
 struct x86_hybrid_pmu {
 	struct pmu			pmu;
 	const char			*name;
@@ -994,7 +977,7 @@ struct x86_pmu {
 	 */
 	int				num_hybrid_pmus;
 	struct x86_hybrid_pmu		*hybrid_pmu;
-	enum hybrid_cpu_type (*get_hybrid_cpu_type)	(void);
+	enum intel_cpu_type (*get_hybrid_cpu_type)	(void);
 };
 
 struct x86_perf_task_context_opt {
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index f9f67afeb48a7..b657d78071c68 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -182,10 +182,23 @@
 /* Family 19 */
 #define INTEL_PANTHERCOVE_X		IFM(19, 0x01) /* Diamond Rapids */
 
-/* CPU core types */
+/*
+ * Intel CPU core types
+ *
+ * CPUID.1AH.EAX[31:0] uniquely identifies the microarchitecture
+ * of the core. Bits 31-24 indicates its core type (Core or Atom)
+ * and Bits [23:0] indicates the native model ID of the core.
+ * Core type and native model ID are defined in below enumerations.
+ */
 enum intel_cpu_type {
+	INTEL_CPU_TYPE_UNKNOWN,
 	INTEL_CPU_TYPE_ATOM = 0x20,
 	INTEL_CPU_TYPE_CORE = 0x40,
 };
 
+enum intel_native_id {
+	INTEL_ATOM_CMT_NATIVE_ID = 0x2,  /* Crestmont */
+	INTEL_ATOM_SKT_NATIVE_ID = 0x3,  /* Skymont */
+};
+
 #endif /* _ASM_X86_INTEL_FAMILY_H */

From db5157df149709c02e6a08c0b3498553bdd2a76c Mon Sep 17 00:00:00 2001
From: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Date: Wed, 11 Dec 2024 22:57:41 -0800
Subject: [PATCH 0731/1173] x86/cpu: Remove get_this_hybrid_cpu_*()

Because calls to get_this_hybrid_cpu_type() and
get_this_hybrid_cpu_native_id() are not required now. cpu-type and
native-model-id are cached at boot in per-cpu struct cpuinfo_topology.

Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/r/20241211-add-cpu-type-v5-4-2ae010f50370@linux.intel.com
---
 arch/x86/include/asm/cpu.h  | 14 --------------
 arch/x86/kernel/cpu/intel.c | 31 -------------------------------
 2 files changed, 45 deletions(-)

diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index 98eced5084ca7..0c8ec62789a12 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -50,20 +50,6 @@ static inline void split_lock_init(void) {}
 static inline void bus_lock_init(void) {}
 #endif
 
-#ifdef CONFIG_CPU_SUP_INTEL
-u8 get_this_hybrid_cpu_type(void);
-u32 get_this_hybrid_cpu_native_id(void);
-#else
-static inline u8 get_this_hybrid_cpu_type(void)
-{
-	return 0;
-}
-
-static inline u32 get_this_hybrid_cpu_native_id(void)
-{
-	return 0;
-}
-#endif
 #ifdef CONFIG_IA32_FEAT_CTL
 void init_ia32_feat_ctl(struct cpuinfo_x86 *c);
 #else
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 3dce22f00dc34..045b439c653a5 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -873,34 +873,3 @@ static const struct cpu_dev intel_cpu_dev = {
 };
 
 cpu_dev_register(intel_cpu_dev);
-
-#define X86_HYBRID_CPU_TYPE_ID_SHIFT	24
-
-/**
- * get_this_hybrid_cpu_type() - Get the type of this hybrid CPU
- *
- * Returns the CPU type [31:24] (i.e., Atom or Core) of a CPU in
- * a hybrid processor. If the processor is not hybrid, returns 0.
- */
-u8 get_this_hybrid_cpu_type(void)
-{
-	if (!cpu_feature_enabled(X86_FEATURE_HYBRID_CPU))
-		return 0;
-
-	return cpuid_eax(0x0000001a) >> X86_HYBRID_CPU_TYPE_ID_SHIFT;
-}
-
-/**
- * get_this_hybrid_cpu_native_id() - Get the native id of this hybrid CPU
- *
- * Returns the uarch native ID [23:0] of a CPU in a hybrid processor.
- * If the processor is not hybrid, returns 0.
- */
-u32 get_this_hybrid_cpu_native_id(void)
-{
-	if (!cpu_feature_enabled(X86_FEATURE_HYBRID_CPU))
-		return 0;
-
-	return cpuid_eax(0x0000001a) &
-	       (BIT_ULL(X86_HYBRID_CPU_TYPE_ID_SHIFT) - 1);
-}

From 9c94c14ca39577b6324c667d8450ffa19fc1e5c4 Mon Sep 17 00:00:00 2001
From: Kuan-Wei Chiu <visitorckw@gmail.com>
Date: Thu, 27 Feb 2025 13:55:45 +0100
Subject: [PATCH 0732/1173] x86/bootflag: Replace open-coded parity calculation
 with parity8()

Refactor parity calculations to use the standard parity8() helper. This
change eliminates redundant implementations and improves code
efficiency.

[ ubizjak: Updated the patch to apply to the latest x86 tree. ]

Co-developed-by: Yu-Chun Lin <eleanor15x@gmail.com>
Signed-off-by: Yu-Chun Lin <eleanor15x@gmail.com>
Signed-off-by: Kuan-Wei Chiu <visitorckw@gmail.com>
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Link: https://lore.kernel.org/r/20250227125616.2253774-1-ubizjak@gmail.com
---
 arch/x86/kernel/bootflag.c | 18 +++---------------
 1 file changed, 3 insertions(+), 15 deletions(-)

diff --git a/arch/x86/kernel/bootflag.c b/arch/x86/kernel/bootflag.c
index b935c3e42bfdf..73274d76ce167 100644
--- a/arch/x86/kernel/bootflag.c
+++ b/arch/x86/kernel/bootflag.c
@@ -8,6 +8,7 @@
 #include <linux/string.h>
 #include <linux/spinlock.h>
 #include <linux/acpi.h>
+#include <linux/bitops.h>
 #include <asm/io.h>
 
 #include <linux/mc146818rtc.h>
@@ -20,25 +21,12 @@
 
 int sbf_port __initdata = -1;	/* set via acpi_boot_init() */
 
-static bool __init parity(u8 v)
-{
-	int x = 0;
-	int i;
-
-	for (i = 0; i < 8; i++) {
-		x ^= (v & 1);
-		v >>= 1;
-	}
-
-	return !!x;
-}
-
 static void __init sbf_write(u8 v)
 {
 	unsigned long flags;
 
 	if (sbf_port != -1) {
-		if (!parity(v))
+		if (!parity8(v))
 			v ^= SBF_PARITY;
 
 		printk(KERN_INFO "Simple Boot Flag at 0x%x set to 0x%x\n",
@@ -69,7 +57,7 @@ static bool __init sbf_value_valid(u8 v)
 {
 	if (v & SBF_RESERVED)		/* Reserved bits */
 		return false;
-	if (!parity(v))
+	if (!parity8(v))
 		return false;
 
 	return true;

From c64a0727f9b1cbc63a5538c8c0014e9a175ad864 Mon Sep 17 00:00:00 2001
From: Justin Iurman <justin.iurman@uliege.be>
Date: Tue, 25 Feb 2025 18:51:38 +0100
Subject: [PATCH 0733/1173] net: ipv6: fix dst ref loop on input in seg6 lwt

Prevent a dst ref loop on input in seg6_iptunnel.

Fixes: af4a2209b134 ("ipv6: sr: use dst_cache in seg6_input")
Cc: David Lebrun <dlebrun@google.com>
Cc: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Justin Iurman <justin.iurman@uliege.be>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv6/seg6_iptunnel.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 33833b2064c07..51583461ae29b 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -472,10 +472,18 @@ static int seg6_input_core(struct net *net, struct sock *sk,
 {
 	struct dst_entry *orig_dst = skb_dst(skb);
 	struct dst_entry *dst = NULL;
+	struct lwtunnel_state *lwtst;
 	struct seg6_lwt *slwt;
 	int err;
 
-	slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate);
+	/* We cannot dereference "orig_dst" once ip6_route_input() or
+	 * skb_dst_drop() is called. However, in order to detect a dst loop, we
+	 * need the address of its lwtstate. So, save the address of lwtstate
+	 * now and use it later as a comparison.
+	 */
+	lwtst = orig_dst->lwtstate;
+
+	slwt = seg6_lwt_lwtunnel(lwtst);
 
 	local_bh_disable();
 	dst = dst_cache_get(&slwt->cache);
@@ -490,7 +498,9 @@ static int seg6_input_core(struct net *net, struct sock *sk,
 	if (!dst) {
 		ip6_route_input(skb);
 		dst = skb_dst(skb);
-		if (!dst->error) {
+
+		/* cache only if we don't create a dst reference loop */
+		if (!dst->error && lwtst != dst->lwtstate) {
 			local_bh_disable();
 			dst_cache_set_ip6(&slwt->cache, dst,
 					  &ipv6_hdr(skb)->saddr);

From 13e55fbaec176119cff68a7e1693b251c8883c5f Mon Sep 17 00:00:00 2001
From: Justin Iurman <justin.iurman@uliege.be>
Date: Tue, 25 Feb 2025 18:51:39 +0100
Subject: [PATCH 0734/1173] net: ipv6: fix dst ref loop on input in rpl lwt

Prevent a dst ref loop on input in rpl_iptunnel.

Fixes: a7a29f9c361f ("net: ipv6: add rpl sr tunnel")
Cc: Alexander Aring <alex.aring@gmail.com>
Cc: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Justin Iurman <justin.iurman@uliege.be>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv6/rpl_iptunnel.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/rpl_iptunnel.c b/net/ipv6/rpl_iptunnel.c
index 0ac4283acdf20..7c05ac846646f 100644
--- a/net/ipv6/rpl_iptunnel.c
+++ b/net/ipv6/rpl_iptunnel.c
@@ -262,10 +262,18 @@ static int rpl_input(struct sk_buff *skb)
 {
 	struct dst_entry *orig_dst = skb_dst(skb);
 	struct dst_entry *dst = NULL;
+	struct lwtunnel_state *lwtst;
 	struct rpl_lwt *rlwt;
 	int err;
 
-	rlwt = rpl_lwt_lwtunnel(orig_dst->lwtstate);
+	/* We cannot dereference "orig_dst" once ip6_route_input() or
+	 * skb_dst_drop() is called. However, in order to detect a dst loop, we
+	 * need the address of its lwtstate. So, save the address of lwtstate
+	 * now and use it later as a comparison.
+	 */
+	lwtst = orig_dst->lwtstate;
+
+	rlwt = rpl_lwt_lwtunnel(lwtst);
 
 	local_bh_disable();
 	dst = dst_cache_get(&rlwt->cache);
@@ -280,7 +288,9 @@ static int rpl_input(struct sk_buff *skb)
 	if (!dst) {
 		ip6_route_input(skb);
 		dst = skb_dst(skb);
-		if (!dst->error) {
+
+		/* cache only if we don't create a dst reference loop */
+		if (!dst->error && lwtst != dst->lwtstate) {
 			local_bh_disable();
 			dst_cache_set_ip6(&rlwt->cache, dst,
 					  &ipv6_hdr(skb)->saddr);

From 1cbddbddee68d17feb6467fc556c144777af91ef Mon Sep 17 00:00:00 2001
From: Joe Damato <jdamato@fastly.com>
Date: Wed, 26 Feb 2025 18:19:57 +0000
Subject: [PATCH 0735/1173] selftests: drv-net: Check if combined-count exists

Some drivers, like tg3, do not set combined-count:

$ ethtool -l enp4s0f1
Channel parameters for enp4s0f1:
Pre-set maximums:
RX:		4
TX:		4
Other:		n/a
Combined:	n/a
Current hardware settings:
RX:		4
TX:		1
Other:		n/a
Combined:	n/a

In the case where combined-count is not set, the ethtool netlink code
in the kernel elides the value and the code in the test:

  netnl.channels_get(...)

With a tg3 device, the returned dictionary looks like:

{'header': {'dev-index': 3, 'dev-name': 'enp4s0f1'},
 'rx-max': 4,
 'rx-count': 4,
 'tx-max': 4,
 'tx-count': 1}

Note that the key 'combined-count' is missing. As a result of this
missing key the test raises an exception:

 # Exception|     if channels['combined-count'] == 0:
 # Exception|        ~~~~~~~~^^^^^^^^^^^^^^^^^^
 # Exception| KeyError: 'combined-count'

Change the test to check if 'combined-count' is a key in the dictionary
first and if not assume that this means the driver has separate RX and
TX queues.

With this change, the test now passes successfully on tg3 and mlx5
(which does have a 'combined-count').

Fixes: 1cf270424218 ("net: selftest: add test for netdev netlink queue-get API")
Signed-off-by: Joe Damato <jdamato@fastly.com>
Reviewed-by: David Wei <dw@davidwei.uk>
Link: https://patch.msgid.link/20250226181957.212189-1-jdamato@fastly.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/queues.py | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/queues.py b/tools/testing/selftests/drivers/net/queues.py
index 38303da957ee5..8a518905a9f9c 100755
--- a/tools/testing/selftests/drivers/net/queues.py
+++ b/tools/testing/selftests/drivers/net/queues.py
@@ -45,10 +45,9 @@ def addremove_queues(cfg, nl) -> None:
 
     netnl = EthtoolFamily()
     channels = netnl.channels_get({'header': {'dev-index': cfg.ifindex}})
-    if channels['combined-count'] == 0:
-        rx_type = 'rx'
-    else:
-        rx_type = 'combined'
+    rx_type = 'rx'
+    if channels.get('combined-count', 0) > 0:
+            rx_type = 'combined'
 
     expected = curr_queues - 1
     cmd(f"ethtool -L {cfg.dev['ifname']} {rx_type} {expected}", timeout=10)

From 674fcb4f4a7e3e277417a01788cc6daae47c3804 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 26 Feb 2025 22:12:52 +0000
Subject: [PATCH 0736/1173] idpf: fix checksums set in idpf_rx_rsc()

idpf_rx_rsc() uses skb_transport_offset(skb) while the transport header
is not set yet.

This triggers the following warning for CONFIG_DEBUG_NET=y builds.

DEBUG_NET_WARN_ON_ONCE(!skb_transport_header_was_set(skb))

[   69.261620] WARNING: CPU: 7 PID: 0 at ./include/linux/skbuff.h:3020 idpf_vport_splitq_napi_poll (include/linux/skbuff.h:3020) idpf
[   69.261629] Modules linked in: vfat fat dummy bridge intel_uncore_frequency_tpmi intel_uncore_frequency_common intel_vsec_tpmi idpf intel_vsec cdc_ncm cdc_eem cdc_ether usbnet mii xhci_pci xhci_hcd ehci_pci ehci_hcd libeth
[   69.261644] CPU: 7 UID: 0 PID: 0 Comm: swapper/7 Tainted: G S      W          6.14.0-smp-DEV #1697
[   69.261648] Tainted: [S]=CPU_OUT_OF_SPEC, [W]=WARN
[   69.261650] RIP: 0010:idpf_vport_splitq_napi_poll (include/linux/skbuff.h:3020) idpf
[   69.261677] ? __warn (kernel/panic.c:242 kernel/panic.c:748)
[   69.261682] ? idpf_vport_splitq_napi_poll (include/linux/skbuff.h:3020) idpf
[   69.261687] ? report_bug (lib/bug.c:?)
[   69.261690] ? handle_bug (arch/x86/kernel/traps.c:285)
[   69.261694] ? exc_invalid_op (arch/x86/kernel/traps.c:309)
[   69.261697] ? asm_exc_invalid_op (arch/x86/include/asm/idtentry.h:621)
[   69.261700] ? __pfx_idpf_vport_splitq_napi_poll (drivers/net/ethernet/intel/idpf/idpf_txrx.c:4011) idpf
[   69.261704] ? idpf_vport_splitq_napi_poll (include/linux/skbuff.h:3020) idpf
[   69.261708] ? idpf_vport_splitq_napi_poll (drivers/net/ethernet/intel/idpf/idpf_txrx.c:3072) idpf
[   69.261712] __napi_poll (net/core/dev.c:7194)
[   69.261716] net_rx_action (net/core/dev.c:7265)
[   69.261718] ? __qdisc_run (net/sched/sch_generic.c:293)
[   69.261721] ? sched_clock (arch/x86/include/asm/preempt.h:84 arch/x86/kernel/tsc.c:288)
[   69.261726] handle_softirqs (kernel/softirq.c:561)

Fixes: 3a8845af66edb ("idpf: add RX splitq napi poll support")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Alan Brady <alan.brady@intel.com>
Cc: Joshua Hay <joshua.a.hay@intel.com>
Cc: Willem de Bruijn <willemb@google.com>
Acked-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Link: https://patch.msgid.link/20250226221253.1927782-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/idpf/idpf_txrx.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index 9be6a6b59c4e1..977741c414980 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -3013,7 +3013,6 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 	skb_shinfo(skb)->gso_size = rsc_seg_len;
 
 	skb_reset_network_header(skb);
-	len = skb->len - skb_transport_offset(skb);
 
 	if (ipv4) {
 		struct iphdr *ipv4h = ip_hdr(skb);
@@ -3022,6 +3021,7 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 
 		/* Reset and set transport header offset in skb */
 		skb_set_transport_header(skb, sizeof(struct iphdr));
+		len = skb->len - skb_transport_offset(skb);
 
 		/* Compute the TCP pseudo header checksum*/
 		tcp_hdr(skb)->check =
@@ -3031,6 +3031,7 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 
 		skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
 		skb_set_transport_header(skb, sizeof(struct ipv6hdr));
+		len = skb->len - skb_transport_offset(skb);
 		tcp_hdr(skb)->check =
 			~tcp_v6_check(len, &ipv6h->saddr, &ipv6h->daddr, 0);
 	}

From 54e1b4becf5e220be03db4e1be773c1310e8cbbd Mon Sep 17 00:00:00 2001
From: Meghana Malladi <m-malladi@ti.com>
Date: Thu, 27 Feb 2025 14:54:41 +0530
Subject: [PATCH 0737/1173] net: ti: icss-iep: Reject perout generation request

IEP driver supports both perout and pps signal generation
but perout feature is faulty with half-cooked support
due to some missing configuration. Remove perout
support from the driver and reject perout requests with
"not supported" error code.

Fixes: c1e0230eeaab2 ("net: ti: icss-iep: Add IEP driver")
Signed-off-by: Meghana Malladi <m-malladi@ti.com>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://patch.msgid.link/20250227092441.1848419-1-m-malladi@ti.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ti/icssg/icss_iep.c | 21 +--------------------
 1 file changed, 1 insertion(+), 20 deletions(-)

diff --git a/drivers/net/ethernet/ti/icssg/icss_iep.c b/drivers/net/ethernet/ti/icssg/icss_iep.c
index 768578c0d9587..d59c1744840af 100644
--- a/drivers/net/ethernet/ti/icssg/icss_iep.c
+++ b/drivers/net/ethernet/ti/icssg/icss_iep.c
@@ -474,26 +474,7 @@ static int icss_iep_perout_enable_hw(struct icss_iep *iep,
 static int icss_iep_perout_enable(struct icss_iep *iep,
 				  struct ptp_perout_request *req, int on)
 {
-	int ret = 0;
-
-	mutex_lock(&iep->ptp_clk_mutex);
-
-	if (iep->pps_enabled) {
-		ret = -EBUSY;
-		goto exit;
-	}
-
-	if (iep->perout_enabled == !!on)
-		goto exit;
-
-	ret = icss_iep_perout_enable_hw(iep, req, on);
-	if (!ret)
-		iep->perout_enabled = !!on;
-
-exit:
-	mutex_unlock(&iep->ptp_clk_mutex);
-
-	return ret;
+	return -EOPNOTSUPP;
 }
 
 static void icss_iep_cap_cmp_work(struct work_struct *work)

From 2b90e7ace79774a3540ce569e000388f8d22c9e0 Mon Sep 17 00:00:00 2001
From: Peter Jones <pjones@redhat.com>
Date: Wed, 26 Feb 2025 15:18:39 -0500
Subject: [PATCH 0738/1173] efi: Don't map the entire mokvar table to determine
 its size

Currently, when validating the mokvar table, we (re)map the entire table
on each iteration of the loop, adding space as we discover new entries.
If the table grows over a certain size, this fails due to limitations of
early_memmap(), and we get a failure and traceback:

  ------------[ cut here ]------------
  WARNING: CPU: 0 PID: 0 at mm/early_ioremap.c:139 __early_ioremap+0xef/0x220
  ...
  Call Trace:
   <TASK>
   ? __early_ioremap+0xef/0x220
   ? __warn.cold+0x93/0xfa
   ? __early_ioremap+0xef/0x220
   ? report_bug+0xff/0x140
   ? early_fixup_exception+0x5d/0xb0
   ? early_idt_handler_common+0x2f/0x3a
   ? __early_ioremap+0xef/0x220
   ? efi_mokvar_table_init+0xce/0x1d0
   ? setup_arch+0x864/0xc10
   ? start_kernel+0x6b/0xa10
   ? x86_64_start_reservations+0x24/0x30
   ? x86_64_start_kernel+0xed/0xf0
   ? common_startup_64+0x13e/0x141
   </TASK>
  ---[ end trace 0000000000000000 ]---
  mokvar: Failed to map EFI MOKvar config table pa=0x7c4c3000, size=265187.

Mapping the entire structure isn't actually necessary, as we don't ever
need more than one entry header mapped at once.

Changes efi_mokvar_table_init() to only map each entry header, not the
entire table, when determining the table size.  Since we're not mapping
any data past the variable name, it also changes the code to enforce
that each variable name is NUL terminated, rather than attempting to
verify it in place.

Cc: <stable@vger.kernel.org>
Signed-off-by: Peter Jones <pjones@redhat.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/mokvar-table.c | 41 +++++++++--------------------
 1 file changed, 13 insertions(+), 28 deletions(-)

diff --git a/drivers/firmware/efi/mokvar-table.c b/drivers/firmware/efi/mokvar-table.c
index 5ed0602c2f75f..d865cb1dbaad1 100644
--- a/drivers/firmware/efi/mokvar-table.c
+++ b/drivers/firmware/efi/mokvar-table.c
@@ -103,7 +103,6 @@ void __init efi_mokvar_table_init(void)
 	void *va = NULL;
 	unsigned long cur_offset = 0;
 	unsigned long offset_limit;
-	unsigned long map_size = 0;
 	unsigned long map_size_needed = 0;
 	unsigned long size;
 	struct efi_mokvar_table_entry *mokvar_entry;
@@ -134,48 +133,34 @@ void __init efi_mokvar_table_init(void)
 	 */
 	err = -EINVAL;
 	while (cur_offset + sizeof(*mokvar_entry) <= offset_limit) {
-		mokvar_entry = va + cur_offset;
-		map_size_needed = cur_offset + sizeof(*mokvar_entry);
-		if (map_size_needed > map_size) {
-			if (va)
-				early_memunmap(va, map_size);
-			/*
-			 * Map a little more than the fixed size entry
-			 * header, anticipating some data. It's safe to
-			 * do so as long as we stay within current memory
-			 * descriptor.
-			 */
-			map_size = min(map_size_needed + 2*EFI_PAGE_SIZE,
-				       offset_limit);
-			va = early_memremap(efi.mokvar_table, map_size);
-			if (!va) {
-				pr_err("Failed to map EFI MOKvar config table pa=0x%lx, size=%lu.\n",
-				       efi.mokvar_table, map_size);
-				return;
-			}
-			mokvar_entry = va + cur_offset;
+		if (va)
+			early_memunmap(va, sizeof(*mokvar_entry));
+		va = early_memremap(efi.mokvar_table + cur_offset, sizeof(*mokvar_entry));
+		if (!va) {
+			pr_err("Failed to map EFI MOKvar config table pa=0x%lx, size=%zu.\n",
+			       efi.mokvar_table + cur_offset, sizeof(*mokvar_entry));
+			return;
 		}
+		mokvar_entry = va;
 
 		/* Check for last sentinel entry */
 		if (mokvar_entry->name[0] == '\0') {
 			if (mokvar_entry->data_size != 0)
 				break;
 			err = 0;
+			map_size_needed = cur_offset + sizeof(*mokvar_entry);
 			break;
 		}
 
-		/* Sanity check that the name is null terminated */
-		size = strnlen(mokvar_entry->name,
-			       sizeof(mokvar_entry->name));
-		if (size >= sizeof(mokvar_entry->name))
-			break;
+		/* Enforce that the name is NUL terminated */
+		mokvar_entry->name[sizeof(mokvar_entry->name) - 1] = '\0';
 
 		/* Advance to the next entry */
-		cur_offset = map_size_needed + mokvar_entry->data_size;
+		cur_offset += sizeof(*mokvar_entry) + mokvar_entry->data_size;
 	}
 
 	if (va)
-		early_memunmap(va, map_size);
+		early_memunmap(va, sizeof(*mokvar_entry));
 	if (err) {
 		pr_err("EFI MOKvar config table is not valid\n");
 		return;

From e3cf2d91d0583cae70aeb512da87e3ade25ea912 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Thu, 27 Feb 2025 14:30:22 +0100
Subject: [PATCH 0739/1173] efi/mokvar-table: Avoid repeated map/unmap of the
 same page

Tweak the logic that traverses the MOKVAR UEFI configuration table to
only unmap the entry header and map the next one if they don't live in
the same physical page.

Link: https://lore.kernel.org/all/8f085931-3e9d-4386-9209-1d6c95616327@uncooperative.org/
Tested-By: Peter Jones <pjones@redhat.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/mokvar-table.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/drivers/firmware/efi/mokvar-table.c b/drivers/firmware/efi/mokvar-table.c
index d865cb1dbaad1..208db29613c63 100644
--- a/drivers/firmware/efi/mokvar-table.c
+++ b/drivers/firmware/efi/mokvar-table.c
@@ -99,13 +99,13 @@ static struct kobject *mokvar_kobj;
  */
 void __init efi_mokvar_table_init(void)
 {
+	struct efi_mokvar_table_entry __aligned(1) *mokvar_entry, *next_entry;
 	efi_memory_desc_t md;
 	void *va = NULL;
 	unsigned long cur_offset = 0;
 	unsigned long offset_limit;
 	unsigned long map_size_needed = 0;
 	unsigned long size;
-	struct efi_mokvar_table_entry *mokvar_entry;
 	int err;
 
 	if (!efi_enabled(EFI_MEMMAP))
@@ -142,7 +142,7 @@ void __init efi_mokvar_table_init(void)
 			return;
 		}
 		mokvar_entry = va;
-
+next:
 		/* Check for last sentinel entry */
 		if (mokvar_entry->name[0] == '\0') {
 			if (mokvar_entry->data_size != 0)
@@ -156,7 +156,19 @@ void __init efi_mokvar_table_init(void)
 		mokvar_entry->name[sizeof(mokvar_entry->name) - 1] = '\0';
 
 		/* Advance to the next entry */
-		cur_offset += sizeof(*mokvar_entry) + mokvar_entry->data_size;
+		size = sizeof(*mokvar_entry) + mokvar_entry->data_size;
+		cur_offset += size;
+
+		/*
+		 * Don't bother remapping if the current entry header and the
+		 * next one end on the same page.
+		 */
+		next_entry = (void *)((unsigned long)mokvar_entry + size);
+		if (((((unsigned long)(mokvar_entry + 1) - 1) ^
+		      ((unsigned long)(next_entry + 1) - 1)) & PAGE_MASK) == 0) {
+			mokvar_entry = next_entry;
+			goto next;
+		}
 	}
 
 	if (va)

From 02410ac72ac3707936c07ede66e94360d0d65319 Mon Sep 17 00:00:00 2001
From: Ryan Roberts <ryan.roberts@arm.com>
Date: Wed, 26 Feb 2025 12:06:51 +0000
Subject: [PATCH 0740/1173] mm: hugetlb: Add huge page size param to
 huge_ptep_get_and_clear()

In order to fix a bug, arm64 needs to be told the size of the huge page
for which the huge_pte is being cleared in huge_ptep_get_and_clear().
Provide for this by adding an `unsigned long sz` parameter to the
function. This follows the same pattern as huge_pte_clear() and
set_huge_pte_at().

This commit makes the required interface modifications to the core mm as
well as all arches that implement this function (arm64, loongarch, mips,
parisc, powerpc, riscv, s390, sparc). The actual arm64 bug will be fixed
in a separate commit.

Cc: stable@vger.kernel.org
Fixes: 66b3923a1a0f ("arm64: hugetlb: add support for PTE contiguous bit")
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com> # riscv
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Acked-by: Alexander Gordeev <agordeev@linux.ibm.com> # s390
Link: https://lore.kernel.org/r/20250226120656.2400136-2-ryan.roberts@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/hugetlb.h     |  4 ++--
 arch/arm64/mm/hugetlbpage.c          |  8 +++++---
 arch/loongarch/include/asm/hugetlb.h |  6 ++++--
 arch/mips/include/asm/hugetlb.h      |  6 ++++--
 arch/parisc/include/asm/hugetlb.h    |  2 +-
 arch/parisc/mm/hugetlbpage.c         |  2 +-
 arch/powerpc/include/asm/hugetlb.h   |  6 ++++--
 arch/riscv/include/asm/hugetlb.h     |  3 ++-
 arch/riscv/mm/hugetlbpage.c          |  2 +-
 arch/s390/include/asm/hugetlb.h      | 16 ++++++++++++----
 arch/s390/mm/hugetlbpage.c           |  4 ++--
 arch/sparc/include/asm/hugetlb.h     |  2 +-
 arch/sparc/mm/hugetlbpage.c          |  2 +-
 include/asm-generic/hugetlb.h        |  2 +-
 include/linux/hugetlb.h              |  4 +++-
 mm/hugetlb.c                         |  4 ++--
 16 files changed, 46 insertions(+), 27 deletions(-)

diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index c6dff3e69539b..03db9cb21ace8 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -42,8 +42,8 @@ extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 				      unsigned long addr, pte_t *ptep,
 				      pte_t pte, int dirty);
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
-extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-				     unsigned long addr, pte_t *ptep);
+extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+				     pte_t *ptep, unsigned long sz);
 #define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT
 extern void huge_ptep_set_wrprotect(struct mm_struct *mm,
 				    unsigned long addr, pte_t *ptep);
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 98a2a0e64e255..06db4649af916 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -396,8 +396,8 @@ void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 		__pte_clear(mm, addr, ptep);
 }
 
-pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-			      unsigned long addr, pte_t *ptep)
+pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep, unsigned long sz)
 {
 	int ncontig;
 	size_t pgsize;
@@ -549,6 +549,8 @@ bool __init arch_hugetlb_valid_size(unsigned long size)
 
 pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
 {
+	unsigned long psize = huge_page_size(hstate_vma(vma));
+
 	if (alternative_has_cap_unlikely(ARM64_WORKAROUND_2645198)) {
 		/*
 		 * Break-before-make (BBM) is required for all user space mappings
@@ -558,7 +560,7 @@ pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr
 		if (pte_user_exec(__ptep_get(ptep)))
 			return huge_ptep_clear_flush(vma, addr, ptep);
 	}
-	return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, psize);
 }
 
 void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep,
diff --git a/arch/loongarch/include/asm/hugetlb.h b/arch/loongarch/include/asm/hugetlb.h
index c8e4057734d0d..4dc4b3e04225f 100644
--- a/arch/loongarch/include/asm/hugetlb.h
+++ b/arch/loongarch/include/asm/hugetlb.h
@@ -36,7 +36,8 @@ static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep)
+					    unsigned long addr, pte_t *ptep,
+					    unsigned long sz)
 {
 	pte_t clear;
 	pte_t pte = ptep_get(ptep);
@@ -51,8 +52,9 @@ static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 					  unsigned long addr, pte_t *ptep)
 {
 	pte_t pte;
+	unsigned long sz = huge_page_size(hstate_vma(vma));
 
-	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, sz);
 	flush_tlb_page(vma, addr);
 	return pte;
 }
diff --git a/arch/mips/include/asm/hugetlb.h b/arch/mips/include/asm/hugetlb.h
index d0a86ce83de91..fbc71ddcf0f68 100644
--- a/arch/mips/include/asm/hugetlb.h
+++ b/arch/mips/include/asm/hugetlb.h
@@ -27,7 +27,8 @@ static inline int prepare_hugepage_range(struct file *file,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep)
+					    unsigned long addr, pte_t *ptep,
+					    unsigned long sz)
 {
 	pte_t clear;
 	pte_t pte = *ptep;
@@ -42,13 +43,14 @@ static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 					  unsigned long addr, pte_t *ptep)
 {
 	pte_t pte;
+	unsigned long sz = huge_page_size(hstate_vma(vma));
 
 	/*
 	 * clear the huge pte entry firstly, so that the other smp threads will
 	 * not get old pte entry after finishing flush_tlb_page and before
 	 * setting new huge pte entry
 	 */
-	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, sz);
 	flush_tlb_page(vma, addr);
 	return pte;
 }
diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h
index 5b3a5429f71b3..21e9ace177395 100644
--- a/arch/parisc/include/asm/hugetlb.h
+++ b/arch/parisc/include/asm/hugetlb.h
@@ -10,7 +10,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep);
+			      pte_t *ptep, unsigned long sz);
 
 #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
 static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
diff --git a/arch/parisc/mm/hugetlbpage.c b/arch/parisc/mm/hugetlbpage.c
index e9d18cf25b792..a94fe546d434f 100644
--- a/arch/parisc/mm/hugetlbpage.c
+++ b/arch/parisc/mm/hugetlbpage.c
@@ -126,7 +126,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 
 
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep)
+			      pte_t *ptep, unsigned long sz)
 {
 	pte_t entry;
 
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index dad2e7980f245..86326587e58de 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -45,7 +45,8 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep)
+					    unsigned long addr, pte_t *ptep,
+					    unsigned long sz)
 {
 	return __pte(pte_update(mm, addr, ptep, ~0UL, 0, 1));
 }
@@ -55,8 +56,9 @@ static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 					  unsigned long addr, pte_t *ptep)
 {
 	pte_t pte;
+	unsigned long sz = huge_page_size(hstate_vma(vma));
 
-	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, sz);
 	flush_hugetlb_page(vma, addr);
 	return pte;
 }
diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h
index faf3624d80577..4461264977684 100644
--- a/arch/riscv/include/asm/hugetlb.h
+++ b/arch/riscv/include/asm/hugetlb.h
@@ -28,7 +28,8 @@ void set_huge_pte_at(struct mm_struct *mm,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-			      unsigned long addr, pte_t *ptep);
+			      unsigned long addr, pte_t *ptep,
+			      unsigned long sz);
 
 #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
 pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c
index 42314f0939220..b4a78a4b35cff 100644
--- a/arch/riscv/mm/hugetlbpage.c
+++ b/arch/riscv/mm/hugetlbpage.c
@@ -293,7 +293,7 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 			      unsigned long addr,
-			      pte_t *ptep)
+			      pte_t *ptep, unsigned long sz)
 {
 	pte_t orig_pte = ptep_get(ptep);
 	int pte_num;
diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index 7c52acaf9f828..663e87220e89f 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -25,8 +25,16 @@ void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 #define __HAVE_ARCH_HUGE_PTEP_GET
 pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
 
+pte_t __huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+				pte_t *ptep);
+
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
-pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
+static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+					    unsigned long addr, pte_t *ptep,
+					    unsigned long sz)
+{
+	return __huge_ptep_get_and_clear(mm, addr, ptep);
+}
 
 static inline void arch_clear_hugetlb_flags(struct folio *folio)
 {
@@ -48,7 +56,7 @@ static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 					  unsigned long address, pte_t *ptep)
 {
-	return huge_ptep_get_and_clear(vma->vm_mm, address, ptep);
+	return __huge_ptep_get_and_clear(vma->vm_mm, address, ptep);
 }
 
 #define  __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
@@ -59,7 +67,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 	int changed = !pte_same(huge_ptep_get(vma->vm_mm, addr, ptep), pte);
 
 	if (changed) {
-		huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+		__huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
 		__set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
 	}
 	return changed;
@@ -69,7 +77,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep)
 {
-	pte_t pte = huge_ptep_get_and_clear(mm, addr, ptep);
+	pte_t pte = __huge_ptep_get_and_clear(mm, addr, ptep);
 
 	__set_huge_pte_at(mm, addr, ptep, pte_wrprotect(pte));
 }
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index d9ce199953de9..2e568f175cd41 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -188,8 +188,8 @@ pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 	return __rste_to_pte(pte_val(*ptep));
 }
 
-pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-			      unsigned long addr, pte_t *ptep)
+pte_t __huge_ptep_get_and_clear(struct mm_struct *mm,
+				unsigned long addr, pte_t *ptep)
 {
 	pte_t pte = huge_ptep_get(mm, addr, ptep);
 	pmd_t *pmdp = (pmd_t *) ptep;
diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h
index c714ca6a05aa0..e7a9cdd498dca 100644
--- a/arch/sparc/include/asm/hugetlb.h
+++ b/arch/sparc/include/asm/hugetlb.h
@@ -20,7 +20,7 @@ void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep);
+			      pte_t *ptep, unsigned long sz);
 
 #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
 static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index eee601a0d2cfb..80504148d8a5b 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -260,7 +260,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 }
 
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep)
+			      pte_t *ptep, unsigned long sz)
 {
 	unsigned int i, nptes, orig_shift, shift;
 	unsigned long size;
diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
index f42133dae68e5..2afc95bf1655f 100644
--- a/include/asm-generic/hugetlb.h
+++ b/include/asm-generic/hugetlb.h
@@ -90,7 +90,7 @@ static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 
 #ifndef __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-		unsigned long addr, pte_t *ptep)
+		unsigned long addr, pte_t *ptep, unsigned long sz)
 {
 	return ptep_get_and_clear(mm, addr, ptep);
 }
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index ec8c0ccc8f959..bf5f7256bd281 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -1004,7 +1004,9 @@ static inline void hugetlb_count_sub(long l, struct mm_struct *mm)
 static inline pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
 						unsigned long addr, pte_t *ptep)
 {
-	return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	unsigned long psize = huge_page_size(hstate_vma(vma));
+
+	return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, psize);
 }
 #endif
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 65068671e460a..de9d49e521c13 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5447,7 +5447,7 @@ static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr,
 	if (src_ptl != dst_ptl)
 		spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
 
-	pte = huge_ptep_get_and_clear(mm, old_addr, src_pte);
+	pte = huge_ptep_get_and_clear(mm, old_addr, src_pte, sz);
 
 	if (need_clear_uffd_wp && pte_marker_uffd_wp(pte))
 		huge_pte_clear(mm, new_addr, dst_pte, sz);
@@ -5622,7 +5622,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 			set_vma_resv_flags(vma, HPAGE_RESV_UNMAPPED);
 		}
 
-		pte = huge_ptep_get_and_clear(mm, address, ptep);
+		pte = huge_ptep_get_and_clear(mm, address, ptep, sz);
 		tlb_remove_huge_tlb_entry(h, tlb, ptep, address);
 		if (huge_pte_dirty(pte))
 			set_page_dirty(page);

From 49c87f7677746f3c5bd16c81b23700bb6b88bfd4 Mon Sep 17 00:00:00 2001
From: Ryan Roberts <ryan.roberts@arm.com>
Date: Wed, 26 Feb 2025 12:06:52 +0000
Subject: [PATCH 0741/1173] arm64: hugetlb: Fix huge_ptep_get_and_clear() for
 non-present ptes

arm64 supports multiple huge_pte sizes. Some of the sizes are covered by
a single pte entry at a particular level (PMD_SIZE, PUD_SIZE), and some
are covered by multiple ptes at a particular level (CONT_PTE_SIZE,
CONT_PMD_SIZE). So the function has to figure out the size from the
huge_pte pointer. This was previously done by walking the pgtable to
determine the level and by using the PTE_CONT bit to determine the
number of ptes at the level.

But the PTE_CONT bit is only valid when the pte is present. For
non-present pte values (e.g. markers, migration entries), the previous
implementation was therefore erroneously determining the size. There is
at least one known caller in core-mm, move_huge_pte(), which may call
huge_ptep_get_and_clear() for a non-present pte. So we must be robust to
this case. Additionally the "regular" ptep_get_and_clear() is robust to
being called for non-present ptes so it makes sense to follow the
behavior.

Fix this by using the new sz parameter which is now provided to the
function. Additionally when clearing each pte in a contig range, don't
gather the access and dirty bits if the pte is not present.

An alternative approach that would not require API changes would be to
store the PTE_CONT bit in a spare bit in the swap entry pte for the
non-present case. But it felt cleaner to follow other APIs' lead and
just pass in the size.

As an aside, PTE_CONT is bit 52, which corresponds to bit 40 in the swap
entry offset field (layout of non-present pte). Since hugetlb is never
swapped to disk, this field will only be populated for markers, which
always set this bit to 0 and hwpoison swap entries, which set the offset
field to a PFN; So it would only ever be 1 for a 52-bit PVA system where
memory in that high half was poisoned (I think!). So in practice, this
bit would almost always be zero for non-present ptes and we would only
clear the first entry if it was actually a contiguous block. That's
probably a less severe symptom than if it was always interpreted as 1
and cleared out potentially-present neighboring PTEs.

Cc: stable@vger.kernel.org
Fixes: 66b3923a1a0f ("arm64: hugetlb: add support for PTE contiguous bit")
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Link: https://lore.kernel.org/r/20250226120656.2400136-3-ryan.roberts@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/mm/hugetlbpage.c | 53 ++++++++++++++-----------------------
 1 file changed, 20 insertions(+), 33 deletions(-)

diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 06db4649af916..b3a7fafe8892d 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -100,20 +100,11 @@ static int find_num_contig(struct mm_struct *mm, unsigned long addr,
 
 static inline int num_contig_ptes(unsigned long size, size_t *pgsize)
 {
-	int contig_ptes = 0;
+	int contig_ptes = 1;
 
 	*pgsize = size;
 
 	switch (size) {
-#ifndef __PAGETABLE_PMD_FOLDED
-	case PUD_SIZE:
-		if (pud_sect_supported())
-			contig_ptes = 1;
-		break;
-#endif
-	case PMD_SIZE:
-		contig_ptes = 1;
-		break;
 	case CONT_PMD_SIZE:
 		*pgsize = PMD_SIZE;
 		contig_ptes = CONT_PMDS;
@@ -122,6 +113,8 @@ static inline int num_contig_ptes(unsigned long size, size_t *pgsize)
 		*pgsize = PAGE_SIZE;
 		contig_ptes = CONT_PTES;
 		break;
+	default:
+		WARN_ON(!__hugetlb_valid_size(size));
 	}
 
 	return contig_ptes;
@@ -163,24 +156,23 @@ static pte_t get_clear_contig(struct mm_struct *mm,
 			     unsigned long pgsize,
 			     unsigned long ncontig)
 {
-	pte_t orig_pte = __ptep_get(ptep);
-	unsigned long i;
-
-	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) {
-		pte_t pte = __ptep_get_and_clear(mm, addr, ptep);
-
-		/*
-		 * If HW_AFDBM is enabled, then the HW could turn on
-		 * the dirty or accessed bit for any page in the set,
-		 * so check them all.
-		 */
-		if (pte_dirty(pte))
-			orig_pte = pte_mkdirty(orig_pte);
-
-		if (pte_young(pte))
-			orig_pte = pte_mkyoung(orig_pte);
+	pte_t pte, tmp_pte;
+	bool present;
+
+	pte = __ptep_get_and_clear(mm, addr, ptep);
+	present = pte_present(pte);
+	while (--ncontig) {
+		ptep++;
+		addr += pgsize;
+		tmp_pte = __ptep_get_and_clear(mm, addr, ptep);
+		if (present) {
+			if (pte_dirty(tmp_pte))
+				pte = pte_mkdirty(pte);
+			if (pte_young(tmp_pte))
+				pte = pte_mkyoung(pte);
+		}
 	}
-	return orig_pte;
+	return pte;
 }
 
 static pte_t get_clear_contig_flush(struct mm_struct *mm,
@@ -401,13 +393,8 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
 {
 	int ncontig;
 	size_t pgsize;
-	pte_t orig_pte = __ptep_get(ptep);
-
-	if (!pte_cont(orig_pte))
-		return __ptep_get_and_clear(mm, addr, ptep);
-
-	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
 
+	ncontig = num_contig_ptes(sz, &pgsize);
 	return get_clear_contig(mm, addr, ptep, pgsize, ncontig);
 }
 

From eed6bfa8b28230382b797a88569f2c7569a1a419 Mon Sep 17 00:00:00 2001
From: Ryan Roberts <ryan.roberts@arm.com>
Date: Wed, 26 Feb 2025 12:06:53 +0000
Subject: [PATCH 0742/1173] arm64: hugetlb: Fix flush_hugetlb_tlb_range()
 invalidation level

commit c910f2b65518 ("arm64/mm: Update tlb invalidation routines for
FEAT_LPA2") changed the "invalidation level unknown" hint from 0 to
TLBI_TTL_UNKNOWN (INT_MAX). But the fallback "unknown level" path in
flush_hugetlb_tlb_range() was not updated. So as it stands, when trying
to invalidate CONT_PMD_SIZE or CONT_PTE_SIZE hugetlb mappings, we will
spuriously try to invalidate at level 0 on LPA2-enabled systems.

Fix this so that the fallback passes TLBI_TTL_UNKNOWN, and while we are
at it, explicitly use the correct stride and level for CONT_PMD_SIZE and
CONT_PTE_SIZE, which should provide a minor optimization.

Cc: stable@vger.kernel.org
Fixes: c910f2b65518 ("arm64/mm: Update tlb invalidation routines for FEAT_LPA2")
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Link: https://lore.kernel.org/r/20250226120656.2400136-4-ryan.roberts@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/hugetlb.h | 22 ++++++++++++++++------
 1 file changed, 16 insertions(+), 6 deletions(-)

diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index 03db9cb21ace8..07fbf5bf85a7e 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -76,12 +76,22 @@ static inline void flush_hugetlb_tlb_range(struct vm_area_struct *vma,
 {
 	unsigned long stride = huge_page_size(hstate_vma(vma));
 
-	if (stride == PMD_SIZE)
-		__flush_tlb_range(vma, start, end, stride, false, 2);
-	else if (stride == PUD_SIZE)
-		__flush_tlb_range(vma, start, end, stride, false, 1);
-	else
-		__flush_tlb_range(vma, start, end, PAGE_SIZE, false, 0);
+	switch (stride) {
+#ifndef __PAGETABLE_PMD_FOLDED
+	case PUD_SIZE:
+		__flush_tlb_range(vma, start, end, PUD_SIZE, false, 1);
+		break;
+#endif
+	case CONT_PMD_SIZE:
+	case PMD_SIZE:
+		__flush_tlb_range(vma, start, end, PMD_SIZE, false, 2);
+		break;
+	case CONT_PTE_SIZE:
+		__flush_tlb_range(vma, start, end, PAGE_SIZE, false, 3);
+		break;
+	default:
+		__flush_tlb_range(vma, start, end, PAGE_SIZE, false, TLBI_TTL_UNKNOWN);
+	}
 }
 
 #endif /* __ASM_HUGETLB_H */

From b6762467a09ba8838c499e4f36561e82fc608ed1 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Thu, 27 Feb 2025 15:06:58 +0100
Subject: [PATCH 0743/1173] x86/percpu: Disable named address spaces for
 UBSAN_BOOL with KASAN for GCC < 14.2

GCC < 14.2 does not correctly propagate address space qualifiers
with -fsanitize=bool,enum. Together with address sanitizer then
causes that load to be sanitized.

Disable named address spaces for GCC < 14.2 when both, UBSAN_BOOL
and KASAN are enabled.

Reported-by: Matt Fleming <matt@readmodwrite.com>
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250227140715.2276353-1-ubizjak@gmail.com
Closes: https://lore.kernel.org/lkml/20241213190119.3449103-1-matt@readmodwrite.com/
---
 arch/x86/Kconfig | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 6595b35dd52da..867ec8a4a9d2f 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2441,18 +2441,20 @@ config CC_HAS_NAMED_AS
 	def_bool $(success,echo 'int __seg_fs fs; int __seg_gs gs;' | $(CC) -x c - -S -o /dev/null)
 	depends on CC_IS_GCC
 
+#
+# -fsanitize=kernel-address (KASAN) and -fsanitize=thread (KCSAN)
+# are incompatible with named address spaces with GCC < 13.3
+# (see GCC PR sanitizer/111736 and also PR sanitizer/115172).
+#
+
 config CC_HAS_NAMED_AS_FIXED_SANITIZERS
-	def_bool CC_IS_GCC && GCC_VERSION >= 130300
+	def_bool y
+	depends on !(KASAN || KCSAN) || GCC_VERSION >= 130300
+	depends on !(UBSAN_BOOL && KASAN) || GCC_VERSION >= 140200
 
 config USE_X86_SEG_SUPPORT
-	def_bool y
-	depends on CC_HAS_NAMED_AS
-	#
-	# -fsanitize=kernel-address (KASAN) and -fsanitize=thread
-	# (KCSAN) are incompatible with named address spaces with
-	# GCC < 13.3 - see GCC PR sanitizer/111736.
-	#
-	depends on !(KASAN || KCSAN) || CC_HAS_NAMED_AS_FIXED_SANITIZERS
+	def_bool CC_HAS_NAMED_AS
+	depends on CC_HAS_NAMED_AS_FIXED_SANITIZERS
 
 config CC_HAS_SLS
 	def_bool $(cc-option,-mharden-sls=all)

From dc8aa31a7ac2c4290ea974c13cb0094e08f8948f Mon Sep 17 00:00:00 2001
From: "Chang S. Bae" <chang.seok.bae@intel.com>
Date: Tue, 10 Dec 2024 17:45:00 -0800
Subject: [PATCH 0744/1173] x86/fpu: Refine and simplify the magic number check
 during signal return

Before restoring xstate from the user space buffer, the kernel performs
sanity checks on these magic numbers: magic1 in the software reserved
area, and magic2 at the end of XSAVE region.

The position of magic2 is calculated based on the xstate size derived
from the user space buffer. But, the in-kernel record is directly
available and reliable for this purpose.

This reliance on user space data is also inconsistent with the recent
fix in:

  d877550eaf2d ("x86/fpu: Stop relying on userspace for info to fault in xsave buffer")

Simply use fpstate->user_size, and then get rid of unnecessary
size-evaluation code.

Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/r/20241211014500.3738-1-chang.seok.bae@intel.com
---
 arch/x86/kernel/fpu/signal.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index 8f62e0666dea5..6c69cb28b2983 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -27,19 +27,14 @@
 static inline bool check_xstate_in_sigframe(struct fxregs_state __user *fxbuf,
 					    struct _fpx_sw_bytes *fx_sw)
 {
-	int min_xstate_size = sizeof(struct fxregs_state) +
-			      sizeof(struct xstate_header);
 	void __user *fpstate = fxbuf;
 	unsigned int magic2;
 
 	if (__copy_from_user(fx_sw, &fxbuf->sw_reserved[0], sizeof(*fx_sw)))
 		return false;
 
-	/* Check for the first magic field and other error scenarios. */
-	if (fx_sw->magic1 != FP_XSTATE_MAGIC1 ||
-	    fx_sw->xstate_size < min_xstate_size ||
-	    fx_sw->xstate_size > current->thread.fpu.fpstate->user_size ||
-	    fx_sw->xstate_size > fx_sw->extended_size)
+	/* Check for the first magic field */
+	if (fx_sw->magic1 != FP_XSTATE_MAGIC1)
 		goto setfx;
 
 	/*
@@ -48,7 +43,7 @@ static inline bool check_xstate_in_sigframe(struct fxregs_state __user *fxbuf,
 	 * fpstate layout with out copying the extended state information
 	 * in the memory layout.
 	 */
-	if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size)))
+	if (__get_user(magic2, (__u32 __user *)(fpstate + current->thread.fpu.fpstate->user_size)))
 		return false;
 
 	if (likely(magic2 == FP_XSTATE_MAGIC2))

From 69a2fdf446049ae31be4a14a0cf16f2f18f09b6c Mon Sep 17 00:00:00 2001
From: "Chang S. Bae" <chang.seok.bae@intel.com>
Date: Thu, 27 Feb 2025 10:44:46 -0800
Subject: [PATCH 0745/1173] x86/fpu/xstate: Simplify print_xstate_features()

print_xstate_features() currently invokes print_xstate_feature() multiple
times on separate lines, which can be simplified in a loop.

print_xstate_feature() already checks the feature's enabled status and is
only called within print_xstate_features(). Inline print_xstate_feature()
and iterate over features in a loop to streamline the enabling message.

No functional changes.

Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/r/20250227184502.10288-2-chang.seok.bae@intel.com
---
 arch/x86/kernel/fpu/xstate.c | 30 +++++++++---------------------
 1 file changed, 9 insertions(+), 21 deletions(-)

diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 27417b685c1db..6a41d1610d8bc 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -259,32 +259,20 @@ static void __init setup_xstate_cache(void)
 	}
 }
 
-static void __init print_xstate_feature(u64 xstate_mask)
-{
-	const char *feature_name;
-
-	if (cpu_has_xfeatures(xstate_mask, &feature_name))
-		pr_info("x86/fpu: Supporting XSAVE feature 0x%03Lx: '%s'\n", xstate_mask, feature_name);
-}
-
 /*
  * Print out all the supported xstate features:
  */
 static void __init print_xstate_features(void)
 {
-	print_xstate_feature(XFEATURE_MASK_FP);
-	print_xstate_feature(XFEATURE_MASK_SSE);
-	print_xstate_feature(XFEATURE_MASK_YMM);
-	print_xstate_feature(XFEATURE_MASK_BNDREGS);
-	print_xstate_feature(XFEATURE_MASK_BNDCSR);
-	print_xstate_feature(XFEATURE_MASK_OPMASK);
-	print_xstate_feature(XFEATURE_MASK_ZMM_Hi256);
-	print_xstate_feature(XFEATURE_MASK_Hi16_ZMM);
-	print_xstate_feature(XFEATURE_MASK_PKRU);
-	print_xstate_feature(XFEATURE_MASK_PASID);
-	print_xstate_feature(XFEATURE_MASK_CET_USER);
-	print_xstate_feature(XFEATURE_MASK_XTILE_CFG);
-	print_xstate_feature(XFEATURE_MASK_XTILE_DATA);
+	int i;
+
+	for (i = 0; i < XFEATURE_MAX; i++) {
+		u64 mask = BIT_ULL(i);
+		const char *name;
+
+		if (cpu_has_xfeatures(mask, &name))
+			pr_info("x86/fpu: Supporting XSAVE feature 0x%03Lx: '%s'\n", mask, name);
+	}
 }
 
 /*

From 6b481ab0e6855fb30e2923c51f62f1662d1cda7e Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Fri, 7 Feb 2025 11:25:31 +1000
Subject: [PATCH 0746/1173] drm/nouveau: select FW caching

nouveau tries to load some firmware during suspend that it loaded
earlier, but with fw caching disabled it hangs suspend, so just rely on
FW cache enabling instead of working around it in the driver.

Fixes: 176fdcbddfd2 ("drm/nouveau/gsp/r535: add support for booting GSP-RM")
Signed-off-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20250207012531.621369-1-airlied@gmail.com
---
 drivers/gpu/drm/nouveau/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/nouveau/Kconfig b/drivers/gpu/drm/nouveau/Kconfig
index ce840300578d8..1050a4617fc15 100644
--- a/drivers/gpu/drm/nouveau/Kconfig
+++ b/drivers/gpu/drm/nouveau/Kconfig
@@ -4,6 +4,7 @@ config DRM_NOUVEAU
 	depends on DRM && PCI && MMU
 	select IOMMU_API
 	select FW_LOADER
+	select FW_CACHE if PM_SLEEP
 	select DRM_CLIENT_SELECTION
 	select DRM_DISPLAY_DP_HELPER
 	select DRM_DISPLAY_HDMI_HELPER

From 18cdd90aba794333f4c6dce39f5c3fe642af5575 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Thu, 27 Feb 2025 14:53:02 -0500
Subject: [PATCH 0747/1173] x86/bpf: Fix BPF percpu accesses

Due to this recent commit in the x86 tree:

  9d7de2aa8b41 ("Use relative percpu offsets")

percpu addresses went from positive offsets from the GSBASE to negative
kernel virtual addresses.  The BPF verifier has an optimization for
x86-64 that loads the address of cpu_number into a register, but was only
doing a 32-bit load which truncates negative addresses.

Change it to a 64-bit load so that the address is properly sign-extended.

Fixes: 9d7de2aa8b41 ("Use relative percpu offsets")
Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Uros Bizjak <ubizjak@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250227195302.1667654-1-brgerst@gmail.com
---
 kernel/bpf/verifier.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 9971c03adfd5d..f74263b206e43 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -21692,7 +21692,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 			 * way, it's fine to back out this inlining logic
 			 */
 #ifdef CONFIG_SMP
-			insn_buf[0] = BPF_MOV32_IMM(BPF_REG_0, (u32)(unsigned long)&pcpu_hot.cpu_number);
+			insn_buf[0] = BPF_MOV64_IMM(BPF_REG_0, (u32)(unsigned long)&pcpu_hot.cpu_number);
 			insn_buf[1] = BPF_MOV64_PERCPU_REG(BPF_REG_0, BPF_REG_0);
 			insn_buf[2] = BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0);
 			cnt = 3;

From 82c387ef7568c0d96a918a5a78d9cad6256cfa15 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 16 Dec 2024 14:20:56 +0100
Subject: [PATCH 0748/1173] sched/core: Prevent rescheduling when interrupts
 are disabled

David reported a warning observed while loop testing kexec jump:

  Interrupts enabled after irqrouter_resume+0x0/0x50
  WARNING: CPU: 0 PID: 560 at drivers/base/syscore.c:103 syscore_resume+0x18a/0x220
   kernel_kexec+0xf6/0x180
   __do_sys_reboot+0x206/0x250
   do_syscall_64+0x95/0x180

The corresponding interrupt flag trace:

  hardirqs last  enabled at (15573): [<ffffffffa8281b8e>] __up_console_sem+0x7e/0x90
  hardirqs last disabled at (15580): [<ffffffffa8281b73>] __up_console_sem+0x63/0x90

That means __up_console_sem() was invoked with interrupts enabled. Further
instrumentation revealed that in the interrupt disabled section of kexec
jump one of the syscore_suspend() callbacks woke up a task, which set the
NEED_RESCHED flag. A later callback in the resume path invoked
cond_resched() which in turn led to the invocation of the scheduler:

  __cond_resched+0x21/0x60
  down_timeout+0x18/0x60
  acpi_os_wait_semaphore+0x4c/0x80
  acpi_ut_acquire_mutex+0x3d/0x100
  acpi_ns_get_node+0x27/0x60
  acpi_ns_evaluate+0x1cb/0x2d0
  acpi_rs_set_srs_method_data+0x156/0x190
  acpi_pci_link_set+0x11c/0x290
  irqrouter_resume+0x54/0x60
  syscore_resume+0x6a/0x200
  kernel_kexec+0x145/0x1c0
  __do_sys_reboot+0xeb/0x240
  do_syscall_64+0x95/0x180

This is a long standing problem, which probably got more visible with
the recent printk changes. Something does a task wakeup and the
scheduler sets the NEED_RESCHED flag. cond_resched() sees it set and
invokes schedule() from a completely bogus context. The scheduler
enables interrupts after context switching, which causes the above
warning at the end.

Quite some of the code paths in syscore_suspend()/resume() can result in
triggering a wakeup with the exactly same consequences. They might not
have done so yet, but as they share a lot of code with normal operations
it's just a question of time.

The problem only affects the PREEMPT_NONE and PREEMPT_VOLUNTARY scheduling
models. Full preemption is not affected as cond_resched() is disabled and
the preemption check preemptible() takes the interrupt disabled flag into
account.

Cure the problem by adding a corresponding check into cond_resched().

Reported-by: David Woodhouse <dwmw@amazon.co.uk>
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: David Woodhouse <dwmw@amazon.co.uk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: stable@vger.kernel.org
Closes: https://lore.kernel.org/all/7717fe2ac0ce5f0a2c43fdab8b11f4483d54a2a4.camel@infradead.org
---
 kernel/sched/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9aecd914ac691..67189907214d3 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7285,7 +7285,7 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
 #if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC)
 int __sched __cond_resched(void)
 {
-	if (should_resched(0)) {
+	if (should_resched(0) && !irqs_disabled()) {
 		preempt_schedule_common();
 		return 1;
 	}

From c133ec0e5717868c9967fa3df92a55e537b1aead Mon Sep 17 00:00:00 2001
From: Michal Pecio <michal.pecio@gmail.com>
Date: Tue, 25 Feb 2025 11:59:27 +0200
Subject: [PATCH 0749/1173] usb: xhci: Enable the TRB overfetch quirk on VIA
 VL805

Raspberry Pi is a major user of those chips and they discovered a bug -
when the end of a transfer ring segment is reached, up to four TRBs can
be prefetched from the next page even if the segment ends with link TRB
and on page boundary (the chip claims to support standard 4KB pages).

It also appears that if the prefetched TRBs belong to a different ring
whose doorbell is later rung, they may be used without refreshing from
system RAM and the endpoint will stay idle if their cycle bit is stale.

Other users complain about IOMMU faults on x86 systems, unsurprisingly.

Deal with it by using existing quirk which allocates a dummy page after
each transfer ring segment. This was seen to resolve both problems. RPi
came up with a more efficient solution, shortening each segment by four
TRBs, but it complicated the driver and they ditched it for this quirk.

Also rename the quirk and add VL805 device ID macro.

Signed-off-by: Michal Pecio <michal.pecio@gmail.com>
Link: https://github.com/raspberrypi/linux/issues/4685
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=215906
CC: stable@vger.kernel.org
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20250225095927.2512358-2-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-mem.c |  3 ++-
 drivers/usb/host/xhci-pci.c | 10 +++++++---
 drivers/usb/host/xhci.h     |  2 +-
 3 files changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index 92703efda1f7b..fdf0c1008225a 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -2437,7 +2437,8 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags)
 	 * and our use of dma addresses in the trb_address_map radix tree needs
 	 * TRB_SEGMENT_SIZE alignment, so we pick the greater alignment need.
 	 */
-	if (xhci->quirks & XHCI_ZHAOXIN_TRB_FETCH)
+	if (xhci->quirks & XHCI_TRB_OVERFETCH)
+		/* Buggy HC prefetches beyond segment bounds - allocate dummy space at the end */
 		xhci->segment_pool = dma_pool_create("xHCI ring segments", dev,
 				TRB_SEGMENT_SIZE * 2, TRB_SEGMENT_SIZE * 2, xhci->page_size * 2);
 	else
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index ad0ff356f6fa0..54460d11f7ee8 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -38,6 +38,8 @@
 #define PCI_DEVICE_ID_ETRON_EJ168		0x7023
 #define PCI_DEVICE_ID_ETRON_EJ188		0x7052
 
+#define PCI_DEVICE_ID_VIA_VL805			0x3483
+
 #define PCI_DEVICE_ID_INTEL_LYNXPOINT_XHCI		0x8c31
 #define PCI_DEVICE_ID_INTEL_LYNXPOINT_LP_XHCI		0x9c31
 #define PCI_DEVICE_ID_INTEL_WILDCATPOINT_LP_XHCI	0x9cb1
@@ -418,8 +420,10 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 			pdev->device == 0x3432)
 		xhci->quirks |= XHCI_BROKEN_STREAMS;
 
-	if (pdev->vendor == PCI_VENDOR_ID_VIA && pdev->device == 0x3483)
+	if (pdev->vendor == PCI_VENDOR_ID_VIA && pdev->device == PCI_DEVICE_ID_VIA_VL805) {
 		xhci->quirks |= XHCI_LPM_SUPPORT;
+		xhci->quirks |= XHCI_TRB_OVERFETCH;
+	}
 
 	if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA &&
 		pdev->device == PCI_DEVICE_ID_ASMEDIA_1042_XHCI) {
@@ -467,11 +471,11 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 
 		if (pdev->device == 0x9202) {
 			xhci->quirks |= XHCI_RESET_ON_RESUME;
-			xhci->quirks |= XHCI_ZHAOXIN_TRB_FETCH;
+			xhci->quirks |= XHCI_TRB_OVERFETCH;
 		}
 
 		if (pdev->device == 0x9203)
-			xhci->quirks |= XHCI_ZHAOXIN_TRB_FETCH;
+			xhci->quirks |= XHCI_TRB_OVERFETCH;
 	}
 
 	if (pdev->vendor == PCI_VENDOR_ID_CDNS &&
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 8c164340a2c35..779b01dee068f 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -1632,7 +1632,7 @@ struct xhci_hcd {
 #define XHCI_EP_CTX_BROKEN_DCS	BIT_ULL(42)
 #define XHCI_SUSPEND_RESUME_CLKS	BIT_ULL(43)
 #define XHCI_RESET_TO_DEFAULT	BIT_ULL(44)
-#define XHCI_ZHAOXIN_TRB_FETCH	BIT_ULL(45)
+#define XHCI_TRB_OVERFETCH	BIT_ULL(45)
 #define XHCI_ZHAOXIN_HOST	BIT_ULL(46)
 #define XHCI_WRITE_64_HI_LO	BIT_ULL(47)
 #define XHCI_CDNS_SCTX_QUIRK	BIT_ULL(48)

From 2397d61ee45cddb8f3bd3a3a9840ef0f0b5aa843 Mon Sep 17 00:00:00 2001
From: Christian Heusel <christian@heusel.eu>
Date: Mon, 24 Feb 2025 09:32:59 +0100
Subject: [PATCH 0750/1173] Revert "drivers/card_reader/rtsx_usb: Restore
 interrupt based detection"

This reverts commit 235b630eda072d7e7b102ab346d6b8a2c028a772.

This commit was found responsible for issues with SD card recognition,
as users had to re-insert their cards in the readers and wait for a
while. As for some people the SD card was involved in the boot process
it also caused boot failures.

Cc: stable@vger.kernel.org
Link: https://bbs.archlinux.org/viewtopic.php?id=303321
Fixes: 235b630eda07 ("drivers/card_reader/rtsx_usb: Restore interrupt based detection")
Reported-by: qf <quintafeira@tutanota.com>
Closes: https://lore.kernel.org/all/1de87dfa-1e81-45b7-8dcb-ad86c21d5352@heusel.eu
Signed-off-by: Christian Heusel <christian@heusel.eu>
Link: https://lore.kernel.org/r/20250224-revert-sdcard-patch-v1-1-d1a457fbb796@heusel.eu
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/cardreader/rtsx_usb.c | 15 ---------------
 1 file changed, 15 deletions(-)

diff --git a/drivers/misc/cardreader/rtsx_usb.c b/drivers/misc/cardreader/rtsx_usb.c
index e0174da5e9fc3..77b0490a1b38d 100644
--- a/drivers/misc/cardreader/rtsx_usb.c
+++ b/drivers/misc/cardreader/rtsx_usb.c
@@ -286,7 +286,6 @@ static int rtsx_usb_get_status_with_bulk(struct rtsx_ucr *ucr, u16 *status)
 int rtsx_usb_get_card_status(struct rtsx_ucr *ucr, u16 *status)
 {
 	int ret;
-	u8 interrupt_val = 0;
 	u16 *buf;
 
 	if (!status)
@@ -309,20 +308,6 @@ int rtsx_usb_get_card_status(struct rtsx_ucr *ucr, u16 *status)
 		ret = rtsx_usb_get_status_with_bulk(ucr, status);
 	}
 
-	rtsx_usb_read_register(ucr, CARD_INT_PEND, &interrupt_val);
-	/* Cross check presence with interrupts */
-	if (*status & XD_CD)
-		if (!(interrupt_val & XD_INT))
-			*status &= ~XD_CD;
-
-	if (*status & SD_CD)
-		if (!(interrupt_val & SD_INT))
-			*status &= ~SD_CD;
-
-	if (*status & MS_CD)
-		if (!(interrupt_val & MS_INT))
-			*status &= ~MS_CD;
-
 	/* usb_control_msg may return positive when success */
 	if (ret < 0)
 		return ret;

From ad546940b5991d3e141238cd80a6d1894b767184 Mon Sep 17 00:00:00 2001
From: "Xin Li (Intel)" <xin@zytor.com>
Date: Tue, 26 Nov 2024 10:45:28 -0800
Subject: [PATCH 0751/1173] x86/ia32: Leave NULL selector values 0~3 unchanged

The first GDT descriptor is reserved as 'NULL descriptor'.  As bits 0
and 1 of a segment selector, i.e., the RPL bits, are NOT used to index
GDT, selector values 0~3 all point to the NULL descriptor, thus values
0, 1, 2 and 3 are all valid NULL selector values.

When a NULL selector value is to be loaded into a segment register,
reload_segments() sets its RPL bits.  Later IRET zeros ES, FS, GS, and
DS segment registers if any of them is found to have any nonzero NULL
selector value.  The two operations offset each other to actually effect
a nop.

Besides, zeroing of RPL in NULL selector values is an information leak
in pre-FRED systems as userspace can spot any interrupt/exception by
loading a nonzero NULL selector, and waiting for it to become zero.
But there is nothing software can do to prevent it before FRED.

ERETU, the only legit instruction to return to userspace from kernel
under FRED, by design does NOT zero any segment register to avoid this
problem behavior.

As such, leave NULL selector values 0~3 unchanged and close the leak.

Do the same on 32-bit kernel as well.

Signed-off-by: Xin Li (Intel) <xin@zytor.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20241126184529.1607334-1-xin@zytor.com
---
 arch/x86/kernel/signal_32.c | 62 +++++++++++++++++++++++++------------
 1 file changed, 43 insertions(+), 19 deletions(-)

diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal_32.c
index ef654530bf5a9..98123ff10506c 100644
--- a/arch/x86/kernel/signal_32.c
+++ b/arch/x86/kernel/signal_32.c
@@ -33,25 +33,55 @@
 #include <asm/smap.h>
 #include <asm/gsseg.h>
 
+/*
+ * The first GDT descriptor is reserved as 'NULL descriptor'.  As bits 0
+ * and 1 of a segment selector, i.e., the RPL bits, are NOT used to index
+ * GDT, selector values 0~3 all point to the NULL descriptor, thus values
+ * 0, 1, 2 and 3 are all valid NULL selector values.
+ *
+ * However IRET zeros ES, FS, GS, and DS segment registers if any of them
+ * is found to have any nonzero NULL selector value, which can be used by
+ * userspace in pre-FRED systems to spot any interrupt/exception by loading
+ * a nonzero NULL selector and waiting for it to become zero.  Before FRED
+ * there was nothing software could do to prevent such an information leak.
+ *
+ * ERETU, the only legit instruction to return to userspace from kernel
+ * under FRED, by design does NOT zero any segment register to avoid this
+ * problem behavior.
+ *
+ * As such, leave NULL selector values 0~3 unchanged.
+ */
+static inline u16 fixup_rpl(u16 sel)
+{
+	return sel <= 3 ? sel : sel | 3;
+}
+
 #ifdef CONFIG_IA32_EMULATION
 #include <asm/unistd_32_ia32.h>
 
 static inline void reload_segments(struct sigcontext_32 *sc)
 {
-	unsigned int cur;
+	u16 cur;
 
+	/*
+	 * Reload fs and gs if they have changed in the signal
+	 * handler.  This does not handle long fs/gs base changes in
+	 * the handler, but does not clobber them at least in the
+	 * normal case.
+	 */
 	savesegment(gs, cur);
-	if ((sc->gs | 0x03) != cur)
-		load_gs_index(sc->gs | 0x03);
+	if (fixup_rpl(sc->gs) != cur)
+		load_gs_index(fixup_rpl(sc->gs));
 	savesegment(fs, cur);
-	if ((sc->fs | 0x03) != cur)
-		loadsegment(fs, sc->fs | 0x03);
+	if (fixup_rpl(sc->fs) != cur)
+		loadsegment(fs, fixup_rpl(sc->fs));
+
 	savesegment(ds, cur);
-	if ((sc->ds | 0x03) != cur)
-		loadsegment(ds, sc->ds | 0x03);
+	if (fixup_rpl(sc->ds) != cur)
+		loadsegment(ds, fixup_rpl(sc->ds));
 	savesegment(es, cur);
-	if ((sc->es | 0x03) != cur)
-		loadsegment(es, sc->es | 0x03);
+	if (fixup_rpl(sc->es) != cur)
+		loadsegment(es, fixup_rpl(sc->es));
 }
 
 #define sigset32_t			compat_sigset_t
@@ -105,18 +135,12 @@ static bool ia32_restore_sigcontext(struct pt_regs *regs,
 	regs->orig_ax = -1;
 
 #ifdef CONFIG_IA32_EMULATION
-	/*
-	 * Reload fs and gs if they have changed in the signal
-	 * handler.  This does not handle long fs/gs base changes in
-	 * the handler, but does not clobber them at least in the
-	 * normal case.
-	 */
 	reload_segments(&sc);
 #else
-	loadsegment(gs, sc.gs);
-	regs->fs = sc.fs;
-	regs->es = sc.es;
-	regs->ds = sc.ds;
+	loadsegment(gs, fixup_rpl(sc.gs));
+	regs->fs = fixup_rpl(sc.fs);
+	regs->es = fixup_rpl(sc.es);
+	regs->ds = fixup_rpl(sc.ds);
 #endif
 
 	return fpu__restore_sig(compat_ptr(sc.fpstate), 1);

From cbf85b9cb80bec6345ffe0368dfff98386f4714f Mon Sep 17 00:00:00 2001
From: Salah Triki <salah.triki@gmail.com>
Date: Fri, 21 Feb 2025 22:32:59 +0100
Subject: [PATCH 0752/1173] bluetooth: btusb: Initialize .owner field of
 force_poll_sync_fops

Initialize .owner field of force_poll_sync_fops to THIS_MODULE in order to
prevent btusb from being unloaded while its operations are in use.

Fixes: 800fe5ec302e ("Bluetooth: btusb: Add support for queuing during polling interval")
Signed-off-by: Salah Triki <salah.triki@gmail.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btusb.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 8149e53fd0a76..2a8d91963c63f 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -3644,6 +3644,7 @@ static ssize_t force_poll_sync_write(struct file *file,
 }
 
 static const struct file_operations force_poll_sync_fops = {
+	.owner		= THIS_MODULE,
 	.open		= simple_open,
 	.read		= force_poll_sync_read,
 	.write		= force_poll_sync_write,

From f2176a07e7b19f73e05c805cf3d130a2999154cb Mon Sep 17 00:00:00 2001
From: Haoxiang Li <haoxiang_li2024@163.com>
Date: Fri, 21 Feb 2025 16:49:47 +0800
Subject: [PATCH 0753/1173] Bluetooth: Add check for mgmt_alloc_skb() in
 mgmt_remote_name()

Add check for the return value of mgmt_alloc_skb() in
mgmt_remote_name() to prevent null pointer dereference.

Fixes: ba17bb62ce41 ("Bluetooth: Fix skb allocation in mgmt_remote_name() & mgmt_device_connected()")
Cc: stable@vger.kernel.org
Signed-off-by: Haoxiang Li <haoxiang_li2024@163.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/mgmt.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index f53304cb09dbe..3e0f88cd975c8 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -10413,6 +10413,8 @@ void mgmt_remote_name(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 
 	skb = mgmt_alloc_skb(hdev, MGMT_EV_DEVICE_FOUND,
 			     sizeof(*ev) + (name ? eir_precalc_len(name_len) : 0));
+	if (!skb)
+		return;
 
 	ev = skb_put(skb, sizeof(*ev));
 	bacpy(&ev->addr.bdaddr, bdaddr);

From d8df010f72b8a32aaea393e36121738bb53ed905 Mon Sep 17 00:00:00 2001
From: Haoxiang Li <haoxiang_li2024@163.com>
Date: Fri, 21 Feb 2025 16:58:01 +0800
Subject: [PATCH 0754/1173] Bluetooth: Add check for mgmt_alloc_skb() in
 mgmt_device_connected()

Add check for the return value of mgmt_alloc_skb() in
mgmt_device_connected() to prevent null pointer dereference.

Fixes: e96741437ef0 ("Bluetooth: mgmt: Make use of mgmt_send_event_skb in MGMT_EV_DEVICE_CONNECTED")
Cc: stable@vger.kernel.org
Signed-off-by: Haoxiang Li <haoxiang_li2024@163.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/mgmt.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 3e0f88cd975c8..621c555f639be 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -9660,6 +9660,9 @@ void mgmt_device_connected(struct hci_dev *hdev, struct hci_conn *conn,
 				     sizeof(*ev) + (name ? eir_precalc_len(name_len) : 0) +
 				     eir_precalc_len(sizeof(conn->dev_class)));
 
+	if (!skb)
+		return;
+
 	ev = skb_put(skb, sizeof(*ev));
 	bacpy(&ev->addr.bdaddr, &conn->dst);
 	ev->addr.type = link_to_bdaddr(conn->type, conn->dst_type);

From b8ffd979356e33a3af0854d47375bba611126f3b Mon Sep 17 00:00:00 2001
From: Zhang Kunbo <zhangkunbo@huawei.com>
Date: Tue, 26 Nov 2024 02:05:11 +0000
Subject: [PATCH 0755/1173] x86/irq: Fix missing declaration of 'io_apic_irqs'

Fix this sparse warning:

  arch/x86/kernel/i8259.c:57:15: warning: symbol 'io_apic_irqs' was not declared. Should it be static?

Signed-off-by: Zhang Kunbo <zhangkunbo@huawei.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20241126020511.3464664-1-zhangkunbo@huawei.com
---
 arch/x86/kernel/i8259.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index c20d1832c4812..2bade73f49e33 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -23,6 +23,7 @@
 #include <asm/desc.h>
 #include <asm/apic.h>
 #include <asm/i8259.h>
+#include <asm/io_apic.h>
 
 /*
  * This is the 'legacy' 8259A Programmable Interrupt Controller,

From e008eeec7868a9ca6e159726aeb9bdbf2ab86647 Mon Sep 17 00:00:00 2001
From: Zhang Kunbo <zhangkunbo@huawei.com>
Date: Tue, 26 Nov 2024 01:54:57 +0000
Subject: [PATCH 0756/1173] x86/platform: Fix missing declaration of
 'x86_apple_machine'

Fix this sparse warning:

  arch/x86/kernel/quirks.c:662:6: warning: symbol 'x86_apple_machine' was not declared. Should it be static?

Signed-off-by: Zhang Kunbo <zhangkunbo@huawei.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20241126015636.3463994-1-zhangkunbo@huawei.com
---
 arch/x86/kernel/quirks.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 6d0df6a58873d..a92f18db96100 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -10,6 +10,8 @@
 #include <asm/setup.h>
 #include <asm/mce.h>
 
+#include <linux/platform_data/x86/apple.h>
+
 #if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_SMP) && defined(CONFIG_PCI)
 
 static void quirk_intel_irqbalance(struct pci_dev *dev)

From 72dafb567760320f2de7447cd6e979bf9d4e5d17 Mon Sep 17 00:00:00 2001
From: Kevin Loughlin <kevinloughlin@google.com>
Date: Fri, 22 Nov 2024 20:23:22 +0000
Subject: [PATCH 0757/1173] x86/sev: Add missing RIP_REL_REF() invocations
 during sme_enable()

The following commit:

  1c811d403afd ("x86/sev: Fix position dependent variable references in startup code")

introduced RIP_REL_REF() to force RIP-relative accesses to global variables,
as needed to prevent crashes during early SEV/SME startup code.

For completeness, RIP_REL_REF() should be used with additional variables during
sme_enable():

  https://lore.kernel.org/all/CAMj1kXHnA0fJu6zh634=fbJswp59kSRAbhW+ubDGj1+NYwZJ-Q@mail.gmail.com/

Access these vars with RIP_REL_REF() to prevent problem reoccurence.

Fixes: 1c811d403afd ("x86/sev: Fix position dependent variable references in startup code")
Signed-off-by: Kevin Loughlin <kevinloughlin@google.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/r/20241122202322.977678-1-kevinloughlin@google.com
---
 arch/x86/mm/mem_encrypt_identity.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c
index e6c7686f443a0..9fce5b87b8c50 100644
--- a/arch/x86/mm/mem_encrypt_identity.c
+++ b/arch/x86/mm/mem_encrypt_identity.c
@@ -565,7 +565,7 @@ void __head sme_enable(struct boot_params *bp)
 	}
 
 	RIP_REL_REF(sme_me_mask) = me_mask;
-	physical_mask &= ~me_mask;
-	cc_vendor = CC_VENDOR_AMD;
+	RIP_REL_REF(physical_mask) &= ~me_mask;
+	RIP_REL_REF(cc_vendor) = CC_VENDOR_AMD;
 	cc_set_mask(me_mask);
 }

From 0979ff3676b1b4e6a20970bc265491d23c2da42b Mon Sep 17 00:00:00 2001
From: Maurizio Lombardi <mlombard@redhat.com>
Date: Thu, 27 Feb 2025 20:00:05 +0100
Subject: [PATCH 0758/1173] nvmet: remove old function prototype

nvmet_subsys_nsid_exists() doesn't exist anymore

Fixes: 74d16965d7ac ("nvmet-loop: avoid using mutex in IO hotpath")
Signed-off-by: Maurizio Lombardi <mlombard@redhat.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/nvmet.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index d2c1233981e1a..fcf4f460dc9a4 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -647,7 +647,6 @@ void nvmet_subsys_disc_changed(struct nvmet_subsys *subsys,
 		struct nvmet_host *host);
 void nvmet_add_async_event(struct nvmet_ctrl *ctrl, u8 event_type,
 		u8 event_info, u8 log_page);
-bool nvmet_subsys_nsid_exists(struct nvmet_subsys *subsys, u32 nsid);
 
 #define NVMET_MIN_QUEUE_SIZE	16
 #define NVMET_MAX_QUEUE_SIZE	1024

From afb41b08c44e5386f2f52fa859010ac4afd2b66f Mon Sep 17 00:00:00 2001
From: Maurizio Lombardi <mlombard@redhat.com>
Date: Mon, 24 Feb 2025 15:40:58 +0100
Subject: [PATCH 0759/1173] nvme-tcp: Fix a C2HTermReq error message

In H2CTermReq, a FES with value 0x05 means "R2T Limit Exceeded"; but
in C2HTermReq the same value has a different meaning (Data Transfer Limit
Exceeded).

Fixes: 84e009042d0f ("nvme-tcp: add basic support for the C2HTermReq PDU")
Signed-off-by: Maurizio Lombardi <mlombard@redhat.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/tcp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 8c14018201dbd..1094cbbec169f 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -775,7 +775,7 @@ static void nvme_tcp_handle_c2h_term(struct nvme_tcp_queue *queue,
 		[NVME_TCP_FES_PDU_SEQ_ERR] = "PDU Sequence Error",
 		[NVME_TCP_FES_HDR_DIGEST_ERR] = "Header Digest Error",
 		[NVME_TCP_FES_DATA_OUT_OF_RANGE] = "Data Transfer Out Of Range",
-		[NVME_TCP_FES_R2T_LIMIT_EXCEEDED] = "R2T Limit Exceeded",
+		[NVME_TCP_FES_DATA_LIMIT_EXCEEDED] = "Data Transfer Limit Exceeded",
 		[NVME_TCP_FES_UNSUPPORTED_PARAM] = "Unsupported Parameter",
 	};
 

From ada9ce437a4da8e27243251bd7a9ecec32ebd72a Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <antonio@openvpn.net>
Date: Thu, 27 Feb 2025 02:21:26 +0100
Subject: [PATCH 0760/1173] mailmap: remove unwanted entry for Antonio
 Quartulli

antonio@openvpn.net is still used for sending
patches under the OpenVPN Inc. umbrella, therefore this
address should not be re-mapped.

Signed-off-by: Antonio Quartulli <antonio@openvpn.net>
Link: https://patch.msgid.link/20250227-b4-ovpn-v20-1-93f363310834@openvpn.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .mailmap | 1 -
 1 file changed, 1 deletion(-)

diff --git a/.mailmap b/.mailmap
index a897c16d3baef..598f31c4b498e 100644
--- a/.mailmap
+++ b/.mailmap
@@ -88,7 +88,6 @@ Antonio Quartulli <antonio@mandelbit.com> <antonio@open-mesh.com>
 Antonio Quartulli <antonio@mandelbit.com> <antonio.quartulli@open-mesh.com>
 Antonio Quartulli <antonio@mandelbit.com> <ordex@autistici.org>
 Antonio Quartulli <antonio@mandelbit.com> <ordex@ritirata.org>
-Antonio Quartulli <antonio@mandelbit.com> <antonio@openvpn.net>
 Antonio Quartulli <antonio@mandelbit.com> <a@unstable.cc>
 Anup Patel <anup@brainfault.org> <anup.patel@wdc.com>
 Archit Taneja <archit@ti.com>

From 6f86bdeab633a56d5c6dccf1a2c5989b6a5e323e Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Thu, 27 Feb 2025 16:39:44 -0500
Subject: [PATCH 0761/1173] tracing: Fix bad hist from corrupting
 named_triggers list

The following commands causes a crash:

 ~# cd /sys/kernel/tracing/events/rcu/rcu_callback
 ~# echo 'hist:name=bad:keys=common_pid:onmax(bogus).save(common_pid)' > trigger
 bash: echo: write error: Invalid argument
 ~# echo 'hist:name=bad:keys=common_pid' > trigger

Because the following occurs:

event_trigger_write() {
  trigger_process_regex() {
    event_hist_trigger_parse() {

      data = event_trigger_alloc(..);

      event_trigger_register(.., data) {
        cmd_ops->reg(.., data, ..) [hist_register_trigger()] {
          data->ops->init() [event_hist_trigger_init()] {
            save_named_trigger(name, data) {
              list_add(&data->named_list, &named_triggers);
            }
          }
        }
      }

      ret = create_actions(); (return -EINVAL)
      if (ret)
        goto out_unreg;
[..]
      ret = hist_trigger_enable(data, ...) {
        list_add_tail_rcu(&data->list, &file->triggers); <<<---- SKIPPED!!! (this is important!)
[..]
 out_unreg:
      event_hist_unregister(.., data) {
        cmd_ops->unreg(.., data, ..) [hist_unregister_trigger()] {
          list_for_each_entry(iter, &file->triggers, list) {
            if (!hist_trigger_match(data, iter, named_data, false))   <- never matches
                continue;
            [..]
            test = iter;
          }
          if (test && test->ops->free) <<<-- test is NULL

            test->ops->free(test) [event_hist_trigger_free()] {
              [..]
              if (data->name)
                del_named_trigger(data) {
                  list_del(&data->named_list);  <<<<-- NEVER gets removed!
                }
              }
           }
         }

         [..]
         kfree(data); <<<-- frees item but it is still on list

The next time a hist with name is registered, it causes an u-a-f bug and
the kernel can crash.

Move the code around such that if event_trigger_register() succeeds, the
next thing called is hist_trigger_enable() which adds it to the list.

A bunch of actions is called if get_named_trigger_data() returns false.
But that doesn't need to be called after event_trigger_register(), so it
can be moved up, allowing event_trigger_register() to be called just
before hist_trigger_enable() keeping them together and allowing the
file->triggers to be properly populated.

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/20250227163944.1c37f85f@gandalf.local.home
Fixes: 067fe038e70f6 ("tracing: Add variable reference handling to hist triggers")
Reported-by: Tomas Glozar <tglozar@redhat.com>
Tested-by: Tomas Glozar <tglozar@redhat.com>
Reviewed-by: Tom Zanussi <zanussi@kernel.org>
Closes: https://lore.kernel.org/all/CAP4=nvTsxjckSBTz=Oe_UYh8keD9_sZC4i++4h72mJLic4_W4A@mail.gmail.com/
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events_hist.c | 30 +++++++++++++++---------------
 1 file changed, 15 insertions(+), 15 deletions(-)

diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 261163b00137a..ad7419e240556 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -6724,27 +6724,27 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops,
 	if (existing_hist_update_only(glob, trigger_data, file))
 		goto out_free;
 
-	ret = event_trigger_register(cmd_ops, file, glob, trigger_data);
-	if (ret < 0)
-		goto out_free;
+	if (!get_named_trigger_data(trigger_data)) {
 
-	if (get_named_trigger_data(trigger_data))
-		goto enable;
+		ret = create_actions(hist_data);
+		if (ret)
+			goto out_free;
 
-	ret = create_actions(hist_data);
-	if (ret)
-		goto out_unreg;
+		if (has_hist_vars(hist_data) || hist_data->n_var_refs) {
+			ret = save_hist_vars(hist_data);
+			if (ret)
+				goto out_free;
+		}
 
-	if (has_hist_vars(hist_data) || hist_data->n_var_refs) {
-		ret = save_hist_vars(hist_data);
+		ret = tracing_map_init(hist_data->map);
 		if (ret)
-			goto out_unreg;
+			goto out_free;
 	}
 
-	ret = tracing_map_init(hist_data->map);
-	if (ret)
-		goto out_unreg;
-enable:
+	ret = event_trigger_register(cmd_ops, file, glob, trigger_data);
+	if (ret < 0)
+		goto out_free;
+
 	ret = hist_trigger_enable(trigger_data, file);
 	if (ret)
 		goto out_unreg;

From 3908b6baf2ac20138915b5ca98338b4f063954d8 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Wed, 26 Feb 2025 15:27:03 +0100
Subject: [PATCH 0762/1173] selftests/ftrace: Let fprobe test consider already
 enabled functions

The fprobe test fails on Fedora 41 since the fprobe test assumption that
the number of enabled_functions is zero before the test starts is not
necessarily true. Some user space tools, like systemd, add BPF programs
that attach to functions. Those will show up in the enabled_functions table
and must be taken into account by the fprobe test.

Therefore count the number of lines of enabled_functions before tests
start, and use that as base when comparing expected results.

Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Link: https://lore.kernel.org/20250226142703.910860-1-hca@linux.ibm.com
Fixes: e85c5e9792b9 ("selftests/ftrace: Update fprobe test to check enabled_functions file")
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 .../test.d/dynevent/add_remove_fprobe.tc       | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe.tc
index 449f9d8be7462..73f6c6fcecabe 100644
--- a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe.tc
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe.tc
@@ -10,12 +10,16 @@ PLACE=$FUNCTION_FORK
 PLACE2="kmem_cache_free"
 PLACE3="schedule_timeout"
 
+# Some functions may have BPF programs attached, therefore
+# count already enabled_functions before tests start
+ocnt=`cat enabled_functions | wc -l`
+
 echo "f:myevent1 $PLACE" >> dynamic_events
 
 # Make sure the event is attached and is the only one
 grep -q $PLACE enabled_functions
 cnt=`cat enabled_functions | wc -l`
-if [ $cnt -ne 1 ]; then
+if [ $cnt -ne $((ocnt + 1)) ]; then
 	exit_fail
 fi
 
@@ -23,7 +27,7 @@ echo "f:myevent2 $PLACE%return" >> dynamic_events
 
 # It should till be the only attached function
 cnt=`cat enabled_functions | wc -l`
-if [ $cnt -ne 1 ]; then
+if [ $cnt -ne $((ocnt + 1)) ]; then
 	exit_fail
 fi
 
@@ -32,7 +36,7 @@ echo "f:myevent3 $PLACE2" >> dynamic_events
 
 grep -q $PLACE2 enabled_functions
 cnt=`cat enabled_functions | wc -l`
-if [ $cnt -ne 2 ]; then
+if [ $cnt -ne $((ocnt + 2)) ]; then
 	exit_fail
 fi
 
@@ -49,7 +53,7 @@ grep -q myevent1 dynamic_events
 
 # should still have 2 left
 cnt=`cat enabled_functions | wc -l`
-if [ $cnt -ne 2 ]; then
+if [ $cnt -ne $((ocnt + 2)) ]; then
 	exit_fail
 fi
 
@@ -57,7 +61,7 @@ echo > dynamic_events
 
 # Should have none left
 cnt=`cat enabled_functions | wc -l`
-if [ $cnt -ne 0 ]; then
+if [ $cnt -ne $ocnt ]; then
 	exit_fail
 fi
 
@@ -65,7 +69,7 @@ echo "f:myevent4 $PLACE" >> dynamic_events
 
 # Should only have one enabled
 cnt=`cat enabled_functions | wc -l`
-if [ $cnt -ne 1 ]; then
+if [ $cnt -ne $((ocnt + 1)) ]; then
 	exit_fail
 fi
 
@@ -73,7 +77,7 @@ echo > dynamic_events
 
 # Should have none left
 cnt=`cat enabled_functions | wc -l`
-if [ $cnt -ne 0 ]; then
+if [ $cnt -ne $ocnt ]; then
 	exit_fail
 fi
 

From a1a7eb89ca0b89dc1c326eeee2596f263291aca3 Mon Sep 17 00:00:00 2001
From: Nikolay Kuratov <kniv@yandex-team.ru>
Date: Thu, 6 Feb 2025 12:01:56 +0300
Subject: [PATCH 0763/1173] ftrace: Avoid potential division by zero in
 function_stat_show()

Check whether denominator expression x * (x - 1) * 1000 mod {2^32, 2^64}
produce zero and skip stddev computation in that case.

For now don't care about rec->counter * rec->counter overflow because
rec->time * rec->time overflow will likely happen earlier.

Cc: stable@vger.kernel.org
Cc: Wen Yang <wenyang@linux.alibaba.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/20250206090156.1561783-1-kniv@yandex-team.ru
Fixes: e31f7939c1c27 ("ftrace: Avoid potential division by zero in function profiler")
Signed-off-by: Nikolay Kuratov <kniv@yandex-team.ru>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/ftrace.c | 27 ++++++++++++---------------
 1 file changed, 12 insertions(+), 15 deletions(-)

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 6b0c25761ccb1..fc88e0688daf0 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -540,6 +540,7 @@ static int function_stat_show(struct seq_file *m, void *v)
 	static struct trace_seq s;
 	unsigned long long avg;
 	unsigned long long stddev;
+	unsigned long long stddev_denom;
 #endif
 	guard(mutex)(&ftrace_profile_lock);
 
@@ -559,23 +560,19 @@ static int function_stat_show(struct seq_file *m, void *v)
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	seq_puts(m, "    ");
 
-	/* Sample standard deviation (s^2) */
-	if (rec->counter <= 1)
-		stddev = 0;
-	else {
-		/*
-		 * Apply Welford's method:
-		 * s^2 = 1 / (n * (n-1)) * (n * \Sum (x_i)^2 - (\Sum x_i)^2)
-		 */
+	/*
+	 * Variance formula:
+	 * s^2 = 1 / (n * (n-1)) * (n * \Sum (x_i)^2 - (\Sum x_i)^2)
+	 * Maybe Welford's method is better here?
+	 * Divide only by 1000 for ns^2 -> us^2 conversion.
+	 * trace_print_graph_duration will divide by 1000 again.
+	 */
+	stddev = 0;
+	stddev_denom = rec->counter * (rec->counter - 1) * 1000;
+	if (stddev_denom) {
 		stddev = rec->counter * rec->time_squared -
 			 rec->time * rec->time;
-
-		/*
-		 * Divide only 1000 for ns^2 -> us^2 conversion.
-		 * trace_print_graph_duration will divide 1000 again.
-		 */
-		stddev = div64_ul(stddev,
-				  rec->counter * (rec->counter - 1) * 1000);
+		stddev = div64_ul(stddev, stddev_denom);
 	}
 
 	trace_seq_init(&s);

From ad95bab0cd28ed77c2c0d0b6e76e03e031391064 Mon Sep 17 00:00:00 2001
From: Maurizio Lombardi <mlombard@redhat.com>
Date: Wed, 26 Feb 2025 14:42:18 +0100
Subject: [PATCH 0764/1173] nvme-tcp: fix potential memory corruption in
 nvme_tcp_recv_pdu()

nvme_tcp_recv_pdu() doesn't check the validity of the header length.
When header digests are enabled, a target might send a packet with an
invalid header length (e.g. 255), causing nvme_tcp_verify_hdgst()
to access memory outside the allocated area and cause memory corruptions
by overwriting it with the calculated digest.

Fix this by rejecting packets with an unexpected header length.

Fixes: 3f2304f8c6d6 ("nvme-tcp: add NVMe over TCP host driver")
Signed-off-by: Maurizio Lombardi <mlombard@redhat.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/tcp.c | 32 +++++++++++++++++++++++++++++---
 1 file changed, 29 insertions(+), 3 deletions(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 1094cbbec169f..23f11527d29d0 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -217,6 +217,19 @@ static inline int nvme_tcp_queue_id(struct nvme_tcp_queue *queue)
 	return queue - queue->ctrl->queues;
 }
 
+static inline bool nvme_tcp_recv_pdu_supported(enum nvme_tcp_pdu_type type)
+{
+	switch (type) {
+	case nvme_tcp_c2h_term:
+	case nvme_tcp_c2h_data:
+	case nvme_tcp_r2t:
+	case nvme_tcp_rsp:
+		return true;
+	default:
+		return false;
+	}
+}
+
 /*
  * Check if the queue is TLS encrypted
  */
@@ -818,6 +831,16 @@ static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb,
 		return 0;
 
 	hdr = queue->pdu;
+	if (unlikely(hdr->hlen != sizeof(struct nvme_tcp_rsp_pdu))) {
+		if (!nvme_tcp_recv_pdu_supported(hdr->type))
+			goto unsupported_pdu;
+
+		dev_err(queue->ctrl->ctrl.device,
+			"pdu type %d has unexpected header length (%d)\n",
+			hdr->type, hdr->hlen);
+		return -EPROTO;
+	}
+
 	if (unlikely(hdr->type == nvme_tcp_c2h_term)) {
 		/*
 		 * C2HTermReq never includes Header or Data digests.
@@ -850,10 +873,13 @@ static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb,
 		nvme_tcp_init_recv_ctx(queue);
 		return nvme_tcp_handle_r2t(queue, (void *)queue->pdu);
 	default:
-		dev_err(queue->ctrl->ctrl.device,
-			"unsupported pdu type (%d)\n", hdr->type);
-		return -EINVAL;
+		goto unsupported_pdu;
 	}
+
+unsupported_pdu:
+	dev_err(queue->ctrl->ctrl.device,
+		"unsupported pdu type (%d)\n", hdr->type);
+	return -EINVAL;
 }
 
 static inline void nvme_tcp_end_request(struct request *rq, u16 status)

From a16f88964c647103dad7743a484b216d488a6352 Mon Sep 17 00:00:00 2001
From: Meir Elisha <meir.elisha@volumez.com>
Date: Wed, 26 Feb 2025 09:28:12 +0200
Subject: [PATCH 0765/1173] nvmet-tcp: Fix a possible sporadic response drops
 in weakly ordered arch

The order in which queue->cmd and rcv_state are updated is crucial.
If these assignments are reordered by the compiler, the worker might not
get queued in nvmet_tcp_queue_response(), hanging the IO. to enforce the
the correct reordering, set rcv_state using smp_store_release().

Fixes: bdaf13279192 ("nvmet-tcp: fix a segmentation fault during io parsing error")

Signed-off-by: Meir Elisha <meir.elisha@volumez.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/tcp.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index 7c51c2a8c109a..4f9cac8a5abe0 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -571,10 +571,16 @@ static void nvmet_tcp_queue_response(struct nvmet_req *req)
 	struct nvmet_tcp_cmd *cmd =
 		container_of(req, struct nvmet_tcp_cmd, req);
 	struct nvmet_tcp_queue	*queue = cmd->queue;
+	enum nvmet_tcp_recv_state queue_state;
+	struct nvmet_tcp_cmd *queue_cmd;
 	struct nvme_sgl_desc *sgl;
 	u32 len;
 
-	if (unlikely(cmd == queue->cmd)) {
+	/* Pairs with store_release in nvmet_prepare_receive_pdu() */
+	queue_state = smp_load_acquire(&queue->rcv_state);
+	queue_cmd = READ_ONCE(queue->cmd);
+
+	if (unlikely(cmd == queue_cmd)) {
 		sgl = &cmd->req.cmd->common.dptr.sgl;
 		len = le32_to_cpu(sgl->length);
 
@@ -583,7 +589,7 @@ static void nvmet_tcp_queue_response(struct nvmet_req *req)
 		 * Avoid using helpers, this might happen before
 		 * nvmet_req_init is completed.
 		 */
-		if (queue->rcv_state == NVMET_TCP_RECV_PDU &&
+		if (queue_state == NVMET_TCP_RECV_PDU &&
 		    len && len <= cmd->req.port->inline_data_size &&
 		    nvme_is_write(cmd->req.cmd))
 			return;
@@ -847,8 +853,9 @@ static void nvmet_prepare_receive_pdu(struct nvmet_tcp_queue *queue)
 {
 	queue->offset = 0;
 	queue->left = sizeof(struct nvme_tcp_hdr);
-	queue->cmd = NULL;
-	queue->rcv_state = NVMET_TCP_RECV_PDU;
+	WRITE_ONCE(queue->cmd, NULL);
+	/* Ensure rcv_state is visible only after queue->cmd is set */
+	smp_store_release(&queue->rcv_state, NVMET_TCP_RECV_PDU);
 }
 
 static void nvmet_tcp_free_crypto(struct nvmet_tcp_queue *queue)

From 00371a3f48775967950c2fe3ec97b7c786ca956d Mon Sep 17 00:00:00 2001
From: Philipp Stanner <phasta@kernel.org>
Date: Wed, 26 Feb 2025 09:52:05 +0100
Subject: [PATCH 0766/1173] stmmac: loongson: Pass correct arg to PCI function

pcim_iomap_regions() should receive the driver's name as its third
parameter, not the PCI device's name.

Define the driver name with a macro and use it at the appropriate
places, including pcim_iomap_regions().

Cc: stable@vger.kernel.org # v5.14+
Fixes: 30bba69d7db4 ("stmmac: pci: Add dwmac support for Loongson")
Signed-off-by: Philipp Stanner <phasta@kernel.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Yanteng Si <si.yanteng@linux.dev>
Tested-by: Henry Chen <chenx97@aosc.io>
Link: https://patch.msgid.link/20250226085208.97891-2-phasta@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
index f5acfb7d4ff65..ab7c2750c1042 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
@@ -11,6 +11,8 @@
 #include "dwmac_dma.h"
 #include "dwmac1000.h"
 
+#define DRIVER_NAME "dwmac-loongson-pci"
+
 /* Normal Loongson Tx Summary */
 #define DMA_INTR_ENA_NIE_TX_LOONGSON	0x00040000
 /* Normal Loongson Rx Summary */
@@ -568,7 +570,7 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id
 	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
 		if (pci_resource_len(pdev, i) == 0)
 			continue;
-		ret = pcim_iomap_regions(pdev, BIT(0), pci_name(pdev));
+		ret = pcim_iomap_regions(pdev, BIT(0), DRIVER_NAME);
 		if (ret)
 			goto err_disable_device;
 		break;
@@ -687,7 +689,7 @@ static const struct pci_device_id loongson_dwmac_id_table[] = {
 MODULE_DEVICE_TABLE(pci, loongson_dwmac_id_table);
 
 static struct pci_driver loongson_dwmac_driver = {
-	.name = "dwmac-loongson-pci",
+	.name = DRIVER_NAME,
 	.id_table = loongson_dwmac_id_table,
 	.probe = loongson_dwmac_probe,
 	.remove = loongson_dwmac_remove,

From 023f3290b02552ea006c1a2013e373750d2cbff6 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Fri, 28 Feb 2025 09:51:15 +0100
Subject: [PATCH 0767/1173] x86/locking: Remove semicolon from "lock" prefix

Minimum version of binutils required to compile the kernel is 2.25.
This version correctly handles the "lock" prefix, so it is possible
to remove the semicolon, which was used to support ancient versions
of GNU as.

Due to the semicolon, the compiler considers "lock; insn" as two
separate instructions. Removing the semicolon makes asm length
calculations more accurate, consequently making scheduling and
inlining decisions of the compiler more accurate.

Removing the semicolon also enables assembler checks involving lock
prefix. Trying to assemble e.g. "lock andl %eax, %ebx" results in:

  Error: expecting lockable instruction after `lock'

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250228085149.2478245-1-ubizjak@gmail.com
---
 arch/x86/include/asm/alternative.h |  2 +-
 arch/x86/include/asm/barrier.h     |  8 ++++----
 arch/x86/include/asm/cmpxchg.h     |  4 ++--
 arch/x86/include/asm/cmpxchg_32.h  |  4 ++--
 arch/x86/include/asm/edac.h        |  2 +-
 arch/x86/include/asm/sync_bitops.h | 12 ++++++------
 6 files changed, 16 insertions(+), 16 deletions(-)

diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index e3903b731305c..3b3d3aa19acd0 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -48,7 +48,7 @@
 		".popsection\n"				\
 		"671:"
 
-#define LOCK_PREFIX LOCK_PREFIX_HERE "\n\tlock; "
+#define LOCK_PREFIX LOCK_PREFIX_HERE "\n\tlock "
 
 #else /* ! CONFIG_SMP */
 #define LOCK_PREFIX_HERE ""
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 7b44b3c4cce11..db70832232d4a 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -12,11 +12,11 @@
  */
 
 #ifdef CONFIG_X86_32
-#define mb() asm volatile(ALTERNATIVE("lock; addl $0,-4(%%esp)", "mfence", \
+#define mb() asm volatile(ALTERNATIVE("lock addl $0,-4(%%esp)", "mfence", \
 				      X86_FEATURE_XMM2) ::: "memory", "cc")
-#define rmb() asm volatile(ALTERNATIVE("lock; addl $0,-4(%%esp)", "lfence", \
+#define rmb() asm volatile(ALTERNATIVE("lock addl $0,-4(%%esp)", "lfence", \
 				       X86_FEATURE_XMM2) ::: "memory", "cc")
-#define wmb() asm volatile(ALTERNATIVE("lock; addl $0,-4(%%esp)", "sfence", \
+#define wmb() asm volatile(ALTERNATIVE("lock addl $0,-4(%%esp)", "sfence", \
 				       X86_FEATURE_XMM2) ::: "memory", "cc")
 #else
 #define __mb()	asm volatile("mfence":::"memory")
@@ -50,7 +50,7 @@
 #define __dma_rmb()	barrier()
 #define __dma_wmb()	barrier()
 
-#define __smp_mb()	asm volatile("lock; addl $0,-4(%%" _ASM_SP ")" ::: "memory", "cc")
+#define __smp_mb()	asm volatile("lock addl $0,-4(%%" _ASM_SP ")" ::: "memory", "cc")
 
 #define __smp_rmb()	dma_rmb()
 #define __smp_wmb()	barrier()
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index 5612648b02022..fd8afc1f5f6bb 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -134,7 +134,7 @@ extern void __add_wrong_size(void)
 	__raw_cmpxchg((ptr), (old), (new), (size), LOCK_PREFIX)
 
 #define __sync_cmpxchg(ptr, old, new, size)				\
-	__raw_cmpxchg((ptr), (old), (new), (size), "lock; ")
+	__raw_cmpxchg((ptr), (old), (new), (size), "lock ")
 
 #define __cmpxchg_local(ptr, old, new, size)				\
 	__raw_cmpxchg((ptr), (old), (new), (size), "")
@@ -222,7 +222,7 @@ extern void __add_wrong_size(void)
 	__raw_try_cmpxchg((ptr), (pold), (new), (size), LOCK_PREFIX)
 
 #define __sync_try_cmpxchg(ptr, pold, new, size)			\
-	__raw_try_cmpxchg((ptr), (pold), (new), (size), "lock; ")
+	__raw_try_cmpxchg((ptr), (pold), (new), (size), "lock ")
 
 #define __try_cmpxchg_local(ptr, pold, new, size)			\
 	__raw_try_cmpxchg((ptr), (pold), (new), (size), "")
diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h
index 95b5f990ca88e..8806c646d452d 100644
--- a/arch/x86/include/asm/cmpxchg_32.h
+++ b/arch/x86/include/asm/cmpxchg_32.h
@@ -105,7 +105,7 @@ static __always_inline bool __try_cmpxchg64_local(volatile u64 *ptr, u64 *oldp,
 
 static __always_inline u64 arch_cmpxchg64(volatile u64 *ptr, u64 old, u64 new)
 {
-	return __arch_cmpxchg64_emu(ptr, old, new, LOCK_PREFIX_HERE, "lock; ");
+	return __arch_cmpxchg64_emu(ptr, old, new, LOCK_PREFIX_HERE, "lock ");
 }
 #define arch_cmpxchg64 arch_cmpxchg64
 
@@ -140,7 +140,7 @@ static __always_inline u64 arch_cmpxchg64_local(volatile u64 *ptr, u64 old, u64
 
 static __always_inline bool arch_try_cmpxchg64(volatile u64 *ptr, u64 *oldp, u64 new)
 {
-	return __arch_try_cmpxchg64_emu(ptr, oldp, new, LOCK_PREFIX_HERE, "lock; ");
+	return __arch_try_cmpxchg64_emu(ptr, oldp, new, LOCK_PREFIX_HERE, "lock ");
 }
 #define arch_try_cmpxchg64 arch_try_cmpxchg64
 
diff --git a/arch/x86/include/asm/edac.h b/arch/x86/include/asm/edac.h
index 426fc53ff8030..dfbd1ebb9f10b 100644
--- a/arch/x86/include/asm/edac.h
+++ b/arch/x86/include/asm/edac.h
@@ -13,7 +13,7 @@ static inline void edac_atomic_scrub(void *va, u32 size)
 	 * are interrupt, DMA and SMP safe.
 	 */
 	for (i = 0; i < size / 4; i++, virt_addr++)
-		asm volatile("lock; addl $0, %0"::"m" (*virt_addr));
+		asm volatile("lock addl $0, %0"::"m" (*virt_addr));
 }
 
 #endif /* _ASM_X86_EDAC_H */
diff --git a/arch/x86/include/asm/sync_bitops.h b/arch/x86/include/asm/sync_bitops.h
index 6d8d6bc183b74..cd21a0405ac52 100644
--- a/arch/x86/include/asm/sync_bitops.h
+++ b/arch/x86/include/asm/sync_bitops.h
@@ -31,7 +31,7 @@
  */
 static inline void sync_set_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile("lock; " __ASM_SIZE(bts) " %1,%0"
+	asm volatile("lock " __ASM_SIZE(bts) " %1,%0"
 		     : "+m" (ADDR)
 		     : "Ir" (nr)
 		     : "memory");
@@ -49,7 +49,7 @@ static inline void sync_set_bit(long nr, volatile unsigned long *addr)
  */
 static inline void sync_clear_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile("lock; " __ASM_SIZE(btr) " %1,%0"
+	asm volatile("lock " __ASM_SIZE(btr) " %1,%0"
 		     : "+m" (ADDR)
 		     : "Ir" (nr)
 		     : "memory");
@@ -66,7 +66,7 @@ static inline void sync_clear_bit(long nr, volatile unsigned long *addr)
  */
 static inline void sync_change_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile("lock; " __ASM_SIZE(btc) " %1,%0"
+	asm volatile("lock " __ASM_SIZE(btc) " %1,%0"
 		     : "+m" (ADDR)
 		     : "Ir" (nr)
 		     : "memory");
@@ -82,7 +82,7 @@ static inline void sync_change_bit(long nr, volatile unsigned long *addr)
  */
 static inline bool sync_test_and_set_bit(long nr, volatile unsigned long *addr)
 {
-	return GEN_BINARY_RMWcc("lock; " __ASM_SIZE(bts), *addr, c, "Ir", nr);
+	return GEN_BINARY_RMWcc("lock " __ASM_SIZE(bts), *addr, c, "Ir", nr);
 }
 
 /**
@@ -95,7 +95,7 @@ static inline bool sync_test_and_set_bit(long nr, volatile unsigned long *addr)
  */
 static inline int sync_test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
-	return GEN_BINARY_RMWcc("lock; " __ASM_SIZE(btr), *addr, c, "Ir", nr);
+	return GEN_BINARY_RMWcc("lock " __ASM_SIZE(btr), *addr, c, "Ir", nr);
 }
 
 /**
@@ -108,7 +108,7 @@ static inline int sync_test_and_clear_bit(long nr, volatile unsigned long *addr)
  */
 static inline int sync_test_and_change_bit(long nr, volatile unsigned long *addr)
 {
-	return GEN_BINARY_RMWcc("lock; " __ASM_SIZE(btc), *addr, c, "Ir", nr);
+	return GEN_BINARY_RMWcc("lock " __ASM_SIZE(btc), *addr, c, "Ir", nr);
 }
 
 #define sync_test_bit(nr, addr) test_bit(nr, addr)

From a4248ee16f411ac1ea7dfab228a6659b111e3d65 Mon Sep 17 00:00:00 2001
From: Max Grobecker <max@grobecker.info>
Date: Thu, 27 Feb 2025 21:45:05 +0100
Subject: [PATCH 0768/1173] x86/cpu: Don't clear X86_FEATURE_LAHF_LM flag in
 init_amd_k8() on AMD when running in a virtual machine
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When running in a virtual machine, we might see the original hardware CPU
vendor string (i.e. "AuthenticAMD"), but a model and family ID set by the
hypervisor. In case we run on AMD hardware and the hypervisor sets a model
ID < 0x14, the LAHF cpu feature is eliminated from the the list of CPU
capabilities present to circumvent a bug with some BIOSes in conjunction with
AMD K8 processors.

Parsing the flags list from /proc/cpuinfo seems to be happening mostly in
bash scripts and prebuilt Docker containers, as it does not need to have
additionals tools present – even though more reliable ways like using "kcpuid",
which calls the CPUID instruction instead of parsing a list, should be preferred.
Scripts, that use /proc/cpuinfo to determine if the current CPU is
"compliant" with defined microarchitecture levels like x86-64-v2 will falsely
claim the CPU is incapable of modern CPU instructions when "lahf_lm" is missing
in that flags list.

This can prevent some docker containers from starting or build scripts to create
unoptimized binaries.

Admittably, this is more a small inconvenience than a severe bug in the kernel
and the shoddy scripts that rely on parsing /proc/cpuinfo
should be fixed instead.

This patch adds an additional check to see if we're running inside a
virtual machine (X86_FEATURE_HYPERVISOR is present), which, to my
understanding, can't be present on a real K8 processor as it was introduced
only with the later/other Athlon64 models.

Example output with the "lahf_lm" flag missing in the flags list
(should be shown between "hypervisor" and "abm"):

    $ cat /proc/cpuinfo
    processor       : 0
    vendor_id       : AuthenticAMD
    cpu family      : 15
    model           : 6
    model name      : Common KVM processor
    stepping        : 1
    microcode       : 0x1000065
    cpu MHz         : 2599.998
    cache size      : 512 KB
    physical id     : 0
    siblings        : 1
    core id         : 0
    cpu cores       : 1
    apicid          : 0
    initial apicid  : 0
    fpu             : yes
    fpu_exception   : yes
    cpuid level     : 13
    wp              : yes
    flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca
                      cmov pat pse36 clflush mmx fxsr sse sse2 syscall nx rdtscp
                      lm rep_good nopl cpuid extd_apicid tsc_known_freq pni
                      pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 x2apic movbe popcnt
                      tsc_deadline_timer aes xsave avx f16c hypervisor abm
                      3dnowprefetch vmmcall bmi1 avx2 bmi2 xsaveopt

... while kcpuid shows the feature to be present in the CPU:

    # kcpuid -d | grep lahf
         lahf_lm             - LAHF/SAHF available in 64-bit mode

[ mingo: Updated the comment a bit, incorporated Boris's review feedback. ]

Signed-off-by: Max Grobecker <max@grobecker.info>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: linux-kernel@vger.kernel.org
Cc: Borislav Petkov <bp@alien8.de>
---
 arch/x86/kernel/cpu/amd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 54194f5995de3..d747515ad0130 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -632,7 +632,7 @@ static void init_amd_k8(struct cpuinfo_x86 *c)
 	 * (model = 0x14) and later actually support it.
 	 * (AMD Erratum #110, docId: 25759).
 	 */
-	if (c->x86_model < 0x14 && cpu_has(c, X86_FEATURE_LAHF_LM)) {
+	if (c->x86_model < 0x14 && cpu_has(c, X86_FEATURE_LAHF_LM) && !cpu_has(c, X86_FEATURE_HYPERVISOR)) {
 		clear_cpu_cap(c, X86_FEATURE_LAHF_LM);
 		if (!rdmsrl_amd_safe(0xc001100d, &value)) {
 			value &= ~BIT_64(32);

From 3414cda9d41f41703832d0abd01063dd8de82b89 Mon Sep 17 00:00:00 2001
From: Antheas Kapenekakis <lkml@antheas.dev>
Date: Thu, 27 Feb 2025 18:51:06 +0100
Subject: [PATCH 0769/1173] ALSA: hda/realtek: Remove (revert) duplicate Ally X
 config

In commit 1e9c708dc3ae ("ALSA: hda/tas2781: Add new quirk for Lenovo,
ASUS, Dell projects") Baojun adds a bunch of projects to the file,
including for the Ally X. Turns out the initial Ally X was not sorted
properly, so the kernel had 2 quirks for it.

The previous quirk overrode the new one due to being earlier and they
are different. When AB testing, the normal pin fixup seems to work ok
but causes a bit of a minor popping. Given the other config is more
complicated and may cause undefined behavior, revert it.

Fixes: 1e9c708dc3ae ("ALSA: hda/tas2781: Add new quirk for Lenovo, ASUS, Dell projects")
Signed-off-by: Antheas Kapenekakis <lkml@antheas.dev>
Link: https://patch.msgid.link/20250227175107.33432-2-lkml@antheas.dev
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index c735f630ecb5a..f92de4a95a4c6 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -7690,7 +7690,6 @@ enum {
 	ALC285_FIXUP_THINKPAD_X1_GEN7,
 	ALC285_FIXUP_THINKPAD_HEADSET_JACK,
 	ALC294_FIXUP_ASUS_ALLY,
-	ALC294_FIXUP_ASUS_ALLY_X,
 	ALC294_FIXUP_ASUS_ALLY_PINS,
 	ALC294_FIXUP_ASUS_ALLY_VERBS,
 	ALC294_FIXUP_ASUS_ALLY_SPEAKER,
@@ -9138,12 +9137,6 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC294_FIXUP_ASUS_ALLY_PINS
 	},
-	[ALC294_FIXUP_ASUS_ALLY_X] = {
-		.type = HDA_FIXUP_FUNC,
-		.v.func = tas2781_fixup_i2c,
-		.chained = true,
-		.chain_id = ALC294_FIXUP_ASUS_ALLY_PINS
-	},
 	[ALC294_FIXUP_ASUS_ALLY_PINS] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {
@@ -10645,7 +10638,6 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1740, "ASUS UX430UA", ALC295_FIXUP_ASUS_DACS),
 	SND_PCI_QUIRK(0x1043, 0x17d1, "ASUS UX431FL", ALC294_FIXUP_ASUS_DUAL_SPK),
 	SND_PCI_QUIRK(0x1043, 0x17f3, "ROG Ally NR2301L/X", ALC294_FIXUP_ASUS_ALLY),
-	SND_PCI_QUIRK(0x1043, 0x1eb3, "ROG Ally X RC72LA", ALC294_FIXUP_ASUS_ALLY_X),
 	SND_PCI_QUIRK(0x1043, 0x1863, "ASUS UX6404VI/VV", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1881, "ASUS Zephyrus S/M", ALC294_FIXUP_ASUS_GX502_PINS),
 	SND_PCI_QUIRK(0x1043, 0x18b1, "Asus MJ401TA", ALC256_FIXUP_ASUS_HEADSET_MIC),

From 12784ca33b62fd327631749e6a0cd2a10110a56c Mon Sep 17 00:00:00 2001
From: Antheas Kapenekakis <lkml@antheas.dev>
Date: Thu, 27 Feb 2025 18:51:07 +0100
Subject: [PATCH 0770/1173] ALSA: hda/realtek: Fix Asus Z13 2025 audio

Use the basic quirk for this type of amplifier. Sound works in speakers,
headphones, and microphone. Whereas none worked before.

Tested-by: Kyle Gospodnetich <me@kylegospodneti.ch>
Signed-off-by: Antheas Kapenekakis <lkml@antheas.dev>
Link: https://patch.msgid.link/20250227175107.33432-3-lkml@antheas.dev
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index f92de4a95a4c6..926007b4a9ba7 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10692,6 +10692,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1f1f, "ASUS H7604JI/JV/J3D", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1f62, "ASUS UX7602ZM", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1f92, "ASUS ROG Flow X16", ALC289_FIXUP_ASUS_GA401),
+	SND_PCI_QUIRK(0x1043, 0x1fb3, "ASUS ROG Flow Z13 GZ302EA", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2),
 	SND_PCI_QUIRK(0x1043, 0x31d0, "ASUS Zen AIO 27 Z272SD_A272SD", ALC274_FIXUP_ASUS_ZEN_AIO_27),
 	SND_PCI_QUIRK(0x1043, 0x3a20, "ASUS G614JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),

From f479ecc5ef15ed8d774968c1a8726a49420f11a0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Daniel=20B=C3=A1rta?= <daniel.barta@trustlab.cz>
Date: Thu, 27 Feb 2025 17:12:55 +0100
Subject: [PATCH 0771/1173] ALSA: hda: Fix speakers on ASUS EXPERTBOOK P5405CSA
 1.0
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After some digging around I have found that this laptop has Cirrus's smart
aplifiers connected to SPI bus (spi1-CSC3551:00-cs35l41-hda).

To get them correctly detected and working I had to modify patch_realtek.c
with ASUS EXPERTBOOK P5405CSA 1.0 SystemID (0x1043, 0x1f63) and add
corresponding hda_quirk (ALC245_FIXUP_CS35L41_SPI_2).

Signed-off-by: Daniel Bárta <daniel.barta@trustlab.cz>
Link: https://patch.msgid.link/20250227161256.18061-2-daniel.barta@trustlab.cz
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 926007b4a9ba7..d58743b955f81 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10691,6 +10691,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1f12, "ASUS UM5302", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x1f1f, "ASUS H7604JI/JV/J3D", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1f62, "ASUS UX7602ZM", ALC245_FIXUP_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x1f63, "ASUS P5405CSA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1f92, "ASUS ROG Flow X16", ALC289_FIXUP_ASUS_GA401),
 	SND_PCI_QUIRK(0x1043, 0x1fb3, "ASUS ROG Flow Z13 GZ302EA", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2),

From f034937f5af32188cd1c07865c885b2f171e17bf Mon Sep 17 00:00:00 2001
From: Brendan Jackman <jackmanb@google.com>
Date: Fri, 20 Dec 2024 15:18:31 +0000
Subject: [PATCH 0772/1173] x86/cpu: Create helper function to parse the
 'clearcpuid=' boot parameter

This is in preparation for a later commit that will reuse this code, to
make review convenient.

Factor out a helper function which does the full handling for this arg
including printing info to the console.

No functional change intended.

Signed-off-by: Brendan Jackman <jackmanb@google.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20241220-force-cpu-bug-v2-1-7dc71bce742a@google.com
---
 arch/x86/kernel/cpu/common.c | 96 +++++++++++++++++++-----------------
 1 file changed, 52 insertions(+), 44 deletions(-)

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 76598a93a8faa..137d3e00a5be7 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1479,56 +1479,18 @@ static void detect_nopl(void)
 #endif
 }
 
-/*
- * We parse cpu parameters early because fpu__init_system() is executed
- * before parse_early_param().
- */
-static void __init cpu_parse_early_param(void)
+static inline void parse_clearcpuid(char *arg)
 {
-	char arg[128];
-	char *argptr = arg, *opt;
-	int arglen, taint = 0;
-
-#ifdef CONFIG_X86_32
-	if (cmdline_find_option_bool(boot_command_line, "no387"))
-#ifdef CONFIG_MATH_EMULATION
-		setup_clear_cpu_cap(X86_FEATURE_FPU);
-#else
-		pr_err("Option 'no387' required CONFIG_MATH_EMULATION enabled.\n");
-#endif
-
-	if (cmdline_find_option_bool(boot_command_line, "nofxsr"))
-		setup_clear_cpu_cap(X86_FEATURE_FXSR);
-#endif
-
-	if (cmdline_find_option_bool(boot_command_line, "noxsave"))
-		setup_clear_cpu_cap(X86_FEATURE_XSAVE);
-
-	if (cmdline_find_option_bool(boot_command_line, "noxsaveopt"))
-		setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
-
-	if (cmdline_find_option_bool(boot_command_line, "noxsaves"))
-		setup_clear_cpu_cap(X86_FEATURE_XSAVES);
-
-	if (cmdline_find_option_bool(boot_command_line, "nousershstk"))
-		setup_clear_cpu_cap(X86_FEATURE_USER_SHSTK);
-
-	/* Minimize the gap between FRED is available and available but disabled. */
-	arglen = cmdline_find_option(boot_command_line, "fred", arg, sizeof(arg));
-	if (arglen != 2 || strncmp(arg, "on", 2))
-		setup_clear_cpu_cap(X86_FEATURE_FRED);
-
-	arglen = cmdline_find_option(boot_command_line, "clearcpuid", arg, sizeof(arg));
-	if (arglen <= 0)
-		return;
+	char *opt;
+	int taint = 0;
 
 	pr_info("Clearing CPUID bits:");
 
-	while (argptr) {
+	while (arg) {
 		bool found __maybe_unused = false;
 		unsigned int bit;
 
-		opt = strsep(&argptr, ",");
+		opt = strsep(&arg, ",");
 
 		/*
 		 * Handle naked numbers first for feature flags which don't
@@ -1570,10 +1532,56 @@ static void __init cpu_parse_early_param(void)
 		if (!found)
 			pr_cont(" (unknown: %s)", opt);
 	}
-	pr_cont("\n");
 
 	if (taint)
 		add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK);
+
+	pr_cont("\n");
+}
+
+
+/*
+ * We parse cpu parameters early because fpu__init_system() is executed
+ * before parse_early_param().
+ */
+static void __init cpu_parse_early_param(void)
+{
+	char arg[128];
+	int arglen;
+
+#ifdef CONFIG_X86_32
+	if (cmdline_find_option_bool(boot_command_line, "no387"))
+#ifdef CONFIG_MATH_EMULATION
+		setup_clear_cpu_cap(X86_FEATURE_FPU);
+#else
+		pr_err("Option 'no387' required CONFIG_MATH_EMULATION enabled.\n");
+#endif
+
+	if (cmdline_find_option_bool(boot_command_line, "nofxsr"))
+		setup_clear_cpu_cap(X86_FEATURE_FXSR);
+#endif
+
+	if (cmdline_find_option_bool(boot_command_line, "noxsave"))
+		setup_clear_cpu_cap(X86_FEATURE_XSAVE);
+
+	if (cmdline_find_option_bool(boot_command_line, "noxsaveopt"))
+		setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
+
+	if (cmdline_find_option_bool(boot_command_line, "noxsaves"))
+		setup_clear_cpu_cap(X86_FEATURE_XSAVES);
+
+	if (cmdline_find_option_bool(boot_command_line, "nousershstk"))
+		setup_clear_cpu_cap(X86_FEATURE_USER_SHSTK);
+
+	/* Minimize the gap between FRED is available and available but disabled. */
+	arglen = cmdline_find_option(boot_command_line, "fred", arg, sizeof(arg));
+	if (arglen != 2 || strncmp(arg, "on", 2))
+		setup_clear_cpu_cap(X86_FEATURE_FRED);
+
+	arglen = cmdline_find_option(boot_command_line, "clearcpuid", arg, sizeof(arg));
+	if (arglen <= 0)
+		return;
+	parse_clearcpuid(arg);
 }
 
 /*

From 814165e9fd1f62332b5444d730b8d6e432328463 Mon Sep 17 00:00:00 2001
From: Brendan Jackman <jackmanb@google.com>
Date: Fri, 20 Dec 2024 15:18:32 +0000
Subject: [PATCH 0773/1173] x86/cpu: Add the 'setcpuid=' boot parameter

In preparation for adding support to inject fake CPU bugs at boot-time,
add a general facility to force enablement of CPU flags.

The flag taints the kernel and the documentation attempts to be clear
that this is highly unsuitable for uses outside of kernel development
and platform experimentation.

The new arg is parsed just like clearcpuid, but instead of leading to
setup_clear_cpu_cap() it leads to setup_force_cpu_cap().

I've tested this by booting a nested QEMU guest on an Intel host, which
with setcpuid=svm will claim that it supports AMD virtualization.

Signed-off-by: Brendan Jackman <jackmanb@google.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20241220-force-cpu-bug-v2-2-7dc71bce742a@google.com
---
 arch/x86/kernel/cpu/common.c | 35 ++++++++++++++++++++++++++---------
 1 file changed, 26 insertions(+), 9 deletions(-)

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 137d3e00a5be7..ff483c9a56c39 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1479,12 +1479,12 @@ static void detect_nopl(void)
 #endif
 }
 
-static inline void parse_clearcpuid(char *arg)
+static inline void parse_set_clear_cpuid(char *arg, bool set)
 {
 	char *opt;
 	int taint = 0;
 
-	pr_info("Clearing CPUID bits:");
+	pr_info("%s CPUID bits:", set ? "Force-enabling" : "Clearing");
 
 	while (arg) {
 		bool found __maybe_unused = false;
@@ -1505,7 +1505,10 @@ static inline void parse_clearcpuid(char *arg)
 				else
 					pr_cont(" " X86_CAP_FMT, x86_cap_flag(bit));
 
-				setup_clear_cpu_cap(bit);
+				if (set)
+					setup_force_cpu_cap(bit);
+				else
+					setup_clear_cpu_cap(bit);
 				taint++;
 			}
 			/*
@@ -1523,7 +1526,10 @@ static inline void parse_clearcpuid(char *arg)
 				continue;
 
 			pr_cont(" %s", opt);
-			setup_clear_cpu_cap(bit);
+			if (set)
+				setup_force_cpu_cap(bit);
+			else
+				setup_clear_cpu_cap(bit);
 			taint++;
 			found = true;
 			break;
@@ -1579,9 +1585,12 @@ static void __init cpu_parse_early_param(void)
 		setup_clear_cpu_cap(X86_FEATURE_FRED);
 
 	arglen = cmdline_find_option(boot_command_line, "clearcpuid", arg, sizeof(arg));
-	if (arglen <= 0)
-		return;
-	parse_clearcpuid(arg);
+	if (arglen > 0)
+		parse_set_clear_cpuid(arg, false);
+
+	arglen = cmdline_find_option(boot_command_line, "setcpuid", arg, sizeof(arg));
+	if (arglen > 0)
+		parse_set_clear_cpuid(arg, true);
 }
 
 /*
@@ -2013,15 +2022,23 @@ void print_cpu_info(struct cpuinfo_x86 *c)
 }
 
 /*
- * clearcpuid= was already parsed in cpu_parse_early_param().  This dummy
- * function prevents it from becoming an environment variable for init.
+ * clearcpuid= and setcpuid= were already parsed in cpu_parse_early_param().
+ * These dummy functions prevent them from becoming an environment variable for
+ * init.
  */
+
 static __init int setup_clearcpuid(char *arg)
 {
 	return 1;
 }
 __setup("clearcpuid=", setup_clearcpuid);
 
+static __init int setup_setcpuid(char *arg)
+{
+	return 1;
+}
+__setup("setcpuid=", setup_setcpuid);
+
 DEFINE_PER_CPU_ALIGNED(struct pcpu_hot, pcpu_hot) = {
 	.current_task	= &init_task,
 	.preempt_count	= INIT_PREEMPT_COUNT,

From ab68d2e36532806b8f86ff2f60861dbb8443f0be Mon Sep 17 00:00:00 2001
From: Brendan Jackman <jackmanb@google.com>
Date: Fri, 20 Dec 2024 15:18:33 +0000
Subject: [PATCH 0774/1173] x86/cpu: Enable modifying CPU bug flags with
 '{clear,set}puid='

Sometimes it can be very useful to run CPU vulnerability mitigations on
systems where they aren't known to mitigate any real-world
vulnerabilities. This can be handy for mundane reasons like debugging
HW-agnostic logic on whatever machine is to hand, but also for research
reasons: while some mitigations are focused on individual vulns and
uarches, others are fairly general, and it's strategically useful to
have an idea how they'd perform on systems where they aren't currently
needed.

As evidence for this being useful, a flag specifically for Retbleed was
added in:

  5c9a92dec323 ("x86/bugs: Add retbleed=force").

Since CPU bugs are tracked using the same basic mechanism as features,
and there are already parameters for manipulating them by hand, extend
that mechanism to support bug as well as capabilities.

With this patch and setcpuid=srso, a QEMU guest running on an Intel host
will boot with Safe-RET enabled.

Signed-off-by: Brendan Jackman <jackmanb@google.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20241220-force-cpu-bug-v2-3-7dc71bce742a@google.com
---
 arch/x86/include/asm/cpufeature.h |  1 +
 arch/x86/kernel/cpu/common.c      | 16 ++++++++++++----
 2 files changed, 13 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index de1ad09fe8d72..e5fc0038c8f65 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -50,6 +50,7 @@ extern const char * const x86_power_flags[32];
  * X86_BUG_<name> - NCAPINTS*32.
  */
 extern const char * const x86_bug_flags[NBUGINTS*32];
+#define x86_bug_flag(flag) x86_bug_flags[flag]
 
 #define test_cpu_cap(c, bit)						\
 	 arch_test_bit(bit, (unsigned long *)((c)->x86_capability))
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index ff483c9a56c39..0f32b6ffbf04f 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1494,7 +1494,8 @@ static inline void parse_set_clear_cpuid(char *arg, bool set)
 
 		/*
 		 * Handle naked numbers first for feature flags which don't
-		 * have names.
+		 * have names. It doesn't make sense for a bug not to have a
+		 * name so don't handle bug flags here.
 		 */
 		if (!kstrtouint(opt, 10, &bit)) {
 			if (bit < NCAPINTS * 32) {
@@ -1518,11 +1519,18 @@ static inline void parse_set_clear_cpuid(char *arg, bool set)
 			continue;
 		}
 
-		for (bit = 0; bit < 32 * NCAPINTS; bit++) {
-			if (!x86_cap_flag(bit))
+		for (bit = 0; bit < 32 * (NCAPINTS + NBUGINTS); bit++) {
+			const char *flag;
+
+			if (bit < 32 * NCAPINTS)
+				flag = x86_cap_flag(bit);
+			else
+				flag = x86_bug_flag(bit - (32 * NCAPINTS));
+
+			if (!flag)
 				continue;
 
-			if (strcmp(x86_cap_flag(bit), opt))
+			if (strcmp(flag, opt))
 				continue;
 
 			pr_cont(" %s", opt);

From 909639aa58fe4789644104c1fd89264c57da0979 Mon Sep 17 00:00:00 2001
From: "H. Peter Anvin (Intel)" <hpa@zytor.com>
Date: Fri, 28 Feb 2025 00:23:34 -0800
Subject: [PATCH 0775/1173] x86/cpufeatures: Rename X86_CMPXCHG64 to X86_CX8

Replace X86_CMPXCHG64 with X86_CX8, as CX8 is the name of the CPUID
flag, thus to make it consistent with X86_FEATURE_CX8 defined in
<asm/cpufeatures.h>.

No functional change intended.

Signed-off-by: H. Peter Anvin (Intel) <hpa@zytor.com>
Signed-off-by: Xin Li (Intel) <xin@zytor.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250228082338.73859-2-xin@zytor.com
---
 arch/x86/Kconfig                               | 2 +-
 arch/x86/Kconfig.cpu                           | 4 ++--
 arch/x86/include/asm/asm-prototypes.h          | 2 +-
 arch/x86/include/asm/atomic64_32.h             | 2 +-
 arch/x86/include/asm/cmpxchg_32.h              | 2 +-
 arch/x86/include/asm/required-features.h       | 2 +-
 arch/x86/lib/Makefile                          | 2 +-
 arch/x86/lib/cmpxchg8b_emu.S                   | 2 +-
 lib/atomic64_test.c                            | 2 +-
 tools/arch/x86/include/asm/required-features.h | 2 +-
 10 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index aa90f0355be11..017035f461cf2 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -133,7 +133,7 @@ config X86
 	select ARCH_SUPPORTS_AUTOFDO_CLANG
 	select ARCH_SUPPORTS_PROPELLER_CLANG    if X86_64
 	select ARCH_USE_BUILTIN_BSWAP
-	select ARCH_USE_CMPXCHG_LOCKREF		if X86_CMPXCHG64
+	select ARCH_USE_CMPXCHG_LOCKREF		if X86_CX8
 	select ARCH_USE_MEMTEST
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_USE_QUEUED_SPINLOCKS
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 8fcb8ccee44b2..f8b3296fe2e1d 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -299,7 +299,7 @@ config X86_HAVE_PAE
 	def_bool y
 	depends on MCRUSOE || MEFFICEON || MCYRIXIII || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC7 || MATOM || X86_64
 
-config X86_CMPXCHG64
+config X86_CX8
 	def_bool y
 	depends on X86_HAVE_PAE || M586TSC || M586MMX || MK6 || MK7 || MGEODEGX1 || MGEODE_LX
 
@@ -313,7 +313,7 @@ config X86_MINIMUM_CPU_FAMILY
 	int
 	default "64" if X86_64
 	default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MK7)
-	default "5" if X86_32 && X86_CMPXCHG64
+	default "5" if X86_32 && X86_CX8
 	default "4"
 
 config X86_DEBUGCTLMSR
diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h
index 3674006e39744..8d9e62725202e 100644
--- a/arch/x86/include/asm/asm-prototypes.h
+++ b/arch/x86/include/asm/asm-prototypes.h
@@ -16,7 +16,7 @@
 #include <asm/gsseg.h>
 #include <asm/nospec-branch.h>
 
-#ifndef CONFIG_X86_CMPXCHG64
+#ifndef CONFIG_X86_CX8
 extern void cmpxchg8b_emu(void);
 #endif
 
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index 6c6e9b9f98a45..797085ecaaa45 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -48,7 +48,7 @@ static __always_inline s64 arch_atomic64_read_nonatomic(const atomic64_t *v)
 	ATOMIC64_EXPORT(atomic64_##sym)
 #endif
 
-#ifdef CONFIG_X86_CMPXCHG64
+#ifdef CONFIG_X86_CX8
 #define __alternative_atomic64(f, g, out, in...) \
 	asm volatile("call %c[func]" \
 		     : ALT_OUTPUT_SP(out) \
diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h
index fd1282a783ddb..c38d4ed94cb34 100644
--- a/arch/x86/include/asm/cmpxchg_32.h
+++ b/arch/x86/include/asm/cmpxchg_32.h
@@ -69,7 +69,7 @@ static __always_inline bool __try_cmpxchg64_local(volatile u64 *ptr, u64 *oldp,
 	return __arch_try_cmpxchg64(ptr, oldp, new,);
 }
 
-#ifdef CONFIG_X86_CMPXCHG64
+#ifdef CONFIG_X86_CX8
 
 #define arch_cmpxchg64 __cmpxchg64
 
diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
index e9187ddd3d1fd..0068133cb622f 100644
--- a/arch/x86/include/asm/required-features.h
+++ b/arch/x86/include/asm/required-features.h
@@ -23,7 +23,7 @@
 # define NEED_PAE	0
 #endif
 
-#ifdef CONFIG_X86_CMPXCHG64
+#ifdef CONFIG_X86_CX8
 # define NEED_CX8	(1<<(X86_FEATURE_CX8 & 31))
 #else
 # define NEED_CX8	0
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 8a59c61624c2f..9bbe2819881fb 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -56,7 +56,7 @@ ifeq ($(CONFIG_X86_32),y)
         lib-y += string_32.o
         lib-y += memmove_32.o
         lib-y += cmpxchg8b_emu.o
-ifneq ($(CONFIG_X86_CMPXCHG64),y)
+ifneq ($(CONFIG_X86_CX8),y)
         lib-y += atomic64_386_32.o
 endif
 else
diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S
index 1c96be769adc3..d4bb24347ff81 100644
--- a/arch/x86/lib/cmpxchg8b_emu.S
+++ b/arch/x86/lib/cmpxchg8b_emu.S
@@ -7,7 +7,7 @@
 
 .text
 
-#ifndef CONFIG_X86_CMPXCHG64
+#ifndef CONFIG_X86_CX8
 
 /*
  * Emulate 'cmpxchg8b (%esi)' on UP
diff --git a/lib/atomic64_test.c b/lib/atomic64_test.c
index 759ea1783cc59..d726068358c7d 100644
--- a/lib/atomic64_test.c
+++ b/lib/atomic64_test.c
@@ -254,7 +254,7 @@ static __init int test_atomics_init(void)
 	pr_info("passed for %s platform %s CX8 and %s SSE\n",
 #ifdef CONFIG_X86_64
 		"x86-64",
-#elif defined(CONFIG_X86_CMPXCHG64)
+#elif defined(CONFIG_X86_CX8)
 		"i586+",
 #else
 		"i386+",
diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h
index e9187ddd3d1fd..0068133cb622f 100644
--- a/tools/arch/x86/include/asm/required-features.h
+++ b/tools/arch/x86/include/asm/required-features.h
@@ -23,7 +23,7 @@
 # define NEED_PAE	0
 #endif
 
-#ifdef CONFIG_X86_CMPXCHG64
+#ifdef CONFIG_X86_CX8
 # define NEED_CX8	(1<<(X86_FEATURE_CX8 & 31))
 #else
 # define NEED_CX8	0

From c5b0320bbf79548fbf058a3925a07c8f281beeab Mon Sep 17 00:00:00 2001
From: Alejandro Jimenez <alejandro.j.jimenez@oracle.com>
Date: Mon, 6 Jan 2025 19:14:13 +0000
Subject: [PATCH 0776/1173] iommu/amd: Preserve default DTE fields when
 updating Host Page Table Root

When updating the page table root field on the DTE, avoid overwriting any
bits that are already set. The earlier call to make_clear_dte() writes
default values that all DTEs must have set (currently DTE[V]), and those
must be preserved.

Currently this doesn't cause problems since the page table root update is
the first field that is set after make_clear_dte() is called, and
DTE_FLAG_V is set again later along with the permission bits (IR/IW).
Remove this redundant assignment too.

Fixes: fd5dff9de4be ("iommu/amd: Modify set_dte_entry() to use 256-bit DTE helpers")
Signed-off-by: Alejandro Jimenez <alejandro.j.jimenez@oracle.com>
Reviewed-by: Dheeraj Kumar Srivastava <dheerajkumar.srivastava@amd.com>
Reviewed-by: Vasant Hegde <vasant.hegde@amd.com>
Link: https://lore.kernel.org/r/20250106191413.3107140-1-alejandro.j.jimenez@oracle.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/amd/iommu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index b48a72bd7b23d..cd5116d8c3b28 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -2043,12 +2043,12 @@ static void set_dte_entry(struct amd_iommu *iommu,
 	make_clear_dte(dev_data, dte, &new);
 
 	if (domain->iop.mode != PAGE_MODE_NONE)
-		new.data[0] = iommu_virt_to_phys(domain->iop.root);
+		new.data[0] |= iommu_virt_to_phys(domain->iop.root);
 
 	new.data[0] |= (domain->iop.mode & DEV_ENTRY_MODE_MASK)
 		    << DEV_ENTRY_MODE_SHIFT;
 
-	new.data[0] |= DTE_FLAG_IR | DTE_FLAG_IW | DTE_FLAG_V;
+	new.data[0] |= DTE_FLAG_IR | DTE_FLAG_IW;
 
 	/*
 	 * When SNP is enabled, we can only support TV=1 with non-zero domain ID.

From 64f792981e35e191eb619f6f2fefab76cc7d6112 Mon Sep 17 00:00:00 2001
From: Jerry Snitselaar <jsnitsel@redhat.com>
Date: Fri, 28 Feb 2025 18:27:25 +0800
Subject: [PATCH 0777/1173] iommu/vt-d: Remove device comparison in
 context_setup_pass_through_cb

Remove the device comparison check in context_setup_pass_through_cb.
pci_for_each_dma_alias already makes a decision on whether the
callback function should be called for a device. With the check
in place it will fail to create context entries for aliases as
it walks up to the root bus.

Fixes: 2031c469f816 ("iommu/vt-d: Add support for static identity domain")
Closes: https://lore.kernel.org/linux-iommu/82499eb6-00b7-4f83-879a-e97b4144f576@linux.intel.com/
Cc: stable@vger.kernel.org
Signed-off-by: Jerry Snitselaar <jsnitsel@redhat.com>
Link: https://lore.kernel.org/r/20250224180316.140123-1-jsnitsel@redhat.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/intel/iommu.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index cc46098f875b1..4d8d4593c9c81 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -4378,9 +4378,6 @@ static int context_setup_pass_through_cb(struct pci_dev *pdev, u16 alias, void *
 {
 	struct device *dev = data;
 
-	if (dev != &pdev->dev)
-		return 0;
-
 	return context_setup_pass_through(dev, PCI_BUS_NUM(alias), alias & 0xff);
 }
 

From b150654f74bf0df8e6a7936d5ec51400d9ec06d8 Mon Sep 17 00:00:00 2001
From: Lu Baolu <baolu.lu@linux.intel.com>
Date: Fri, 28 Feb 2025 18:27:26 +0800
Subject: [PATCH 0778/1173] iommu/vt-d: Fix suspicious RCU usage

Commit <d74169ceb0d2> ("iommu/vt-d: Allocate DMAR fault interrupts
locally") moved the call to enable_drhd_fault_handling() to a code
path that does not hold any lock while traversing the drhd list. Fix
it by ensuring the dmar_global_lock lock is held when traversing the
drhd list.

Without this fix, the following warning is triggered:
 =============================
 WARNING: suspicious RCU usage
 6.14.0-rc3 #55 Not tainted
 -----------------------------
 drivers/iommu/intel/dmar.c:2046 RCU-list traversed in non-reader section!!
               other info that might help us debug this:
               rcu_scheduler_active = 1, debug_locks = 1
 2 locks held by cpuhp/1/23:
 #0: ffffffff84a67c50 (cpu_hotplug_lock){++++}-{0:0}, at: cpuhp_thread_fun+0x87/0x2c0
 #1: ffffffff84a6a380 (cpuhp_state-up){+.+.}-{0:0}, at: cpuhp_thread_fun+0x87/0x2c0
 stack backtrace:
 CPU: 1 UID: 0 PID: 23 Comm: cpuhp/1 Not tainted 6.14.0-rc3 #55
 Call Trace:
  <TASK>
  dump_stack_lvl+0xb7/0xd0
  lockdep_rcu_suspicious+0x159/0x1f0
  ? __pfx_enable_drhd_fault_handling+0x10/0x10
  enable_drhd_fault_handling+0x151/0x180
  cpuhp_invoke_callback+0x1df/0x990
  cpuhp_thread_fun+0x1ea/0x2c0
  smpboot_thread_fn+0x1f5/0x2e0
  ? __pfx_smpboot_thread_fn+0x10/0x10
  kthread+0x12a/0x2d0
  ? __pfx_kthread+0x10/0x10
  ret_from_fork+0x4a/0x60
  ? __pfx_kthread+0x10/0x10
  ret_from_fork_asm+0x1a/0x30
  </TASK>

Holding the lock in enable_drhd_fault_handling() triggers a lockdep splat
about a possible deadlock between dmar_global_lock and cpu_hotplug_lock.
This is avoided by not holding dmar_global_lock when calling
iommu_device_register(), which initiates the device probe process.

Fixes: d74169ceb0d2 ("iommu/vt-d: Allocate DMAR fault interrupts locally")
Reported-and-tested-by: Ido Schimmel <idosch@nvidia.com>
Closes: https://lore.kernel.org/linux-iommu/Zx9OwdLIc_VoQ0-a@shredder.mtl.com/
Tested-by: Breno Leitao <leitao@debian.org>
Cc: stable@vger.kernel.org
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20250218022422.2315082-1-baolu.lu@linux.intel.com
Tested-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/intel/dmar.c  | 1 +
 drivers/iommu/intel/iommu.c | 7 +++++++
 2 files changed, 8 insertions(+)

diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
index 9f424acf474e9..e540092d664d2 100644
--- a/drivers/iommu/intel/dmar.c
+++ b/drivers/iommu/intel/dmar.c
@@ -2043,6 +2043,7 @@ int enable_drhd_fault_handling(unsigned int cpu)
 	/*
 	 * Enable fault control interrupt.
 	 */
+	guard(rwsem_read)(&dmar_global_lock);
 	for_each_iommu(iommu, drhd) {
 		u32 fault_status;
 		int ret;
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 4d8d4593c9c81..bf1f0c8143483 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -3146,7 +3146,14 @@ int __init intel_iommu_init(void)
 		iommu_device_sysfs_add(&iommu->iommu, NULL,
 				       intel_iommu_groups,
 				       "%s", iommu->name);
+		/*
+		 * The iommu device probe is protected by the iommu_probe_device_lock.
+		 * Release the dmar_global_lock before entering the device probe path
+		 * to avoid unnecessary lock order splat.
+		 */
+		up_read(&dmar_global_lock);
 		iommu_device_register(&iommu->iommu, &intel_iommu_ops, NULL);
+		down_read(&dmar_global_lock);
 
 		iommu_pmu_register(iommu);
 	}

From 98c7a713db91c5a9a7ffc47cd85e7158e0963cb8 Mon Sep 17 00:00:00 2001
From: David Kaplan <david.kaplan@amd.com>
Date: Wed, 8 Jan 2025 14:24:41 -0600
Subject: [PATCH 0779/1173] x86/bugs: Add X86_BUG_SPECTRE_V2_USER

All CPU vulnerabilities with command line options map to a single X86_BUG bit
except for Spectre V2 where both the spectre_v2 and spectre_v2_user command
line options are related to the same bug.

The spectre_v2 command line options mostly relate to user->kernel and
guest->host mitigations, while the spectre_v2_user command line options relate
to user->user or guest->guest protections.

Define a new X86_BUG bit for spectre_v2_user so each *_select_mitigation()
function in bugs.c is related to a unique X86_BUG bit.

No functional changes.

Signed-off-by: David Kaplan <david.kaplan@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20250108202515.385902-2-david.kaplan@amd.com
---
 arch/x86/include/asm/cpufeatures.h | 1 +
 arch/x86/kernel/cpu/common.c       | 4 +++-
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index c8701abb77524..0bc420319ee24 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -537,4 +537,5 @@
 #define X86_BUG_RFDS			X86_BUG(1*32 + 2) /* "rfds" CPU is vulnerable to Register File Data Sampling */
 #define X86_BUG_BHI			X86_BUG(1*32 + 3) /* "bhi" CPU is affected by Branch History Injection */
 #define X86_BUG_IBPB_NO_RET	   	X86_BUG(1*32 + 4) /* "ibpb_no_ret" IBPB omits return target predictions */
+#define X86_BUG_SPECTRE_V2_USER		X86_BUG(1*32 + 5) /* "spectre_v2_user" CPU is affected by Spectre variant 2 attack between user processes */
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 7cce91b19fb2c..1e80d76dc9c1d 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1331,8 +1331,10 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 
 	setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
 
-	if (!cpu_matches(cpu_vuln_whitelist, NO_SPECTRE_V2))
+	if (!cpu_matches(cpu_vuln_whitelist, NO_SPECTRE_V2)) {
 		setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
+		setup_force_cpu_bug(X86_BUG_SPECTRE_V2_USER);
+	}
 
 	if (!cpu_matches(cpu_vuln_whitelist, NO_SSB) &&
 	    !(x86_arch_cap_msr & ARCH_CAP_SSB_NO) &&

From 2c93762ec4b3ab66980ee7aaffde1e050bfbf291 Mon Sep 17 00:00:00 2001
From: David Kaplan <david.kaplan@amd.com>
Date: Wed, 8 Jan 2025 14:24:42 -0600
Subject: [PATCH 0780/1173] x86/bugs: Relocate mds/taa/mmio/rfds defines

Move the mds, taa, mmio, and rfds mitigation enums earlier in the file to
prepare for restructuring of these mitigations as they are all inter-related.

No functional change.

Signed-off-by: David Kaplan <david.kaplan@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20250108202515.385902-3-david.kaplan@amd.com
---
 arch/x86/kernel/cpu/bugs.c | 60 ++++++++++++++++++++------------------
 1 file changed, 31 insertions(+), 29 deletions(-)

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 5397d0afac089..4269ed1103083 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -247,6 +247,37 @@ static const char * const mds_strings[] = {
 	[MDS_MITIGATION_VMWERV]	= "Vulnerable: Clear CPU buffers attempted, no microcode",
 };
 
+enum taa_mitigations {
+	TAA_MITIGATION_OFF,
+	TAA_MITIGATION_UCODE_NEEDED,
+	TAA_MITIGATION_VERW,
+	TAA_MITIGATION_TSX_DISABLED,
+};
+
+/* Default mitigation for TAA-affected CPUs */
+static enum taa_mitigations taa_mitigation __ro_after_init =
+	IS_ENABLED(CONFIG_MITIGATION_TAA) ? TAA_MITIGATION_VERW : TAA_MITIGATION_OFF;
+
+enum mmio_mitigations {
+	MMIO_MITIGATION_OFF,
+	MMIO_MITIGATION_UCODE_NEEDED,
+	MMIO_MITIGATION_VERW,
+};
+
+/* Default mitigation for Processor MMIO Stale Data vulnerabilities */
+static enum mmio_mitigations mmio_mitigation __ro_after_init =
+	IS_ENABLED(CONFIG_MITIGATION_MMIO_STALE_DATA) ? MMIO_MITIGATION_VERW : MMIO_MITIGATION_OFF;
+
+enum rfds_mitigations {
+	RFDS_MITIGATION_OFF,
+	RFDS_MITIGATION_VERW,
+	RFDS_MITIGATION_UCODE_NEEDED,
+};
+
+/* Default mitigation for Register File Data Sampling */
+static enum rfds_mitigations rfds_mitigation __ro_after_init =
+	IS_ENABLED(CONFIG_MITIGATION_RFDS) ? RFDS_MITIGATION_VERW : RFDS_MITIGATION_OFF;
+
 static void __init mds_select_mitigation(void)
 {
 	if (!boot_cpu_has_bug(X86_BUG_MDS) || cpu_mitigations_off()) {
@@ -290,16 +321,6 @@ early_param("mds", mds_cmdline);
 #undef pr_fmt
 #define pr_fmt(fmt)	"TAA: " fmt
 
-enum taa_mitigations {
-	TAA_MITIGATION_OFF,
-	TAA_MITIGATION_UCODE_NEEDED,
-	TAA_MITIGATION_VERW,
-	TAA_MITIGATION_TSX_DISABLED,
-};
-
-/* Default mitigation for TAA-affected CPUs */
-static enum taa_mitigations taa_mitigation __ro_after_init =
-	IS_ENABLED(CONFIG_MITIGATION_TAA) ? TAA_MITIGATION_VERW : TAA_MITIGATION_OFF;
 static bool taa_nosmt __ro_after_init;
 
 static const char * const taa_strings[] = {
@@ -390,15 +411,6 @@ early_param("tsx_async_abort", tsx_async_abort_parse_cmdline);
 #undef pr_fmt
 #define pr_fmt(fmt)	"MMIO Stale Data: " fmt
 
-enum mmio_mitigations {
-	MMIO_MITIGATION_OFF,
-	MMIO_MITIGATION_UCODE_NEEDED,
-	MMIO_MITIGATION_VERW,
-};
-
-/* Default mitigation for Processor MMIO Stale Data vulnerabilities */
-static enum mmio_mitigations mmio_mitigation __ro_after_init =
-	IS_ENABLED(CONFIG_MITIGATION_MMIO_STALE_DATA) ? MMIO_MITIGATION_VERW : MMIO_MITIGATION_OFF;
 static bool mmio_nosmt __ro_after_init = false;
 
 static const char * const mmio_strings[] = {
@@ -487,16 +499,6 @@ early_param("mmio_stale_data", mmio_stale_data_parse_cmdline);
 #undef pr_fmt
 #define pr_fmt(fmt)	"Register File Data Sampling: " fmt
 
-enum rfds_mitigations {
-	RFDS_MITIGATION_OFF,
-	RFDS_MITIGATION_VERW,
-	RFDS_MITIGATION_UCODE_NEEDED,
-};
-
-/* Default mitigation for Register File Data Sampling */
-static enum rfds_mitigations rfds_mitigation __ro_after_init =
-	IS_ENABLED(CONFIG_MITIGATION_RFDS) ? RFDS_MITIGATION_VERW : RFDS_MITIGATION_OFF;
-
 static const char * const rfds_strings[] = {
 	[RFDS_MITIGATION_OFF]			= "Vulnerable",
 	[RFDS_MITIGATION_VERW]			= "Mitigation: Clear Register File",

From b8ce25df2999ac6a135ce1bd14b7243030a1338a Mon Sep 17 00:00:00 2001
From: David Kaplan <david.kaplan@amd.com>
Date: Wed, 8 Jan 2025 14:24:43 -0600
Subject: [PATCH 0781/1173] x86/bugs: Add AUTO mitigations for
 mds/taa/mmio/rfds

Add AUTO mitigations for mds/taa/mmio/rfds to create consistent vulnerability
handling.  These AUTO mitigations will be turned into the appropriate default
mitigations in the <vuln>_select_mitigation() functions.  Later, these will be
used with the new attack vector controls to help select appropriate
mitigations.

Signed-off-by: David Kaplan <david.kaplan@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20250108202515.385902-4-david.kaplan@amd.com
---
 arch/x86/include/asm/processor.h |  1 +
 arch/x86/kernel/cpu/bugs.c       | 20 ++++++++++++++++----
 2 files changed, 17 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index c0cd10182e90c..90278d0c071b0 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -757,6 +757,7 @@ extern enum l1tf_mitigations l1tf_mitigation;
 
 enum mds_mitigations {
 	MDS_MITIGATION_OFF,
+	MDS_MITIGATION_AUTO,
 	MDS_MITIGATION_FULL,
 	MDS_MITIGATION_VMWERV,
 };
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 4269ed1103083..93c437f44c245 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -238,7 +238,7 @@ static void x86_amd_ssb_disable(void)
 
 /* Default mitigation for MDS-affected CPUs */
 static enum mds_mitigations mds_mitigation __ro_after_init =
-	IS_ENABLED(CONFIG_MITIGATION_MDS) ? MDS_MITIGATION_FULL : MDS_MITIGATION_OFF;
+	IS_ENABLED(CONFIG_MITIGATION_MDS) ? MDS_MITIGATION_AUTO : MDS_MITIGATION_OFF;
 static bool mds_nosmt __ro_after_init = false;
 
 static const char * const mds_strings[] = {
@@ -249,6 +249,7 @@ static const char * const mds_strings[] = {
 
 enum taa_mitigations {
 	TAA_MITIGATION_OFF,
+	TAA_MITIGATION_AUTO,
 	TAA_MITIGATION_UCODE_NEEDED,
 	TAA_MITIGATION_VERW,
 	TAA_MITIGATION_TSX_DISABLED,
@@ -256,27 +257,29 @@ enum taa_mitigations {
 
 /* Default mitigation for TAA-affected CPUs */
 static enum taa_mitigations taa_mitigation __ro_after_init =
-	IS_ENABLED(CONFIG_MITIGATION_TAA) ? TAA_MITIGATION_VERW : TAA_MITIGATION_OFF;
+	IS_ENABLED(CONFIG_MITIGATION_TAA) ? TAA_MITIGATION_AUTO : TAA_MITIGATION_OFF;
 
 enum mmio_mitigations {
 	MMIO_MITIGATION_OFF,
+	MMIO_MITIGATION_AUTO,
 	MMIO_MITIGATION_UCODE_NEEDED,
 	MMIO_MITIGATION_VERW,
 };
 
 /* Default mitigation for Processor MMIO Stale Data vulnerabilities */
 static enum mmio_mitigations mmio_mitigation __ro_after_init =
-	IS_ENABLED(CONFIG_MITIGATION_MMIO_STALE_DATA) ? MMIO_MITIGATION_VERW : MMIO_MITIGATION_OFF;
+	IS_ENABLED(CONFIG_MITIGATION_MMIO_STALE_DATA) ?	MMIO_MITIGATION_AUTO : MMIO_MITIGATION_OFF;
 
 enum rfds_mitigations {
 	RFDS_MITIGATION_OFF,
+	RFDS_MITIGATION_AUTO,
 	RFDS_MITIGATION_VERW,
 	RFDS_MITIGATION_UCODE_NEEDED,
 };
 
 /* Default mitigation for Register File Data Sampling */
 static enum rfds_mitigations rfds_mitigation __ro_after_init =
-	IS_ENABLED(CONFIG_MITIGATION_RFDS) ? RFDS_MITIGATION_VERW : RFDS_MITIGATION_OFF;
+	IS_ENABLED(CONFIG_MITIGATION_RFDS) ? RFDS_MITIGATION_AUTO : RFDS_MITIGATION_OFF;
 
 static void __init mds_select_mitigation(void)
 {
@@ -285,6 +288,9 @@ static void __init mds_select_mitigation(void)
 		return;
 	}
 
+	if (mds_mitigation == MDS_MITIGATION_AUTO)
+		mds_mitigation = MDS_MITIGATION_FULL;
+
 	if (mds_mitigation == MDS_MITIGATION_FULL) {
 		if (!boot_cpu_has(X86_FEATURE_MD_CLEAR))
 			mds_mitigation = MDS_MITIGATION_VMWERV;
@@ -514,6 +520,9 @@ static void __init rfds_select_mitigation(void)
 	if (rfds_mitigation == RFDS_MITIGATION_OFF)
 		return;
 
+	if (rfds_mitigation == RFDS_MITIGATION_AUTO)
+		rfds_mitigation = RFDS_MITIGATION_VERW;
+
 	if (x86_arch_cap_msr & ARCH_CAP_RFDS_CLEAR)
 		setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
 	else
@@ -1979,6 +1988,7 @@ void cpu_bugs_smt_update(void)
 
 	switch (mds_mitigation) {
 	case MDS_MITIGATION_FULL:
+	case MDS_MITIGATION_AUTO:
 	case MDS_MITIGATION_VMWERV:
 		if (sched_smt_active() && !boot_cpu_has(X86_BUG_MSBDS_ONLY))
 			pr_warn_once(MDS_MSG_SMT);
@@ -1990,6 +2000,7 @@ void cpu_bugs_smt_update(void)
 
 	switch (taa_mitigation) {
 	case TAA_MITIGATION_VERW:
+	case TAA_MITIGATION_AUTO:
 	case TAA_MITIGATION_UCODE_NEEDED:
 		if (sched_smt_active())
 			pr_warn_once(TAA_MSG_SMT);
@@ -2001,6 +2012,7 @@ void cpu_bugs_smt_update(void)
 
 	switch (mmio_mitigation) {
 	case MMIO_MITIGATION_VERW:
+	case MMIO_MITIGATION_AUTO:
 	case MMIO_MITIGATION_UCODE_NEEDED:
 		if (sched_smt_active())
 			pr_warn_once(MMIO_MSG_SMT);

From b654f7a51ffb386131de42aa98ed831f8c126546 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Fri, 28 Feb 2025 21:26:56 +0800
Subject: [PATCH 0782/1173] block: fix 'kmem_cache of name 'bio-108' already
 exists'

Device mapper bioset often has big bio_slab size, which can be more than
1000, then 8byte can't hold the slab name any more, cause the kmem_cache
allocation warning of 'kmem_cache of name 'bio-108' already exists'.

Fix the warning by extending bio_slab->name to 12 bytes, but fix output
of /proc/slabinfo

Reported-by: Guangwu Zhang <guazhang@redhat.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250228132656.2838008-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/block/bio.c b/block/bio.c
index f0c416e5931d9..6ac5983ba51e6 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -77,7 +77,7 @@ struct bio_slab {
 	struct kmem_cache *slab;
 	unsigned int slab_ref;
 	unsigned int slab_size;
-	char name[8];
+	char name[12];
 };
 static DEFINE_MUTEX(bio_slab_lock);
 static DEFINE_XARRAY(bio_slabs);

From 64407f4b5807dc9dec8135e1bfd45d2cb11b4ea0 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Fri, 28 Feb 2025 16:03:47 +0300
Subject: [PATCH 0783/1173] gpiolib: Fix Oops in
 gpiod_direction_input_nonotify()

The gpiod_direction_input_nonotify() function is supposed to return zero
if the direction for the pin is input.  But instead it accidentally
returns GPIO_LINE_DIRECTION_IN (1) which will be cast into an ERR_PTR()
in gpiochip_request_own_desc().  The callers dereference it and it leads
to a crash.

I changed gpiod_direction_output_raw_commit() just for consistency but
returning GPIO_LINE_DIRECTION_OUT (0) is fine.

Cc: stable@vger.kernel.org
Fixes: 9d846b1aebbe ("gpiolib: check the return value of gpio_chip::get_direction()")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/254f3925-3015-4c9d-aac5-bb9b4b2cd2c5@stanley.mountain
[Bartosz: moved the variable declarations to the top of the functions]
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpiolib.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index fc19df5a64c2b..8741600af7efb 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -2712,7 +2712,7 @@ EXPORT_SYMBOL_GPL(gpiod_direction_input);
 
 int gpiod_direction_input_nonotify(struct gpio_desc *desc)
 {
-	int ret = 0;
+	int ret = 0, dir;
 
 	CLASS(gpio_chip_guard, guard)(desc);
 	if (!guard.gc)
@@ -2740,12 +2740,12 @@ int gpiod_direction_input_nonotify(struct gpio_desc *desc)
 		ret = guard.gc->direction_input(guard.gc,
 						gpio_chip_hwgpio(desc));
 	} else if (guard.gc->get_direction) {
-		ret = guard.gc->get_direction(guard.gc,
+		dir = guard.gc->get_direction(guard.gc,
 					      gpio_chip_hwgpio(desc));
-		if (ret < 0)
-			return ret;
+		if (dir < 0)
+			return dir;
 
-		if (ret != GPIO_LINE_DIRECTION_IN) {
+		if (dir != GPIO_LINE_DIRECTION_IN) {
 			gpiod_warn(desc,
 				   "%s: missing direction_input() operation and line is output\n",
 				    __func__);
@@ -2764,7 +2764,7 @@ int gpiod_direction_input_nonotify(struct gpio_desc *desc)
 
 static int gpiod_direction_output_raw_commit(struct gpio_desc *desc, int value)
 {
-	int val = !!value, ret = 0;
+	int val = !!value, ret = 0, dir;
 
 	CLASS(gpio_chip_guard, guard)(desc);
 	if (!guard.gc)
@@ -2788,12 +2788,12 @@ static int gpiod_direction_output_raw_commit(struct gpio_desc *desc, int value)
 	} else {
 		/* Check that we are in output mode if we can */
 		if (guard.gc->get_direction) {
-			ret = guard.gc->get_direction(guard.gc,
+			dir = guard.gc->get_direction(guard.gc,
 						      gpio_chip_hwgpio(desc));
-			if (ret < 0)
-				return ret;
+			if (dir < 0)
+				return dir;
 
-			if (ret != GPIO_LINE_DIRECTION_OUT) {
+			if (dir != GPIO_LINE_DIRECTION_OUT) {
 				gpiod_warn(desc,
 					   "%s: missing direction_output() operation\n",
 					   __func__);

From 693bbf2a50447353c6a47961e6a7240a823ace02 Mon Sep 17 00:00:00 2001
From: Kevin Brodsky <kevin.brodsky@arm.com>
Date: Thu, 12 Dec 2024 08:09:03 +0000
Subject: [PATCH 0784/1173] x86/mm: Remove unused __set_memory_prot()

__set_memory_prot() is unused since:

  5c11f00b09c1 ("x86: remove memory hotplug support on X86_32")

Let's remove it.

Signed-off-by: Kevin Brodsky <kevin.brodsky@arm.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: David Hildenbrand <david@redhat.com>
Link: https://lore.kernel.org/r/20241212080904.2089632-2-kevin.brodsky@arm.com
---
 arch/x86/include/asm/set_memory.h |  1 -
 arch/x86/mm/pat/set_memory.c      | 13 -------------
 2 files changed, 14 deletions(-)

diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h
index cc62ef70ccc0a..6586d533fe3ad 100644
--- a/arch/x86/include/asm/set_memory.h
+++ b/arch/x86/include/asm/set_memory.h
@@ -38,7 +38,6 @@ int set_memory_rox(unsigned long addr, int numpages);
  * The caller is required to take care of these.
  */
 
-int __set_memory_prot(unsigned long addr, int numpages, pgprot_t prot);
 int _set_memory_uc(unsigned long addr, int numpages);
 int _set_memory_wc(unsigned long addr, int numpages);
 int _set_memory_wt(unsigned long addr, int numpages);
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index ef4514d64c052..b28966783c617 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -1942,19 +1942,6 @@ static inline int cpa_clear_pages_array(struct page **pages, int numpages,
 		CPA_PAGES_ARRAY, pages);
 }
 
-/*
- * __set_memory_prot is an internal helper for callers that have been passed
- * a pgprot_t value from upper layers and a reservation has already been taken.
- * If you want to set the pgprot to a specific page protocol, use the
- * set_memory_xx() functions.
- */
-int __set_memory_prot(unsigned long addr, int numpages, pgprot_t prot)
-{
-	return change_page_attr_set_clr(&addr, numpages, prot,
-					__pgprot(~pgprot_val(prot)), 0, 0,
-					NULL);
-}
-
 int _set_memory_uc(unsigned long addr, int numpages)
 {
 	/*

From 95c4cc5a585400982ae5b3bf9e3be6de71768376 Mon Sep 17 00:00:00 2001
From: Kevin Brodsky <kevin.brodsky@arm.com>
Date: Thu, 12 Dec 2024 08:09:04 +0000
Subject: [PATCH 0785/1173] x86/mm: Reduce header dependencies in
 <asm/set_memory.h>

Commit:

  03b122da74b2 ("x86/sgx: Hook arch_memory_failure() into mainline code")

... added <linux/mm.h> to <asm/set_memory.h> to provide some helpers.

However the following commit:

  b3fdf9398a16 ("x86/mce: relocate set{clear}_mce_nospec() functions")

... moved the inline definitions someplace else, and now <asm/set_memory.h>
just declares a bunch of mostly self-contained functions.

No need for the whole <linux/mm.h> inclusion to declare functions; just
remove that include. This helps avoid circular dependency headaches
(e.g. if <linux/mm.h> ends up including <linux/set_memory.h>).

This change requires a couple of include fixups not to break the
build:

* <asm/smp.h>: including <asm/thread_info.h> directly relies on
  <linux/thread_info.h> having already been included, because the
  former needs the BAD_STACK/NOT_STACK constants defined in the
  latter. This is no longer the case when <asm/smp.h> is included from
  some driver file - just include <linux/thread_info.h> to stay out
  of trouble.

* sev-guest.c relies on <asm/set_memory.h> including <linux/mm.h>,
  so we just need to make that include explicit.

[ mingo: Cleaned up the changelog ]

Signed-off-by: Kevin Brodsky <kevin.brodsky@arm.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: David Hildenbrand <david@redhat.com>
Link: https://lore.kernel.org/r/20241212080904.2089632-3-kevin.brodsky@arm.com
---
 arch/x86/include/asm/set_memory.h       | 1 -
 arch/x86/include/asm/smp.h              | 2 +-
 drivers/virt/coco/sev-guest/sev-guest.c | 1 +
 3 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h
index 6586d533fe3ad..8d9f1c9aaa4ce 100644
--- a/arch/x86/include/asm/set_memory.h
+++ b/arch/x86/include/asm/set_memory.h
@@ -2,7 +2,6 @@
 #ifndef _ASM_X86_SET_MEMORY_H
 #define _ASM_X86_SET_MEMORY_H
 
-#include <linux/mm.h>
 #include <asm/page.h>
 #include <asm-generic/set_memory.h>
 
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index ca073f40698fa..2ca1da5f16d96 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -3,10 +3,10 @@
 #define _ASM_X86_SMP_H
 #ifndef __ASSEMBLY__
 #include <linux/cpumask.h>
+#include <linux/thread_info.h>
 
 #include <asm/cpumask.h>
 #include <asm/current.h>
-#include <asm/thread_info.h>
 
 DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map);
 DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map);
diff --git a/drivers/virt/coco/sev-guest/sev-guest.c b/drivers/virt/coco/sev-guest/sev-guest.c
index 264b6523fe52f..ddec5677e247e 100644
--- a/drivers/virt/coco/sev-guest/sev-guest.c
+++ b/drivers/virt/coco/sev-guest/sev-guest.c
@@ -23,6 +23,7 @@
 #include <linux/cleanup.h>
 #include <linux/uuid.h>
 #include <linux/configfs.h>
+#include <linux/mm.h>
 #include <uapi/linux/sev-guest.h>
 #include <uapi/linux/psp-sev.h>
 

From fd5935f9c20431eeadd6993fd4d2672e3e17a6b8 Mon Sep 17 00:00:00 2001
From: Philip Redkin <me@rarity.fan>
Date: Fri, 15 Nov 2024 20:36:59 +0300
Subject: [PATCH 0786/1173] x86/mm: Check return value from
 memblock_phys_alloc_range()

At least with CONFIG_PHYSICAL_START=0x100000, if there is < 4 MiB of
contiguous free memory available at this point, the kernel will crash
and burn because memblock_phys_alloc_range() returns 0 on failure,
which leads memblock_phys_free() to throw the first 4 MiB of physical
memory to the wolves.

At a minimum it should fail gracefully with a meaningful diagnostic,
but in fact everything seems to work fine without the weird reserve
allocation.

Signed-off-by: Philip Redkin <me@rarity.fan>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Link: https://lore.kernel.org/r/94b3e98f-96a7-3560-1f76-349eb95ccf7f@rarity.fan
---
 arch/x86/mm/init.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 62aa4d66a032d..bfa444a7dbb04 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -645,8 +645,13 @@ static void __init memory_map_top_down(unsigned long map_start,
 	 */
 	addr = memblock_phys_alloc_range(PMD_SIZE, PMD_SIZE, map_start,
 					 map_end);
-	memblock_phys_free(addr, PMD_SIZE);
-	real_end = addr + PMD_SIZE;
+	if (!addr) {
+		pr_warn("Failed to release memory for alloc_low_pages()");
+		real_end = max(map_start, ALIGN_DOWN(map_end, PMD_SIZE));
+	} else {
+		memblock_phys_free(addr, PMD_SIZE);
+		real_end = addr + PMD_SIZE;
+	}
 
 	/* step_size need to be small so pgt_buf from BRK could cover it */
 	step_size = PMD_SIZE;

From be45bc4eff33d9a7dae84a2150f242a91a617402 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Mon, 24 Feb 2025 08:54:41 -0800
Subject: [PATCH 0787/1173] KVM: SVM: Set RFLAGS.IF=1 in C code, to get VMRUN
 out of the STI shadow

Enable/disable local IRQs, i.e. set/clear RFLAGS.IF, in the common
svm_vcpu_enter_exit() just after/before guest_state_{enter,exit}_irqoff()
so that VMRUN is not executed in an STI shadow.  AMD CPUs have a quirk
(some would say "bug"), where the STI shadow bleeds into the guest's
intr_state field if a #VMEXIT occurs during injection of an event, i.e. if
the VMRUN doesn't complete before the subsequent #VMEXIT.

The spurious "interrupts masked" state is relatively benign, as it only
occurs during event injection and is transient.  Because KVM is already
injecting an event, the guest can't be in HLT, and if KVM is querying IRQ
blocking for injection, then KVM would need to force an immediate exit
anyways since injecting multiple events is impossible.

However, because KVM copies int_state verbatim from vmcb02 to vmcb12, the
spurious STI shadow is visible to L1 when running a nested VM, which can
trip sanity checks, e.g. in VMware's VMM.

Hoist the STI+CLI all the way to C code, as the aforementioned calls to
guest_state_{enter,exit}_irqoff() already inform lockdep that IRQs are
enabled/disabled, and taking a fault on VMRUN with RFLAGS.IF=1 is already
possible.  I.e. if there's kernel code that is confused by running with
RFLAGS.IF=1, then it's already a problem.  In practice, since GIF=0 also
blocks NMIs, the only change in exposure to non-KVM code (relative to
surrounding VMRUN with STI+CLI) is exception handling code, and except for
the kvm_rebooting=1 case, all exception in the core VM-Enter/VM-Exit path
are fatal.

Use the "raw" variants to enable/disable IRQs to avoid tracing in the
"no instrumentation" code; the guest state helpers also take care of
tracing IRQ state.

Oppurtunstically document why KVM needs to do STI in the first place.

Reported-by: Doug Covelli <doug.covelli@broadcom.com>
Closes: https://lore.kernel.org/all/CADH9ctBs1YPmE4aCfGPNBwA10cA8RuAk2gO7542DjMZgs4uzJQ@mail.gmail.com
Fixes: f14eec0a3203 ("KVM: SVM: move more vmentry code to assembly")
Cc: stable@vger.kernel.org
Reviewed-by: Jim Mattson <jmattson@google.com>
Link: https://lore.kernel.org/r/20250224165442.2338294-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/svm.c     | 14 ++++++++++++++
 arch/x86/kvm/svm/vmenter.S | 10 +---------
 2 files changed, 15 insertions(+), 9 deletions(-)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index a713c803a3a37..0d299f3f921e6 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4189,6 +4189,18 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_in
 
 	guest_state_enter_irqoff();
 
+	/*
+	 * Set RFLAGS.IF prior to VMRUN, as the host's RFLAGS.IF at the time of
+	 * VMRUN controls whether or not physical IRQs are masked (KVM always
+	 * runs with V_INTR_MASKING_MASK).  Toggle RFLAGS.IF here to avoid the
+	 * temptation to do STI+VMRUN+CLI, as AMD CPUs bleed the STI shadow
+	 * into guest state if delivery of an event during VMRUN triggers a
+	 * #VMEXIT, and the guest_state transitions already tell lockdep that
+	 * IRQs are being enabled/disabled.  Note!  GIF=0 for the entirety of
+	 * this path, so IRQs aren't actually unmasked while running host code.
+	 */
+	raw_local_irq_enable();
+
 	amd_clear_divider();
 
 	if (sev_es_guest(vcpu->kvm))
@@ -4197,6 +4209,8 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_in
 	else
 		__svm_vcpu_run(svm, spec_ctrl_intercepted);
 
+	raw_local_irq_disable();
+
 	guest_state_exit_irqoff();
 }
 
diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S
index 2ed80aea3bb13..0c61153b275f6 100644
--- a/arch/x86/kvm/svm/vmenter.S
+++ b/arch/x86/kvm/svm/vmenter.S
@@ -170,12 +170,8 @@ SYM_FUNC_START(__svm_vcpu_run)
 	mov VCPU_RDI(%_ASM_DI), %_ASM_DI
 
 	/* Enter guest mode */
-	sti
-
 3:	vmrun %_ASM_AX
 4:
-	cli
-
 	/* Pop @svm to RAX while it's the only available register. */
 	pop %_ASM_AX
 
@@ -340,12 +336,8 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run)
 	mov KVM_VMCB_pa(%rax), %rax
 
 	/* Enter guest mode */
-	sti
-
 1:	vmrun %rax
-
-2:	cli
-
+2:
 	/* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */
 	FILL_RETURN_BUFFER %rax, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT
 

From f3513a335e71296a1851167b4e3b0e2bf09fc5f1 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Mon, 24 Feb 2025 08:54:42 -0800
Subject: [PATCH 0788/1173] KVM: selftests: Assert that STI blocking isn't set
 after event injection

Add an L1 (guest) assert to the nested exceptions test to verify that KVM
doesn't put VMRUN in an STI shadow (AMD CPUs bleed the shadow into the
guest's int_state if a #VMEXIT occurs before VMRUN fully completes).

Add a similar assert to the VMX side as well, because why not.

Reviewed-by: Jim Mattson <jmattson@google.com>
Link: https://lore.kernel.org/r/20250224165442.2338294-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/x86/nested_exceptions_test.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/testing/selftests/kvm/x86/nested_exceptions_test.c b/tools/testing/selftests/kvm/x86/nested_exceptions_test.c
index 3eb0313ffa397..3641a42934acb 100644
--- a/tools/testing/selftests/kvm/x86/nested_exceptions_test.c
+++ b/tools/testing/selftests/kvm/x86/nested_exceptions_test.c
@@ -85,6 +85,7 @@ static void svm_run_l2(struct svm_test_data *svm, void *l2_code, int vector,
 
 	GUEST_ASSERT_EQ(ctrl->exit_code, (SVM_EXIT_EXCP_BASE + vector));
 	GUEST_ASSERT_EQ(ctrl->exit_info_1, error_code);
+	GUEST_ASSERT(!ctrl->int_state);
 }
 
 static void l1_svm_code(struct svm_test_data *svm)
@@ -122,6 +123,7 @@ static void vmx_run_l2(void *l2_code, int vector, uint32_t error_code)
 	GUEST_ASSERT_EQ(vmreadz(VM_EXIT_REASON), EXIT_REASON_EXCEPTION_NMI);
 	GUEST_ASSERT_EQ((vmreadz(VM_EXIT_INTR_INFO) & 0xff), vector);
 	GUEST_ASSERT_EQ(vmreadz(VM_EXIT_INTR_ERROR_CODE), error_code);
+	GUEST_ASSERT(!vmreadz(GUEST_INTERRUPTIBILITY_INFO));
 }
 
 static void l1_vmx_code(struct vmx_pages *vmx)

From ee89e8013383d50a27ea9bf3c8a69eed6799856f Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 27 Feb 2025 14:24:06 -0800
Subject: [PATCH 0789/1173] KVM: SVM: Drop DEBUGCTL[5:2] from guest's effective
 value
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Drop bits 5:2 from the guest's effective DEBUGCTL value, as AMD changed
the architectural behavior of the bits and broke backwards compatibility.
On CPUs without BusLockTrap (or at least, in APMs from before ~2023),
bits 5:2 controlled the behavior of external pins:

  Performance-Monitoring/Breakpoint Pin-Control (PBi)—Bits 5:2, read/write.
  Software uses thesebits to control the type of information reported by
  the four external performance-monitoring/breakpoint pins on the
  processor. When a PBi bit is cleared to 0, the corresponding external pin
  (BPi) reports performance-monitor information. When a PBi bit is set to
  1, the corresponding external pin (BPi) reports breakpoint information.

With the introduction of BusLockTrap, presumably to be compatible with
Intel CPUs, AMD redefined bit 2 to be BLCKDB:

  Bus Lock #DB Trap (BLCKDB)—Bit 2, read/write. Software sets this bit to
  enable generation of a #DB trap following successful execution of a bus
  lock when CPL is > 0.

and redefined bits 5:3 (and bit 6) as "6:3 Reserved MBZ".

Ideally, KVM would treat bits 5:2 as reserved.  Defer that change to a
feature cleanup to avoid breaking existing guest in LTS kernels.  For now,
drop the bits to retain backwards compatibility (of a sort).

Note, dropping bits 5:2 is still a guest-visible change, e.g. if the guest
is enabling LBRs *and* the legacy PBi bits, then the state of the PBi bits
is visible to the guest, whereas now the guest will always see '0'.

Reported-by: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: stable@vger.kernel.org
Reviewed-and-tested-by: Ravi Bangoria <ravi.bangoria@amd.com>
Link: https://lore.kernel.org/r/20250227222411.3490595-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/svm.c | 12 ++++++++++++
 arch/x86/kvm/svm/svm.h |  2 +-
 2 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 0d299f3f921e6..bdafbde1f211a 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3165,6 +3165,18 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 			kvm_pr_unimpl_wrmsr(vcpu, ecx, data);
 			break;
 		}
+
+		/*
+		 * AMD changed the architectural behavior of bits 5:2.  On CPUs
+		 * without BusLockTrap, bits 5:2 control "external pins", but
+		 * on CPUs that support BusLockDetect, bit 2 enables BusLockTrap
+		 * and bits 5:3 are reserved-to-zero.  Sadly, old KVM allowed
+		 * the guest to set bits 5:2 despite not actually virtualizing
+		 * Performance-Monitoring/Breakpoint external pins.  Drop bits
+		 * 5:2 for backwards compatibility.
+		 */
+		data &= ~GENMASK(5, 2);
+
 		if (data & DEBUGCTL_RESERVED_BITS)
 			return 1;
 
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 9d7cdb8fbf872..3a931d3885e71 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -584,7 +584,7 @@ static inline bool is_vnmi_enabled(struct vcpu_svm *svm)
 /* svm.c */
 #define MSR_INVALID				0xffffffffU
 
-#define DEBUGCTL_RESERVED_BITS (~(0x3fULL))
+#define DEBUGCTL_RESERVED_BITS (~(DEBUGCTLMSR_BTF | DEBUGCTLMSR_LBR))
 
 extern bool dump_invalid_vmcb;
 

From d0eac42f5cecce009d315655bee341304fbe075e Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 27 Feb 2025 14:24:07 -0800
Subject: [PATCH 0790/1173] KVM: SVM: Suppress DEBUGCTL.BTF on AMD

Mark BTF as reserved in DEBUGCTL on AMD, as KVM doesn't actually support
BTF, and fully enabling BTF virtualization is non-trivial due to
interactions with the emulator, guest_debug, #DB interception, nested SVM,
etc.

Don't inject #GP if the guest attempts to set BTF, as there's no way to
communicate lack of support to the guest, and instead suppress the flag
and treat the WRMSR as (partially) unsupported.

In short, make KVM behave the same on AMD and Intel (VMX already squashes
BTF).

Note, due to other bugs in KVM's handling of DEBUGCTL, the only way BTF
has "worked" in any capacity is if the guest simultaneously enables LBRs.

Reported-by: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: stable@vger.kernel.org
Reviewed-and-tested-by: Ravi Bangoria <ravi.bangoria@amd.com>
Link: https://lore.kernel.org/r/20250227222411.3490595-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/svm.c | 9 +++++++++
 arch/x86/kvm/svm/svm.h | 2 +-
 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index bdafbde1f211a..ed48465186961 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3177,6 +3177,15 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		 */
 		data &= ~GENMASK(5, 2);
 
+		/*
+		 * Suppress BTF as KVM doesn't virtualize BTF, but there's no
+		 * way to communicate lack of support to the guest.
+		 */
+		if (data & DEBUGCTLMSR_BTF) {
+			kvm_pr_unimpl_wrmsr(vcpu, MSR_IA32_DEBUGCTLMSR, data);
+			data &= ~DEBUGCTLMSR_BTF;
+		}
+
 		if (data & DEBUGCTL_RESERVED_BITS)
 			return 1;
 
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 3a931d3885e71..ea44c1da5a7c9 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -584,7 +584,7 @@ static inline bool is_vnmi_enabled(struct vcpu_svm *svm)
 /* svm.c */
 #define MSR_INVALID				0xffffffffU
 
-#define DEBUGCTL_RESERVED_BITS (~(DEBUGCTLMSR_BTF | DEBUGCTLMSR_LBR))
+#define DEBUGCTL_RESERVED_BITS (~DEBUGCTLMSR_LBR)
 
 extern bool dump_invalid_vmcb;
 

From fb71c795935652fa20eaf9517ca9547f5af99a76 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 27 Feb 2025 14:24:08 -0800
Subject: [PATCH 0791/1173] KVM: x86: Snapshot the host's DEBUGCTL in common
 x86

Move KVM's snapshot of DEBUGCTL to kvm_vcpu_arch and take the snapshot in
common x86, so that SVM can also use the snapshot.

Opportunistically change the field to a u64.  While bits 63:32 are reserved
on AMD, not mentioned at all in Intel's SDM, and managed as an "unsigned
long" by the kernel, DEBUGCTL is an MSR and therefore a 64-bit value.

Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
Cc: stable@vger.kernel.org
Reviewed-and-tested-by: Ravi Bangoria <ravi.bangoria@amd.com>
Link: https://lore.kernel.org/r/20250227222411.3490595-4-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/kvm_host.h | 1 +
 arch/x86/kvm/vmx/vmx.c          | 8 ++------
 arch/x86/kvm/vmx/vmx.h          | 2 --
 arch/x86/kvm/x86.c              | 1 +
 4 files changed, 4 insertions(+), 8 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 0b7af5902ff75..32ae3aa50c7e3 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -780,6 +780,7 @@ struct kvm_vcpu_arch {
 	u32 pkru;
 	u32 hflags;
 	u64 efer;
+	u64 host_debugctl;
 	u64 apic_base;
 	struct kvm_lapic *apic;    /* kernel irqchip context */
 	bool load_eoi_exitmap_pending;
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 6c56d5235f0f3..3b92f893b2392 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1514,16 +1514,12 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
  */
 void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-
 	if (vcpu->scheduled_out && !kvm_pause_in_guest(vcpu->kvm))
 		shrink_ple_window(vcpu);
 
 	vmx_vcpu_load_vmcs(vcpu, cpu, NULL);
 
 	vmx_vcpu_pi_load(vcpu, cpu);
-
-	vmx->host_debugctlmsr = get_debugctlmsr();
 }
 
 void vmx_vcpu_put(struct kvm_vcpu *vcpu)
@@ -7458,8 +7454,8 @@ fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
 	}
 
 	/* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */
-	if (vmx->host_debugctlmsr)
-		update_debugctlmsr(vmx->host_debugctlmsr);
+	if (vcpu->arch.host_debugctl)
+		update_debugctlmsr(vcpu->arch.host_debugctl);
 
 #ifndef CONFIG_X86_64
 	/*
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 8b111ce1087c7..951e44dc9d0ea 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -340,8 +340,6 @@ struct vcpu_vmx {
 	/* apic deadline value in host tsc */
 	u64 hv_deadline_tsc;
 
-	unsigned long host_debugctlmsr;
-
 	/*
 	 * Only bits masked by msr_ia32_feature_control_valid_bits can be set in
 	 * msr_ia32_feature_control. FEAT_CTL_LOCKED is always included
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 02159c967d29e..5c6fd0edc41f4 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4968,6 +4968,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	/* Save host pkru register if supported */
 	vcpu->arch.host_pkru = read_pkru();
+	vcpu->arch.host_debugctl = get_debugctlmsr();
 
 	/* Apply any externally detected TSC adjustments (due to suspend) */
 	if (unlikely(vcpu->arch.tsc_offset_adjustment)) {

From 433265870ab3455b418885bff48fa5fd02f7e448 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 27 Feb 2025 14:24:09 -0800
Subject: [PATCH 0792/1173] KVM: SVM: Manually context switch DEBUGCTL if LBR
 virtualization is disabled

Manually load the guest's DEBUGCTL prior to VMRUN (and restore the host's
value on #VMEXIT) if it diverges from the host's value and LBR
virtualization is disabled, as hardware only context switches DEBUGCTL if
LBR virtualization is fully enabled.  Running the guest with the host's
value has likely been mildly problematic for quite some time, e.g. it will
result in undesirable behavior if BTF diverges (with the caveat that KVM
now suppresses guest BTF due to lack of support).

But the bug became fatal with the introduction of Bus Lock Trap ("Detect"
in kernel paralance) support for AMD (commit 408eb7417a92
("x86/bus_lock: Add support for AMD")), as a bus lock in the guest will
trigger an unexpected #DB.

Note, suppressing the bus lock #DB, i.e. simply resuming the guest without
injecting a #DB, is not an option.  It wouldn't address the general issue
with DEBUGCTL, e.g. for things like BTF, and there are other guest-visible
side effects if BusLockTrap is left enabled.

If BusLockTrap is disabled, then DR6.BLD is reserved-to-1; any attempts to
clear it by software are ignored.  But if BusLockTrap is enabled, software
can clear DR6.BLD:

  Software enables bus lock trap by setting DebugCtl MSR[BLCKDB] (bit 2)
  to 1.  When bus lock trap is enabled, ... The processor indicates that
  this #DB was caused by a bus lock by clearing DR6[BLD] (bit 11).  DR6[11]
  previously had been defined to be always 1.

and clearing DR6.BLD is "sticky" in that it's not set (i.e. lowered) by
other #DBs:

  All other #DB exceptions leave DR6[BLD] unmodified

E.g. leaving BusLockTrap enable can confuse a legacy guest that writes '0'
to reset DR6.

Reported-by: rangemachine@gmail.com
Reported-by: whanos@sergal.fun
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219787
Closes: https://lore.kernel.org/all/bug-219787-28872@https.bugzilla.kernel.org%2F
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: stable@vger.kernel.org
Reviewed-and-tested-by: Ravi Bangoria <ravi.bangoria@amd.com>
Link: https://lore.kernel.org/r/20250227222411.3490595-5-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/svm.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index ed48465186961..e67de787fc714 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4288,6 +4288,16 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu,
 	clgi();
 	kvm_load_guest_xsave_state(vcpu);
 
+	/*
+	 * Hardware only context switches DEBUGCTL if LBR virtualization is
+	 * enabled.  Manually load DEBUGCTL if necessary (and restore it after
+	 * VM-Exit), as running with the host's DEBUGCTL can negatively affect
+	 * guest state and can even be fatal, e.g. due to Bus Lock Detect.
+	 */
+	if (!(svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK) &&
+	    vcpu->arch.host_debugctl != svm->vmcb->save.dbgctl)
+		update_debugctlmsr(svm->vmcb->save.dbgctl);
+
 	kvm_wait_lapic_expire(vcpu);
 
 	/*
@@ -4315,6 +4325,10 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu,
 	if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI))
 		kvm_before_interrupt(vcpu, KVM_HANDLING_NMI);
 
+	if (!(svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK) &&
+	    vcpu->arch.host_debugctl != svm->vmcb->save.dbgctl)
+		update_debugctlmsr(vcpu->arch.host_debugctl);
+
 	kvm_load_host_xsave_state(vcpu);
 	stgi();
 

From 189ecdb3e112da703ac0699f4ec76aa78122f911 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 27 Feb 2025 14:24:10 -0800
Subject: [PATCH 0793/1173] KVM: x86: Snapshot the host's DEBUGCTL after
 disabling IRQs

Snapshot the host's DEBUGCTL after disabling IRQs, as perf can toggle
debugctl bits from IRQ context, e.g. when enabling/disabling events via
smp_call_function_single().  Taking the snapshot (long) before IRQs are
disabled could result in KVM effectively clobbering DEBUGCTL due to using
a stale snapshot.

Cc: stable@vger.kernel.org
Reviewed-and-tested-by: Ravi Bangoria <ravi.bangoria@amd.com>
Link: https://lore.kernel.org/r/20250227222411.3490595-6-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/x86.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 5c6fd0edc41f4..12d5f47c1bbe9 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4968,7 +4968,6 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	/* Save host pkru register if supported */
 	vcpu->arch.host_pkru = read_pkru();
-	vcpu->arch.host_debugctl = get_debugctlmsr();
 
 	/* Apply any externally detected TSC adjustments (due to suspend) */
 	if (unlikely(vcpu->arch.tsc_offset_adjustment)) {
@@ -10969,6 +10968,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		set_debugreg(0, 7);
 	}
 
+	vcpu->arch.host_debugctl = get_debugctlmsr();
+
 	guest_timing_enter_irqoff();
 
 	for (;;) {

From c157d351460bcf202970e97e611cb6b54a3dd4a4 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 25 Feb 2025 23:37:08 +0100
Subject: [PATCH 0794/1173] intel_idle: Handle older CPUs, which stop the TSC
 in deeper C states, correctly

The Intel idle driver is preferred over the ACPI processor idle driver,
but fails to implement the work around for Core2 generation CPUs, where
the TSC stops in C2 and deeper C-states. This causes stalls and boot
delays, when the clocksource watchdog does not catch the unstable TSC
before the CPU goes deep idle for the first time.

The ACPI driver marks the TSC unstable when it detects that the CPU
supports C2 or deeper and the CPU does not have a non-stop TSC.

Add the equivivalent work around to the Intel idle driver to cure that.

Fixes: 18734958e9bf ("intel_idle: Use ACPI _CST for processor models without C-state tables")
Reported-by: Fab Stz <fabstz-it@yahoo.fr>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Fab Stz <fabstz-it@yahoo.fr>
Cc: All applicable <stable@vger.kernel.org>
Closes: https://lore.kernel.org/all/10cf96aa-1276-4bd4-8966-c890377030c3@yahoo.fr
Link: https://patch.msgid.link/87bjupfy7f.ffs@tglx
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/idle/intel_idle.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 118fe1d37c226..0fdb1d1316c44 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -56,6 +56,7 @@
 #include <asm/intel-family.h>
 #include <asm/mwait.h>
 #include <asm/spec-ctrl.h>
+#include <asm/tsc.h>
 #include <asm/fpu/api.h>
 
 #define INTEL_IDLE_VERSION "0.5.1"
@@ -1799,6 +1800,9 @@ static void __init intel_idle_init_cstates_acpi(struct cpuidle_driver *drv)
 		if (intel_idle_state_needs_timer_stop(state))
 			state->flags |= CPUIDLE_FLAG_TIMER_STOP;
 
+		if (cx->type > ACPI_STATE_C1 && !boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
+			mark_tsc_unstable("TSC halts in idle");
+
 		state->enter = intel_idle;
 		state->enter_s2idle = intel_idle_s2idle;
 	}

From 4a4f9b5c7c13601c4f1b3d8c607d7439e39f40d2 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Fri, 28 Feb 2025 15:58:30 -0500
Subject: [PATCH 0795/1173] bcachefs: Don't set
 BCH_FEATURE_incompat_version_field unless requested

We shouldn't be setting incompatible bits or the incompatible version
field unless explicitly request or allowed - otherwise we break mounting
with old kernels or userspace.

Reported-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/super-io.c | 24 ++++++++++++++++--------
 fs/bcachefs/super-io.h | 11 ++++-------
 2 files changed, 20 insertions(+), 15 deletions(-)

diff --git a/fs/bcachefs/super-io.c b/fs/bcachefs/super-io.c
index 8037ccbacf6af..a81a7b6c09897 100644
--- a/fs/bcachefs/super-io.c
+++ b/fs/bcachefs/super-io.c
@@ -69,14 +69,20 @@ enum bcachefs_metadata_version bch2_latest_compatible_version(enum bcachefs_meta
 	return v;
 }
 
-void bch2_set_version_incompat(struct bch_fs *c, enum bcachefs_metadata_version version)
+bool bch2_set_version_incompat(struct bch_fs *c, enum bcachefs_metadata_version version)
 {
-	mutex_lock(&c->sb_lock);
-	SET_BCH_SB_VERSION_INCOMPAT(c->disk_sb.sb,
-		max(BCH_SB_VERSION_INCOMPAT(c->disk_sb.sb), version));
-	c->disk_sb.sb->features[0] |= cpu_to_le64(BCH_FEATURE_incompat_version_field);
-	bch2_write_super(c);
-	mutex_unlock(&c->sb_lock);
+	bool ret = (c->sb.features & BIT_ULL(BCH_FEATURE_incompat_version_field)) &&
+		   version <= c->sb.version_incompat_allowed;
+
+	if (ret) {
+		mutex_lock(&c->sb_lock);
+		SET_BCH_SB_VERSION_INCOMPAT(c->disk_sb.sb,
+			max(BCH_SB_VERSION_INCOMPAT(c->disk_sb.sb), version));
+		bch2_write_super(c);
+		mutex_unlock(&c->sb_lock);
+	}
+
+	return ret;
 }
 
 const char * const bch2_sb_fields[] = {
@@ -1219,9 +1225,11 @@ void bch2_sb_upgrade(struct bch_fs *c, unsigned new_version, bool incompat)
 	c->disk_sb.sb->version = cpu_to_le16(new_version);
 	c->disk_sb.sb->features[0] |= cpu_to_le64(BCH_SB_FEATURES_ALL);
 
-	if (incompat)
+	if (incompat) {
 		SET_BCH_SB_VERSION_INCOMPAT_ALLOWED(c->disk_sb.sb,
 			max(BCH_SB_VERSION_INCOMPAT_ALLOWED(c->disk_sb.sb), new_version));
+		c->disk_sb.sb->features[0] |= cpu_to_le64(BCH_FEATURE_incompat_version_field);
+	}
 }
 
 static int bch2_sb_ext_validate(struct bch_sb *sb, struct bch_sb_field *f,
diff --git a/fs/bcachefs/super-io.h b/fs/bcachefs/super-io.h
index f1ab4f9437203..b4cff9ebdebbf 100644
--- a/fs/bcachefs/super-io.h
+++ b/fs/bcachefs/super-io.h
@@ -21,17 +21,14 @@ static inline bool bch2_version_compatible(u16 version)
 void bch2_version_to_text(struct printbuf *, enum bcachefs_metadata_version);
 enum bcachefs_metadata_version bch2_latest_compatible_version(enum bcachefs_metadata_version);
 
-void bch2_set_version_incompat(struct bch_fs *, enum bcachefs_metadata_version);
+bool bch2_set_version_incompat(struct bch_fs *, enum bcachefs_metadata_version);
 
 static inline bool bch2_request_incompat_feature(struct bch_fs *c,
 						 enum bcachefs_metadata_version version)
 {
-	if (unlikely(version > c->sb.version_incompat)) {
-		if (version > c->sb.version_incompat_allowed)
-			return false;
-		bch2_set_version_incompat(c, version);
-	}
-	return true;
+	return likely(version <= c->sb.version_incompat)
+		? true
+		: bch2_set_version_incompat(c, version);
 }
 
 static inline size_t bch2_sb_field_bytes(struct bch_sb_field *f)

From ee01b2f2d7d0010787c2343463965bbc283a497f Mon Sep 17 00:00:00 2001
From: Antoine Tenart <atenart@kernel.org>
Date: Wed, 26 Feb 2025 18:13:42 +0100
Subject: [PATCH 0796/1173] net: gso: fix ownership in __udp_gso_segment

In __udp_gso_segment the skb destructor is removed before segmenting the
skb but the socket reference is kept as-is. This is an issue if the
original skb is later orphaned as we can hit the following bug:

  kernel BUG at ./include/linux/skbuff.h:3312!  (skb_orphan)
  RIP: 0010:ip_rcv_core+0x8b2/0xca0
  Call Trace:
   ip_rcv+0xab/0x6e0
   __netif_receive_skb_one_core+0x168/0x1b0
   process_backlog+0x384/0x1100
   __napi_poll.constprop.0+0xa1/0x370
   net_rx_action+0x925/0xe50

The above can happen following a sequence of events when using
OpenVSwitch, when an OVS_ACTION_ATTR_USERSPACE action precedes an
OVS_ACTION_ATTR_OUTPUT action:

1. OVS_ACTION_ATTR_USERSPACE is handled (in do_execute_actions): the skb
   goes through queue_gso_packets and then __udp_gso_segment, where its
   destructor is removed.
2. The segments' data are copied and sent to userspace.
3. OVS_ACTION_ATTR_OUTPUT is handled (in do_execute_actions) and the
   same original skb is sent to its path.
4. If it later hits skb_orphan, we hit the bug.

Fix this by also removing the reference to the socket in
__udp_gso_segment.

Fixes: ad405857b174 ("udp: better wmem accounting on gso")
Signed-off-by: Antoine Tenart <atenart@kernel.org>
Link: https://patch.msgid.link/20250226171352.258045-1-atenart@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/udp_offload.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index a5be6e4ed326f..ecfca59f31f13 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -321,13 +321,17 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
 
 	/* clear destructor to avoid skb_segment assigning it to tail */
 	copy_dtor = gso_skb->destructor == sock_wfree;
-	if (copy_dtor)
+	if (copy_dtor) {
 		gso_skb->destructor = NULL;
+		gso_skb->sk = NULL;
+	}
 
 	segs = skb_segment(gso_skb, features);
 	if (IS_ERR_OR_NULL(segs)) {
-		if (copy_dtor)
+		if (copy_dtor) {
 			gso_skb->destructor = sock_wfree;
+			gso_skb->sk = sk;
+		}
 		return segs;
 	}
 

From a466fd7e9fafd975949e5945e2f70c33a94b1a70 Mon Sep 17 00:00:00 2001
From: Vitaliy Shevtsov <v.shevtsov@mt-integration.ru>
Date: Thu, 27 Feb 2025 23:46:27 +0500
Subject: [PATCH 0797/1173] caif_virtio: fix wrong pointer check in cfv_probe()

del_vqs() frees virtqueues, therefore cfv->vq_tx pointer should be checked
for NULL before calling it, not cfv->vdev. Also the current implementation
is redundant because the pointer cfv->vdev is dereferenced before it is
checked for NULL.

Fix this by checking cfv->vq_tx for NULL instead of cfv->vdev before
calling del_vqs().

Fixes: 0d2e1a2926b1 ("caif_virtio: Introduce caif over virtio")
Signed-off-by: Vitaliy Shevtsov <v.shevtsov@mt-integration.ru>
Reviewed-by: Gerhard Engleder <gerhard@engleder-embedded.com>
Link: https://patch.msgid.link/20250227184716.4715-1-v.shevtsov@mt-integration.ru
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/caif/caif_virtio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/caif/caif_virtio.c b/drivers/net/caif/caif_virtio.c
index 7fea00c7ca8a6..c60386bf2d1a4 100644
--- a/drivers/net/caif/caif_virtio.c
+++ b/drivers/net/caif/caif_virtio.c
@@ -745,7 +745,7 @@ static int cfv_probe(struct virtio_device *vdev)
 
 	if (cfv->vr_rx)
 		vdev->vringh_config->del_vrhs(cfv->vdev);
-	if (cfv->vdev)
+	if (cfv->vq_tx)
 		vdev->config->del_vqs(cfv->vdev);
 	free_netdev(netdev);
 	return err;

From cb380909ae3b1ebf14d6a455a4f92d7916d790cb Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Thu, 27 Feb 2025 15:06:30 -0800
Subject: [PATCH 0798/1173] vhost: return task creation error instead of NULL

Lets callers distinguish why the vhost task creation failed. No one
currently cares why it failed, so no real runtime change from this
patch, but that will not be the case for long.

Signed-off-by: Keith Busch <kbusch@kernel.org>
Message-ID: <20250227230631.303431-2-kbusch@meta.com>
Reviewed-by: Mike Christie <michael.christie@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c | 2 +-
 drivers/vhost/vhost.c  | 2 +-
 kernel/vhost_task.c    | 4 ++--
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index d4ac4a1f8b81b..18ca1ea6dc240 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -7471,7 +7471,7 @@ static void kvm_mmu_start_lpage_recovery(struct once *once)
 				      kvm_nx_huge_page_recovery_worker_kill,
 				      kvm, "kvm-nx-lpage-recovery");
 
-	if (!nx_thread)
+	if (IS_ERR(nx_thread))
 		return;
 
 	vhost_task_start(nx_thread);
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 9ac25d08f473e..63612faeab727 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -666,7 +666,7 @@ static struct vhost_worker *vhost_worker_create(struct vhost_dev *dev)
 
 	vtsk = vhost_task_create(vhost_run_work_list, vhost_worker_killed,
 				 worker, name);
-	if (!vtsk)
+	if (IS_ERR(vtsk))
 		goto free_worker;
 
 	mutex_init(&worker->mutex);
diff --git a/kernel/vhost_task.c b/kernel/vhost_task.c
index 8800f5acc0071..2ef2e1b800916 100644
--- a/kernel/vhost_task.c
+++ b/kernel/vhost_task.c
@@ -133,7 +133,7 @@ struct vhost_task *vhost_task_create(bool (*fn)(void *),
 
 	vtsk = kzalloc(sizeof(*vtsk), GFP_KERNEL);
 	if (!vtsk)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	init_completion(&vtsk->exited);
 	mutex_init(&vtsk->exit_mutex);
 	vtsk->data = arg;
@@ -145,7 +145,7 @@ struct vhost_task *vhost_task_create(bool (*fn)(void *),
 	tsk = copy_process(NULL, 0, NUMA_NO_NODE, &args);
 	if (IS_ERR(tsk)) {
 		kfree(vtsk);
-		return NULL;
+		return ERR_PTR(PTR_ERR(tsk));
 	}
 
 	vtsk->task = tsk;

From 916b7f42b3b3b539a71c204a9b49fdc4ca92cd82 Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Thu, 27 Feb 2025 15:06:31 -0800
Subject: [PATCH 0799/1173] kvm: retry nx_huge_page_recovery_thread creation

A VMM may send a non-fatal signal to its threads, including vCPU tasks,
at any time, and thus may signal vCPU tasks during KVM_RUN.  If a vCPU
task receives the signal while its trying to spawn the huge page recovery
vhost task, then KVM_RUN will fail due to copy_process() returning
-ERESTARTNOINTR.

Rework call_once() to mark the call complete if and only if the called
function succeeds, and plumb the function's true error code back to the
call_once() invoker.  This provides userspace with the correct, non-fatal
error code so that the VMM doesn't terminate the VM on -ENOMEM, and allows
subsequent KVM_RUN a succeed by virtue of retrying creation of the NX huge
page task.

Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
[implemented the kvm user side]
Signed-off-by: Keith Busch <kbusch@kernel.org>
Message-ID: <20250227230631.303431-3-kbusch@meta.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c    | 10 ++++-----
 include/linux/call_once.h | 47 ++++++++++++++++++++++++++++-----------
 2 files changed, 38 insertions(+), 19 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 18ca1ea6dc240..8160870398b90 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -7460,7 +7460,7 @@ static bool kvm_nx_huge_page_recovery_worker(void *data)
 	return true;
 }
 
-static void kvm_mmu_start_lpage_recovery(struct once *once)
+static int kvm_mmu_start_lpage_recovery(struct once *once)
 {
 	struct kvm_arch *ka = container_of(once, struct kvm_arch, nx_once);
 	struct kvm *kvm = container_of(ka, struct kvm, arch);
@@ -7472,12 +7472,13 @@ static void kvm_mmu_start_lpage_recovery(struct once *once)
 				      kvm, "kvm-nx-lpage-recovery");
 
 	if (IS_ERR(nx_thread))
-		return;
+		return PTR_ERR(nx_thread);
 
 	vhost_task_start(nx_thread);
 
 	/* Make the task visible only once it is fully started. */
 	WRITE_ONCE(kvm->arch.nx_huge_page_recovery_thread, nx_thread);
+	return 0;
 }
 
 int kvm_mmu_post_init_vm(struct kvm *kvm)
@@ -7485,10 +7486,7 @@ int kvm_mmu_post_init_vm(struct kvm *kvm)
 	if (nx_hugepage_mitigation_hard_disabled)
 		return 0;
 
-	call_once(&kvm->arch.nx_once, kvm_mmu_start_lpage_recovery);
-	if (!kvm->arch.nx_huge_page_recovery_thread)
-		return -ENOMEM;
-	return 0;
+	return call_once(&kvm->arch.nx_once, kvm_mmu_start_lpage_recovery);
 }
 
 void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
diff --git a/include/linux/call_once.h b/include/linux/call_once.h
index 6261aa0b3fb00..13cd6469e7e56 100644
--- a/include/linux/call_once.h
+++ b/include/linux/call_once.h
@@ -26,20 +26,41 @@ do {									\
 	__once_init((once), #once, &__key);				\
 } while (0)
 
-static inline void call_once(struct once *once, void (*cb)(struct once *))
+/*
+ * call_once - Ensure a function has been called exactly once
+ *
+ * @once: Tracking struct
+ * @cb: Function to be called
+ *
+ * If @once has never completed successfully before, call @cb and, if
+ * it returns a zero or positive value, mark @once as completed.  Return
+ * the value returned by @cb
+ *
+ * If @once has completed succesfully before, return 0.
+ *
+ * The call to @cb is implicitly surrounded by a mutex, though for
+ * efficiency the * function avoids taking it after the first call.
+ */
+static inline int call_once(struct once *once, int (*cb)(struct once *))
 {
-        /* Pairs with atomic_set_release() below.  */
-        if (atomic_read_acquire(&once->state) == ONCE_COMPLETED)
-                return;
-
-        guard(mutex)(&once->lock);
-        WARN_ON(atomic_read(&once->state) == ONCE_RUNNING);
-        if (atomic_read(&once->state) != ONCE_NOT_STARTED)
-                return;
-
-        atomic_set(&once->state, ONCE_RUNNING);
-        cb(once);
-        atomic_set_release(&once->state, ONCE_COMPLETED);
+	int r, state;
+
+	/* Pairs with atomic_set_release() below.  */
+	if (atomic_read_acquire(&once->state) == ONCE_COMPLETED)
+		return 0;
+
+	guard(mutex)(&once->lock);
+	state = atomic_read(&once->state);
+	if (unlikely(state != ONCE_NOT_STARTED))
+		return WARN_ON_ONCE(state != ONCE_COMPLETED) ? -EINVAL : 0;
+
+	atomic_set(&once->state, ONCE_RUNNING);
+	r = cb(once);
+	if (r < 0)
+		atomic_set(&once->state, ONCE_NOT_STARTED);
+	else
+		atomic_set_release(&once->state, ONCE_COMPLETED);
+	return r;
 }
 
 #endif /* _LINUX_CALL_ONCE_H */

From a2f925a2f62254119cdaa360cfc9c0424bccd531 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <cassel@kernel.org>
Date: Fri, 28 Feb 2025 13:26:04 +0100
Subject: [PATCH 0800/1173] Revert "ata: libata-core: Add ATA_QUIRK_NOLPM for
 Samsung SSD 870 QVO drives"

This reverts commit cc77e2ce187d26cc66af3577bf896d7410eb25ab.

It was reported that adding ATA_QUIRK_NOLPM for Samsung SSD 870 QVO drives
breaks entering lower package states for certain systems.

It turns out that Samsung SSD 870 QVO actually has working LPM when using
a recent SSD firmware version.

The author of commit cc77e2ce187d ("ata: libata-core: Add ATA_QUIRK_NOLPM
for Samsung SSD 870 QVO drives") reported himself that only older SSD
firmware versions have broken LPM:
https://lore.kernel.org/stable/93c10d38-718c-459d-84a5-4d87680b4da7@debian.org/

Unfortunately, he did not specify which older firmware version he was using
which had broken LPM.

Let's revert this quirk, which has FW version field specified as NULL
(which means that it applies for all Samsung SSD 870 QVO firmware versions)
for now. Once the author reports which older firmware version(s) that are
broken, we can create a more fine grained quirk, which populates the FW
version field accordingly.

Fixes: cc77e2ce187d ("ata: libata-core: Add ATA_QUIRK_NOLPM for Samsung SSD 870 QVO drives")
Reported-by: Dieter Mummenschanz <dmummenschanz@web.de>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219747
Link: https://lore.kernel.org/r/20250228122603.91814-2-cassel@kernel.org
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/libata-core.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 63ec2f2184319..c085dd81ebe7f 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4143,10 +4143,6 @@ static const struct ata_dev_quirks_entry __ata_dev_quirks[] = {
 	{ "Samsung SSD 860*",		NULL,	ATA_QUIRK_NO_NCQ_TRIM |
 						ATA_QUIRK_ZERO_AFTER_TRIM |
 						ATA_QUIRK_NO_NCQ_ON_ATI },
-	{ "Samsung SSD 870 QVO*",	NULL,	ATA_QUIRK_NO_NCQ_TRIM |
-						ATA_QUIRK_ZERO_AFTER_TRIM |
-						ATA_QUIRK_NO_NCQ_ON_ATI |
-						ATA_QUIRK_NOLPM },
 	{ "Samsung SSD 870*",		NULL,	ATA_QUIRK_NO_NCQ_TRIM |
 						ATA_QUIRK_ZERO_AFTER_TRIM |
 						ATA_QUIRK_NO_NCQ_ON_ATI },

From a1b65f3f7c6f7f0a08a7dba8be458c6415236487 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 4 Nov 2024 14:39:10 +0100
Subject: [PATCH 0801/1173] lockdep/mm: Fix might_fault() lockdep check of
 current->mm->mmap_lock

Turns out that this commit, about 10 years ago:

  9ec23531fd48 ("sched/preempt, mm/fault: Trigger might_sleep() in might_fault() with disabled pagefaults")

... accidentally (and unnessecarily) put the lockdep part of
__might_fault() under CONFIG_DEBUG_ATOMIC_SLEEP=y.

This is potentially notable because large distributions such as
Ubuntu are running with !CONFIG_DEBUG_ATOMIC_SLEEP.

Restore the debug check.

[ mingo: Update changelog. ]

Fixes: 9ec23531fd48 ("sched/preempt, mm/fault: Trigger might_sleep() in might_fault() with disabled pagefaults")
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: https://lore.kernel.org/r/20241104135517.536628371@infradead.org
---
 mm/memory.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index 539c0f7c6d545..1dfad4536cfef 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -6835,10 +6835,8 @@ void __might_fault(const char *file, int line)
 	if (pagefault_disabled())
 		return;
 	__might_sleep(file, line);
-#if defined(CONFIG_DEBUG_ATOMIC_SLEEP)
 	if (current->mm)
 		might_lock_read(&current->mm->mmap_lock);
-#endif
 }
 EXPORT_SYMBOL(__might_fault);
 #endif

From 2565e42539b120b81a68a58da961ce5d1e34eac8 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 4 Nov 2024 14:39:11 +0100
Subject: [PATCH 0802/1173] perf/core: Fix pmus_lock vs. pmus_srcu ordering

Commit a63fbed776c7 ("perf/tracing/cpuhotplug: Fix locking order")
placed pmus_lock inside pmus_srcu, this makes perf_pmu_unregister()
trip lockdep.

Move the locking about such that only pmu_idr and pmus (list) are
modified while holding pmus_lock. This avoids doing synchronize_srcu()
while holding pmus_lock and all is well again.

Fixes: a63fbed776c7 ("perf/tracing/cpuhotplug: Fix locking order")
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20241104135517.679556858@infradead.org
---
 kernel/events/core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 6364319e2f888..11793d690cbb7 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -11939,6 +11939,8 @@ void perf_pmu_unregister(struct pmu *pmu)
 {
 	mutex_lock(&pmus_lock);
 	list_del_rcu(&pmu->entry);
+	idr_remove(&pmu_idr, pmu->type);
+	mutex_unlock(&pmus_lock);
 
 	/*
 	 * We dereference the pmu list under both SRCU and regular RCU, so
@@ -11948,7 +11950,6 @@ void perf_pmu_unregister(struct pmu *pmu)
 	synchronize_rcu();
 
 	free_percpu(pmu->pmu_disable_count);
-	idr_remove(&pmu_idr, pmu->type);
 	if (pmu_bus_running && pmu->dev && pmu->dev != PMU_NULL_DEV) {
 		if (pmu->nr_addr_filters)
 			device_remove_file(pmu->dev, &dev_attr_nr_addr_filters);
@@ -11956,7 +11957,6 @@ void perf_pmu_unregister(struct pmu *pmu)
 		put_device(pmu->dev);
 	}
 	free_pmu_context(pmu);
-	mutex_unlock(&pmus_lock);
 }
 EXPORT_SYMBOL_GPL(perf_pmu_unregister);
 

From 003659fec9f6d8c04738cb74b5384398ae8a7e88 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 4 Nov 2024 14:39:12 +0100
Subject: [PATCH 0803/1173] perf/core: Fix perf_pmu_register() vs.
 perf_init_event()

There is a fairly obvious race between perf_init_event() doing
idr_find() and perf_pmu_register() doing idr_alloc() with an
incompletely initialized PMU pointer.

Avoid by doing idr_alloc() on a NULL pointer to register the id, and
swizzling the real struct pmu pointer at the end using idr_replace().

Also making sure to not set struct pmu members after publishing
the struct pmu, duh.

[ introduce idr_cmpxchg() in order to better handle the idr_replace()
  error case -- if it were to return an unexpected pointer, it will
  already have replaced the value and there is no going back. ]

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20241104135517.858805880@infradead.org
---
 kernel/events/core.c | 28 ++++++++++++++++++++++++++--
 1 file changed, 26 insertions(+), 2 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 11793d690cbb7..823aa08249161 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -11830,6 +11830,21 @@ static int pmu_dev_alloc(struct pmu *pmu)
 static struct lock_class_key cpuctx_mutex;
 static struct lock_class_key cpuctx_lock;
 
+static bool idr_cmpxchg(struct idr *idr, unsigned long id, void *old, void *new)
+{
+	void *tmp, *val = idr_find(idr, id);
+
+	if (val != old)
+		return false;
+
+	tmp = idr_replace(idr, new, id);
+	if (IS_ERR(tmp))
+		return false;
+
+	WARN_ON_ONCE(tmp != val);
+	return true;
+}
+
 int perf_pmu_register(struct pmu *pmu, const char *name, int type)
 {
 	int cpu, ret, max = PERF_TYPE_MAX;
@@ -11856,7 +11871,7 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type)
 	if (type >= 0)
 		max = type;
 
-	ret = idr_alloc(&pmu_idr, pmu, max, 0, GFP_KERNEL);
+	ret = idr_alloc(&pmu_idr, NULL, max, 0, GFP_KERNEL);
 	if (ret < 0)
 		goto free_pdc;
 
@@ -11864,6 +11879,7 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type)
 
 	type = ret;
 	pmu->type = type;
+	atomic_set(&pmu->exclusive_cnt, 0);
 
 	if (pmu_bus_running && !pmu->dev) {
 		ret = pmu_dev_alloc(pmu);
@@ -11912,14 +11928,22 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type)
 	if (!pmu->event_idx)
 		pmu->event_idx = perf_event_idx_default;
 
+	/*
+	 * Now that the PMU is complete, make it visible to perf_try_init_event().
+	 */
+	if (!idr_cmpxchg(&pmu_idr, pmu->type, NULL, pmu))
+		goto free_context;
 	list_add_rcu(&pmu->entry, &pmus);
-	atomic_set(&pmu->exclusive_cnt, 0);
+
 	ret = 0;
 unlock:
 	mutex_unlock(&pmus_lock);
 
 	return ret;
 
+free_context:
+	free_percpu(pmu->cpu_pmu_context);
+
 free_dev:
 	if (pmu->dev && pmu->dev != PMU_NULL_DEV) {
 		device_del(pmu->dev);

From c9ce148ea753bef66686460fa3cec6641cdfbb9f Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Sat, 1 Mar 2025 12:45:29 +0100
Subject: [PATCH 0804/1173] ALSA: seq: Avoid module auto-load handling at event
 delivery

snd_seq_client_use_ptr() is supposed to return the snd_seq_client
object for the given client ID, and it tries to handle the module
auto-loading when no matching object is found.  Although the module
handling is performed only conditionally with "!in_interrupt()", this
condition may be fragile, e.g. when the code is called from the ALSA
timer callback where the spinlock is temporarily disabled while the
irq is disabled.  Then his doesn't fit well and spews the error about
sleep from invalid context, as complained recently by syzbot.

Also, in general, handling the module-loading at each time if no
matching object is found is really an overkill.  It can be still
useful when performed at the top-level ioctl or proc reads, but it
shouldn't be done at event delivery at all.

For addressing the issues above, this patch disables the module
handling in snd_seq_client_use_ptr() in normal cases like event
deliveries, but allow only in limited and safe situations.
A new function client_load_and_use_ptr() is used for the cases where
the module loading can be done safely, instead.

Reported-by: syzbot+4cb9fad083898f54c517@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/67c272e5.050a0220.dc10f.0159.GAE@google.com
Cc: <stable@vger.kernel.org>
Link: https://patch.msgid.link/20250301114530.8975-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/seq/seq_clientmgr.c | 46 ++++++++++++++++++++++------------
 1 file changed, 30 insertions(+), 16 deletions(-)

diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c
index cb66ec42a3f8a..706f53e39b53c 100644
--- a/sound/core/seq/seq_clientmgr.c
+++ b/sound/core/seq/seq_clientmgr.c
@@ -106,7 +106,7 @@ static struct snd_seq_client *clientptr(int clientid)
 	return clienttab[clientid];
 }
 
-struct snd_seq_client *snd_seq_client_use_ptr(int clientid)
+static struct snd_seq_client *client_use_ptr(int clientid, bool load_module)
 {
 	unsigned long flags;
 	struct snd_seq_client *client;
@@ -126,7 +126,7 @@ struct snd_seq_client *snd_seq_client_use_ptr(int clientid)
 	}
 	spin_unlock_irqrestore(&clients_lock, flags);
 #ifdef CONFIG_MODULES
-	if (!in_interrupt()) {
+	if (load_module) {
 		static DECLARE_BITMAP(client_requested, SNDRV_SEQ_GLOBAL_CLIENTS);
 		static DECLARE_BITMAP(card_requested, SNDRV_CARDS);
 
@@ -168,6 +168,20 @@ struct snd_seq_client *snd_seq_client_use_ptr(int clientid)
 	return client;
 }
 
+/* get snd_seq_client object for the given id quickly */
+struct snd_seq_client *snd_seq_client_use_ptr(int clientid)
+{
+	return client_use_ptr(clientid, false);
+}
+
+/* get snd_seq_client object for the given id;
+ * if not found, retry after loading the modules
+ */
+static struct snd_seq_client *client_load_and_use_ptr(int clientid)
+{
+	return client_use_ptr(clientid, IS_ENABLED(CONFIG_MODULES));
+}
+
 /* Take refcount and perform ioctl_mutex lock on the given client;
  * used only for OSS sequencer
  * Unlock via snd_seq_client_ioctl_unlock() below
@@ -176,7 +190,7 @@ bool snd_seq_client_ioctl_lock(int clientid)
 {
 	struct snd_seq_client *client;
 
-	client = snd_seq_client_use_ptr(clientid);
+	client = client_load_and_use_ptr(clientid);
 	if (!client)
 		return false;
 	mutex_lock(&client->ioctl_mutex);
@@ -1195,7 +1209,7 @@ static int snd_seq_ioctl_running_mode(struct snd_seq_client *client, void  *arg)
 	int err = 0;
 
 	/* requested client number */
-	cptr = snd_seq_client_use_ptr(info->client);
+	cptr = client_load_and_use_ptr(info->client);
 	if (cptr == NULL)
 		return -ENOENT;		/* don't change !!! */
 
@@ -1257,7 +1271,7 @@ static int snd_seq_ioctl_get_client_info(struct snd_seq_client *client,
 	struct snd_seq_client *cptr;
 
 	/* requested client number */
-	cptr = snd_seq_client_use_ptr(client_info->client);
+	cptr = client_load_and_use_ptr(client_info->client);
 	if (cptr == NULL)
 		return -ENOENT;		/* don't change !!! */
 
@@ -1396,7 +1410,7 @@ static int snd_seq_ioctl_get_port_info(struct snd_seq_client *client, void *arg)
 	struct snd_seq_client *cptr;
 	struct snd_seq_client_port *port;
 
-	cptr = snd_seq_client_use_ptr(info->addr.client);
+	cptr = client_load_and_use_ptr(info->addr.client);
 	if (cptr == NULL)
 		return -ENXIO;
 
@@ -1503,10 +1517,10 @@ static int snd_seq_ioctl_subscribe_port(struct snd_seq_client *client,
 	struct snd_seq_client *receiver = NULL, *sender = NULL;
 	struct snd_seq_client_port *sport = NULL, *dport = NULL;
 
-	receiver = snd_seq_client_use_ptr(subs->dest.client);
+	receiver = client_load_and_use_ptr(subs->dest.client);
 	if (!receiver)
 		goto __end;
-	sender = snd_seq_client_use_ptr(subs->sender.client);
+	sender = client_load_and_use_ptr(subs->sender.client);
 	if (!sender)
 		goto __end;
 	sport = snd_seq_port_use_ptr(sender, subs->sender.port);
@@ -1871,7 +1885,7 @@ static int snd_seq_ioctl_get_client_pool(struct snd_seq_client *client,
 	struct snd_seq_client_pool *info = arg;
 	struct snd_seq_client *cptr;
 
-	cptr = snd_seq_client_use_ptr(info->client);
+	cptr = client_load_and_use_ptr(info->client);
 	if (cptr == NULL)
 		return -ENOENT;
 	memset(info, 0, sizeof(*info));
@@ -1975,7 +1989,7 @@ static int snd_seq_ioctl_get_subscription(struct snd_seq_client *client,
 	struct snd_seq_client_port *sport = NULL;
 
 	result = -EINVAL;
-	sender = snd_seq_client_use_ptr(subs->sender.client);
+	sender = client_load_and_use_ptr(subs->sender.client);
 	if (!sender)
 		goto __end;
 	sport = snd_seq_port_use_ptr(sender, subs->sender.port);
@@ -2006,7 +2020,7 @@ static int snd_seq_ioctl_query_subs(struct snd_seq_client *client, void *arg)
 	struct list_head *p;
 	int i;
 
-	cptr = snd_seq_client_use_ptr(subs->root.client);
+	cptr = client_load_and_use_ptr(subs->root.client);
 	if (!cptr)
 		goto __end;
 	port = snd_seq_port_use_ptr(cptr, subs->root.port);
@@ -2073,7 +2087,7 @@ static int snd_seq_ioctl_query_next_client(struct snd_seq_client *client,
 	if (info->client < 0)
 		info->client = 0;
 	for (; info->client < SNDRV_SEQ_MAX_CLIENTS; info->client++) {
-		cptr = snd_seq_client_use_ptr(info->client);
+		cptr = client_load_and_use_ptr(info->client);
 		if (cptr)
 			break; /* found */
 	}
@@ -2096,7 +2110,7 @@ static int snd_seq_ioctl_query_next_port(struct snd_seq_client *client,
 	struct snd_seq_client *cptr;
 	struct snd_seq_client_port *port = NULL;
 
-	cptr = snd_seq_client_use_ptr(info->addr.client);
+	cptr = client_load_and_use_ptr(info->addr.client);
 	if (cptr == NULL)
 		return -ENXIO;
 
@@ -2193,7 +2207,7 @@ static int snd_seq_ioctl_client_ump_info(struct snd_seq_client *caller,
 		size = sizeof(struct snd_ump_endpoint_info);
 	else
 		size = sizeof(struct snd_ump_block_info);
-	cptr = snd_seq_client_use_ptr(client);
+	cptr = client_load_and_use_ptr(client);
 	if (!cptr)
 		return -ENOENT;
 
@@ -2475,7 +2489,7 @@ int snd_seq_kernel_client_enqueue(int client, struct snd_seq_event *ev,
 	if (check_event_type_and_length(ev))
 		return -EINVAL;
 
-	cptr = snd_seq_client_use_ptr(client);
+	cptr = client_load_and_use_ptr(client);
 	if (cptr == NULL)
 		return -EINVAL;
 	
@@ -2707,7 +2721,7 @@ void snd_seq_info_clients_read(struct snd_info_entry *entry,
 
 	/* list the client table */
 	for (c = 0; c < SNDRV_SEQ_MAX_CLIENTS; c++) {
-		client = snd_seq_client_use_ptr(c);
+		client = client_load_and_use_ptr(c);
 		if (client == NULL)
 			continue;
 		if (client->type == NO_CLIENT) {

From 7a68b55ff39b0a1638acb1694c185d49f6077a0d Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Thu, 27 Feb 2025 18:05:25 +0000
Subject: [PATCH 0805/1173] KVM: arm64: Initialize HCR_EL2.E2H early

On CPUs without FEAT_E2H0, HCR_EL2.E2H is RES1, but may reset to an
UNKNOWN value out of reset and consequently may not read as 1 unless it
has been explicitly initialized.

We handled this for the head.S boot code in commits:

  3944382fa6f22b54 ("arm64: Treat HCR_EL2.E2H as RES1 when ID_AA64MMFR4_EL1.E2H0 is negative")
  b3320142f3db9b3f ("arm64: Fix early handling of FEAT_E2H0 not being implemented")

Unfortunately, we forgot to apply a similar fix to the KVM PSCI entry
points used when relaying CPU_ON, CPU_SUSPEND, and SYSTEM SUSPEND. When
KVM is entered via these entry points, the value of HCR_EL2.E2H may be
consumed before it has been initialized (e.g. by the 'init_el2_state'
macro).

Initialize HCR_EL2.E2H early in these paths such that it can be consumed
reliably. The existing code in head.S is factored out into a new
'init_el2_hcr' macro, and this is used in the __kvm_hyp_init_cpu()
function common to all the relevant PSCI entry points.

For clarity, I've tweaked the assembly used to check whether
ID_AA64MMFR4_EL1.E2H0 is negative. The bitfield is extracted as a signed
value, and this is checked with a signed-greater-or-equal (GE) comparison.

As the hyp code will reconfigure HCR_EL2 later in ___kvm_hyp_init(), all
bits other than E2H are initialized to zero in __kvm_hyp_init_cpu().

Fixes: 3944382fa6f22b54 ("arm64: Treat HCR_EL2.E2H as RES1 when ID_AA64MMFR4_EL1.E2H0 is negative")
Fixes: b3320142f3db9b3f ("arm64: Fix early handling of FEAT_E2H0 not being implemented")
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Ahmed Genidi <ahmed.genidi@arm.com>
Cc: Ben Horgan <ben.horgan@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20250227180526.1204723-2-mark.rutland@arm.com
[maz: fixed LT->GE thinko]
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/el2_setup.h | 26 ++++++++++++++++++++++++++
 arch/arm64/kernel/head.S           | 19 +------------------
 arch/arm64/kvm/hyp/nvhe/hyp-init.S |  8 +++++++-
 3 files changed, 34 insertions(+), 19 deletions(-)

diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h
index 25e1626517500..56034a394b437 100644
--- a/arch/arm64/include/asm/el2_setup.h
+++ b/arch/arm64/include/asm/el2_setup.h
@@ -16,6 +16,32 @@
 #include <asm/sysreg.h>
 #include <linux/irqchip/arm-gic-v3.h>
 
+.macro init_el2_hcr	val
+	mov_q	x0, \val
+
+	/*
+	 * Compliant CPUs advertise their VHE-onlyness with
+	 * ID_AA64MMFR4_EL1.E2H0 < 0. On such CPUs HCR_EL2.E2H is RES1, but it
+	 * can reset into an UNKNOWN state and might not read as 1 until it has
+	 * been initialized explicitly.
+	 *
+	 * Fruity CPUs seem to have HCR_EL2.E2H set to RAO/WI, but
+	 * don't advertise it (they predate this relaxation).
+	 *
+	 * Initalize HCR_EL2.E2H so that later code can rely upon HCR_EL2.E2H
+	 * indicating whether the CPU is running in E2H mode.
+	 */
+	mrs_s	x1, SYS_ID_AA64MMFR4_EL1
+	sbfx	x1, x1, #ID_AA64MMFR4_EL1_E2H0_SHIFT, #ID_AA64MMFR4_EL1_E2H0_WIDTH
+	cmp	x1, #0
+	b.ge	.LnVHE_\@
+
+	orr	x0, x0, #HCR_E2H
+.LnVHE_\@:
+	msr	hcr_el2, x0
+	isb
+.endm
+
 .macro __init_el2_sctlr
 	mov_q	x0, INIT_SCTLR_EL2_MMU_OFF
 	msr	sctlr_el2, x0
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 5ab1970ee5436..2d56459d6c94c 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -298,25 +298,8 @@ SYM_INNER_LABEL(init_el2, SYM_L_LOCAL)
 	msr	sctlr_el2, x0
 	isb
 0:
-	mov_q	x0, HCR_HOST_NVHE_FLAGS
-
-	/*
-	 * Compliant CPUs advertise their VHE-onlyness with
-	 * ID_AA64MMFR4_EL1.E2H0 < 0. HCR_EL2.E2H can be
-	 * RES1 in that case. Publish the E2H bit early so that
-	 * it can be picked up by the init_el2_state macro.
-	 *
-	 * Fruity CPUs seem to have HCR_EL2.E2H set to RAO/WI, but
-	 * don't advertise it (they predate this relaxation).
-	 */
-	mrs_s	x1, SYS_ID_AA64MMFR4_EL1
-	tbz	x1, #(ID_AA64MMFR4_EL1_E2H0_SHIFT + ID_AA64MMFR4_EL1_E2H0_WIDTH - 1), 1f
-
-	orr	x0, x0, #HCR_E2H
-1:
-	msr	hcr_el2, x0
-	isb
 
+	init_el2_hcr	HCR_HOST_NVHE_FLAGS
 	init_el2_state
 
 	/* Hypervisor stub */
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
index fc18662260676..3fb5504a7d7fc 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
@@ -73,8 +73,12 @@ __do_hyp_init:
 	eret
 SYM_CODE_END(__kvm_hyp_init)
 
+/*
+ * Initialize EL2 CPU state to sane values.
+ *
+ * HCR_EL2.E2H must have been initialized already.
+ */
 SYM_CODE_START_LOCAL(__kvm_init_el2_state)
-	/* Initialize EL2 CPU state to sane values. */
 	init_el2_state				// Clobbers x0..x2
 	finalise_el2_state
 	ret
@@ -206,6 +210,8 @@ SYM_CODE_START_LOCAL(__kvm_hyp_init_cpu)
 
 2:	msr	SPsel, #1			// We want to use SP_EL{1,2}
 
+	init_el2_hcr	0
+
 	bl	__kvm_init_el2_state
 
 	__init_el2_nvhe_prepare_eret

From 3855a7b91d42ebf3513b7ccffc44807274978b3d Mon Sep 17 00:00:00 2001
From: Ahmed Genidi <ahmed.genidi@arm.com>
Date: Thu, 27 Feb 2025 18:05:26 +0000
Subject: [PATCH 0806/1173] KVM: arm64: Initialize SCTLR_EL1 in
 __kvm_hyp_init_cpu()

When KVM is in protected mode, host calls to PSCI are proxied via EL2,
and cold entries from CPU_ON, CPU_SUSPEND, and SYSTEM_SUSPEND bounce
through __kvm_hyp_init_cpu() at EL2 before entering the host kernel's
entry point at EL1. While __kvm_hyp_init_cpu() initializes SPSR_EL2 for
the exception return to EL1, it does not initialize SCTLR_EL1.

Due to this, it's possible to enter EL1 with SCTLR_EL1 in an UNKNOWN
state. In practice this has been seen to result in kernel crashes after
CPU_ON as a result of SCTLR_EL1.M being 1 in violation of the initial
core configuration specified by PSCI.

Fix this by initializing SCTLR_EL1 for cold entry to the host kernel.
As it's necessary to write to SCTLR_EL12 in VHE mode, this
initialization is moved into __kvm_host_psci_cpu_entry() where we can
use write_sysreg_el1().

The remnants of the '__init_el2_nvhe_prepare_eret' macro are folded into
its only caller, as this is clearer than having the macro.

Fixes: cdf367192766ad11 ("KVM: arm64: Intercept host's CPU_ON SMCs")
Reported-by: Leo Yan <leo.yan@arm.com>
Signed-off-by: Ahmed Genidi <ahmed.genidi@arm.com>
[ Mark: clarify commit message, handle E2H, move to C, remove macro ]
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Ahmed Genidi <ahmed.genidi@arm.com>
Cc: Ben Horgan <ben.horgan@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Will Deacon <will@kernel.org>
Reviewed-by: Leo Yan <leo.yan@arm.com>
Link: https://lore.kernel.org/r/20250227180526.1204723-3-mark.rutland@arm.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/el2_setup.h   | 5 -----
 arch/arm64/kernel/head.S             | 3 ++-
 arch/arm64/kvm/hyp/nvhe/hyp-init.S   | 2 --
 arch/arm64/kvm/hyp/nvhe/psci-relay.c | 3 +++
 4 files changed, 5 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h
index 56034a394b437..555c613fd2324 100644
--- a/arch/arm64/include/asm/el2_setup.h
+++ b/arch/arm64/include/asm/el2_setup.h
@@ -270,11 +270,6 @@
 .Lskip_gcs_\@:
 .endm
 
-.macro __init_el2_nvhe_prepare_eret
-	mov	x0, #INIT_PSTATE_EL1
-	msr	spsr_el2, x0
-.endm
-
 .macro __init_el2_mpam
 	/* Memory Partitioning And Monitoring: disable EL2 traps */
 	mrs	x1, id_aa64pfr0_el1
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 2d56459d6c94c..2ce73525de2c9 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -322,7 +322,8 @@ SYM_INNER_LABEL(init_el2, SYM_L_LOCAL)
 	msr	sctlr_el1, x1
 	mov	x2, xzr
 3:
-	__init_el2_nvhe_prepare_eret
+	mov	x0, #INIT_PSTATE_EL1
+	msr	spsr_el2, x0
 
 	mov	w0, #BOOT_CPU_MODE_EL2
 	orr	x0, x0, x2
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
index 3fb5504a7d7fc..f8af11189572f 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
@@ -214,8 +214,6 @@ SYM_CODE_START_LOCAL(__kvm_hyp_init_cpu)
 
 	bl	__kvm_init_el2_state
 
-	__init_el2_nvhe_prepare_eret
-
 	/* Enable MMU, set vectors and stack. */
 	mov	x0, x28
 	bl	___kvm_hyp_init			// Clobbers x0..x2
diff --git a/arch/arm64/kvm/hyp/nvhe/psci-relay.c b/arch/arm64/kvm/hyp/nvhe/psci-relay.c
index 9c2ce1e0e99a5..c3e196fb8b18f 100644
--- a/arch/arm64/kvm/hyp/nvhe/psci-relay.c
+++ b/arch/arm64/kvm/hyp/nvhe/psci-relay.c
@@ -218,6 +218,9 @@ asmlinkage void __noreturn __kvm_host_psci_cpu_entry(bool is_cpu_on)
 	if (is_cpu_on)
 		release_boot_args(boot_args);
 
+	write_sysreg_el1(INIT_SCTLR_EL1_MMU_OFF, SYS_SCTLR);
+	write_sysreg(INIT_PSTATE_EL1, SPSR_EL2);
+
 	__host_enter(host_ctxt);
 }
 

From e04918dc594669068f5d59d567d08db531167188 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Sun, 2 Mar 2025 15:18:24 +0800
Subject: [PATCH 0807/1173] cred: Fix RCU warnings in override/revert_creds

Fix RCU warnings in override_creds and revert_creds by turning
the RCU pointer into a normal pointer using rcu_replace_pointer.

These warnings were previously private to the cred code, but due
to the move into the header file they are now polluting unrelated
subsystems.

Fixes: 49dffdfde462 ("cred: Add a light version of override/revert_creds()")
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Link: https://lore.kernel.org/r/Z8QGQGW0IaSklKG7@gondor.apana.org.au
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/cred.h | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/include/linux/cred.h b/include/linux/cred.h
index 0c3c4b16b469c..5658a3bfe803c 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -172,18 +172,12 @@ static inline bool cap_ambient_invariant_ok(const struct cred *cred)
 
 static inline const struct cred *override_creds(const struct cred *override_cred)
 {
-	const struct cred *old = current->cred;
-
-	rcu_assign_pointer(current->cred, override_cred);
-	return old;
+	return rcu_replace_pointer(current->cred, override_cred, 1);
 }
 
 static inline const struct cred *revert_creds(const struct cred *revert_cred)
 {
-	const struct cred *override_cred = current->cred;
-
-	rcu_assign_pointer(current->cred, revert_cred);
-	return override_cred;
+	return rcu_replace_pointer(current->cred, revert_cred, 1);
 }
 
 /**

From 6b6e2e8fd0de3fa7c6f4f8fe6841b01770b2e7bc Mon Sep 17 00:00:00 2001
From: Titus Rwantare <titusr@google.com>
Date: Thu, 27 Feb 2025 22:24:55 +0000
Subject: [PATCH 0808/1173] hwmon: (pmbus) Initialise page count in
 pmbus_identify()

The `pmbus_identify()` function fails to correctly determine the number
of supported pages on PMBus devices. This occurs because `info->pages`
is implicitly zero-initialised, and `pmbus_set_page()` does not perform
writes to the page register if `info->pages` is not yet initialised.
Without this patch, `info->pages` is always set to the maximum after
scanning.

This patch initialises `info->pages` to `PMBUS_PAGES` before the probing
loop, enabling `pmbus_set_page()` writes to make it out onto the bus
correctly identifying the number of pages. `PMBUS_PAGES` seemed like a
reasonable non-zero number because that's the current result of the
identification process.

Testing was done with a PMBus device in QEMU.

Signed-off-by: Titus Rwantare <titusr@google.com>
Fixes: 442aba78728e7 ("hwmon: PMBus device driver")
Link: https://lore.kernel.org/r/20250227222455.2583468-1-titusr@google.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/pmbus/pmbus.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/hwmon/pmbus/pmbus.c b/drivers/hwmon/pmbus/pmbus.c
index 77cf268e7d2d6..920cd5408141a 100644
--- a/drivers/hwmon/pmbus/pmbus.c
+++ b/drivers/hwmon/pmbus/pmbus.c
@@ -103,6 +103,8 @@ static int pmbus_identify(struct i2c_client *client,
 		if (pmbus_check_byte_register(client, 0, PMBUS_PAGE)) {
 			int page;
 
+			info->pages = PMBUS_PAGES;
+
 			for (page = 1; page < PMBUS_PAGES; page++) {
 				if (pmbus_set_page(client, page, 0xff) < 0)
 					break;

From 1c7932d5ae0f5c22fa52ac811b4c427bbca5aff5 Mon Sep 17 00:00:00 2001
From: Maud Spierings <maudspierings@gocontroll.com>
Date: Thu, 27 Feb 2025 13:57:53 +0100
Subject: [PATCH 0809/1173] hwmon: (ntc_thermistor) Fix the ncpXXxh103 sensor
 table

I could not find a single table that has the values currently present in
the table, change it to the actual values that can be found in [1]/[2]
and [3] (page 15 column 2)

[1]: https://www.murata.com/products/productdetail?partno=NCP15XH103F03RC
[2]: https://www.murata.com/products/productdata/8796836626462/NTHCG83.txt?1437969843000
[3]: https://nl.mouser.com/datasheet/2/281/r44e-522712.pdf

Fixes: 54ce3a0d8011 ("hwmon: (ntc_thermistor) Add support for ncpXXxh103")
Signed-off-by: Maud Spierings <maudspierings@gocontroll.com>
Link: https://lore.kernel.org/r/20250227-ntc_thermistor_fixes-v1-3-70fa73200b52@gocontroll.com
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/ntc_thermistor.c | 66 +++++++++++++++++-----------------
 1 file changed, 33 insertions(+), 33 deletions(-)

diff --git a/drivers/hwmon/ntc_thermistor.c b/drivers/hwmon/ntc_thermistor.c
index b5352900463fb..0d29c8f97ba7c 100644
--- a/drivers/hwmon/ntc_thermistor.c
+++ b/drivers/hwmon/ntc_thermistor.c
@@ -181,40 +181,40 @@ static const struct ntc_compensation ncpXXwf104[] = {
 };
 
 static const struct ntc_compensation ncpXXxh103[] = {
-	{ .temp_c	= -40, .ohm	= 247565 },
-	{ .temp_c	= -35, .ohm	= 181742 },
-	{ .temp_c	= -30, .ohm	= 135128 },
-	{ .temp_c	= -25, .ohm	= 101678 },
-	{ .temp_c	= -20, .ohm	= 77373 },
-	{ .temp_c	= -15, .ohm	= 59504 },
-	{ .temp_c	= -10, .ohm	= 46222 },
-	{ .temp_c	= -5, .ohm	= 36244 },
-	{ .temp_c	= 0, .ohm	= 28674 },
-	{ .temp_c	= 5, .ohm	= 22878 },
-	{ .temp_c	= 10, .ohm	= 18399 },
-	{ .temp_c	= 15, .ohm	= 14910 },
-	{ .temp_c	= 20, .ohm	= 12169 },
+	{ .temp_c	= -40, .ohm	= 195652 },
+	{ .temp_c	= -35, .ohm	= 148171 },
+	{ .temp_c	= -30, .ohm	= 113347 },
+	{ .temp_c	= -25, .ohm	= 87559 },
+	{ .temp_c	= -20, .ohm	= 68237 },
+	{ .temp_c	= -15, .ohm	= 53650 },
+	{ .temp_c	= -10, .ohm	= 42506 },
+	{ .temp_c	= -5, .ohm	= 33892 },
+	{ .temp_c	= 0, .ohm	= 27219 },
+	{ .temp_c	= 5, .ohm	= 22021 },
+	{ .temp_c	= 10, .ohm	= 17926 },
+	{ .temp_c	= 15, .ohm	= 14674 },
+	{ .temp_c	= 20, .ohm	= 12081 },
 	{ .temp_c	= 25, .ohm	= 10000 },
-	{ .temp_c	= 30, .ohm	= 8271 },
-	{ .temp_c	= 35, .ohm	= 6883 },
-	{ .temp_c	= 40, .ohm	= 5762 },
-	{ .temp_c	= 45, .ohm	= 4851 },
-	{ .temp_c	= 50, .ohm	= 4105 },
-	{ .temp_c	= 55, .ohm	= 3492 },
-	{ .temp_c	= 60, .ohm	= 2985 },
-	{ .temp_c	= 65, .ohm	= 2563 },
-	{ .temp_c	= 70, .ohm	= 2211 },
-	{ .temp_c	= 75, .ohm	= 1915 },
-	{ .temp_c	= 80, .ohm	= 1666 },
-	{ .temp_c	= 85, .ohm	= 1454 },
-	{ .temp_c	= 90, .ohm	= 1275 },
-	{ .temp_c	= 95, .ohm	= 1121 },
-	{ .temp_c	= 100, .ohm	= 990 },
-	{ .temp_c	= 105, .ohm	= 876 },
-	{ .temp_c	= 110, .ohm	= 779 },
-	{ .temp_c	= 115, .ohm	= 694 },
-	{ .temp_c	= 120, .ohm	= 620 },
-	{ .temp_c	= 125, .ohm	= 556 },
+	{ .temp_c	= 30, .ohm	= 8315 },
+	{ .temp_c	= 35, .ohm	= 6948 },
+	{ .temp_c	= 40, .ohm	= 5834 },
+	{ .temp_c	= 45, .ohm	= 4917 },
+	{ .temp_c	= 50, .ohm	= 4161 },
+	{ .temp_c	= 55, .ohm	= 3535 },
+	{ .temp_c	= 60, .ohm	= 3014 },
+	{ .temp_c	= 65, .ohm	= 2586 },
+	{ .temp_c	= 70, .ohm	= 2228 },
+	{ .temp_c	= 75, .ohm	= 1925 },
+	{ .temp_c	= 80, .ohm	= 1669 },
+	{ .temp_c	= 85, .ohm	= 1452 },
+	{ .temp_c	= 90, .ohm	= 1268 },
+	{ .temp_c	= 95, .ohm	= 1110 },
+	{ .temp_c	= 100, .ohm	= 974 },
+	{ .temp_c	= 105, .ohm	= 858 },
+	{ .temp_c	= 110, .ohm	= 758 },
+	{ .temp_c	= 115, .ohm	= 672 },
+	{ .temp_c	= 120, .ohm	= 596 },
+	{ .temp_c	= 125, .ohm	= 531 },
 };
 
 /*

From e278d5e8aef4c0a1d9a9fa8b8910d713a89aa800 Mon Sep 17 00:00:00 2001
From: Erik Schumacher <erik.schumacher@iris-sensing.com>
Date: Mon, 24 Feb 2025 09:19:04 +0000
Subject: [PATCH 0810/1173] hwmon: (ad7314) Validate leading zero bits and
 return error

Leading zero bits are sent on the bus before the temperature value is
transmitted. If any of these bits are high, the connection might be
unstable or there could be no AD7314 / ADT730x (or compatible) at all.
Return -EIO in that case.

Signed-off-by: Erik Schumacher <erik.schumacher@iris-sensing.com>
Fixes: 4f3a659581cab ("hwmon: AD7314 driver (ported from IIO)")
Link: https://lore.kernel.org/r/24a50c2981a318580aca8f50d23be7987b69ea00.camel@iris-sensing.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/ad7314.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/hwmon/ad7314.c b/drivers/hwmon/ad7314.c
index 7802bbf5f9587..59424103f6348 100644
--- a/drivers/hwmon/ad7314.c
+++ b/drivers/hwmon/ad7314.c
@@ -22,11 +22,13 @@
  */
 #define AD7314_TEMP_MASK		0x7FE0
 #define AD7314_TEMP_SHIFT		5
+#define AD7314_LEADING_ZEROS_MASK	BIT(15)
 
 /*
  * ADT7301 and ADT7302 temperature masks
  */
 #define ADT7301_TEMP_MASK		0x3FFF
+#define ADT7301_LEADING_ZEROS_MASK	(BIT(15) | BIT(14))
 
 enum ad7314_variant {
 	adt7301,
@@ -65,12 +67,20 @@ static ssize_t ad7314_temperature_show(struct device *dev,
 		return ret;
 	switch (spi_get_device_id(chip->spi_dev)->driver_data) {
 	case ad7314:
+		if (ret & AD7314_LEADING_ZEROS_MASK) {
+			/* Invalid read-out, leading zero part is missing */
+			return -EIO;
+		}
 		data = (ret & AD7314_TEMP_MASK) >> AD7314_TEMP_SHIFT;
 		data = sign_extend32(data, 9);
 
 		return sprintf(buf, "%d\n", 250 * data);
 	case adt7301:
 	case adt7302:
+		if (ret & ADT7301_LEADING_ZEROS_MASK) {
+			/* Invalid read-out, leading zero part is missing */
+			return -EIO;
+		}
 		/*
 		 * Documented as a 13 bit twos complement register
 		 * with a sign bit - which is a 14 bit 2's complement

From 7eb172143d5508b4da468ed59ee857c6e5e01da6 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 2 Mar 2025 11:48:20 -0800
Subject: [PATCH 0811/1173] Linux 6.14-rc5

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index 30dab4c8b0120..70bdbf2218fc5 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 14
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc5
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*

From fd5ba38390c59e1c147480ae49b6133c4ac24001 Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Wed, 26 Feb 2025 15:19:18 +0900
Subject: [PATCH 0812/1173] tracing: probe-events: Remove unused
 MAX_ARG_BUF_LEN macro

Commit 18b1e870a496 ("tracing/probes: Add $arg* meta argument for all
function args") introduced MAX_ARG_BUF_LEN but it is not used.
Remove it.

Link: https://lore.kernel.org/all/174055075876.4079315.8805416872155957588.stgit@mhiramat.tok.corp.google.com/

Fixes: 18b1e870a496 ("tracing/probes: Add $arg* meta argument for all function args")
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_probe.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index c47ca002347a7..96792bc4b0924 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -36,7 +36,6 @@
 #define MAX_BTF_ARGS_LEN	128
 #define MAX_DENTRY_ARGS_LEN	256
 #define MAX_STRING_SIZE		PATH_MAX
-#define MAX_ARG_BUF_LEN		(MAX_TRACE_ARGS * MAX_ARG_NAME_LEN)
 
 /* Reserved field names */
 #define FIELD_STRING_IP		"__probe_ip"

From 4dd541f9d9e4d8cdfa9797e68d893b0c27e4c46c Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Sat, 15 Feb 2025 11:01:49 +0900
Subject: [PATCH 0813/1173] MAINTAINERS: update email address in cifs and ksmbd
 entry

Steve mainly checks his email through his gmail address.
I also check issues through another email address.

Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 MAINTAINERS | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 8e0736dc2ee0e..ca11a553d4121 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5775,6 +5775,7 @@ X:	drivers/clk/clkdev.c
 
 COMMON INTERNET FILE SYSTEM CLIENT (CIFS and SMB3)
 M:	Steve French <sfrench@samba.org>
+M:	Steve French <smfrench@gmail.com>
 R:	Paulo Alcantara <pc@manguebit.com> (DFS, global name space)
 R:	Ronnie Sahlberg <ronniesahlberg@gmail.com> (directory leases, sparse files)
 R:	Shyam Prasad N <sprasad@microsoft.com> (multichannel)
@@ -12655,7 +12656,9 @@ F:	tools/testing/selftests/
 
 KERNEL SMB3 SERVER (KSMBD)
 M:	Namjae Jeon <linkinjeon@kernel.org>
+M:	Namjae Jeon <linkinjeon@samba.org>
 M:	Steve French <sfrench@samba.org>
+M:	Steve French <smfrench@gmail.com>
 R:	Sergey Senozhatsky <senozhatsky@chromium.org>
 R:	Tom Talpey <tom@talpey.com>
 L:	linux-cifs@vger.kernel.org

From d6e13e19063db24f94b690159d0633aaf72a0f03 Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Tue, 18 Feb 2025 22:49:50 +0900
Subject: [PATCH 0814/1173] ksmbd: fix out-of-bounds in parse_sec_desc()

If osidoffset, gsidoffset and dacloffset could be greater than smb_ntsd
struct size. If it is smaller, It could cause slab-out-of-bounds.
And when validating sid, It need to check it included subauth array size.

Cc: stable@vger.kernel.org
Reported-by: Norbert Szetei <norbert@doyensec.com>
Tested-by: Norbert Szetei <norbert@doyensec.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/smbacl.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/fs/smb/server/smbacl.c b/fs/smb/server/smbacl.c
index d39d3e553366d..89415b02dd649 100644
--- a/fs/smb/server/smbacl.c
+++ b/fs/smb/server/smbacl.c
@@ -807,6 +807,13 @@ static int parse_sid(struct smb_sid *psid, char *end_of_acl)
 		return -EINVAL;
 	}
 
+	if (!psid->num_subauth)
+		return 0;
+
+	if (psid->num_subauth > SID_MAX_SUB_AUTHORITIES ||
+	    end_of_acl < (char *)psid + 8 + sizeof(__le32) * psid->num_subauth)
+		return -EINVAL;
+
 	return 0;
 }
 
@@ -848,6 +855,9 @@ int parse_sec_desc(struct mnt_idmap *idmap, struct smb_ntsd *pntsd,
 	pntsd->type = cpu_to_le16(DACL_PRESENT);
 
 	if (pntsd->osidoffset) {
+		if (le32_to_cpu(pntsd->osidoffset) < sizeof(struct smb_ntsd))
+			return -EINVAL;
+
 		rc = parse_sid(owner_sid_ptr, end_of_acl);
 		if (rc) {
 			pr_err("%s: Error %d parsing Owner SID\n", __func__, rc);
@@ -863,6 +873,9 @@ int parse_sec_desc(struct mnt_idmap *idmap, struct smb_ntsd *pntsd,
 	}
 
 	if (pntsd->gsidoffset) {
+		if (le32_to_cpu(pntsd->gsidoffset) < sizeof(struct smb_ntsd))
+			return -EINVAL;
+
 		rc = parse_sid(group_sid_ptr, end_of_acl);
 		if (rc) {
 			pr_err("%s: Error %d mapping Owner SID to gid\n",
@@ -884,6 +897,9 @@ int parse_sec_desc(struct mnt_idmap *idmap, struct smb_ntsd *pntsd,
 		pntsd->type |= cpu_to_le16(DACL_PROTECTED);
 
 	if (dacloffset) {
+		if (dacloffset < sizeof(struct smb_ntsd))
+			return -EINVAL;
+
 		parse_dacl(idmap, dacl_ptr, end_of_acl,
 			   owner_sid_ptr, group_sid_ptr, fattr);
 	}

From e2ff19f0b7a30e03516e6eb73b948e27a55bc9d2 Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Fri, 21 Feb 2025 14:16:23 +0900
Subject: [PATCH 0815/1173] ksmbd: fix type confusion via race condition when
 using ipc_msg_send_request

req->handle is allocated using ksmbd_acquire_id(&ipc_ida), based on
ida_alloc. req->handle from ksmbd_ipc_login_request and
FSCTL_PIPE_TRANSCEIVE ioctl can be same and it could lead to type confusion
between messages, resulting in access to unexpected parts of memory after
an incorrect delivery. ksmbd check type of ipc response but missing add
continue to check next ipc reponse.

Cc: stable@vger.kernel.org
Reported-by: Norbert Szetei <norbert@doyensec.com>
Tested-by: Norbert Szetei <norbert@doyensec.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/transport_ipc.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/smb/server/transport_ipc.c b/fs/smb/server/transport_ipc.c
index 0460ebea6ff02..3f185ae60dc51 100644
--- a/fs/smb/server/transport_ipc.c
+++ b/fs/smb/server/transport_ipc.c
@@ -281,6 +281,7 @@ static int handle_response(int type, void *payload, size_t sz)
 		if (entry->type + 1 != type) {
 			pr_err("Waiting for IPC type %d, got %d. Ignore.\n",
 			       entry->type + 1, type);
+			continue;
 		}
 
 		entry->response = kvzalloc(sz, KSMBD_DEFAULT_GFP);

From 84d2d1641b71dec326e8736a749b7ee76a9599fc Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Wed, 26 Feb 2025 15:44:02 +0900
Subject: [PATCH 0816/1173] ksmbd: fix use-after-free in smb2_lock

If smb_lock->zero_len has value, ->llist of smb_lock is not delete and
flock is old one. It will cause use-after-free on error handling
routine.

Cc: stable@vger.kernel.org
Reported-by: Norbert Szetei <norbert@doyensec.com>
Tested-by: Norbert Szetei <norbert@doyensec.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/smb2pdu.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index f1efcd0274750..35bed8fc1b970 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -7458,13 +7458,13 @@ int smb2_lock(struct ksmbd_work *work)
 		}
 
 no_check_cl:
+		flock = smb_lock->fl;
+		list_del(&smb_lock->llist);
+
 		if (smb_lock->zero_len) {
 			err = 0;
 			goto skip;
 		}
-
-		flock = smb_lock->fl;
-		list_del(&smb_lock->llist);
 retry:
 		rc = vfs_lock_file(filp, smb_lock->cmd, flock, NULL);
 skip:

From e26e2d2e15daf1ab33e0135caf2304a0cfa2744b Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Thu, 27 Feb 2025 15:49:10 +0900
Subject: [PATCH 0817/1173] ksmbd: fix bug on trap in smb2_lock

If lock count is greater than 1, flags could be old value.
It should be checked with flags of smb_lock, not flags.
It will cause bug-on trap from locks_free_lock in error handling
routine.

Cc: stable@vger.kernel.org
Reported-by: Norbert Szetei <norbert@doyensec.com>
Tested-by: Norbert Szetei <norbert@doyensec.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/smb2pdu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 35bed8fc1b970..c53121538990e 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -7468,7 +7468,7 @@ int smb2_lock(struct ksmbd_work *work)
 retry:
 		rc = vfs_lock_file(filp, smb_lock->cmd, flock, NULL);
 skip:
-		if (flags & SMB2_LOCKFLAG_UNLOCK) {
+		if (smb_lock->flags & SMB2_LOCKFLAG_UNLOCK) {
 			if (!rc) {
 				ksmbd_debug(SMB, "File unlocked\n");
 			} else if (rc == -ENOENT) {

From 62e7dd0a39c2d0d7ff03274c36df971f1b3d2d0d Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Wed, 12 Feb 2025 23:26:09 +0900
Subject: [PATCH 0818/1173] smb: common: change the data type of num_aces to
 le16

2.4.5 in [MS-DTYP].pdf describe the data type of num_aces as le16.

AceCount (2 bytes): An unsigned 16-bit integer that specifies the count
of the number of ACE records in the ACL.

Change it to le16 and add reserved field to smb_acl struct.

Reported-by: Igor Leite Ladessa <igor-ladessa@hotmail.com>
Tested-by: Igor Leite Ladessa <igor-ladessa@hotmail.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifsacl.c | 26 +++++++++++++-------------
 fs/smb/common/smbacl.h  |  3 ++-
 fs/smb/server/smbacl.c  | 31 ++++++++++++++++---------------
 fs/smb/server/smbacl.h  |  2 +-
 4 files changed, 32 insertions(+), 30 deletions(-)

diff --git a/fs/smb/client/cifsacl.c b/fs/smb/client/cifsacl.c
index 699a3f76d0834..7d953208046af 100644
--- a/fs/smb/client/cifsacl.c
+++ b/fs/smb/client/cifsacl.c
@@ -763,7 +763,7 @@ static void parse_dacl(struct smb_acl *pdacl, char *end_of_acl,
 		       struct cifs_fattr *fattr, bool mode_from_special_sid)
 {
 	int i;
-	int num_aces = 0;
+	u16 num_aces = 0;
 	int acl_size;
 	char *acl_base;
 	struct smb_ace **ppace;
@@ -785,7 +785,7 @@ static void parse_dacl(struct smb_acl *pdacl, char *end_of_acl,
 
 	cifs_dbg(NOISY, "DACL revision %d size %d num aces %d\n",
 		 le16_to_cpu(pdacl->revision), le16_to_cpu(pdacl->size),
-		 le32_to_cpu(pdacl->num_aces));
+		 le16_to_cpu(pdacl->num_aces));
 
 	/* reset rwx permissions for user/group/other.
 	   Also, if num_aces is 0 i.e. DACL has no ACEs,
@@ -795,7 +795,7 @@ static void parse_dacl(struct smb_acl *pdacl, char *end_of_acl,
 	acl_base = (char *)pdacl;
 	acl_size = sizeof(struct smb_acl);
 
-	num_aces = le32_to_cpu(pdacl->num_aces);
+	num_aces = le16_to_cpu(pdacl->num_aces);
 	if (num_aces > 0) {
 		umode_t denied_mode = 0;
 
@@ -937,12 +937,12 @@ unsigned int setup_special_user_owner_ACE(struct smb_ace *pntace)
 static void populate_new_aces(char *nacl_base,
 		struct smb_sid *pownersid,
 		struct smb_sid *pgrpsid,
-		__u64 *pnmode, u32 *pnum_aces, u16 *pnsize,
+		__u64 *pnmode, u16 *pnum_aces, u16 *pnsize,
 		bool modefromsid,
 		bool posix)
 {
 	__u64 nmode;
-	u32 num_aces = 0;
+	u16 num_aces = 0;
 	u16 nsize = 0;
 	__u64 user_mode;
 	__u64 group_mode;
@@ -1050,7 +1050,7 @@ static __u16 replace_sids_and_copy_aces(struct smb_acl *pdacl, struct smb_acl *p
 	u16 size = 0;
 	struct smb_ace *pntace = NULL;
 	char *acl_base = NULL;
-	u32 src_num_aces = 0;
+	u16 src_num_aces = 0;
 	u16 nsize = 0;
 	struct smb_ace *pnntace = NULL;
 	char *nacl_base = NULL;
@@ -1058,7 +1058,7 @@ static __u16 replace_sids_and_copy_aces(struct smb_acl *pdacl, struct smb_acl *p
 
 	acl_base = (char *)pdacl;
 	size = sizeof(struct smb_acl);
-	src_num_aces = le32_to_cpu(pdacl->num_aces);
+	src_num_aces = le16_to_cpu(pdacl->num_aces);
 
 	nacl_base = (char *)pndacl;
 	nsize = sizeof(struct smb_acl);
@@ -1090,11 +1090,11 @@ static int set_chmod_dacl(struct smb_acl *pdacl, struct smb_acl *pndacl,
 	u16 size = 0;
 	struct smb_ace *pntace = NULL;
 	char *acl_base = NULL;
-	u32 src_num_aces = 0;
+	u16 src_num_aces = 0;
 	u16 nsize = 0;
 	struct smb_ace *pnntace = NULL;
 	char *nacl_base = NULL;
-	u32 num_aces = 0;
+	u16 num_aces = 0;
 	bool new_aces_set = false;
 
 	/* Assuming that pndacl and pnmode are never NULL */
@@ -1112,7 +1112,7 @@ static int set_chmod_dacl(struct smb_acl *pdacl, struct smb_acl *pndacl,
 
 	acl_base = (char *)pdacl;
 	size = sizeof(struct smb_acl);
-	src_num_aces = le32_to_cpu(pdacl->num_aces);
+	src_num_aces = le16_to_cpu(pdacl->num_aces);
 
 	/* Retain old ACEs which we can retain */
 	for (i = 0; i < src_num_aces; ++i) {
@@ -1158,7 +1158,7 @@ static int set_chmod_dacl(struct smb_acl *pdacl, struct smb_acl *pndacl,
 	}
 
 finalize_dacl:
-	pndacl->num_aces = cpu_to_le32(num_aces);
+	pndacl->num_aces = cpu_to_le16(num_aces);
 	pndacl->size = cpu_to_le16(nsize);
 
 	return 0;
@@ -1293,7 +1293,7 @@ static int build_sec_desc(struct smb_ntsd *pntsd, struct smb_ntsd *pnntsd,
 			dacloffset ? dacl_ptr->revision : cpu_to_le16(ACL_REVISION);
 
 		ndacl_ptr->size = cpu_to_le16(0);
-		ndacl_ptr->num_aces = cpu_to_le32(0);
+		ndacl_ptr->num_aces = cpu_to_le16(0);
 
 		rc = set_chmod_dacl(dacl_ptr, ndacl_ptr, owner_sid_ptr, group_sid_ptr,
 				    pnmode, mode_from_sid, posix);
@@ -1653,7 +1653,7 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 *pnmode,
 			dacl_ptr = (struct smb_acl *)((char *)pntsd + dacloffset);
 			if (mode_from_sid)
 				nsecdesclen +=
-					le32_to_cpu(dacl_ptr->num_aces) * sizeof(struct smb_ace);
+					le16_to_cpu(dacl_ptr->num_aces) * sizeof(struct smb_ace);
 			else /* cifsacl */
 				nsecdesclen += le16_to_cpu(dacl_ptr->size);
 		}
diff --git a/fs/smb/common/smbacl.h b/fs/smb/common/smbacl.h
index 6a60698fc6f0f..a624ec9e4a144 100644
--- a/fs/smb/common/smbacl.h
+++ b/fs/smb/common/smbacl.h
@@ -107,7 +107,8 @@ struct smb_sid {
 struct smb_acl {
 	__le16 revision; /* revision level */
 	__le16 size;
-	__le32 num_aces;
+	__le16 num_aces;
+	__le16 reserved;
 } __attribute__((packed));
 
 struct smb_ace {
diff --git a/fs/smb/server/smbacl.c b/fs/smb/server/smbacl.c
index 89415b02dd649..561f80d3f953e 100644
--- a/fs/smb/server/smbacl.c
+++ b/fs/smb/server/smbacl.c
@@ -333,7 +333,7 @@ void posix_state_to_acl(struct posix_acl_state *state,
 	pace->e_perm = state->other.allow;
 }
 
-int init_acl_state(struct posix_acl_state *state, int cnt)
+int init_acl_state(struct posix_acl_state *state, u16 cnt)
 {
 	int alloc;
 
@@ -368,7 +368,7 @@ static void parse_dacl(struct mnt_idmap *idmap,
 		       struct smb_fattr *fattr)
 {
 	int i, ret;
-	int num_aces = 0;
+	u16 num_aces = 0;
 	unsigned int acl_size;
 	char *acl_base;
 	struct smb_ace **ppace;
@@ -389,12 +389,12 @@ static void parse_dacl(struct mnt_idmap *idmap,
 
 	ksmbd_debug(SMB, "DACL revision %d size %d num aces %d\n",
 		    le16_to_cpu(pdacl->revision), le16_to_cpu(pdacl->size),
-		    le32_to_cpu(pdacl->num_aces));
+		    le16_to_cpu(pdacl->num_aces));
 
 	acl_base = (char *)pdacl;
 	acl_size = sizeof(struct smb_acl);
 
-	num_aces = le32_to_cpu(pdacl->num_aces);
+	num_aces = le16_to_cpu(pdacl->num_aces);
 	if (num_aces <= 0)
 		return;
 
@@ -580,7 +580,7 @@ static void parse_dacl(struct mnt_idmap *idmap,
 
 static void set_posix_acl_entries_dacl(struct mnt_idmap *idmap,
 				       struct smb_ace *pndace,
-				       struct smb_fattr *fattr, u32 *num_aces,
+				       struct smb_fattr *fattr, u16 *num_aces,
 				       u16 *size, u32 nt_aces_num)
 {
 	struct posix_acl_entry *pace;
@@ -701,7 +701,7 @@ static void set_ntacl_dacl(struct mnt_idmap *idmap,
 			   struct smb_fattr *fattr)
 {
 	struct smb_ace *ntace, *pndace;
-	int nt_num_aces = le32_to_cpu(nt_dacl->num_aces), num_aces = 0;
+	u16 nt_num_aces = le16_to_cpu(nt_dacl->num_aces), num_aces = 0;
 	unsigned short size = 0;
 	int i;
 
@@ -728,7 +728,7 @@ static void set_ntacl_dacl(struct mnt_idmap *idmap,
 
 	set_posix_acl_entries_dacl(idmap, pndace, fattr,
 				   &num_aces, &size, nt_num_aces);
-	pndacl->num_aces = cpu_to_le32(num_aces);
+	pndacl->num_aces = cpu_to_le16(num_aces);
 	pndacl->size = cpu_to_le16(le16_to_cpu(pndacl->size) + size);
 }
 
@@ -736,7 +736,7 @@ static void set_mode_dacl(struct mnt_idmap *idmap,
 			  struct smb_acl *pndacl, struct smb_fattr *fattr)
 {
 	struct smb_ace *pace, *pndace;
-	u32 num_aces = 0;
+	u16 num_aces = 0;
 	u16 size = 0, ace_size = 0;
 	uid_t uid;
 	const struct smb_sid *sid;
@@ -792,7 +792,7 @@ static void set_mode_dacl(struct mnt_idmap *idmap,
 				 fattr->cf_mode, 0007);
 
 out:
-	pndacl->num_aces = cpu_to_le32(num_aces);
+	pndacl->num_aces = cpu_to_le16(num_aces);
 	pndacl->size = cpu_to_le16(le16_to_cpu(pndacl->size) + size);
 }
 
@@ -1022,8 +1022,9 @@ int smb_inherit_dacl(struct ksmbd_conn *conn,
 	struct smb_sid owner_sid, group_sid;
 	struct dentry *parent = path->dentry->d_parent;
 	struct mnt_idmap *idmap = mnt_idmap(path->mnt);
-	int inherited_flags = 0, flags = 0, i, ace_cnt = 0, nt_size = 0, pdacl_size;
-	int rc = 0, num_aces, dacloffset, pntsd_type, pntsd_size, acl_len, aces_size;
+	int inherited_flags = 0, flags = 0, i, nt_size = 0, pdacl_size;
+	int rc = 0, dacloffset, pntsd_type, pntsd_size, acl_len, aces_size;
+	u16 num_aces, ace_cnt = 0;
 	char *aces_base;
 	bool is_dir = S_ISDIR(d_inode(path->dentry)->i_mode);
 
@@ -1039,7 +1040,7 @@ int smb_inherit_dacl(struct ksmbd_conn *conn,
 
 	parent_pdacl = (struct smb_acl *)((char *)parent_pntsd + dacloffset);
 	acl_len = pntsd_size - dacloffset;
-	num_aces = le32_to_cpu(parent_pdacl->num_aces);
+	num_aces = le16_to_cpu(parent_pdacl->num_aces);
 	pntsd_type = le16_to_cpu(parent_pntsd->type);
 	pdacl_size = le16_to_cpu(parent_pdacl->size);
 
@@ -1199,7 +1200,7 @@ int smb_inherit_dacl(struct ksmbd_conn *conn,
 			pdacl = (struct smb_acl *)((char *)pntsd + le32_to_cpu(pntsd->dacloffset));
 			pdacl->revision = cpu_to_le16(2);
 			pdacl->size = cpu_to_le16(sizeof(struct smb_acl) + nt_size);
-			pdacl->num_aces = cpu_to_le32(ace_cnt);
+			pdacl->num_aces = cpu_to_le16(ace_cnt);
 			pace = (struct smb_ace *)((char *)pdacl + sizeof(struct smb_acl));
 			memcpy(pace, aces_base, nt_size);
 			pntsd_size += sizeof(struct smb_acl) + nt_size;
@@ -1280,7 +1281,7 @@ int smb_check_perm_dacl(struct ksmbd_conn *conn, const struct path *path,
 
 		ace = (struct smb_ace *)((char *)pdacl + sizeof(struct smb_acl));
 		aces_size = acl_size - sizeof(struct smb_acl);
-		for (i = 0; i < le32_to_cpu(pdacl->num_aces); i++) {
+		for (i = 0; i < le16_to_cpu(pdacl->num_aces); i++) {
 			if (offsetof(struct smb_ace, access_req) > aces_size)
 				break;
 			ace_size = le16_to_cpu(ace->size);
@@ -1301,7 +1302,7 @@ int smb_check_perm_dacl(struct ksmbd_conn *conn, const struct path *path,
 
 	ace = (struct smb_ace *)((char *)pdacl + sizeof(struct smb_acl));
 	aces_size = acl_size - sizeof(struct smb_acl);
-	for (i = 0; i < le32_to_cpu(pdacl->num_aces); i++) {
+	for (i = 0; i < le16_to_cpu(pdacl->num_aces); i++) {
 		if (offsetof(struct smb_ace, access_req) > aces_size)
 			break;
 		ace_size = le16_to_cpu(ace->size);
diff --git a/fs/smb/server/smbacl.h b/fs/smb/server/smbacl.h
index 24ce576fc2924..355adaee39b87 100644
--- a/fs/smb/server/smbacl.h
+++ b/fs/smb/server/smbacl.h
@@ -86,7 +86,7 @@ int parse_sec_desc(struct mnt_idmap *idmap, struct smb_ntsd *pntsd,
 int build_sec_desc(struct mnt_idmap *idmap, struct smb_ntsd *pntsd,
 		   struct smb_ntsd *ppntsd, int ppntsd_size, int addition_info,
 		   __u32 *secdesclen, struct smb_fattr *fattr);
-int init_acl_state(struct posix_acl_state *state, int cnt);
+int init_acl_state(struct posix_acl_state *state, u16 cnt);
 void free_acl_state(struct posix_acl_state *state);
 void posix_state_to_acl(struct posix_acl_state *state,
 			struct posix_acl_entry *pace);

From 1b8b67f3c5e5169535e26efedd3e422172e2db64 Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Wed, 12 Feb 2025 09:32:11 +0900
Subject: [PATCH 0819/1173] ksmbd: fix incorrect validation for num_aces field
 of smb_acl

parse_dcal() validate num_aces to allocate posix_ace_state_array.

if (num_aces > ULONG_MAX / sizeof(struct smb_ace *))

It is an incorrect validation that we can create an array of size ULONG_MAX.
smb_acl has ->size field to calculate actual number of aces in request buffer
size. Use this to check invalid num_aces.

Reported-by: Igor Leite Ladessa <igor-ladessa@hotmail.com>
Tested-by: Igor Leite Ladessa <igor-ladessa@hotmail.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/smbacl.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/fs/smb/server/smbacl.c b/fs/smb/server/smbacl.c
index 561f80d3f953e..49b128698670a 100644
--- a/fs/smb/server/smbacl.c
+++ b/fs/smb/server/smbacl.c
@@ -398,7 +398,9 @@ static void parse_dacl(struct mnt_idmap *idmap,
 	if (num_aces <= 0)
 		return;
 
-	if (num_aces > ULONG_MAX / sizeof(struct smb_ace *))
+	if (num_aces > (le16_to_cpu(pdacl->size) - sizeof(struct smb_acl)) /
+			(offsetof(struct smb_ace, sid) +
+			 offsetof(struct smb_sid, sub_auth) + sizeof(__le16)))
 		return;
 
 	ret = init_acl_state(&acl_state, num_aces);
@@ -432,6 +434,7 @@ static void parse_dacl(struct mnt_idmap *idmap,
 			offsetof(struct smb_sid, sub_auth);
 
 		if (end_of_acl - acl_base < acl_size ||
+		    ppace[i]->sid.num_subauth == 0 ||
 		    ppace[i]->sid.num_subauth > SID_MAX_SUB_AUTHORITIES ||
 		    (end_of_acl - acl_base <
 		     acl_size + sizeof(__le32) * ppace[i]->sid.num_subauth) ||

From aa2a739a75ab6f24ef72fb3fdb9192c081eacf06 Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Wed, 12 Feb 2025 09:37:57 +0900
Subject: [PATCH 0820/1173] cifs: fix incorrect validation for num_aces field
 of smb_acl

parse_dcal() validate num_aces to allocate ace array.

f (num_aces > ULONG_MAX / sizeof(struct smb_ace *))

It is an incorrect validation that we can create an array of size ULONG_MAX.
smb_acl has ->size field to calculate actual number of aces in response buffer
size. Use this to check invalid num_aces.

Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifsacl.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/fs/smb/client/cifsacl.c b/fs/smb/client/cifsacl.c
index 7d953208046af..64bd68f750f84 100644
--- a/fs/smb/client/cifsacl.c
+++ b/fs/smb/client/cifsacl.c
@@ -778,7 +778,8 @@ static void parse_dacl(struct smb_acl *pdacl, char *end_of_acl,
 	}
 
 	/* validate that we do not go past end of acl */
-	if (end_of_acl < (char *)pdacl + le16_to_cpu(pdacl->size)) {
+	if (end_of_acl < (char *)pdacl + sizeof(struct smb_acl) ||
+	    end_of_acl < (char *)pdacl + le16_to_cpu(pdacl->size)) {
 		cifs_dbg(VFS, "ACL too small to parse DACL\n");
 		return;
 	}
@@ -799,8 +800,11 @@ static void parse_dacl(struct smb_acl *pdacl, char *end_of_acl,
 	if (num_aces > 0) {
 		umode_t denied_mode = 0;
 
-		if (num_aces > ULONG_MAX / sizeof(struct smb_ace *))
+		if (num_aces > (le16_to_cpu(pdacl->size) - sizeof(struct smb_acl)) /
+				(offsetof(struct smb_ace, sid) +
+				 offsetof(struct smb_sid, sub_auth) + sizeof(__le16)))
 			return;
+
 		ppace = kmalloc_array(num_aces, sizeof(struct smb_ace *),
 				      GFP_KERNEL);
 		if (!ppace)

From f603b159231b0c58f0c27ab39348534063d38223 Mon Sep 17 00:00:00 2001
From: Kailang Yang <kailang@realtek.com>
Date: Mon, 3 Mar 2025 14:56:10 +0800
Subject: [PATCH 0821/1173] ALSA: hda/realtek - add supported Mic Mute LED for
 Lenovo platform

Support Mic Mute LED for ThinkCentre M series.

Signed-off-by: Kailang Yang <kailang@realtek.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/c211a2702f1f411e86bd7420d7eebc03@realtek.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index d58743b955f81..ebf54ef5877a4 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -5053,6 +5053,16 @@ static void alc269_fixup_hp_line1_mic1_led(struct hda_codec *codec,
 	}
 }
 
+static void alc233_fixup_lenovo_low_en_micmute_led(struct hda_codec *codec,
+				const struct hda_fixup *fix, int action)
+{
+	struct alc_spec *spec = codec->spec;
+
+	if (action == HDA_FIXUP_ACT_PRE_PROBE)
+		spec->micmute_led_polarity = 1;
+	alc233_fixup_lenovo_line2_mic_hotkey(codec, fix, action);
+}
+
 static void alc_hp_mute_disable(struct hda_codec *codec, unsigned int delay)
 {
 	if (delay <= 0)
@@ -7621,6 +7631,7 @@ enum {
 	ALC275_FIXUP_DELL_XPS,
 	ALC293_FIXUP_LENOVO_SPK_NOISE,
 	ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY,
+	ALC233_FIXUP_LENOVO_L2MH_LOW_ENLED,
 	ALC255_FIXUP_DELL_SPK_NOISE,
 	ALC225_FIXUP_DISABLE_MIC_VREF,
 	ALC225_FIXUP_DELL1_MIC_NO_PRESENCE,
@@ -8615,6 +8626,10 @@ static const struct hda_fixup alc269_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc233_fixup_lenovo_line2_mic_hotkey,
 	},
+	[ALC233_FIXUP_LENOVO_L2MH_LOW_ENLED] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc233_fixup_lenovo_low_en_micmute_led,
+	},
 	[ALC233_FIXUP_INTEL_NUC8_DMIC] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc_fixup_inv_dmic,
@@ -10906,6 +10921,9 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x3178, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x17aa, 0x31af, "ThinkCentre Station", ALC623_FIXUP_LENOVO_THINKSTATION_P340),
 	SND_PCI_QUIRK(0x17aa, 0x334b, "Lenovo ThinkCentre M70 Gen5", ALC283_FIXUP_HEADSET_MIC),
+	SND_PCI_QUIRK(0x17aa, 0x3384, "ThinkCentre M90a PRO", ALC233_FIXUP_LENOVO_L2MH_LOW_ENLED),
+	SND_PCI_QUIRK(0x17aa, 0x3386, "ThinkCentre M90a Gen6", ALC233_FIXUP_LENOVO_L2MH_LOW_ENLED),
+	SND_PCI_QUIRK(0x17aa, 0x3387, "ThinkCentre M70a Gen6", ALC233_FIXUP_LENOVO_L2MH_LOW_ENLED),
 	SND_PCI_QUIRK(0x17aa, 0x3801, "Lenovo Yoga9 14IAP7", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN),
 	HDA_CODEC_QUIRK(0x17aa, 0x3802, "DuetITL 2021", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS),
 	SND_PCI_QUIRK(0x17aa, 0x3802, "Lenovo Yoga Pro 9 14IRP8", ALC287_FIXUP_TAS2781_I2C),

From 59b348be7597c4a9903cb003c69e37df20c04a30 Mon Sep 17 00:00:00 2001
From: Nikita Zhandarovich <n.zhandarovich@fintech.ru>
Date: Fri, 28 Feb 2025 16:46:57 +0300
Subject: [PATCH 0822/1173] wifi: cfg80211: regulatory: improve invalid hints
 checking
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Syzbot keeps reporting an issue [1] that occurs when erroneous symbols
sent from userspace get through into user_alpha2[] via
regulatory_hint_user() call. Such invalid regulatory hints should be
rejected.

While a sanity check from commit 47caf685a685 ("cfg80211: regulatory:
reject invalid hints") looks to be enough to deter these very cases,
there is a way to get around it due to 2 reasons.

1) The way isalpha() works, symbols other than latin lower and
upper letters may be used to determine a country/domain.
For instance, greek letters will also be considered upper/lower
letters and for such characters isalpha() will return true as well.
However, ISO-3166-1 alpha2 codes should only hold latin
characters.

2) While processing a user regulatory request, between
reg_process_hint_user() and regulatory_hint_user() there happens to
be a call to queue_regulatory_request() which modifies letters in
request->alpha2[] with toupper(). This works fine for latin symbols,
less so for weird letter characters from the second part of _ctype[].

Syzbot triggers a warning in is_user_regdom_saved() by first sending
over an unexpected non-latin letter that gets malformed by toupper()
into a character that ends up failing isalpha() check.

Prevent this by enhancing is_an_alpha2() to ensure that incoming
symbols are latin letters and nothing else.

[1] Syzbot report:
------------[ cut here ]------------
Unexpected user alpha2: A�
WARNING: CPU: 1 PID: 964 at net/wireless/reg.c:442 is_user_regdom_saved net/wireless/reg.c:440 [inline]
WARNING: CPU: 1 PID: 964 at net/wireless/reg.c:442 restore_alpha2 net/wireless/reg.c:3424 [inline]
WARNING: CPU: 1 PID: 964 at net/wireless/reg.c:442 restore_regulatory_settings+0x3c0/0x1e50 net/wireless/reg.c:3516
Modules linked in:
CPU: 1 UID: 0 PID: 964 Comm: kworker/1:2 Not tainted 6.12.0-rc5-syzkaller-00044-gc1e939a21eb1 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/13/2024
Workqueue: events_power_efficient crda_timeout_work
RIP: 0010:is_user_regdom_saved net/wireless/reg.c:440 [inline]
RIP: 0010:restore_alpha2 net/wireless/reg.c:3424 [inline]
RIP: 0010:restore_regulatory_settings+0x3c0/0x1e50 net/wireless/reg.c:3516
...
Call Trace:
 <TASK>
 crda_timeout_work+0x27/0x50 net/wireless/reg.c:542
 process_one_work kernel/workqueue.c:3229 [inline]
 process_scheduled_works+0xa65/0x1850 kernel/workqueue.c:3310
 worker_thread+0x870/0xd30 kernel/workqueue.c:3391
 kthread+0x2f2/0x390 kernel/kthread.c:389
 ret_from_fork+0x4d/0x80 arch/x86/kernel/process.c:147
 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244
 </TASK>

Reported-by: syzbot+e10709ac3c44f3d4e800@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=e10709ac3c44f3d4e800
Fixes: 09d989d179d0 ("cfg80211: add regulatory hint disconnect support")
Cc: stable@kernel.org
Signed-off-by: Nikita Zhandarovich <n.zhandarovich@fintech.ru>
Link: https://patch.msgid.link/20250228134659.1577656-1-n.zhandarovich@fintech.ru
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/reg.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 2dd0533e76605..212e9561aae77 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -407,7 +407,8 @@ static bool is_an_alpha2(const char *alpha2)
 {
 	if (!alpha2)
 		return false;
-	return isalpha(alpha2[0]) && isalpha(alpha2[1]);
+	return isascii(alpha2[0]) && isalpha(alpha2[0]) &&
+	       isascii(alpha2[1]) && isalpha(alpha2[1]);
 }
 
 static bool alpha2_equal(const char *alpha2_x, const char *alpha2_y)

From 487cfd4a8e3dc42d34a759017978a4edaf85fce0 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Thu, 27 Feb 2025 19:45:29 +0000
Subject: [PATCH 0823/1173] xhci: Restrict USB4 tunnel detection for USB3
 devices to Intel hosts

When adding support for USB3-over-USB4 tunnelling detection, a check
for an Intel-specific capability was added. This capability, which
goes by ID 206, is used without any check that we are actually
dealing with an Intel host.

As it turns out, the Cadence XHCI controller *also* exposes an
extended capability numbered 206 (for unknown purposes), but of
course doesn't have the Intel-specific registers that the tunnelling
code is trying to access. Fun follows.

The core of the problems is that the tunnelling code blindly uses
vendor-specific capabilities without any check (the Intel-provided
documentation I have at hand indicates that 192-255 are indeed
vendor-specific).

Restrict the detection code to Intel HW for real, preventing any
further explosion on my (non-Intel) HW.

Cc: stable <stable@kernel.org>
Fixes: 948ce83fbb7df ("xhci: Add USB4 tunnel detection for USB3 devices on Intel hosts")
Signed-off-by: Marc Zyngier <maz@kernel.org>
Acked-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20250227194529.2288718-1-maz@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-hub.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index 9693464c05204..69c278b64084b 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -12,6 +12,7 @@
 #include <linux/slab.h>
 #include <linux/unaligned.h>
 #include <linux/bitfield.h>
+#include <linux/pci.h>
 
 #include "xhci.h"
 #include "xhci-trace.h"
@@ -770,9 +771,16 @@ static int xhci_exit_test_mode(struct xhci_hcd *xhci)
 enum usb_link_tunnel_mode xhci_port_is_tunneled(struct xhci_hcd *xhci,
 						struct xhci_port *port)
 {
+	struct usb_hcd *hcd;
 	void __iomem *base;
 	u32 offset;
 
+	/* Don't try and probe this capability for non-Intel hosts */
+	hcd = xhci_to_hcd(xhci);
+	if (!dev_is_pci(hcd->self.controller) ||
+	    to_pci_dev(hcd->self.controller)->vendor != PCI_VENDOR_ID_INTEL)
+		return USB_LINK_UNKNOWN;
+
 	base = &xhci->cap_regs->hc_capbase;
 	offset = xhci_find_next_ext_cap(base, 0, XHCI_EXT_CAPS_INTEL_SPR_SHADOW);
 

From 8e812e9355a6f14dffd54a33d951ca403b9732f5 Mon Sep 17 00:00:00 2001
From: Prashanth K <prashanth.k@oss.qualcomm.com>
Date: Mon, 24 Feb 2025 14:26:04 +0530
Subject: [PATCH 0824/1173] usb: gadget: Check bmAttributes only if
 configuration is valid

If the USB configuration is not valid, then avoid checking for
bmAttributes to prevent null pointer deference.

Cc: stable <stable@kernel.org>
Fixes: 40e89ff5750f ("usb: gadget: Set self-powered based on MaxPower and bmAttributes")
Signed-off-by: Prashanth K <prashanth.k@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20250224085604.417327-1-prashanth.k@oss.qualcomm.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/composite.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index 4bcf73bae7610..869ad99afb48b 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -1051,7 +1051,7 @@ static int set_config(struct usb_composite_dev *cdev,
 		usb_gadget_set_remote_wakeup(gadget, 0);
 done:
 	if (power > USB_SELF_POWER_VBUS_MAX_DRAW ||
-	    !(c->bmAttributes & USB_CONFIG_ATT_SELFPOWER))
+	    (c && !(c->bmAttributes & USB_CONFIG_ATT_SELFPOWER)))
 		usb_gadget_clear_selfpowered(gadget);
 	else
 		usb_gadget_set_selfpowered(gadget);

From 69c58deec19628c8a686030102176484eb94fed4 Mon Sep 17 00:00:00 2001
From: Badhri Jagan Sridharan <badhri@google.com>
Date: Sun, 16 Feb 2025 22:30:02 +0000
Subject: [PATCH 0825/1173] usb: dwc3: gadget: Prevent irq storm when TH
 re-executes

While commit d325a1de49d6 ("usb: dwc3: gadget: Prevent losing events in
event cache") makes sure that top half(TH) does not end up overwriting the
cached events before processing them when the TH gets invoked more than one
time, returning IRQ_HANDLED results in occasional irq storm where the TH
hogs the CPU. The irq storm can be prevented by the flag before event
handler busy is cleared. Default enable interrupt moderation in all
versions which support them.

ftrace event stub during dwc3 irq storm:
    irq/504_dwc3-1111  ( 1111) [000] .... 70.000866: irq_handler_exit: irq=14 ret=handled
    irq/504_dwc3-1111  ( 1111) [000] .... 70.000872: irq_handler_entry: irq=504 name=dwc3
    irq/504_dwc3-1111  ( 1111) [000] .... 70.000874: irq_handler_exit: irq=504 ret=handled
    irq/504_dwc3-1111  ( 1111) [000] .... 70.000881: irq_handler_entry: irq=504 name=dwc3
    irq/504_dwc3-1111  ( 1111) [000] .... 70.000883: irq_handler_exit: irq=504 ret=handled
    irq/504_dwc3-1111  ( 1111) [000] .... 70.000889: irq_handler_entry: irq=504 name=dwc3
    irq/504_dwc3-1111  ( 1111) [000] .... 70.000892: irq_handler_exit: irq=504 ret=handled
    irq/504_dwc3-1111  ( 1111) [000] .... 70.000898: irq_handler_entry: irq=504 name=dwc3
    irq/504_dwc3-1111  ( 1111) [000] .... 70.000901: irq_handler_exit: irq=504 ret=handled
    irq/504_dwc3-1111  ( 1111) [000] .... 70.000907: irq_handler_entry: irq=504 name=dwc3
    irq/504_dwc3-1111  ( 1111) [000] .... 70.000909: irq_handler_exit: irq=504 ret=handled
    irq/504_dwc3-1111  ( 1111) [000] .... 70.000915: irq_handler_entry: irq=504 name=dwc3
    irq/504_dwc3-1111  ( 1111) [000] .... 70.000918: irq_handler_exit: irq=504 ret=handled
    irq/504_dwc3-1111  ( 1111) [000] .... 70.000924: irq_handler_entry: irq=504 name=dwc3
    irq/504_dwc3-1111  ( 1111) [000] .... 70.000927: irq_handler_exit: irq=504 ret=handled
    irq/504_dwc3-1111  ( 1111) [000] .... 70.000933: irq_handler_entry: irq=504 name=dwc3
    irq/504_dwc3-1111  ( 1111) [000] .... 70.000935: irq_handler_exit: irq=504 ret=handled
    ....

Cc: stable <stable@kernel.org>
Suggested-by: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Fixes: d325a1de49d6 ("usb: dwc3: gadget: Prevent losing events in event cache")
Signed-off-by: Badhri Jagan Sridharan <badhri@google.com>
Acked-by: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Link: https://lore.kernel.org/r/20250216223003.3568039-1-badhri@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/core.c   | 16 ++++++----------
 drivers/usb/dwc3/gadget.c | 10 +++++++---
 2 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index dfa1b5fe48dc4..2c472cb97f6c7 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -1835,8 +1835,6 @@ static void dwc3_get_properties(struct dwc3 *dwc)
 	dwc->tx_thr_num_pkt_prd = tx_thr_num_pkt_prd;
 	dwc->tx_max_burst_prd = tx_max_burst_prd;
 
-	dwc->imod_interval = 0;
-
 	dwc->tx_fifo_resize_max_num = tx_fifo_resize_max_num;
 }
 
@@ -1854,21 +1852,19 @@ static void dwc3_check_params(struct dwc3 *dwc)
 	unsigned int hwparam_gen =
 		DWC3_GHWPARAMS3_SSPHY_IFC(dwc->hwparams.hwparams3);
 
-	/* Check for proper value of imod_interval */
-	if (dwc->imod_interval && !dwc3_has_imod(dwc)) {
-		dev_warn(dwc->dev, "Interrupt moderation not supported\n");
-		dwc->imod_interval = 0;
-	}
-
 	/*
+	 * Enable IMOD for all supporting controllers.
+	 *
+	 * Particularly, DWC_usb3 v3.00a must enable this feature for
+	 * the following reason:
+	 *
 	 * Workaround for STAR 9000961433 which affects only version
 	 * 3.00a of the DWC_usb3 core. This prevents the controller
 	 * interrupt from being masked while handling events. IMOD
 	 * allows us to work around this issue. Enable it for the
 	 * affected version.
 	 */
-	if (!dwc->imod_interval &&
-	    DWC3_VER_IS(DWC3, 300A))
+	if (dwc3_has_imod((dwc)))
 		dwc->imod_interval = 1;
 
 	/* Check the maximum_speed parameter */
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index ddd6b2ce57107..89a4dc8ebf948 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -4501,14 +4501,18 @@ static irqreturn_t dwc3_process_event_buf(struct dwc3_event_buffer *evt)
 	dwc3_writel(dwc->regs, DWC3_GEVNTSIZ(0),
 		    DWC3_GEVNTSIZ_SIZE(evt->length));
 
+	evt->flags &= ~DWC3_EVENT_PENDING;
+	/*
+	 * Add an explicit write memory barrier to make sure that the update of
+	 * clearing DWC3_EVENT_PENDING is observed in dwc3_check_event_buf()
+	 */
+	wmb();
+
 	if (dwc->imod_interval) {
 		dwc3_writel(dwc->regs, DWC3_GEVNTCOUNT(0), DWC3_GEVNTCOUNT_EHB);
 		dwc3_writel(dwc->regs, DWC3_DEV_IMOD(0), dwc->imod_interval);
 	}
 
-	/* Keep the clearing of DWC3_EVENT_PENDING at the end */
-	evt->flags &= ~DWC3_EVENT_PENDING;
-
 	return ret;
 }
 

From b5ea08aa883da05106fcc683d12489a4292d1122 Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Date: Tue, 25 Feb 2025 13:02:46 +0200
Subject: [PATCH 0826/1173] usb: renesas_usbhs: Call clk_put()

Clocks acquired with of_clk_get() need to be freed with clk_put(). Call
clk_put() on priv->clks[0] on error path.

Fixes: 3df0e240caba ("usb: renesas_usbhs: Add multiple clocks management")
Cc: stable <stable@kernel.org>
Reviewed-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Tested-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Signed-off-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Link: https://lore.kernel.org/r/20250225110248.870417-2-claudiu.beznea.uj@bp.renesas.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/renesas_usbhs/common.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/renesas_usbhs/common.c b/drivers/usb/renesas_usbhs/common.c
index 935fc496fe94b..6c7857b66a219 100644
--- a/drivers/usb/renesas_usbhs/common.c
+++ b/drivers/usb/renesas_usbhs/common.c
@@ -312,8 +312,10 @@ static int usbhsc_clk_get(struct device *dev, struct usbhs_priv *priv)
 	priv->clks[1] = of_clk_get(dev_of_node(dev), 1);
 	if (PTR_ERR(priv->clks[1]) == -ENOENT)
 		priv->clks[1] = NULL;
-	else if (IS_ERR(priv->clks[1]))
+	else if (IS_ERR(priv->clks[1])) {
+		clk_put(priv->clks[0]);
 		return PTR_ERR(priv->clks[1]);
+	}
 
 	return 0;
 }

From e0c92440938930e7fa7aa6362780d39cdea34449 Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Date: Tue, 25 Feb 2025 13:02:47 +0200
Subject: [PATCH 0827/1173] usb: renesas_usbhs: Use devm_usb_get_phy()

The gpriv->transceiver is retrieved in probe() through usb_get_phy() but
never released. Use devm_usb_get_phy() to handle this scenario.

This issue was identified through code investigation. No issue was found
without this change.

Fixes: b5a2875605ca ("usb: renesas_usbhs: Allow an OTG PHY driver to provide VBUS")
Cc: stable <stable@kernel.org>
Reviewed-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Tested-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Signed-off-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Link: https://lore.kernel.org/r/20250225110248.870417-3-claudiu.beznea.uj@bp.renesas.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/renesas_usbhs/mod_gadget.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/renesas_usbhs/mod_gadget.c b/drivers/usb/renesas_usbhs/mod_gadget.c
index 105132ae87acb..e8e5723f54122 100644
--- a/drivers/usb/renesas_usbhs/mod_gadget.c
+++ b/drivers/usb/renesas_usbhs/mod_gadget.c
@@ -1094,7 +1094,7 @@ int usbhs_mod_gadget_probe(struct usbhs_priv *priv)
 		goto usbhs_mod_gadget_probe_err_gpriv;
 	}
 
-	gpriv->transceiver = usb_get_phy(USB_PHY_TYPE_UNDEFINED);
+	gpriv->transceiver = devm_usb_get_phy(dev, USB_PHY_TYPE_UNDEFINED);
 	dev_info(dev, "%stransceiver found\n",
 		 !IS_ERR(gpriv->transceiver) ? "" : "no ");
 

From 552ca6b87e3778f3dd5b87842f95138162e16c82 Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Date: Tue, 25 Feb 2025 13:02:48 +0200
Subject: [PATCH 0828/1173] usb: renesas_usbhs: Flush the notify_hotplug_work

When performing continuous unbind/bind operations on the USB drivers
available on the Renesas RZ/G2L SoC, a kernel crash with the message
"Unable to handle kernel NULL pointer dereference at virtual address"
may occur. This issue points to the usbhsc_notify_hotplug() function.

Flush the delayed work to avoid its execution when driver resources are
unavailable.

Fixes: bc57381e6347 ("usb: renesas_usbhs: use delayed_work instead of work_struct")
Cc: stable <stable@kernel.org>
Reviewed-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Tested-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Signed-off-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Link: https://lore.kernel.org/r/20250225110248.870417-4-claudiu.beznea.uj@bp.renesas.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/renesas_usbhs/common.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/usb/renesas_usbhs/common.c b/drivers/usb/renesas_usbhs/common.c
index 6c7857b66a219..4b35ef216125c 100644
--- a/drivers/usb/renesas_usbhs/common.c
+++ b/drivers/usb/renesas_usbhs/common.c
@@ -781,6 +781,8 @@ static void usbhs_remove(struct platform_device *pdev)
 
 	dev_dbg(&pdev->dev, "usb remove\n");
 
+	flush_delayed_work(&priv->notify_hotplug_work);
+
 	/* power off */
 	if (!usbhs_get_dparam(priv, runtime_pwctrl))
 		usbhsc_power_ctrl(priv, 0);

From 2b66ef84d0d2a0ea955b40bd306f5e3abbc5cf9c Mon Sep 17 00:00:00 2001
From: Pawel Laszczak <pawell@cadence.com>
Date: Fri, 28 Feb 2025 07:50:25 +0000
Subject: [PATCH 0829/1173] usb: hub: lack of clearing xHC resources

The xHC resources allocated for USB devices are not released in correct
order after resuming in case when while suspend device was reconnected.

This issue has been detected during the fallowing scenario:
- connect hub HS to root port
- connect LS/FS device to hub port
- wait for enumeration to finish
- force host to suspend
- reconnect hub attached to root port
- wake host

For this scenario during enumeration of USB LS/FS device the Cadence xHC
reports completion error code for xHC commands because the xHC resources
used for devices has not been properly released.
XHCI specification doesn't mention that device can be reset in any order
so, we should not treat this issue as Cadence xHC controller bug.
Similar as during disconnecting in this case the device resources should
be cleared starting form the last usb device in tree toward the root hub.
To fix this issue usbcore driver should call hcd->driver->reset_device
for all USB devices connected to hub which was reconnected while
suspending.

Fixes: 3d82904559f4 ("usb: cdnsp: cdns3 Add main part of Cadence USBSSP DRD Driver")
Cc: stable <stable@kernel.org>
Signed-off-by: Pawel Laszczak <pawell@cadence.com>
Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
Link: https://lore.kernel.org/r/PH7PR07MB953841E38C088678ACDCF6EEDDCC2@PH7PR07MB9538.namprd07.prod.outlook.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/hub.c | 33 +++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index a76bb50b62026..dcba4281ea486 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -6065,6 +6065,36 @@ void usb_hub_cleanup(void)
 	usb_deregister(&hub_driver);
 } /* usb_hub_cleanup() */
 
+/**
+ * hub_hc_release_resources - clear resources used by host controller
+ * @udev: pointer to device being released
+ *
+ * Context: task context, might sleep
+ *
+ * Function releases the host controller resources in correct order before
+ * making any operation on resuming usb device. The host controller resources
+ * allocated for devices in tree should be released starting from the last
+ * usb device in tree toward the root hub. This function is used only during
+ * resuming device when usb device require reinitialization – that is, when
+ * flag udev->reset_resume is set.
+ *
+ * This call is synchronous, and may not be used in an interrupt context.
+ */
+static void hub_hc_release_resources(struct usb_device *udev)
+{
+	struct usb_hub *hub = usb_hub_to_struct_hub(udev);
+	struct usb_hcd *hcd = bus_to_hcd(udev->bus);
+	int i;
+
+	/* Release up resources for all children before this device */
+	for (i = 0; i < udev->maxchild; i++)
+		if (hub->ports[i]->child)
+			hub_hc_release_resources(hub->ports[i]->child);
+
+	if (hcd->driver->reset_device)
+		hcd->driver->reset_device(hcd, udev);
+}
+
 /**
  * usb_reset_and_verify_device - perform a USB port reset to reinitialize a device
  * @udev: device to reset (not in SUSPENDED or NOTATTACHED state)
@@ -6129,6 +6159,9 @@ static int usb_reset_and_verify_device(struct usb_device *udev)
 	bos = udev->bos;
 	udev->bos = NULL;
 
+	if (udev->reset_resume)
+		hub_hc_release_resources(udev);
+
 	mutex_lock(hcd->address0_mutex);
 
 	for (i = 0; i < PORT_INIT_TRIES; ++i) {

From 73e8079be9e7ae5ed197d074e0ba6c43674c52f7 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 3 Mar 2025 10:21:47 +0100
Subject: [PATCH 0830/1173] x86/ibt: Make cfi_bhi a constant for FINEIBT_BHI=n

Robot yielded a .config that tripped:

  vmlinux.o: warning: objtool: do_jit+0x276: relocation to !ENDBR: .noinstr.text+0x6a60

This is the result of using __bhi_args[1] in unreachable code; make
sure the compiler is able to determine this is unreachable and trigger
DCE.

Closes: https://lore.kernel.org/oe-kbuild-all/202503030704.H9KFysNS-lkp@intel.com/
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250303094911.GL5880@noisy.programming.kicks-ass.net
---
 arch/x86/include/asm/cfi.h    | 5 +++++
 arch/x86/kernel/alternative.c | 7 +++++++
 2 files changed, 12 insertions(+)

diff --git a/arch/x86/include/asm/cfi.h b/arch/x86/include/asm/cfi.h
index 2f6a01f098b5c..3e51ba4591546 100644
--- a/arch/x86/include/asm/cfi.h
+++ b/arch/x86/include/asm/cfi.h
@@ -100,7 +100,12 @@ enum cfi_mode {
 };
 
 extern enum cfi_mode cfi_mode;
+
+#ifdef CONFIG_FINEIBT_BHI
 extern bool cfi_bhi;
+#else
+#define cfi_bhi (0)
+#endif
 
 typedef u8 bhi_thunk[32];
 extern bhi_thunk __bhi_args[];
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 32e4b801db991..bf82c6f7d6905 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -936,7 +936,10 @@ void __init_or_module apply_seal_endbr(s32 *start, s32 *end) { }
 #endif
 
 enum cfi_mode cfi_mode __ro_after_init = __CFI_DEFAULT;
+
+#ifdef CONFIG_FINEIBT_BHI
 bool cfi_bhi __ro_after_init = false;
+#endif
 
 #ifdef CONFIG_CFI_CLANG
 struct bpf_insn;
@@ -1070,11 +1073,15 @@ static __init int cfi_parse_cmdline(char *str)
 				pr_err("Ignoring paranoid; depends on fineibt.\n");
 			}
 		} else if (!strcmp(str, "bhi")) {
+#ifdef CONFIG_FINEIBT_BHI
 			if (cfi_mode == CFI_FINEIBT) {
 				cfi_bhi = true;
 			} else {
 				pr_err("Ignoring bhi; depends on fineibt.\n");
 			}
+#else
+			pr_err("Ignoring bhi; depends on FINEIBT_BHI=y.\n");
+#endif
 		} else {
 			pr_err("Ignoring unknown cfi option (%s).", str);
 		}

From 3101900218d7b6acbdee8af3e7bcf04acf5bf9ef Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Mon, 3 Mar 2025 00:44:41 +0000
Subject: [PATCH 0831/1173] x86/paravirt: Remove unused
 paravirt_disable_iospace()

The last use of paravirt_disable_iospace() was removed in 2015 by
commit d1c29465b8a5 ("lguest: don't disable iospace.")

Remove it.

Note the comment above it about 'entry.S' is unrelated to this
but stayed when intervening code got deleted.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Juergen Gross <jgross@suse.com>
Link: https://lore.kernel.org/r/20250303004441.250451-1-linux@treblig.org
---
 arch/x86/include/asm/paravirt_types.h |  2 --
 arch/x86/kernel/paravirt.c            | 20 --------------------
 2 files changed, 22 deletions(-)

diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 8b36a9562191c..8e21a1a85e74c 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -242,8 +242,6 @@ extern struct paravirt_patch_template pv_ops;
 
 #define paravirt_ptr(op)	[paravirt_opptr] "m" (pv_ops.op)
 
-int paravirt_disable_iospace(void);
-
 /*
  * This generates an indirect call based on the operation type number.
  *
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 1dc114c810ac9..d0b789d042459 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -90,26 +90,6 @@ void paravirt_set_sched_clock(u64 (*func)(void))
 	static_call_update(pv_sched_clock, func);
 }
 
-/* These are in entry.S */
-static struct resource reserve_ioports = {
-	.start = 0,
-	.end = IO_SPACE_LIMIT,
-	.name = "paravirt-ioport",
-	.flags = IORESOURCE_IO | IORESOURCE_BUSY,
-};
-
-/*
- * Reserve the whole legacy IO space to prevent any legacy drivers
- * from wasting time probing for their hardware.  This is a fairly
- * brute-force approach to disabling all non-virtual drivers.
- *
- * Note that this must be called very early to have any effect.
- */
-int paravirt_disable_iospace(void)
-{
-	return request_resource(&ioport_resource, &reserve_ioports);
-}
-
 #ifdef CONFIG_PARAVIRT_XXL
 static noinstr void pv_native_write_cr2(unsigned long val)
 {

From 7ab02bd36eb444654183ad6c5b15211ddfa32a8f Mon Sep 17 00:00:00 2001
From: "Nysal Jan K.A." <nysal@linux.ibm.com>
Date: Mon, 3 Mar 2025 11:34:50 +0530
Subject: [PATCH 0832/1173] sched/membarrier: Fix redundant load of
 membarrier_state

On architectures where ARCH_HAS_SYNC_CORE_BEFORE_USERMODE
is not selected, sync_core_before_usermode() is a no-op.
In membarrier_mm_sync_core_before_usermode() the compiler does not
eliminate redundant branches and load of mm->membarrier_state
for this case as the atomic_read() cannot be optimized away.

Here's a snippet of the code generated for finish_task_switch() on powerpc
prior to this change:

  1b786c:   ld      r26,2624(r30)   # mm = rq->prev_mm;
  .......
  1b78c8:   cmpdi   cr7,r26,0
  1b78cc:   beq     cr7,1b78e4 <finish_task_switch+0xd0>
  1b78d0:   ld      r9,2312(r13)    # current
  1b78d4:   ld      r9,1888(r9)     # current->mm
  1b78d8:   cmpd    cr7,r26,r9
  1b78dc:   beq     cr7,1b7a70 <finish_task_switch+0x25c>
  1b78e0:   hwsync
  1b78e4:   cmplwi  cr7,r27,128
  .......
  1b7a70:   lwz     r9,176(r26)     # atomic_read(&mm->membarrier_state)
  1b7a74:   b       1b78e0 <finish_task_switch+0xcc>

This was found while analyzing "perf c2c" reports on kernels prior
to commit c1753fd02a00 ("mm: move mm_count into its own cache line")
where mm_count was false sharing with membarrier_state.

There is a minor improvement in the size of finish_task_switch().
The following are results from bloat-o-meter for ppc64le:

  GCC 7.5.0
  ---------
  add/remove: 0/0 grow/shrink: 0/1 up/down: 0/-32 (-32)
  Function                                     old     new   delta
  finish_task_switch                           884     852     -32

  GCC 12.2.1
  ----------
  add/remove: 0/0 grow/shrink: 0/1 up/down: 0/-32 (-32)
  Function                                     old     new   delta
  finish_task_switch.isra                      852     820     -32

  LLVM 17.0.6
  -----------
  add/remove: 0/0 grow/shrink: 0/2 up/down: 0/-36 (-36)
  Function                                     old     new   delta
  rt_mutex_schedule                            120     104     -16
  finish_task_switch                           792     772     -20

Results on aarch64:

  GCC 14.1.1
  ----------
  add/remove: 0/2 grow/shrink: 1/1 up/down: 4/-60 (-56)
  Function                                     old     new   delta
  get_nohz_timer_target                        352     356      +4
  e843419@0b02_0000d7e7_408                      8       -      -8
  e843419@01bb_000021d2_868                      8       -      -8
  finish_task_switch.isra                      592     548     -44

Signed-off-by: Nysal Jan K.A. <nysal@linux.ibm.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Reviewed-by: Michael Ellerman <mpe@ellerman.id.au>
Reviewed-by: Segher Boessenkool <segher@kernel.crashing.org>
Link: https://lore.kernel.org/r/20250303060457.531293-1-nysal@linux.ibm.com
---
 include/linux/sched/mm.h | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 928a626725e69..b13474825130f 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -531,6 +531,13 @@ enum {
 
 static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm)
 {
+	/*
+	 * The atomic_read() below prevents CSE. The following should
+	 * help the compiler generate more efficient code on architectures
+	 * where sync_core_before_usermode() is a no-op.
+	 */
+	if (!IS_ENABLED(CONFIG_ARCH_HAS_SYNC_CORE_BEFORE_USERMODE))
+		return;
 	if (current->mm != mm)
 		return;
 	if (likely(!(atomic_read(&mm->membarrier_state) &

From 1be4e29e94a6be77de3bc210820b74f40814f17a Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Thu, 27 Feb 2025 11:03:06 -0600
Subject: [PATCH 0833/1173] platform/x86/amd/pmf: Initialize and clean up
 `cb_mutex`
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

`cb_mutex` was introduced in commit 9e0894d07072e ("platform/x86/amd/pmf:
Enable Custom BIOS Inputs for PMF-TA") to prevent conccurrent access for
BIOS inputs. It however isn't initialized and so on use it may lead to
a NULL pointer dereference.

Add code to initialize on probe and clean up on destroy.

Reported-by: Yijun Shen <Yijun.Shen@dell.com>
Cc: Richard Gong <richgong@amd.com>
Fixes: 9e0894d07072e ("platform/x86/amd/pmf: Enable Custom BIOS Inputs for PMF-TA")
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Tested-By: Yijun Shen <Yijun_Shen@Dell.com>
Acked-by: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Link: https://lore.kernel.org/r/20250227170308.435862-1-superm1@kernel.org
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/amd/pmf/core.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/platform/x86/amd/pmf/core.c b/drivers/platform/x86/amd/pmf/core.c
index 764cc1fe90ae4..a2cb2d5544f5b 100644
--- a/drivers/platform/x86/amd/pmf/core.c
+++ b/drivers/platform/x86/amd/pmf/core.c
@@ -452,6 +452,7 @@ static int amd_pmf_probe(struct platform_device *pdev)
 
 	mutex_init(&dev->lock);
 	mutex_init(&dev->update_mutex);
+	mutex_init(&dev->cb_mutex);
 
 	apmf_acpi_init(dev);
 	platform_set_drvdata(pdev, dev);
@@ -477,6 +478,7 @@ static void amd_pmf_remove(struct platform_device *pdev)
 	amd_pmf_dbgfs_unregister(dev);
 	mutex_destroy(&dev->lock);
 	mutex_destroy(&dev->update_mutex);
+	mutex_destroy(&dev->cb_mutex);
 	kfree(dev->buf);
 }
 

From 010c4a461c1dbf3fa75ddea8df018a6128b700c6 Mon Sep 17 00:00:00 2001
From: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Date: Fri, 28 Feb 2025 18:35:43 -0800
Subject: [PATCH 0834/1173] x86/speculation: Simplify and make CALL_NOSPEC
 consistent

CALL_NOSPEC macro is used to generate Spectre-v2 mitigation friendly
indirect branches. At compile time the macro defaults to indirect branch,
and at runtime those can be patched to thunk based mitigations.

This approach is opposite of what is done for the rest of the kernel, where
the compile time default is to replace indirect calls with retpoline thunk
calls.

Make CALL_NOSPEC consistent with the rest of the kernel, default to
retpoline thunk at compile time when CONFIG_MITIGATION_RETPOLINE is
enabled.

Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Andrew Cooper <andrew.cooper3@citrix.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250228-call-nospec-v3-1-96599fed0f33@linux.intel.com
---
 arch/x86/include/asm/nospec-branch.h | 15 +++++----------
 1 file changed, 5 insertions(+), 10 deletions(-)

diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 7e8bf78c03d5d..1e6b915ce9564 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -424,16 +424,11 @@ static inline void call_depth_return_thunk(void) {}
  * Inline asm uses the %V modifier which is only in newer GCC
  * which is ensured when CONFIG_MITIGATION_RETPOLINE is defined.
  */
-# define CALL_NOSPEC						\
-	ALTERNATIVE_2(						\
-	ANNOTATE_RETPOLINE_SAFE					\
-	"call *%[thunk_target]\n",				\
-	"call __x86_indirect_thunk_%V[thunk_target]\n",		\
-	X86_FEATURE_RETPOLINE,					\
-	"lfence;\n"						\
-	ANNOTATE_RETPOLINE_SAFE					\
-	"call *%[thunk_target]\n",				\
-	X86_FEATURE_RETPOLINE_LFENCE)
+#ifdef CONFIG_MITIGATION_RETPOLINE
+#define CALL_NOSPEC	"call __x86_indirect_thunk_%V[thunk_target]\n"
+#else
+#define CALL_NOSPEC	"call *%[thunk_target]\n"
+#endif
 
 # define THUNK_TARGET(addr) [thunk_target] "r" (addr)
 

From 9af9ad85ac44cb754e526d468c3006b48db5dfd8 Mon Sep 17 00:00:00 2001
From: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Date: Fri, 28 Feb 2025 18:35:58 -0800
Subject: [PATCH 0835/1173] x86/speculation: Add a conditional CS prefix to
 CALL_NOSPEC

Retpoline mitigation for spectre-v2 uses thunks for indirect branches. To
support this mitigation compilers add a CS prefix with
-mindirect-branch-cs-prefix. For an indirect branch in asm, this needs to
be added manually.

CS prefix is already being added to indirect branches in asm files, but not
in inline asm. Add CS prefix to CALL_NOSPEC for inline asm as well. There
is no JMP_NOSPEC for inline asm.

Reported-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Andrew Cooper <andrew.cooper3@citrix.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250228-call-nospec-v3-2-96599fed0f33@linux.intel.com
---
 arch/x86/include/asm/nospec-branch.h | 19 +++++++++++++++----
 1 file changed, 15 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 1e6b915ce9564..aee26bb8230f8 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -198,9 +198,8 @@
 .endm
 
 /*
- * Equivalent to -mindirect-branch-cs-prefix; emit the 5 byte jmp/call
- * to the retpoline thunk with a CS prefix when the register requires
- * a RAX prefix byte to encode. Also see apply_retpolines().
+ * Emits a conditional CS prefix that is compatible with
+ * -mindirect-branch-cs-prefix.
  */
 .macro __CS_PREFIX reg:req
 	.irp rs,r8,r9,r10,r11,r12,r13,r14,r15
@@ -420,12 +419,24 @@ static inline void call_depth_return_thunk(void) {}
 
 #ifdef CONFIG_X86_64
 
+/*
+ * Emits a conditional CS prefix that is compatible with
+ * -mindirect-branch-cs-prefix.
+ */
+#define __CS_PREFIX(reg)				\
+	".irp rs,r8,r9,r10,r11,r12,r13,r14,r15\n"	\
+	".ifc \\rs," reg "\n"				\
+	".byte 0x2e\n"					\
+	".endif\n"					\
+	".endr\n"
+
 /*
  * Inline asm uses the %V modifier which is only in newer GCC
  * which is ensured when CONFIG_MITIGATION_RETPOLINE is defined.
  */
 #ifdef CONFIG_MITIGATION_RETPOLINE
-#define CALL_NOSPEC	"call __x86_indirect_thunk_%V[thunk_target]\n"
+#define CALL_NOSPEC	__CS_PREFIX("%V[thunk_target]")	\
+			"call __x86_indirect_thunk_%V[thunk_target]\n"
 #else
 #define CALL_NOSPEC	"call *%[thunk_target]\n"
 #endif

From 40fc7561013914ec08c200bb7a0805643a23e070 Mon Sep 17 00:00:00 2001
From: Mirsad Todorovac <mtodorovac69@gmail.com>
Date: Fri, 1 Nov 2024 12:15:23 +0100
Subject: [PATCH 0836/1173] selftests/x86/syscall: Fix coccinelle WARNING
 recommending the use of ARRAY_SIZE()

Coccinelle gives WARNING recommending the use of ARRAY_SIZE() macro definition
to improve the code readability:

  ./tools/testing/selftests/x86/syscall_numbering.c:316:35-36: WARNING: Use ARRAY_SIZE

Fixes: 15c82d98a0f78 ("selftests/x86/syscall: Update and extend syscall_numbering_64")
Signed-off-by: Mirsad Todorovac <mtodorovac69@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Link: https://lore.kernel.org/r/20241101111523.1293193-2-mtodorovac69@gmail.com
---
 tools/testing/selftests/x86/syscall_numbering.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/x86/syscall_numbering.c b/tools/testing/selftests/x86/syscall_numbering.c
index 991591718bb0a..41c42b7b54a6c 100644
--- a/tools/testing/selftests/x86/syscall_numbering.c
+++ b/tools/testing/selftests/x86/syscall_numbering.c
@@ -25,6 +25,7 @@
 #include <sys/mman.h>
 
 #include <linux/ptrace.h>
+#include "../kselftest.h"
 
 /* Common system call numbers */
 #define SYS_READ	  0
@@ -313,7 +314,7 @@ static void test_syscall_numbering(void)
 	 * The MSB is supposed to be ignored, so we loop over a few
 	 * to test that out.
 	 */
-	for (size_t i = 0; i < sizeof(msbs)/sizeof(msbs[0]); i++) {
+	for (size_t i = 0; i < ARRAY_SIZE(msbs); i++) {
 		int msb = msbs[i];
 		run("Checking system calls with msb = %d (0x%x)\n",
 		    msb, msb);

From 2a08b832712980b9eb0e913d64a42c74fc56319b Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 31 Oct 2024 04:06:16 -0700
Subject: [PATCH 0837/1173] x86/bugs: Use the cpu_smt_possible() helper instead
 of open-coded code

There is a helper function to check if SMT is available. Use this helper
instead of performing the check manually.

The helper function cpu_smt_possible() does exactly the same thing as
was being done manually inside spectre_v2_user_select_mitigation().
Specifically, it returns false if CONFIG_SMP is disabled, otherwise
it checks the cpu_smt_control global variable.

This change improves code consistency and reduces duplication.

No change in functionality intended.

Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Cc: David Kaplan <David.Kaplan@amd.com>
Link: https://lore.kernel.org/r/20241031-x86_bugs_last_v2-v2-1-b7ff1dab840e@debian.org
---
 arch/x86/kernel/cpu/bugs.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 93c437f44c245..346bebff3f6cb 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -1346,16 +1346,11 @@ static void __init
 spectre_v2_user_select_mitigation(void)
 {
 	enum spectre_v2_user_mitigation mode = SPECTRE_V2_USER_NONE;
-	bool smt_possible = IS_ENABLED(CONFIG_SMP);
 	enum spectre_v2_user_cmd cmd;
 
 	if (!boot_cpu_has(X86_FEATURE_IBPB) && !boot_cpu_has(X86_FEATURE_STIBP))
 		return;
 
-	if (cpu_smt_control == CPU_SMT_FORCE_DISABLED ||
-	    cpu_smt_control == CPU_SMT_NOT_SUPPORTED)
-		smt_possible = false;
-
 	cmd = spectre_v2_parse_user_cmdline();
 	switch (cmd) {
 	case SPECTRE_V2_USER_CMD_NONE:
@@ -1416,7 +1411,7 @@ spectre_v2_user_select_mitigation(void)
 	 * so allow for STIBP to be selected in those cases.
 	 */
 	if (!boot_cpu_has(X86_FEATURE_STIBP) ||
-	    !smt_possible ||
+	    !cpu_smt_possible() ||
 	    (spectre_v2_in_eibrs_mode(spectre_v2_enabled) &&
 	     !boot_cpu_has(X86_FEATURE_AUTOIBRS)))
 		return;

From 98fdaeb296f51ef08e727a7cc72e5b5c864c4f4d Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 31 Oct 2024 04:06:17 -0700
Subject: [PATCH 0838/1173] x86/bugs: Make spectre user default depend on
 MITIGATION_SPECTRE_V2

Change the default value of spectre v2 in user mode to respect the
CONFIG_MITIGATION_SPECTRE_V2 config option.

Currently, user mode spectre v2 is set to auto
(SPECTRE_V2_USER_CMD_AUTO) by default, even if
CONFIG_MITIGATION_SPECTRE_V2 is disabled.

Set the spectre_v2 value to auto (SPECTRE_V2_USER_CMD_AUTO) if the
Spectre v2 config (CONFIG_MITIGATION_SPECTRE_V2) is enabled, otherwise
set the value to none (SPECTRE_V2_USER_CMD_NONE).

Important to say the command line argument "spectre_v2_user" overwrites
the default value in both cases.

When CONFIG_MITIGATION_SPECTRE_V2 is not set, users have the flexibility
to opt-in for specific mitigations independently. In this scenario,
setting spectre_v2= will not enable spectre_v2_user=, and command line
options spectre_v2_user and spectre_v2 are independent when
CONFIG_MITIGATION_SPECTRE_V2=n.

Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Acked-by: Josh Poimboeuf <jpoimboe@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: David Kaplan <David.Kaplan@amd.com>
Link: https://lore.kernel.org/r/20241031-x86_bugs_last_v2-v2-2-b7ff1dab840e@debian.org
---
 Documentation/admin-guide/kernel-parameters.txt |  2 ++
 arch/x86/kernel/cpu/bugs.c                      | 10 +++++++---
 2 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index fb8752b42ec85..274b71a6fcf9b 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -6582,6 +6582,8 @@
 
 			Selecting 'on' will also enable the mitigation
 			against user space to user space task attacks.
+			Selecting specific mitigation does not force enable
+			user mitigations.
 
 			Selecting 'off' will disable both the kernel and
 			the user space protections.
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 346bebff3f6cb..4386aa6c69e12 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -1308,9 +1308,13 @@ static __ro_after_init enum spectre_v2_mitigation_cmd spectre_v2_cmd;
 static enum spectre_v2_user_cmd __init
 spectre_v2_parse_user_cmdline(void)
 {
+	enum spectre_v2_user_cmd mode;
 	char arg[20];
 	int ret, i;
 
+	mode = IS_ENABLED(CONFIG_MITIGATION_SPECTRE_V2) ?
+		SPECTRE_V2_USER_CMD_AUTO : SPECTRE_V2_USER_CMD_NONE;
+
 	switch (spectre_v2_cmd) {
 	case SPECTRE_V2_CMD_NONE:
 		return SPECTRE_V2_USER_CMD_NONE;
@@ -1323,7 +1327,7 @@ spectre_v2_parse_user_cmdline(void)
 	ret = cmdline_find_option(boot_command_line, "spectre_v2_user",
 				  arg, sizeof(arg));
 	if (ret < 0)
-		return SPECTRE_V2_USER_CMD_AUTO;
+		return mode;
 
 	for (i = 0; i < ARRAY_SIZE(v2_user_options); i++) {
 		if (match_option(arg, ret, v2_user_options[i].option)) {
@@ -1333,8 +1337,8 @@ spectre_v2_parse_user_cmdline(void)
 		}
 	}
 
-	pr_err("Unknown user space protection option (%s). Switching to AUTO select\n", arg);
-	return SPECTRE_V2_USER_CMD_AUTO;
+	pr_err("Unknown user space protection option (%s). Switching to default\n", arg);
+	return mode;
 }
 
 static inline bool spectre_v2_in_ibrs_mode(enum spectre_v2_mitigation mode)

From df1a1ed5e1bdd9cc13148e0e5549f5ebcf76cf13 Mon Sep 17 00:00:00 2001
From: Brendan King <Brendan.King@imgtec.com>
Date: Wed, 26 Feb 2025 15:42:19 +0000
Subject: [PATCH 0839/1173] drm/imagination: avoid deadlock on fence release

Do scheduler queue fence release processing on a workqueue, rather
than in the release function itself.

Fixes deadlock issues such as the following:

[  607.400437] ============================================
[  607.405755] WARNING: possible recursive locking detected
[  607.415500] --------------------------------------------
[  607.420817] weston:zfq0/24149 is trying to acquire lock:
[  607.426131] ffff000017d041a0 (reservation_ww_class_mutex){+.+.}-{3:3}, at: pvr_gem_object_vunmap+0x40/0xc0 [powervr]
[  607.436728]
               but task is already holding lock:
[  607.442554] ffff000017d105a0 (reservation_ww_class_mutex){+.+.}-{3:3}, at: dma_buf_ioctl+0x250/0x554
[  607.451727]
               other info that might help us debug this:
[  607.458245]  Possible unsafe locking scenario:

[  607.464155]        CPU0
[  607.466601]        ----
[  607.469044]   lock(reservation_ww_class_mutex);
[  607.473584]   lock(reservation_ww_class_mutex);
[  607.478114]
                *** DEADLOCK ***

Cc: stable@vger.kernel.org
Fixes: eaf01ee5ba28 ("drm/imagination: Implement job submission and scheduling")
Signed-off-by: Brendan King <brendan.king@imgtec.com>
Reviewed-by: Matt Coster <matt.coster@imgtec.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250226-fence-release-deadlock-v2-1-6fed2fc1fe88@imgtec.com
Signed-off-by: Matt Coster <matt.coster@imgtec.com>
---
 drivers/gpu/drm/imagination/pvr_queue.c | 13 +++++++++++--
 drivers/gpu/drm/imagination/pvr_queue.h |  4 ++++
 2 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/imagination/pvr_queue.c b/drivers/gpu/drm/imagination/pvr_queue.c
index c4f08432882b1..f3f1c5212df74 100644
--- a/drivers/gpu/drm/imagination/pvr_queue.c
+++ b/drivers/gpu/drm/imagination/pvr_queue.c
@@ -109,12 +109,20 @@ pvr_queue_fence_get_driver_name(struct dma_fence *f)
 	return PVR_DRIVER_NAME;
 }
 
+static void pvr_queue_fence_release_work(struct work_struct *w)
+{
+	struct pvr_queue_fence *fence = container_of(w, struct pvr_queue_fence, release_work);
+
+	pvr_context_put(fence->queue->ctx);
+	dma_fence_free(&fence->base);
+}
+
 static void pvr_queue_fence_release(struct dma_fence *f)
 {
 	struct pvr_queue_fence *fence = container_of(f, struct pvr_queue_fence, base);
+	struct pvr_device *pvr_dev = fence->queue->ctx->pvr_dev;
 
-	pvr_context_put(fence->queue->ctx);
-	dma_fence_free(f);
+	queue_work(pvr_dev->sched_wq, &fence->release_work);
 }
 
 static const char *
@@ -268,6 +276,7 @@ pvr_queue_fence_init(struct dma_fence *f,
 
 	pvr_context_get(queue->ctx);
 	fence->queue = queue;
+	INIT_WORK(&fence->release_work, pvr_queue_fence_release_work);
 	dma_fence_init(&fence->base, fence_ops,
 		       &fence_ctx->lock, fence_ctx->id,
 		       atomic_inc_return(&fence_ctx->seqno));
diff --git a/drivers/gpu/drm/imagination/pvr_queue.h b/drivers/gpu/drm/imagination/pvr_queue.h
index e06ced69302fc..93fe9ac9f58cc 100644
--- a/drivers/gpu/drm/imagination/pvr_queue.h
+++ b/drivers/gpu/drm/imagination/pvr_queue.h
@@ -5,6 +5,7 @@
 #define PVR_QUEUE_H
 
 #include <drm/gpu_scheduler.h>
+#include <linux/workqueue.h>
 
 #include "pvr_cccb.h"
 #include "pvr_device.h"
@@ -63,6 +64,9 @@ struct pvr_queue_fence {
 
 	/** @queue: Queue that created this fence. */
 	struct pvr_queue *queue;
+
+	/** @release_work: Fence release work structure. */
+	struct work_struct release_work;
 };
 
 /**

From a5c4c3ba95a52d66315acdfbaba9bd82ed39c250 Mon Sep 17 00:00:00 2001
From: Brendan King <Brendan.King@imgtec.com>
Date: Wed, 26 Feb 2025 15:43:06 +0000
Subject: [PATCH 0840/1173] drm/imagination: Hold drm_gem_gpuva lock for unmap

Avoid a warning from drm_gem_gpuva_assert_lock_held in drm_gpuva_unlink.

The Imagination driver uses the GEM object reservation lock to protect
the gpuva list, but the GEM object was not always known in the code
paths that ended up calling drm_gpuva_unlink. When the GEM object isn't
known, it is found by calling drm_gpuva_find to lookup the object
associated with a given virtual address range, or by calling
drm_gpuva_find_first when removing all mappings.

Cc: stable@vger.kernel.org
Fixes: 4bc736f890ce ("drm/imagination: vm: make use of GPUVM's drm_exec helper")
Signed-off-by: Brendan King <brendan.king@imgtec.com>
Reviewed-by: Matt Coster <matt.coster@imgtec.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250226-hold-drm_gem_gpuva-lock-for-unmap-v2-1-3fdacded227f@imgtec.com
Signed-off-by: Matt Coster <matt.coster@imgtec.com>
---
 drivers/gpu/drm/imagination/pvr_fw_meta.c |   6 +-
 drivers/gpu/drm/imagination/pvr_vm.c      | 134 +++++++++++++++++-----
 drivers/gpu/drm/imagination/pvr_vm.h      |   3 +
 3 files changed, 115 insertions(+), 28 deletions(-)

diff --git a/drivers/gpu/drm/imagination/pvr_fw_meta.c b/drivers/gpu/drm/imagination/pvr_fw_meta.c
index c39beb70c3173..6d13864851fc2 100644
--- a/drivers/gpu/drm/imagination/pvr_fw_meta.c
+++ b/drivers/gpu/drm/imagination/pvr_fw_meta.c
@@ -527,8 +527,10 @@ pvr_meta_vm_map(struct pvr_device *pvr_dev, struct pvr_fw_object *fw_obj)
 static void
 pvr_meta_vm_unmap(struct pvr_device *pvr_dev, struct pvr_fw_object *fw_obj)
 {
-	pvr_vm_unmap(pvr_dev->kernel_vm_ctx, fw_obj->fw_mm_node.start,
-		     fw_obj->fw_mm_node.size);
+	struct pvr_gem_object *pvr_obj = fw_obj->gem;
+
+	pvr_vm_unmap_obj(pvr_dev->kernel_vm_ctx, pvr_obj,
+			 fw_obj->fw_mm_node.start, fw_obj->fw_mm_node.size);
 }
 
 static bool
diff --git a/drivers/gpu/drm/imagination/pvr_vm.c b/drivers/gpu/drm/imagination/pvr_vm.c
index 363f885a70982..2896fa7501b1c 100644
--- a/drivers/gpu/drm/imagination/pvr_vm.c
+++ b/drivers/gpu/drm/imagination/pvr_vm.c
@@ -293,8 +293,9 @@ pvr_vm_bind_op_map_init(struct pvr_vm_bind_op *bind_op,
 
 static int
 pvr_vm_bind_op_unmap_init(struct pvr_vm_bind_op *bind_op,
-			  struct pvr_vm_context *vm_ctx, u64 device_addr,
-			  u64 size)
+			  struct pvr_vm_context *vm_ctx,
+			  struct pvr_gem_object *pvr_obj,
+			  u64 device_addr, u64 size)
 {
 	int err;
 
@@ -318,6 +319,7 @@ pvr_vm_bind_op_unmap_init(struct pvr_vm_bind_op *bind_op,
 		goto err_bind_op_fini;
 	}
 
+	bind_op->pvr_obj = pvr_obj;
 	bind_op->vm_ctx = vm_ctx;
 	bind_op->device_addr = device_addr;
 	bind_op->size = size;
@@ -597,20 +599,6 @@ pvr_vm_create_context(struct pvr_device *pvr_dev, bool is_userspace_context)
 	return ERR_PTR(err);
 }
 
-/**
- * pvr_vm_unmap_all() - Unmap all mappings associated with a VM context.
- * @vm_ctx: Target VM context.
- *
- * This function ensures that no mappings are left dangling by unmapping them
- * all in order of ascending device-virtual address.
- */
-void
-pvr_vm_unmap_all(struct pvr_vm_context *vm_ctx)
-{
-	WARN_ON(pvr_vm_unmap(vm_ctx, vm_ctx->gpuvm_mgr.mm_start,
-			     vm_ctx->gpuvm_mgr.mm_range));
-}
-
 /**
  * pvr_vm_context_release() - Teardown a VM context.
  * @ref_count: Pointer to reference counter of the VM context.
@@ -703,11 +691,7 @@ pvr_vm_lock_extra(struct drm_gpuvm_exec *vm_exec)
 	struct pvr_vm_bind_op *bind_op = vm_exec->extra.priv;
 	struct pvr_gem_object *pvr_obj = bind_op->pvr_obj;
 
-	/* Unmap operations don't have an object to lock. */
-	if (!pvr_obj)
-		return 0;
-
-	/* Acquire lock on the GEM being mapped. */
+	/* Acquire lock on the GEM object being mapped/unmapped. */
 	return drm_exec_lock_obj(&vm_exec->exec, gem_from_pvr_gem(pvr_obj));
 }
 
@@ -772,8 +756,10 @@ pvr_vm_map(struct pvr_vm_context *vm_ctx, struct pvr_gem_object *pvr_obj,
 }
 
 /**
- * pvr_vm_unmap() - Unmap an already mapped section of device-virtual memory.
+ * pvr_vm_unmap_obj_locked() - Unmap an already mapped section of device-virtual
+ * memory.
  * @vm_ctx: Target VM context.
+ * @pvr_obj: Target PowerVR memory object.
  * @device_addr: Virtual device address at the start of the target mapping.
  * @size: Size of the target mapping.
  *
@@ -784,9 +770,13 @@ pvr_vm_map(struct pvr_vm_context *vm_ctx, struct pvr_gem_object *pvr_obj,
  *  * Any error encountered while performing internal operations required to
  *    destroy the mapping (returned from pvr_vm_gpuva_unmap or
  *    pvr_vm_gpuva_remap).
+ *
+ * The vm_ctx->lock must be held when calling this function.
  */
-int
-pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size)
+static int
+pvr_vm_unmap_obj_locked(struct pvr_vm_context *vm_ctx,
+			struct pvr_gem_object *pvr_obj,
+			u64 device_addr, u64 size)
 {
 	struct pvr_vm_bind_op bind_op = {0};
 	struct drm_gpuvm_exec vm_exec = {
@@ -799,11 +789,13 @@ pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size)
 		},
 	};
 
-	int err = pvr_vm_bind_op_unmap_init(&bind_op, vm_ctx, device_addr,
-					    size);
+	int err = pvr_vm_bind_op_unmap_init(&bind_op, vm_ctx, pvr_obj,
+					    device_addr, size);
 	if (err)
 		return err;
 
+	pvr_gem_object_get(pvr_obj);
+
 	err = drm_gpuvm_exec_lock(&vm_exec);
 	if (err)
 		goto err_cleanup;
@@ -818,6 +810,96 @@ pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size)
 	return err;
 }
 
+/**
+ * pvr_vm_unmap_obj() - Unmap an already mapped section of device-virtual
+ * memory.
+ * @vm_ctx: Target VM context.
+ * @pvr_obj: Target PowerVR memory object.
+ * @device_addr: Virtual device address at the start of the target mapping.
+ * @size: Size of the target mapping.
+ *
+ * Return:
+ *  * 0 on success,
+ *  * Any error encountered by pvr_vm_unmap_obj_locked.
+ */
+int
+pvr_vm_unmap_obj(struct pvr_vm_context *vm_ctx, struct pvr_gem_object *pvr_obj,
+		 u64 device_addr, u64 size)
+{
+	int err;
+
+	mutex_lock(&vm_ctx->lock);
+	err = pvr_vm_unmap_obj_locked(vm_ctx, pvr_obj, device_addr, size);
+	mutex_unlock(&vm_ctx->lock);
+
+	return err;
+}
+
+/**
+ * pvr_vm_unmap() - Unmap an already mapped section of device-virtual memory.
+ * @vm_ctx: Target VM context.
+ * @device_addr: Virtual device address at the start of the target mapping.
+ * @size: Size of the target mapping.
+ *
+ * Return:
+ *  * 0 on success,
+ *  * Any error encountered by drm_gpuva_find,
+ *  * Any error encountered by pvr_vm_unmap_obj_locked.
+ */
+int
+pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size)
+{
+	struct pvr_gem_object *pvr_obj;
+	struct drm_gpuva *va;
+	int err;
+
+	mutex_lock(&vm_ctx->lock);
+
+	va = drm_gpuva_find(&vm_ctx->gpuvm_mgr, device_addr, size);
+	if (va) {
+		pvr_obj = gem_to_pvr_gem(va->gem.obj);
+		err = pvr_vm_unmap_obj_locked(vm_ctx, pvr_obj,
+					      va->va.addr, va->va.range);
+	} else {
+		err = -ENOENT;
+	}
+
+	mutex_unlock(&vm_ctx->lock);
+
+	return err;
+}
+
+/**
+ * pvr_vm_unmap_all() - Unmap all mappings associated with a VM context.
+ * @vm_ctx: Target VM context.
+ *
+ * This function ensures that no mappings are left dangling by unmapping them
+ * all in order of ascending device-virtual address.
+ */
+void
+pvr_vm_unmap_all(struct pvr_vm_context *vm_ctx)
+{
+	mutex_lock(&vm_ctx->lock);
+
+	for (;;) {
+		struct pvr_gem_object *pvr_obj;
+		struct drm_gpuva *va;
+
+		va = drm_gpuva_find_first(&vm_ctx->gpuvm_mgr,
+					  vm_ctx->gpuvm_mgr.mm_start,
+					  vm_ctx->gpuvm_mgr.mm_range);
+		if (!va)
+			break;
+
+		pvr_obj = gem_to_pvr_gem(va->gem.obj);
+
+		WARN_ON(pvr_vm_unmap_obj_locked(vm_ctx, pvr_obj,
+						va->va.addr, va->va.range));
+	}
+
+	mutex_unlock(&vm_ctx->lock);
+}
+
 /* Static data areas are determined by firmware. */
 static const struct drm_pvr_static_data_area static_data_areas[] = {
 	{
diff --git a/drivers/gpu/drm/imagination/pvr_vm.h b/drivers/gpu/drm/imagination/pvr_vm.h
index 79406243617c1..b0528dffa7f1b 100644
--- a/drivers/gpu/drm/imagination/pvr_vm.h
+++ b/drivers/gpu/drm/imagination/pvr_vm.h
@@ -38,6 +38,9 @@ struct pvr_vm_context *pvr_vm_create_context(struct pvr_device *pvr_dev,
 int pvr_vm_map(struct pvr_vm_context *vm_ctx,
 	       struct pvr_gem_object *pvr_obj, u64 pvr_obj_offset,
 	       u64 device_addr, u64 size);
+int pvr_vm_unmap_obj(struct pvr_vm_context *vm_ctx,
+		     struct pvr_gem_object *pvr_obj,
+		     u64 device_addr, u64 size);
 int pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size);
 void pvr_vm_unmap_all(struct pvr_vm_context *vm_ctx);
 

From 68c3de7f707e8a70e0a6d8087cf0fe4a3d5dbfb0 Mon Sep 17 00:00:00 2001
From: Brendan King <Brendan.King@imgtec.com>
Date: Wed, 26 Feb 2025 15:43:54 +0000
Subject: [PATCH 0841/1173] drm/imagination: only init job done fences once

Ensure job done fences are only initialised once.

This fixes a memory manager not clean warning from drm_mm_takedown
on module unload.

Cc: stable@vger.kernel.org
Fixes: eaf01ee5ba28 ("drm/imagination: Implement job submission and scheduling")
Signed-off-by: Brendan King <brendan.king@imgtec.com>
Reviewed-by: Matt Coster <matt.coster@imgtec.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250226-init-done-fences-once-v2-1-c1b2f556b329@imgtec.com
Signed-off-by: Matt Coster <matt.coster@imgtec.com>
---
 drivers/gpu/drm/imagination/pvr_queue.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/imagination/pvr_queue.c b/drivers/gpu/drm/imagination/pvr_queue.c
index f3f1c5212df74..43411be930a21 100644
--- a/drivers/gpu/drm/imagination/pvr_queue.c
+++ b/drivers/gpu/drm/imagination/pvr_queue.c
@@ -313,8 +313,9 @@ pvr_queue_cccb_fence_init(struct dma_fence *fence, struct pvr_queue *queue)
 static void
 pvr_queue_job_fence_init(struct dma_fence *fence, struct pvr_queue *queue)
 {
-	pvr_queue_fence_init(fence, queue, &pvr_queue_job_fence_ops,
-			     &queue->job_fence_ctx);
+	if (!fence->ops)
+		pvr_queue_fence_init(fence, queue, &pvr_queue_job_fence_ops,
+				     &queue->job_fence_ctx);
 }
 
 /**

From 1d2eabb6616433ccaa13927811bdfa205e91ba60 Mon Sep 17 00:00:00 2001
From: Alessio Belle <alessio.belle@imgtec.com>
Date: Fri, 21 Feb 2025 10:49:35 +0000
Subject: [PATCH 0842/1173] drm/imagination: Fix timestamps in firmware traces

When firmware traces are enabled, the firmware dumps 48-bit timestamps
for each trace as two 32-bit values, highest 32 bits (of which only 16
useful) first.

The driver was reassembling them the other way round i.e. interpreting
the first value in memory as the lowest 32 bits, and the second value
as the highest 32 bits (then truncated to 16 bits).

Due to this, firmware trace dumps showed very large timestamps even for
traces recorded shortly after GPU boot. The timestamps in these dumps
would also sometimes jump backwards because of the truncation.

Example trace dumped after loading the powervr module and enabling
firmware traces, where each line is commented with the timestamp value
in hexadecimal to better show both issues:

[93540092739584] : Host Sync Partition marker: 1    // 0x551300000000
[28419798597632] : GPU units deinit                 // 0x19d900000000
[28548647616512] : GPU deinit                       // 0x19f700000000

Update logic to reassemble the timestamps halves in the correct order.

Fixes: cb56cd610866 ("drm/imagination: Add firmware trace to debugfs")
Signed-off-by: Alessio Belle <alessio.belle@imgtec.com>
Reviewed-by: Matt Coster <matt.coster@imgtec.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250221-fix-fw-trace-timestamps-v1-1-dba4aeb030ca@imgtec.com
Signed-off-by: Matt Coster <matt.coster@imgtec.com>
---
 drivers/gpu/drm/imagination/pvr_fw_trace.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/imagination/pvr_fw_trace.c b/drivers/gpu/drm/imagination/pvr_fw_trace.c
index 73707daa4e52d..5dbb636d7d4ff 100644
--- a/drivers/gpu/drm/imagination/pvr_fw_trace.c
+++ b/drivers/gpu/drm/imagination/pvr_fw_trace.c
@@ -333,8 +333,8 @@ static int fw_trace_seq_show(struct seq_file *s, void *v)
 	if (sf_id == ROGUE_FW_SF_LAST)
 		return -EINVAL;
 
-	timestamp = read_fw_trace(trace_seq_data, 1) |
-		((u64)read_fw_trace(trace_seq_data, 2) << 32);
+	timestamp = ((u64)read_fw_trace(trace_seq_data, 1) << 32) |
+		read_fw_trace(trace_seq_data, 2);
 	timestamp = (timestamp & ~ROGUE_FWT_TIMESTAMP_TIME_CLRMSK) >>
 		ROGUE_FWT_TIMESTAMP_TIME_SHIFT;
 

From 2738d06fb4f01145b24c542fb06de538ffc56430 Mon Sep 17 00:00:00 2001
From: Dmitry Panchenko <dmitry@d-systems.ee>
Date: Thu, 20 Feb 2025 17:39:31 +0200
Subject: [PATCH 0843/1173] platform/x86: intel-hid: fix volume buttons on
 Microsoft Surface Go 4 tablet
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Volume buttons on Microsoft Surface Go 4 tablet didn't send any events.
Add Surface Go 4 DMI match to button_array_table to fix this.

Signed-off-by: Dmitry Panchenko <dmitry@d-systems.ee>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20250220154016.3620917-1-dmitry@d-systems.ee
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/intel/hid.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/platform/x86/intel/hid.c b/drivers/platform/x86/intel/hid.c
index 927a2993f6160..88a1a9ff2f344 100644
--- a/drivers/platform/x86/intel/hid.c
+++ b/drivers/platform/x86/intel/hid.c
@@ -139,6 +139,13 @@ static const struct dmi_system_id button_array_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Surface Go 3"),
 		},
 	},
+	{
+		.ident = "Microsoft Surface Go 4",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Microsoft Corporation"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Surface Go 4"),
+		},
+	},
 	{ }
 };
 

From d0d10eaedcb53740883d7e5d53c5e15c879b48fb Mon Sep 17 00:00:00 2001
From: Mingcong Bai <jeffbai@aosc.io>
Date: Sat, 22 Feb 2025 00:48:24 +0800
Subject: [PATCH 0844/1173] platform/x86: thinkpad_acpi: Add battery quirk for
 ThinkPad X131e
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Based on the dmesg messages from the original reporter:

[    4.964073] ACPI: \_SB_.PCI0.LPCB.EC__.HKEY: BCTG evaluated but flagged as error
[    4.964083] thinkpad_acpi: Error probing battery 2

Lenovo ThinkPad X131e also needs this battery quirk.

Reported-by: Fan Yang <804284660@qq.com>
Tested-by: Fan Yang <804284660@qq.com>
Co-developed-by: Xi Ruoyao <xry111@xry111.site>
Signed-off-by: Xi Ruoyao <xry111@xry111.site>
Signed-off-by: Mingcong Bai <jeffbai@aosc.io>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250221164825.77315-1-jeffbai@aosc.io
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/thinkpad_acpi.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index 72a10ed2017ce..1cc91173e0127 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -9972,6 +9972,7 @@ static const struct tpacpi_quirk battery_quirk_table[] __initconst = {
 	 * Individual addressing is broken on models that expose the
 	 * primary battery as BAT1.
 	 */
+	TPACPI_Q_LNV('G', '8', true),       /* ThinkPad X131e */
 	TPACPI_Q_LNV('8', 'F', true),       /* Thinkpad X120e */
 	TPACPI_Q_LNV('J', '7', true),       /* B5400 */
 	TPACPI_Q_LNV('J', 'I', true),       /* Thinkpad 11e */

From f317f38e7fbb15a0d8329289fef8cf034938fb4f Mon Sep 17 00:00:00 2001
From: "David E. Box" <david.e.box@linux.intel.com>
Date: Wed, 26 Feb 2025 13:47:27 -0800
Subject: [PATCH 0845/1173] platform/x86/intel/vsec: Add Diamond Rapids support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add PCI ID for the Diamond Rapids Platforms

Signed-off-by: David E. Box <david.e.box@linux.intel.com>
Link: https://lore.kernel.org/r/20250226214728.1256747-1-david.e.box@linux.intel.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/intel/vsec.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/platform/x86/intel/vsec.c b/drivers/platform/x86/intel/vsec.c
index 8272f1dd0fbc0..db3c031d17572 100644
--- a/drivers/platform/x86/intel/vsec.c
+++ b/drivers/platform/x86/intel/vsec.c
@@ -404,6 +404,11 @@ static const struct intel_vsec_platform_info oobmsm_info = {
 	.caps = VSEC_CAP_TELEMETRY | VSEC_CAP_SDSI | VSEC_CAP_TPMI,
 };
 
+/* DMR OOBMSM info */
+static const struct intel_vsec_platform_info dmr_oobmsm_info = {
+	.caps = VSEC_CAP_TELEMETRY | VSEC_CAP_TPMI,
+};
+
 /* TGL info */
 static const struct intel_vsec_platform_info tgl_info = {
 	.caps = VSEC_CAP_TELEMETRY,
@@ -420,6 +425,7 @@ static const struct intel_vsec_platform_info lnl_info = {
 #define PCI_DEVICE_ID_INTEL_VSEC_MTL_M		0x7d0d
 #define PCI_DEVICE_ID_INTEL_VSEC_MTL_S		0xad0d
 #define PCI_DEVICE_ID_INTEL_VSEC_OOBMSM		0x09a7
+#define PCI_DEVICE_ID_INTEL_VSEC_OOBMSM_DMR	0x09a1
 #define PCI_DEVICE_ID_INTEL_VSEC_RPL		0xa77d
 #define PCI_DEVICE_ID_INTEL_VSEC_TGL		0x9a0d
 #define PCI_DEVICE_ID_INTEL_VSEC_LNL_M		0x647d
@@ -430,6 +436,7 @@ static const struct pci_device_id intel_vsec_pci_ids[] = {
 	{ PCI_DEVICE_DATA(INTEL, VSEC_MTL_M, &mtl_info) },
 	{ PCI_DEVICE_DATA(INTEL, VSEC_MTL_S, &mtl_info) },
 	{ PCI_DEVICE_DATA(INTEL, VSEC_OOBMSM, &oobmsm_info) },
+	{ PCI_DEVICE_DATA(INTEL, VSEC_OOBMSM_DMR, &dmr_oobmsm_info) },
 	{ PCI_DEVICE_DATA(INTEL, VSEC_RPL, &tgl_info) },
 	{ PCI_DEVICE_DATA(INTEL, VSEC_TGL, &tgl_info) },
 	{ PCI_DEVICE_DATA(INTEL, VSEC_LNL_M, &lnl_info) },

From 4e1c520c95849e16f8dfbcacbfd37be5330447b9 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Tue, 29 Oct 2024 22:03:31 +0100
Subject: [PATCH 0846/1173] x86/mm/pat: Fix VM_PAT handling when fork() fails
 in copy_page_range()

If track_pfn_copy() fails, we already added the dst VMA to the maple
tree. As fork() fails, we'll cleanup the maple tree, and stumble over
the dst VMA for which we neither performed any reservation nor copied
any page tables.

Consequently untrack_pfn() will see VM_PAT and try obtaining the
PAT information from the page table -- which fails because the page
table was not copied.

The easiest fix would be to simply clear the VM_PAT flag of the dst VMA
if track_pfn_copy() fails. However, the whole thing is about "simply"
clearing the VM_PAT flag is shaky as well: if we passed track_pfn_copy()
and performed a reservation, but copying the page tables fails, we'll
simply clear the VM_PAT flag, not properly undoing the reservation ...
which is also wrong.

So let's fix it properly: set the VM_PAT flag only if the reservation
succeeded (leaving it clear initially), and undo the reservation if
anything goes wrong while copying the page tables: clearing the VM_PAT
flag after undoing the reservation.

Note that any copied page table entries will get zapped when the VMA will
get removed later, after copy_page_range() succeeded; as VM_PAT is not set
then, we won't try cleaning VM_PAT up once more and untrack_pfn() will be
happy. Note that leaving these page tables in place without a reservation
is not a problem, as we are aborting fork(); this process will never run.

A reproducer can trigger this usually at the first try:

  https://gitlab.com/davidhildenbrand/scratchspace/-/raw/main/reproducers/pat_fork.c

  [   45.239440] WARNING: CPU: 26 PID: 11650 at arch/x86/mm/pat/memtype.c:983 get_pat_info+0xf6/0x110
  [   45.241082] Modules linked in: ...
  [   45.249119] CPU: 26 UID: 0 PID: 11650 Comm: repro3 Not tainted 6.12.0-rc5+ #92
  [   45.250598] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-2.fc40 04/01/2014
  [   45.252181] RIP: 0010:get_pat_info+0xf6/0x110
  ...
  [   45.268513] Call Trace:
  [   45.269003]  <TASK>
  [   45.269425]  ? __warn.cold+0xb7/0x14d
  [   45.270131]  ? get_pat_info+0xf6/0x110
  [   45.270846]  ? report_bug+0xff/0x140
  [   45.271519]  ? handle_bug+0x58/0x90
  [   45.272192]  ? exc_invalid_op+0x17/0x70
  [   45.272935]  ? asm_exc_invalid_op+0x1a/0x20
  [   45.273717]  ? get_pat_info+0xf6/0x110
  [   45.274438]  ? get_pat_info+0x71/0x110
  [   45.275165]  untrack_pfn+0x52/0x110
  [   45.275835]  unmap_single_vma+0xa6/0xe0
  [   45.276549]  unmap_vmas+0x105/0x1f0
  [   45.277256]  exit_mmap+0xf6/0x460
  [   45.277913]  __mmput+0x4b/0x120
  [   45.278512]  copy_process+0x1bf6/0x2aa0
  [   45.279264]  kernel_clone+0xab/0x440
  [   45.279959]  __do_sys_clone+0x66/0x90
  [   45.280650]  do_syscall_64+0x95/0x180

Likely this case was missed in:

  d155df53f310 ("x86/mm/pat: clear VM_PAT if copy_p4d_range failed")

... and instead of undoing the reservation we simply cleared the VM_PAT flag.

Keep the documentation of these functions in include/linux/pgtable.h,
one place is more than sufficient -- we should clean that up for the other
functions like track_pfn_remap/untrack_pfn separately.

Fixes: d155df53f310 ("x86/mm/pat: clear VM_PAT if copy_p4d_range failed")
Fixes: 2ab640379a0a ("x86: PAT: hooks in generic vm code to help archs to track pfnmap regions - v3")
Reported-by: xingwei lee <xrivendell7@gmail.com>
Reported-by: yuxin wang <wang1315768607@163.com>
Reported-by: Marius Fleischer <fleischermarius@gmail.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20241029210331.1339581-1-david@redhat.com
Closes: https://lore.kernel.org/lkml/CAJg=8jwijTP5fre8woS4JVJQ8iUA6v+iNcsOgtj9Zfpc3obDOQ@mail.gmail.com/
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@surriel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Peter Xu <peterx@redhat.com>
---
 arch/x86/mm/pat/memtype.c | 66 +++++++++++++++++++++++++--------------
 include/linux/pgtable.h   | 27 ++++++++++++----
 kernel/fork.c             |  4 +++
 mm/memory.c               |  9 ++----
 4 files changed, 70 insertions(+), 36 deletions(-)

diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c
index feb8cc6a12bf2..3a9e6dd58e2f0 100644
--- a/arch/x86/mm/pat/memtype.c
+++ b/arch/x86/mm/pat/memtype.c
@@ -984,27 +984,54 @@ static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr,
 	return -EINVAL;
 }
 
-/*
- * track_pfn_copy is called when vma that is covering the pfnmap gets
- * copied through copy_page_range().
- *
- * If the vma has a linear pfn mapping for the entire range, we get the prot
- * from pte and reserve the entire vma range with single reserve_pfn_range call.
- */
-int track_pfn_copy(struct vm_area_struct *vma)
+int track_pfn_copy(struct vm_area_struct *dst_vma,
+		struct vm_area_struct *src_vma)
 {
+	const unsigned long vma_size = src_vma->vm_end - src_vma->vm_start;
 	resource_size_t paddr;
-	unsigned long vma_size = vma->vm_end - vma->vm_start;
 	pgprot_t pgprot;
+	int rc;
 
-	if (vma->vm_flags & VM_PAT) {
-		if (get_pat_info(vma, &paddr, &pgprot))
-			return -EINVAL;
-		/* reserve the whole chunk covered by vma. */
-		return reserve_pfn_range(paddr, vma_size, &pgprot, 1);
+	if (!(src_vma->vm_flags & VM_PAT))
+		return 0;
+
+	/*
+	 * Duplicate the PAT information for the dst VMA based on the src
+	 * VMA.
+	 */
+	if (get_pat_info(src_vma, &paddr, &pgprot))
+		return -EINVAL;
+	rc = reserve_pfn_range(paddr, vma_size, &pgprot, 1);
+	if (!rc)
+		/* Reservation for the destination VMA succeeded. */
+		vm_flags_set(dst_vma, VM_PAT);
+	return rc;
+}
+
+void untrack_pfn_copy(struct vm_area_struct *dst_vma,
+		struct vm_area_struct *src_vma)
+{
+	resource_size_t paddr;
+	unsigned long size;
+
+	if (!(dst_vma->vm_flags & VM_PAT))
+		return;
+
+	/*
+	 * As the page tables might not have been copied yet, the PAT
+	 * information is obtained from the src VMA, just like during
+	 * track_pfn_copy().
+	 */
+	if (get_pat_info(src_vma, &paddr, NULL)) {
+		size = src_vma->vm_end - src_vma->vm_start;
+		free_pfn_range(paddr, size);
 	}
 
-	return 0;
+	/*
+	 * Reservation was freed, any copied page tables will get cleaned
+	 * up later, but without getting PAT involved again.
+	 */
+	vm_flags_clear(dst_vma, VM_PAT);
 }
 
 /*
@@ -1095,15 +1122,6 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
 	}
 }
 
-/*
- * untrack_pfn_clear is called if the following situation fits:
- *
- * 1) while mremapping a pfnmap for a new region,  with the old vma after
- * its pfnmap page table has been removed.  The new vma has a new pfnmap
- * to the same pfn & cache type with VM_PAT set.
- * 2) while duplicating vm area, the new vma fails to copy the pgtable from
- * old vma.
- */
 void untrack_pfn_clear(struct vm_area_struct *vma)
 {
 	vm_flags_clear(vma, VM_PAT);
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 94d267d02372e..acf387d199d7b 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -1508,14 +1508,24 @@ static inline void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
 }
 
 /*
- * track_pfn_copy is called when vma that is covering the pfnmap gets
- * copied through copy_page_range().
+ * track_pfn_copy is called when a VM_PFNMAP VMA is about to get the page
+ * tables copied during copy_page_range().
  */
-static inline int track_pfn_copy(struct vm_area_struct *vma)
+static inline int track_pfn_copy(struct vm_area_struct *dst_vma,
+		struct vm_area_struct *src_vma)
 {
 	return 0;
 }
 
+/*
+ * untrack_pfn_copy is called when a VM_PFNMAP VMA failed to copy during
+ * copy_page_range(), but after track_pfn_copy() was already called.
+ */
+static inline void untrack_pfn_copy(struct vm_area_struct *dst_vma,
+		struct vm_area_struct *src_vma)
+{
+}
+
 /*
  * untrack_pfn is called while unmapping a pfnmap for a region.
  * untrack can be called for a specific region indicated by pfn and size or
@@ -1528,8 +1538,10 @@ static inline void untrack_pfn(struct vm_area_struct *vma,
 }
 
 /*
- * untrack_pfn_clear is called while mremapping a pfnmap for a new region
- * or fails to copy pgtable during duplicate vm area.
+ * untrack_pfn_clear is called in the following cases on a VM_PFNMAP VMA:
+ *
+ * 1) During mremap() on the src VMA after the page tables were moved.
+ * 2) During fork() on the dst VMA, immediately after duplicating the src VMA.
  */
 static inline void untrack_pfn_clear(struct vm_area_struct *vma)
 {
@@ -1540,7 +1552,10 @@ extern int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
 			   unsigned long size);
 extern void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
 			     pfn_t pfn);
-extern int track_pfn_copy(struct vm_area_struct *vma);
+extern int track_pfn_copy(struct vm_area_struct *dst_vma,
+		struct vm_area_struct *src_vma);
+extern void untrack_pfn_copy(struct vm_area_struct *dst_vma,
+		struct vm_area_struct *src_vma);
 extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
 			unsigned long size, bool mm_wr_locked);
 extern void untrack_pfn_clear(struct vm_area_struct *vma);
diff --git a/kernel/fork.c b/kernel/fork.c
index 735405a9c5f32..ca2ca3884f763 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -504,6 +504,10 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
 	vma_numab_state_init(new);
 	dup_anon_vma_name(orig, new);
 
+	/* track_pfn_copy() will later take care of copying internal state. */
+	if (unlikely(new->vm_flags & VM_PFNMAP))
+		untrack_pfn_clear(new);
+
 	return new;
 }
 
diff --git a/mm/memory.c b/mm/memory.c
index 539c0f7c6d545..890333c8c8573 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1379,11 +1379,7 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
 		return copy_hugetlb_page_range(dst_mm, src_mm, dst_vma, src_vma);
 
 	if (unlikely(src_vma->vm_flags & VM_PFNMAP)) {
-		/*
-		 * We do not free on error cases below as remove_vma
-		 * gets called on error from higher level routine
-		 */
-		ret = track_pfn_copy(src_vma);
+		ret = track_pfn_copy(dst_vma, src_vma);
 		if (ret)
 			return ret;
 	}
@@ -1420,7 +1416,6 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
 			continue;
 		if (unlikely(copy_p4d_range(dst_vma, src_vma, dst_pgd, src_pgd,
 					    addr, next))) {
-			untrack_pfn_clear(dst_vma);
 			ret = -ENOMEM;
 			break;
 		}
@@ -1430,6 +1425,8 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
 		raw_write_seqcount_end(&src_mm->write_protect_seq);
 		mmu_notifier_invalidate_range_end(&range);
 	}
+	if (ret && unlikely(src_vma->vm_flags & VM_PFNMAP))
+		untrack_pfn_copy(dst_vma, src_vma);
 	return ret;
 }
 

From 172a0f509723fe4741d4b8e9190cf434b18320d8 Mon Sep 17 00:00:00 2001
From: Murad Masimov <m.masimov@mt-integration.ru>
Date: Mon, 3 Mar 2025 13:04:13 +0300
Subject: [PATCH 0847/1173] ALSA: usx2y: validate nrpacks module parameter on
 probe

The module parameter defines number of iso packets per one URB. User is
allowed to set any value to the parameter of type int, which can lead to
various kinds of weird and incorrect behavior like integer overflows,
truncations, etc. Number of packets should be a small non-negative number.

Since this parameter is read-only, its value can be validated on driver
probe.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Murad Masimov <m.masimov@mt-integration.ru>
Link: https://patch.msgid.link/20250303100413.835-1-m.masimov@mt-integration.ru
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/usx2y/usbusx2y.c      | 11 +++++++++++
 sound/usb/usx2y/usbusx2y.h      | 26 ++++++++++++++++++++++++++
 sound/usb/usx2y/usbusx2yaudio.c | 27 ---------------------------
 3 files changed, 37 insertions(+), 27 deletions(-)

diff --git a/sound/usb/usx2y/usbusx2y.c b/sound/usb/usx2y/usbusx2y.c
index 5f81c68fd42b6..5756ff3528a2d 100644
--- a/sound/usb/usx2y/usbusx2y.c
+++ b/sound/usb/usx2y/usbusx2y.c
@@ -151,6 +151,12 @@ static int snd_usx2y_card_used[SNDRV_CARDS];
 static void snd_usx2y_card_private_free(struct snd_card *card);
 static void usx2y_unlinkseq(struct snd_usx2y_async_seq *s);
 
+#ifdef USX2Y_NRPACKS_VARIABLE
+int nrpacks = USX2Y_NRPACKS; /* number of packets per urb */
+module_param(nrpacks, int, 0444);
+MODULE_PARM_DESC(nrpacks, "Number of packets per URB.");
+#endif
+
 /*
  * pipe 4 is used for switching the lamps, setting samplerate, volumes ....
  */
@@ -432,6 +438,11 @@ static int snd_usx2y_probe(struct usb_interface *intf,
 	struct snd_card *card;
 	int err;
 
+#ifdef USX2Y_NRPACKS_VARIABLE
+	if (nrpacks < 0 || nrpacks > USX2Y_NRPACKS_MAX)
+		return -EINVAL;
+#endif
+
 	if (le16_to_cpu(device->descriptor.idVendor) != 0x1604 ||
 	    (le16_to_cpu(device->descriptor.idProduct) != USB_ID_US122 &&
 	     le16_to_cpu(device->descriptor.idProduct) != USB_ID_US224 &&
diff --git a/sound/usb/usx2y/usbusx2y.h b/sound/usb/usx2y/usbusx2y.h
index 391fd7b4ed5ef..6a76d04bf1c7d 100644
--- a/sound/usb/usx2y/usbusx2y.h
+++ b/sound/usb/usx2y/usbusx2y.h
@@ -7,6 +7,32 @@
 
 #define NRURBS	        2
 
+/* Default value used for nr of packs per urb.
+ * 1 to 4 have been tested ok on uhci.
+ * To use 3 on ohci, you'd need a patch:
+ * look for "0000425-linux-2.6.9-rc4-mm1_ohci-hcd.patch.gz" on
+ * "https://bugtrack.alsa-project.org/alsa-bug/bug_view_page.php?bug_id=0000425"
+ *
+ * 1, 2 and 4 work out of the box on ohci, if I recall correctly.
+ * Bigger is safer operation, smaller gives lower latencies.
+ */
+#define USX2Y_NRPACKS 4
+
+#define USX2Y_NRPACKS_MAX 1024
+
+/* If your system works ok with this module's parameter
+ * nrpacks set to 1, you might as well comment
+ * this define out, and thereby produce smaller, faster code.
+ * You'd also set USX2Y_NRPACKS to 1 then.
+ */
+#define USX2Y_NRPACKS_VARIABLE 1
+
+#ifdef USX2Y_NRPACKS_VARIABLE
+extern int nrpacks;
+#define nr_of_packs() nrpacks
+#else
+#define nr_of_packs() USX2Y_NRPACKS
+#endif
 
 #define URBS_ASYNC_SEQ 10
 #define URB_DATA_LEN_ASYNC_SEQ 32
diff --git a/sound/usb/usx2y/usbusx2yaudio.c b/sound/usb/usx2y/usbusx2yaudio.c
index f540f46a0b143..acca8bead82e5 100644
--- a/sound/usb/usx2y/usbusx2yaudio.c
+++ b/sound/usb/usx2y/usbusx2yaudio.c
@@ -28,33 +28,6 @@
 #include "usx2y.h"
 #include "usbusx2y.h"
 
-/* Default value used for nr of packs per urb.
- * 1 to 4 have been tested ok on uhci.
- * To use 3 on ohci, you'd need a patch:
- * look for "0000425-linux-2.6.9-rc4-mm1_ohci-hcd.patch.gz" on
- * "https://bugtrack.alsa-project.org/alsa-bug/bug_view_page.php?bug_id=0000425"
- *
- * 1, 2 and 4 work out of the box on ohci, if I recall correctly.
- * Bigger is safer operation, smaller gives lower latencies.
- */
-#define USX2Y_NRPACKS 4
-
-/* If your system works ok with this module's parameter
- * nrpacks set to 1, you might as well comment
- * this define out, and thereby produce smaller, faster code.
- * You'd also set USX2Y_NRPACKS to 1 then.
- */
-#define USX2Y_NRPACKS_VARIABLE 1
-
-#ifdef USX2Y_NRPACKS_VARIABLE
-static int nrpacks = USX2Y_NRPACKS; /* number of packets per urb */
-#define  nr_of_packs() nrpacks
-module_param(nrpacks, int, 0444);
-MODULE_PARM_DESC(nrpacks, "Number of packets per URB.");
-#else
-#define nr_of_packs() USX2Y_NRPACKS
-#endif
-
 static int usx2y_urb_capt_retire(struct snd_usx2y_substream *subs)
 {
 	struct urb	*urb = subs->completed_urb;

From 64e6a754d33d31aa844b3ee66fb93ac84ca1565e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 27 Feb 2025 08:26:42 +0000
Subject: [PATCH 0848/1173] llc: do not use skb_get() before dev_queue_xmit()

syzbot is able to crash hosts [1], using llc and devices
not supporting IFF_TX_SKB_SHARING.

In this case, e1000 driver calls eth_skb_pad(), while
the skb is shared.

Simply replace skb_get() by skb_clone() in net/llc/llc_s_ac.c

Note that e1000 driver might have an issue with pktgen,
because it does not clear IFF_TX_SKB_SHARING, this is an
orthogonal change.

We need to audit other skb_get() uses in net/llc.

[1]

kernel BUG at net/core/skbuff.c:2178 !
Oops: invalid opcode: 0000 [#1] PREEMPT SMP KASAN NOPTI
CPU: 0 UID: 0 PID: 16371 Comm: syz.2.2764 Not tainted 6.14.0-rc4-syzkaller-00052-gac9c34d1e45a #0
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014
 RIP: 0010:pskb_expand_head+0x6ce/0x1240 net/core/skbuff.c:2178
Call Trace:
 <TASK>
  __skb_pad+0x18a/0x610 net/core/skbuff.c:2466
  __skb_put_padto include/linux/skbuff.h:3843 [inline]
  skb_put_padto include/linux/skbuff.h:3862 [inline]
  eth_skb_pad include/linux/etherdevice.h:656 [inline]
  e1000_xmit_frame+0x2d99/0x5800 drivers/net/ethernet/intel/e1000/e1000_main.c:3128
  __netdev_start_xmit include/linux/netdevice.h:5151 [inline]
  netdev_start_xmit include/linux/netdevice.h:5160 [inline]
  xmit_one net/core/dev.c:3806 [inline]
  dev_hard_start_xmit+0x9a/0x7b0 net/core/dev.c:3822
  sch_direct_xmit+0x1ae/0xc30 net/sched/sch_generic.c:343
  __dev_xmit_skb net/core/dev.c:4045 [inline]
  __dev_queue_xmit+0x13d4/0x43e0 net/core/dev.c:4621
  dev_queue_xmit include/linux/netdevice.h:3313 [inline]
  llc_sap_action_send_test_c+0x268/0x320 net/llc/llc_s_ac.c:144
  llc_exec_sap_trans_actions net/llc/llc_sap.c:153 [inline]
  llc_sap_next_state net/llc/llc_sap.c:182 [inline]
  llc_sap_state_process+0x239/0x510 net/llc/llc_sap.c:209
  llc_ui_sendmsg+0xd0d/0x14e0 net/llc/af_llc.c:993
  sock_sendmsg_nosec net/socket.c:718 [inline]

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzbot+da65c993ae113742a25f@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/67c020c0.050a0220.222324.0011.GAE@google.com/T/#u
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/llc/llc_s_ac.c | 49 +++++++++++++++++++++++++---------------------
 1 file changed, 27 insertions(+), 22 deletions(-)

diff --git a/net/llc/llc_s_ac.c b/net/llc/llc_s_ac.c
index 06fb8e6944b06..7a0cae9a81114 100644
--- a/net/llc/llc_s_ac.c
+++ b/net/llc/llc_s_ac.c
@@ -24,7 +24,7 @@
 #include <net/llc_s_ac.h>
 #include <net/llc_s_ev.h>
 #include <net/llc_sap.h>
-
+#include <net/sock.h>
 
 /**
  *	llc_sap_action_unitdata_ind - forward UI PDU to network layer
@@ -40,6 +40,26 @@ int llc_sap_action_unitdata_ind(struct llc_sap *sap, struct sk_buff *skb)
 	return 0;
 }
 
+static int llc_prepare_and_xmit(struct sk_buff *skb)
+{
+	struct llc_sap_state_ev *ev = llc_sap_ev(skb);
+	struct sk_buff *nskb;
+	int rc;
+
+	rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac);
+	if (rc)
+		return rc;
+
+	nskb = skb_clone(skb, GFP_ATOMIC);
+	if (!nskb)
+		return -ENOMEM;
+
+	if (skb->sk)
+		skb_set_owner_w(nskb, skb->sk);
+
+	return dev_queue_xmit(nskb);
+}
+
 /**
  *	llc_sap_action_send_ui - sends UI PDU resp to UNITDATA REQ to MAC layer
  *	@sap: SAP
@@ -52,17 +72,12 @@ int llc_sap_action_unitdata_ind(struct llc_sap *sap, struct sk_buff *skb)
 int llc_sap_action_send_ui(struct llc_sap *sap, struct sk_buff *skb)
 {
 	struct llc_sap_state_ev *ev = llc_sap_ev(skb);
-	int rc;
 
 	llc_pdu_header_init(skb, LLC_PDU_TYPE_U, ev->saddr.lsap,
 			    ev->daddr.lsap, LLC_PDU_CMD);
 	llc_pdu_init_as_ui_cmd(skb);
-	rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac);
-	if (likely(!rc)) {
-		skb_get(skb);
-		rc = dev_queue_xmit(skb);
-	}
-	return rc;
+
+	return llc_prepare_and_xmit(skb);
 }
 
 /**
@@ -77,17 +92,12 @@ int llc_sap_action_send_ui(struct llc_sap *sap, struct sk_buff *skb)
 int llc_sap_action_send_xid_c(struct llc_sap *sap, struct sk_buff *skb)
 {
 	struct llc_sap_state_ev *ev = llc_sap_ev(skb);
-	int rc;
 
 	llc_pdu_header_init(skb, LLC_PDU_TYPE_U_XID, ev->saddr.lsap,
 			    ev->daddr.lsap, LLC_PDU_CMD);
 	llc_pdu_init_as_xid_cmd(skb, LLC_XID_NULL_CLASS_2, 0);
-	rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac);
-	if (likely(!rc)) {
-		skb_get(skb);
-		rc = dev_queue_xmit(skb);
-	}
-	return rc;
+
+	return llc_prepare_and_xmit(skb);
 }
 
 /**
@@ -133,17 +143,12 @@ int llc_sap_action_send_xid_r(struct llc_sap *sap, struct sk_buff *skb)
 int llc_sap_action_send_test_c(struct llc_sap *sap, struct sk_buff *skb)
 {
 	struct llc_sap_state_ev *ev = llc_sap_ev(skb);
-	int rc;
 
 	llc_pdu_header_init(skb, LLC_PDU_TYPE_U, ev->saddr.lsap,
 			    ev->daddr.lsap, LLC_PDU_CMD);
 	llc_pdu_init_as_test_cmd(skb);
-	rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac);
-	if (likely(!rc)) {
-		skb_get(skb);
-		rc = dev_queue_xmit(skb);
-	}
-	return rc;
+
+	return llc_prepare_and_xmit(skb);
 }
 
 int llc_sap_action_send_test_r(struct llc_sap *sap, struct sk_buff *skb)

From 10fce7ebe888fa8c97eee7e317a47e7603e5e78d Mon Sep 17 00:00:00 2001
From: Xinghuo Chen <xinghuo.chen@foxmail.com>
Date: Mon, 3 Mar 2025 07:57:33 -0500
Subject: [PATCH 0849/1173] hwmon: fix a NULL vs IS_ERR_OR_NULL() check in
 xgene_hwmon_probe()

The devm_memremap() function returns error pointers on error,
it doesn't return NULL.

Fixes: c7cefce03e69 ("hwmon: (xgene) access mailbox as RAM")
Signed-off-by: Xinghuo Chen <xinghuo.chen@foxmail.com>
Link: https://lore.kernel.org/r/tencent_9AD8E7683EC29CAC97496B44F3F865BA070A@qq.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/xgene-hwmon.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hwmon/xgene-hwmon.c b/drivers/hwmon/xgene-hwmon.c
index 1e3bd129a922d..7087197383c96 100644
--- a/drivers/hwmon/xgene-hwmon.c
+++ b/drivers/hwmon/xgene-hwmon.c
@@ -706,7 +706,7 @@ static int xgene_hwmon_probe(struct platform_device *pdev)
 			goto out;
 		}
 
-		if (!ctx->pcc_comm_addr) {
+		if (IS_ERR_OR_NULL(ctx->pcc_comm_addr)) {
 			dev_err(&pdev->dev,
 				"Failed to ioremap PCC comm region\n");
 			rc = -ENOMEM;

From 23e0832d6d7be2d3c713f9390c060b6f1c48bf36 Mon Sep 17 00:00:00 2001
From: Philipp Stanner <phasta@kernel.org>
Date: Tue, 18 Feb 2025 13:41:50 +0100
Subject: [PATCH 0850/1173] drm/sched: Fix preprocessor guard

When writing the header guard for gpu_scheduler_trace.h, a typo,
apparently, occurred.

Fix the typo and document the scope of the guard.

Fixes: 353da3c520b4 ("drm/amdgpu: add tracepoint for scheduler (v2)")
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Signed-off-by: Philipp Stanner <phasta@kernel.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20250218124149.118002-2-phasta@kernel.org
---
 drivers/gpu/drm/scheduler/gpu_scheduler_trace.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler_trace.h b/drivers/gpu/drm/scheduler/gpu_scheduler_trace.h
index c75302ca3427c..f56e77e7f6d02 100644
--- a/drivers/gpu/drm/scheduler/gpu_scheduler_trace.h
+++ b/drivers/gpu/drm/scheduler/gpu_scheduler_trace.h
@@ -21,7 +21,7 @@
  *
  */
 
-#if !defined(_GPU_SCHED_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#if !defined(_GPU_SCHED_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ)
 #define _GPU_SCHED_TRACE_H_
 
 #include <linux/stringify.h>
@@ -106,7 +106,7 @@ TRACE_EVENT(drm_sched_job_wait_dep,
 		      __entry->seqno)
 );
 
-#endif
+#endif /* _GPU_SCHED_TRACE_H_ */
 
 /* This part must be outside protection */
 #undef TRACE_INCLUDE_PATH

From b2653cd3b75f62f29b72df4070e20357acb52bc4 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 26 Feb 2025 17:25:32 -0800
Subject: [PATCH 0851/1173] KVM: SVM: Save host DR masks on CPUs with DebugSwap

When running SEV-SNP guests on a CPU that supports DebugSwap, always save
the host's DR0..DR3 mask MSR values irrespective of whether or not
DebugSwap is enabled, to ensure the host values aren't clobbered by the
CPU.  And for now, also save DR0..DR3, even though doing so isn't
necessary (see below).

SVM_VMGEXIT_AP_CREATE is deeply flawed in that it allows the *guest* to
create a VMSA with guest-controlled SEV_FEATURES.  A well behaved guest
can inform the hypervisor, i.e. KVM, of its "requested" features, but on
CPUs without ALLOWED_SEV_FEATURES support, nothing prevents the guest from
lying about which SEV features are being enabled (or not!).

If a misbehaving guest enables DebugSwap in a secondary vCPU's VMSA, the
CPU will load the DR0..DR3 mask MSRs on #VMEXIT, i.e. will clobber the
MSRs with '0' if KVM doesn't save its desired value.

Note, DR0..DR3 themselves are "ok", as DR7 is reset on #VMEXIT, and KVM
restores all DRs in common x86 code as needed via hw_breakpoint_restore().
I.e. there is no risk of host DR0..DR3 being clobbered (when it matters).
However, there is a flaw in the opposite direction; because the guest can
lie about enabling DebugSwap, i.e. can *disable* DebugSwap without KVM's
knowledge, KVM must not rely on the CPU to restore DRs.  Defer fixing
that wart, as it's more of a documentation issue than a bug in the code.

Note, KVM added support for DebugSwap on commit d1f85fbe836e ("KVM: SEV:
Enable data breakpoints in SEV-ES"), but that is not an appropriate Fixes,
as the underlying flaw exists in hardware, not in KVM.  I.e. all kernels
that support SEV-SNP need to be patched, not just kernels with KVM's full
support for DebugSwap (ignoring that DebugSwap support landed first).

Opportunistically fix an incorrect statement in the comment; on CPUs
without DebugSwap, the CPU does NOT save or load debug registers, i.e.

Fixes: e366f92ea99e ("KVM: SEV: Support SEV-SNP AP Creation NAE event")
Cc: stable@vger.kernel.org
Cc: Naveen N Rao <naveen@kernel.org>
Cc: Kim Phillips <kim.phillips@amd.com>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Alexey Kardashevskiy <aik@amd.com>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Link: https://lore.kernel.org/r/20250227012541.3234589-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/sev.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index a2a794c320503..ef057c85a67ce 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -4580,6 +4580,8 @@ void sev_es_vcpu_reset(struct vcpu_svm *svm)
 
 void sev_es_prepare_switch_to_guest(struct vcpu_svm *svm, struct sev_es_save_area *hostsa)
 {
+	struct kvm *kvm = svm->vcpu.kvm;
+
 	/*
 	 * All host state for SEV-ES guests is categorized into three swap types
 	 * based on how it is handled by hardware during a world switch:
@@ -4603,10 +4605,15 @@ void sev_es_prepare_switch_to_guest(struct vcpu_svm *svm, struct sev_es_save_are
 
 	/*
 	 * If DebugSwap is enabled, debug registers are loaded but NOT saved by
-	 * the CPU (Type-B). If DebugSwap is disabled/unsupported, the CPU both
-	 * saves and loads debug registers (Type-A).
+	 * the CPU (Type-B). If DebugSwap is disabled/unsupported, the CPU does
+	 * not save or load debug registers.  Sadly, on CPUs without
+	 * ALLOWED_SEV_FEATURES, KVM can't prevent SNP guests from enabling
+	 * DebugSwap on secondary vCPUs without KVM's knowledge via "AP Create".
+	 * Save all registers if DebugSwap is supported to prevent host state
+	 * from being clobbered by a misbehaving guest.
 	 */
-	if (sev_vcpu_has_debug_swap(svm)) {
+	if (sev_vcpu_has_debug_swap(svm) ||
+	    (sev_snp_guest(kvm) && cpu_feature_enabled(X86_FEATURE_DEBUG_SWAP))) {
 		hostsa->dr0 = native_get_debugreg(0);
 		hostsa->dr1 = native_get_debugreg(1);
 		hostsa->dr2 = native_get_debugreg(2);

From 807cb9ce2ed9a1b6e79e70fb2cdb7860f1517dcc Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 26 Feb 2025 17:25:33 -0800
Subject: [PATCH 0852/1173] KVM: SVM: Don't rely on DebugSwap to restore host
 DR0..DR3

Never rely on the CPU to restore/load host DR0..DR3 values, even if the
CPU supports DebugSwap, as there are no guarantees that SNP guests will
actually enable DebugSwap on APs.  E.g. if KVM were to rely on the CPU to
load DR0..DR3 and skipped them during hw_breakpoint_restore(), KVM would
run with clobbered-to-zero DRs if an SNP guest created APs without
DebugSwap enabled.

Update the comment to explain the dangers, and hopefully prevent breaking
KVM in the future.

Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Link: https://lore.kernel.org/r/20250227012541.3234589-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/sev.c | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index ef057c85a67ce..080f8cecd7ca6 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -4606,18 +4606,21 @@ void sev_es_prepare_switch_to_guest(struct vcpu_svm *svm, struct sev_es_save_are
 	/*
 	 * If DebugSwap is enabled, debug registers are loaded but NOT saved by
 	 * the CPU (Type-B). If DebugSwap is disabled/unsupported, the CPU does
-	 * not save or load debug registers.  Sadly, on CPUs without
-	 * ALLOWED_SEV_FEATURES, KVM can't prevent SNP guests from enabling
-	 * DebugSwap on secondary vCPUs without KVM's knowledge via "AP Create".
-	 * Save all registers if DebugSwap is supported to prevent host state
-	 * from being clobbered by a misbehaving guest.
+	 * not save or load debug registers.  Sadly, KVM can't prevent SNP
+	 * guests from lying about DebugSwap on secondary vCPUs, i.e. the
+	 * SEV_FEATURES provided at "AP Create" isn't guaranteed to match what
+	 * the guest has actually enabled (or not!) in the VMSA.
+	 *
+	 * If DebugSwap is *possible*, save the masks so that they're restored
+	 * if the guest enables DebugSwap.  But for the DRs themselves, do NOT
+	 * rely on the CPU to restore the host values; KVM will restore them as
+	 * needed in common code, via hw_breakpoint_restore().  Note, KVM does
+	 * NOT support virtualizing Breakpoint Extensions, i.e. the mask MSRs
+	 * don't need to be restored per se, KVM just needs to ensure they are
+	 * loaded with the correct values *if* the CPU writes the MSRs.
 	 */
 	if (sev_vcpu_has_debug_swap(svm) ||
 	    (sev_snp_guest(kvm) && cpu_feature_enabled(X86_FEATURE_DEBUG_SWAP))) {
-		hostsa->dr0 = native_get_debugreg(0);
-		hostsa->dr1 = native_get_debugreg(1);
-		hostsa->dr2 = native_get_debugreg(2);
-		hostsa->dr3 = native_get_debugreg(3);
 		hostsa->dr0_addr_mask = amd_get_dr_addr_mask(0);
 		hostsa->dr1_addr_mask = amd_get_dr_addr_mask(1);
 		hostsa->dr2_addr_mask = amd_get_dr_addr_mask(2);

From d88ed5fb7c88f404e57fe2b2a6d19fefc35b4dc7 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Feb 2025 15:08:04 -0800
Subject: [PATCH 0853/1173] KVM: selftests: Ensure all vCPUs hit -EFAULT during
 initial RO stage

During the initial mprotect(RO) stage of mmu_stress_test, keep vCPUs
spinning until all vCPUs have hit -EFAULT, i.e. until all vCPUs have tried
to write to a read-only page.  If a vCPU manages to complete an entire
iteration of the loop without hitting a read-only page, *and* the vCPU
observes mprotect_ro_done before starting a second iteration, then the
vCPU will prematurely fall through to GUEST_SYNC(3) (on x86 and arm64) and
get out of sequence.

Replace the "do-while (!r)" loop around the associated _vcpu_run() with
a single invocation, as barring a KVM bug, the vCPU is guaranteed to hit
-EFAULT, and retrying on success is super confusion, hides KVM bugs, and
complicates this fix.  The do-while loop was semi-unintentionally added
specifically to fudge around a KVM x86 bug, and said bug is unhittable
without modifying the test to force x86 down the !(x86||arm64) path.

On x86, if forced emulation is enabled, vcpu_arch_put_guest() may trigger
emulation of the store to memory.  Due a (very, very) longstanding bug in
KVM x86's emulator, emulate writes to guest memory that fail during
__kvm_write_guest_page() unconditionally return KVM_EXIT_MMIO.  While that
is desirable in the !memslot case, it's wrong in this case as the failure
happens due to __copy_to_user() hitting a read-only page, not an emulated
MMIO region.

But as above, x86 only uses vcpu_arch_put_guest() if the __x86_64__ guards
are clobbered to force x86 down the common path, and of course the
unexpected MMIO is a KVM bug, i.e. *should* cause a test failure.

Fixes: b6c304aec648 ("KVM: selftests: Verify KVM correctly handles mprotect(PROT_READ)")
Reported-by: Yan Zhao <yan.y.zhao@intel.com>
Closes: https://lore.kernel.org/all/20250208105318.16861-1-yan.y.zhao@intel.com
Debugged-by: Yan Zhao <yan.y.zhao@intel.com>
Reviewed-by: Yan Zhao <yan.y.zhao@intel.com>
Tested-by: Yan Zhao <yan.y.zhao@intel.com>
Link: https://lore.kernel.org/r/20250228230804.3845860-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/mmu_stress_test.c | 21 ++++++++++++-------
 1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/tools/testing/selftests/kvm/mmu_stress_test.c b/tools/testing/selftests/kvm/mmu_stress_test.c
index d9c76b4c0d88a..6a437d2be9fa4 100644
--- a/tools/testing/selftests/kvm/mmu_stress_test.c
+++ b/tools/testing/selftests/kvm/mmu_stress_test.c
@@ -18,6 +18,7 @@
 #include "ucall_common.h"
 
 static bool mprotect_ro_done;
+static bool all_vcpus_hit_ro_fault;
 
 static void guest_code(uint64_t start_gpa, uint64_t end_gpa, uint64_t stride)
 {
@@ -36,9 +37,9 @@ static void guest_code(uint64_t start_gpa, uint64_t end_gpa, uint64_t stride)
 
 	/*
 	 * Write to the region while mprotect(PROT_READ) is underway.  Keep
-	 * looping until the memory is guaranteed to be read-only, otherwise
-	 * vCPUs may complete their writes and advance to the next stage
-	 * prematurely.
+	 * looping until the memory is guaranteed to be read-only and a fault
+	 * has occurred, otherwise vCPUs may complete their writes and advance
+	 * to the next stage prematurely.
 	 *
 	 * For architectures that support skipping the faulting instruction,
 	 * generate the store via inline assembly to ensure the exact length
@@ -56,7 +57,7 @@ static void guest_code(uint64_t start_gpa, uint64_t end_gpa, uint64_t stride)
 #else
 			vcpu_arch_put_guest(*((volatile uint64_t *)gpa), gpa);
 #endif
-	} while (!READ_ONCE(mprotect_ro_done));
+	} while (!READ_ONCE(mprotect_ro_done) || !READ_ONCE(all_vcpus_hit_ro_fault));
 
 	/*
 	 * Only architectures that write the entire range can explicitly sync,
@@ -81,6 +82,7 @@ struct vcpu_info {
 
 static int nr_vcpus;
 static atomic_t rendezvous;
+static atomic_t nr_ro_faults;
 
 static void rendezvous_with_boss(void)
 {
@@ -148,12 +150,16 @@ static void *vcpu_worker(void *data)
 	 * be stuck on the faulting instruction for other architectures.  Go to
 	 * stage 3 without a rendezvous
 	 */
-	do {
-		r = _vcpu_run(vcpu);
-	} while (!r);
+	r = _vcpu_run(vcpu);
 	TEST_ASSERT(r == -1 && errno == EFAULT,
 		    "Expected EFAULT on write to RO memory, got r = %d, errno = %d", r, errno);
 
+	atomic_inc(&nr_ro_faults);
+	if (atomic_read(&nr_ro_faults) == nr_vcpus) {
+		WRITE_ONCE(all_vcpus_hit_ro_fault, true);
+		sync_global_to_guest(vm, all_vcpus_hit_ro_fault);
+	}
+
 #if defined(__x86_64__) || defined(__aarch64__)
 	/*
 	 * Verify *all* writes from the guest hit EFAULT due to the VMA now
@@ -378,7 +384,6 @@ int main(int argc, char *argv[])
 	rendezvous_with_vcpus(&time_run2, "run 2");
 
 	mprotect(mem, slot_size, PROT_READ);
-	usleep(10);
 	mprotect_ro_done = true;
 	sync_global_to_guest(vm, mprotect_ro_done);
 

From 3b2d3db368013729fd2167a0d91fec821dba807c Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Feb 2025 15:38:52 -0800
Subject: [PATCH 0854/1173] KVM: selftests: Fix printf() format goof in SEV
 smoke test

Print out the index of mismatching XSAVE bytes using unsigned decimal
format.  Some versions of clang complain about trying to print an integer
as an unsigned char.

  x86/sev_smoke_test.c:55:51: error: format specifies type 'unsigned char'
                                     but the argument has type 'int' [-Werror,-Wformat]

Fixes: 8c53183dbaa2 ("selftests: kvm: add test for transferring FPU state into VMSA")
Link: https://lore.kernel.org/r/20250228233852.3855676-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/x86/sev_smoke_test.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/kvm/x86/sev_smoke_test.c b/tools/testing/selftests/kvm/x86/sev_smoke_test.c
index a1a688e752666..d97816dc476a2 100644
--- a/tools/testing/selftests/kvm/x86/sev_smoke_test.c
+++ b/tools/testing/selftests/kvm/x86/sev_smoke_test.c
@@ -52,7 +52,8 @@ static void compare_xsave(u8 *from_host, u8 *from_guest)
 	bool bad = false;
 	for (i = 0; i < 4095; i++) {
 		if (from_host[i] != from_guest[i]) {
-			printf("mismatch at %02hhx | %02hhx %02hhx\n", i, from_host[i], from_guest[i]);
+			printf("mismatch at %u | %02hhx %02hhx\n",
+			       i, from_host[i], from_guest[i]);
 			bad = true;
 		}
 	}

From ba2e35644d09af730880bb404bb6dd84685dcd7e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Wed, 26 Feb 2025 12:44:40 +0100
Subject: [PATCH 0855/1173] MAINTAINERS: Add vDSO selftests
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

These currently have no maintainer besides the default kselftest ones.
Add the general vDSO maintainers, too.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Acked-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/all/20250226-parse_vdso-nolibc-v2-1-28e14e031ed8@linutronix.de
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 25c86f47353de..74c6399529c7f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9777,6 +9777,7 @@ F:	include/asm-generic/vdso/vsyscall.h
 F:	include/vdso/
 F:	kernel/time/vsyscall.c
 F:	lib/vdso/
+F:	tools/testing/selftests/vDSO/
 
 GENWQE (IBM Generic Workqueue Card)
 M:	Frank Haverkamp <haver@linux.ibm.com>

From c4131140961b93883e69a01b09f8ed4bcebefaf1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Wed, 26 Feb 2025 12:44:41 +0100
Subject: [PATCH 0856/1173] elf, uapi: Add definition for STN_UNDEF
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The definition is used by tools/testing/selftests/vDSO/parse_vdso.c.

To be able to build the vDSO selftests without a libc dependency,
add the definition to the kernels own UAPI headers.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Kees Cook <kees@kernel.org>
Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Acked-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://refspecs.linuxfoundation.org/elf/gabi4+/ch4.symtab.html
Link: https://lore.kernel.org/all/20250226-parse_vdso-nolibc-v2-2-28e14e031ed8@linutronix.de
---
 include/uapi/linux/elf.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h
index b44069d29cecc..448695c736404 100644
--- a/include/uapi/linux/elf.h
+++ b/include/uapi/linux/elf.h
@@ -125,6 +125,8 @@ typedef __s64	Elf64_Sxword;
 #define STB_GLOBAL 1
 #define STB_WEAK   2
 
+#define STN_UNDEF 0
+
 #define STT_NOTYPE  0
 #define STT_OBJECT  1
 #define STT_FUNC    2

From 50881d1469cf35eec690d863276cf257c391eec5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Wed, 26 Feb 2025 12:44:42 +0100
Subject: [PATCH 0857/1173] elf, uapi: Add definition for DT_GNU_HASH
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The definition is used by tools/testing/selftests/vDSO/parse_vdso.c.

To be able to build the vDSO selftests without a libc dependency,
add the define to the kernels own UAPI headers.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Kees Cook <kees@kernel.org>
Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Acked-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://refspecs.linuxbase.org/LSB_5.0.0/LSB-Core-generic/LSB-Core-generic/libc-ddefs.html
Link: https://lore.kernel.org/all/20250226-parse_vdso-nolibc-v2-3-28e14e031ed8@linutronix.de
---
 include/uapi/linux/elf.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h
index 448695c736404..c5383cc7bb13c 100644
--- a/include/uapi/linux/elf.h
+++ b/include/uapi/linux/elf.h
@@ -107,6 +107,7 @@ typedef __s64	Elf64_Sxword;
 #define DT_VALRNGLO	0x6ffffd00
 #define DT_VALRNGHI	0x6ffffdff
 #define DT_ADDRRNGLO	0x6ffffe00
+#define DT_GNU_HASH	0x6ffffef5
 #define DT_ADDRRNGHI	0x6ffffeff
 #define DT_VERSYM	0x6ffffff0
 #define DT_RELACOUNT	0x6ffffff9

From 049d19bb3807e10902d41125c9d511025389718f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Wed, 26 Feb 2025 12:44:43 +0100
Subject: [PATCH 0858/1173] elf, uapi: Add definitions for VER_FLG_BASE and
 VER_FLG_WEAK
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The definitions are used by tools/testing/selftests/vDSO/parse_vdso.c.

To be able to build the vDSO selftests without a libc dependency,
add the definitions to the kernels own UAPI headers.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Kees Cook <kees@kernel.org>
Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Acked-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://docs.oracle.com/cd/E19683-01/816-1386/chapter6-80869/index.html
Link: https://lore.kernel.org/all/20250226-parse_vdso-nolibc-v2-4-28e14e031ed8@linutronix.de
---
 include/uapi/linux/elf.h | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h
index c5383cc7bb13c..d040f12ff1c0a 100644
--- a/include/uapi/linux/elf.h
+++ b/include/uapi/linux/elf.h
@@ -136,6 +136,9 @@ typedef __s64	Elf64_Sxword;
 #define STT_COMMON  5
 #define STT_TLS     6
 
+#define VER_FLG_BASE 0x1
+#define VER_FLG_WEAK 0x2
+
 #define ELF_ST_BIND(x)		((x) >> 4)
 #define ELF_ST_TYPE(x)		((x) & 0xf)
 #define ELF32_ST_BIND(x)	ELF_ST_BIND(x)

From 2c86f604f85def1be0b7889c18e055ed63591018 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Wed, 26 Feb 2025 12:44:44 +0100
Subject: [PATCH 0859/1173] elf, uapi: Add type ElfXX_Versym
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The type is used by tools/testing/selftests/vDSO/parse_vdso.c.

To be able to build the vDSO selftests without a libc dependency,
add the type to the kernels own UAPI headers. As documented by elf(5).

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Kees Cook <kees@kernel.org>
Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Acked-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/all/20250226-parse_vdso-nolibc-v2-5-28e14e031ed8@linutronix.de
---
 include/uapi/linux/elf.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h
index d040f12ff1c0a..8846fe03ca5b8 100644
--- a/include/uapi/linux/elf.h
+++ b/include/uapi/linux/elf.h
@@ -11,6 +11,7 @@ typedef __u16	Elf32_Half;
 typedef __u32	Elf32_Off;
 typedef __s32	Elf32_Sword;
 typedef __u32	Elf32_Word;
+typedef __u16	Elf32_Versym;
 
 /* 64-bit ELF base types. */
 typedef __u64	Elf64_Addr;
@@ -21,6 +22,7 @@ typedef __s32	Elf64_Sword;
 typedef __u32	Elf64_Word;
 typedef __u64	Elf64_Xword;
 typedef __s64	Elf64_Sxword;
+typedef __u16	Elf64_Versym;
 
 /* These constants are for the segment types stored in the image headers */
 #define PT_NULL    0

From e0d15896f5dc90f4bd36ab79c958f6eff3f7f403 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Wed, 26 Feb 2025 12:44:45 +0100
Subject: [PATCH 0860/1173] elf, uapi: Add types ElfXX_Verdef and ElfXX_Veraux
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The types are used by tools/testing/selftests/vDSO/parse_vdso.c.

To be able to build the vDSO selftests without a libc dependency,
add the types to the kernels own UAPI headers.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Kees Cook <kees@kernel.org>
Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Acked-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://refspecs.linuxfoundation.org/LSB_5.0.0/LSB-Core-generic/LSB-Core-generic/symversion.html#VERDEFEXTS
Link: https://lore.kernel.org/all/20250226-parse_vdso-nolibc-v2-6-28e14e031ed8@linutronix.de
---
 include/uapi/linux/elf.h | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h
index 8846fe03ca5b8..49f9f90458d8c 100644
--- a/include/uapi/linux/elf.h
+++ b/include/uapi/linux/elf.h
@@ -491,4 +491,34 @@ typedef struct elf64_note {
 /* Bits for GNU_PROPERTY_AARCH64_FEATURE_1_BTI */
 #define GNU_PROPERTY_AARCH64_FEATURE_1_BTI	(1U << 0)
 
+typedef struct {
+  Elf32_Half	vd_version;
+  Elf32_Half	vd_flags;
+  Elf32_Half	vd_ndx;
+  Elf32_Half	vd_cnt;
+  Elf32_Word	vd_hash;
+  Elf32_Word	vd_aux;
+  Elf32_Word	vd_next;
+} Elf32_Verdef;
+
+typedef struct {
+  Elf64_Half	vd_version;
+  Elf64_Half	vd_flags;
+  Elf64_Half	vd_ndx;
+  Elf64_Half	vd_cnt;
+  Elf64_Word	vd_hash;
+  Elf64_Word	vd_aux;
+  Elf64_Word	vd_next;
+} Elf64_Verdef;
+
+typedef struct {
+  Elf32_Word    vda_name;
+  Elf32_Word    vda_next;
+} Elf32_Verdaux;
+
+typedef struct {
+  Elf64_Word    vda_name;
+  Elf64_Word    vda_next;
+} Elf64_Verdaux;
+
 #endif /* _UAPI_LINUX_ELF_H */

From 626fd35278295fbb21f2da331cd8028e9738d965 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Wed, 26 Feb 2025 12:44:46 +0100
Subject: [PATCH 0861/1173] tools/include: Add uapi/linux/elf.h
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It will be used by the vDSO selftests.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Acked-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/all/20250226-parse_vdso-nolibc-v2-7-28e14e031ed8@linutronix.de
---
 tools/include/uapi/linux/elf.h | 524 +++++++++++++++++++++++++++++++++
 1 file changed, 524 insertions(+)
 create mode 100644 tools/include/uapi/linux/elf.h

diff --git a/tools/include/uapi/linux/elf.h b/tools/include/uapi/linux/elf.h
new file mode 100644
index 0000000000000..5834b83d7f9a4
--- /dev/null
+++ b/tools/include/uapi/linux/elf.h
@@ -0,0 +1,524 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_ELF_H
+#define _LINUX_ELF_H
+
+#include <linux/types.h>
+#include <linux/elf-em.h>
+
+/* 32-bit ELF base types. */
+typedef __u32	Elf32_Addr;
+typedef __u16	Elf32_Half;
+typedef __u32	Elf32_Off;
+typedef __s32	Elf32_Sword;
+typedef __u32	Elf32_Word;
+typedef __u16	Elf32_Versym;
+
+/* 64-bit ELF base types. */
+typedef __u64	Elf64_Addr;
+typedef __u16	Elf64_Half;
+typedef __s16	Elf64_SHalf;
+typedef __u64	Elf64_Off;
+typedef __s32	Elf64_Sword;
+typedef __u32	Elf64_Word;
+typedef __u64	Elf64_Xword;
+typedef __s64	Elf64_Sxword;
+typedef __u16	Elf64_Versym;
+
+/* These constants are for the segment types stored in the image headers */
+#define PT_NULL    0
+#define PT_LOAD    1
+#define PT_DYNAMIC 2
+#define PT_INTERP  3
+#define PT_NOTE    4
+#define PT_SHLIB   5
+#define PT_PHDR    6
+#define PT_TLS     7		/* Thread local storage segment */
+#define PT_LOOS    0x60000000	/* OS-specific */
+#define PT_HIOS    0x6fffffff	/* OS-specific */
+#define PT_LOPROC  0x70000000
+#define PT_HIPROC  0x7fffffff
+#define PT_GNU_EH_FRAME	(PT_LOOS + 0x474e550)
+#define PT_GNU_STACK	(PT_LOOS + 0x474e551)
+#define PT_GNU_RELRO	(PT_LOOS + 0x474e552)
+#define PT_GNU_PROPERTY	(PT_LOOS + 0x474e553)
+
+
+/* ARM MTE memory tag segment type */
+#define PT_AARCH64_MEMTAG_MTE	(PT_LOPROC + 0x2)
+
+/*
+ * Extended Numbering
+ *
+ * If the real number of program header table entries is larger than
+ * or equal to PN_XNUM(0xffff), it is set to sh_info field of the
+ * section header at index 0, and PN_XNUM is set to e_phnum
+ * field. Otherwise, the section header at index 0 is zero
+ * initialized, if it exists.
+ *
+ * Specifications are available in:
+ *
+ * - Oracle: Linker and Libraries.
+ *   Part No: 817–1984–19, August 2011.
+ *   https://docs.oracle.com/cd/E18752_01/pdf/817-1984.pdf
+ *
+ * - System V ABI AMD64 Architecture Processor Supplement
+ *   Draft Version 0.99.4,
+ *   January 13, 2010.
+ *   http://www.cs.washington.edu/education/courses/cse351/12wi/supp-docs/abi.pdf
+ */
+#define PN_XNUM 0xffff
+
+/* These constants define the different elf file types */
+#define ET_NONE   0
+#define ET_REL    1
+#define ET_EXEC   2
+#define ET_DYN    3
+#define ET_CORE   4
+#define ET_LOPROC 0xff00
+#define ET_HIPROC 0xffff
+
+/* This is the info that is needed to parse the dynamic section of the file */
+#define DT_NULL		0
+#define DT_NEEDED	1
+#define DT_PLTRELSZ	2
+#define DT_PLTGOT	3
+#define DT_HASH		4
+#define DT_STRTAB	5
+#define DT_SYMTAB	6
+#define DT_RELA		7
+#define DT_RELASZ	8
+#define DT_RELAENT	9
+#define DT_STRSZ	10
+#define DT_SYMENT	11
+#define DT_INIT		12
+#define DT_FINI		13
+#define DT_SONAME	14
+#define DT_RPATH	15
+#define DT_SYMBOLIC	16
+#define DT_REL		17
+#define DT_RELSZ	18
+#define DT_RELENT	19
+#define DT_PLTREL	20
+#define DT_DEBUG	21
+#define DT_TEXTREL	22
+#define DT_JMPREL	23
+#define DT_ENCODING	32
+#define OLD_DT_LOOS	0x60000000
+#define DT_LOOS		0x6000000d
+#define DT_HIOS		0x6ffff000
+#define DT_VALRNGLO	0x6ffffd00
+#define DT_VALRNGHI	0x6ffffdff
+#define DT_ADDRRNGLO	0x6ffffe00
+#define DT_GNU_HASH	0x6ffffef5
+#define DT_ADDRRNGHI	0x6ffffeff
+#define DT_VERSYM	0x6ffffff0
+#define DT_RELACOUNT	0x6ffffff9
+#define DT_RELCOUNT	0x6ffffffa
+#define DT_FLAGS_1	0x6ffffffb
+#define DT_VERDEF	0x6ffffffc
+#define	DT_VERDEFNUM	0x6ffffffd
+#define DT_VERNEED	0x6ffffffe
+#define	DT_VERNEEDNUM	0x6fffffff
+#define OLD_DT_HIOS     0x6fffffff
+#define DT_LOPROC	0x70000000
+#define DT_HIPROC	0x7fffffff
+
+/* This info is needed when parsing the symbol table */
+#define STB_LOCAL  0
+#define STB_GLOBAL 1
+#define STB_WEAK   2
+
+#define STN_UNDEF 0
+
+#define STT_NOTYPE  0
+#define STT_OBJECT  1
+#define STT_FUNC    2
+#define STT_SECTION 3
+#define STT_FILE    4
+#define STT_COMMON  5
+#define STT_TLS     6
+
+#define VER_FLG_BASE 0x1
+#define VER_FLG_WEAK 0x2
+
+#define ELF_ST_BIND(x)		((x) >> 4)
+#define ELF_ST_TYPE(x)		((x) & 0xf)
+#define ELF32_ST_BIND(x)	ELF_ST_BIND(x)
+#define ELF32_ST_TYPE(x)	ELF_ST_TYPE(x)
+#define ELF64_ST_BIND(x)	ELF_ST_BIND(x)
+#define ELF64_ST_TYPE(x)	ELF_ST_TYPE(x)
+
+typedef struct {
+  Elf32_Sword d_tag;
+  union {
+    Elf32_Sword	d_val;
+    Elf32_Addr	d_ptr;
+  } d_un;
+} Elf32_Dyn;
+
+typedef struct {
+  Elf64_Sxword d_tag;		/* entry tag value */
+  union {
+    Elf64_Xword d_val;
+    Elf64_Addr d_ptr;
+  } d_un;
+} Elf64_Dyn;
+
+/* The following are used with relocations */
+#define ELF32_R_SYM(x) ((x) >> 8)
+#define ELF32_R_TYPE(x) ((x) & 0xff)
+
+#define ELF64_R_SYM(i)			((i) >> 32)
+#define ELF64_R_TYPE(i)			((i) & 0xffffffff)
+
+typedef struct elf32_rel {
+  Elf32_Addr	r_offset;
+  Elf32_Word	r_info;
+} Elf32_Rel;
+
+typedef struct elf64_rel {
+  Elf64_Addr r_offset;	/* Location at which to apply the action */
+  Elf64_Xword r_info;	/* index and type of relocation */
+} Elf64_Rel;
+
+typedef struct elf32_rela {
+  Elf32_Addr	r_offset;
+  Elf32_Word	r_info;
+  Elf32_Sword	r_addend;
+} Elf32_Rela;
+
+typedef struct elf64_rela {
+  Elf64_Addr r_offset;	/* Location at which to apply the action */
+  Elf64_Xword r_info;	/* index and type of relocation */
+  Elf64_Sxword r_addend;	/* Constant addend used to compute value */
+} Elf64_Rela;
+
+typedef struct elf32_sym {
+  Elf32_Word	st_name;
+  Elf32_Addr	st_value;
+  Elf32_Word	st_size;
+  unsigned char	st_info;
+  unsigned char	st_other;
+  Elf32_Half	st_shndx;
+} Elf32_Sym;
+
+typedef struct elf64_sym {
+  Elf64_Word st_name;		/* Symbol name, index in string tbl */
+  unsigned char	st_info;	/* Type and binding attributes */
+  unsigned char	st_other;	/* No defined meaning, 0 */
+  Elf64_Half st_shndx;		/* Associated section index */
+  Elf64_Addr st_value;		/* Value of the symbol */
+  Elf64_Xword st_size;		/* Associated symbol size */
+} Elf64_Sym;
+
+
+#define EI_NIDENT	16
+
+typedef struct elf32_hdr {
+  unsigned char	e_ident[EI_NIDENT];
+  Elf32_Half	e_type;
+  Elf32_Half	e_machine;
+  Elf32_Word	e_version;
+  Elf32_Addr	e_entry;  /* Entry point */
+  Elf32_Off	e_phoff;
+  Elf32_Off	e_shoff;
+  Elf32_Word	e_flags;
+  Elf32_Half	e_ehsize;
+  Elf32_Half	e_phentsize;
+  Elf32_Half	e_phnum;
+  Elf32_Half	e_shentsize;
+  Elf32_Half	e_shnum;
+  Elf32_Half	e_shstrndx;
+} Elf32_Ehdr;
+
+typedef struct elf64_hdr {
+  unsigned char	e_ident[EI_NIDENT];	/* ELF "magic number" */
+  Elf64_Half e_type;
+  Elf64_Half e_machine;
+  Elf64_Word e_version;
+  Elf64_Addr e_entry;		/* Entry point virtual address */
+  Elf64_Off e_phoff;		/* Program header table file offset */
+  Elf64_Off e_shoff;		/* Section header table file offset */
+  Elf64_Word e_flags;
+  Elf64_Half e_ehsize;
+  Elf64_Half e_phentsize;
+  Elf64_Half e_phnum;
+  Elf64_Half e_shentsize;
+  Elf64_Half e_shnum;
+  Elf64_Half e_shstrndx;
+} Elf64_Ehdr;
+
+/* These constants define the permissions on sections in the program
+   header, p_flags. */
+#define PF_R		0x4
+#define PF_W		0x2
+#define PF_X		0x1
+
+typedef struct elf32_phdr {
+  Elf32_Word	p_type;
+  Elf32_Off	p_offset;
+  Elf32_Addr	p_vaddr;
+  Elf32_Addr	p_paddr;
+  Elf32_Word	p_filesz;
+  Elf32_Word	p_memsz;
+  Elf32_Word	p_flags;
+  Elf32_Word	p_align;
+} Elf32_Phdr;
+
+typedef struct elf64_phdr {
+  Elf64_Word p_type;
+  Elf64_Word p_flags;
+  Elf64_Off p_offset;		/* Segment file offset */
+  Elf64_Addr p_vaddr;		/* Segment virtual address */
+  Elf64_Addr p_paddr;		/* Segment physical address */
+  Elf64_Xword p_filesz;		/* Segment size in file */
+  Elf64_Xword p_memsz;		/* Segment size in memory */
+  Elf64_Xword p_align;		/* Segment alignment, file & memory */
+} Elf64_Phdr;
+
+/* sh_type */
+#define SHT_NULL	0
+#define SHT_PROGBITS	1
+#define SHT_SYMTAB	2
+#define SHT_STRTAB	3
+#define SHT_RELA	4
+#define SHT_HASH	5
+#define SHT_DYNAMIC	6
+#define SHT_NOTE	7
+#define SHT_NOBITS	8
+#define SHT_REL		9
+#define SHT_SHLIB	10
+#define SHT_DYNSYM	11
+#define SHT_NUM		12
+#define SHT_LOPROC	0x70000000
+#define SHT_HIPROC	0x7fffffff
+#define SHT_LOUSER	0x80000000
+#define SHT_HIUSER	0xffffffff
+
+/* sh_flags */
+#define SHF_WRITE		0x1
+#define SHF_ALLOC		0x2
+#define SHF_EXECINSTR		0x4
+#define SHF_RELA_LIVEPATCH	0x00100000
+#define SHF_RO_AFTER_INIT	0x00200000
+#define SHF_MASKPROC		0xf0000000
+
+/* special section indexes */
+#define SHN_UNDEF	0
+#define SHN_LORESERVE	0xff00
+#define SHN_LOPROC	0xff00
+#define SHN_HIPROC	0xff1f
+#define SHN_LIVEPATCH	0xff20
+#define SHN_ABS		0xfff1
+#define SHN_COMMON	0xfff2
+#define SHN_HIRESERVE	0xffff
+
+typedef struct elf32_shdr {
+  Elf32_Word	sh_name;
+  Elf32_Word	sh_type;
+  Elf32_Word	sh_flags;
+  Elf32_Addr	sh_addr;
+  Elf32_Off	sh_offset;
+  Elf32_Word	sh_size;
+  Elf32_Word	sh_link;
+  Elf32_Word	sh_info;
+  Elf32_Word	sh_addralign;
+  Elf32_Word	sh_entsize;
+} Elf32_Shdr;
+
+typedef struct elf64_shdr {
+  Elf64_Word sh_name;		/* Section name, index in string tbl */
+  Elf64_Word sh_type;		/* Type of section */
+  Elf64_Xword sh_flags;		/* Miscellaneous section attributes */
+  Elf64_Addr sh_addr;		/* Section virtual addr at execution */
+  Elf64_Off sh_offset;		/* Section file offset */
+  Elf64_Xword sh_size;		/* Size of section in bytes */
+  Elf64_Word sh_link;		/* Index of another section */
+  Elf64_Word sh_info;		/* Additional section information */
+  Elf64_Xword sh_addralign;	/* Section alignment */
+  Elf64_Xword sh_entsize;	/* Entry size if section holds table */
+} Elf64_Shdr;
+
+#define	EI_MAG0		0		/* e_ident[] indexes */
+#define	EI_MAG1		1
+#define	EI_MAG2		2
+#define	EI_MAG3		3
+#define	EI_CLASS	4
+#define	EI_DATA		5
+#define	EI_VERSION	6
+#define	EI_OSABI	7
+#define	EI_PAD		8
+
+#define	ELFMAG0		0x7f		/* EI_MAG */
+#define	ELFMAG1		'E'
+#define	ELFMAG2		'L'
+#define	ELFMAG3		'F'
+#define	ELFMAG		"\177ELF"
+#define	SELFMAG		4
+
+#define	ELFCLASSNONE	0		/* EI_CLASS */
+#define	ELFCLASS32	1
+#define	ELFCLASS64	2
+#define	ELFCLASSNUM	3
+
+#define ELFDATANONE	0		/* e_ident[EI_DATA] */
+#define ELFDATA2LSB	1
+#define ELFDATA2MSB	2
+
+#define EV_NONE		0		/* e_version, EI_VERSION */
+#define EV_CURRENT	1
+#define EV_NUM		2
+
+#define ELFOSABI_NONE	0
+#define ELFOSABI_LINUX	3
+
+#ifndef ELF_OSABI
+#define ELF_OSABI ELFOSABI_NONE
+#endif
+
+/*
+ * Notes used in ET_CORE. Architectures export some of the arch register sets
+ * using the corresponding note types via the PTRACE_GETREGSET and
+ * PTRACE_SETREGSET requests.
+ * The note name for these types is "LINUX", except NT_PRFPREG that is named
+ * "CORE".
+ */
+#define NT_PRSTATUS	1
+#define NT_PRFPREG	2
+#define NT_PRPSINFO	3
+#define NT_TASKSTRUCT	4
+#define NT_AUXV		6
+/*
+ * Note to userspace developers: size of NT_SIGINFO note may increase
+ * in the future to accomodate more fields, don't assume it is fixed!
+ */
+#define NT_SIGINFO      0x53494749
+#define NT_FILE		0x46494c45
+#define NT_PRXFPREG     0x46e62b7f      /* copied from gdb5.1/include/elf/common.h */
+#define NT_PPC_VMX	0x100		/* PowerPC Altivec/VMX registers */
+#define NT_PPC_SPE	0x101		/* PowerPC SPE/EVR registers */
+#define NT_PPC_VSX	0x102		/* PowerPC VSX registers */
+#define NT_PPC_TAR	0x103		/* Target Address Register */
+#define NT_PPC_PPR	0x104		/* Program Priority Register */
+#define NT_PPC_DSCR	0x105		/* Data Stream Control Register */
+#define NT_PPC_EBB	0x106		/* Event Based Branch Registers */
+#define NT_PPC_PMU	0x107		/* Performance Monitor Registers */
+#define NT_PPC_TM_CGPR	0x108		/* TM checkpointed GPR Registers */
+#define NT_PPC_TM_CFPR	0x109		/* TM checkpointed FPR Registers */
+#define NT_PPC_TM_CVMX	0x10a		/* TM checkpointed VMX Registers */
+#define NT_PPC_TM_CVSX	0x10b		/* TM checkpointed VSX Registers */
+#define NT_PPC_TM_SPR	0x10c		/* TM Special Purpose Registers */
+#define NT_PPC_TM_CTAR	0x10d		/* TM checkpointed Target Address Register */
+#define NT_PPC_TM_CPPR	0x10e		/* TM checkpointed Program Priority Register */
+#define NT_PPC_TM_CDSCR	0x10f		/* TM checkpointed Data Stream Control Register */
+#define NT_PPC_PKEY	0x110		/* Memory Protection Keys registers */
+#define NT_PPC_DEXCR	0x111		/* PowerPC DEXCR registers */
+#define NT_PPC_HASHKEYR	0x112		/* PowerPC HASHKEYR register */
+#define NT_386_TLS	0x200		/* i386 TLS slots (struct user_desc) */
+#define NT_386_IOPERM	0x201		/* x86 io permission bitmap (1=deny) */
+#define NT_X86_XSTATE	0x202		/* x86 extended state using xsave */
+/* Old binutils treats 0x203 as a CET state */
+#define NT_X86_SHSTK	0x204		/* x86 SHSTK state */
+#define NT_X86_XSAVE_LAYOUT	0x205	/* XSAVE layout description */
+#define NT_S390_HIGH_GPRS	0x300	/* s390 upper register halves */
+#define NT_S390_TIMER	0x301		/* s390 timer register */
+#define NT_S390_TODCMP	0x302		/* s390 TOD clock comparator register */
+#define NT_S390_TODPREG	0x303		/* s390 TOD programmable register */
+#define NT_S390_CTRS	0x304		/* s390 control registers */
+#define NT_S390_PREFIX	0x305		/* s390 prefix register */
+#define NT_S390_LAST_BREAK	0x306	/* s390 breaking event address */
+#define NT_S390_SYSTEM_CALL	0x307	/* s390 system call restart data */
+#define NT_S390_TDB	0x308		/* s390 transaction diagnostic block */
+#define NT_S390_VXRS_LOW	0x309	/* s390 vector registers 0-15 upper half */
+#define NT_S390_VXRS_HIGH	0x30a	/* s390 vector registers 16-31 */
+#define NT_S390_GS_CB	0x30b		/* s390 guarded storage registers */
+#define NT_S390_GS_BC	0x30c		/* s390 guarded storage broadcast control block */
+#define NT_S390_RI_CB	0x30d		/* s390 runtime instrumentation */
+#define NT_S390_PV_CPU_DATA	0x30e	/* s390 protvirt cpu dump data */
+#define NT_ARM_VFP	0x400		/* ARM VFP/NEON registers */
+#define NT_ARM_TLS	0x401		/* ARM TLS register */
+#define NT_ARM_HW_BREAK	0x402		/* ARM hardware breakpoint registers */
+#define NT_ARM_HW_WATCH	0x403		/* ARM hardware watchpoint registers */
+#define NT_ARM_SYSTEM_CALL	0x404	/* ARM system call number */
+#define NT_ARM_SVE	0x405		/* ARM Scalable Vector Extension registers */
+#define NT_ARM_PAC_MASK		0x406	/* ARM pointer authentication code masks */
+#define NT_ARM_PACA_KEYS	0x407	/* ARM pointer authentication address keys */
+#define NT_ARM_PACG_KEYS	0x408	/* ARM pointer authentication generic key */
+#define NT_ARM_TAGGED_ADDR_CTRL	0x409	/* arm64 tagged address control (prctl()) */
+#define NT_ARM_PAC_ENABLED_KEYS	0x40a	/* arm64 ptr auth enabled keys (prctl()) */
+#define NT_ARM_SSVE	0x40b		/* ARM Streaming SVE registers */
+#define NT_ARM_ZA	0x40c		/* ARM SME ZA registers */
+#define NT_ARM_ZT	0x40d		/* ARM SME ZT registers */
+#define NT_ARM_FPMR	0x40e		/* ARM floating point mode register */
+#define NT_ARM_POE	0x40f		/* ARM POE registers */
+#define NT_ARM_GCS	0x410		/* ARM GCS state */
+#define NT_ARC_V2	0x600		/* ARCv2 accumulator/extra registers */
+#define NT_VMCOREDD	0x700		/* Vmcore Device Dump Note */
+#define NT_MIPS_DSP	0x800		/* MIPS DSP ASE registers */
+#define NT_MIPS_FP_MODE	0x801		/* MIPS floating-point mode */
+#define NT_MIPS_MSA	0x802		/* MIPS SIMD registers */
+#define NT_RISCV_CSR	0x900		/* RISC-V Control and Status Registers */
+#define NT_RISCV_VECTOR	0x901		/* RISC-V vector registers */
+#define NT_RISCV_TAGGED_ADDR_CTRL 0x902	/* RISC-V tagged address control (prctl()) */
+#define NT_LOONGARCH_CPUCFG	0xa00	/* LoongArch CPU config registers */
+#define NT_LOONGARCH_CSR	0xa01	/* LoongArch control and status registers */
+#define NT_LOONGARCH_LSX	0xa02	/* LoongArch Loongson SIMD Extension registers */
+#define NT_LOONGARCH_LASX	0xa03	/* LoongArch Loongson Advanced SIMD Extension registers */
+#define NT_LOONGARCH_LBT	0xa04	/* LoongArch Loongson Binary Translation registers */
+#define NT_LOONGARCH_HW_BREAK	0xa05   /* LoongArch hardware breakpoint registers */
+#define NT_LOONGARCH_HW_WATCH	0xa06   /* LoongArch hardware watchpoint registers */
+
+/* Note types with note name "GNU" */
+#define NT_GNU_PROPERTY_TYPE_0	5
+
+/* Note header in a PT_NOTE section */
+typedef struct elf32_note {
+  Elf32_Word	n_namesz;	/* Name size */
+  Elf32_Word	n_descsz;	/* Content size */
+  Elf32_Word	n_type;		/* Content type */
+} Elf32_Nhdr;
+
+/* Note header in a PT_NOTE section */
+typedef struct elf64_note {
+  Elf64_Word n_namesz;	/* Name size */
+  Elf64_Word n_descsz;	/* Content size */
+  Elf64_Word n_type;	/* Content type */
+} Elf64_Nhdr;
+
+/* .note.gnu.property types for EM_AARCH64: */
+#define GNU_PROPERTY_AARCH64_FEATURE_1_AND	0xc0000000
+
+/* Bits for GNU_PROPERTY_AARCH64_FEATURE_1_BTI */
+#define GNU_PROPERTY_AARCH64_FEATURE_1_BTI	(1U << 0)
+
+typedef struct {
+  Elf32_Half	vd_version;
+  Elf32_Half	vd_flags;
+  Elf32_Half	vd_ndx;
+  Elf32_Half	vd_cnt;
+  Elf32_Word	vd_hash;
+  Elf32_Word	vd_aux;
+  Elf32_Word	vd_next;
+} Elf32_Verdef;
+
+typedef struct {
+  Elf64_Half	vd_version;
+  Elf64_Half	vd_flags;
+  Elf64_Half	vd_ndx;
+  Elf64_Half	vd_cnt;
+  Elf64_Word	vd_hash;
+  Elf64_Word	vd_aux;
+  Elf64_Word	vd_next;
+} Elf64_Verdef;
+
+typedef struct {
+  Elf32_Word    vda_name;
+  Elf32_Word    vda_next;
+} Elf32_Verdaux;
+
+typedef struct {
+  Elf64_Word    vda_name;
+  Elf64_Word    vda_next;
+} Elf64_Verdaux;
+
+#endif /* _LINUX_ELF_H */

From 1a59f5d31569c742da3dafbbb5620901de11a245 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Wed, 26 Feb 2025 12:44:47 +0100
Subject: [PATCH 0862/1173] selftests: Add headers target
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some selftests need access to a full UAPI headers tree, for example when
building with nolibc which heavily relies on UAPI headers.
A reference to such a tree is available in the KHDR_INCLUDES variable,
but there is currently no way to populate such a tree automatically.

Provide a target that the tests can depend on to get access to usable
UAPI headers.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Acked-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/all/20250226-parse_vdso-nolibc-v2-8-28e14e031ed8@linutronix.de
---
 tools/testing/selftests/lib.mk | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index d6edcfcb5be83..5303900339292 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -228,4 +228,7 @@ $(OUTPUT)/%:%.S
 	$(LINK.S) $^ $(LDLIBS) -o $@
 endif
 
-.PHONY: run_tests all clean install emit_tests gen_mods_dir clean_mods_dir
+headers:
+	$(Q)$(MAKE) -C $(top_srcdir) headers
+
+.PHONY: run_tests all clean install emit_tests gen_mods_dir clean_mods_dir headers

From 5caaa0aa7c61513a2f606fd6d00fc29ae475ce9e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Wed, 26 Feb 2025 12:44:48 +0100
Subject: [PATCH 0863/1173] tools/nolibc: add limits.h shim header
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

limits.h is a widely used standard header.  Missing it from nolibc requires
adoption effort to port applications.

Add a shim header which includes the global nolibc.h header.
It makes all nolibc symbols available.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Willy Tarreau <w@1wt.eu>
Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Acked-by: Willy Tarreau <w@1wt.eu>
Acked-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/all/20250226-parse_vdso-nolibc-v2-9-28e14e031ed8@linutronix.de
---
 tools/include/nolibc/Makefile | 1 +
 tools/include/nolibc/limits.h | 7 +++++++
 2 files changed, 8 insertions(+)
 create mode 100644 tools/include/nolibc/limits.h

diff --git a/tools/include/nolibc/Makefile b/tools/include/nolibc/Makefile
index a1f55fb24bb38..c1299a0531457 100644
--- a/tools/include/nolibc/Makefile
+++ b/tools/include/nolibc/Makefile
@@ -30,6 +30,7 @@ all_files := \
 		crt.h \
 		ctype.h \
 		errno.h \
+		limits.h \
 		nolibc.h \
 		signal.h \
 		stackprotector.h \
diff --git a/tools/include/nolibc/limits.h b/tools/include/nolibc/limits.h
new file mode 100644
index 0000000000000..306d4141f4d24
--- /dev/null
+++ b/tools/include/nolibc/limits.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * Shim limits.h header for NOLIBC.
+ * Copyright (C) 2025 Thomas Weißschuh <thomas.weissschuh@linutronix.de>
+ */
+
+#include "nolibc.h"

From 05c204acf5131740f5f4e193c9749b92da4bcb16 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Wed, 26 Feb 2025 12:44:49 +0100
Subject: [PATCH 0864/1173] selftests: vDSO: vdso_standalone_test_x86: Use
 vdso_init_form_sysinfo_ehdr
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

vdso_standalone_test_x86 is the only user of vdso_init_from_auxv().
Instead of combining the parsing the aux vector with the parsing of the
vDSO, split them apart into getauxval() and the regular
vdso_init_from_sysinfo_ehdr().

The implementation of getauxval() is taken from
tools/include/nolibc/stdlib.h.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Acked-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/all/20250226-parse_vdso-nolibc-v2-10-28e14e031ed8@linutronix.de
---
 .../selftests/vDSO/vdso_standalone_test_x86.c | 27 ++++++++++++++++++-
 1 file changed, 26 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c b/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c
index 644915862af88..500608f89c66b 100644
--- a/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c
+++ b/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c
@@ -15,6 +15,7 @@
 #include <sys/time.h>
 #include <unistd.h>
 #include <stdint.h>
+#include <linux/auxvec.h>
 
 #include "parse_vdso.h"
 
@@ -84,6 +85,30 @@ void to_base10(char *lastdig, time_t n)
 	}
 }
 
+unsigned long getauxval(const unsigned long *auxv, unsigned long type)
+{
+	unsigned long ret;
+
+	if (!auxv)
+		return 0;
+
+	while (1) {
+		if (!auxv[0] && !auxv[1]) {
+			ret = 0;
+			break;
+		}
+
+		if (auxv[0] == type) {
+			ret = auxv[1];
+			break;
+		}
+
+		auxv += 2;
+	}
+
+	return ret;
+}
+
 void c_main(void **stack)
 {
 	/* Parse the stack */
@@ -96,7 +121,7 @@ void c_main(void **stack)
 	stack++;
 
 	/* Now we're pointing at auxv.  Initialize the vDSO parser. */
-	vdso_init_from_auxv((void *)stack);
+	vdso_init_from_sysinfo_ehdr(getauxval((unsigned long *)stack, AT_SYSINFO_EHDR));
 
 	/* Find gettimeofday. */
 	typedef long (*gtod_t)(struct timeval *tv, struct timezone *tz);

From 09dcec64707df85f5def668d4724fce832114d91 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Wed, 26 Feb 2025 12:44:50 +0100
Subject: [PATCH 0865/1173] selftests: vDSO: parse_vdso: Drop
 vdso_init_from_auxv()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There are no users left.

This also removes the usage of ElfXX_auxv_t, which is not formally
standardized.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Acked-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/all/20250226-parse_vdso-nolibc-v2-11-28e14e031ed8@linutronix.de
---
 tools/testing/selftests/vDSO/parse_vdso.c | 14 --------------
 tools/testing/selftests/vDSO/parse_vdso.h |  1 -
 2 files changed, 15 deletions(-)

diff --git a/tools/testing/selftests/vDSO/parse_vdso.c b/tools/testing/selftests/vDSO/parse_vdso.c
index 2fe5e983cb22f..3638fe605e80c 100644
--- a/tools/testing/selftests/vDSO/parse_vdso.c
+++ b/tools/testing/selftests/vDSO/parse_vdso.c
@@ -297,17 +297,3 @@ void *vdso_sym(const char *version, const char *name)
 
 	return 0;
 }
-
-void vdso_init_from_auxv(void *auxv)
-{
-	ELF(auxv_t) *elf_auxv = auxv;
-	for (int i = 0; elf_auxv[i].a_type != AT_NULL; i++)
-	{
-		if (elf_auxv[i].a_type == AT_SYSINFO_EHDR) {
-			vdso_init_from_sysinfo_ehdr(elf_auxv[i].a_un.a_val);
-			return;
-		}
-	}
-
-	vdso_info.valid = false;
-}
diff --git a/tools/testing/selftests/vDSO/parse_vdso.h b/tools/testing/selftests/vDSO/parse_vdso.h
index de0453067d7cd..09d068ed11f97 100644
--- a/tools/testing/selftests/vDSO/parse_vdso.h
+++ b/tools/testing/selftests/vDSO/parse_vdso.h
@@ -26,6 +26,5 @@
  */
 void *vdso_sym(const char *version, const char *name);
 void vdso_init_from_sysinfo_ehdr(uintptr_t base);
-void vdso_init_from_auxv(void *auxv);
 
 #endif

From c9fbaa879508ea36f5be0b3f1125b8f9f11b4945 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Wed, 26 Feb 2025 12:44:51 +0100
Subject: [PATCH 0866/1173] selftests: vDSO: parse_vdso: Use UAPI headers
 instead of libc headers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To allow the usage of parse_vdso.c together with a limited libc like
nolibc, use the kernels own elf.h and auxvec.h headers.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Acked-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/all/20250226-parse_vdso-nolibc-v2-12-28e14e031ed8@linutronix.de
---
 tools/testing/selftests/vDSO/Makefile     | 3 +++
 tools/testing/selftests/vDSO/parse_vdso.c | 3 ++-
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/vDSO/Makefile b/tools/testing/selftests/vDSO/Makefile
index 1cf14a8da4380..bc8ca186fb877 100644
--- a/tools/testing/selftests/vDSO/Makefile
+++ b/tools/testing/selftests/vDSO/Makefile
@@ -19,6 +19,9 @@ LDLIBS += -lgcc_s
 endif
 
 include ../lib.mk
+
+CFLAGS += $(TOOLS_INCLUDES)
+
 $(OUTPUT)/vdso_test_gettimeofday: parse_vdso.c vdso_test_gettimeofday.c
 $(OUTPUT)/vdso_test_getcpu: parse_vdso.c vdso_test_getcpu.c
 $(OUTPUT)/vdso_test_abi: parse_vdso.c vdso_test_abi.c
diff --git a/tools/testing/selftests/vDSO/parse_vdso.c b/tools/testing/selftests/vDSO/parse_vdso.c
index 3638fe605e80c..200c534cc70e2 100644
--- a/tools/testing/selftests/vDSO/parse_vdso.c
+++ b/tools/testing/selftests/vDSO/parse_vdso.c
@@ -19,7 +19,8 @@
 #include <stdint.h>
 #include <string.h>
 #include <limits.h>
-#include <elf.h>
+#include <linux/auxvec.h>
+#include <linux/elf.h>
 
 #include "parse_vdso.h"
 

From 032e871686483ec1bac27ce73e7094692fc76268 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Wed, 26 Feb 2025 12:44:52 +0100
Subject: [PATCH 0867/1173] selftests: vDSO: parse_vdso: Test __SIZEOF_LONG__
 instead of ULONG_MAX
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

According to limits.h(2) ULONG_MAX is only guaranteed to expand to an
expression, not a symbolic constant which can be evaluated by the
preprocessor.

Specifically the definition of ULONG_MAX from nolibc can not be evaluated
by the preprocessor. To provide compatibility with nolibc, check with
__SIZEOF_LONG__ instead, with is provided directly by the preprocessor
and therefore always a symbolic constant.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Acked-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/all/20250226-parse_vdso-nolibc-v2-13-28e14e031ed8@linutronix.de
---
 tools/testing/selftests/vDSO/parse_vdso.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/vDSO/parse_vdso.c b/tools/testing/selftests/vDSO/parse_vdso.c
index 200c534cc70e2..902b8f9984a1f 100644
--- a/tools/testing/selftests/vDSO/parse_vdso.c
+++ b/tools/testing/selftests/vDSO/parse_vdso.c
@@ -26,7 +26,7 @@
 
 /* And here's the code. */
 #ifndef ELF_BITS
-# if ULONG_MAX > 0xffffffffUL
+# if __SIZEOF_LONG__ >= 8
 #  define ELF_BITS 64
 # else
 #  define ELF_BITS 32

From 97a88141241fcf3d1e54a120afefea04fbd1a484 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Wed, 26 Feb 2025 12:44:53 +0100
Subject: [PATCH 0868/1173] selftests: vDSO: vdso_test_gettimeofday: Clean up
 includes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some unnecessary headers are included, remove them.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Acked-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/all/20250226-parse_vdso-nolibc-v2-14-28e14e031ed8@linutronix.de
---
 tools/testing/selftests/vDSO/vdso_test_gettimeofday.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/tools/testing/selftests/vDSO/vdso_test_gettimeofday.c b/tools/testing/selftests/vDSO/vdso_test_gettimeofday.c
index e31b18ffae338..636a56ccf8e4e 100644
--- a/tools/testing/selftests/vDSO/vdso_test_gettimeofday.c
+++ b/tools/testing/selftests/vDSO/vdso_test_gettimeofday.c
@@ -10,8 +10,6 @@
  * Tested on x86, 32-bit and 64-bit.  It may work on other architectures, too.
  */
 
-#include <stdint.h>
-#include <elf.h>
 #include <stdio.h>
 #include <sys/auxv.h>
 #include <sys/time.h>

From 4f65df6a58b3de5132f978305c5f807ec3803943 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Wed, 26 Feb 2025 12:44:54 +0100
Subject: [PATCH 0869/1173] selftests: vDSO: vdso_test_gettimeofday: Make
 compatible with nolibc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

nolibc does not provide sys/time.h and sys/auxv.h,
instead their definitions are available unconditionally.

Guard the includes so they are not attempted on nolibc.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Acked-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/all/20250226-parse_vdso-nolibc-v2-15-28e14e031ed8@linutronix.de
---
 tools/testing/selftests/vDSO/vdso_test_gettimeofday.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/testing/selftests/vDSO/vdso_test_gettimeofday.c b/tools/testing/selftests/vDSO/vdso_test_gettimeofday.c
index 636a56ccf8e4e..9ce795b806f09 100644
--- a/tools/testing/selftests/vDSO/vdso_test_gettimeofday.c
+++ b/tools/testing/selftests/vDSO/vdso_test_gettimeofday.c
@@ -11,8 +11,10 @@
  */
 
 #include <stdio.h>
+#ifndef NOLIBC
 #include <sys/auxv.h>
 #include <sys/time.h>
+#endif
 
 #include "../kselftest.h"
 #include "parse_vdso.h"

From 8770a9183fe18442c7cfbb56bb7e006462775a91 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Wed, 26 Feb 2025 12:44:55 +0100
Subject: [PATCH 0870/1173] selftests: vDSO: vdso_standalone_test_x86: Switch
 to nolibc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

vdso_standalone_test_x86 provides its own ASM syscall wrappers and
_start() implementation. The in-tree nolibc library already provides
this functionality for multiple architectures. By making use of nolibc,
the standalone testcase can be built from the exact same codebase as the
non-standalone version.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Acked-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/all/20250226-parse_vdso-nolibc-v2-16-28e14e031ed8@linutronix.de
---
 tools/testing/selftests/vDSO/Makefile         |   8 +-
 .../selftests/vDSO/vdso_standalone_test_x86.c | 175 ++++--------------
 2 files changed, 39 insertions(+), 144 deletions(-)

diff --git a/tools/testing/selftests/vDSO/Makefile b/tools/testing/selftests/vDSO/Makefile
index bc8ca186fb877..12a0614b9fd49 100644
--- a/tools/testing/selftests/vDSO/Makefile
+++ b/tools/testing/selftests/vDSO/Makefile
@@ -22,13 +22,17 @@ include ../lib.mk
 
 CFLAGS += $(TOOLS_INCLUDES)
 
+CFLAGS_NOLIBC := -nostdlib -nostdinc -ffreestanding -fno-asynchronous-unwind-tables \
+		 -fno-stack-protector -include $(top_srcdir)/tools/include/nolibc/nolibc.h \
+		 -I$(top_srcdir)/tools/include/nolibc/ $(KHDR_INCLUDES)
+
 $(OUTPUT)/vdso_test_gettimeofday: parse_vdso.c vdso_test_gettimeofday.c
 $(OUTPUT)/vdso_test_getcpu: parse_vdso.c vdso_test_getcpu.c
 $(OUTPUT)/vdso_test_abi: parse_vdso.c vdso_test_abi.c
 $(OUTPUT)/vdso_test_clock_getres: vdso_test_clock_getres.c
 
-$(OUTPUT)/vdso_standalone_test_x86: vdso_standalone_test_x86.c parse_vdso.c
-$(OUTPUT)/vdso_standalone_test_x86: CFLAGS +=-nostdlib -fno-asynchronous-unwind-tables -fno-stack-protector
+$(OUTPUT)/vdso_standalone_test_x86: vdso_standalone_test_x86.c parse_vdso.c | headers
+$(OUTPUT)/vdso_standalone_test_x86: CFLAGS:=$(CFLAGS_NOLIBC) $(CFLAGS)
 
 $(OUTPUT)/vdso_test_correctness: vdso_test_correctness.c
 $(OUTPUT)/vdso_test_correctness: LDFLAGS += -ldl
diff --git a/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c b/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c
index 500608f89c66b..9ce795b806f09 100644
--- a/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c
+++ b/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c
@@ -1,167 +1,58 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * vdso_test.c: Sample code to test parse_vdso.c on x86
- * Copyright (c) 2011-2014 Andy Lutomirski
+ * vdso_test_gettimeofday.c: Sample code to test parse_vdso.c and
+ *                           vDSO gettimeofday()
+ * Copyright (c) 2014 Andy Lutomirski
  *
- * You can amuse yourself by compiling with:
- * gcc -std=gnu99 -nostdlib
- *     -Os -fno-asynchronous-unwind-tables -flto -lgcc_s
- *      vdso_standalone_test_x86.c parse_vdso.c
- * to generate a small binary.  On x86_64, you can omit -lgcc_s
- * if you want the binary to be completely standalone.
+ * Compile with:
+ * gcc -std=gnu99 vdso_test_gettimeofday.c parse_vdso_gettimeofday.c
+ *
+ * Tested on x86, 32-bit and 64-bit.  It may work on other architectures, too.
  */
 
-#include <sys/syscall.h>
+#include <stdio.h>
+#ifndef NOLIBC
+#include <sys/auxv.h>
 #include <sys/time.h>
-#include <unistd.h>
-#include <stdint.h>
-#include <linux/auxvec.h>
-
-#include "parse_vdso.h"
-
-/* We need some libc functions... */
-int strcmp(const char *a, const char *b)
-{
-	/* This implementation is buggy: it never returns -1. */
-	while (*a || *b) {
-		if (*a != *b)
-			return 1;
-		if (*a == 0 || *b == 0)
-			return 1;
-		a++;
-		b++;
-	}
-
-	return 0;
-}
-
-/*
- * The clang build needs this, although gcc does not.
- * Stolen from lib/string.c.
- */
-void *memcpy(void *dest, const void *src, size_t count)
-{
-	char *tmp = dest;
-	const char *s = src;
-
-	while (count--)
-		*tmp++ = *s++;
-	return dest;
-}
-
-/* ...and two syscalls.  This is x86-specific. */
-static inline long x86_syscall3(long nr, long a0, long a1, long a2)
-{
-	long ret;
-#ifdef __x86_64__
-	asm volatile ("syscall" : "=a" (ret) : "a" (nr),
-		      "D" (a0), "S" (a1), "d" (a2) :
-		      "cc", "memory", "rcx",
-		      "r8", "r9", "r10", "r11" );
-#else
-	asm volatile ("int $0x80" : "=a" (ret) : "a" (nr),
-		      "b" (a0), "c" (a1), "d" (a2) :
-		      "cc", "memory" );
 #endif
-	return ret;
-}
-
-static inline long linux_write(int fd, const void *data, size_t len)
-{
-	return x86_syscall3(__NR_write, fd, (long)data, (long)len);
-}
 
-static inline void linux_exit(int code)
-{
-	x86_syscall3(__NR_exit, code, 0, 0);
-}
-
-void to_base10(char *lastdig, time_t n)
-{
-	while (n) {
-		*lastdig = (n % 10) + '0';
-		n /= 10;
-		lastdig--;
-	}
-}
+#include "../kselftest.h"
+#include "parse_vdso.h"
+#include "vdso_config.h"
+#include "vdso_call.h"
 
-unsigned long getauxval(const unsigned long *auxv, unsigned long type)
+int main(int argc, char **argv)
 {
-	unsigned long ret;
-
-	if (!auxv)
-		return 0;
-
-	while (1) {
-		if (!auxv[0] && !auxv[1]) {
-			ret = 0;
-			break;
-		}
+	const char *version = versions[VDSO_VERSION];
+	const char **name = (const char **)&names[VDSO_NAMES];
 
-		if (auxv[0] == type) {
-			ret = auxv[1];
-			break;
-		}
-
-		auxv += 2;
+	unsigned long sysinfo_ehdr = getauxval(AT_SYSINFO_EHDR);
+	if (!sysinfo_ehdr) {
+		printf("AT_SYSINFO_EHDR is not present!\n");
+		return KSFT_SKIP;
 	}
 
-	return ret;
-}
-
-void c_main(void **stack)
-{
-	/* Parse the stack */
-	long argc = (long)*stack;
-	stack += argc + 2;
-
-	/* Now we're pointing at the environment.  Skip it. */
-	while(*stack)
-		stack++;
-	stack++;
-
-	/* Now we're pointing at auxv.  Initialize the vDSO parser. */
-	vdso_init_from_sysinfo_ehdr(getauxval((unsigned long *)stack, AT_SYSINFO_EHDR));
+	vdso_init_from_sysinfo_ehdr(getauxval(AT_SYSINFO_EHDR));
 
 	/* Find gettimeofday. */
 	typedef long (*gtod_t)(struct timeval *tv, struct timezone *tz);
-	gtod_t gtod = (gtod_t)vdso_sym("LINUX_2.6", "__vdso_gettimeofday");
+	gtod_t gtod = (gtod_t)vdso_sym(version, name[0]);
 
-	if (!gtod)
-		linux_exit(1);
+	if (!gtod) {
+		printf("Could not find %s\n", name[0]);
+		return KSFT_SKIP;
+	}
 
 	struct timeval tv;
-	long ret = gtod(&tv, 0);
+	long ret = VDSO_CALL(gtod, 2, &tv, 0);
 
 	if (ret == 0) {
-		char buf[] = "The time is                     .000000\n";
-		to_base10(buf + 31, tv.tv_sec);
-		to_base10(buf + 38, tv.tv_usec);
-		linux_write(1, buf, sizeof(buf) - 1);
+		printf("The time is %lld.%06lld\n",
+		       (long long)tv.tv_sec, (long long)tv.tv_usec);
 	} else {
-		linux_exit(ret);
+		printf("%s failed\n", name[0]);
+		return KSFT_FAIL;
 	}
 
-	linux_exit(0);
+	return 0;
 }
-
-/*
- * This is the real entry point.  It passes the initial stack into
- * the C entry point.
- */
-asm (
-	".text\n"
-	".global _start\n"
-	".type _start,@function\n"
-	"_start:\n\t"
-#ifdef __x86_64__
-	"mov %rsp,%rdi\n\t"
-	"and $-16,%rsp\n\t"
-	"sub $8,%rsp\n\t"
-	"jmp c_main"
-#else
-	"push %esp\n\t"
-	"call c_main\n\t"
-	"int $3"
-#endif
-	);

From 399fd7a26441586021ca3722f6a98ff33ed32caf Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Mon, 3 Mar 2025 13:31:11 -0500
Subject: [PATCH 0871/1173] x86/asm: Merge KSTK_ESP() implementations

Commit:

  263042e4630a ("Save user RSP in pt_regs->sp on SYSCALL64 fastpath")

simplified the 64-bit implementation of KSTK_ESP() which is
now identical to 32-bit.  Merge them into a common definition.

No functional change.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250303183111.2245129-1-brgerst@gmail.com
---
 arch/x86/include/asm/processor.h | 5 +----
 arch/x86/kernel/process_64.c     | 5 -----
 2 files changed, 1 insertion(+), 9 deletions(-)

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index c0cd10182e90c..0c911083fdd1c 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -668,8 +668,6 @@ static __always_inline void prefetchw(const void *x)
 	.sysenter_cs		= __KERNEL_CS,				  \
 }
 
-#define KSTK_ESP(task)		(task_pt_regs(task)->sp)
-
 #else
 extern unsigned long __top_init_kernel_stack[];
 
@@ -677,8 +675,6 @@ extern unsigned long __top_init_kernel_stack[];
 	.sp	= (unsigned long)&__top_init_kernel_stack,		\
 }
 
-extern unsigned long KSTK_ESP(struct task_struct *task);
-
 #endif /* CONFIG_X86_64 */
 
 extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
@@ -692,6 +688,7 @@ extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
 #define TASK_UNMAPPED_BASE		__TASK_UNMAPPED_BASE(TASK_SIZE_LOW)
 
 #define KSTK_EIP(task)		(task_pt_regs(task)->ip)
+#define KSTK_ESP(task)		(task_pt_regs(task)->sp)
 
 /* Get/set a process' ability to use the timestamp counter instruction */
 #define GET_TSC_CTL(adr)	get_tsc_mode((adr))
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 4ca73ddfb30bc..f983d2a57ac3c 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -979,8 +979,3 @@ long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2)
 
 	return ret;
 }
-
-unsigned long KSTK_ESP(struct task_struct *task)
-{
-	return task_pt_regs(task)->sp;
-}

From 604ea3e90b17f27928a64d86259c57710c254438 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Mon, 3 Mar 2025 12:01:15 -0500
Subject: [PATCH 0872/1173] x86/smp/32: Remove safe_smp_processor_id()

The safe_smp_processor_id() function was originally implemented in:

  dc2bc768a009 ("stack overflow safe kdump: safe_smp_processor_id()")

to mitigate the CPU number corruption on a stack overflow.  At the time,
x86-32 stored the CPU number in thread_struct, which was located at the
bottom of the task stack and thus vulnerable to an overflow.

The CPU number is now located in percpu memory, so this workaround
is no longer needed.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Uros Bizjak <ubizjak@gmail.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Link: https://lore.kernel.org/r/20250303170115.2176553-1-brgerst@gmail.com
---
 arch/x86/include/asm/cpu.h |  1 -
 arch/x86/include/asm/smp.h |  6 ------
 arch/x86/kernel/apic/ipi.c | 30 ------------------------------
 arch/x86/kernel/crash.c    |  2 +-
 arch/x86/kernel/reboot.c   |  2 +-
 5 files changed, 2 insertions(+), 39 deletions(-)

diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index 98eced5084ca7..f44bbce18859e 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -12,7 +12,6 @@
 #ifndef CONFIG_SMP
 #define cpu_physical_id(cpu)			boot_cpu_physical_apicid
 #define cpu_acpi_id(cpu)			0
-#define safe_smp_processor_id()			0
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index ca073f40698fa..2419e5086c9ee 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -136,12 +136,6 @@ __visible void smp_call_function_single_interrupt(struct pt_regs *r);
 #define raw_smp_processor_id()  this_cpu_read(pcpu_hot.cpu_number)
 #define __smp_processor_id() __this_cpu_read(pcpu_hot.cpu_number)
 
-#ifdef CONFIG_X86_32
-extern int safe_smp_processor_id(void);
-#else
-# define safe_smp_processor_id()	smp_processor_id()
-#endif
-
 static inline struct cpumask *cpu_llc_shared_mask(int cpu)
 {
 	return per_cpu(cpu_llc_shared_map, cpu);
diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c
index 5da693d633b78..23025a3a1db4d 100644
--- a/arch/x86/kernel/apic/ipi.c
+++ b/arch/x86/kernel/apic/ipi.c
@@ -287,34 +287,4 @@ void default_send_IPI_mask_logical(const struct cpumask *cpumask, int vector)
 	__default_send_IPI_dest_field(mask, vector, APIC_DEST_LOGICAL);
 	local_irq_restore(flags);
 }
-
-#ifdef CONFIG_SMP
-static int convert_apicid_to_cpu(u32 apic_id)
-{
-	int i;
-
-	for_each_possible_cpu(i) {
-		if (per_cpu(x86_cpu_to_apicid, i) == apic_id)
-			return i;
-	}
-	return -1;
-}
-
-int safe_smp_processor_id(void)
-{
-	u32 apicid;
-	int cpuid;
-
-	if (!boot_cpu_has(X86_FEATURE_APIC))
-		return 0;
-
-	apicid = read_apic_id();
-	if (apicid == BAD_APICID)
-		return 0;
-
-	cpuid = convert_apicid_to_cpu(apicid);
-
-	return cpuid >= 0 ? cpuid : 0;
-}
-#endif
 #endif
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 340af81556584..0be61c45400cd 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -140,7 +140,7 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
 	x86_platform.guest.enc_kexec_begin();
 	x86_platform.guest.enc_kexec_finish();
 
-	crash_save_cpu(regs, safe_smp_processor_id());
+	crash_save_cpu(regs, smp_processor_id());
 }
 
 #if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_HOTPLUG)
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 9aaac1f9f45b5..964f6b0a3d68c 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -921,7 +921,7 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback)
 		return;
 
 	/* Make a note of crashing cpu. Will be used in NMI callback. */
-	crashing_cpu = safe_smp_processor_id();
+	crashing_cpu = smp_processor_id();
 
 	shootdown_callback = callback;
 

From 01499ae673dc66cf5e98589648848b520f6fdfe9 Mon Sep 17 00:00:00 2001
From: Hans Zhang <18255117159@163.com>
Date: Mon, 3 Mar 2025 20:10:08 +0800
Subject: [PATCH 0873/1173] genirq/msi: Expose MSI message data in debugfs

When debugging MSI-related hardware issues (e.g. interrupt delivery
failures), developers currently need to either:

  1. Recompile the kernel with dynamic debug for tracing msi_desc.
  2. Manually read device registers through low-level tools.

Both approaches become challenging in production environments where
dynamic debugging is often disabled.

The interrupt core provides a debugfs interface for inspection of interrupt
related data, which contains the per interrupt information in the view of
the hierarchical interrupt domains. Though this interface does not expose
the MSI address/data pair, which is important information to:

  - Verify whether the MSI configuration matches the hardware expectations
  - Diagnose interrupt routing errors (e.g., mismatched destination ID)
  - Validate remapping behavior in virtualized environments

Implement the debug_show() callback for the generic MSI interrupt domains,
and use it to expose the MSI address/data pair in the per interrupt
diagnostics.

Sample output:
  address_hi: 0x00000000
  address_lo: 0xfe670040
  msg_data:   0x00000001

[ tglx: Massaged change log. Use irq_data_get_msi_desc() to avoid pointless
  	lookup. ]

Signed-off-by: Hans Zhang <18255117159@163.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250303121008.309265-1-18255117159@163.com
---
 kernel/irq/msi.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 396a067a8a56b..fa92882efdb1f 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -15,6 +15,7 @@
 #include <linux/mutex.h>
 #include <linux/pci.h>
 #include <linux/slab.h>
+#include <linux/seq_file.h>
 #include <linux/sysfs.h>
 #include <linux/types.h>
 #include <linux/xarray.h>
@@ -756,12 +757,30 @@ static int msi_domain_translate(struct irq_domain *domain, struct irq_fwspec *fw
 	return info->ops->msi_translate(domain, fwspec, hwirq, type);
 }
 
+#ifdef CONFIG_GENERIC_IRQ_DEBUGFS
+static void msi_domain_debug_show(struct seq_file *m, struct irq_domain *d,
+				  struct irq_data *irqd, int ind)
+{
+	struct msi_desc *desc = irq_data_get_msi_desc(irqd);
+
+	if (!desc)
+		return;
+
+	seq_printf(m, "\n%*saddress_hi: 0x%08x", ind + 1, "", desc->msg.address_hi);
+	seq_printf(m, "\n%*saddress_lo: 0x%08x", ind + 1, "", desc->msg.address_lo);
+	seq_printf(m, "\n%*smsg_data:   0x%08x\n", ind + 1, "", desc->msg.data);
+}
+#endif
+
 static const struct irq_domain_ops msi_domain_ops = {
 	.alloc		= msi_domain_alloc,
 	.free		= msi_domain_free,
 	.activate	= msi_domain_activate,
 	.deactivate	= msi_domain_deactivate,
 	.translate	= msi_domain_translate,
+#ifdef CONFIG_GENERIC_IRQ_DEBUGFS
+	.debug_show     = msi_domain_debug_show,
+#endif
 };
 
 static irq_hw_number_t msi_domain_ops_get_hwirq(struct msi_domain_info *info,

From cc5bfc4e16fc1d1c520cd7bb28646e82b6e69217 Mon Sep 17 00:00:00 2001
From: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Date: Thu, 30 Jan 2025 23:49:31 +0000
Subject: [PATCH 0874/1173] usb: dwc3: Set SUSPENDENABLE soon after phy init

After phy initialization, some phy operations can only be executed while
in lower P states. Ensure GUSB3PIPECTL.SUSPENDENABLE and
GUSB2PHYCFG.SUSPHY are set soon after initialization to avoid blocking
phy ops.

Previously the SUSPENDENABLE bits are only set after the controller
initialization, which may not happen right away if there's no gadget
driver or xhci driver bound. Revise this to clear SUSPENDENABLE bits
only when there's mode switching (change in GCTL.PRTCAPDIR).

Fixes: 6d735722063a ("usb: dwc3: core: Prevent phy suspend during init")
Cc: stable <stable@kernel.org>
Signed-off-by: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Link: https://lore.kernel.org/r/633aef0afee7d56d2316f7cc3e1b2a6d518a8cc9.1738280911.git.Thinh.Nguyen@synopsys.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/core.c | 69 +++++++++++++++++++++++++----------------
 drivers/usb/dwc3/core.h |  2 +-
 drivers/usb/dwc3/drd.c  |  4 +--
 3 files changed, 45 insertions(+), 30 deletions(-)

diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index 2c472cb97f6c7..66a08b5271653 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -131,11 +131,24 @@ void dwc3_enable_susphy(struct dwc3 *dwc, bool enable)
 	}
 }
 
-void dwc3_set_prtcap(struct dwc3 *dwc, u32 mode)
+void dwc3_set_prtcap(struct dwc3 *dwc, u32 mode, bool ignore_susphy)
 {
+	unsigned int hw_mode;
 	u32 reg;
 
 	reg = dwc3_readl(dwc->regs, DWC3_GCTL);
+
+	 /*
+	  * For DRD controllers, GUSB3PIPECTL.SUSPENDENABLE and
+	  * GUSB2PHYCFG.SUSPHY should be cleared during mode switching,
+	  * and they can be set after core initialization.
+	  */
+	hw_mode = DWC3_GHWPARAMS0_MODE(dwc->hwparams.hwparams0);
+	if (hw_mode == DWC3_GHWPARAMS0_MODE_DRD && !ignore_susphy) {
+		if (DWC3_GCTL_PRTCAP(reg) != mode)
+			dwc3_enable_susphy(dwc, false);
+	}
+
 	reg &= ~(DWC3_GCTL_PRTCAPDIR(DWC3_GCTL_PRTCAP_OTG));
 	reg |= DWC3_GCTL_PRTCAPDIR(mode);
 	dwc3_writel(dwc->regs, DWC3_GCTL, reg);
@@ -216,7 +229,7 @@ static void __dwc3_set_mode(struct work_struct *work)
 
 	spin_lock_irqsave(&dwc->lock, flags);
 
-	dwc3_set_prtcap(dwc, desired_dr_role);
+	dwc3_set_prtcap(dwc, desired_dr_role, false);
 
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
@@ -658,16 +671,7 @@ static int dwc3_ss_phy_setup(struct dwc3 *dwc, int index)
 	 */
 	reg &= ~DWC3_GUSB3PIPECTL_UX_EXIT_PX;
 
-	/*
-	 * Above DWC_usb3.0 1.94a, it is recommended to set
-	 * DWC3_GUSB3PIPECTL_SUSPHY to '0' during coreConsultant configuration.
-	 * So default value will be '0' when the core is reset. Application
-	 * needs to set it to '1' after the core initialization is completed.
-	 *
-	 * Similarly for DRD controllers, GUSB3PIPECTL.SUSPENDENABLE must be
-	 * cleared after power-on reset, and it can be set after core
-	 * initialization.
-	 */
+	/* Ensure the GUSB3PIPECTL.SUSPENDENABLE is cleared prior to phy init. */
 	reg &= ~DWC3_GUSB3PIPECTL_SUSPHY;
 
 	if (dwc->u2ss_inp3_quirk)
@@ -747,15 +751,7 @@ static int dwc3_hs_phy_setup(struct dwc3 *dwc, int index)
 		break;
 	}
 
-	/*
-	 * Above DWC_usb3.0 1.94a, it is recommended to set
-	 * DWC3_GUSB2PHYCFG_SUSPHY to '0' during coreConsultant configuration.
-	 * So default value will be '0' when the core is reset. Application
-	 * needs to set it to '1' after the core initialization is completed.
-	 *
-	 * Similarly for DRD controllers, GUSB2PHYCFG.SUSPHY must be cleared
-	 * after power-on reset, and it can be set after core initialization.
-	 */
+	/* Ensure the GUSB2PHYCFG.SUSPHY is cleared prior to phy init. */
 	reg &= ~DWC3_GUSB2PHYCFG_SUSPHY;
 
 	if (dwc->dis_enblslpm_quirk)
@@ -830,6 +826,25 @@ static int dwc3_phy_init(struct dwc3 *dwc)
 			goto err_exit_usb3_phy;
 	}
 
+	/*
+	 * Above DWC_usb3.0 1.94a, it is recommended to set
+	 * DWC3_GUSB3PIPECTL_SUSPHY and DWC3_GUSB2PHYCFG_SUSPHY to '0' during
+	 * coreConsultant configuration. So default value will be '0' when the
+	 * core is reset. Application needs to set it to '1' after the core
+	 * initialization is completed.
+	 *
+	 * Certain phy requires to be in P0 power state during initialization.
+	 * Make sure GUSB3PIPECTL.SUSPENDENABLE and GUSB2PHYCFG.SUSPHY are clear
+	 * prior to phy init to maintain in the P0 state.
+	 *
+	 * After phy initialization, some phy operations can only be executed
+	 * while in lower P states. Ensure GUSB3PIPECTL.SUSPENDENABLE and
+	 * GUSB2PHYCFG.SUSPHY are set soon after initialization to avoid
+	 * blocking phy ops.
+	 */
+	if (!DWC3_VER_IS_WITHIN(DWC3, ANY, 194A))
+		dwc3_enable_susphy(dwc, true);
+
 	return 0;
 
 err_exit_usb3_phy:
@@ -1588,7 +1603,7 @@ static int dwc3_core_init_mode(struct dwc3 *dwc)
 
 	switch (dwc->dr_mode) {
 	case USB_DR_MODE_PERIPHERAL:
-		dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_DEVICE);
+		dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_DEVICE, false);
 
 		if (dwc->usb2_phy)
 			otg_set_vbus(dwc->usb2_phy->otg, false);
@@ -1600,7 +1615,7 @@ static int dwc3_core_init_mode(struct dwc3 *dwc)
 			return dev_err_probe(dev, ret, "failed to initialize gadget\n");
 		break;
 	case USB_DR_MODE_HOST:
-		dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_HOST);
+		dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_HOST, false);
 
 		if (dwc->usb2_phy)
 			otg_set_vbus(dwc->usb2_phy->otg, true);
@@ -1645,7 +1660,7 @@ static void dwc3_core_exit_mode(struct dwc3 *dwc)
 	}
 
 	/* de-assert DRVVBUS for HOST and OTG mode */
-	dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_DEVICE);
+	dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_DEVICE, true);
 }
 
 static void dwc3_get_software_properties(struct dwc3 *dwc)
@@ -2453,7 +2468,7 @@ static int dwc3_resume_common(struct dwc3 *dwc, pm_message_t msg)
 		if (ret)
 			return ret;
 
-		dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_DEVICE);
+		dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_DEVICE, true);
 		dwc3_gadget_resume(dwc);
 		break;
 	case DWC3_GCTL_PRTCAP_HOST:
@@ -2461,7 +2476,7 @@ static int dwc3_resume_common(struct dwc3 *dwc, pm_message_t msg)
 			ret = dwc3_core_init_for_resume(dwc);
 			if (ret)
 				return ret;
-			dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_HOST);
+			dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_HOST, true);
 			break;
 		}
 		/* Restore GUSB2PHYCFG bits that were modified in suspend */
@@ -2490,7 +2505,7 @@ static int dwc3_resume_common(struct dwc3 *dwc, pm_message_t msg)
 		if (ret)
 			return ret;
 
-		dwc3_set_prtcap(dwc, dwc->current_dr_role);
+		dwc3_set_prtcap(dwc, dwc->current_dr_role, true);
 
 		dwc3_otg_init(dwc);
 		if (dwc->current_otg_role == DWC3_OTG_ROLE_HOST) {
diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index c955039bb4f62..aaa39e663f60a 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -1558,7 +1558,7 @@ struct dwc3_gadget_ep_cmd_params {
 #define DWC3_HAS_OTG			BIT(3)
 
 /* prototypes */
-void dwc3_set_prtcap(struct dwc3 *dwc, u32 mode);
+void dwc3_set_prtcap(struct dwc3 *dwc, u32 mode, bool ignore_susphy);
 void dwc3_set_mode(struct dwc3 *dwc, u32 mode);
 u32 dwc3_core_fifo_space(struct dwc3_ep *dep, u8 type);
 
diff --git a/drivers/usb/dwc3/drd.c b/drivers/usb/dwc3/drd.c
index d76ae676783cf..7977860932b14 100644
--- a/drivers/usb/dwc3/drd.c
+++ b/drivers/usb/dwc3/drd.c
@@ -173,7 +173,7 @@ void dwc3_otg_init(struct dwc3 *dwc)
 	 * block "Initialize GCTL for OTG operation".
 	 */
 	/* GCTL.PrtCapDir=2'b11 */
-	dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_OTG);
+	dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_OTG, true);
 	/* GUSB2PHYCFG0.SusPHY=0 */
 	reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0));
 	reg &= ~DWC3_GUSB2PHYCFG_SUSPHY;
@@ -556,7 +556,7 @@ int dwc3_drd_init(struct dwc3 *dwc)
 
 		dwc3_drd_update(dwc);
 	} else {
-		dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_OTG);
+		dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_OTG, true);
 
 		/* use OTG block to get ID event */
 		irq = dwc3_otg_get_irq(dwc);

From dfd3df31c9db752234d7d2e09bef2aeabb643ce4 Mon Sep 17 00:00:00 2001
From: "Uladzislau Rezki (Sony)" <urezki@gmail.com>
Date: Fri, 28 Feb 2025 13:13:56 +0100
Subject: [PATCH 0875/1173] mm/slab/kvfree_rcu: Switch to WQ_MEM_RECLAIM wq

Currently kvfree_rcu() APIs use a system workqueue which is
"system_unbound_wq" to driver RCU machinery to reclaim a memory.

Recently, it has been noted that the following kernel warning can
be observed:

<snip>
workqueue: WQ_MEM_RECLAIM nvme-wq:nvme_scan_work is flushing !WQ_MEM_RECLAIM events_unbound:kfree_rcu_work
  WARNING: CPU: 21 PID: 330 at kernel/workqueue.c:3719 check_flush_dependency+0x112/0x120
  Modules linked in: intel_uncore_frequency(E) intel_uncore_frequency_common(E) skx_edac(E) ...
  CPU: 21 UID: 0 PID: 330 Comm: kworker/u144:6 Tainted: G            E      6.13.2-0_g925d379822da #1
  Hardware name: Wiwynn Twin Lakes MP/Twin Lakes Passive MP, BIOS YMM20 02/01/2023
  Workqueue: nvme-wq nvme_scan_work
  RIP: 0010:check_flush_dependency+0x112/0x120
  Code: 05 9a 40 14 02 01 48 81 c6 c0 00 00 00 48 8b 50 18 48 81 c7 c0 00 00 00 48 89 f9 48 ...
  RSP: 0018:ffffc90000df7bd8 EFLAGS: 00010082
  RAX: 000000000000006a RBX: ffffffff81622390 RCX: 0000000000000027
  RDX: 00000000fffeffff RSI: 000000000057ffa8 RDI: ffff88907f960c88
  RBP: 0000000000000000 R08: ffffffff83068e50 R09: 000000000002fffd
  R10: 0000000000000004 R11: 0000000000000000 R12: ffff8881001a4400
  R13: 0000000000000000 R14: ffff88907f420fb8 R15: 0000000000000000
  FS:  0000000000000000(0000) GS:ffff88907f940000(0000) knlGS:0000000000000000
  CR2: 00007f60c3001000 CR3: 000000107d010005 CR4: 00000000007726f0
  PKRU: 55555554
  Call Trace:
   <TASK>
   ? __warn+0xa4/0x140
   ? check_flush_dependency+0x112/0x120
   ? report_bug+0xe1/0x140
   ? check_flush_dependency+0x112/0x120
   ? handle_bug+0x5e/0x90
   ? exc_invalid_op+0x16/0x40
   ? asm_exc_invalid_op+0x16/0x20
   ? timer_recalc_next_expiry+0x190/0x190
   ? check_flush_dependency+0x112/0x120
   ? check_flush_dependency+0x112/0x120
   __flush_work.llvm.1643880146586177030+0x174/0x2c0
   flush_rcu_work+0x28/0x30
   kvfree_rcu_barrier+0x12f/0x160
   kmem_cache_destroy+0x18/0x120
   bioset_exit+0x10c/0x150
   disk_release.llvm.6740012984264378178+0x61/0xd0
   device_release+0x4f/0x90
   kobject_put+0x95/0x180
   nvme_put_ns+0x23/0xc0
   nvme_remove_invalid_namespaces+0xb3/0xd0
   nvme_scan_work+0x342/0x490
   process_scheduled_works+0x1a2/0x370
   worker_thread+0x2ff/0x390
   ? pwq_release_workfn+0x1e0/0x1e0
   kthread+0xb1/0xe0
   ? __kthread_parkme+0x70/0x70
   ret_from_fork+0x30/0x40
   ? __kthread_parkme+0x70/0x70
   ret_from_fork_asm+0x11/0x20
   </TASK>
  ---[ end trace 0000000000000000 ]---
<snip>

To address this switch to use of independent WQ_MEM_RECLAIM
workqueue, so the rules are not violated from workqueue framework
point of view.

Apart of that, since kvfree_rcu() does reclaim memory it is worth
to go with WQ_MEM_RECLAIM type of wq because it is designed for
this purpose.

Fixes: 6c6c47b063b5 ("mm, slab: call kvfree_rcu_barrier() from kmem_cache_destroy()"),
Reported-by: Keith Busch <kbusch@kernel.org>
Closes: https://lore.kernel.org/all/Z7iqJtCjHKfo8Kho@kbusch-mbp/
Cc: stable@vger.kernel.org
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Reviewed-by: Joel Fernandes <joelagnelf@nvidia.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
 mm/slab_common.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/mm/slab_common.c b/mm/slab_common.c
index 4030907b6b7d8..4c9f0a87f733b 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -1304,6 +1304,8 @@ module_param(rcu_min_cached_objs, int, 0444);
 static int rcu_delay_page_cache_fill_msec = 5000;
 module_param(rcu_delay_page_cache_fill_msec, int, 0444);
 
+static struct workqueue_struct *rcu_reclaim_wq;
+
 /* Maximum number of jiffies to wait before draining a batch. */
 #define KFREE_DRAIN_JIFFIES (5 * HZ)
 #define KFREE_N_BATCHES 2
@@ -1632,10 +1634,10 @@ __schedule_delayed_monitor_work(struct kfree_rcu_cpu *krcp)
 	if (delayed_work_pending(&krcp->monitor_work)) {
 		delay_left = krcp->monitor_work.timer.expires - jiffies;
 		if (delay < delay_left)
-			mod_delayed_work(system_unbound_wq, &krcp->monitor_work, delay);
+			mod_delayed_work(rcu_reclaim_wq, &krcp->monitor_work, delay);
 		return;
 	}
-	queue_delayed_work(system_unbound_wq, &krcp->monitor_work, delay);
+	queue_delayed_work(rcu_reclaim_wq, &krcp->monitor_work, delay);
 }
 
 static void
@@ -1733,7 +1735,7 @@ kvfree_rcu_queue_batch(struct kfree_rcu_cpu *krcp)
 			// "free channels", the batch can handle. Break
 			// the loop since it is done with this CPU thus
 			// queuing an RCU work is _always_ success here.
-			queued = queue_rcu_work(system_unbound_wq, &krwp->rcu_work);
+			queued = queue_rcu_work(rcu_reclaim_wq, &krwp->rcu_work);
 			WARN_ON_ONCE(!queued);
 			break;
 		}
@@ -1883,7 +1885,7 @@ run_page_cache_worker(struct kfree_rcu_cpu *krcp)
 	if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING &&
 			!atomic_xchg(&krcp->work_in_progress, 1)) {
 		if (atomic_read(&krcp->backoff_page_cache_fill)) {
-			queue_delayed_work(system_unbound_wq,
+			queue_delayed_work(rcu_reclaim_wq,
 				&krcp->page_cache_work,
 					msecs_to_jiffies(rcu_delay_page_cache_fill_msec));
 		} else {
@@ -2120,6 +2122,10 @@ void __init kvfree_rcu_init(void)
 	int i, j;
 	struct shrinker *kfree_rcu_shrinker;
 
+	rcu_reclaim_wq = alloc_workqueue("kvfree_rcu_reclaim",
+			WQ_UNBOUND | WQ_MEM_RECLAIM, 0);
+	WARN_ON(!rcu_reclaim_wq);
+
 	/* Clamp it to [0:100] seconds interval. */
 	if (rcu_delay_page_cache_fill_msec < 0 ||
 		rcu_delay_page_cache_fill_msec > 100 * MSEC_PER_SEC) {

From 061c991697062f3bf87b72ed553d1d33a0e370dd Mon Sep 17 00:00:00 2001
From: Saket Kumar Bhaskar <skb99@linux.ibm.com>
Date: Mon, 3 Mar 2025 14:54:51 +0530
Subject: [PATCH 0876/1173] perf/hw_breakpoint: Return EOPNOTSUPP for
 unsupported breakpoint type

Currently, __reserve_bp_slot() returns -ENOSPC for unsupported
breakpoint types on the architecture. For example, powerpc
does not support hardware instruction breakpoints. This causes
the perf_skip BPF selftest to fail, as neither ENOENT nor
EOPNOTSUPP is returned by perf_event_open for unsupported
breakpoint types. As a result, the test that should be skipped
for this arch is not correctly identified.

To resolve this, hw_breakpoint_event_init() should exit early by
checking for unsupported breakpoint types using
hw_breakpoint_slots_cached() and return the appropriate error
(-EOPNOTSUPP).

Signed-off-by: Saket Kumar Bhaskar <skb99@linux.ibm.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Marco Elver <elver@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Link: https://lore.kernel.org/r/20250303092451.1862862-1-skb99@linux.ibm.com
---
 kernel/events/hw_breakpoint.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index bc4a61029b6dc..8ec2cb6889038 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -950,9 +950,10 @@ static int hw_breakpoint_event_init(struct perf_event *bp)
 		return -ENOENT;
 
 	/*
-	 * no branch sampling for breakpoint events
+	 * Check if breakpoint type is supported before proceeding.
+	 * Also, no branch sampling for breakpoint events.
 	 */
-	if (has_branch_stack(bp))
+	if (!hw_breakpoint_slots_cached(find_slot_idx(bp->attr.bp_type)) || has_branch_stack(bp))
 		return -EOPNOTSUPP;
 
 	err = register_perf_hw_breakpoint(bp);

From c70ca298036c58a88686ff388d3d367e9d21acf0 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 4 Nov 2024 14:39:13 +0100
Subject: [PATCH 0877/1173] perf/core: Simplify the perf_event_alloc() error
 path

The error cleanup sequence in perf_event_alloc() is a subset of the
existing _free_event() function (it must of course be).

Split this out into __free_event() and simplify the error path.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ravi Bangoria <ravi.bangoria@amd.com>
Link: https://lore.kernel.org/r/20241104135517.967889521@infradead.org
---
 include/linux/perf_event.h |  16 +++--
 kernel/events/core.c       | 138 ++++++++++++++++++-------------------
 2 files changed, 78 insertions(+), 76 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index c4525bae2fe9f..8c0117bcbdb9f 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -673,13 +673,15 @@ struct swevent_hlist {
 	struct rcu_head			rcu_head;
 };
 
-#define PERF_ATTACH_CONTEXT	0x01
-#define PERF_ATTACH_GROUP	0x02
-#define PERF_ATTACH_TASK	0x04
-#define PERF_ATTACH_TASK_DATA	0x08
-#define PERF_ATTACH_ITRACE	0x10
-#define PERF_ATTACH_SCHED_CB	0x20
-#define PERF_ATTACH_CHILD	0x40
+#define PERF_ATTACH_CONTEXT	0x0001
+#define PERF_ATTACH_GROUP	0x0002
+#define PERF_ATTACH_TASK	0x0004
+#define PERF_ATTACH_TASK_DATA	0x0008
+#define PERF_ATTACH_ITRACE	0x0010
+#define PERF_ATTACH_SCHED_CB	0x0020
+#define PERF_ATTACH_CHILD	0x0040
+#define PERF_ATTACH_EXCLUSIVE	0x0080
+#define PERF_ATTACH_CALLCHAIN	0x0100
 
 struct bpf_prog;
 struct perf_cgroup;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 6ccf363d73cc6..1b8b1c8f41ff2 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5289,6 +5289,8 @@ static int exclusive_event_init(struct perf_event *event)
 			return -EBUSY;
 	}
 
+	event->attach_state |= PERF_ATTACH_EXCLUSIVE;
+
 	return 0;
 }
 
@@ -5296,14 +5298,13 @@ static void exclusive_event_destroy(struct perf_event *event)
 {
 	struct pmu *pmu = event->pmu;
 
-	if (!is_exclusive_pmu(pmu))
-		return;
-
 	/* see comment in exclusive_event_init() */
 	if (event->attach_state & PERF_ATTACH_TASK)
 		atomic_dec(&pmu->exclusive_cnt);
 	else
 		atomic_inc(&pmu->exclusive_cnt);
+
+	event->attach_state &= ~PERF_ATTACH_EXCLUSIVE;
 }
 
 static bool exclusive_event_match(struct perf_event *e1, struct perf_event *e2)
@@ -5362,40 +5363,20 @@ static void perf_pending_task_sync(struct perf_event *event)
 	rcuwait_wait_event(&event->pending_work_wait, !event->pending_work, TASK_UNINTERRUPTIBLE);
 }
 
-static void _free_event(struct perf_event *event)
+/* vs perf_event_alloc() error */
+static void __free_event(struct perf_event *event)
 {
-	irq_work_sync(&event->pending_irq);
-	irq_work_sync(&event->pending_disable_irq);
-	perf_pending_task_sync(event);
+	if (event->attach_state & PERF_ATTACH_CALLCHAIN)
+		put_callchain_buffers();
 
-	unaccount_event(event);
+	kfree(event->addr_filter_ranges);
 
-	security_perf_event_free(event);
-
-	if (event->rb) {
-		/*
-		 * Can happen when we close an event with re-directed output.
-		 *
-		 * Since we have a 0 refcount, perf_mmap_close() will skip
-		 * over us; possibly making our ring_buffer_put() the last.
-		 */
-		mutex_lock(&event->mmap_mutex);
-		ring_buffer_attach(event, NULL);
-		mutex_unlock(&event->mmap_mutex);
-	}
+	if (event->attach_state & PERF_ATTACH_EXCLUSIVE)
+		exclusive_event_destroy(event);
 
 	if (is_cgroup_event(event))
 		perf_detach_cgroup(event);
 
-	if (!event->parent) {
-		if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)
-			put_callchain_buffers();
-	}
-
-	perf_event_free_bpf_prog(event);
-	perf_addr_filters_splice(event, NULL);
-	kfree(event->addr_filter_ranges);
-
 	if (event->destroy)
 		event->destroy(event);
 
@@ -5406,22 +5387,58 @@ static void _free_event(struct perf_event *event)
 	if (event->hw.target)
 		put_task_struct(event->hw.target);
 
-	if (event->pmu_ctx)
+	if (event->pmu_ctx) {
+		/*
+		 * put_pmu_ctx() needs an event->ctx reference, because of
+		 * epc->ctx.
+		 */
+		WARN_ON_ONCE(!event->ctx);
+		WARN_ON_ONCE(event->pmu_ctx->ctx != event->ctx);
 		put_pmu_ctx(event->pmu_ctx);
+	}
 
 	/*
-	 * perf_event_free_task() relies on put_ctx() being 'last', in particular
-	 * all task references must be cleaned up.
+	 * perf_event_free_task() relies on put_ctx() being 'last', in
+	 * particular all task references must be cleaned up.
 	 */
 	if (event->ctx)
 		put_ctx(event->ctx);
 
-	exclusive_event_destroy(event);
-	module_put(event->pmu->module);
+	if (event->pmu)
+		module_put(event->pmu->module);
 
 	call_rcu(&event->rcu_head, free_event_rcu);
 }
 
+/* vs perf_event_alloc() success */
+static void _free_event(struct perf_event *event)
+{
+	irq_work_sync(&event->pending_irq);
+	irq_work_sync(&event->pending_disable_irq);
+	perf_pending_task_sync(event);
+
+	unaccount_event(event);
+
+	security_perf_event_free(event);
+
+	if (event->rb) {
+		/*
+		 * Can happen when we close an event with re-directed output.
+		 *
+		 * Since we have a 0 refcount, perf_mmap_close() will skip
+		 * over us; possibly making our ring_buffer_put() the last.
+		 */
+		mutex_lock(&event->mmap_mutex);
+		ring_buffer_attach(event, NULL);
+		mutex_unlock(&event->mmap_mutex);
+	}
+
+	perf_event_free_bpf_prog(event);
+	perf_addr_filters_splice(event, NULL);
+
+	__free_event(event);
+}
+
 /*
  * Used to free events which have a known refcount of 1, such as in error paths
  * where the event isn't exposed yet and inherited events.
@@ -12093,8 +12110,10 @@ static int perf_try_init_event(struct pmu *pmu, struct perf_event *event)
 			event->destroy(event);
 	}
 
-	if (ret)
+	if (ret) {
+		event->pmu = NULL;
 		module_put(pmu->module);
+	}
 
 	return ret;
 }
@@ -12422,7 +12441,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	 * See perf_output_read().
 	 */
 	if (has_inherit_and_sample_read(attr) && !(attr->sample_type & PERF_SAMPLE_TID))
-		goto err_ns;
+		goto err;
 
 	if (!has_branch_stack(event))
 		event->attr.branch_sample_type = 0;
@@ -12430,7 +12449,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	pmu = perf_init_event(event);
 	if (IS_ERR(pmu)) {
 		err = PTR_ERR(pmu);
-		goto err_ns;
+		goto err;
 	}
 
 	/*
@@ -12440,25 +12459,25 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	 */
 	if (pmu->task_ctx_nr == perf_invalid_context && (task || cgroup_fd != -1)) {
 		err = -EINVAL;
-		goto err_pmu;
+		goto err;
 	}
 
 	if (event->attr.aux_output &&
 	    (!(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT) ||
 	     event->attr.aux_pause || event->attr.aux_resume)) {
 		err = -EOPNOTSUPP;
-		goto err_pmu;
+		goto err;
 	}
 
 	if (event->attr.aux_pause && event->attr.aux_resume) {
 		err = -EINVAL;
-		goto err_pmu;
+		goto err;
 	}
 
 	if (event->attr.aux_start_paused) {
 		if (!(pmu->capabilities & PERF_PMU_CAP_AUX_PAUSE)) {
 			err = -EOPNOTSUPP;
-			goto err_pmu;
+			goto err;
 		}
 		event->hw.aux_paused = 1;
 	}
@@ -12466,12 +12485,12 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	if (cgroup_fd != -1) {
 		err = perf_cgroup_connect(cgroup_fd, event, attr, group_leader);
 		if (err)
-			goto err_pmu;
+			goto err;
 	}
 
 	err = exclusive_event_init(event);
 	if (err)
-		goto err_pmu;
+		goto err;
 
 	if (has_addr_filter(event)) {
 		event->addr_filter_ranges = kcalloc(pmu->nr_addr_filters,
@@ -12479,7 +12498,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 						    GFP_KERNEL);
 		if (!event->addr_filter_ranges) {
 			err = -ENOMEM;
-			goto err_per_task;
+			goto err;
 		}
 
 		/*
@@ -12504,41 +12523,22 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 		if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) {
 			err = get_callchain_buffers(attr->sample_max_stack);
 			if (err)
-				goto err_addr_filters;
+				goto err;
+			event->attach_state |= PERF_ATTACH_CALLCHAIN;
 		}
 	}
 
 	err = security_perf_event_alloc(event);
 	if (err)
-		goto err_callchain_buffer;
+		goto err;
 
 	/* symmetric to unaccount_event() in _free_event() */
 	account_event(event);
 
 	return event;
 
-err_callchain_buffer:
-	if (!event->parent) {
-		if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)
-			put_callchain_buffers();
-	}
-err_addr_filters:
-	kfree(event->addr_filter_ranges);
-
-err_per_task:
-	exclusive_event_destroy(event);
-
-err_pmu:
-	if (is_cgroup_event(event))
-		perf_detach_cgroup(event);
-	if (event->destroy)
-		event->destroy(event);
-	module_put(pmu->module);
-err_ns:
-	if (event->hw.target)
-		put_task_struct(event->hw.target);
-	call_rcu(&event->rcu_head, free_event_rcu);
-
+err:
+	__free_event(event);
 	return ERR_PTR(err);
 }
 

From 8f4c4963d28349cbf1920ab71edea8276f6ac4c5 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 4 Nov 2024 14:39:14 +0100
Subject: [PATCH 0878/1173] perf/core: Simplify the perf_pmu_register() error
 path

The error path of perf_pmu_register() is of course very similar to a
subset of perf_pmu_unregister(). Extract this common part in
perf_pmu_free() and simplify things.

[ mingo: Forward ported it ]

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Ravi Bangoria <ravi.bangoria@amd.com>
Link: https://lore.kernel.org/r/20241104135518.090915501@infradead.org
---
 kernel/events/core.c | 67 ++++++++++++++++++++------------------------
 1 file changed, 30 insertions(+), 37 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1b8b1c8f41ff2..ee5cdd692383a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -11675,11 +11675,6 @@ static int perf_event_idx_default(struct perf_event *event)
 	return 0;
 }
 
-static void free_pmu_context(struct pmu *pmu)
-{
-	free_percpu(pmu->cpu_pmu_context);
-}
-
 /*
  * Let userspace know that this PMU supports address range filtering:
  */
@@ -11885,6 +11880,7 @@ static int pmu_dev_alloc(struct pmu *pmu)
 
 free_dev:
 	put_device(pmu->dev);
+	pmu->dev = NULL;
 	goto out;
 }
 
@@ -11906,25 +11902,38 @@ static bool idr_cmpxchg(struct idr *idr, unsigned long id, void *old, void *new)
 	return true;
 }
 
+static void perf_pmu_free(struct pmu *pmu)
+{
+	free_percpu(pmu->pmu_disable_count);
+	if (pmu_bus_running && pmu->dev && pmu->dev != PMU_NULL_DEV) {
+		if (pmu->nr_addr_filters)
+			device_remove_file(pmu->dev, &dev_attr_nr_addr_filters);
+		device_del(pmu->dev);
+		put_device(pmu->dev);
+	}
+	free_percpu(pmu->cpu_pmu_context);
+}
+
 int perf_pmu_register(struct pmu *pmu, const char *name, int type)
 {
 	int cpu, ret, max = PERF_TYPE_MAX;
 
+	pmu->type = -1;
+
 	mutex_lock(&pmus_lock);
 	ret = -ENOMEM;
 	pmu->pmu_disable_count = alloc_percpu(int);
 	if (!pmu->pmu_disable_count)
 		goto unlock;
 
-	pmu->type = -1;
 	if (WARN_ONCE(!name, "Can not register anonymous pmu.\n")) {
 		ret = -EINVAL;
-		goto free_pdc;
+		goto free;
 	}
 
 	if (WARN_ONCE(pmu->scope >= PERF_PMU_MAX_SCOPE, "Can not register a pmu with an invalid scope.\n")) {
 		ret = -EINVAL;
-		goto free_pdc;
+		goto free;
 	}
 
 	pmu->name = name;
@@ -11934,24 +11943,23 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type)
 
 	ret = idr_alloc(&pmu_idr, NULL, max, 0, GFP_KERNEL);
 	if (ret < 0)
-		goto free_pdc;
+		goto free;
 
 	WARN_ON(type >= 0 && ret != type);
 
-	type = ret;
-	pmu->type = type;
+	pmu->type = ret;
 	atomic_set(&pmu->exclusive_cnt, 0);
 
 	if (pmu_bus_running && !pmu->dev) {
 		ret = pmu_dev_alloc(pmu);
 		if (ret)
-			goto free_idr;
+			goto free;
 	}
 
 	ret = -ENOMEM;
 	pmu->cpu_pmu_context = alloc_percpu(struct perf_cpu_pmu_context);
 	if (!pmu->cpu_pmu_context)
-		goto free_dev;
+		goto free;
 
 	for_each_possible_cpu(cpu) {
 		struct perf_cpu_pmu_context *cpc;
@@ -11992,8 +12000,10 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type)
 	/*
 	 * Now that the PMU is complete, make it visible to perf_try_init_event().
 	 */
-	if (!idr_cmpxchg(&pmu_idr, pmu->type, NULL, pmu))
-		goto free_context;
+	if (!idr_cmpxchg(&pmu_idr, pmu->type, NULL, pmu)) {
+		ret = -EINVAL;
+		goto free;
+	}
 	list_add_rcu(&pmu->entry, &pmus);
 
 	ret = 0;
@@ -12002,20 +12012,10 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type)
 
 	return ret;
 
-free_context:
-	free_percpu(pmu->cpu_pmu_context);
-
-free_dev:
-	if (pmu->dev && pmu->dev != PMU_NULL_DEV) {
-		device_del(pmu->dev);
-		put_device(pmu->dev);
-	}
-
-free_idr:
-	idr_remove(&pmu_idr, pmu->type);
-
-free_pdc:
-	free_percpu(pmu->pmu_disable_count);
+free:
+	if (pmu->type >= 0)
+		idr_remove(&pmu_idr, pmu->type);
+	perf_pmu_free(pmu);
 	goto unlock;
 }
 EXPORT_SYMBOL_GPL(perf_pmu_register);
@@ -12034,14 +12034,7 @@ void perf_pmu_unregister(struct pmu *pmu)
 	synchronize_srcu(&pmus_srcu);
 	synchronize_rcu();
 
-	free_percpu(pmu->pmu_disable_count);
-	if (pmu_bus_running && pmu->dev && pmu->dev != PMU_NULL_DEV) {
-		if (pmu->nr_addr_filters)
-			device_remove_file(pmu->dev, &dev_attr_nr_addr_filters);
-		device_del(pmu->dev);
-		put_device(pmu->dev);
-	}
-	free_pmu_context(pmu);
+	perf_pmu_free(pmu);
 }
 EXPORT_SYMBOL_GPL(perf_pmu_unregister);
 

From 6c8b0b835f003647e593c08331a4dd2150d5eb0e Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 4 Nov 2024 14:39:15 +0100
Subject: [PATCH 0879/1173] perf/core: Simplify perf_pmu_register()

Using the previously introduced perf_pmu_free() and a new IDR helper,
simplify the perf_pmu_register error paths.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Ravi Bangoria <ravi.bangoria@amd.com>
Link: https://lore.kernel.org/r/20241104135518.198937277@infradead.org
---
 include/linux/idr.h  | 17 +++++++++++
 kernel/events/core.c | 71 ++++++++++++++++++--------------------------
 2 files changed, 46 insertions(+), 42 deletions(-)

diff --git a/include/linux/idr.h b/include/linux/idr.h
index da5f5fa4a3a6a..cd729be369b36 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -15,6 +15,7 @@
 #include <linux/radix-tree.h>
 #include <linux/gfp.h>
 #include <linux/percpu.h>
+#include <linux/cleanup.h>
 
 struct idr {
 	struct radix_tree_root	idr_rt;
@@ -124,6 +125,22 @@ void *idr_get_next_ul(struct idr *, unsigned long *nextid);
 void *idr_replace(struct idr *, void *, unsigned long id);
 void idr_destroy(struct idr *);
 
+struct __class_idr {
+	struct idr *idr;
+	int id;
+};
+
+#define idr_null ((struct __class_idr){ NULL, -1 })
+#define take_idr_id(id) __get_and_null(id, idr_null)
+
+DEFINE_CLASS(idr_alloc, struct __class_idr,
+	     if (_T.id >= 0) idr_remove(_T.idr, _T.id),
+	     ((struct __class_idr){
+	     	.idr = idr,
+		.id = idr_alloc(idr, ptr, start, end, gfp),
+	     }),
+	     struct idr *idr, void *ptr, int start, int end, gfp_t gfp);
+
 /**
  * idr_init_base() - Initialise an IDR.
  * @idr: IDR handle.
diff --git a/kernel/events/core.c b/kernel/events/core.c
index ee5cdd692383a..215dad53aa1b5 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -11914,52 +11914,49 @@ static void perf_pmu_free(struct pmu *pmu)
 	free_percpu(pmu->cpu_pmu_context);
 }
 
-int perf_pmu_register(struct pmu *pmu, const char *name, int type)
+DEFINE_FREE(pmu_unregister, struct pmu *, if (_T) perf_pmu_free(_T))
+
+int perf_pmu_register(struct pmu *_pmu, const char *name, int type)
 {
-	int cpu, ret, max = PERF_TYPE_MAX;
+	int cpu, max = PERF_TYPE_MAX;
 
-	pmu->type = -1;
+	struct pmu *pmu __free(pmu_unregister) = _pmu;
+	guard(mutex)(&pmus_lock);
 
-	mutex_lock(&pmus_lock);
-	ret = -ENOMEM;
 	pmu->pmu_disable_count = alloc_percpu(int);
 	if (!pmu->pmu_disable_count)
-		goto unlock;
+		return -ENOMEM;
 
-	if (WARN_ONCE(!name, "Can not register anonymous pmu.\n")) {
-		ret = -EINVAL;
-		goto free;
-	}
+	if (WARN_ONCE(!name, "Can not register anonymous pmu.\n"))
+		return -EINVAL;
 
-	if (WARN_ONCE(pmu->scope >= PERF_PMU_MAX_SCOPE, "Can not register a pmu with an invalid scope.\n")) {
-		ret = -EINVAL;
-		goto free;
-	}
+	if (WARN_ONCE(pmu->scope >= PERF_PMU_MAX_SCOPE,
+		      "Can not register a pmu with an invalid scope.\n"))
+		return -EINVAL;
 
 	pmu->name = name;
 
 	if (type >= 0)
 		max = type;
 
-	ret = idr_alloc(&pmu_idr, NULL, max, 0, GFP_KERNEL);
-	if (ret < 0)
-		goto free;
+	CLASS(idr_alloc, pmu_type)(&pmu_idr, NULL, max, 0, GFP_KERNEL);
+	if (pmu_type.id < 0)
+		return pmu_type.id;
 
-	WARN_ON(type >= 0 && ret != type);
+	WARN_ON(type >= 0 && pmu_type.id != type);
 
-	pmu->type = ret;
+	pmu->type = pmu_type.id;
 	atomic_set(&pmu->exclusive_cnt, 0);
 
 	if (pmu_bus_running && !pmu->dev) {
-		ret = pmu_dev_alloc(pmu);
+		int ret = pmu_dev_alloc(pmu);
 		if (ret)
-			goto free;
+			return ret;
 	}
 
-	ret = -ENOMEM;
 	pmu->cpu_pmu_context = alloc_percpu(struct perf_cpu_pmu_context);
 	if (!pmu->cpu_pmu_context)
-		goto free;
+		return -ENOMEM;
 
 	for_each_possible_cpu(cpu) {
 		struct perf_cpu_pmu_context *cpc;
@@ -12000,32 +11997,22 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type)
 	/*
 	 * Now that the PMU is complete, make it visible to perf_try_init_event().
 	 */
-	if (!idr_cmpxchg(&pmu_idr, pmu->type, NULL, pmu)) {
-		ret = -EINVAL;
-		goto free;
-	}
+	if (!idr_cmpxchg(&pmu_idr, pmu->type, NULL, pmu))
+		return -EINVAL;
 	list_add_rcu(&pmu->entry, &pmus);
 
-	ret = 0;
-unlock:
-	mutex_unlock(&pmus_lock);
-
-	return ret;
-
-free:
-	if (pmu->type >= 0)
-		idr_remove(&pmu_idr, pmu->type);
-	perf_pmu_free(pmu);
-	goto unlock;
+	take_idr_id(pmu_type);
+	_pmu = no_free_ptr(pmu); // let it rip
+	return 0;
 }
 EXPORT_SYMBOL_GPL(perf_pmu_register);
 
 void perf_pmu_unregister(struct pmu *pmu)
 {
-	mutex_lock(&pmus_lock);
-	list_del_rcu(&pmu->entry);
-	idr_remove(&pmu_idr, pmu->type);
-	mutex_unlock(&pmus_lock);
+	scoped_guard (mutex, &pmus_lock) {
+		list_del_rcu(&pmu->entry);
+		idr_remove(&pmu_idr, pmu->type);
+	}
 
 	/*
 	 * We dereference the pmu list under both SRCU and regular RCU, so

From caf8b765d453198d4ca5305d9e207535934b6e3b Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 4 Nov 2024 14:39:16 +0100
Subject: [PATCH 0880/1173] perf/core: Simplify perf_init_event()

Use the <linux/cleanup.h> guard() and scoped_guard() infrastructure
to simplify the control flow.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20241104135518.302444446@infradead.org
---
 kernel/events/core.c | 31 ++++++++++++-------------------
 1 file changed, 12 insertions(+), 19 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 215dad53aa1b5..fd352361259ca 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -12101,10 +12101,10 @@ static int perf_try_init_event(struct pmu *pmu, struct perf_event *event)
 static struct pmu *perf_init_event(struct perf_event *event)
 {
 	bool extended_type = false;
-	int idx, type, ret;
 	struct pmu *pmu;
+	int type, ret;
 
-	idx = srcu_read_lock(&pmus_srcu);
+	guard(srcu)(&pmus_srcu);
 
 	/*
 	 * Save original type before calling pmu->event_init() since certain
@@ -12117,7 +12117,7 @@ static struct pmu *perf_init_event(struct perf_event *event)
 		pmu = event->parent->pmu;
 		ret = perf_try_init_event(pmu, event);
 		if (!ret)
-			goto unlock;
+			return pmu;
 	}
 
 	/*
@@ -12136,13 +12136,12 @@ static struct pmu *perf_init_event(struct perf_event *event)
 	}
 
 again:
-	rcu_read_lock();
-	pmu = idr_find(&pmu_idr, type);
-	rcu_read_unlock();
+	scoped_guard (rcu)
+		pmu = idr_find(&pmu_idr, type);
 	if (pmu) {
 		if (event->attr.type != type && type != PERF_TYPE_RAW &&
 		    !(pmu->capabilities & PERF_PMU_CAP_EXTENDED_HW_TYPE))
-			goto fail;
+			return ERR_PTR(-ENOENT);
 
 		ret = perf_try_init_event(pmu, event);
 		if (ret == -ENOENT && event->attr.type != type && !extended_type) {
@@ -12151,27 +12150,21 @@ static struct pmu *perf_init_event(struct perf_event *event)
 		}
 
 		if (ret)
-			pmu = ERR_PTR(ret);
+			return ERR_PTR(ret);
 
-		goto unlock;
+		return pmu;
 	}
 
 	list_for_each_entry_rcu(pmu, &pmus, entry, lockdep_is_held(&pmus_srcu)) {
 		ret = perf_try_init_event(pmu, event);
 		if (!ret)
-			goto unlock;
+			return pmu;
 
-		if (ret != -ENOENT) {
-			pmu = ERR_PTR(ret);
-			goto unlock;
-		}
+		if (ret != -ENOENT)
+			return ERR_PTR(ret);
 	}
-fail:
-	pmu = ERR_PTR(-ENOENT);
-unlock:
-	srcu_read_unlock(&pmus_srcu, idx);
 
-	return pmu;
+	return ERR_PTR(-ENOENT);
 }
 
 static void attach_sb_event(struct perf_event *event)

From 8f2221f52eced88e74c7ae22b4b2d67dc7a96bd2 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 4 Nov 2024 14:39:17 +0100
Subject: [PATCH 0881/1173] perf/core: Simplify perf_event_alloc()

Using the previous simplifications, transition perf_event_alloc() to
the cleanup way of things -- reducing error path magic.

[ mingo: Ported it to recent kernels. ]

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ravi Bangoria <ravi.bangoria@amd.com>
Link: https://lore.kernel.org/r/20241104135518.410755241@infradead.org
---
 kernel/events/core.c | 59 +++++++++++++++++---------------------------
 1 file changed, 22 insertions(+), 37 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index fd352361259ca..348a379d4f051 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5410,6 +5410,8 @@ static void __free_event(struct perf_event *event)
 	call_rcu(&event->rcu_head, free_event_rcu);
 }
 
+DEFINE_FREE(__free_event, struct perf_event *, if (_T) __free_event(_T))
+
 /* vs perf_event_alloc() success */
 static void _free_event(struct perf_event *event)
 {
@@ -12291,7 +12293,6 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 		 void *context, int cgroup_fd)
 {
 	struct pmu *pmu;
-	struct perf_event *event;
 	struct hw_perf_event *hwc;
 	long err = -EINVAL;
 	int node;
@@ -12306,8 +12307,8 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	}
 
 	node = (cpu >= 0) ? cpu_to_node(cpu) : -1;
-	event = kmem_cache_alloc_node(perf_event_cache, GFP_KERNEL | __GFP_ZERO,
-				      node);
+	struct perf_event *event __free(__free_event) =
+		kmem_cache_alloc_node(perf_event_cache, GFP_KERNEL | __GFP_ZERO, node);
 	if (!event)
 		return ERR_PTR(-ENOMEM);
 
@@ -12414,65 +12415,53 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	 * See perf_output_read().
 	 */
 	if (has_inherit_and_sample_read(attr) && !(attr->sample_type & PERF_SAMPLE_TID))
-		goto err;
+		return ERR_PTR(-EINVAL);
 
 	if (!has_branch_stack(event))
 		event->attr.branch_sample_type = 0;
 
 	pmu = perf_init_event(event);
-	if (IS_ERR(pmu)) {
-		err = PTR_ERR(pmu);
-		goto err;
-	}
+	if (IS_ERR(pmu))
+		return (void*)pmu;
 
 	/*
 	 * Disallow uncore-task events. Similarly, disallow uncore-cgroup
 	 * events (they don't make sense as the cgroup will be different
 	 * on other CPUs in the uncore mask).
 	 */
-	if (pmu->task_ctx_nr == perf_invalid_context && (task || cgroup_fd != -1)) {
-		err = -EINVAL;
-		goto err;
-	}
+	if (pmu->task_ctx_nr == perf_invalid_context && (task || cgroup_fd != -1))
+		return ERR_PTR(-EINVAL);
 
 	if (event->attr.aux_output &&
 	    (!(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT) ||
-	     event->attr.aux_pause || event->attr.aux_resume)) {
-		err = -EOPNOTSUPP;
-		goto err;
-	}
+	     event->attr.aux_pause || event->attr.aux_resume))
+		return ERR_PTR(-EOPNOTSUPP);
 
-	if (event->attr.aux_pause && event->attr.aux_resume) {
-		err = -EINVAL;
-		goto err;
-	}
+	if (event->attr.aux_pause && event->attr.aux_resume)
+		return ERR_PTR(-EINVAL);
 
 	if (event->attr.aux_start_paused) {
-		if (!(pmu->capabilities & PERF_PMU_CAP_AUX_PAUSE)) {
-			err = -EOPNOTSUPP;
-			goto err;
-		}
+		if (!(pmu->capabilities & PERF_PMU_CAP_AUX_PAUSE))
+			return ERR_PTR(-EOPNOTSUPP);
 		event->hw.aux_paused = 1;
 	}
 
 	if (cgroup_fd != -1) {
 		err = perf_cgroup_connect(cgroup_fd, event, attr, group_leader);
 		if (err)
-			goto err;
+			return ERR_PTR(err);
 	}
 
 	err = exclusive_event_init(event);
 	if (err)
-		goto err;
+		return ERR_PTR(err);
 
 	if (has_addr_filter(event)) {
 		event->addr_filter_ranges = kcalloc(pmu->nr_addr_filters,
 						    sizeof(struct perf_addr_filter_range),
 						    GFP_KERNEL);
-		if (!event->addr_filter_ranges) {
-			err = -ENOMEM;
-			goto err;
-		}
+		if (!event->addr_filter_ranges)
+			return ERR_PTR(-ENOMEM);
 
 		/*
 		 * Clone the parent's vma offsets: they are valid until exec()
@@ -12496,23 +12485,19 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 		if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) {
 			err = get_callchain_buffers(attr->sample_max_stack);
 			if (err)
-				goto err;
+				return ERR_PTR(err);
 			event->attach_state |= PERF_ATTACH_CALLCHAIN;
 		}
 	}
 
 	err = security_perf_event_alloc(event);
 	if (err)
-		goto err;
+		return ERR_PTR(err);
 
 	/* symmetric to unaccount_event() in _free_event() */
 	account_event(event);
 
-	return event;
-
-err:
-	__free_event(event);
-	return ERR_PTR(err);
+	return_ptr(event);
 }
 
 static int perf_copy_attr(struct perf_event_attr __user *uattr,

From 4baeb0687abf5eca3f7ab8b147c27cce82ec49ea Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 4 Nov 2024 14:39:18 +0100
Subject: [PATCH 0882/1173] perf/core: Merge struct pmu::pmu_disable_count into
 struct perf_cpu_pmu_context::pmu_disable_count

Because it makes no sense to have two per-cpu allocations per pmu.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ravi Bangoria <ravi.bangoria@amd.com>
Link: https://lore.kernel.org/r/20241104135518.518730578@infradead.org
---
 include/linux/perf_event.h |  2 +-
 kernel/events/core.c       | 12 ++++--------
 2 files changed, 5 insertions(+), 9 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 8c0117bcbdb9f..5f293e679ab6b 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -343,7 +343,6 @@ struct pmu {
 	 */
 	unsigned int			scope;
 
-	int __percpu			*pmu_disable_count;
 	struct perf_cpu_pmu_context __percpu *cpu_pmu_context;
 	atomic_t			exclusive_cnt; /* < 0: cpu; > 0: tsk */
 	int				task_ctx_nr;
@@ -1031,6 +1030,7 @@ struct perf_cpu_pmu_context {
 
 	int				active_oncpu;
 	int				exclusive;
+	int				pmu_disable_count;
 
 	raw_spinlock_t			hrtimer_lock;
 	struct hrtimer			hrtimer;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 348a379d4f051..8321b719b6abf 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1219,21 +1219,22 @@ static int perf_mux_hrtimer_restart_ipi(void *arg)
 
 void perf_pmu_disable(struct pmu *pmu)
 {
-	int *count = this_cpu_ptr(pmu->pmu_disable_count);
+	int *count = &this_cpu_ptr(pmu->cpu_pmu_context)->pmu_disable_count;
 	if (!(*count)++)
 		pmu->pmu_disable(pmu);
 }
 
 void perf_pmu_enable(struct pmu *pmu)
 {
-	int *count = this_cpu_ptr(pmu->pmu_disable_count);
+	int *count = &this_cpu_ptr(pmu->cpu_pmu_context)->pmu_disable_count;
 	if (!--(*count))
 		pmu->pmu_enable(pmu);
 }
 
 static void perf_assert_pmu_disabled(struct pmu *pmu)
 {
-	WARN_ON_ONCE(*this_cpu_ptr(pmu->pmu_disable_count) == 0);
+	int *count = &this_cpu_ptr(pmu->cpu_pmu_context)->pmu_disable_count;
+	WARN_ON_ONCE(*count == 0);
 }
 
 static inline void perf_pmu_read(struct perf_event *event)
@@ -11906,7 +11907,6 @@ static bool idr_cmpxchg(struct idr *idr, unsigned long id, void *old, void *new)
 
 static void perf_pmu_free(struct pmu *pmu)
 {
-	free_percpu(pmu->pmu_disable_count);
 	if (pmu_bus_running && pmu->dev && pmu->dev != PMU_NULL_DEV) {
 		if (pmu->nr_addr_filters)
 			device_remove_file(pmu->dev, &dev_attr_nr_addr_filters);
@@ -11925,10 +11925,6 @@ int perf_pmu_register(struct pmu *_pmu, const char *name, int type)
 	struct pmu *pmu __free(pmu_unregister) = _pmu;
 	guard(mutex)(&pmus_lock);
 
-	pmu->pmu_disable_count = alloc_percpu(int);
-	if (!pmu->pmu_disable_count)
-		return -ENOMEM;
-
 	if (WARN_ONCE(!name, "Can not register anonymous pmu.\n"))
 		return -EINVAL;
 

From b2996f56556e389a13377158904c218da6fffa91 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 4 Nov 2024 14:39:19 +0100
Subject: [PATCH 0883/1173] perf/core: Add this_cpc() helper

As a preparation for adding yet another indirection.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ravi Bangoria <ravi.bangoria@amd.com>
Link: https://lore.kernel.org/r/20241104135518.650051565@infradead.org
---
 kernel/events/core.c | 34 ++++++++++++++++++----------------
 1 file changed, 18 insertions(+), 16 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 8321b719b6abf..0c7015f3ec030 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1217,23 +1217,28 @@ static int perf_mux_hrtimer_restart_ipi(void *arg)
 	return perf_mux_hrtimer_restart(arg);
 }
 
+static __always_inline struct perf_cpu_pmu_context *this_cpc(struct pmu *pmu)
+{
+	return this_cpu_ptr(pmu->cpu_pmu_context);
+}
+
 void perf_pmu_disable(struct pmu *pmu)
 {
-	int *count = &this_cpu_ptr(pmu->cpu_pmu_context)->pmu_disable_count;
+	int *count = &this_cpc(pmu)->pmu_disable_count;
 	if (!(*count)++)
 		pmu->pmu_disable(pmu);
 }
 
 void perf_pmu_enable(struct pmu *pmu)
 {
-	int *count = &this_cpu_ptr(pmu->cpu_pmu_context)->pmu_disable_count;
+	int *count = &this_cpc(pmu)->pmu_disable_count;
 	if (!--(*count))
 		pmu->pmu_enable(pmu);
 }
 
 static void perf_assert_pmu_disabled(struct pmu *pmu)
 {
-	int *count = &this_cpu_ptr(pmu->cpu_pmu_context)->pmu_disable_count;
+	int *count = &this_cpc(pmu)->pmu_disable_count;
 	WARN_ON_ONCE(*count == 0);
 }
 
@@ -2355,7 +2360,7 @@ static void
 event_sched_out(struct perf_event *event, struct perf_event_context *ctx)
 {
 	struct perf_event_pmu_context *epc = event->pmu_ctx;
-	struct perf_cpu_pmu_context *cpc = this_cpu_ptr(epc->pmu->cpu_pmu_context);
+	struct perf_cpu_pmu_context *cpc = this_cpc(epc->pmu);
 	enum perf_event_state state = PERF_EVENT_STATE_INACTIVE;
 
 	// XXX cpc serialization, probably per-cpu IRQ disabled
@@ -2496,9 +2501,8 @@ __perf_remove_from_context(struct perf_event *event,
 		pmu_ctx->rotate_necessary = 0;
 
 		if (ctx->task && ctx->is_active) {
-			struct perf_cpu_pmu_context *cpc;
+			struct perf_cpu_pmu_context *cpc = this_cpc(pmu_ctx->pmu);
 
-			cpc = this_cpu_ptr(pmu_ctx->pmu->cpu_pmu_context);
 			WARN_ON_ONCE(cpc->task_epc && cpc->task_epc != pmu_ctx);
 			cpc->task_epc = NULL;
 		}
@@ -2636,7 +2640,7 @@ static int
 event_sched_in(struct perf_event *event, struct perf_event_context *ctx)
 {
 	struct perf_event_pmu_context *epc = event->pmu_ctx;
-	struct perf_cpu_pmu_context *cpc = this_cpu_ptr(epc->pmu->cpu_pmu_context);
+	struct perf_cpu_pmu_context *cpc = this_cpc(epc->pmu);
 	int ret = 0;
 
 	WARN_ON_ONCE(event->ctx != ctx);
@@ -2743,7 +2747,7 @@ group_sched_in(struct perf_event *group_event, struct perf_event_context *ctx)
 static int group_can_go_on(struct perf_event *event, int can_add_hw)
 {
 	struct perf_event_pmu_context *epc = event->pmu_ctx;
-	struct perf_cpu_pmu_context *cpc = this_cpu_ptr(epc->pmu->cpu_pmu_context);
+	struct perf_cpu_pmu_context *cpc = this_cpc(epc->pmu);
 
 	/*
 	 * Groups consisting entirely of software events can always go on.
@@ -3366,9 +3370,8 @@ static void __pmu_ctx_sched_out(struct perf_event_pmu_context *pmu_ctx,
 	struct pmu *pmu = pmu_ctx->pmu;
 
 	if (ctx->task && !(ctx->is_active & EVENT_ALL)) {
-		struct perf_cpu_pmu_context *cpc;
+		struct perf_cpu_pmu_context *cpc = this_cpc(pmu);
 
-		cpc = this_cpu_ptr(pmu->cpu_pmu_context);
 		WARN_ON_ONCE(cpc->task_epc && cpc->task_epc != pmu_ctx);
 		cpc->task_epc = NULL;
 	}
@@ -3615,7 +3618,7 @@ static void perf_ctx_sched_task_cb(struct perf_event_context *ctx, bool sched_in
 	struct perf_cpu_pmu_context *cpc;
 
 	list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) {
-		cpc = this_cpu_ptr(pmu_ctx->pmu->cpu_pmu_context);
+		cpc = this_cpc(pmu_ctx->pmu);
 
 		if (cpc->sched_cb_usage && pmu_ctx->pmu->sched_task)
 			pmu_ctx->pmu->sched_task(pmu_ctx, sched_in);
@@ -3724,7 +3727,7 @@ static DEFINE_PER_CPU(int, perf_sched_cb_usages);
 
 void perf_sched_cb_dec(struct pmu *pmu)
 {
-	struct perf_cpu_pmu_context *cpc = this_cpu_ptr(pmu->cpu_pmu_context);
+	struct perf_cpu_pmu_context *cpc = this_cpc(pmu);
 
 	this_cpu_dec(perf_sched_cb_usages);
 	barrier();
@@ -3736,7 +3739,7 @@ void perf_sched_cb_dec(struct pmu *pmu)
 
 void perf_sched_cb_inc(struct pmu *pmu)
 {
-	struct perf_cpu_pmu_context *cpc = this_cpu_ptr(pmu->cpu_pmu_context);
+	struct perf_cpu_pmu_context *cpc = this_cpc(pmu);
 
 	if (!cpc->sched_cb_usage++)
 		list_add(&cpc->sched_cb_entry, this_cpu_ptr(&sched_cb_list));
@@ -3853,7 +3856,7 @@ static void __link_epc(struct perf_event_pmu_context *pmu_ctx)
 	if (!pmu_ctx->ctx->task)
 		return;
 
-	cpc = this_cpu_ptr(pmu_ctx->pmu->cpu_pmu_context);
+	cpc = this_cpc(pmu_ctx->pmu);
 	WARN_ON_ONCE(cpc->task_epc && cpc->task_epc != pmu_ctx);
 	cpc->task_epc = pmu_ctx;
 }
@@ -3982,10 +3985,9 @@ static int merge_sched_in(struct perf_event *event, void *data)
 			perf_cgroup_event_disable(event, ctx);
 			perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
 		} else {
-			struct perf_cpu_pmu_context *cpc;
+			struct perf_cpu_pmu_context *cpc = this_cpc(event->pmu_ctx->pmu);
 
 			event->pmu_ctx->rotate_necessary = 1;
-			cpc = this_cpu_ptr(event->pmu_ctx->pmu->cpu_pmu_context);
 			perf_mux_hrtimer_restart(cpc);
 			group_update_userpage(event);
 		}

From adc38b4ca1ed25ed2f1300e4d87c483bf51bfd50 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 4 Nov 2024 14:39:21 +0100
Subject: [PATCH 0884/1173] perf/core: Introduce perf_free_addr_filters()

Replace _free_event()'s use of perf_addr_filters_splice()s use with an
explicit perf_free_addr_filters() with the explicit propery that it is
able to be called a second time without ill effect.

Most notable, referencing event->pmu must be avoided when there are no
filters left (from eg a previous call).

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ravi Bangoria <ravi.bangoria@amd.com>
Link: https://lore.kernel.org/r/20241104135518.868460518@infradead.org
---
 kernel/events/core.c | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 0c7015f3ec030..525c64ee7925b 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5339,8 +5339,7 @@ static bool exclusive_event_installable(struct perf_event *event,
 	return true;
 }
 
-static void perf_addr_filters_splice(struct perf_event *event,
-				       struct list_head *head);
+static void perf_free_addr_filters(struct perf_event *event);
 
 static void perf_pending_task_sync(struct perf_event *event)
 {
@@ -5439,7 +5438,7 @@ static void _free_event(struct perf_event *event)
 	}
 
 	perf_event_free_bpf_prog(event);
-	perf_addr_filters_splice(event, NULL);
+	perf_free_addr_filters(event);
 
 	__free_event(event);
 }
@@ -11004,6 +11003,17 @@ static void perf_addr_filters_splice(struct perf_event *event,
 	free_filters_list(&list);
 }
 
+static void perf_free_addr_filters(struct perf_event *event)
+{
+	/*
+	 * Used during free paths, there is no concurrency.
+	 */
+	if (list_empty(&event->addr_filters.list))
+		return;
+
+	perf_addr_filters_splice(event, NULL);
+}
+
 /*
  * Scan through mm's vmas and see if one of them matches the
  * @filter; if so, adjust filter's address range.

From c5b96789575b670b1e776071bb243e0ed3d3abaa Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 4 Nov 2024 14:39:22 +0100
Subject: [PATCH 0885/1173] perf/bpf: Robustify perf_event_free_bpf_prog()

Ensure perf_event_free_bpf_prog() is safe to call a second time;
notably without making any references to event->pmu when there is no
prog left.

Note: perf_event_detach_bpf_prog() might leave a stale event->prog

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20241104135518.978956692@infradead.org
---
 kernel/events/core.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 525c64ee7925b..ab4e497087daf 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -10905,6 +10905,9 @@ int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog,
 
 void perf_event_free_bpf_prog(struct perf_event *event)
 {
+	if (!event->prog)
+		return;
+
 	if (!perf_event_is_tracing(event)) {
 		perf_event_free_bpf_handler(event);
 		return;

From 954878377bc81459b95937a05f01e8ebf6a05083 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 4 Nov 2024 14:39:23 +0100
Subject: [PATCH 0886/1173] perf/core: Simplify the perf_mmap() control flow

Identity-transform:

	if (c) {
		X1;
	} else {
		Y;
		goto l;
	}

	X2;
  l:

into the simpler:

	if (c) {
		X1;
		X2;
	} else {
		Y;
	}

[ mingo: Forward ported it ]

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ravi Bangoria <ravi.bangoria@amd.com>
Link: https://lore.kernel.org/r/20241104135519.095904637@infradead.org
---
 kernel/events/core.c | 75 +++++++++++++++++++++-----------------------
 1 file changed, 36 insertions(+), 39 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index ab4e497087daf..d1b04c8508810 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6701,6 +6701,42 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 
 	if (vma->vm_pgoff == 0) {
 		nr_pages = (vma_size / PAGE_SIZE) - 1;
+
+		/*
+		 * If we have rb pages ensure they're a power-of-two number, so we
+		 * can do bitmasks instead of modulo.
+		 */
+		if (nr_pages != 0 && !is_power_of_2(nr_pages))
+			return -EINVAL;
+
+		if (vma_size != PAGE_SIZE * (1 + nr_pages))
+			return -EINVAL;
+
+		WARN_ON_ONCE(event->ctx->parent_ctx);
+again:
+		mutex_lock(&event->mmap_mutex);
+		if (event->rb) {
+			if (data_page_nr(event->rb) != nr_pages) {
+				ret = -EINVAL;
+				goto unlock;
+			}
+
+			if (!atomic_inc_not_zero(&event->rb->mmap_count)) {
+				/*
+				 * Raced against perf_mmap_close(); remove the
+				 * event and try again.
+				 */
+				ring_buffer_attach(event, NULL);
+				mutex_unlock(&event->mmap_mutex);
+				goto again;
+			}
+
+			/* We need the rb to map pages. */
+			rb = event->rb;
+			goto unlock;
+		}
+
+		user_extra = nr_pages + 1;
 	} else {
 		/*
 		 * AUX area mapping: if rb->aux_nr_pages != 0, it's already
@@ -6760,47 +6796,8 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 
 		atomic_set(&rb->aux_mmap_count, 1);
 		user_extra = nr_pages;
-
-		goto accounting;
-	}
-
-	/*
-	 * If we have rb pages ensure they're a power-of-two number, so we
-	 * can do bitmasks instead of modulo.
-	 */
-	if (nr_pages != 0 && !is_power_of_2(nr_pages))
-		return -EINVAL;
-
-	if (vma_size != PAGE_SIZE * (1 + nr_pages))
-		return -EINVAL;
-
-	WARN_ON_ONCE(event->ctx->parent_ctx);
-again:
-	mutex_lock(&event->mmap_mutex);
-	if (event->rb) {
-		if (data_page_nr(event->rb) != nr_pages) {
-			ret = -EINVAL;
-			goto unlock;
-		}
-
-		if (!atomic_inc_not_zero(&event->rb->mmap_count)) {
-			/*
-			 * Raced against perf_mmap_close(); remove the
-			 * event and try again.
-			 */
-			ring_buffer_attach(event, NULL);
-			mutex_unlock(&event->mmap_mutex);
-			goto again;
-		}
-
-		/* We need the rb to map pages. */
-		rb = event->rb;
-		goto unlock;
 	}
 
-	user_extra = nr_pages + 1;
-
-accounting:
 	user_lock_limit = sysctl_perf_event_mlock >> (PAGE_SHIFT - 10);
 
 	/*

From 0c8a4e4139adf09b27fb910edbc596ea2d31a5db Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 4 Nov 2024 14:39:25 +0100
Subject: [PATCH 0887/1173] perf/core: Further simplify perf_mmap()

Perform CSE and such.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ravi Bangoria <ravi.bangoria@amd.com>
Link: https://lore.kernel.org/r/20241104135519.354909594@infradead.org
---
 kernel/events/core.c | 21 ++++++++++-----------
 1 file changed, 10 insertions(+), 11 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index d1b04c8508810..4cd3494c65e20 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6698,9 +6698,18 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 		return ret;
 
 	vma_size = vma->vm_end - vma->vm_start;
+	nr_pages = vma_size / PAGE_SIZE;
+
+	if (nr_pages > INT_MAX)
+		return -ENOMEM;
+
+	if (vma_size != PAGE_SIZE * nr_pages)
+		return -EINVAL;
+
+	user_extra = nr_pages;
 
 	if (vma->vm_pgoff == 0) {
-		nr_pages = (vma_size / PAGE_SIZE) - 1;
+		nr_pages -= 1;
 
 		/*
 		 * If we have rb pages ensure they're a power-of-two number, so we
@@ -6709,9 +6718,6 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 		if (nr_pages != 0 && !is_power_of_2(nr_pages))
 			return -EINVAL;
 
-		if (vma_size != PAGE_SIZE * (1 + nr_pages))
-			return -EINVAL;
-
 		WARN_ON_ONCE(event->ctx->parent_ctx);
 again:
 		mutex_lock(&event->mmap_mutex);
@@ -6735,8 +6741,6 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 			rb = event->rb;
 			goto unlock;
 		}
-
-		user_extra = nr_pages + 1;
 	} else {
 		/*
 		 * AUX area mapping: if rb->aux_nr_pages != 0, it's already
@@ -6748,10 +6752,6 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 		if (!event->rb)
 			return -EINVAL;
 
-		nr_pages = vma_size / PAGE_SIZE;
-		if (nr_pages > INT_MAX)
-			return -ENOMEM;
-
 		mutex_lock(&event->mmap_mutex);
 		ret = -EINVAL;
 
@@ -6795,7 +6795,6 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 		}
 
 		atomic_set(&rb->aux_mmap_count, 1);
-		user_extra = nr_pages;
 	}
 
 	user_lock_limit = sysctl_perf_event_mlock >> (PAGE_SHIFT - 10);

From 8eaec7bb723c9a0addfc0457e2f28e41735607af Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 4 Nov 2024 14:39:26 +0100
Subject: [PATCH 0888/1173] perf/core: Remove retry loop from perf_mmap()

AFAICT there is no actual benefit from the mutex drop on re-try. The
'worst' case scenario is that we instantly re-gain the mutex without
perf_mmap_close() getting it. So might as well make that the normal
case.

Reflow the code to make the ring buffer detach case naturally flow
into the no ring buffer case.

[ mingo: Forward ported it ]

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ravi Bangoria <ravi.bangoria@amd.com>
Link: https://lore.kernel.org/r/20241104135519.463607258@infradead.org
---
 kernel/events/core.c | 25 +++++++++++++++----------
 1 file changed, 15 insertions(+), 10 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4cd3494c65e20..ca4c1242c29b5 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6719,28 +6719,33 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 			return -EINVAL;
 
 		WARN_ON_ONCE(event->ctx->parent_ctx);
-again:
 		mutex_lock(&event->mmap_mutex);
+
 		if (event->rb) {
 			if (data_page_nr(event->rb) != nr_pages) {
 				ret = -EINVAL;
 				goto unlock;
 			}
 
-			if (!atomic_inc_not_zero(&event->rb->mmap_count)) {
+			if (atomic_inc_not_zero(&event->rb->mmap_count)) {
 				/*
-				 * Raced against perf_mmap_close(); remove the
-				 * event and try again.
+				 * Success -- managed to mmap() the same buffer
+				 * multiple times.
 				 */
-				ring_buffer_attach(event, NULL);
-				mutex_unlock(&event->mmap_mutex);
-				goto again;
+				ret = 0;
+				/* We need the rb to map pages. */
+				rb = event->rb;
+				goto unlock;
 			}
 
-			/* We need the rb to map pages. */
-			rb = event->rb;
-			goto unlock;
+			/*
+			 * Raced against perf_mmap_close()'s
+			 * atomic_dec_and_mutex_lock() remove the
+			 * event and continue as if !event->rb
+			 */
+			ring_buffer_attach(event, NULL);
 		}
+
 	} else {
 		/*
 		 * AUX area mapping: if rb->aux_nr_pages != 0, it's already

From 0983593f32c4c94239e01e42e4a17664b64a3c63 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 4 Nov 2024 14:39:27 +0100
Subject: [PATCH 0889/1173] perf/core: Lift event->mmap_mutex in perf_mmap()

This puts 'all' of perf_mmap() under single event->mmap_mutex.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ravi Bangoria <ravi.bangoria@amd.com>
Link: https://lore.kernel.org/r/20241104135519.582252957@infradead.org
---
 kernel/events/core.c | 20 ++++++++------------
 1 file changed, 8 insertions(+), 12 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index ca4c1242c29b5..773875aaa2916 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6680,7 +6680,7 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 	unsigned long vma_size;
 	unsigned long nr_pages;
 	long user_extra = 0, extra = 0;
-	int ret = 0, flags = 0;
+	int ret, flags = 0;
 
 	/*
 	 * Don't allow mmap() of inherited per-task counters. This would
@@ -6708,6 +6708,9 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 
 	user_extra = nr_pages;
 
+	mutex_lock(&event->mmap_mutex);
+	ret = -EINVAL;
+
 	if (vma->vm_pgoff == 0) {
 		nr_pages -= 1;
 
@@ -6716,16 +6719,13 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 		 * can do bitmasks instead of modulo.
 		 */
 		if (nr_pages != 0 && !is_power_of_2(nr_pages))
-			return -EINVAL;
+			goto unlock;
 
 		WARN_ON_ONCE(event->ctx->parent_ctx);
-		mutex_lock(&event->mmap_mutex);
 
 		if (event->rb) {
-			if (data_page_nr(event->rb) != nr_pages) {
-				ret = -EINVAL;
+			if (data_page_nr(event->rb) != nr_pages)
 				goto unlock;
-			}
 
 			if (atomic_inc_not_zero(&event->rb->mmap_count)) {
 				/*
@@ -6754,12 +6754,6 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 		 */
 		u64 aux_offset, aux_size;
 
-		if (!event->rb)
-			return -EINVAL;
-
-		mutex_lock(&event->mmap_mutex);
-		ret = -EINVAL;
-
 		rb = event->rb;
 		if (!rb)
 			goto aux_unlock;
@@ -6869,6 +6863,8 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 			rb->aux_mmap_locked = extra;
 	}
 
+	ret = 0;
+
 unlock:
 	if (!ret) {
 		atomic_long_add(user_extra, &user->locked_vm);

From 4eabf533fb1886089ef57e0c8ec52048b1741e39 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 4 Nov 2024 14:39:20 +0100
Subject: [PATCH 0890/1173] perf/core: Detach 'struct perf_cpu_pmu_context' and
 'struct pmu' lifetimes

In prepration for being able to unregister a PMU with existing events,
it becomes important to detach struct perf_cpu_pmu_context lifetimes
from that of struct pmu.

Notably struct perf_cpu_pmu_context embeds a struct perf_event_pmu_context
that can stay referenced until the last event goes.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ravi Bangoria <ravi.bangoria@amd.com>
Link: https://lore.kernel.org/r/20241104135518.760214287@infradead.org
---
 include/linux/perf_event.h |  4 +--
 kernel/events/core.c       | 56 ++++++++++++++++++++++++++++++++------
 2 files changed, 49 insertions(+), 11 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 5f293e679ab6b..76f4265efee92 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -343,7 +343,7 @@ struct pmu {
 	 */
 	unsigned int			scope;
 
-	struct perf_cpu_pmu_context __percpu *cpu_pmu_context;
+	struct perf_cpu_pmu_context __percpu **cpu_pmu_context;
 	atomic_t			exclusive_cnt; /* < 0: cpu; > 0: tsk */
 	int				task_ctx_nr;
 	int				hrtimer_interval_ms;
@@ -922,7 +922,7 @@ struct perf_event_pmu_context {
 	struct list_head		pinned_active;
 	struct list_head		flexible_active;
 
-	/* Used to avoid freeing per-cpu perf_event_pmu_context */
+	/* Used to identify the per-cpu perf_event_pmu_context */
 	unsigned int			embedded : 1;
 
 	unsigned int			nr_events;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 773875aaa2916..8b2a8c36d1241 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1219,7 +1219,7 @@ static int perf_mux_hrtimer_restart_ipi(void *arg)
 
 static __always_inline struct perf_cpu_pmu_context *this_cpc(struct pmu *pmu)
 {
-	return this_cpu_ptr(pmu->cpu_pmu_context);
+	return *this_cpu_ptr(pmu->cpu_pmu_context);
 }
 
 void perf_pmu_disable(struct pmu *pmu)
@@ -5007,11 +5007,14 @@ find_get_pmu_context(struct pmu *pmu, struct perf_event_context *ctx,
 		 */
 		struct perf_cpu_pmu_context *cpc;
 
-		cpc = per_cpu_ptr(pmu->cpu_pmu_context, event->cpu);
+		cpc = *per_cpu_ptr(pmu->cpu_pmu_context, event->cpu);
 		epc = &cpc->epc;
 		raw_spin_lock_irq(&ctx->lock);
 		if (!epc->ctx) {
-			atomic_set(&epc->refcount, 1);
+			/*
+			 * One extra reference for the pmu; see perf_pmu_free().
+			 */
+			atomic_set(&epc->refcount, 2);
 			epc->embedded = 1;
 			list_add(&epc->pmu_ctx_entry, &ctx->pmu_ctx_list);
 			epc->ctx = ctx;
@@ -5087,6 +5090,15 @@ static void get_pmu_ctx(struct perf_event_pmu_context *epc)
 	WARN_ON_ONCE(!atomic_inc_not_zero(&epc->refcount));
 }
 
+static void free_cpc_rcu(struct rcu_head *head)
+{
+	struct perf_cpu_pmu_context *cpc =
+		container_of(head, typeof(*cpc), epc.rcu_head);
+
+	kfree(cpc->epc.task_ctx_data);
+	kfree(cpc);
+}
+
 static void free_epc_rcu(struct rcu_head *head)
 {
 	struct perf_event_pmu_context *epc = container_of(head, typeof(*epc), rcu_head);
@@ -5121,8 +5133,10 @@ static void put_pmu_ctx(struct perf_event_pmu_context *epc)
 
 	raw_spin_unlock_irqrestore(&ctx->lock, flags);
 
-	if (epc->embedded)
+	if (epc->embedded) {
+		call_rcu(&epc->rcu_head, free_cpc_rcu);
 		return;
+	}
 
 	call_rcu(&epc->rcu_head, free_epc_rcu);
 }
@@ -11752,7 +11766,7 @@ perf_event_mux_interval_ms_store(struct device *dev,
 	cpus_read_lock();
 	for_each_online_cpu(cpu) {
 		struct perf_cpu_pmu_context *cpc;
-		cpc = per_cpu_ptr(pmu->cpu_pmu_context, cpu);
+		cpc = *per_cpu_ptr(pmu->cpu_pmu_context, cpu);
 		cpc->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * timer);
 
 		cpu_function_call(cpu, perf_mux_hrtimer_restart_ipi, cpc);
@@ -11925,7 +11939,25 @@ static void perf_pmu_free(struct pmu *pmu)
 		device_del(pmu->dev);
 		put_device(pmu->dev);
 	}
-	free_percpu(pmu->cpu_pmu_context);
+
+	if (pmu->cpu_pmu_context) {
+		int cpu;
+
+		for_each_possible_cpu(cpu) {
+			struct perf_cpu_pmu_context *cpc;
+
+			cpc = *per_cpu_ptr(pmu->cpu_pmu_context, cpu);
+			if (!cpc)
+				continue;
+			if (cpc->epc.embedded) {
+				/* refcount managed */
+				put_pmu_ctx(&cpc->epc);
+				continue;
+			}
+			kfree(cpc);
+		}
+		free_percpu(pmu->cpu_pmu_context);
+	}
 }
 
 DEFINE_FREE(pmu_unregister, struct pmu *, if (_T) perf_pmu_free(_T))
@@ -11964,14 +11996,20 @@ int perf_pmu_register(struct pmu *_pmu, const char *name, int type)
 			return ret;
 	}
 
-	pmu->cpu_pmu_context = alloc_percpu(struct perf_cpu_pmu_context);
+	pmu->cpu_pmu_context = alloc_percpu(struct perf_cpu_pmu_context *);
 	if (!pmu->cpu_pmu_context)
 		return -ENOMEM;
 
 	for_each_possible_cpu(cpu) {
-		struct perf_cpu_pmu_context *cpc;
+		struct perf_cpu_pmu_context *cpc =
+			kmalloc_node(sizeof(struct perf_cpu_pmu_context),
+				     GFP_KERNEL | __GFP_ZERO,
+				     cpu_to_node(cpu));
+
+		if (!cpc)
+			return -ENOMEM;
 
-		cpc = per_cpu_ptr(pmu->cpu_pmu_context, cpu);
+		*per_cpu_ptr(pmu->cpu_pmu_context, cpu) = cpc;
 		__perf_init_event_pmu_context(&cpc->epc, pmu);
 		__perf_mux_hrtimer_init(cpc, cpu);
 	}

From 66477c7230eb1f9b90deb8c0f4da2bac2053c329 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 4 Nov 2024 14:39:24 +0100
Subject: [PATCH 0891/1173] perf/core: Fix perf_mmap() failure path

When f_ops->mmap() returns failure, m_ops->close() is *not* called.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Ravi Bangoria <ravi.bangoria@amd.com>
Link: https://lore.kernel.org/r/20241104135519.248358497@infradead.org
---
 kernel/events/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 8b2a8c36d1241..b2334d27511b6 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6903,7 +6903,7 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 	if (!ret)
 		ret = map_range(rb, vma);
 
-	if (event->pmu->event_mapped)
+	if (!ret && event->pmu->event_mapped)
 		event->pmu->event_mapped(event, vma->vm_mm);
 
 	return ret;

From 8177c6bedb7013cf736137da586cf783922309dd Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <darwi@linutronix.de>
Date: Tue, 4 Mar 2025 09:51:12 +0100
Subject: [PATCH 0892/1173] x86/cacheinfo: Validate CPUID leaf 0x2 EDX output

CPUID leaf 0x2 emits one-byte descriptors in its four output registers
EAX, EBX, ECX, and EDX.  For these descriptors to be valid, the most
significant bit (MSB) of each register must be clear.

The historical Git commit:

  019361a20f016 ("- pre6: Intel: start to add Pentium IV specific stuff (128-byte cacheline etc)...")

introduced leaf 0x2 output parsing.  It only validated the MSBs of EAX,
EBX, and ECX, but left EDX unchecked.

Validate EDX's most-significant bit.

Signed-off-by: Ahmed S. Darwish <darwi@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: stable@vger.kernel.org
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250304085152.51092-2-darwi@linutronix.de
---
 arch/x86/kernel/cpu/cacheinfo.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index e6fa03ed9172c..a6c6bccfa8b8d 100644
--- a/arch/x86/kernel/cpu/cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -808,7 +808,7 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c)
 			cpuid(2, &regs[0], &regs[1], &regs[2], &regs[3]);
 
 			/* If bit 31 is set, this is an unknown format */
-			for (j = 0 ; j < 3 ; j++)
+			for (j = 0 ; j < 4 ; j++)
 				if (regs[j] & (1 << 31))
 					regs[j] = 0;
 

From 1881148215c67151b146450fb89ec22fd92337a7 Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <darwi@linutronix.de>
Date: Tue, 4 Mar 2025 09:51:13 +0100
Subject: [PATCH 0893/1173] x86/cpu: Validate CPUID leaf 0x2 EDX output

CPUID leaf 0x2 emits one-byte descriptors in its four output registers
EAX, EBX, ECX, and EDX.  For these descriptors to be valid, the most
significant bit (MSB) of each register must be clear.

Leaf 0x2 parsing at intel.c only validated the MSBs of EAX, EBX, and
ECX, but left EDX unchecked.

Validate EDX's most-significant bit as well.

Fixes: e0ba94f14f74 ("x86/tlb_info: get last level TLB entry number of CPU")
Signed-off-by: Ahmed S. Darwish <darwi@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: stable@kernel.org
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250304085152.51092-3-darwi@linutronix.de
---
 arch/x86/kernel/cpu/intel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 3dce22f00dc34..2a3716afee633 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -799,7 +799,7 @@ static void intel_detect_tlb(struct cpuinfo_x86 *c)
 		cpuid(2, &regs[0], &regs[1], &regs[2], &regs[3]);
 
 		/* If bit 31 is set, this is an unknown format */
-		for (j = 0 ; j < 3 ; j++)
+		for (j = 0 ; j < 4 ; j++)
 			if (regs[j] & (1 << 31))
 				regs[j] = 0;
 

From f6bdaab79ee4228a143ee1b4cb80416d6ffc0c63 Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <darwi@linutronix.de>
Date: Tue, 4 Mar 2025 09:51:14 +0100
Subject: [PATCH 0894/1173] x86/cpu: Properly parse CPUID leaf 0x2 TLB
 descriptor 0x63

CPUID leaf 0x2's one-byte TLB descriptors report the number of entries
for specific TLB types, among other properties.

Typically, each emitted descriptor implies the same number of entries
for its respective TLB type(s).  An emitted 0x63 descriptor is an
exception: it implies 4 data TLB entries for 1GB pages and 32 data TLB
entries for 2MB or 4MB pages.

For the TLB descriptors parsing code, the entry count for 1GB pages is
encoded at the intel_tlb_table[] mapping, but the 2MB/4MB entry count is
totally ignored.

Update leaf 0x2's parsing logic 0x2 to account for 32 data TLB entries
for 2MB/4MB pages implied by the 0x63 descriptor.

Fixes: e0ba94f14f74 ("x86/tlb_info: get last level TLB entry number of CPU")
Signed-off-by: Ahmed S. Darwish <darwi@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: stable@kernel.org
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250304085152.51092-4-darwi@linutronix.de
---
 arch/x86/kernel/cpu/intel.c | 50 +++++++++++++++++++++++++------------
 1 file changed, 34 insertions(+), 16 deletions(-)

diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 2a3716afee633..134368a3f4b1e 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -635,26 +635,37 @@ static unsigned int intel_size_cache(struct cpuinfo_x86 *c, unsigned int size)
 }
 #endif
 
-#define TLB_INST_4K	0x01
-#define TLB_INST_4M	0x02
-#define TLB_INST_2M_4M	0x03
+#define TLB_INST_4K		0x01
+#define TLB_INST_4M		0x02
+#define TLB_INST_2M_4M		0x03
 
-#define TLB_INST_ALL	0x05
-#define TLB_INST_1G	0x06
+#define TLB_INST_ALL		0x05
+#define TLB_INST_1G		0x06
 
-#define TLB_DATA_4K	0x11
-#define TLB_DATA_4M	0x12
-#define TLB_DATA_2M_4M	0x13
-#define TLB_DATA_4K_4M	0x14
+#define TLB_DATA_4K		0x11
+#define TLB_DATA_4M		0x12
+#define TLB_DATA_2M_4M		0x13
+#define TLB_DATA_4K_4M		0x14
 
-#define TLB_DATA_1G	0x16
+#define TLB_DATA_1G		0x16
+#define TLB_DATA_1G_2M_4M	0x17
 
-#define TLB_DATA0_4K	0x21
-#define TLB_DATA0_4M	0x22
-#define TLB_DATA0_2M_4M	0x23
+#define TLB_DATA0_4K		0x21
+#define TLB_DATA0_4M		0x22
+#define TLB_DATA0_2M_4M		0x23
 
-#define STLB_4K		0x41
-#define STLB_4K_2M	0x42
+#define STLB_4K			0x41
+#define STLB_4K_2M		0x42
+
+/*
+ * All of leaf 0x2's one-byte TLB descriptors implies the same number of
+ * entries for their respective TLB types.  The 0x63 descriptor is an
+ * exception: it implies 4 dTLB entries for 1GB pages 32 dTLB entries
+ * for 2MB or 4MB pages.  Encode descriptor 0x63 dTLB entry count for
+ * 2MB/4MB pages here, as its count for dTLB 1GB pages is already at the
+ * intel_tlb_table[] mapping.
+ */
+#define TLB_0x63_2M_4M_ENTRIES	32
 
 static const struct _tlb_table intel_tlb_table[] = {
 	{ 0x01, TLB_INST_4K,		32,	" TLB_INST 4 KByte pages, 4-way set associative" },
@@ -676,7 +687,8 @@ static const struct _tlb_table intel_tlb_table[] = {
 	{ 0x5c, TLB_DATA_4K_4M,		128,	" TLB_DATA 4 KByte and 4 MByte pages" },
 	{ 0x5d, TLB_DATA_4K_4M,		256,	" TLB_DATA 4 KByte and 4 MByte pages" },
 	{ 0x61, TLB_INST_4K,		48,	" TLB_INST 4 KByte pages, full associative" },
-	{ 0x63, TLB_DATA_1G,		4,	" TLB_DATA 1 GByte pages, 4-way set associative" },
+	{ 0x63, TLB_DATA_1G_2M_4M,	4,	" TLB_DATA 1 GByte pages, 4-way set associative"
+						" (plus 32 entries TLB_DATA 2 MByte or 4 MByte pages, not encoded here)" },
 	{ 0x6b, TLB_DATA_4K,		256,	" TLB_DATA 4 KByte pages, 8-way associative" },
 	{ 0x6c, TLB_DATA_2M_4M,		128,	" TLB_DATA 2 MByte or 4 MByte pages, 8-way associative" },
 	{ 0x6d, TLB_DATA_1G,		16,	" TLB_DATA 1 GByte pages, fully associative" },
@@ -776,6 +788,12 @@ static void intel_tlb_lookup(const unsigned char desc)
 		if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
 			tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
 		break;
+	case TLB_DATA_1G_2M_4M:
+		if (tlb_lld_2m[ENTRIES] < TLB_0x63_2M_4M_ENTRIES)
+			tlb_lld_2m[ENTRIES] = TLB_0x63_2M_4M_ENTRIES;
+		if (tlb_lld_4m[ENTRIES] < TLB_0x63_2M_4M_ENTRIES)
+			tlb_lld_4m[ENTRIES] = TLB_0x63_2M_4M_ENTRIES;
+		fallthrough;
 	case TLB_DATA_1G:
 		if (tlb_lld_1g[ENTRIES] < intel_tlb_table[k].entries)
 			tlb_lld_1g[ENTRIES] = intel_tlb_table[k].entries;

From 091b768604a8df7822aade75dd5bfc5c788154ee Mon Sep 17 00:00:00 2001
From: Lukas Bulwahn <lukas.bulwahn@redhat.com>
Date: Mon, 3 Mar 2025 10:37:59 +0100
Subject: [PATCH 0895/1173] xen: Kconfig: Drop reference to obsolete configs
 MCORE2 and MK8

Commit f388f60ca904 ("x86/cpu: Drop configuration options for early 64-bit CPUs")
removes the config symbols MCORE2 and MK8.

With that, the references to those two config symbols in xen's x86 Kconfig
are obsolete. Drop them.

Fixes: f388f60ca904 ("x86/cpu: Drop configuration options for early 64-bit CPUs")
Signed-off-by: Lukas Bulwahn <lukas.bulwahn@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Juergen Gross <jgross@suse.com>
Link: https://lore.kernel.org/r/20250303093759.371445-1-lukas.bulwahn@redhat.com
---
 arch/x86/xen/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index 77e788e928cd4..98d8a50d2aed4 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -9,7 +9,7 @@ config XEN
 	select PARAVIRT_CLOCK
 	select X86_HV_CALLBACK_VECTOR
 	depends on X86_64 || (X86_32 && X86_PAE)
-	depends on X86_64 || (X86_GENERIC || MPENTIUM4 || MCORE2 || MATOM || MK8)
+	depends on X86_64 || (X86_GENERIC || MPENTIUM4 || MATOM)
 	depends on X86_LOCAL_APIC && X86_TSC
 	help
 	  This is the Linux Xen port.  Enabling this will allow the

From 1a82d19ca2d6835904ee71e2d40fd331098f94a0 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <razor@blackwall.org>
Date: Thu, 27 Feb 2025 18:41:29 +0200
Subject: [PATCH 0896/1173] be2net: fix sleeping while atomic bugs in
 be_ndo_bridge_getlink

Partially revert commit b71724147e73 ("be2net: replace polling with
sleeping in the FW completion path") w.r.t mcc mutex it introduces and the
use of usleep_range. The be2net be_ndo_bridge_getlink() callback is
called with rcu_read_lock, so this code has been broken for a long time.
Both the mutex_lock and the usleep_range can cause the issue Ian Kumlien
reported[1]. The call path is:
be_ndo_bridge_getlink -> be_cmd_get_hsw_config -> be_mcc_notify_wait ->
be_mcc_wait_compl -> usleep_range()

[1] https://lore.kernel.org/netdev/CAA85sZveppNgEVa_FD+qhOMtG_AavK9_mFiU+jWrMtXmwqefGA@mail.gmail.com/

Tested-by: Ian Kumlien <ian.kumlien@gmail.com>
Fixes: b71724147e73 ("be2net: replace polling with sleeping in the FW completion path")
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20250227164129.1201164-1-razor@blackwall.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/emulex/benet/be.h      |   2 +-
 drivers/net/ethernet/emulex/benet/be_cmds.c | 197 ++++++++++----------
 drivers/net/ethernet/emulex/benet/be_main.c |   2 +-
 3 files changed, 100 insertions(+), 101 deletions(-)

diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index e48b861e4ce15..270ff9aab3352 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -562,7 +562,7 @@ struct be_adapter {
 	struct be_dma_mem mbox_mem_alloced;
 
 	struct be_mcc_obj mcc_obj;
-	struct mutex mcc_lock;	/* For serializing mcc cmds to BE card */
+	spinlock_t mcc_lock;	/* For serializing mcc cmds to BE card */
 	spinlock_t mcc_cq_lock;
 
 	u16 cfg_num_rx_irqs;		/* configured via set-channels */
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index 61adcebeef010..51b8377edd1d0 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -575,7 +575,7 @@ int be_process_mcc(struct be_adapter *adapter)
 /* Wait till no more pending mcc requests are present */
 static int be_mcc_wait_compl(struct be_adapter *adapter)
 {
-#define mcc_timeout		12000 /* 12s timeout */
+#define mcc_timeout		120000 /* 12s timeout */
 	int i, status = 0;
 	struct be_mcc_obj *mcc_obj = &adapter->mcc_obj;
 
@@ -589,7 +589,7 @@ static int be_mcc_wait_compl(struct be_adapter *adapter)
 
 		if (atomic_read(&mcc_obj->q.used) == 0)
 			break;
-		usleep_range(500, 1000);
+		udelay(100);
 	}
 	if (i == mcc_timeout) {
 		dev_err(&adapter->pdev->dev, "FW not responding\n");
@@ -866,7 +866,7 @@ static bool use_mcc(struct be_adapter *adapter)
 static int be_cmd_lock(struct be_adapter *adapter)
 {
 	if (use_mcc(adapter)) {
-		mutex_lock(&adapter->mcc_lock);
+		spin_lock_bh(&adapter->mcc_lock);
 		return 0;
 	} else {
 		return mutex_lock_interruptible(&adapter->mbox_lock);
@@ -877,7 +877,7 @@ static int be_cmd_lock(struct be_adapter *adapter)
 static void be_cmd_unlock(struct be_adapter *adapter)
 {
 	if (use_mcc(adapter))
-		return mutex_unlock(&adapter->mcc_lock);
+		return spin_unlock_bh(&adapter->mcc_lock);
 	else
 		return mutex_unlock(&adapter->mbox_lock);
 }
@@ -1047,7 +1047,7 @@ int be_cmd_mac_addr_query(struct be_adapter *adapter, u8 *mac_addr,
 	struct be_cmd_req_mac_query *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1076,7 +1076,7 @@ int be_cmd_mac_addr_query(struct be_adapter *adapter, u8 *mac_addr,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1088,7 +1088,7 @@ int be_cmd_pmac_add(struct be_adapter *adapter, const u8 *mac_addr,
 	struct be_cmd_req_pmac_add *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1113,7 +1113,7 @@ int be_cmd_pmac_add(struct be_adapter *adapter, const u8 *mac_addr,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 
 	if (base_status(status) == MCC_STATUS_UNAUTHORIZED_REQUEST)
 		status = -EPERM;
@@ -1131,7 +1131,7 @@ int be_cmd_pmac_del(struct be_adapter *adapter, u32 if_id, int pmac_id, u32 dom)
 	if (pmac_id == -1)
 		return 0;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1151,7 +1151,7 @@ int be_cmd_pmac_del(struct be_adapter *adapter, u32 if_id, int pmac_id, u32 dom)
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1414,7 +1414,7 @@ int be_cmd_rxq_create(struct be_adapter *adapter,
 	struct be_dma_mem *q_mem = &rxq->dma_mem;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1444,7 +1444,7 @@ int be_cmd_rxq_create(struct be_adapter *adapter,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1508,7 +1508,7 @@ int be_cmd_rxq_destroy(struct be_adapter *adapter, struct be_queue_info *q)
 	struct be_cmd_req_q_destroy *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1525,7 +1525,7 @@ int be_cmd_rxq_destroy(struct be_adapter *adapter, struct be_queue_info *q)
 	q->created = false;
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1593,7 +1593,7 @@ int be_cmd_get_stats(struct be_adapter *adapter, struct be_dma_mem *nonemb_cmd)
 	struct be_cmd_req_hdr *hdr;
 	int status = 0;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1621,7 +1621,7 @@ int be_cmd_get_stats(struct be_adapter *adapter, struct be_dma_mem *nonemb_cmd)
 	adapter->stats_cmd_sent = true;
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1637,7 +1637,7 @@ int lancer_cmd_get_pport_stats(struct be_adapter *adapter,
 			    CMD_SUBSYSTEM_ETH))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1660,7 +1660,7 @@ int lancer_cmd_get_pport_stats(struct be_adapter *adapter,
 	adapter->stats_cmd_sent = true;
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1697,7 +1697,7 @@ int be_cmd_link_status_query(struct be_adapter *adapter, u16 *link_speed,
 	struct be_cmd_req_link_status *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	if (link_status)
 		*link_status = LINK_DOWN;
@@ -1736,7 +1736,7 @@ int be_cmd_link_status_query(struct be_adapter *adapter, u16 *link_speed,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1747,7 +1747,7 @@ int be_cmd_get_die_temperature(struct be_adapter *adapter)
 	struct be_cmd_req_get_cntl_addnl_attribs *req;
 	int status = 0;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1762,7 +1762,7 @@ int be_cmd_get_die_temperature(struct be_adapter *adapter)
 
 	status = be_mcc_notify(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1811,7 +1811,7 @@ int be_cmd_get_fat_dump(struct be_adapter *adapter, u32 buf_len, void *buf)
 	if (!get_fat_cmd.va)
 		return -ENOMEM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	while (total_size) {
 		buf_size = min(total_size, (u32)60 * 1024);
@@ -1849,9 +1849,9 @@ int be_cmd_get_fat_dump(struct be_adapter *adapter, u32 buf_len, void *buf)
 		log_offset += buf_size;
 	}
 err:
+	spin_unlock_bh(&adapter->mcc_lock);
 	dma_free_coherent(&adapter->pdev->dev, get_fat_cmd.size,
 			  get_fat_cmd.va, get_fat_cmd.dma);
-	mutex_unlock(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1862,7 +1862,7 @@ int be_cmd_get_fw_ver(struct be_adapter *adapter)
 	struct be_cmd_req_get_fw_version *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1885,7 +1885,7 @@ int be_cmd_get_fw_ver(struct be_adapter *adapter)
 			sizeof(adapter->fw_on_flash));
 	}
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1899,7 +1899,7 @@ static int __be_cmd_modify_eqd(struct be_adapter *adapter,
 	struct be_cmd_req_modify_eq_delay *req;
 	int status = 0, i;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1922,7 +1922,7 @@ static int __be_cmd_modify_eqd(struct be_adapter *adapter,
 
 	status = be_mcc_notify(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1949,7 +1949,7 @@ int be_cmd_vlan_config(struct be_adapter *adapter, u32 if_id, u16 *vtag_array,
 	struct be_cmd_req_vlan_config *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1971,7 +1971,7 @@ int be_cmd_vlan_config(struct be_adapter *adapter, u32 if_id, u16 *vtag_array,
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1982,7 +1982,7 @@ static int __be_cmd_rx_filter(struct be_adapter *adapter, u32 flags, u32 value)
 	struct be_cmd_req_rx_filter *req = mem->va;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2015,7 +2015,7 @@ static int __be_cmd_rx_filter(struct be_adapter *adapter, u32 flags, u32 value)
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2046,7 +2046,7 @@ int be_cmd_set_flow_control(struct be_adapter *adapter, u32 tx_fc, u32 rx_fc)
 			    CMD_SUBSYSTEM_COMMON))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2066,7 +2066,7 @@ int be_cmd_set_flow_control(struct be_adapter *adapter, u32 tx_fc, u32 rx_fc)
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 
 	if (base_status(status) == MCC_STATUS_FEATURE_NOT_SUPPORTED)
 		return  -EOPNOTSUPP;
@@ -2085,7 +2085,7 @@ int be_cmd_get_flow_control(struct be_adapter *adapter, u32 *tx_fc, u32 *rx_fc)
 			    CMD_SUBSYSTEM_COMMON))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2108,7 +2108,7 @@ int be_cmd_get_flow_control(struct be_adapter *adapter, u32 *tx_fc, u32 *rx_fc)
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2189,7 +2189,7 @@ int be_cmd_rss_config(struct be_adapter *adapter, u8 *rsstable,
 	if (!(be_if_cap_flags(adapter) & BE_IF_FLAGS_RSS))
 		return 0;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2214,7 +2214,7 @@ int be_cmd_rss_config(struct be_adapter *adapter, u8 *rsstable,
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2226,7 +2226,7 @@ int be_cmd_set_beacon_state(struct be_adapter *adapter, u8 port_num,
 	struct be_cmd_req_enable_disable_beacon *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2247,7 +2247,7 @@ int be_cmd_set_beacon_state(struct be_adapter *adapter, u8 port_num,
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2258,7 +2258,7 @@ int be_cmd_get_beacon_state(struct be_adapter *adapter, u8 port_num, u32 *state)
 	struct be_cmd_req_get_beacon_state *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2282,7 +2282,7 @@ int be_cmd_get_beacon_state(struct be_adapter *adapter, u8 port_num, u32 *state)
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2306,7 +2306,7 @@ int be_cmd_read_port_transceiver_data(struct be_adapter *adapter,
 		return -ENOMEM;
 	}
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2328,7 +2328,7 @@ int be_cmd_read_port_transceiver_data(struct be_adapter *adapter,
 		memcpy(data, resp->page_data + off, len);
 	}
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va, cmd.dma);
 	return status;
 }
@@ -2345,7 +2345,7 @@ static int lancer_cmd_write_object(struct be_adapter *adapter,
 	void *ctxt = NULL;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 	adapter->flash_status = 0;
 
 	wrb = wrb_from_mccq(adapter);
@@ -2387,7 +2387,7 @@ static int lancer_cmd_write_object(struct be_adapter *adapter,
 	if (status)
 		goto err_unlock;
 
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 
 	if (!wait_for_completion_timeout(&adapter->et_cmd_compl,
 					 msecs_to_jiffies(60000)))
@@ -2406,7 +2406,7 @@ static int lancer_cmd_write_object(struct be_adapter *adapter,
 	return status;
 
 err_unlock:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2460,7 +2460,7 @@ static int lancer_cmd_delete_object(struct be_adapter *adapter,
 	struct be_mcc_wrb *wrb;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2478,7 +2478,7 @@ static int lancer_cmd_delete_object(struct be_adapter *adapter,
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2491,7 +2491,7 @@ int lancer_cmd_read_object(struct be_adapter *adapter, struct be_dma_mem *cmd,
 	struct lancer_cmd_resp_read_object *resp;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2525,7 +2525,7 @@ int lancer_cmd_read_object(struct be_adapter *adapter, struct be_dma_mem *cmd,
 	}
 
 err_unlock:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2537,7 +2537,7 @@ static int be_cmd_write_flashrom(struct be_adapter *adapter,
 	struct be_cmd_write_flashrom *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 	adapter->flash_status = 0;
 
 	wrb = wrb_from_mccq(adapter);
@@ -2562,7 +2562,7 @@ static int be_cmd_write_flashrom(struct be_adapter *adapter,
 	if (status)
 		goto err_unlock;
 
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 
 	if (!wait_for_completion_timeout(&adapter->et_cmd_compl,
 					 msecs_to_jiffies(40000)))
@@ -2573,7 +2573,7 @@ static int be_cmd_write_flashrom(struct be_adapter *adapter,
 	return status;
 
 err_unlock:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2584,7 +2584,7 @@ static int be_cmd_get_flash_crc(struct be_adapter *adapter, u8 *flashed_crc,
 	struct be_mcc_wrb *wrb;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2611,7 +2611,7 @@ static int be_cmd_get_flash_crc(struct be_adapter *adapter, u8 *flashed_crc,
 		memcpy(flashed_crc, req->crc, 4);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3217,7 +3217,7 @@ int be_cmd_enable_magic_wol(struct be_adapter *adapter, u8 *mac,
 	struct be_cmd_req_acpi_wol_magic_config *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3234,7 +3234,7 @@ int be_cmd_enable_magic_wol(struct be_adapter *adapter, u8 *mac,
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3249,7 +3249,7 @@ int be_cmd_set_loopback(struct be_adapter *adapter, u8 port_num,
 			    CMD_SUBSYSTEM_LOWLEVEL))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3272,7 +3272,7 @@ int be_cmd_set_loopback(struct be_adapter *adapter, u8 port_num,
 	if (status)
 		goto err_unlock;
 
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 
 	if (!wait_for_completion_timeout(&adapter->et_cmd_compl,
 					 msecs_to_jiffies(SET_LB_MODE_TIMEOUT)))
@@ -3281,7 +3281,7 @@ int be_cmd_set_loopback(struct be_adapter *adapter, u8 port_num,
 	return status;
 
 err_unlock:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3298,7 +3298,7 @@ int be_cmd_loopback_test(struct be_adapter *adapter, u32 port_num,
 			    CMD_SUBSYSTEM_LOWLEVEL))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3324,7 +3324,7 @@ int be_cmd_loopback_test(struct be_adapter *adapter, u32 port_num,
 	if (status)
 		goto err;
 
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 
 	wait_for_completion(&adapter->et_cmd_compl);
 	resp = embedded_payload(wrb);
@@ -3332,7 +3332,7 @@ int be_cmd_loopback_test(struct be_adapter *adapter, u32 port_num,
 
 	return status;
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3348,7 +3348,7 @@ int be_cmd_ddr_dma_test(struct be_adapter *adapter, u64 pattern,
 			    CMD_SUBSYSTEM_LOWLEVEL))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3382,7 +3382,7 @@ int be_cmd_ddr_dma_test(struct be_adapter *adapter, u64 pattern,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3393,7 +3393,7 @@ int be_cmd_get_seeprom_data(struct be_adapter *adapter,
 	struct be_cmd_req_seeprom_read *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3409,7 +3409,7 @@ int be_cmd_get_seeprom_data(struct be_adapter *adapter,
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3424,7 +3424,7 @@ int be_cmd_get_phy_info(struct be_adapter *adapter)
 			    CMD_SUBSYSTEM_COMMON))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3469,7 +3469,7 @@ int be_cmd_get_phy_info(struct be_adapter *adapter)
 	}
 	dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va, cmd.dma);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3479,7 +3479,7 @@ static int be_cmd_set_qos(struct be_adapter *adapter, u32 bps, u32 domain)
 	struct be_cmd_req_set_qos *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3499,7 +3499,7 @@ static int be_cmd_set_qos(struct be_adapter *adapter, u32 bps, u32 domain)
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3611,7 +3611,7 @@ int be_cmd_get_fn_privileges(struct be_adapter *adapter, u32 *privilege,
 	struct be_cmd_req_get_fn_privileges *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3643,7 +3643,7 @@ int be_cmd_get_fn_privileges(struct be_adapter *adapter, u32 *privilege,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3655,7 +3655,7 @@ int be_cmd_set_fn_privileges(struct be_adapter *adapter, u32 privileges,
 	struct be_cmd_req_set_fn_privileges *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3675,7 +3675,7 @@ int be_cmd_set_fn_privileges(struct be_adapter *adapter, u32 privileges,
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3707,7 +3707,7 @@ int be_cmd_get_mac_from_list(struct be_adapter *adapter, u8 *mac,
 		return -ENOMEM;
 	}
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3771,7 +3771,7 @@ int be_cmd_get_mac_from_list(struct be_adapter *adapter, u8 *mac,
 	}
 
 out:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	dma_free_coherent(&adapter->pdev->dev, get_mac_list_cmd.size,
 			  get_mac_list_cmd.va, get_mac_list_cmd.dma);
 	return status;
@@ -3831,7 +3831,7 @@ int be_cmd_set_mac_list(struct be_adapter *adapter, u8 *mac_array,
 	if (!cmd.va)
 		return -ENOMEM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3853,7 +3853,7 @@ int be_cmd_set_mac_list(struct be_adapter *adapter, u8 *mac_array,
 
 err:
 	dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va, cmd.dma);
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3889,7 +3889,7 @@ int be_cmd_set_hsw_config(struct be_adapter *adapter, u16 pvid,
 			    CMD_SUBSYSTEM_COMMON))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3930,7 +3930,7 @@ int be_cmd_set_hsw_config(struct be_adapter *adapter, u16 pvid,
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3944,7 +3944,7 @@ int be_cmd_get_hsw_config(struct be_adapter *adapter, u16 *pvid,
 	int status;
 	u16 vid;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3991,7 +3991,7 @@ int be_cmd_get_hsw_config(struct be_adapter *adapter, u16 *pvid,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -4190,7 +4190,7 @@ int be_cmd_set_ext_fat_capabilites(struct be_adapter *adapter,
 	struct be_cmd_req_set_ext_fat_caps *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -4206,7 +4206,7 @@ int be_cmd_set_ext_fat_capabilites(struct be_adapter *adapter,
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -4684,7 +4684,7 @@ int be_cmd_manage_iface(struct be_adapter *adapter, u32 iface, u8 op)
 	if (iface == 0xFFFFFFFF)
 		return -1;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -4701,7 +4701,7 @@ int be_cmd_manage_iface(struct be_adapter *adapter, u32 iface, u8 op)
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -4735,7 +4735,7 @@ int be_cmd_get_if_id(struct be_adapter *adapter, struct be_vf_cfg *vf_cfg,
 	struct be_cmd_resp_get_iface_list *resp;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -4756,7 +4756,7 @@ int be_cmd_get_if_id(struct be_adapter *adapter, struct be_vf_cfg *vf_cfg,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -4850,7 +4850,7 @@ int be_cmd_enable_vf(struct be_adapter *adapter, u8 domain)
 	if (BEx_chip(adapter))
 		return 0;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -4868,7 +4868,7 @@ int be_cmd_enable_vf(struct be_adapter *adapter, u8 domain)
 	req->enable = 1;
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -4941,7 +4941,7 @@ __be_cmd_set_logical_link_config(struct be_adapter *adapter,
 	u32 link_config = 0;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -4969,7 +4969,7 @@ __be_cmd_set_logical_link_config(struct be_adapter *adapter,
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -5000,8 +5000,7 @@ int be_cmd_set_features(struct be_adapter *adapter)
 	struct be_mcc_wrb *wrb;
 	int status;
 
-	if (mutex_lock_interruptible(&adapter->mcc_lock))
-		return -1;
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -5039,7 +5038,7 @@ int be_cmd_set_features(struct be_adapter *adapter)
 		dev_info(&adapter->pdev->dev,
 			 "Adapter does not support HW error recovery\n");
 
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -5053,7 +5052,7 @@ int be_roce_mcc_cmd(void *netdev_handle, void *wrb_payload,
 	struct be_cmd_resp_hdr *resp;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -5076,7 +5075,7 @@ int be_roce_mcc_cmd(void *netdev_handle, void *wrb_payload,
 	memcpy(wrb_payload, resp, sizeof(*resp) + resp->response_length);
 	be_dws_le_to_cpu(wrb_payload, sizeof(*resp) + resp->response_length);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 EXPORT_SYMBOL(be_roce_mcc_cmd);
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 875fe379eea21..3d2e215921191 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -5667,8 +5667,8 @@ static int be_drv_init(struct be_adapter *adapter)
 	}
 
 	mutex_init(&adapter->mbox_lock);
-	mutex_init(&adapter->mcc_lock);
 	mutex_init(&adapter->rx_filter_lock);
+	spin_lock_init(&adapter->mcc_lock);
 	spin_lock_init(&adapter->mcc_cq_lock);
 	init_completion(&adapter->et_cmd_compl);
 

From 4e32645cd8f97a308300623f81c902747df6b97b Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@kernel.org>
Date: Sun, 2 Mar 2025 16:48:51 -0800
Subject: [PATCH 0897/1173] x86/smp: Fix mwait_play_dead() and
 acpi_processor_ffh_play_dead() noreturn behavior

Fix some related issues (done in a single patch to avoid introducing
intermediate bisect warnings):

  1) The SMP version of mwait_play_dead() doesn't return, but its
     !SMP counterpart does.  Make its calling behavior consistent by
     resolving the !SMP version to a BUG().  It should never be called
     anyway, this just enforces that at runtime and enables its callers
     to be marked as __noreturn.

  2) While the SMP definition of mwait_play_dead() is annotated as
     __noreturn, the declaration isn't.  Nor is it listed in
     tools/objtool/noreturns.h.  Fix that.

  3) Similar to #1, the SMP version of acpi_processor_ffh_play_dead()
     doesn't return but its !SMP counterpart does.  Make the !SMP
     version a BUG().  It should never be called.

  4) acpi_processor_ffh_play_dead() doesn't return, but is lacking any
     __noreturn annotations.  Fix that.

This fixes the following objtool warnings:

  vmlinux.o: warning: objtool: acpi_processor_ffh_play_dead+0x67: mwait_play_dead() is missing a __noreturn annotation
  vmlinux.o: warning: objtool: acpi_idle_play_dead+0x3c: acpi_processor_ffh_play_dead() is missing a __noreturn annotation

Fixes: a7dd183f0b38 ("x86/smp: Allow calling mwait_play_dead with an arbitrary hint")
Fixes: 541ddf31e300 ("ACPI/processor_idle: Add FFH state handling")
Reported-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Paul E. McKenney <paulmck@kernel.org>
Link: https://lore.kernel.org/r/e885c6fa9e96a61471b33e48c2162d28b15b14c5.1740962711.git.jpoimboe@kernel.org
---
 arch/x86/include/asm/smp.h    | 4 ++--
 arch/x86/kernel/acpi/cstate.c | 2 +-
 include/acpi/processor.h      | 6 +++---
 tools/objtool/noreturns.h     | 2 ++
 4 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 80f8bfd83fc7b..1d3b11eba084d 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -114,7 +114,7 @@ void wbinvd_on_cpu(int cpu);
 int wbinvd_on_all_cpus(void);
 
 void smp_kick_mwait_play_dead(void);
-void mwait_play_dead(unsigned int eax_hint);
+void __noreturn mwait_play_dead(unsigned int eax_hint);
 
 void native_smp_send_reschedule(int cpu);
 void native_send_call_func_ipi(const struct cpumask *mask);
@@ -166,7 +166,7 @@ static inline struct cpumask *cpu_llc_shared_mask(int cpu)
 	return (struct cpumask *)cpumask_of(0);
 }
 
-static inline void mwait_play_dead(unsigned int eax_hint) { }
+static inline void __noreturn mwait_play_dead(unsigned int eax_hint) { BUG(); }
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_DEBUG_NMI_SELFTEST
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index 86c87c01d23df..d25584255ab82 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -206,7 +206,7 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu,
 }
 EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_probe);
 
-void acpi_processor_ffh_play_dead(struct acpi_processor_cx *cx)
+void __noreturn acpi_processor_ffh_play_dead(struct acpi_processor_cx *cx)
 {
 	unsigned int cpu = smp_processor_id();
 	struct cstate_entry *percpu_entry;
diff --git a/include/acpi/processor.h b/include/acpi/processor.h
index 63a37e72b7218..d0eccbd920e5c 100644
--- a/include/acpi/processor.h
+++ b/include/acpi/processor.h
@@ -280,7 +280,7 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu,
 				    struct acpi_processor_cx *cx,
 				    struct acpi_power_register *reg);
 void acpi_processor_ffh_cstate_enter(struct acpi_processor_cx *cstate);
-void acpi_processor_ffh_play_dead(struct acpi_processor_cx *cx);
+void __noreturn acpi_processor_ffh_play_dead(struct acpi_processor_cx *cx);
 #else
 static inline void acpi_processor_power_init_bm_check(struct
 						      acpi_processor_flags
@@ -301,9 +301,9 @@ static inline void acpi_processor_ffh_cstate_enter(struct acpi_processor_cx
 {
 	return;
 }
-static inline void acpi_processor_ffh_play_dead(struct acpi_processor_cx *cx)
+static inline void __noreturn acpi_processor_ffh_play_dead(struct acpi_processor_cx *cx)
 {
-	return;
+	BUG();
 }
 #endif
 
diff --git a/tools/objtool/noreturns.h b/tools/objtool/noreturns.h
index b2174894f9f71..5a4aec4c46398 100644
--- a/tools/objtool/noreturns.h
+++ b/tools/objtool/noreturns.h
@@ -16,6 +16,7 @@ NORETURN(__tdx_hypercall_failed)
 NORETURN(__ubsan_handle_builtin_unreachable)
 NORETURN(__x64_sys_exit)
 NORETURN(__x64_sys_exit_group)
+NORETURN(acpi_processor_ffh_play_dead)
 NORETURN(arch_cpu_idle_dead)
 NORETURN(bch2_trans_in_restart_error)
 NORETURN(bch2_trans_restart_error)
@@ -34,6 +35,7 @@ NORETURN(kunit_try_catch_throw)
 NORETURN(machine_real_restart)
 NORETURN(make_task_dead)
 NORETURN(mpt_halt_firmware)
+NORETURN(mwait_play_dead)
 NORETURN(nmi_panic_self_stop)
 NORETURN(panic)
 NORETURN(panic_smp_self_stop)

From cfceff8526a426948b53445c02bcb98453c7330d Mon Sep 17 00:00:00 2001
From: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Date: Fri, 28 Feb 2025 18:35:43 -0800
Subject: [PATCH 0898/1173] x86/speculation: Simplify and make CALL_NOSPEC
 consistent

CALL_NOSPEC macro is used to generate Spectre-v2 mitigation friendly
indirect branches. At compile time the macro defaults to indirect branch,
and at runtime those can be patched to thunk based mitigations.

This approach is opposite of what is done for the rest of the kernel, where
the compile time default is to replace indirect calls with retpoline thunk
calls.

Make CALL_NOSPEC consistent with the rest of the kernel, default to
retpoline thunk at compile time when CONFIG_MITIGATION_RETPOLINE is
enabled.

Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Andrew Cooper <andrew.cooper3@citrix.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250228-call-nospec-v3-1-96599fed0f33@linux.intel.com
---
 arch/x86/include/asm/nospec-branch.h | 15 +++++----------
 1 file changed, 5 insertions(+), 10 deletions(-)

diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 7e8bf78c03d5d..1e6b915ce9564 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -424,16 +424,11 @@ static inline void call_depth_return_thunk(void) {}
  * Inline asm uses the %V modifier which is only in newer GCC
  * which is ensured when CONFIG_MITIGATION_RETPOLINE is defined.
  */
-# define CALL_NOSPEC						\
-	ALTERNATIVE_2(						\
-	ANNOTATE_RETPOLINE_SAFE					\
-	"call *%[thunk_target]\n",				\
-	"call __x86_indirect_thunk_%V[thunk_target]\n",		\
-	X86_FEATURE_RETPOLINE,					\
-	"lfence;\n"						\
-	ANNOTATE_RETPOLINE_SAFE					\
-	"call *%[thunk_target]\n",				\
-	X86_FEATURE_RETPOLINE_LFENCE)
+#ifdef CONFIG_MITIGATION_RETPOLINE
+#define CALL_NOSPEC	"call __x86_indirect_thunk_%V[thunk_target]\n"
+#else
+#define CALL_NOSPEC	"call *%[thunk_target]\n"
+#endif
 
 # define THUNK_TARGET(addr) [thunk_target] "r" (addr)
 

From 052040e34c08428a5a388b85787e8531970c0c67 Mon Sep 17 00:00:00 2001
From: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Date: Fri, 28 Feb 2025 18:35:58 -0800
Subject: [PATCH 0899/1173] x86/speculation: Add a conditional CS prefix to
 CALL_NOSPEC

Retpoline mitigation for spectre-v2 uses thunks for indirect branches. To
support this mitigation compilers add a CS prefix with
-mindirect-branch-cs-prefix. For an indirect branch in asm, this needs to
be added manually.

CS prefix is already being added to indirect branches in asm files, but not
in inline asm. Add CS prefix to CALL_NOSPEC for inline asm as well. There
is no JMP_NOSPEC for inline asm.

Reported-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Andrew Cooper <andrew.cooper3@citrix.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250228-call-nospec-v3-2-96599fed0f33@linux.intel.com
---
 arch/x86/include/asm/nospec-branch.h | 19 +++++++++++++++----
 1 file changed, 15 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 1e6b915ce9564..aee26bb8230f8 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -198,9 +198,8 @@
 .endm
 
 /*
- * Equivalent to -mindirect-branch-cs-prefix; emit the 5 byte jmp/call
- * to the retpoline thunk with a CS prefix when the register requires
- * a RAX prefix byte to encode. Also see apply_retpolines().
+ * Emits a conditional CS prefix that is compatible with
+ * -mindirect-branch-cs-prefix.
  */
 .macro __CS_PREFIX reg:req
 	.irp rs,r8,r9,r10,r11,r12,r13,r14,r15
@@ -420,12 +419,24 @@ static inline void call_depth_return_thunk(void) {}
 
 #ifdef CONFIG_X86_64
 
+/*
+ * Emits a conditional CS prefix that is compatible with
+ * -mindirect-branch-cs-prefix.
+ */
+#define __CS_PREFIX(reg)				\
+	".irp rs,r8,r9,r10,r11,r12,r13,r14,r15\n"	\
+	".ifc \\rs," reg "\n"				\
+	".byte 0x2e\n"					\
+	".endif\n"					\
+	".endr\n"
+
 /*
  * Inline asm uses the %V modifier which is only in newer GCC
  * which is ensured when CONFIG_MITIGATION_RETPOLINE is defined.
  */
 #ifdef CONFIG_MITIGATION_RETPOLINE
-#define CALL_NOSPEC	"call __x86_indirect_thunk_%V[thunk_target]\n"
+#define CALL_NOSPEC	__CS_PREFIX("%V[thunk_target]")	\
+			"call __x86_indirect_thunk_%V[thunk_target]\n"
 #else
 #define CALL_NOSPEC	"call *%[thunk_target]\n"
 #endif

From 27c3b452c1a554483ac692702639c826602d1089 Mon Sep 17 00:00:00 2001
From: Brendan Jackman <jackmanb@google.com>
Date: Mon, 3 Mar 2025 15:45:37 +0000
Subject: [PATCH 0900/1173] x86/cpu: Remove unnecessary macro indirection
 related to CPU feature names

These macros used to abstract over CONFIG_X86_FEATURE_NAMES, but that
was removed in:

  7583e8fbdc49 ("x86/cpu: Remove X86_FEATURE_NAMES")

Now they are just an unnecessary indirection, remove them.

Signed-off-by: Brendan Jackman <jackmanb@google.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20250303-setcpuid-taint-louder-v1-1-8d255032cb4c@google.com
---
 arch/x86/include/asm/cpufeature.h |  5 -----
 arch/x86/kernel/cpu/common.c      | 12 ++++++------
 2 files changed, 6 insertions(+), 11 deletions(-)

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index e5fc0038c8f65..e955da397e0e2 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -37,13 +37,8 @@ enum cpuid_leafs
 	NR_CPUID_WORDS,
 };
 
-#define X86_CAP_FMT_NUM "%d:%d"
-#define x86_cap_flag_num(flag) ((flag) >> 5), ((flag) & 31)
-
 extern const char * const x86_cap_flags[NCAPINTS*32];
 extern const char * const x86_power_flags[32];
-#define X86_CAP_FMT "%s"
-#define x86_cap_flag(flag) x86_cap_flags[flag]
 
 /*
  * In order to save room, we index into this array by doing
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 0f32b6ffbf04f..b5fdaa6fd4c4f 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -667,8 +667,8 @@ static void filter_cpuid_features(struct cpuinfo_x86 *c, bool warn)
 		if (!warn)
 			continue;
 
-		pr_warn("CPU: CPU feature " X86_CAP_FMT " disabled, no CPUID level 0x%x\n",
-			x86_cap_flag(df->feature), df->level);
+		pr_warn("CPU: CPU feature %s disabled, no CPUID level 0x%x\n",
+			x86_cap_flags[df->feature], df->level);
 	}
 }
 
@@ -1502,9 +1502,9 @@ static inline void parse_set_clear_cpuid(char *arg, bool set)
 
 				/* empty-string, i.e., ""-defined feature flags */
 				if (!x86_cap_flags[bit])
-					pr_cont(" " X86_CAP_FMT_NUM, x86_cap_flag_num(bit));
+					pr_cont(" %d:%d", bit >> 5, bit & 31);
 				else
-					pr_cont(" " X86_CAP_FMT, x86_cap_flag(bit));
+					pr_cont(" %s", x86_cap_flags[bit]);
 
 				if (set)
 					setup_force_cpu_cap(bit);
@@ -1523,9 +1523,9 @@ static inline void parse_set_clear_cpuid(char *arg, bool set)
 			const char *flag;
 
 			if (bit < 32 * NCAPINTS)
-				flag = x86_cap_flag(bit);
+				flag = x86_cap_flags[bit];
 			else
-				flag = x86_bug_flag(bit - (32 * NCAPINTS));
+				flag = x86_bug_flags[bit - (32 * NCAPINTS)];
 
 			if (!flag)
 				continue;

From 681955761bf6845241c6d33e2fb222f5e92c8b89 Mon Sep 17 00:00:00 2001
From: Brendan Jackman <jackmanb@google.com>
Date: Mon, 3 Mar 2025 15:45:38 +0000
Subject: [PATCH 0901/1173] x86/cpu: Warn louder about the {set,clear}cpuid
 boot parameters

Commit 814165e9fd1f6 ("x86/cpu: Add the 'setcpuid=' boot parameter")
recently expanded the user's ability to break their system horribly by
overriding effective CPU flags. This was reflected with updates to the
documentation to try and make people aware that this is dangerous.

To further reduce the risk of users mistaking this for a "real feature",
and try to help them figure out why their kernel is tainted if they do
use it:

- Upgrade the existing printk to pr_warn, to help ensure kernel logs
  reflect what changes are in effect.

- Print an extra warning that tries to be as dramatic as possible, while
  also highlighting the fact that it tainted the kernel.

Suggested-by: Ingo Molnar <mingo@redhat.com>
Signed-off-by: Brendan Jackman <jackmanb@google.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20250303-setcpuid-taint-louder-v1-2-8d255032cb4c@google.com
---
 arch/x86/kernel/cpu/common.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index b5fdaa6fd4c4f..c1ced31f976d9 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1479,12 +1479,12 @@ static void detect_nopl(void)
 #endif
 }
 
-static inline void parse_set_clear_cpuid(char *arg, bool set)
+static inline bool parse_set_clear_cpuid(char *arg, bool set)
 {
 	char *opt;
 	int taint = 0;
 
-	pr_info("%s CPUID bits:", set ? "Force-enabling" : "Clearing");
+	pr_warn("%s CPUID bits:", set ? "Force-enabling" : "Clearing");
 
 	while (arg) {
 		bool found __maybe_unused = false;
@@ -1547,10 +1547,9 @@ static inline void parse_set_clear_cpuid(char *arg, bool set)
 			pr_cont(" (unknown: %s)", opt);
 	}
 
-	if (taint)
-		add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK);
-
 	pr_cont("\n");
+
+	return taint;
 }
 
 
@@ -1560,6 +1559,7 @@ static inline void parse_set_clear_cpuid(char *arg, bool set)
  */
 static void __init cpu_parse_early_param(void)
 {
+	bool cpuid_taint = false;
 	char arg[128];
 	int arglen;
 
@@ -1594,11 +1594,16 @@ static void __init cpu_parse_early_param(void)
 
 	arglen = cmdline_find_option(boot_command_line, "clearcpuid", arg, sizeof(arg));
 	if (arglen > 0)
-		parse_set_clear_cpuid(arg, false);
+		cpuid_taint |= parse_set_clear_cpuid(arg, false);
 
 	arglen = cmdline_find_option(boot_command_line, "setcpuid", arg, sizeof(arg));
 	if (arglen > 0)
-		parse_set_clear_cpuid(arg, true);
+		cpuid_taint |= parse_set_clear_cpuid(arg, true);
+
+	if (cpuid_taint) {
+		pr_warn("!!! setcpuid=/clearcpuid= in use, this is for TESTING ONLY, may break things horribly. Tainting kernel.\n");
+		add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK);
+	}
 }
 
 /*

From d0ba9bcf001c7907e4755b0e498f5ff9d1a228ef Mon Sep 17 00:00:00 2001
From: Brendan Jackman <jackmanb@google.com>
Date: Mon, 3 Mar 2025 15:45:39 +0000
Subject: [PATCH 0902/1173] x86/cpu: Log CPU flag cmdline hacks more verbosely

Since using these options is very dangerous, make details as visible as
possible:

- Instead of a single message for each of the cmdline options, print a
  separate pr_warn() for each individual flag.

- Say explicitly whether the flag is a "feature" or a "bug".

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Brendan Jackman <jackmanb@google.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20250303-setcpuid-taint-louder-v1-3-8d255032cb4c@google.com
---
 arch/x86/kernel/cpu/common.c | 39 +++++++++++++++++++++---------------
 1 file changed, 23 insertions(+), 16 deletions(-)

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index c1ced31f976d9..8eba9ca9c2161 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1484,8 +1484,6 @@ static inline bool parse_set_clear_cpuid(char *arg, bool set)
 	char *opt;
 	int taint = 0;
 
-	pr_warn("%s CPUID bits:", set ? "Force-enabling" : "Clearing");
-
 	while (arg) {
 		bool found __maybe_unused = false;
 		unsigned int bit;
@@ -1500,16 +1498,19 @@ static inline bool parse_set_clear_cpuid(char *arg, bool set)
 		if (!kstrtouint(opt, 10, &bit)) {
 			if (bit < NCAPINTS * 32) {
 
+				if (set) {
+					pr_warn("setcpuid: force-enabling CPU feature flag:");
+					setup_force_cpu_cap(bit);
+				} else {
+					pr_warn("clearcpuid: force-disabling CPU feature flag:");
+					setup_clear_cpu_cap(bit);
+				}
 				/* empty-string, i.e., ""-defined feature flags */
 				if (!x86_cap_flags[bit])
-					pr_cont(" %d:%d", bit >> 5, bit & 31);
+					pr_cont(" %d:%d\n", bit >> 5, bit & 31);
 				else
-					pr_cont(" %s", x86_cap_flags[bit]);
+					pr_cont(" %s\n", x86_cap_flags[bit]);
 
-				if (set)
-					setup_force_cpu_cap(bit);
-				else
-					setup_clear_cpu_cap(bit);
 				taint++;
 			}
 			/*
@@ -1521,11 +1522,15 @@ static inline bool parse_set_clear_cpuid(char *arg, bool set)
 
 		for (bit = 0; bit < 32 * (NCAPINTS + NBUGINTS); bit++) {
 			const char *flag;
+			const char *kind;
 
-			if (bit < 32 * NCAPINTS)
+			if (bit < 32 * NCAPINTS) {
 				flag = x86_cap_flags[bit];
-			else
+				kind = "feature";
+			} else {
+				kind = "bug";
 				flag = x86_bug_flags[bit - (32 * NCAPINTS)];
+			}
 
 			if (!flag)
 				continue;
@@ -1533,22 +1538,24 @@ static inline bool parse_set_clear_cpuid(char *arg, bool set)
 			if (strcmp(flag, opt))
 				continue;
 
-			pr_cont(" %s", opt);
-			if (set)
+			if (set) {
+				pr_warn("setcpuid: force-enabling CPU %s flag: %s\n",
+					kind, flag);
 				setup_force_cpu_cap(bit);
-			else
+			} else {
+				pr_warn("clearcpuid: force-disabling CPU %s flag: %s\n",
+					kind, flag);
 				setup_clear_cpu_cap(bit);
+			}
 			taint++;
 			found = true;
 			break;
 		}
 
 		if (!found)
-			pr_cont(" (unknown: %s)", opt);
+			pr_warn("%s: unknown CPU flag: %s", set ? "setcpuid" : "clearcpuid", opt);
 	}
 
-	pr_cont("\n");
-
 	return taint;
 }
 

From 97c7d5723537de08e076892e07d6089ae9777965 Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <darwi@linutronix.de>
Date: Tue, 4 Mar 2025 09:51:15 +0100
Subject: [PATCH 0903/1173] x86/cpuid: Include <linux/build_bug.h> in
 <asm/cpuid.h>

<asm/cpuid.h> uses static_assert() at multiple locations but it does not
include the CPP macro's definition at linux/build_bug.h.

Include the needed header to make <asm/cpuid.h> self-sufficient.

This gets triggered when cpuid.h is included in new C files, which is to
be done in further commits.

Fixes: 43d86e3cd9a7 ("x86/cpu: Provide cpuid_read() et al.")
Signed-off-by: Ahmed S. Darwish <darwi@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250304085152.51092-5-darwi@linutronix.de
---
 arch/x86/include/asm/cpuid.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/include/asm/cpuid.h b/arch/x86/include/asm/cpuid.h
index b2b9b4ef3dae1..a92e4b08820ad 100644
--- a/arch/x86/include/asm/cpuid.h
+++ b/arch/x86/include/asm/cpuid.h
@@ -6,6 +6,7 @@
 #ifndef _ASM_X86_CPUID_H
 #define _ASM_X86_CPUID_H
 
+#include <linux/build_bug.h>
 #include <linux/types.h>
 
 #include <asm/string.h>

From dec7fdc0b79c2ae0a537343b17f5ba1c6c47e1ca Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <darwi@linutronix.de>
Date: Tue, 4 Mar 2025 09:51:16 +0100
Subject: [PATCH 0904/1173] x86/cpu: Remove unnecessary headers and reorder the
 rest

Remove the headers at intel.c that are no longer required.

Alphabetically reorder what remains since more headers will be included
in further commits.

Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ahmed S. Darwish <darwi@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250304085152.51092-6-darwi@linutronix.de
---
 arch/x86/kernel/cpu/intel.c | 36 +++++++++++++-----------------------
 1 file changed, 13 insertions(+), 23 deletions(-)

diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index c5d833f5bffbc..60b58b1a0c69f 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -1,40 +1,30 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/kernel.h>
-#include <linux/pgtable.h>
 
-#include <linux/string.h>
 #include <linux/bitops.h>
-#include <linux/smp.h>
-#include <linux/sched.h>
-#include <linux/sched/clock.h>
-#include <linux/thread_info.h>
 #include <linux/init.h>
-#include <linux/uaccess.h>
+#include <linux/kernel.h>
+#include <linux/smp.h>
+#include <linux/string.h>
+
+#ifdef CONFIG_X86_64
+#include <linux/topology.h>
+#endif
 
-#include <asm/cpufeature.h>
-#include <asm/msr.h>
 #include <asm/bugs.h>
+#include <asm/cpu_device_id.h>
+#include <asm/cpufeature.h>
 #include <asm/cpu.h>
+#include <asm/hwcap2.h>
 #include <asm/intel-family.h>
 #include <asm/microcode.h>
-#include <asm/hwcap2.h>
-#include <asm/elf.h>
-#include <asm/cpu_device_id.h>
-#include <asm/resctrl.h>
+#include <asm/msr.h>
 #include <asm/numa.h>
+#include <asm/resctrl.h>
 #include <asm/thermal.h>
-
-#ifdef CONFIG_X86_64
-#include <linux/topology.h>
-#endif
+#include <asm/uaccess.h>
 
 #include "cpu.h"
 
-#ifdef CONFIG_X86_LOCAL_APIC
-#include <asm/mpspec.h>
-#include <asm/apic.h>
-#endif
-
 /*
  * Processors which have self-snooping capability can handle conflicting
  * memory type across CPUs by snooping its own cache. However, there exists

From cb5f4c76b2a9314c35e00c67c98ccd03542c2634 Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <darwi@linutronix.de>
Date: Tue, 4 Mar 2025 09:51:17 +0100
Subject: [PATCH 0905/1173] x86/cpu: Use max() for CPUID leaf 0x2 TLB
 descriptors parsing

The conditional statement "if (x < y) { x = y; }" appears 22 times at
the Intel leaf 0x2 descriptors parsing logic.

Replace each of such instances with a max() expression to simplify
the code.

Signed-off-by: Ahmed S. Darwish <darwi@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250304085152.51092-7-darwi@linutronix.de
---
 arch/x86/kernel/cpu/intel.c | 76 ++++++++++++++-----------------------
 1 file changed, 28 insertions(+), 48 deletions(-)

diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 60b58b1a0c69f..42a57b85f93bd 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -3,6 +3,7 @@
 #include <linux/bitops.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/minmax.h>
 #include <linux/smp.h>
 #include <linux/string.h>
 
@@ -700,7 +701,9 @@ static const struct _tlb_table intel_tlb_table[] = {
 
 static void intel_tlb_lookup(const unsigned char desc)
 {
+	unsigned int entries;
 	unsigned char k;
+
 	if (desc == 0)
 		return;
 
@@ -712,81 +715,58 @@ static void intel_tlb_lookup(const unsigned char desc)
 	if (intel_tlb_table[k].tlb_type == 0)
 		return;
 
+	entries = intel_tlb_table[k].entries;
 	switch (intel_tlb_table[k].tlb_type) {
 	case STLB_4K:
-		if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lli_4k[ENTRIES] = max(tlb_lli_4k[ENTRIES], entries);
+		tlb_lld_4k[ENTRIES] = max(tlb_lld_4k[ENTRIES], entries);
 		break;
 	case STLB_4K_2M:
-		if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lli_2m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_2m[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lld_2m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_2m[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lli_4k[ENTRIES] = max(tlb_lli_4k[ENTRIES], entries);
+		tlb_lld_4k[ENTRIES] = max(tlb_lld_4k[ENTRIES], entries);
+		tlb_lli_2m[ENTRIES] = max(tlb_lli_2m[ENTRIES], entries);
+		tlb_lld_2m[ENTRIES] = max(tlb_lld_2m[ENTRIES], entries);
+		tlb_lli_4m[ENTRIES] = max(tlb_lli_4m[ENTRIES], entries);
+		tlb_lld_4m[ENTRIES] = max(tlb_lld_4m[ENTRIES], entries);
 		break;
 	case TLB_INST_ALL:
-		if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lli_2m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_2m[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lli_4k[ENTRIES] = max(tlb_lli_4k[ENTRIES], entries);
+		tlb_lli_2m[ENTRIES] = max(tlb_lli_2m[ENTRIES], entries);
+		tlb_lli_4m[ENTRIES] = max(tlb_lli_4m[ENTRIES], entries);
 		break;
 	case TLB_INST_4K:
-		if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lli_4k[ENTRIES] = max(tlb_lli_4k[ENTRIES], entries);
 		break;
 	case TLB_INST_4M:
-		if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lli_4m[ENTRIES] = max(tlb_lli_4m[ENTRIES], entries);
 		break;
 	case TLB_INST_2M_4M:
-		if (tlb_lli_2m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_2m[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lli_2m[ENTRIES] = max(tlb_lli_2m[ENTRIES], entries);
+		tlb_lli_4m[ENTRIES] = max(tlb_lli_4m[ENTRIES], entries);
 		break;
 	case TLB_DATA_4K:
 	case TLB_DATA0_4K:
-		if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lld_4k[ENTRIES] = max(tlb_lld_4k[ENTRIES], entries);
 		break;
 	case TLB_DATA_4M:
 	case TLB_DATA0_4M:
-		if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lld_4m[ENTRIES] = max(tlb_lld_4m[ENTRIES], entries);
 		break;
 	case TLB_DATA_2M_4M:
 	case TLB_DATA0_2M_4M:
-		if (tlb_lld_2m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_2m[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lld_2m[ENTRIES] = max(tlb_lld_2m[ENTRIES], entries);
+		tlb_lld_4m[ENTRIES] = max(tlb_lld_4m[ENTRIES], entries);
 		break;
 	case TLB_DATA_4K_4M:
-		if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lld_4k[ENTRIES] = max(tlb_lld_4k[ENTRIES], entries);
+		tlb_lld_4m[ENTRIES] = max(tlb_lld_4m[ENTRIES], entries);
 		break;
 	case TLB_DATA_1G_2M_4M:
-		if (tlb_lld_2m[ENTRIES] < TLB_0x63_2M_4M_ENTRIES)
-			tlb_lld_2m[ENTRIES] = TLB_0x63_2M_4M_ENTRIES;
-		if (tlb_lld_4m[ENTRIES] < TLB_0x63_2M_4M_ENTRIES)
-			tlb_lld_4m[ENTRIES] = TLB_0x63_2M_4M_ENTRIES;
+		tlb_lld_2m[ENTRIES] = max(tlb_lld_2m[ENTRIES], TLB_0x63_2M_4M_ENTRIES);
+		tlb_lld_4m[ENTRIES] = max(tlb_lld_4m[ENTRIES], TLB_0x63_2M_4M_ENTRIES);
 		fallthrough;
 	case TLB_DATA_1G:
-		if (tlb_lld_1g[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_1g[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lld_1g[ENTRIES] = max(tlb_lld_1g[ENTRIES], entries);
 		break;
 	}
 }

From 8b7e54b542103753619a37cbb3216849a934872f Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <darwi@linutronix.de>
Date: Tue, 4 Mar 2025 09:51:18 +0100
Subject: [PATCH 0906/1173] x86/cpu: Simplify TLB entry count storage

Commit:

  e0ba94f14f74 ("x86/tlb_info: get last level TLB entry number of CPU")

introduced u16 "info" arrays for each TLB type.

Since 2012 and each array stores just one type of information: the
number of TLB entries for its respective TLB type.

Replace such arrays with simple variables.

Signed-off-by: Ahmed S. Darwish <darwi@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250304085152.51092-8-darwi@linutronix.de
---
 arch/x86/include/asm/processor.h | 19 +++++--------
 arch/x86/kernel/cpu/amd.c        | 18 ++++++------
 arch/x86/kernel/cpu/common.c     | 20 ++++++-------
 arch/x86/kernel/cpu/hygon.c      | 16 +++++------
 arch/x86/kernel/cpu/intel.c      | 48 ++++++++++++++++----------------
 5 files changed, 57 insertions(+), 64 deletions(-)

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index c0cd10182e90c..0ea227fa027c5 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -60,18 +60,13 @@ struct vm86;
 # define ARCH_MIN_MMSTRUCT_ALIGN	0
 #endif
 
-enum tlb_infos {
-	ENTRIES,
-	NR_INFO
-};
-
-extern u16 __read_mostly tlb_lli_4k[NR_INFO];
-extern u16 __read_mostly tlb_lli_2m[NR_INFO];
-extern u16 __read_mostly tlb_lli_4m[NR_INFO];
-extern u16 __read_mostly tlb_lld_4k[NR_INFO];
-extern u16 __read_mostly tlb_lld_2m[NR_INFO];
-extern u16 __read_mostly tlb_lld_4m[NR_INFO];
-extern u16 __read_mostly tlb_lld_1g[NR_INFO];
+extern u16 __read_mostly tlb_lli_4k;
+extern u16 __read_mostly tlb_lli_2m;
+extern u16 __read_mostly tlb_lli_4m;
+extern u16 __read_mostly tlb_lld_4k;
+extern u16 __read_mostly tlb_lld_2m;
+extern u16 __read_mostly tlb_lld_4m;
+extern u16 __read_mostly tlb_lld_1g;
 
 /*
  * CPU type and hardware bug flags. Kept separately for each CPU.
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index d747515ad0130..3157664402011 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -1105,8 +1105,8 @@ static void cpu_detect_tlb_amd(struct cpuinfo_x86 *c)
 
 	cpuid(0x80000006, &eax, &ebx, &ecx, &edx);
 
-	tlb_lld_4k[ENTRIES] = (ebx >> 16) & mask;
-	tlb_lli_4k[ENTRIES] = ebx & mask;
+	tlb_lld_4k = (ebx >> 16) & mask;
+	tlb_lli_4k = ebx & mask;
 
 	/*
 	 * K8 doesn't have 2M/4M entries in the L2 TLB so read out the L1 TLB
@@ -1119,26 +1119,26 @@ static void cpu_detect_tlb_amd(struct cpuinfo_x86 *c)
 
 	/* Handle DTLB 2M and 4M sizes, fall back to L1 if L2 is disabled */
 	if (!((eax >> 16) & mask))
-		tlb_lld_2m[ENTRIES] = (cpuid_eax(0x80000005) >> 16) & 0xff;
+		tlb_lld_2m = (cpuid_eax(0x80000005) >> 16) & 0xff;
 	else
-		tlb_lld_2m[ENTRIES] = (eax >> 16) & mask;
+		tlb_lld_2m = (eax >> 16) & mask;
 
 	/* a 4M entry uses two 2M entries */
-	tlb_lld_4m[ENTRIES] = tlb_lld_2m[ENTRIES] >> 1;
+	tlb_lld_4m = tlb_lld_2m >> 1;
 
 	/* Handle ITLB 2M and 4M sizes, fall back to L1 if L2 is disabled */
 	if (!(eax & mask)) {
 		/* Erratum 658 */
 		if (c->x86 == 0x15 && c->x86_model <= 0x1f) {
-			tlb_lli_2m[ENTRIES] = 1024;
+			tlb_lli_2m = 1024;
 		} else {
 			cpuid(0x80000005, &eax, &ebx, &ecx, &edx);
-			tlb_lli_2m[ENTRIES] = eax & 0xff;
+			tlb_lli_2m = eax & 0xff;
 		}
 	} else
-		tlb_lli_2m[ENTRIES] = eax & mask;
+		tlb_lli_2m = eax & mask;
 
-	tlb_lli_4m[ENTRIES] = tlb_lli_2m[ENTRIES] >> 1;
+	tlb_lli_4m = tlb_lli_2m >> 1;
 }
 
 static const struct cpu_dev amd_cpu_dev = {
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 8eba9ca9c2161..3a1a957e0c60e 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -846,13 +846,13 @@ void cpu_detect_cache_sizes(struct cpuinfo_x86 *c)
 	c->x86_cache_size = l2size;
 }
 
-u16 __read_mostly tlb_lli_4k[NR_INFO];
-u16 __read_mostly tlb_lli_2m[NR_INFO];
-u16 __read_mostly tlb_lli_4m[NR_INFO];
-u16 __read_mostly tlb_lld_4k[NR_INFO];
-u16 __read_mostly tlb_lld_2m[NR_INFO];
-u16 __read_mostly tlb_lld_4m[NR_INFO];
-u16 __read_mostly tlb_lld_1g[NR_INFO];
+u16 __read_mostly tlb_lli_4k;
+u16 __read_mostly tlb_lli_2m;
+u16 __read_mostly tlb_lli_4m;
+u16 __read_mostly tlb_lld_4k;
+u16 __read_mostly tlb_lld_2m;
+u16 __read_mostly tlb_lld_4m;
+u16 __read_mostly tlb_lld_1g;
 
 static void cpu_detect_tlb(struct cpuinfo_x86 *c)
 {
@@ -860,12 +860,10 @@ static void cpu_detect_tlb(struct cpuinfo_x86 *c)
 		this_cpu->c_detect_tlb(c);
 
 	pr_info("Last level iTLB entries: 4KB %d, 2MB %d, 4MB %d\n",
-		tlb_lli_4k[ENTRIES], tlb_lli_2m[ENTRIES],
-		tlb_lli_4m[ENTRIES]);
+		tlb_lli_4k, tlb_lli_2m, tlb_lli_4m);
 
 	pr_info("Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d, 1GB %d\n",
-		tlb_lld_4k[ENTRIES], tlb_lld_2m[ENTRIES],
-		tlb_lld_4m[ENTRIES], tlb_lld_1g[ENTRIES]);
+		tlb_lld_4k, tlb_lld_2m, tlb_lld_4m, tlb_lld_1g);
 }
 
 void get_cpu_vendor(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c
index c5191b06f9f21..6af4a4a90a521 100644
--- a/arch/x86/kernel/cpu/hygon.c
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -240,26 +240,26 @@ static void cpu_detect_tlb_hygon(struct cpuinfo_x86 *c)
 
 	cpuid(0x80000006, &eax, &ebx, &ecx, &edx);
 
-	tlb_lld_4k[ENTRIES] = (ebx >> 16) & mask;
-	tlb_lli_4k[ENTRIES] = ebx & mask;
+	tlb_lld_4k = (ebx >> 16) & mask;
+	tlb_lli_4k = ebx & mask;
 
 	/* Handle DTLB 2M and 4M sizes, fall back to L1 if L2 is disabled */
 	if (!((eax >> 16) & mask))
-		tlb_lld_2m[ENTRIES] = (cpuid_eax(0x80000005) >> 16) & 0xff;
+		tlb_lld_2m = (cpuid_eax(0x80000005) >> 16) & 0xff;
 	else
-		tlb_lld_2m[ENTRIES] = (eax >> 16) & mask;
+		tlb_lld_2m = (eax >> 16) & mask;
 
 	/* a 4M entry uses two 2M entries */
-	tlb_lld_4m[ENTRIES] = tlb_lld_2m[ENTRIES] >> 1;
+	tlb_lld_4m = tlb_lld_2m >> 1;
 
 	/* Handle ITLB 2M and 4M sizes, fall back to L1 if L2 is disabled */
 	if (!(eax & mask)) {
 		cpuid(0x80000005, &eax, &ebx, &ecx, &edx);
-		tlb_lli_2m[ENTRIES] = eax & 0xff;
+		tlb_lli_2m = eax & 0xff;
 	} else
-		tlb_lli_2m[ENTRIES] = eax & mask;
+		tlb_lli_2m = eax & mask;
 
-	tlb_lli_4m[ENTRIES] = tlb_lli_2m[ENTRIES] >> 1;
+	tlb_lli_4m = tlb_lli_2m >> 1;
 }
 
 static const struct cpu_dev hygon_cpu_dev = {
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 42a57b85f93bd..61d3fd31baeeb 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -718,55 +718,55 @@ static void intel_tlb_lookup(const unsigned char desc)
 	entries = intel_tlb_table[k].entries;
 	switch (intel_tlb_table[k].tlb_type) {
 	case STLB_4K:
-		tlb_lli_4k[ENTRIES] = max(tlb_lli_4k[ENTRIES], entries);
-		tlb_lld_4k[ENTRIES] = max(tlb_lld_4k[ENTRIES], entries);
+		tlb_lli_4k = max(tlb_lli_4k, entries);
+		tlb_lld_4k = max(tlb_lld_4k, entries);
 		break;
 	case STLB_4K_2M:
-		tlb_lli_4k[ENTRIES] = max(tlb_lli_4k[ENTRIES], entries);
-		tlb_lld_4k[ENTRIES] = max(tlb_lld_4k[ENTRIES], entries);
-		tlb_lli_2m[ENTRIES] = max(tlb_lli_2m[ENTRIES], entries);
-		tlb_lld_2m[ENTRIES] = max(tlb_lld_2m[ENTRIES], entries);
-		tlb_lli_4m[ENTRIES] = max(tlb_lli_4m[ENTRIES], entries);
-		tlb_lld_4m[ENTRIES] = max(tlb_lld_4m[ENTRIES], entries);
+		tlb_lli_4k = max(tlb_lli_4k, entries);
+		tlb_lld_4k = max(tlb_lld_4k, entries);
+		tlb_lli_2m = max(tlb_lli_2m, entries);
+		tlb_lld_2m = max(tlb_lld_2m, entries);
+		tlb_lli_4m = max(tlb_lli_4m, entries);
+		tlb_lld_4m = max(tlb_lld_4m, entries);
 		break;
 	case TLB_INST_ALL:
-		tlb_lli_4k[ENTRIES] = max(tlb_lli_4k[ENTRIES], entries);
-		tlb_lli_2m[ENTRIES] = max(tlb_lli_2m[ENTRIES], entries);
-		tlb_lli_4m[ENTRIES] = max(tlb_lli_4m[ENTRIES], entries);
+		tlb_lli_4k = max(tlb_lli_4k, entries);
+		tlb_lli_2m = max(tlb_lli_2m, entries);
+		tlb_lli_4m = max(tlb_lli_4m, entries);
 		break;
 	case TLB_INST_4K:
-		tlb_lli_4k[ENTRIES] = max(tlb_lli_4k[ENTRIES], entries);
+		tlb_lli_4k = max(tlb_lli_4k, entries);
 		break;
 	case TLB_INST_4M:
-		tlb_lli_4m[ENTRIES] = max(tlb_lli_4m[ENTRIES], entries);
+		tlb_lli_4m = max(tlb_lli_4m, entries);
 		break;
 	case TLB_INST_2M_4M:
-		tlb_lli_2m[ENTRIES] = max(tlb_lli_2m[ENTRIES], entries);
-		tlb_lli_4m[ENTRIES] = max(tlb_lli_4m[ENTRIES], entries);
+		tlb_lli_2m = max(tlb_lli_2m, entries);
+		tlb_lli_4m = max(tlb_lli_4m, entries);
 		break;
 	case TLB_DATA_4K:
 	case TLB_DATA0_4K:
-		tlb_lld_4k[ENTRIES] = max(tlb_lld_4k[ENTRIES], entries);
+		tlb_lld_4k = max(tlb_lld_4k, entries);
 		break;
 	case TLB_DATA_4M:
 	case TLB_DATA0_4M:
-		tlb_lld_4m[ENTRIES] = max(tlb_lld_4m[ENTRIES], entries);
+		tlb_lld_4m = max(tlb_lld_4m, entries);
 		break;
 	case TLB_DATA_2M_4M:
 	case TLB_DATA0_2M_4M:
-		tlb_lld_2m[ENTRIES] = max(tlb_lld_2m[ENTRIES], entries);
-		tlb_lld_4m[ENTRIES] = max(tlb_lld_4m[ENTRIES], entries);
+		tlb_lld_2m = max(tlb_lld_2m, entries);
+		tlb_lld_4m = max(tlb_lld_4m, entries);
 		break;
 	case TLB_DATA_4K_4M:
-		tlb_lld_4k[ENTRIES] = max(tlb_lld_4k[ENTRIES], entries);
-		tlb_lld_4m[ENTRIES] = max(tlb_lld_4m[ENTRIES], entries);
+		tlb_lld_4k = max(tlb_lld_4k, entries);
+		tlb_lld_4m = max(tlb_lld_4m, entries);
 		break;
 	case TLB_DATA_1G_2M_4M:
-		tlb_lld_2m[ENTRIES] = max(tlb_lld_2m[ENTRIES], TLB_0x63_2M_4M_ENTRIES);
-		tlb_lld_4m[ENTRIES] = max(tlb_lld_4m[ENTRIES], TLB_0x63_2M_4M_ENTRIES);
+		tlb_lld_2m = max(tlb_lld_2m, TLB_0x63_2M_4M_ENTRIES);
+		tlb_lld_4m = max(tlb_lld_4m, TLB_0x63_2M_4M_ENTRIES);
 		fallthrough;
 	case TLB_DATA_1G:
-		tlb_lld_1g[ENTRIES] = max(tlb_lld_1g[ENTRIES], entries);
+		tlb_lld_1g = max(tlb_lld_1g, entries);
 		break;
 	}
 }

From 535d9a82702ee75b0da6e4547f367beeeef184a3 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 4 Mar 2025 09:51:19 +0100
Subject: [PATCH 0907/1173] x86/cpu: Get rid of the smp_store_cpu_info()
 indirection

smp_store_cpu_info() is just a wrapper around identify_secondary_cpu()
without further value.

Move the extra bits from smp_store_cpu_info() into identify_secondary_cpu()
and remove the wrapper.

[ darwi: Make it compile and fix up the xen/smp_pv.c instance ]

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ahmed S. Darwish <darwi@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250304085152.51092-9-darwi@linutronix.de
---
 arch/x86/include/asm/processor.h |  2 +-
 arch/x86/include/asm/smp.h       |  2 --
 arch/x86/kernel/cpu/common.c     | 11 +++++++++--
 arch/x86/kernel/smpboot.c        | 24 ++----------------------
 arch/x86/xen/smp_pv.c            |  2 +-
 5 files changed, 13 insertions(+), 28 deletions(-)

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 0ea227fa027c5..d5d9a071cddc9 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -229,7 +229,7 @@ static inline unsigned long long l1tf_pfn_limit(void)
 void init_cpu_devs(void);
 void get_cpu_vendor(struct cpuinfo_x86 *c);
 extern void early_cpu_init(void);
-extern void identify_secondary_cpu(struct cpuinfo_x86 *);
+extern void identify_secondary_cpu(unsigned int cpu);
 extern void print_cpu_info(struct cpuinfo_x86 *);
 void print_cpu_msr(struct cpuinfo_x86 *);
 
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 1d3b11eba084d..128e06a18e51b 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -120,8 +120,6 @@ void native_smp_send_reschedule(int cpu);
 void native_send_call_func_ipi(const struct cpumask *mask);
 void native_send_call_func_single_ipi(int cpu);
 
-void smp_store_cpu_info(int id);
-
 asmlinkage __visible void smp_reboot_interrupt(void);
 __visible void smp_reschedule_interrupt(struct pt_regs *regs);
 __visible void smp_call_function_interrupt(struct pt_regs *regs);
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 3a1a957e0c60e..5f81c553e733d 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1997,9 +1997,15 @@ static __init void identify_boot_cpu(void)
 	lkgs_init();
 }
 
-void identify_secondary_cpu(struct cpuinfo_x86 *c)
+void identify_secondary_cpu(unsigned int cpu)
 {
-	BUG_ON(c == &boot_cpu_data);
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+
+	/* Copy boot_cpu_data only on the first bringup */
+	if (!c->initialized)
+		*c = boot_cpu_data;
+	c->cpu_index = cpu;
+
 	identify_cpu(c);
 #ifdef CONFIG_X86_32
 	enable_sep_cpu();
@@ -2010,6 +2016,7 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c)
 		update_gds_msr();
 
 	tsx_ap_init();
+	c->initialized = true;
 }
 
 void print_cpu_info(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 5746084bafe44..8ecf1bf571038 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -190,7 +190,7 @@ static void ap_starting(void)
 	apic_ap_setup();
 
 	/* Save the processor parameters. */
-	smp_store_cpu_info(cpuid);
+	identify_secondary_cpu(cpuid);
 
 	/*
 	 * The topology information must be up to date before
@@ -215,7 +215,7 @@ static void ap_calibrate_delay(void)
 {
 	/*
 	 * Calibrate the delay loop and update loops_per_jiffy in cpu_data.
-	 * smp_store_cpu_info() stored a value that is close but not as
+	 * identify_secondary_cpu() stored a value that is close but not as
 	 * accurate as the value just calculated.
 	 *
 	 * As this is invoked after the TSC synchronization check,
@@ -315,26 +315,6 @@ static void notrace start_secondary(void *unused)
 	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
 
-/*
- * The bootstrap kernel entry code has set these up. Save them for
- * a given CPU
- */
-void smp_store_cpu_info(int id)
-{
-	struct cpuinfo_x86 *c = &cpu_data(id);
-
-	/* Copy boot_cpu_data only on the first bringup */
-	if (!c->initialized)
-		*c = boot_cpu_data;
-	c->cpu_index = id;
-	/*
-	 * During boot time, CPU0 has this setup already. Save the info when
-	 * bringing up an AP.
-	 */
-	identify_secondary_cpu(c);
-	c->initialized = true;
-}
-
 static bool
 topology_same_node(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 {
diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index 6863d3da7decf..688ff59318ae2 100644
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -70,7 +70,7 @@ static void cpu_bringup(void)
 		xen_enable_syscall();
 	}
 	cpu = smp_processor_id();
-	smp_store_cpu_info(cpu);
+	identify_secondary_cpu(cpu);
 	set_cpu_sibling_map(cpu);
 
 	speculative_store_bypass_ht_init();

From 1f61dfdf16cd3bab383741c2eb43e7f69e9f592f Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 4 Mar 2025 09:51:20 +0100
Subject: [PATCH 0908/1173] x86/cpu: Remove unused TLB strings

Commit:

  e0ba94f14f74 ("x86/tlb_info: get last level TLB entry number of CPU")

added the TLB table for parsing CPUID(0x4), including strings
describing them. The string entry in the table was never used.

Convert them to comments.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ahmed S. Darwish <darwi@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250304085152.51092-10-darwi@linutronix.de
---
 arch/x86/kernel/cpu/cpu.h   |  8 ----
 arch/x86/kernel/cpu/intel.c | 80 ++++++++++++++++++++-----------------
 2 files changed, 43 insertions(+), 45 deletions(-)

diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 1beccefbaff9a..51deb60a9d267 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -33,14 +33,6 @@ struct cpu_dev {
 #endif
 };
 
-struct _tlb_table {
-	unsigned char descriptor;
-	char tlb_type;
-	unsigned int entries;
-	/* unsigned int ways; */
-	char info[128];
-};
-
 #define cpu_dev_register(cpu_devX) \
 	static const struct cpu_dev *const __cpu_dev_##cpu_devX __used \
 	__section(".x86_cpu_dev.init") = \
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 61d3fd31baeeb..291c82816797e 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -658,44 +658,50 @@ static unsigned int intel_size_cache(struct cpuinfo_x86 *c, unsigned int size)
  */
 #define TLB_0x63_2M_4M_ENTRIES	32
 
+struct _tlb_table {
+	unsigned char descriptor;
+	char tlb_type;
+	unsigned int entries;
+};
+
 static const struct _tlb_table intel_tlb_table[] = {
-	{ 0x01, TLB_INST_4K,		32,	" TLB_INST 4 KByte pages, 4-way set associative" },
-	{ 0x02, TLB_INST_4M,		2,	" TLB_INST 4 MByte pages, full associative" },
-	{ 0x03, TLB_DATA_4K,		64,	" TLB_DATA 4 KByte pages, 4-way set associative" },
-	{ 0x04, TLB_DATA_4M,		8,	" TLB_DATA 4 MByte pages, 4-way set associative" },
-	{ 0x05, TLB_DATA_4M,		32,	" TLB_DATA 4 MByte pages, 4-way set associative" },
-	{ 0x0b, TLB_INST_4M,		4,	" TLB_INST 4 MByte pages, 4-way set associative" },
-	{ 0x4f, TLB_INST_4K,		32,	" TLB_INST 4 KByte pages" },
-	{ 0x50, TLB_INST_ALL,		64,	" TLB_INST 4 KByte and 2-MByte or 4-MByte pages" },
-	{ 0x51, TLB_INST_ALL,		128,	" TLB_INST 4 KByte and 2-MByte or 4-MByte pages" },
-	{ 0x52, TLB_INST_ALL,		256,	" TLB_INST 4 KByte and 2-MByte or 4-MByte pages" },
-	{ 0x55, TLB_INST_2M_4M,		7,	" TLB_INST 2-MByte or 4-MByte pages, fully associative" },
-	{ 0x56, TLB_DATA0_4M,		16,	" TLB_DATA0 4 MByte pages, 4-way set associative" },
-	{ 0x57, TLB_DATA0_4K,		16,	" TLB_DATA0 4 KByte pages, 4-way associative" },
-	{ 0x59, TLB_DATA0_4K,		16,	" TLB_DATA0 4 KByte pages, fully associative" },
-	{ 0x5a, TLB_DATA0_2M_4M,	32,	" TLB_DATA0 2-MByte or 4 MByte pages, 4-way set associative" },
-	{ 0x5b, TLB_DATA_4K_4M,		64,	" TLB_DATA 4 KByte and 4 MByte pages" },
-	{ 0x5c, TLB_DATA_4K_4M,		128,	" TLB_DATA 4 KByte and 4 MByte pages" },
-	{ 0x5d, TLB_DATA_4K_4M,		256,	" TLB_DATA 4 KByte and 4 MByte pages" },
-	{ 0x61, TLB_INST_4K,		48,	" TLB_INST 4 KByte pages, full associative" },
-	{ 0x63, TLB_DATA_1G_2M_4M,	4,	" TLB_DATA 1 GByte pages, 4-way set associative"
-						" (plus 32 entries TLB_DATA 2 MByte or 4 MByte pages, not encoded here)" },
-	{ 0x6b, TLB_DATA_4K,		256,	" TLB_DATA 4 KByte pages, 8-way associative" },
-	{ 0x6c, TLB_DATA_2M_4M,		128,	" TLB_DATA 2 MByte or 4 MByte pages, 8-way associative" },
-	{ 0x6d, TLB_DATA_1G,		16,	" TLB_DATA 1 GByte pages, fully associative" },
-	{ 0x76, TLB_INST_2M_4M,		8,	" TLB_INST 2-MByte or 4-MByte pages, fully associative" },
-	{ 0xb0, TLB_INST_4K,		128,	" TLB_INST 4 KByte pages, 4-way set associative" },
-	{ 0xb1, TLB_INST_2M_4M,		4,	" TLB_INST 2M pages, 4-way, 8 entries or 4M pages, 4-way entries" },
-	{ 0xb2, TLB_INST_4K,		64,	" TLB_INST 4KByte pages, 4-way set associative" },
-	{ 0xb3, TLB_DATA_4K,		128,	" TLB_DATA 4 KByte pages, 4-way set associative" },
-	{ 0xb4, TLB_DATA_4K,		256,	" TLB_DATA 4 KByte pages, 4-way associative" },
-	{ 0xb5, TLB_INST_4K,		64,	" TLB_INST 4 KByte pages, 8-way set associative" },
-	{ 0xb6, TLB_INST_4K,		128,	" TLB_INST 4 KByte pages, 8-way set associative" },
-	{ 0xba, TLB_DATA_4K,		64,	" TLB_DATA 4 KByte pages, 4-way associative" },
-	{ 0xc0, TLB_DATA_4K_4M,		8,	" TLB_DATA 4 KByte and 4 MByte pages, 4-way associative" },
-	{ 0xc1, STLB_4K_2M,		1024,	" STLB 4 KByte and 2 MByte pages, 8-way associative" },
-	{ 0xc2, TLB_DATA_2M_4M,		16,	" TLB_DATA 2 MByte/4MByte pages, 4-way associative" },
-	{ 0xca, STLB_4K,		512,	" STLB 4 KByte pages, 4-way associative" },
+	{ 0x01, TLB_INST_4K,		32},	/* TLB_INST 4 KByte pages, 4-way set associative */
+	{ 0x02, TLB_INST_4M,		2},	/* TLB_INST 4 MByte pages, full associative */
+	{ 0x03, TLB_DATA_4K,		64},	/* TLB_DATA 4 KByte pages, 4-way set associative */
+	{ 0x04, TLB_DATA_4M,		8},	/* TLB_DATA 4 MByte pages, 4-way set associative */
+	{ 0x05, TLB_DATA_4M,		32},	/* TLB_DATA 4 MByte pages, 4-way set associative */
+	{ 0x0b, TLB_INST_4M,		4},	/* TLB_INST 4 MByte pages, 4-way set associative */
+	{ 0x4f, TLB_INST_4K,		32},	/* TLB_INST 4 KByte pages */
+	{ 0x50, TLB_INST_ALL,		64},	/* TLB_INST 4 KByte and 2-MByte or 4-MByte pages */
+	{ 0x51, TLB_INST_ALL,		128},	/* TLB_INST 4 KByte and 2-MByte or 4-MByte pages */
+	{ 0x52, TLB_INST_ALL,		256},	/* TLB_INST 4 KByte and 2-MByte or 4-MByte pages */
+	{ 0x55, TLB_INST_2M_4M,		7},	/* TLB_INST 2-MByte or 4-MByte pages, fully associative */
+	{ 0x56, TLB_DATA0_4M,		16},	/* TLB_DATA0 4 MByte pages, 4-way set associative */
+	{ 0x57, TLB_DATA0_4K,		16},	/* TLB_DATA0 4 KByte pages, 4-way associative */
+	{ 0x59, TLB_DATA0_4K,		16},	/* TLB_DATA0 4 KByte pages, fully associative */
+	{ 0x5a, TLB_DATA0_2M_4M,	32},	/* TLB_DATA0 2-MByte or 4 MByte pages, 4-way set associative */
+	{ 0x5b, TLB_DATA_4K_4M,		64},	/* TLB_DATA 4 KByte and 4 MByte pages */
+	{ 0x5c, TLB_DATA_4K_4M,		128},	/* TLB_DATA 4 KByte and 4 MByte pages */
+	{ 0x5d, TLB_DATA_4K_4M,		256},	/* TLB_DATA 4 KByte and 4 MByte pages */
+	{ 0x61, TLB_INST_4K,		48},	/* TLB_INST 4 KByte pages, full associative */
+	{ 0x63, TLB_DATA_1G_2M_4M,	4},	/* TLB_DATA 1 GByte pages, 4-way set associative
+						 * (plus 32 entries TLB_DATA 2 MByte or 4 MByte pages, not encoded here) */
+	{ 0x6b, TLB_DATA_4K,		256},	/* TLB_DATA 4 KByte pages, 8-way associative */
+	{ 0x6c, TLB_DATA_2M_4M,		128},	/* TLB_DATA 2 MByte or 4 MByte pages, 8-way associative */
+	{ 0x6d, TLB_DATA_1G,		16},	/* TLB_DATA 1 GByte pages, fully associative */
+	{ 0x76, TLB_INST_2M_4M,		8},	/* TLB_INST 2-MByte or 4-MByte pages, fully associative */
+	{ 0xb0, TLB_INST_4K,		128},	/* TLB_INST 4 KByte pages, 4-way set associative */
+	{ 0xb1, TLB_INST_2M_4M,		4},	/* TLB_INST 2M pages, 4-way, 8 entries or 4M pages, 4-way entries */
+	{ 0xb2, TLB_INST_4K,		64},	/* TLB_INST 4KByte pages, 4-way set associative */
+	{ 0xb3, TLB_DATA_4K,		128},	/* TLB_DATA 4 KByte pages, 4-way set associative */
+	{ 0xb4, TLB_DATA_4K,		256},	/* TLB_DATA 4 KByte pages, 4-way associative */
+	{ 0xb5, TLB_INST_4K,		64},	/* TLB_INST 4 KByte pages, 8-way set associative */
+	{ 0xb6, TLB_INST_4K,		128},	/* TLB_INST 4 KByte pages, 8-way set associative */
+	{ 0xba, TLB_DATA_4K,		64},	/* TLB_DATA 4 KByte pages, 4-way associative */
+	{ 0xc0, TLB_DATA_4K_4M,		8},	/* TLB_DATA 4 KByte and 4 MByte pages, 4-way associative */
+	{ 0xc1, STLB_4K_2M,		1024},	/* STLB 4 KByte and 2 MByte pages, 8-way associative */
+	{ 0xc2, TLB_DATA_2M_4M,		16},	/* TLB_DATA 2 MByte/4MByte pages, 4-way associative */
+	{ 0xca, STLB_4K,		512},	/* STLB 4 KByte pages, 4-way associative */
 	{ 0x00, 0, 0 }
 };
 

From b3a756bd72ec8d1ba43334b17115e0ece1144a88 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 4 Mar 2025 09:51:22 +0100
Subject: [PATCH 0909/1173] x86/cacheinfo: Remove the P4 trace leftovers for
 real

Commit 851026a2bf54 ("x86/cacheinfo: Remove unused trace variable") removed
the switch case for LVL_TRACE but did not get rid of the surrounding gunk.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ahmed S. Darwish <darwi@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250304085152.51092-12-darwi@linutronix.de
---
 arch/x86/kernel/cpu/cacheinfo.c | 19 +++----------------
 1 file changed, 3 insertions(+), 16 deletions(-)

diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index a6c6bccfa8b8d..eccffe2ea06cf 100644
--- a/arch/x86/kernel/cpu/cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -31,7 +31,6 @@
 #define LVL_1_DATA	2
 #define LVL_2		3
 #define LVL_3		4
-#define LVL_TRACE	5
 
 /* Shared last level cache maps */
 DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
@@ -96,10 +95,6 @@ static const struct _cache_table cache_table[] =
 	{ 0x66, LVL_1_DATA, 8 },	/* 4-way set assoc, sectored cache, 64 byte line size */
 	{ 0x67, LVL_1_DATA, 16 },	/* 4-way set assoc, sectored cache, 64 byte line size */
 	{ 0x68, LVL_1_DATA, 32 },	/* 4-way set assoc, sectored cache, 64 byte line size */
-	{ 0x70, LVL_TRACE,  12 },	/* 8-way set assoc */
-	{ 0x71, LVL_TRACE,  16 },	/* 8-way set assoc */
-	{ 0x72, LVL_TRACE,  32 },	/* 8-way set assoc */
-	{ 0x73, LVL_TRACE,  64 },	/* 8-way set assoc */
 	{ 0x78, LVL_2,      MB(1) },	/* 4-way set assoc, 64 byte line size */
 	{ 0x79, LVL_2,      128 },	/* 8-way set assoc, sectored cache, 64 byte line size */
 	{ 0x7a, LVL_2,      256 },	/* 8-way set assoc, sectored cache, 64 byte line size */
@@ -787,19 +782,13 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c)
 			}
 		}
 	}
-	/*
-	 * Don't use cpuid2 if cpuid4 is supported. For P4, we use cpuid2 for
-	 * trace cache
-	 */
-	if ((!ci->num_leaves || c->x86 == 15) && c->cpuid_level > 1) {
+
+	/* Don't use CPUID(2) if CPUID(4) is supported. */
+	if (!ci->num_leaves && c->cpuid_level > 1) {
 		/* supports eax=2  call */
 		int j, n;
 		unsigned int regs[4];
 		unsigned char *dp = (unsigned char *)regs;
-		int only_trace = 0;
-
-		if (ci->num_leaves && c->x86 == 15)
-			only_trace = 1;
 
 		/* Number of times to iterate */
 		n = cpuid_eax(2) & 0xFF;
@@ -820,8 +809,6 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c)
 				/* look up this descriptor in the table */
 				while (cache_table[k].descriptor != 0) {
 					if (cache_table[k].descriptor == des) {
-						if (only_trace && cache_table[k].cache_type != LVL_TRACE)
-							break;
 						switch (cache_table[k].cache_type) {
 						case LVL_1_INST:
 							l1i += cache_table[k].size;

From 6309ff98f00bad118812f7f250fbbee4867e88d3 Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <darwi@linutronix.de>
Date: Tue, 4 Mar 2025 09:51:23 +0100
Subject: [PATCH 0910/1173] x86/cacheinfo: Remove unnecessary headers and
 reorder the rest

Remove the headers at cacheinfo.c that are no longer required.

Alphabetically reorder what remains since more headers will be included
in further commits.

Signed-off-by: Ahmed S. Darwish <darwi@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250304085152.51092-13-darwi@linutronix.de
---
 arch/x86/kernel/cpu/cacheinfo.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index eccffe2ea06cf..b3a520959b510 100644
--- a/arch/x86/kernel/cpu/cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -8,21 +8,19 @@
  *	Andi Kleen / Andreas Herrmann	: CPUID4 emulation on AMD.
  */
 
-#include <linux/slab.h>
 #include <linux/cacheinfo.h>
+#include <linux/capability.h>
 #include <linux/cpu.h>
 #include <linux/cpuhotplug.h>
-#include <linux/sched.h>
-#include <linux/capability.h>
-#include <linux/sysfs.h>
 #include <linux/pci.h>
 #include <linux/stop_machine.h>
+#include <linux/sysfs.h>
 
-#include <asm/cpufeature.h>
-#include <asm/cacheinfo.h>
 #include <asm/amd_nb.h>
-#include <asm/smp.h>
+#include <asm/cacheinfo.h>
+#include <asm/cpufeature.h>
 #include <asm/mtrr.h>
+#include <asm/smp.h>
 #include <asm/tlbflush.h>
 
 #include "cpu.h"

From 4f2a0b765c9731d2fa94e209ee9ae0e96b280f17 Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <darwi@linutronix.de>
Date: Tue, 4 Mar 2025 09:51:41 +0100
Subject: [PATCH 0911/1173] <linux/sizes.h>: Cover all possible x86 CPU cache
 sizes

Add size macros for 24/192/384 Kilobytes and 3/6/12/18/24 Megabytes.

With that, the x86 subsystem can avoid locally defining its own macros
for CPU cache sizes.

Signed-off-by: Ahmed S. Darwish <darwi@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Link: https://lore.kernel.org/r/20250304085152.51092-31-darwi@linutronix.de
---
 include/linux/sizes.h | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/include/linux/sizes.h b/include/linux/sizes.h
index c3a00b967d18a..49039494076fa 100644
--- a/include/linux/sizes.h
+++ b/include/linux/sizes.h
@@ -23,17 +23,25 @@
 #define SZ_4K				0x00001000
 #define SZ_8K				0x00002000
 #define SZ_16K				0x00004000
+#define SZ_24K				0x00006000
 #define SZ_32K				0x00008000
 #define SZ_64K				0x00010000
 #define SZ_128K				0x00020000
+#define SZ_192K				0x00030000
 #define SZ_256K				0x00040000
+#define SZ_384K				0x00060000
 #define SZ_512K				0x00080000
 
 #define SZ_1M				0x00100000
 #define SZ_2M				0x00200000
+#define SZ_3M				0x00300000
 #define SZ_4M				0x00400000
+#define SZ_6M				0x00600000
 #define SZ_8M				0x00800000
+#define SZ_12M				0x00c00000
 #define SZ_16M				0x01000000
+#define SZ_18M				0x01200000
+#define SZ_24M				0x01800000
 #define SZ_32M				0x02000000
 #define SZ_64M				0x04000000
 #define SZ_128M				0x08000000

From e1c49eaee52384ec9e3734138b3929a35b64e0c3 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@kernel.org>
Date: Sun, 2 Mar 2025 17:20:59 -0800
Subject: [PATCH 0912/1173] KVM: VMX: Use named operands in inline asm

Convert the non-asm-goto version of the inline asm in __vmcs_readl() to
use named operands, similar to its asm-goto version.

Do this in preparation of changing the ASM_CALL_CONSTRAINT primitive.

Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Sean Christopherson <seanjc@google.com>
Cc: linux-kernel@vger.kernel.org
---
 arch/x86/kvm/vmx/vmx_ops.h | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h
index 633c87e2fd92e..96677576c836d 100644
--- a/arch/x86/kvm/vmx/vmx_ops.h
+++ b/arch/x86/kvm/vmx/vmx_ops.h
@@ -118,7 +118,7 @@ static __always_inline unsigned long __vmcs_readl(unsigned long field)
 
 #else /* !CONFIG_CC_HAS_ASM_GOTO_OUTPUT */
 
-	asm volatile("1: vmread %2, %1\n\t"
+	asm volatile("1: vmread %[field], %[output]\n\t"
 		     ".byte 0x3e\n\t" /* branch taken hint */
 		     "ja 3f\n\t"
 
@@ -127,24 +127,26 @@ static __always_inline unsigned long __vmcs_readl(unsigned long field)
 		      * @field, and bounce through the trampoline to preserve
 		      * volatile registers.
 		      */
-		     "xorl %k1, %k1\n\t"
+		     "xorl %k[output], %k[output]\n\t"
 		     "2:\n\t"
-		     "push %1\n\t"
-		     "push %2\n\t"
+		     "push %[output]\n\t"
+		     "push %[field]\n\t"
 		     "call vmread_error_trampoline\n\t"
 
 		     /*
 		      * Unwind the stack.  Note, the trampoline zeros out the
 		      * memory for @fault so that the result is '0' on error.
 		      */
-		     "pop %2\n\t"
-		     "pop %1\n\t"
+		     "pop %[field]\n\t"
+		     "pop %[output]\n\t"
 		     "3:\n\t"
 
 		     /* VMREAD faulted.  As above, except push '1' for @fault. */
-		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_ONE_REG, %1)
+		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_ONE_REG, %[output])
 
-		     : ASM_CALL_CONSTRAINT, "=&r"(value) : "r"(field) : "cc");
+		     : ASM_CALL_CONSTRAINT, [output] "=&r" (value)
+		     : [field] "r" (field)
+		     : "cc");
 	return value;
 
 #endif /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */

From 9064a8e556fa70ccfd9c414350406ed4887d3059 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@kernel.org>
Date: Sun, 2 Mar 2025 17:21:00 -0800
Subject: [PATCH 0913/1173] x86/hyperv: Use named operands in inline asm

Use named operands in inline asm to make it easier to change the
constraint order.

Do this in preparation of changing the ASM_CALL_CONSTRAINT primitive.

Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Wei Liu <wei.liu@kernel.org>
Cc: Dexuan Cui <decui@microsoft.com>
Cc: linux-kernel@vger.kernel.org
---
 arch/x86/include/asm/mshyperv.h | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index f91ab1e75f9ff..5e6193dbc97e3 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -77,11 +77,11 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
 		return hv_tdx_hypercall(control, input_address, output_address);
 
 	if (hv_isolation_type_snp() && !hyperv_paravisor_present) {
-		__asm__ __volatile__("mov %4, %%r8\n"
+		__asm__ __volatile__("mov %[output_address], %%r8\n"
 				     "vmmcall"
 				     : "=a" (hv_status), ASM_CALL_CONSTRAINT,
 				       "+c" (control), "+d" (input_address)
-				     :  "r" (output_address)
+				     : [output_address] "r" (output_address)
 				     : "cc", "memory", "r8", "r9", "r10", "r11");
 		return hv_status;
 	}
@@ -89,12 +89,12 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
 	if (!hv_hypercall_pg)
 		return U64_MAX;
 
-	__asm__ __volatile__("mov %4, %%r8\n"
+	__asm__ __volatile__("mov %[output_address], %%r8\n"
 			     CALL_NOSPEC
 			     : "=a" (hv_status), ASM_CALL_CONSTRAINT,
 			       "+c" (control), "+d" (input_address)
-			     :  "r" (output_address),
-				THUNK_TARGET(hv_hypercall_pg)
+			     : [output_address] "r" (output_address),
+			       THUNK_TARGET(hv_hypercall_pg)
 			     : "cc", "memory", "r8", "r9", "r10", "r11");
 #else
 	u32 input_address_hi = upper_32_bits(input_address);
@@ -187,18 +187,18 @@ static inline u64 _hv_do_fast_hypercall16(u64 control, u64 input1, u64 input2)
 		return hv_tdx_hypercall(control, input1, input2);
 
 	if (hv_isolation_type_snp() && !hyperv_paravisor_present) {
-		__asm__ __volatile__("mov %4, %%r8\n"
+		__asm__ __volatile__("mov %[input2], %%r8\n"
 				     "vmmcall"
 				     : "=a" (hv_status), ASM_CALL_CONSTRAINT,
 				       "+c" (control), "+d" (input1)
-				     : "r" (input2)
+				     : [input2] "r" (input2)
 				     : "cc", "r8", "r9", "r10", "r11");
 	} else {
-		__asm__ __volatile__("mov %4, %%r8\n"
+		__asm__ __volatile__("mov %[input2], %%r8\n"
 				     CALL_NOSPEC
 				     : "=a" (hv_status), ASM_CALL_CONSTRAINT,
 				       "+c" (control), "+d" (input1)
-				     : "r" (input2),
+				     : [input2] "r" (input2),
 				       THUNK_TARGET(hv_hypercall_pg)
 				     : "cc", "r8", "r9", "r10", "r11");
 	}

From 224788b63a2e426b6b82c76456a068a2ab87610f Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@kernel.org>
Date: Sun, 2 Mar 2025 17:21:01 -0800
Subject: [PATCH 0914/1173] x86/alternatives: Simplify alternative_call()
 interface

Separate the input from the clobbers in preparation for appending the
input.

Do this in preparation of changing the ASM_CALL_CONSTRAINT primitive.

Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: linux-kernel@vger.kernel.org
---
 arch/x86/include/asm/alternative.h | 24 +++-----
 arch/x86/include/asm/apic.h        |  4 +-
 arch/x86/include/asm/asm.h         | 11 ++++
 arch/x86/include/asm/atomic64_32.h | 96 ++++++++++++++++++------------
 arch/x86/include/asm/page_64.h     |  4 +-
 5 files changed, 82 insertions(+), 57 deletions(-)

diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index a2141665239b5..52626a7251e62 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -237,10 +237,12 @@ static inline int alternatives_text_reserved(void *start, void *end)
  * references: i.e., if used for a function, it would add the PLT
  * suffix.
  */
-#define alternative_call(oldfunc, newfunc, ft_flags, output, input...)			\
+#define alternative_call(oldfunc, newfunc, ft_flags, output, input, clobbers...)	\
 	asm_inline volatile(ALTERNATIVE("call %c[old]", "call %c[new]", ft_flags)	\
 		: ALT_OUTPUT_SP(output)							\
-		: [old] "i" (oldfunc), [new] "i" (newfunc), ## input)
+		: [old] "i" (oldfunc), [new] "i" (newfunc)				\
+		  COMMA(input)								\
+		: clobbers)
 
 /*
  * Like alternative_call, but there are two features and respective functions.
@@ -249,24 +251,14 @@ static inline int alternatives_text_reserved(void *start, void *end)
  * Otherwise, old function is used.
  */
 #define alternative_call_2(oldfunc, newfunc1, ft_flags1, newfunc2, ft_flags2,		\
-			   output, input...)						\
+			   output, input, clobbers...)					\
 	asm_inline volatile(ALTERNATIVE_2("call %c[old]", "call %c[new1]", ft_flags1,	\
 		"call %c[new2]", ft_flags2)						\
 		: ALT_OUTPUT_SP(output)							\
 		: [old] "i" (oldfunc), [new1] "i" (newfunc1),				\
-		  [new2] "i" (newfunc2), ## input)
-
-/*
- * use this macro(s) if you need more than one output parameter
- * in alternative_io
- */
-#define ASM_OUTPUT2(a...) a
-
-/*
- * use this macro if you need clobbers but no inputs in
- * alternative_{input,io,call}()
- */
-#define ASM_NO_INPUT_CLOBBER(clbr...) "i" (0) : clbr
+		  [new2] "i" (newfunc2)							\
+		  COMMA(input)								\
+		: clobbers)
 
 #define ALT_OUTPUT_SP(...) ASM_CALL_CONSTRAINT, ## __VA_ARGS__
 
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index f21ff19326994..c903d358405d3 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -99,8 +99,8 @@ static inline void native_apic_mem_write(u32 reg, u32 v)
 	volatile u32 *addr = (volatile u32 *)(APIC_BASE + reg);
 
 	alternative_io("movl %0, %1", "xchgl %0, %1", X86_BUG_11AP,
-		       ASM_OUTPUT2("=r" (v), "=m" (*addr)),
-		       ASM_OUTPUT2("0" (v), "m" (*addr)));
+		       ASM_OUTPUT("=r" (v), "=m" (*addr)),
+		       ASM_INPUT("0" (v), "m" (*addr)));
 }
 
 static inline u32 native_apic_mem_read(u32 reg)
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 2bec0c89a95c2..975ae7a9397eb 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -213,6 +213,17 @@ static __always_inline __pure void *rip_rel_ptr(void *p)
 
 /* For C file, we already have NOKPROBE_SYMBOL macro */
 
+/* Insert a comma if args are non-empty */
+#define COMMA(x...)		__COMMA(x)
+#define __COMMA(...)		, ##__VA_ARGS__
+
+/*
+ * Combine multiple asm inline constraint args into a single arg for passing to
+ * another macro.
+ */
+#define ASM_OUTPUT(x...)	x
+#define ASM_INPUT(x...)		x
+
 /*
  * This output constraint should be used for any inline asm which has a "call"
  * instruction.  Otherwise the asm may be inserted before the frame pointer
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index 797085ecaaa45..ab838205c1c66 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -49,16 +49,19 @@ static __always_inline s64 arch_atomic64_read_nonatomic(const atomic64_t *v)
 #endif
 
 #ifdef CONFIG_X86_CX8
-#define __alternative_atomic64(f, g, out, in...) \
-	asm volatile("call %c[func]" \
+#define __alternative_atomic64(f, g, out, in, clobbers...)		\
+	asm volatile("call %c[func]"					\
 		     : ALT_OUTPUT_SP(out) \
-		     : [func] "i" (atomic64_##g##_cx8), ## in)
+		     : [func] "i" (atomic64_##g##_cx8)			\
+		       COMMA(in)					\
+		     : clobbers)
 
 #define ATOMIC64_DECL(sym) ATOMIC64_DECL_ONE(sym##_cx8)
 #else
-#define __alternative_atomic64(f, g, out, in...) \
-	alternative_call(atomic64_##f##_386, atomic64_##g##_cx8, \
-			 X86_FEATURE_CX8, ASM_OUTPUT2(out), ## in)
+#define __alternative_atomic64(f, g, out, in, clobbers...)		\
+	alternative_call(atomic64_##f##_386, atomic64_##g##_cx8,	\
+			 X86_FEATURE_CX8, ASM_OUTPUT(out),		\
+			 ASM_INPUT(in), clobbers)
 
 #define ATOMIC64_DECL(sym) ATOMIC64_DECL_ONE(sym##_cx8); \
 	ATOMIC64_DECL_ONE(sym##_386)
@@ -69,8 +72,8 @@ ATOMIC64_DECL_ONE(inc_386);
 ATOMIC64_DECL_ONE(dec_386);
 #endif
 
-#define alternative_atomic64(f, out, in...) \
-	__alternative_atomic64(f, f, ASM_OUTPUT2(out), ## in)
+#define alternative_atomic64(f, out, in, clobbers...) \
+	__alternative_atomic64(f, f, ASM_OUTPUT(out), ASM_INPUT(in), clobbers)
 
 ATOMIC64_DECL(read);
 ATOMIC64_DECL(set);
@@ -105,9 +108,10 @@ static __always_inline s64 arch_atomic64_xchg(atomic64_t *v, s64 n)
 	s64 o;
 	unsigned high = (unsigned)(n >> 32);
 	unsigned low = (unsigned)n;
-	alternative_atomic64(xchg, "=&A" (o),
-			     "S" (v), "b" (low), "c" (high)
-			     : "memory");
+	alternative_atomic64(xchg,
+			     "=&A" (o),
+			     ASM_INPUT("S" (v), "b" (low), "c" (high)),
+			     "memory");
 	return o;
 }
 #define arch_atomic64_xchg arch_atomic64_xchg
@@ -116,23 +120,25 @@ static __always_inline void arch_atomic64_set(atomic64_t *v, s64 i)
 {
 	unsigned high = (unsigned)(i >> 32);
 	unsigned low = (unsigned)i;
-	alternative_atomic64(set, /* no output */,
-			     "S" (v), "b" (low), "c" (high)
-			     : "eax", "edx", "memory");
+	alternative_atomic64(set,
+			     /* no output */,
+			     ASM_INPUT("S" (v), "b" (low), "c" (high)),
+			     "eax", "edx", "memory");
 }
 
 static __always_inline s64 arch_atomic64_read(const atomic64_t *v)
 {
 	s64 r;
-	alternative_atomic64(read, "=&A" (r), "c" (v) : "memory");
+	alternative_atomic64(read, "=&A" (r), "c" (v), "memory");
 	return r;
 }
 
 static __always_inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v)
 {
 	alternative_atomic64(add_return,
-			     ASM_OUTPUT2("+A" (i), "+c" (v)),
-			     ASM_NO_INPUT_CLOBBER("memory"));
+			     ASM_OUTPUT("+A" (i), "+c" (v)),
+			     /* no input */,
+			     "memory");
 	return i;
 }
 #define arch_atomic64_add_return arch_atomic64_add_return
@@ -140,8 +146,9 @@ static __always_inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v)
 static __always_inline s64 arch_atomic64_sub_return(s64 i, atomic64_t *v)
 {
 	alternative_atomic64(sub_return,
-			     ASM_OUTPUT2("+A" (i), "+c" (v)),
-			     ASM_NO_INPUT_CLOBBER("memory"));
+			     ASM_OUTPUT("+A" (i), "+c" (v)),
+			     /* no input */,
+			     "memory");
 	return i;
 }
 #define arch_atomic64_sub_return arch_atomic64_sub_return
@@ -149,8 +156,10 @@ static __always_inline s64 arch_atomic64_sub_return(s64 i, atomic64_t *v)
 static __always_inline s64 arch_atomic64_inc_return(atomic64_t *v)
 {
 	s64 a;
-	alternative_atomic64(inc_return, "=&A" (a),
-			     "S" (v) : "memory", "ecx");
+	alternative_atomic64(inc_return,
+			     "=&A" (a),
+			     "S" (v),
+			     "memory", "ecx");
 	return a;
 }
 #define arch_atomic64_inc_return arch_atomic64_inc_return
@@ -158,8 +167,10 @@ static __always_inline s64 arch_atomic64_inc_return(atomic64_t *v)
 static __always_inline s64 arch_atomic64_dec_return(atomic64_t *v)
 {
 	s64 a;
-	alternative_atomic64(dec_return, "=&A" (a),
-			     "S" (v) : "memory", "ecx");
+	alternative_atomic64(dec_return,
+			     "=&A" (a),
+			     "S" (v),
+			     "memory", "ecx");
 	return a;
 }
 #define arch_atomic64_dec_return arch_atomic64_dec_return
@@ -167,28 +178,34 @@ static __always_inline s64 arch_atomic64_dec_return(atomic64_t *v)
 static __always_inline void arch_atomic64_add(s64 i, atomic64_t *v)
 {
 	__alternative_atomic64(add, add_return,
-			       ASM_OUTPUT2("+A" (i), "+c" (v)),
-			       ASM_NO_INPUT_CLOBBER("memory"));
+			       ASM_OUTPUT("+A" (i), "+c" (v)),
+			       /* no input */,
+			       "memory");
 }
 
 static __always_inline void arch_atomic64_sub(s64 i, atomic64_t *v)
 {
 	__alternative_atomic64(sub, sub_return,
-			       ASM_OUTPUT2("+A" (i), "+c" (v)),
-			       ASM_NO_INPUT_CLOBBER("memory"));
+			       ASM_OUTPUT("+A" (i), "+c" (v)),
+			       /* no input */,
+			       "memory");
 }
 
 static __always_inline void arch_atomic64_inc(atomic64_t *v)
 {
-	__alternative_atomic64(inc, inc_return, /* no output */,
-			       "S" (v) : "memory", "eax", "ecx", "edx");
+	__alternative_atomic64(inc, inc_return,
+			       /* no output */,
+			       "S" (v),
+			       "memory", "eax", "ecx", "edx");
 }
 #define arch_atomic64_inc arch_atomic64_inc
 
 static __always_inline void arch_atomic64_dec(atomic64_t *v)
 {
-	__alternative_atomic64(dec, dec_return, /* no output */,
-			       "S" (v) : "memory", "eax", "ecx", "edx");
+	__alternative_atomic64(dec, dec_return,
+			       /* no output */,
+			       "S" (v),
+			       "memory", "eax", "ecx", "edx");
 }
 #define arch_atomic64_dec arch_atomic64_dec
 
@@ -197,8 +214,9 @@ static __always_inline int arch_atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
 	unsigned low = (unsigned)u;
 	unsigned high = (unsigned)(u >> 32);
 	alternative_atomic64(add_unless,
-			     ASM_OUTPUT2("+A" (a), "+c" (low), "+D" (high)),
-			     "S" (v) : "memory");
+			     ASM_OUTPUT("+A" (a), "+c" (low), "+D" (high)),
+			     "S" (v),
+			     "memory");
 	return (int)a;
 }
 #define arch_atomic64_add_unless arch_atomic64_add_unless
@@ -206,8 +224,10 @@ static __always_inline int arch_atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
 static __always_inline int arch_atomic64_inc_not_zero(atomic64_t *v)
 {
 	int r;
-	alternative_atomic64(inc_not_zero, "=&a" (r),
-			     "S" (v) : "ecx", "edx", "memory");
+	alternative_atomic64(inc_not_zero,
+			     "=&a" (r),
+			     "S" (v),
+			     "ecx", "edx", "memory");
 	return r;
 }
 #define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero
@@ -215,8 +235,10 @@ static __always_inline int arch_atomic64_inc_not_zero(atomic64_t *v)
 static __always_inline s64 arch_atomic64_dec_if_positive(atomic64_t *v)
 {
 	s64 r;
-	alternative_atomic64(dec_if_positive, "=&A" (r),
-			     "S" (v) : "ecx", "memory");
+	alternative_atomic64(dec_if_positive,
+			     "=&A" (r),
+			     "S" (v),
+			     "ecx", "memory");
 	return r;
 }
 #define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive
diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h
index d63576608ce76..d081e8000f349 100644
--- a/arch/x86/include/asm/page_64.h
+++ b/arch/x86/include/asm/page_64.h
@@ -55,8 +55,8 @@ static inline void clear_page(void *page)
 			   clear_page_rep, X86_FEATURE_REP_GOOD,
 			   clear_page_erms, X86_FEATURE_ERMS,
 			   "=D" (page),
-			   "D" (page)
-			   : "cc", "memory", "rax", "rcx");
+			   "D" (page),
+			   "cc", "memory", "rax", "rcx");
 }
 
 void copy_page(void *to, void *from);

From fd521566cc0cd5e327683fea70cba93b1966ebac Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@surriel.com>
Date: Tue, 25 Feb 2025 22:00:36 -0500
Subject: [PATCH 0915/1173] x86/mm: Consolidate full flush threshold decision

Reduce code duplication by consolidating the decision point for whether to do
individual invalidations or a full flush inside get_flush_tlb_info().

Suggested-by: Dave Hansen <dave.hansen@intel.com>
Signed-off-by: Rik van Riel <riel@surriel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Borislav Petkov (AMD) <bp@alien8.de>
Acked-by: Dave Hansen <dave.hansen@intel.com>
Link: https://lore.kernel.org/r/20250226030129.530345-2-riel@surriel.com
---
 arch/x86/mm/tlb.c | 41 +++++++++++++++++++----------------------
 1 file changed, 19 insertions(+), 22 deletions(-)

diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index ffc25b3480415..dbcb5c968ff9e 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -1000,6 +1000,15 @@ static struct flush_tlb_info *get_flush_tlb_info(struct mm_struct *mm,
 	BUG_ON(this_cpu_inc_return(flush_tlb_info_idx) != 1);
 #endif
 
+	/*
+	 * If the number of flushes is so large that a full flush
+	 * would be faster, do a full flush.
+	 */
+	if ((end - start) >> stride_shift > tlb_single_page_flush_ceiling) {
+		start = 0;
+		end = TLB_FLUSH_ALL;
+	}
+
 	info->start		= start;
 	info->end		= end;
 	info->mm		= mm;
@@ -1026,17 +1035,8 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 				bool freed_tables)
 {
 	struct flush_tlb_info *info;
+	int cpu = get_cpu();
 	u64 new_tlb_gen;
-	int cpu;
-
-	cpu = get_cpu();
-
-	/* Should we flush just the requested range? */
-	if ((end == TLB_FLUSH_ALL) ||
-	    ((end - start) >> stride_shift) > tlb_single_page_flush_ceiling) {
-		start = 0;
-		end = TLB_FLUSH_ALL;
-	}
 
 	/* This is also a barrier that synchronizes with switch_mm(). */
 	new_tlb_gen = inc_mm_tlb_gen(mm);
@@ -1089,22 +1089,19 @@ static void do_kernel_range_flush(void *info)
 
 void flush_tlb_kernel_range(unsigned long start, unsigned long end)
 {
-	/* Balance as user space task's flush, a bit conservative */
-	if (end == TLB_FLUSH_ALL ||
-	    (end - start) > tlb_single_page_flush_ceiling << PAGE_SHIFT) {
-		on_each_cpu(do_flush_tlb_all, NULL, 1);
-	} else {
-		struct flush_tlb_info *info;
+	struct flush_tlb_info *info;
+
+	guard(preempt)();
 
-		preempt_disable();
-		info = get_flush_tlb_info(NULL, start, end, 0, false,
-					  TLB_GENERATION_INVALID);
+	info = get_flush_tlb_info(NULL, start, end, PAGE_SHIFT, false,
+				  TLB_GENERATION_INVALID);
 
+	if (info->end == TLB_FLUSH_ALL)
+		on_each_cpu(do_flush_tlb_all, NULL, 1);
+	else
 		on_each_cpu(do_kernel_range_flush, info, 1);
 
-		put_flush_tlb_info();
-		preempt_enable();
-	}
+	put_flush_tlb_info();
 }
 
 /*

From c34424eb3be4c01db831428c0d7d483701ae820f Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 27 Feb 2025 16:45:34 -0800
Subject: [PATCH 0916/1173] net: dsa: rtl8366rb: don't prompt users for LED
 control

Make NET_DSA_REALTEK_RTL8366RB_LEDS a hidden symbol.
It seems very unlikely user would want to intentionally
disable it.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20250228004534.3428681-1-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/dsa/realtek/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/realtek/Kconfig b/drivers/net/dsa/realtek/Kconfig
index 10687722d14c0..d6eb6713e5f6b 100644
--- a/drivers/net/dsa/realtek/Kconfig
+++ b/drivers/net/dsa/realtek/Kconfig
@@ -44,7 +44,7 @@ config NET_DSA_REALTEK_RTL8366RB
 	  Select to enable support for Realtek RTL8366RB.
 
 config NET_DSA_REALTEK_RTL8366RB_LEDS
-	bool "Support RTL8366RB LED control"
+	bool
 	depends on (LEDS_CLASS=y || LEDS_CLASS=NET_DSA_REALTEK_RTL8366RB)
 	depends on NET_DSA_REALTEK_RTL8366RB
 	default NET_DSA_REALTEK_RTL8366RB

From 1f860eb4cdda634589d75e78ff586d5dff20b8af Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 3 Mar 2025 11:05:36 +0100
Subject: [PATCH 0917/1173] wifi: nl80211: disable multi-link reconfiguration

Both the APIs in cfg80211 and the implementation in mac80211
aren't really ready yet, we have a large number of fixes. In
addition, it's not possible right now to discover support for
this feature from userspace. Disable it for now, there's no
rush.

Link: https://patch.msgid.link/20250303110538.fbeef42a5687.Iab122c22137e5675ebd99f5c031e30c0e5c7af2e@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/nl80211.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index fdb2aac951d18..e87267fbb442e 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -16534,7 +16534,7 @@ static int nl80211_assoc_ml_reconf(struct sk_buff *skb, struct genl_info *info)
 		goto out;
 	}
 
-	err = cfg80211_assoc_ml_reconf(rdev, dev, links, rem_links);
+	err = -EOPNOTSUPP;
 
 out:
 	for (link_id = 0; link_id < ARRAY_SIZE(links); link_id++)

From b7365eab39831487a84e63a9638209b68dc54008 Mon Sep 17 00:00:00 2001
From: Peiyang Wang <wangpeiyang1@huawei.com>
Date: Fri, 28 Feb 2025 18:52:58 +0800
Subject: [PATCH 0918/1173] net: hns3: make sure ptp clock is unregister and
 freed if hclge_ptp_get_cycle returns an error

During the initialization of ptp, hclge_ptp_get_cycle might return an error
and returned directly without unregister clock and free it. To avoid that,
call hclge_ptp_destroy_clock to unregist and free clock if
hclge_ptp_get_cycle failed.

Fixes: 8373cd38a888 ("net: hns3: change the method of obtaining default ptp cycle")
Signed-off-by: Peiyang Wang <wangpeiyang1@huawei.com>
Signed-off-by: Jijie Shao <shaojijie@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250228105258.1243461-1-shaojijie@huawei.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
index bab16c2191b2f..181af419b878d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
@@ -483,7 +483,7 @@ int hclge_ptp_init(struct hclge_dev *hdev)
 
 		ret = hclge_ptp_get_cycle(hdev);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
 	ret = hclge_ptp_int_en(hdev, true);

From c7c1f3b05c67173f462d73d301d572b3f9e57e3b Mon Sep 17 00:00:00 2001
From: Michal Pecio <michal.pecio@gmail.com>
Date: Tue, 4 Mar 2025 13:31:47 +0200
Subject: [PATCH 0919/1173] usb: xhci: Fix host controllers "dying" after
 suspend and resume

A recent cleanup went a bit too far and dropped clearing the cycle bit
of link TRBs, so it stays different from the rest of the ring half of
the time. Then a race occurs: if the xHC reaches such link TRB before
more commands are queued, the link's cycle bit unintentionally matches
the xHC's cycle so it follows the link and waits for further commands.
If more commands are queued before the xHC gets there, inc_enq() flips
the bit so the xHC later sees a mismatch and stops executing commands.

This function is called before suspend and 50% of times after resuming
the xHC is doomed to get stuck sooner or later. Then some Stop Endpoint
command fails to complete in 5 seconds and this shows up

xhci_hcd 0000:00:10.0: xHCI host not responding to stop endpoint command
xhci_hcd 0000:00:10.0: xHCI host controller not responding, assume dead
xhci_hcd 0000:00:10.0: HC died; cleaning up

followed by loss of all USB decives on the affected bus. That's if you
are lucky, because if Set Deq gets stuck instead, the failure is silent.

Likely responsible for kernel bug 219824. I found this while searching
for possible causes of that regression and reproduced it locally before
hearing back from the reporter. To repro, simply wait for link cycle to
become set (debugfs), then suspend, resume and wait. To accelerate the
failure I used a script which repeatedly starts and stops a UVC camera.

Some HCs get fully reinitialized on resume and they are not affected.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=219824
Fixes: 36b972d4b7ce ("usb: xhci: improve xhci_clear_command_ring()")
Cc: stable@vger.kernel.org
Signed-off-by: Michal Pecio <michal.pecio@gmail.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20250304113147.3322584-2-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 45653114ccd7f..1a90ebc8a30ea 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -780,8 +780,12 @@ static void xhci_clear_command_ring(struct xhci_hcd *xhci)
 	struct xhci_segment *seg;
 
 	ring = xhci->cmd_ring;
-	xhci_for_each_ring_seg(ring->first_seg, seg)
+	xhci_for_each_ring_seg(ring->first_seg, seg) {
+		/* erase all TRBs before the link */
 		memset(seg->trbs, 0, sizeof(union xhci_trb) * (TRBS_PER_SEGMENT - 1));
+		/* clear link cycle bit */
+		seg->trbs[TRBS_PER_SEGMENT - 1].link.control &= cpu_to_le32(~TRB_CYCLE);
+	}
 
 	xhci_initialize_ring_info(ring);
 	/*

From 71cbbb7149e3de8c39dfe8a97eaa7f1cbcbff52f Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Tue, 4 Mar 2025 14:18:14 +0100
Subject: [PATCH 0920/1173] irqchip/davinci-cp-intc: Remove public header

There are no more users of irq-davinci-cp-intc.h (da830.c doesn't use
any of its symbols). Remove the header and make the driver stop using the
config structure.

[ tglx: Mop up coding style ]

Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250304131815.86549-1-brgl@bgdev.pl
---
 arch/arm/mach-davinci/da830.c               |  1 -
 drivers/irqchip/irq-davinci-cp-intc.c       | 57 ++++++++-------------
 include/linux/irqchip/irq-davinci-cp-intc.h | 25 ---------
 3 files changed, 21 insertions(+), 62 deletions(-)
 delete mode 100644 include/linux/irqchip/irq-davinci-cp-intc.h

diff --git a/arch/arm/mach-davinci/da830.c b/arch/arm/mach-davinci/da830.c
index 2e497745b6246..a044ea5cb4f18 100644
--- a/arch/arm/mach-davinci/da830.c
+++ b/arch/arm/mach-davinci/da830.c
@@ -11,7 +11,6 @@
 #include <linux/gpio.h>
 #include <linux/init.h>
 #include <linux/io.h>
-#include <linux/irqchip/irq-davinci-cp-intc.h>
 
 #include <clocksource/timer-davinci.h>
 
diff --git a/drivers/irqchip/irq-davinci-cp-intc.c b/drivers/irqchip/irq-davinci-cp-intc.c
index f4f8e9fadbbfb..d7948c55f5422 100644
--- a/drivers/irqchip/irq-davinci-cp-intc.c
+++ b/drivers/irqchip/irq-davinci-cp-intc.c
@@ -11,7 +11,6 @@
 #include <linux/init.h>
 #include <linux/irq.h>
 #include <linux/irqchip.h>
-#include <linux/irqchip/irq-davinci-cp-intc.h>
 #include <linux/irqdomain.h>
 #include <linux/io.h>
 #include <linux/of.h>
@@ -154,24 +153,20 @@ static const struct irq_domain_ops davinci_cp_intc_irq_domain_ops = {
 	.xlate = irq_domain_xlate_onetwocell,
 };
 
-static int __init
-davinci_cp_intc_do_init(const struct davinci_cp_intc_config *config,
-			struct device_node *node)
+static int __init davinci_cp_intc_do_init(struct resource *res, unsigned int num_irqs,
+					  struct device_node *node)
 {
-	unsigned int num_regs = BITS_TO_LONGS(config->num_irqs);
+	unsigned int num_regs = BITS_TO_LONGS(num_irqs);
 	int offset, irq_base;
 	void __iomem *req;
 
-	req = request_mem_region(config->reg.start,
-				 resource_size(&config->reg),
-				 "davinci-cp-intc");
+	req = request_mem_region(res->start, resource_size(res), "davinci-cp-intc");
 	if (!req) {
 		pr_err("%s: register range busy\n", __func__);
 		return -EBUSY;
 	}
 
-	davinci_cp_intc_base = ioremap(config->reg.start,
-				       resource_size(&config->reg));
+	davinci_cp_intc_base = ioremap(res->start, resource_size(res));
 	if (!davinci_cp_intc_base) {
 		pr_err("%s: unable to ioremap register range\n", __func__);
 		return -EINVAL;
@@ -184,8 +179,7 @@ davinci_cp_intc_do_init(const struct davinci_cp_intc_config *config,
 
 	/* Disable system interrupts */
 	for (offset = 0; offset < num_regs; offset++)
-		davinci_cp_intc_write(~0,
-			DAVINCI_CP_INTC_SYS_ENABLE_CLR(offset));
+		davinci_cp_intc_write(~0, DAVINCI_CP_INTC_SYS_ENABLE_CLR(offset));
 
 	/* Set to normal mode, no nesting, no priority hold */
 	davinci_cp_intc_write(0, DAVINCI_CP_INTC_CTRL);
@@ -193,28 +187,25 @@ davinci_cp_intc_do_init(const struct davinci_cp_intc_config *config,
 
 	/* Clear system interrupt status */
 	for (offset = 0; offset < num_regs; offset++)
-		davinci_cp_intc_write(~0,
-			DAVINCI_CP_INTC_SYS_STAT_CLR(offset));
+		davinci_cp_intc_write(~0, DAVINCI_CP_INTC_SYS_STAT_CLR(offset));
 
 	/* Enable nIRQ (what about nFIQ?) */
 	davinci_cp_intc_write(1, DAVINCI_CP_INTC_HOST_ENABLE_IDX_SET);
 
+	/* 4 channels per register */
+	num_regs = (num_irqs + 3) >> 2;
 	/* Default all priorities to channel 7. */
-	num_regs = (config->num_irqs + 3) >> 2;	/* 4 channels per register */
 	for (offset = 0; offset < num_regs; offset++)
-		davinci_cp_intc_write(0x07070707,
-			DAVINCI_CP_INTC_CHAN_MAP(offset));
+		davinci_cp_intc_write(0x07070707, DAVINCI_CP_INTC_CHAN_MAP(offset));
 
-	irq_base = irq_alloc_descs(-1, 0, config->num_irqs, 0);
+	irq_base = irq_alloc_descs(-1, 0, num_irqs, 0);
 	if (irq_base < 0) {
-		pr_err("%s: unable to allocate interrupt descriptors: %d\n",
-		       __func__, irq_base);
+		pr_err("%s: unable to allocate interrupt descriptors: %d\n", __func__, irq_base);
 		return irq_base;
 	}
 
-	davinci_cp_intc_irq_domain = irq_domain_add_legacy(
-					node, config->num_irqs, irq_base, 0,
-					&davinci_cp_intc_irq_domain_ops, NULL);
+	davinci_cp_intc_irq_domain = irq_domain_add_legacy(node, num_irqs, irq_base, 0,
+							   &davinci_cp_intc_irq_domain_ops, NULL);
 
 	if (!davinci_cp_intc_irq_domain) {
 		pr_err("%s: unable to create an interrupt domain\n", __func__);
@@ -229,31 +220,25 @@ davinci_cp_intc_do_init(const struct davinci_cp_intc_config *config,
 	return 0;
 }
 
-int __init davinci_cp_intc_init(const struct davinci_cp_intc_config *config)
-{
-	return davinci_cp_intc_do_init(config, NULL);
-}
-
 static int __init davinci_cp_intc_of_init(struct device_node *node,
 					  struct device_node *parent)
 {
-	struct davinci_cp_intc_config config = { };
+	unsigned int num_irqs;
+	struct resource res;
 	int ret;
 
-	ret = of_address_to_resource(node, 0, &config.reg);
+	ret = of_address_to_resource(node, 0, &res);
 	if (ret) {
-		pr_err("%s: unable to get the register range from device-tree\n",
-		       __func__);
+		pr_err("%s: unable to get the register range from device-tree\n", __func__);
 		return ret;
 	}
 
-	ret = of_property_read_u32(node, "ti,intc-size", &config.num_irqs);
+	ret = of_property_read_u32(node, "ti,intc-size", &num_irqs);
 	if (ret) {
-		pr_err("%s: unable to read the 'ti,intc-size' property\n",
-		       __func__);
+		pr_err("%s: unable to read the 'ti,intc-size' property\n", __func__);
 		return ret;
 	}
 
-	return davinci_cp_intc_do_init(&config, node);
+	return davinci_cp_intc_do_init(&res, num_irqs, node);
 }
 IRQCHIP_DECLARE(cp_intc, "ti,cp-intc", davinci_cp_intc_of_init);
diff --git a/include/linux/irqchip/irq-davinci-cp-intc.h b/include/linux/irqchip/irq-davinci-cp-intc.h
deleted file mode 100644
index 8d71ed5b5a61f..0000000000000
--- a/include/linux/irqchip/irq-davinci-cp-intc.h
+++ /dev/null
@@ -1,25 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Copyright (C) 2019 Texas Instruments
- */
-
-#ifndef _LINUX_IRQ_DAVINCI_CP_INTC_
-#define _LINUX_IRQ_DAVINCI_CP_INTC_
-
-#include <linux/ioport.h>
-
-/**
- * struct davinci_cp_intc_config - configuration data for davinci-cp-intc
- *                                 driver.
- *
- * @reg: register range to map
- * @num_irqs: number of HW interrupts supported by the controller
- */
-struct davinci_cp_intc_config {
-	struct resource reg;
-	unsigned int num_irqs;
-};
-
-int davinci_cp_intc_init(const struct davinci_cp_intc_config *config);
-
-#endif /* _LINUX_IRQ_DAVINCI_CP_INTC_ */

From d0bbe332669c5db32c8c92bc967f8e7f8d460ddf Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 4 Mar 2025 15:25:55 +0100
Subject: [PATCH 0921/1173] ALSA: hda: realtek: fix incorrect IS_REACHABLE()
 usage

The alternative path leads to a build error after a recent change:

sound/pci/hda/patch_realtek.c: In function 'alc233_fixup_lenovo_low_en_micmute_led':
include/linux/stddef.h:9:14: error: called object is not a function or function pointer
    9 | #define NULL ((void *)0)
      |              ^
sound/pci/hda/patch_realtek.c:5041:49: note: in expansion of macro 'NULL'
 5041 | #define alc233_fixup_lenovo_line2_mic_hotkey    NULL
      |                                                 ^~~~
sound/pci/hda/patch_realtek.c:5063:9: note: in expansion of macro 'alc233_fixup_lenovo_line2_mic_hotkey'
 5063 |         alc233_fixup_lenovo_line2_mic_hotkey(codec, fix, action);

Using IS_REACHABLE() is somewhat questionable here anyway since it
leads to the input code not working when the HDA driver is builtin
but input is in a loadable module. Replace this with a hard compile-time
dependency on CONFIG_INPUT. In practice this won't chance much
other than solve the compiler error because it is rare to require
sound output but no input support.

Fixes: f603b159231b ("ALSA: hda/realtek - add supported Mic Mute LED for Lenovo platform")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://patch.msgid.link/20250304142620.582191-1-arnd@kernel.org
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/Kconfig         | 1 +
 sound/pci/hda/patch_realtek.c | 5 -----
 2 files changed, 1 insertion(+), 5 deletions(-)

diff --git a/sound/pci/hda/Kconfig b/sound/pci/hda/Kconfig
index e393578cbe684..84ebf19f28836 100644
--- a/sound/pci/hda/Kconfig
+++ b/sound/pci/hda/Kconfig
@@ -222,6 +222,7 @@ comment "Set to Y if you want auto-loading the side codec driver"
 
 config SND_HDA_CODEC_REALTEK
 	tristate "Build Realtek HD-audio codec support"
+	depends on INPUT
 	select SND_HDA_GENERIC
 	select SND_HDA_GENERIC_LEDS
 	select SND_HDA_SCODEC_COMPONENT
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index ebf54ef5877a4..697a38e41e166 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -4927,7 +4927,6 @@ static void alc298_fixup_samsung_amp_v2_4_amps(struct hda_codec *codec,
 		alc298_samsung_v2_init_amps(codec, 4);
 }
 
-#if IS_REACHABLE(CONFIG_INPUT)
 static void gpio2_mic_hotkey_event(struct hda_codec *codec,
 				   struct hda_jack_callback *event)
 {
@@ -5036,10 +5035,6 @@ static void alc233_fixup_lenovo_line2_mic_hotkey(struct hda_codec *codec,
 		spec->kb_dev = NULL;
 	}
 }
-#else /* INPUT */
-#define alc280_fixup_hp_gpio2_mic_hotkey	NULL
-#define alc233_fixup_lenovo_line2_mic_hotkey	NULL
-#endif /* INPUT */
 
 static void alc269_fixup_hp_line1_mic1_led(struct hda_codec *codec,
 				const struct hda_fixup *fix, int action)

From 5623bc23a1cb9f9a9470fa73b3a20321dc4c4870 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Tue, 25 Feb 2025 10:53:10 +0100
Subject: [PATCH 0922/1173] s390/traps: Fix test_monitor_call() inline assembly

The test_monitor_call() inline assembly uses the xgr instruction, which
also modifies the condition code, to clear a register. However the clobber
list of the inline assembly does not specify that the condition code is
modified, which may lead to incorrect code generation.

Use the lhi instruction instead to clear the register without that the
condition code is modified. Furthermore this limits clearing to the lower
32 bits of val, since its type is int.

Fixes: 17248ea03674 ("s390: fix __EMIT_BUG() macro")
Cc: stable@vger.kernel.org
Reviewed-by: Juergen Christ <jchrist@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/kernel/traps.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index 24fee11b030d8..b746213d3110c 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -285,10 +285,10 @@ static void __init test_monitor_call(void)
 		return;
 	asm volatile(
 		"	mc	0,0\n"
-		"0:	xgr	%0,%0\n"
+		"0:	lhi	%[val],0\n"
 		"1:\n"
-		EX_TABLE(0b,1b)
-		: "+d" (val));
+		EX_TABLE(0b, 1b)
+		: [val] "+d" (val));
 	if (!val)
 		panic("Monitor call doesn't work!\n");
 }

From a22ee38d2efe18edc53791fd1036396c23b43ad0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Mon, 17 Feb 2025 14:04:18 +0100
Subject: [PATCH 0923/1173] selftests/vDSO: Fix GNU hash table entry size for
 s390x
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 14be4e6f3522 ("selftests: vDSO: fix ELF hash table entry size for s390x")
changed the type of the ELF hash table entries to 64bit on s390x.
However the *GNU* hash tables entries are always 32bit.
The "bucket" pointer is shared between both hash algorithms.
On s390, this caused the GNU hash algorithm to access its 32-bit entries as if they
were 64-bit, triggering compiler warnings (assignment between "Elf64_Xword *" and
"Elf64_Word *") and runtime crashes.

Introduce a new dedicated "gnu_bucket" pointer which is used by the GNU hash.

Fixes: e0746bde6f82 ("selftests/vDSO: support DT_GNU_HASH")
Reviewed-by: Jens Remus <jremus@linux.ibm.com>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Acked-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/r/20250217-selftests-vdso-s390-gnu-hash-v2-1-f6c2532ffe2a@linutronix.de
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 tools/testing/selftests/vDSO/parse_vdso.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/vDSO/parse_vdso.c b/tools/testing/selftests/vDSO/parse_vdso.c
index 2fe5e983cb22f..f89d052c730eb 100644
--- a/tools/testing/selftests/vDSO/parse_vdso.c
+++ b/tools/testing/selftests/vDSO/parse_vdso.c
@@ -53,7 +53,7 @@ static struct vdso_info
 	/* Symbol table */
 	ELF(Sym) *symtab;
 	const char *symstrings;
-	ELF(Word) *gnu_hash;
+	ELF(Word) *gnu_hash, *gnu_bucket;
 	ELF_HASH_ENTRY *bucket, *chain;
 	ELF_HASH_ENTRY nbucket, nchain;
 
@@ -185,8 +185,8 @@ void vdso_init_from_sysinfo_ehdr(uintptr_t base)
 		/* The bucket array is located after the header (4 uint32) and the bloom
 		 * filter (size_t array of gnu_hash[2] elements).
 		 */
-		vdso_info.bucket = vdso_info.gnu_hash + 4 +
-				   sizeof(size_t) / 4 * vdso_info.gnu_hash[2];
+		vdso_info.gnu_bucket = vdso_info.gnu_hash + 4 +
+				       sizeof(size_t) / 4 * vdso_info.gnu_hash[2];
 	} else {
 		vdso_info.nbucket = hash[0];
 		vdso_info.nchain = hash[1];
@@ -268,11 +268,11 @@ void *vdso_sym(const char *version, const char *name)
 	if (vdso_info.gnu_hash) {
 		uint32_t h1 = gnu_hash(name), h2, *hashval;
 
-		i = vdso_info.bucket[h1 % vdso_info.nbucket];
+		i = vdso_info.gnu_bucket[h1 % vdso_info.nbucket];
 		if (i == 0)
 			return 0;
 		h1 |= 1;
-		hashval = vdso_info.bucket + vdso_info.nbucket +
+		hashval = vdso_info.gnu_bucket + vdso_info.nbucket +
 			  (i - vdso_info.gnu_hash[1]);
 		for (;; i++) {
 			ELF(Sym) *sym = &vdso_info.symtab[i];

From b4a1dec11793936ffe1a9fb811724532ff3b1174 Mon Sep 17 00:00:00 2001
From: Sumanth Korikkar <sumanthk@linux.ibm.com>
Date: Mon, 24 Feb 2025 12:27:04 +0100
Subject: [PATCH 0924/1173] s390/ftrace: Fix return address recovery of traced
 function

When fgraph is enabled the traced function return address is replaced with
trampoline return_to_handler(). The original return address of the traced
function is saved in per task return stack along with a stack pointer for
reliable stack unwinding via function_graph_enter_regs().

During stack unwinding e.g. for livepatching, ftrace_graph_ret_addr()
identifies the original return address of the traced function with the
saved stack pointer.

With a recent change, the stack pointers passed to ftrace_graph_ret_addr()
and function_graph_enter_regs() do not match anymore, and therefore the
original return address is not found.

Pass the correct stack pointer to function_graph_enter_regs() to fix this.

Fixes: 7495e179b478 ("s390/tracing: Enable HAVE_FTRACE_GRAPH_FUNC")
Reviewed-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Sumanth Korikkar <sumanthk@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/kernel/ftrace.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 63ba6306632ef..e540b022ceb23 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -266,12 +266,13 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
 		       struct ftrace_ops *op, struct ftrace_regs *fregs)
 {
 	unsigned long *parent = &arch_ftrace_regs(fregs)->regs.gprs[14];
+	unsigned long sp = arch_ftrace_regs(fregs)->regs.gprs[15];
 
 	if (unlikely(ftrace_graph_is_dead()))
 		return;
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		return;
-	if (!function_graph_enter_regs(*parent, ip, 0, parent, fregs))
+	if (!function_graph_enter_regs(*parent, ip, 0, (unsigned long *)sp, fregs))
 		*parent = (unsigned long)&return_to_handler;
 }
 

From f9dc8fb3afc968042bdaf4b6e445a9272071c9f3 Mon Sep 17 00:00:00 2001
From: Xiaoyao Li <xiaoyao.li@intel.com>
Date: Tue, 4 Mar 2025 03:23:14 -0500
Subject: [PATCH 0925/1173] KVM: x86: Explicitly zero EAX and EBX when
 PERFMON_V2 isn't supported by KVM

Fix a goof where KVM sets CPUID.0x80000022.EAX to CPUID.0x80000022.EBX
instead of zeroing both when PERFMON_V2 isn't supported by KVM.  In
practice, barring a buggy CPU (or vCPU model when running nested) only the
!enable_pmu case is affected, as KVM always supports PERFMON_V2 if it's
available in hardware, i.e. CPUID.0x80000022.EBX will be '0' if PERFMON_V2
is unsupported.

For the !enable_pmu case, the bug is relatively benign as KVM will refuse
to enable PMU capabilities, but a VMM that reflects KVM's supported CPUID
into the guest could inadvertently induce #GPs in the guest due to
advertising support for MSRs that KVM refuses to emulate.

Fixes: 94cdeebd8211 ("KVM: x86/cpuid: Add AMD CPUID ExtPerfMonAndDbg leaf 0x80000022")
Signed-off-by: Xiaoyao Li <xiaoyao.li@intel.com>
Link: https://lore.kernel.org/r/20250304082314.472202-3-xiaoyao.li@intel.com
[sean: massage shortlog and changelog, tag for stable]
Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/cpuid.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 8eb3a88707f21..121edf1f2a79a 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -1763,7 +1763,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 
 		entry->ecx = entry->edx = 0;
 		if (!enable_pmu || !kvm_cpu_cap_has(X86_FEATURE_PERFMON_V2)) {
-			entry->eax = entry->ebx;
+			entry->eax = entry->ebx = 0;
 			break;
 		}
 

From 3d252160b818045f3a152b13756f6f37ca34639d Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Tue, 4 Mar 2025 13:51:38 +0000
Subject: [PATCH 0926/1173] fs/pipe: Read pipe->{head,tail} atomically outside
 pipe->mutex

pipe_readable(), pipe_writable(), and pipe_poll() can read "pipe->head"
and "pipe->tail" outside of "pipe->mutex" critical section. When the
head and the tail are read individually in that order, there is a window
for interruption between the two reads in which both the head and the
tail can be updated by concurrent readers and writers.

One of the problematic scenarios observed with hackbench running
multiple groups on a large server on a particular pipe inode is as
follows:

    pipe->head = 36
    pipe->tail = 36

    hackbench-118762  [057] .....  1029.550548: pipe_write: *wakes up: pipe not full*
    hackbench-118762  [057] .....  1029.550548: pipe_write: head: 36 -> 37 [tail: 36]
    hackbench-118762  [057] .....  1029.550548: pipe_write: *wake up next reader 118740*
    hackbench-118762  [057] .....  1029.550548: pipe_write: *wake up next writer 118768*

    hackbench-118768  [206] .....  1029.55055X: pipe_write: *writer wakes up*
    hackbench-118768  [206] .....  1029.55055X: pipe_write: head = READ_ONCE(pipe->head) [37]
    ... CPU 206 interrupted (exact wakeup was not traced but 118768 did read head at 37 in traces)

    hackbench-118740  [057] .....  1029.550558: pipe_read:  *reader wakes up: pipe is not empty*
    hackbench-118740  [057] .....  1029.550558: pipe_read:  tail: 36 -> 37 [head = 37]
    hackbench-118740  [057] .....  1029.550559: pipe_read:  *pipe is empty; wakeup writer 118768*
    hackbench-118740  [057] .....  1029.550559: pipe_read:  *sleeps*

    hackbench-118766  [185] .....  1029.550592: pipe_write: *New writer comes in*
    hackbench-118766  [185] .....  1029.550592: pipe_write: head: 37 -> 38 [tail: 37]
    hackbench-118766  [185] .....  1029.550592: pipe_write: *wakes up reader 118766*

    hackbench-118740  [185] .....  1029.550598: pipe_read:  *reader wakes up; pipe not empty*
    hackbench-118740  [185] .....  1029.550599: pipe_read:  tail: 37 -> 38 [head: 38]
    hackbench-118740  [185] .....  1029.550599: pipe_read:  *pipe is empty*
    hackbench-118740  [185] .....  1029.550599: pipe_read:  *reader sleeps; wakeup writer 118768*

    ... CPU 206 switches back to writer
    hackbench-118768  [206] .....  1029.550601: pipe_write: tail = READ_ONCE(pipe->tail) [38]
    hackbench-118768  [206] .....  1029.550601: pipe_write: pipe_full()? (u32)(37 - 38) >= 16? Yes
    hackbench-118768  [206] .....  1029.550601: pipe_write: *writer goes back to sleep*

    [ Tasks 118740 and 118768 can then indefinitely wait on each other. ]

The unsigned arithmetic in pipe_occupancy() wraps around when
"pipe->tail > pipe->head" leading to pipe_full() returning true despite
the pipe being empty.

The case of genuine wraparound of "pipe->head" is handled since pipe
buffer has data allowing readers to make progress until the pipe->tail
wraps too after which the reader will wakeup a sleeping writer, however,
mistaking the pipe to be full when it is in fact empty can lead to
readers and writers waiting on each other indefinitely.

This issue became more problematic and surfaced as a hang in hackbench
after the optimization in commit aaec5a95d596 ("pipe_read: don't wake up
the writer if the pipe is still full") significantly reduced the number
of spurious wakeups of writers that had previously helped mask the
issue.

To avoid missing any updates between the reads of "pipe->head" and
"pipe->write", unionize the two with a single unsigned long
"pipe->head_tail" member that can be loaded atomically.

Using "pipe->head_tail" to read the head and the tail ensures the
lockless checks do not miss any updates to the head or the tail and
since those two are only updated under "pipe->mutex", it ensures that
the head is always ahead of, or equal to the tail resulting in correct
calculations.

  [ prateek: commit log, testing on x86 platforms. ]

Reported-and-debugged-by: Swapnil Sapkal <swapnil.sapkal@amd.com>
Closes: https://lore.kernel.org/lkml/e813814e-7094-4673-bc69-731af065a0eb@amd.com/
Reported-by: Alexey Gladkov <legion@kernel.org>
Closes: https://lore.kernel.org/all/Z8Wn0nTvevLRG_4m@example.org/
Fixes: 8cefc107ca54 ("pipe: Use head and tail pointers for the ring, not cursor and length")
Tested-by: Swapnil Sapkal <swapnil.sapkal@amd.com>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Tested-by: Alexey Gladkov <legion@kernel.org>
Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/pipe.c                 | 19 ++++++++-----------
 include/linux/pipe_fs_i.h | 39 +++++++++++++++++++++++++++++++++++++--
 2 files changed, 45 insertions(+), 13 deletions(-)

diff --git a/fs/pipe.c b/fs/pipe.c
index ce1af7592780d..e8e6698f36981 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -210,11 +210,10 @@ static const struct pipe_buf_operations anon_pipe_buf_ops = {
 /* Done while waiting without holding the pipe lock - thus the READ_ONCE() */
 static inline bool pipe_readable(const struct pipe_inode_info *pipe)
 {
-	unsigned int head = READ_ONCE(pipe->head);
-	unsigned int tail = READ_ONCE(pipe->tail);
+	union pipe_index idx = { .head_tail = READ_ONCE(pipe->head_tail) };
 	unsigned int writers = READ_ONCE(pipe->writers);
 
-	return !pipe_empty(head, tail) || !writers;
+	return !pipe_empty(idx.head, idx.tail) || !writers;
 }
 
 static inline unsigned int pipe_update_tail(struct pipe_inode_info *pipe,
@@ -417,11 +416,10 @@ static inline int is_packetized(struct file *file)
 /* Done while waiting without holding the pipe lock - thus the READ_ONCE() */
 static inline bool pipe_writable(const struct pipe_inode_info *pipe)
 {
-	unsigned int head = READ_ONCE(pipe->head);
-	unsigned int tail = READ_ONCE(pipe->tail);
+	union pipe_index idx = { .head_tail = READ_ONCE(pipe->head_tail) };
 	unsigned int max_usage = READ_ONCE(pipe->max_usage);
 
-	return !pipe_full(head, tail, max_usage) ||
+	return !pipe_full(idx.head, idx.tail, max_usage) ||
 		!READ_ONCE(pipe->readers);
 }
 
@@ -659,7 +657,7 @@ pipe_poll(struct file *filp, poll_table *wait)
 {
 	__poll_t mask;
 	struct pipe_inode_info *pipe = filp->private_data;
-	unsigned int head, tail;
+	union pipe_index idx;
 
 	/* Epoll has some historical nasty semantics, this enables them */
 	WRITE_ONCE(pipe->poll_usage, true);
@@ -680,19 +678,18 @@ pipe_poll(struct file *filp, poll_table *wait)
 	 * if something changes and you got it wrong, the poll
 	 * table entry will wake you up and fix it.
 	 */
-	head = READ_ONCE(pipe->head);
-	tail = READ_ONCE(pipe->tail);
+	idx.head_tail = READ_ONCE(pipe->head_tail);
 
 	mask = 0;
 	if (filp->f_mode & FMODE_READ) {
-		if (!pipe_empty(head, tail))
+		if (!pipe_empty(idx.head, idx.tail))
 			mask |= EPOLLIN | EPOLLRDNORM;
 		if (!pipe->writers && filp->f_pipe != pipe->w_counter)
 			mask |= EPOLLHUP;
 	}
 
 	if (filp->f_mode & FMODE_WRITE) {
-		if (!pipe_full(head, tail, pipe->max_usage))
+		if (!pipe_full(idx.head, idx.tail, pipe->max_usage))
 			mask |= EPOLLOUT | EPOLLWRNORM;
 		/*
 		 * Most Unices do not set EPOLLERR for FIFOs but on Linux they
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index 8ff23bf5a8197..3cc4f8eab853f 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -31,6 +31,33 @@ struct pipe_buffer {
 	unsigned long private;
 };
 
+/*
+ * Really only alpha needs 32-bit fields, but
+ * might as well do it for 64-bit architectures
+ * since that's what we've historically done,
+ * and it makes 'head_tail' always be a simple
+ * 'unsigned long'.
+ */
+#ifdef CONFIG_64BIT
+typedef unsigned int pipe_index_t;
+#else
+typedef unsigned short pipe_index_t;
+#endif
+
+/*
+ * We have to declare this outside 'struct pipe_inode_info',
+ * but then we can't use 'union pipe_index' for an anonymous
+ * union, so we end up having to duplicate this declaration
+ * below. Annoying.
+ */
+union pipe_index {
+	unsigned long head_tail;
+	struct {
+		pipe_index_t head;
+		pipe_index_t tail;
+	};
+};
+
 /**
  *	struct pipe_inode_info - a linux kernel pipe
  *	@mutex: mutex protecting the whole thing
@@ -58,8 +85,16 @@ struct pipe_buffer {
 struct pipe_inode_info {
 	struct mutex mutex;
 	wait_queue_head_t rd_wait, wr_wait;
-	unsigned int head;
-	unsigned int tail;
+
+	/* This has to match the 'union pipe_index' above */
+	union {
+		unsigned long head_tail;
+		struct {
+			pipe_index_t head;
+			pipe_index_t tail;
+		};
+	};
+
 	unsigned int max_usage;
 	unsigned int ring_size;
 	unsigned int nr_accounted;

From dfc1b168a8c4b376fa222b27b97c2c4ad4b786e1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Mon, 17 Feb 2025 08:27:54 +0100
Subject: [PATCH 0927/1173] kbuild: userprogs: use correct lld when linking
 through clang
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The userprog infrastructure links objects files through $(CC).
Either explicitly by manually calling $(CC) on multiple object files or
implicitly by directly compiling a source file to an executable.
The documentation at Documentation/kbuild/llvm.rst indicates that ld.lld
would be used for linking if LLVM=1 is specified.
However clang instead will use either a globally installed cross linker
from $PATH called ${target}-ld or fall back to the system linker, which
probably does not support crosslinking.
For the normal kernel build this is not an issue because the linker is
always executed directly, without the compiler being involved.

Explicitly pass --ld-path to clang so $(LD) is respected.
As clang 13.0.1 is required to build the kernel, this option is available.

Fixes: 7f3a59db274c ("kbuild: add infrastructure to build userspace programs")
Cc: stable@vger.kernel.org # needs wrapping in $(cc-option) for < 6.9
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 Makefile | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/Makefile b/Makefile
index 70bdbf2218fc5..6a8e5be6b0043 100644
--- a/Makefile
+++ b/Makefile
@@ -1123,6 +1123,11 @@ endif
 KBUILD_USERCFLAGS  += $(filter -m32 -m64 --target=%, $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS))
 KBUILD_USERLDFLAGS += $(filter -m32 -m64 --target=%, $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS))
 
+# userspace programs are linked via the compiler, use the correct linker
+ifeq ($(CONFIG_CC_IS_CLANG)$(CONFIG_LD_IS_LLD),yy)
+KBUILD_USERLDFLAGS += --ld-path=$(LD)
+endif
+
 # make the checker run with the right architecture
 CHECKFLAGS += --arch=$(ARCH)
 

From 02e9a22ceef0227175e391902d8760425fa072c6 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 25 Feb 2025 11:00:31 +0100
Subject: [PATCH 0928/1173] kbuild: hdrcheck: fix cross build with clang

The headercheck tries to call clang with a mix of compiler arguments
that don't include the target architecture. When building e.g. x86
headers on arm64, this produces a warning like

   clang: warning: unknown platform, assuming -mfloat-abi=soft

Add in the KBUILD_CPPFLAGS, which contain the target, in order to make it
build properly.

See also 1b71c2fb04e7 ("kbuild: userprogs: fix bitsize and target
detection on clang").

Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Fixes: feb843a469fb ("kbuild: add $(CLANG_FLAGS) to KBUILD_CPPFLAGS")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 usr/include/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/usr/include/Makefile b/usr/include/Makefile
index 6c6de1b1622b1..e3d6b03527fec 100644
--- a/usr/include/Makefile
+++ b/usr/include/Makefile
@@ -10,7 +10,7 @@ UAPI_CFLAGS := -std=c90 -Wall -Werror=implicit-function-declaration
 
 # In theory, we do not care -m32 or -m64 for header compile tests.
 # It is here just because CONFIG_CC_CAN_LINK is tested with -m32 or -m64.
-UAPI_CFLAGS += $(filter -m32 -m64 --target=%, $(KBUILD_CFLAGS))
+UAPI_CFLAGS += $(filter -m32 -m64 --target=%, $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS))
 
 # USERCFLAGS might contain sysroot location for CC.
 UAPI_CFLAGS += $(USERCFLAGS)

From dd0b7d4a56e3349de65bf9752734510fb55baf29 Mon Sep 17 00:00:00 2001
From: Satoru Takeuchi <satoru.takeuchi@gmail.com>
Date: Fri, 28 Feb 2025 20:37:08 +0900
Subject: [PATCH 0929/1173] docs: Kconfig: fix defconfig description

Commit 2a86f6612164 ("kbuild: use KBUILD_DEFCONFIG as the fallback
for DEFCONFIG_LIST") removed arch/$ARCH/defconfig; however,
the document has not been updated to reflect this change yet.

Signed-off-by: Satoru Takeuchi <satoru.takeuchi@gmail.com>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 Documentation/admin-guide/README.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/admin-guide/README.rst b/Documentation/admin-guide/README.rst
index eb94526689091..b557cf1c820d2 100644
--- a/Documentation/admin-guide/README.rst
+++ b/Documentation/admin-guide/README.rst
@@ -176,7 +176,7 @@ Configuring the kernel
                         values without prompting.
 
      "make defconfig"   Create a ./.config file by using the default
-                        symbol values from either arch/$ARCH/defconfig
+                        symbol values from either arch/$ARCH/configs/defconfig
                         or arch/$ARCH/configs/${PLATFORM}_defconfig,
                         depending on the architecture.
 

From 0ec914707c3ed052ed26eb88f9300109030a7fb2 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Mon, 3 Mar 2025 16:54:21 +0100
Subject: [PATCH 0930/1173] x86/irq/32: Use named operands in inline asm

Also use inout "+" constraint modifier where appropriate.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250303155446.112769-1-ubizjak@gmail.com
---
 arch/x86/kernel/irq_32.c | 20 +++++++++-----------
 1 file changed, 9 insertions(+), 11 deletions(-)

diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index dc1049c01f9b9..c4719c40252fc 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -54,12 +54,11 @@ static inline void print_stack_overflow(void) { }
 
 static void call_on_stack(void *func, void *stack)
 {
-	asm volatile("xchgl	%%ebx,%%esp	\n"
+	asm volatile("xchgl %[sp], %%esp\n"
 		     CALL_NOSPEC
-		     "movl	%%ebx,%%esp	\n"
-		     : "=b" (stack)
-		     : "0" (stack),
-		       [thunk_target] "D"(func)
+		     "movl %[sp], %%esp"
+		     : [sp] "+b" (stack)
+		     : [thunk_target] "D" (func)
 		     : "memory", "cc", "edx", "ecx", "eax");
 }
 
@@ -71,7 +70,7 @@ static inline void *current_stack(void)
 static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
 {
 	struct irq_stack *curstk, *irqstk;
-	u32 *isp, *prev_esp, arg1;
+	u32 *isp, *prev_esp;
 
 	curstk = (struct irq_stack *) current_stack();
 	irqstk = __this_cpu_read(pcpu_hot.hardirq_stack_ptr);
@@ -94,12 +93,11 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
 	if (unlikely(overflow))
 		call_on_stack(print_stack_overflow, isp);
 
-	asm volatile("xchgl	%%ebx,%%esp	\n"
+	asm volatile("xchgl %[sp], %%esp\n"
 		     CALL_NOSPEC
-		     "movl	%%ebx,%%esp	\n"
-		     : "=a" (arg1), "=b" (isp)
-		     :  "0" (desc),   "1" (isp),
-			[thunk_target] "D" (desc->handle_irq)
+		     "movl %[sp], %%esp"
+		     : "+a" (desc), [sp] "+b" (isp)
+		     : [thunk_target] "D" (desc->handle_irq)
 		     : "memory", "cc", "ecx");
 	return 1;
 }

From 76f71137811a6dfa52b3e22a86a772e5753021d3 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Mon, 3 Mar 2025 16:54:22 +0100
Subject: [PATCH 0931/1173] x86/irq/32: Add missing clobber to inline asm

i386 ABI declares %edx as a call-clobbered register.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250303155446.112769-2-ubizjak@gmail.com
---
 arch/x86/kernel/irq_32.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index c4719c40252fc..eab458009f973 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -98,7 +98,7 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
 		     "movl %[sp], %%esp"
 		     : "+a" (desc), [sp] "+b" (isp)
 		     : [thunk_target] "D" (desc->handle_irq)
-		     : "memory", "cc", "ecx");
+		     : "memory", "cc", "edx", "ecx");
 	return 1;
 }
 

From d4432fb5b8798a7663974bed277a8a6e330a50d8 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Mon, 3 Mar 2025 16:54:24 +0100
Subject: [PATCH 0932/1173] x86/irq/32: Use current_stack_pointer to avoid
 asm() in check_stack_overflow()

Make code more readable by using the 'current_stack_pointer' global variable.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250303155446.112769-4-ubizjak@gmail.com
---
 arch/x86/kernel/irq_32.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index eab458009f973..8c7babbcf6b70 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -31,10 +31,7 @@ int sysctl_panic_on_stackoverflow __read_mostly;
 /* Debugging check for stack overflow: is there less than 1KB free? */
 static int check_stack_overflow(void)
 {
-	long sp;
-
-	__asm__ __volatile__("andl %%esp,%0" :
-			     "=r" (sp) : "0" (THREAD_SIZE - 1));
+	unsigned long sp = current_stack_pointer & (THREAD_SIZE - 1);
 
 	return sp < (sizeof(struct thread_info) + STACK_WARN);
 }

From c8b584fe82d0f1e478a598f954943b095a4a8f5c Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Mon, 3 Mar 2025 16:54:25 +0100
Subject: [PATCH 0933/1173] x86/irq/32: Change some static functions to bool

The return values of these functions is 0/1, but they use an int
type instead of bool:

  check_stack_overflow()
  execute_on_irq_stack()

Change the type of these function to bool and adjust their return
values and affected helper variables.

[ mingo: Rewrote the changelog ]

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250303155446.112769-5-ubizjak@gmail.com
---
 arch/x86/kernel/irq_32.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 8c7babbcf6b70..d301208d35d02 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -29,7 +29,7 @@
 int sysctl_panic_on_stackoverflow __read_mostly;
 
 /* Debugging check for stack overflow: is there less than 1KB free? */
-static int check_stack_overflow(void)
+static bool check_stack_overflow(void)
 {
 	unsigned long sp = current_stack_pointer & (THREAD_SIZE - 1);
 
@@ -45,7 +45,7 @@ static void print_stack_overflow(void)
 }
 
 #else
-static inline int check_stack_overflow(void) { return 0; }
+static inline bool check_stack_overflow(void) { return false; }
 static inline void print_stack_overflow(void) { }
 #endif
 
@@ -64,7 +64,7 @@ static inline void *current_stack(void)
 	return (void *)(current_stack_pointer & ~(THREAD_SIZE - 1));
 }
 
-static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
+static inline bool execute_on_irq_stack(bool overflow, struct irq_desc *desc)
 {
 	struct irq_stack *curstk, *irqstk;
 	u32 *isp, *prev_esp;
@@ -79,7 +79,7 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
 	 * current stack (which is the irq stack already after all)
 	 */
 	if (unlikely(curstk == irqstk))
-		return 0;
+		return false;
 
 	isp = (u32 *) ((char *)irqstk + sizeof(*irqstk));
 
@@ -96,7 +96,7 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
 		     : "+a" (desc), [sp] "+b" (isp)
 		     : [thunk_target] "D" (desc->handle_irq)
 		     : "memory", "cc", "edx", "ecx");
-	return 1;
+	return true;
 }
 
 /*
@@ -145,7 +145,7 @@ void do_softirq_own_stack(void)
 
 void __handle_irq(struct irq_desc *desc, struct pt_regs *regs)
 {
-	int overflow = check_stack_overflow();
+	bool overflow = check_stack_overflow();
 
 	if (user_mode(regs) || !execute_on_irq_stack(overflow, desc)) {
 		if (unlikely(overflow))

From ab2bb9c084f7e3b641ceba91efc33b3adcd1846e Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Mon, 3 Mar 2025 11:52:36 -0500
Subject: [PATCH 0934/1173] percpu: Introduce percpu hot section

Add a subsection to the percpu data for frequently accessed variables
that should remain cached on each processor.  These varables should not
be accessed from other processors to avoid cacheline bouncing.

This will replace the pcpu_hot struct on x86, and open up similar
functionality to other architectures and the kernel core.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250303165246.2175811-2-brgerst@gmail.com
---
 include/asm-generic/vmlinux.lds.h | 11 +++++++++++
 include/linux/percpu-defs.h       | 13 +++++++++++++
 2 files changed, 24 insertions(+)

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index b32e453acf9d3..c4e8fac502543 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -385,6 +385,11 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
 	. = ALIGN(PAGE_SIZE);						\
 	__nosave_end = .;
 
+#define CACHE_HOT_DATA(align)						\
+	. = ALIGN(align);						\
+	*(SORT_BY_ALIGNMENT(.data..hot.*))				\
+	. = ALIGN(align);
+
 #define PAGE_ALIGNED_DATA(page_align)					\
 	. = ALIGN(page_align);						\
 	*(.data..page_aligned)						\
@@ -1065,6 +1070,11 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
 	. = ALIGN(PAGE_SIZE);						\
 	*(.data..percpu..page_aligned)					\
 	. = ALIGN(cacheline);						\
+	__per_cpu_hot_start = .;					\
+	*(SORT_BY_ALIGNMENT(.data..percpu..hot.*))			\
+	__per_cpu_hot_pad = .;						\
+	. = ALIGN(cacheline);						\
+	__per_cpu_hot_end = .;						\
 	*(.data..percpu..read_mostly)					\
 	. = ALIGN(cacheline);						\
 	*(.data..percpu)						\
@@ -1112,6 +1122,7 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
 		INIT_TASK_DATA(inittask)				\
 		NOSAVE_DATA						\
 		PAGE_ALIGNED_DATA(pagealigned)				\
+		CACHE_HOT_DATA(cacheline)				\
 		CACHELINE_ALIGNED_DATA(cacheline)			\
 		READ_MOSTLY_DATA(cacheline)				\
 		DATA_DATA						\
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index 40d34e032d5b8..0fcacb9097789 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -112,6 +112,19 @@
 #define DEFINE_PER_CPU(type, name)					\
 	DEFINE_PER_CPU_SECTION(type, name, "")
 
+/*
+ * Declaration/definition used for per-CPU variables that are frequently
+ * accessed and should be in a single cacheline.
+ *
+ * For use only by architecture and core code.  Only use scalar or pointer
+ * types to maximize density.
+ */
+#define DECLARE_PER_CPU_CACHE_HOT(type, name)				\
+	DECLARE_PER_CPU_SECTION(type, name, "..hot.." #name)
+
+#define DEFINE_PER_CPU_CACHE_HOT(type, name)				\
+	DEFINE_PER_CPU_SECTION(type, name, "..hot.." #name)
+
 /*
  * Declaration/definition used for per-CPU variables that must be cacheline
  * aligned under SMP conditions so that, whilst a particular instance of the

From 972f9cdff924ca53715019b63b4d4aed69d23b1e Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Mon, 3 Mar 2025 11:52:37 -0500
Subject: [PATCH 0935/1173] x86/percpu: Move pcpu_hot to percpu hot section

Also change the alignment of the percpu hot section:

 -       PERCPU_SECTION(INTERNODE_CACHE_BYTES)
 +       PERCPU_SECTION(L1_CACHE_BYTES)

As vSMP will muck with INTERNODE_CACHE_BYTES that invalidates the
too-large-section assert we do:

  ASSERT(__per_cpu_hot_end - __per_cpu_hot_start <= 64, "percpu cache hot section too large")

[ mingo: Added INTERNODE_CACHE_BYTES fix & explanation. ]

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250303165246.2175811-3-brgerst@gmail.com
---
 arch/x86/include/asm/current.h | 28 +++++++++++-----------------
 arch/x86/kernel/cpu/common.c   |  2 +-
 arch/x86/kernel/vmlinux.lds.S  |  5 ++++-
 3 files changed, 16 insertions(+), 19 deletions(-)

diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h
index bf5953883ec36..60bc66edca833 100644
--- a/arch/x86/include/asm/current.h
+++ b/arch/x86/include/asm/current.h
@@ -13,32 +13,26 @@
 struct task_struct;
 
 struct pcpu_hot {
-	union {
-		struct {
-			struct task_struct	*current_task;
-			int			preempt_count;
-			int			cpu_number;
+	struct task_struct	*current_task;
+	int			preempt_count;
+	int			cpu_number;
 #ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING
-			u64			call_depth;
+	u64			call_depth;
 #endif
-			unsigned long		top_of_stack;
-			void			*hardirq_stack_ptr;
-			u16			softirq_pending;
+	unsigned long		top_of_stack;
+	void			*hardirq_stack_ptr;
+	u16			softirq_pending;
 #ifdef CONFIG_X86_64
-			bool			hardirq_stack_inuse;
+	bool			hardirq_stack_inuse;
 #else
-			void			*softirq_stack_ptr;
+	void			*softirq_stack_ptr;
 #endif
-		};
-		u8	pad[64];
-	};
 };
-static_assert(sizeof(struct pcpu_hot) == 64);
 
-DECLARE_PER_CPU_ALIGNED(struct pcpu_hot, pcpu_hot);
+DECLARE_PER_CPU_CACHE_HOT(struct pcpu_hot, pcpu_hot);
 
 /* const-qualified alias to pcpu_hot, aliased by linker. */
-DECLARE_PER_CPU_ALIGNED(const struct pcpu_hot __percpu_seg_override,
+DECLARE_PER_CPU_CACHE_HOT(const struct pcpu_hot __percpu_seg_override,
 			const_pcpu_hot);
 
 static __always_inline struct task_struct *get_current(void)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 88a6707b765cf..f00870b2c9807 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -2064,7 +2064,7 @@ static __init int setup_setcpuid(char *arg)
 }
 __setup("setcpuid=", setup_setcpuid);
 
-DEFINE_PER_CPU_ALIGNED(struct pcpu_hot, pcpu_hot) = {
+DEFINE_PER_CPU_CACHE_HOT(struct pcpu_hot, pcpu_hot) = {
 	.current_task	= &init_task,
 	.preempt_count	= INIT_PREEMPT_COUNT,
 	.top_of_stack	= TOP_OF_INIT_STACK,
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 1769a7126224c..0ef9870ea52ec 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -187,6 +187,8 @@ SECTIONS
 
 		PAGE_ALIGNED_DATA(PAGE_SIZE)
 
+		CACHE_HOT_DATA(L1_CACHE_BYTES)
+
 		CACHELINE_ALIGNED_DATA(L1_CACHE_BYTES)
 
 		DATA_DATA
@@ -327,7 +329,8 @@ SECTIONS
 		EXIT_DATA
 	}
 
-	PERCPU_SECTION(INTERNODE_CACHE_BYTES)
+	PERCPU_SECTION(L1_CACHE_BYTES)
+	ASSERT(__per_cpu_hot_end - __per_cpu_hot_start <= 64, "percpu cache hot section too large")
 
 	RUNTIME_CONST_VARIABLES
 	RUNTIME_CONST(ptr, USER_PTR_MAX)

From 46e8fff6d45fe44cb0939c9339b6d5936551b1e4 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Mon, 3 Mar 2025 11:52:38 -0500
Subject: [PATCH 0936/1173] x86/preempt: Move preempt count to percpu hot
 section

No functional change.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250303165246.2175811-4-brgerst@gmail.com
---
 arch/x86/include/asm/current.h |  1 -
 arch/x86/include/asm/preempt.h | 25 +++++++++++++------------
 arch/x86/kernel/cpu/common.c   |  4 +++-
 include/linux/preempt.h        |  1 +
 4 files changed, 17 insertions(+), 14 deletions(-)

diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h
index 60bc66edca833..46a736d6f2eca 100644
--- a/arch/x86/include/asm/current.h
+++ b/arch/x86/include/asm/current.h
@@ -14,7 +14,6 @@ struct task_struct;
 
 struct pcpu_hot {
 	struct task_struct	*current_task;
-	int			preempt_count;
 	int			cpu_number;
 #ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING
 	u64			call_depth;
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index 919909d8cb77e..578441db09f0b 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -4,10 +4,11 @@
 
 #include <asm/rmwcc.h>
 #include <asm/percpu.h>
-#include <asm/current.h>
 
 #include <linux/static_call_types.h>
 
+DECLARE_PER_CPU_CACHE_HOT(int, __preempt_count);
+
 /* We use the MSB mostly because its available */
 #define PREEMPT_NEED_RESCHED	0x80000000
 
@@ -23,18 +24,18 @@
  */
 static __always_inline int preempt_count(void)
 {
-	return raw_cpu_read_4(pcpu_hot.preempt_count) & ~PREEMPT_NEED_RESCHED;
+	return raw_cpu_read_4(__preempt_count) & ~PREEMPT_NEED_RESCHED;
 }
 
 static __always_inline void preempt_count_set(int pc)
 {
 	int old, new;
 
-	old = raw_cpu_read_4(pcpu_hot.preempt_count);
+	old = raw_cpu_read_4(__preempt_count);
 	do {
 		new = (old & PREEMPT_NEED_RESCHED) |
 			(pc & ~PREEMPT_NEED_RESCHED);
-	} while (!raw_cpu_try_cmpxchg_4(pcpu_hot.preempt_count, &old, new));
+	} while (!raw_cpu_try_cmpxchg_4(__preempt_count, &old, new));
 }
 
 /*
@@ -43,7 +44,7 @@ static __always_inline void preempt_count_set(int pc)
 #define init_task_preempt_count(p) do { } while (0)
 
 #define init_idle_preempt_count(p, cpu) do { \
-	per_cpu(pcpu_hot.preempt_count, (cpu)) = PREEMPT_DISABLED; \
+	per_cpu(__preempt_count, (cpu)) = PREEMPT_DISABLED; \
 } while (0)
 
 /*
@@ -57,17 +58,17 @@ static __always_inline void preempt_count_set(int pc)
 
 static __always_inline void set_preempt_need_resched(void)
 {
-	raw_cpu_and_4(pcpu_hot.preempt_count, ~PREEMPT_NEED_RESCHED);
+	raw_cpu_and_4(__preempt_count, ~PREEMPT_NEED_RESCHED);
 }
 
 static __always_inline void clear_preempt_need_resched(void)
 {
-	raw_cpu_or_4(pcpu_hot.preempt_count, PREEMPT_NEED_RESCHED);
+	raw_cpu_or_4(__preempt_count, PREEMPT_NEED_RESCHED);
 }
 
 static __always_inline bool test_preempt_need_resched(void)
 {
-	return !(raw_cpu_read_4(pcpu_hot.preempt_count) & PREEMPT_NEED_RESCHED);
+	return !(raw_cpu_read_4(__preempt_count) & PREEMPT_NEED_RESCHED);
 }
 
 /*
@@ -76,12 +77,12 @@ static __always_inline bool test_preempt_need_resched(void)
 
 static __always_inline void __preempt_count_add(int val)
 {
-	raw_cpu_add_4(pcpu_hot.preempt_count, val);
+	raw_cpu_add_4(__preempt_count, val);
 }
 
 static __always_inline void __preempt_count_sub(int val)
 {
-	raw_cpu_add_4(pcpu_hot.preempt_count, -val);
+	raw_cpu_add_4(__preempt_count, -val);
 }
 
 /*
@@ -91,7 +92,7 @@ static __always_inline void __preempt_count_sub(int val)
  */
 static __always_inline bool __preempt_count_dec_and_test(void)
 {
-	return GEN_UNARY_RMWcc("decl", __my_cpu_var(pcpu_hot.preempt_count), e,
+	return GEN_UNARY_RMWcc("decl", __my_cpu_var(__preempt_count), e,
 			       __percpu_arg([var]));
 }
 
@@ -100,7 +101,7 @@ static __always_inline bool __preempt_count_dec_and_test(void)
  */
 static __always_inline bool should_resched(int preempt_offset)
 {
-	return unlikely(raw_cpu_read_4(pcpu_hot.preempt_count) == preempt_offset);
+	return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset);
 }
 
 #ifdef CONFIG_PREEMPTION
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index f00870b2c9807..a9d61537d4a64 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -2066,12 +2066,14 @@ __setup("setcpuid=", setup_setcpuid);
 
 DEFINE_PER_CPU_CACHE_HOT(struct pcpu_hot, pcpu_hot) = {
 	.current_task	= &init_task,
-	.preempt_count	= INIT_PREEMPT_COUNT,
 	.top_of_stack	= TOP_OF_INIT_STACK,
 };
 EXPORT_PER_CPU_SYMBOL(pcpu_hot);
 EXPORT_PER_CPU_SYMBOL(const_pcpu_hot);
 
+DEFINE_PER_CPU_CACHE_HOT(int, __preempt_count) = INIT_PREEMPT_COUNT;
+EXPORT_PER_CPU_SYMBOL(__preempt_count);
+
 #ifdef CONFIG_X86_64
 static void wrmsrl_cstar(unsigned long val)
 {
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index ca86235ac15c0..4c1af9b7e28b2 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -319,6 +319,7 @@ do { \
 #ifdef CONFIG_PREEMPT_NOTIFIERS
 
 struct preempt_notifier;
+struct task_struct;
 
 /**
  * preempt_ops - notifiers called when a task is preempted and rescheduled

From 01c7bc5198e9ef5628fad0346c5cdba2633a79da Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Mon, 3 Mar 2025 11:52:39 -0500
Subject: [PATCH 0937/1173] x86/smp: Move cpu number to percpu hot section

No functional change.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250303165246.2175811-5-brgerst@gmail.com
---
 arch/x86/include/asm/current.h | 1 -
 arch/x86/include/asm/smp.h     | 7 ++++---
 arch/x86/kernel/setup_percpu.c | 5 ++++-
 kernel/bpf/verifier.c          | 4 ++--
 4 files changed, 10 insertions(+), 7 deletions(-)

diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h
index 46a736d6f2eca..f988462d8b696 100644
--- a/arch/x86/include/asm/current.h
+++ b/arch/x86/include/asm/current.h
@@ -14,7 +14,6 @@ struct task_struct;
 
 struct pcpu_hot {
 	struct task_struct	*current_task;
-	int			cpu_number;
 #ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING
 	u64			call_depth;
 #endif
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 76d7c013cd089..bcfa00232d790 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -6,7 +6,8 @@
 #include <linux/thread_info.h>
 
 #include <asm/cpumask.h>
-#include <asm/current.h>
+
+DECLARE_PER_CPU_CACHE_HOT(int, cpu_number);
 
 DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map);
 DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map);
@@ -132,8 +133,8 @@ __visible void smp_call_function_single_interrupt(struct pt_regs *r);
  * This function is needed by all SMP systems. It must _always_ be valid
  * from the initial startup.
  */
-#define raw_smp_processor_id()  this_cpu_read(pcpu_hot.cpu_number)
-#define __smp_processor_id() __this_cpu_read(pcpu_hot.cpu_number)
+#define raw_smp_processor_id()  this_cpu_read(cpu_number)
+#define __smp_processor_id() __this_cpu_read(cpu_number)
 
 static inline struct cpumask *cpu_llc_shared_mask(int cpu)
 {
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 1e7be9409aa26..175afc3ffb128 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -23,6 +23,9 @@
 #include <asm/cpumask.h>
 #include <asm/cpu.h>
 
+DEFINE_PER_CPU_CACHE_HOT(int, cpu_number);
+EXPORT_PER_CPU_SYMBOL(cpu_number);
+
 DEFINE_PER_CPU_READ_MOSTLY(unsigned long, this_cpu_off);
 EXPORT_PER_CPU_SYMBOL(this_cpu_off);
 
@@ -161,7 +164,7 @@ void __init setup_per_cpu_areas(void)
 	for_each_possible_cpu(cpu) {
 		per_cpu_offset(cpu) = delta + pcpu_unit_offsets[cpu];
 		per_cpu(this_cpu_off, cpu) = per_cpu_offset(cpu);
-		per_cpu(pcpu_hot.cpu_number, cpu) = cpu;
+		per_cpu(cpu_number, cpu) = cpu;
 		setup_percpu_segment(cpu);
 		/*
 		 * Copy data used in early init routines from the
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index f4859516b190f..6e604caa870cb 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -21702,12 +21702,12 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 		if (insn->imm == BPF_FUNC_get_smp_processor_id &&
 		    verifier_inlines_helper_call(env, insn->imm)) {
 			/* BPF_FUNC_get_smp_processor_id inlining is an
-			 * optimization, so if pcpu_hot.cpu_number is ever
+			 * optimization, so if cpu_number is ever
 			 * changed in some incompatible and hard to support
 			 * way, it's fine to back out this inlining logic
 			 */
 #ifdef CONFIG_SMP
-			insn_buf[0] = BPF_MOV64_IMM(BPF_REG_0, (u32)(unsigned long)&pcpu_hot.cpu_number);
+			insn_buf[0] = BPF_MOV64_IMM(BPF_REG_0, (u32)(unsigned long)&cpu_number);
 			insn_buf[1] = BPF_MOV64_PERCPU_REG(BPF_REG_0, BPF_REG_0);
 			insn_buf[2] = BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0);
 			cnt = 3;

From 839be1619fb897364b782997bc2c5d072d7a79f2 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Mon, 3 Mar 2025 11:52:40 -0500
Subject: [PATCH 0938/1173] x86/retbleed: Move call depth to percpu hot section

No functional change.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250303165246.2175811-6-brgerst@gmail.com
---
 arch/x86/include/asm/current.h       |  3 ---
 arch/x86/include/asm/nospec-branch.h | 11 ++++++-----
 arch/x86/kernel/asm-offsets.c        |  3 ---
 arch/x86/kernel/cpu/common.c         |  8 ++++++++
 arch/x86/lib/retpoline.S             |  2 +-
 5 files changed, 15 insertions(+), 12 deletions(-)

diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h
index f988462d8b696..8ba2c0f8bcaf9 100644
--- a/arch/x86/include/asm/current.h
+++ b/arch/x86/include/asm/current.h
@@ -14,9 +14,6 @@ struct task_struct;
 
 struct pcpu_hot {
 	struct task_struct	*current_task;
-#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING
-	u64			call_depth;
-#endif
 	unsigned long		top_of_stack;
 	void			*hardirq_stack_ptr;
 	u16			softirq_pending;
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index aee26bb8230f8..44c6076fd22ba 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -12,7 +12,6 @@
 #include <asm/msr-index.h>
 #include <asm/unwind_hints.h>
 #include <asm/percpu.h>
-#include <asm/current.h>
 
 /*
  * Call depth tracking for Intel SKL CPUs to address the RSB underflow
@@ -78,21 +77,21 @@
 #include <asm/asm-offsets.h>
 
 #define CREDIT_CALL_DEPTH					\
-	movq	$-1, PER_CPU_VAR(pcpu_hot + X86_call_depth);
+	movq	$-1, PER_CPU_VAR(__x86_call_depth);
 
 #define RESET_CALL_DEPTH					\
 	xor	%eax, %eax;					\
 	bts	$63, %rax;					\
-	movq	%rax, PER_CPU_VAR(pcpu_hot + X86_call_depth);
+	movq	%rax, PER_CPU_VAR(__x86_call_depth);
 
 #define RESET_CALL_DEPTH_FROM_CALL				\
 	movb	$0xfc, %al;					\
 	shl	$56, %rax;					\
-	movq	%rax, PER_CPU_VAR(pcpu_hot + X86_call_depth);	\
+	movq	%rax, PER_CPU_VAR(__x86_call_depth);		\
 	CALL_THUNKS_DEBUG_INC_CALLS
 
 #define INCREMENT_CALL_DEPTH					\
-	sarq	$5, PER_CPU_VAR(pcpu_hot + X86_call_depth);	\
+	sarq	$5, PER_CPU_VAR(__x86_call_depth);		\
 	CALL_THUNKS_DEBUG_INC_CALLS
 
 #else
@@ -387,6 +386,8 @@ extern void call_depth_return_thunk(void);
 		    __stringify(INCREMENT_CALL_DEPTH),		\
 		    X86_FEATURE_CALL_DEPTH)
 
+DECLARE_PER_CPU_CACHE_HOT(u64, __x86_call_depth);
+
 #ifdef CONFIG_CALL_THUNKS_DEBUG
 DECLARE_PER_CPU(u64, __x86_call_count);
 DECLARE_PER_CPU(u64, __x86_ret_count);
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index a98020bf31bb4..6fae88f8ae1e7 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -109,9 +109,6 @@ static void __used common(void)
 	OFFSET(TSS_sp2, tss_struct, x86_tss.sp2);
 	OFFSET(X86_top_of_stack, pcpu_hot, top_of_stack);
 	OFFSET(X86_current_task, pcpu_hot, current_task);
-#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING
-	OFFSET(X86_call_depth, pcpu_hot, call_depth);
-#endif
 #if IS_ENABLED(CONFIG_CRYPTO_ARIA_AESNI_AVX_X86_64)
 	/* Offset for fields in aria_ctx */
 	BLANK();
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index a9d61537d4a64..fd224ae57d62e 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -2075,6 +2075,14 @@ DEFINE_PER_CPU_CACHE_HOT(int, __preempt_count) = INIT_PREEMPT_COUNT;
 EXPORT_PER_CPU_SYMBOL(__preempt_count);
 
 #ifdef CONFIG_X86_64
+/*
+ * Note: Do not make this dependant on CONFIG_MITIGATION_CALL_DEPTH_TRACKING
+ * so that this space is reserved in the hot cache section even when the
+ * mitigation is disabled.
+ */
+DEFINE_PER_CPU_CACHE_HOT(u64, __x86_call_depth);
+EXPORT_PER_CPU_SYMBOL(__x86_call_depth);
+
 static void wrmsrl_cstar(unsigned long val)
 {
 	/*
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index 038f49a43ab43..a26c43abd47d8 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -343,7 +343,7 @@ SYM_FUNC_START(call_depth_return_thunk)
 	 * case.
 	 */
 	CALL_THUNKS_DEBUG_INC_RETS
-	shlq	$5, PER_CPU_VAR(pcpu_hot + X86_call_depth)
+	shlq	$5, PER_CPU_VAR(__x86_call_depth)
 	jz	1f
 	ANNOTATE_UNRET_SAFE
 	ret

From c8f1ac2bd7771a3bc536f897c142ca219cac13e1 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Mon, 3 Mar 2025 11:52:41 -0500
Subject: [PATCH 0939/1173] x86/softirq: Move softirq_pending to percpu hot
 section

No functional change.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250303165246.2175811-7-brgerst@gmail.com
---
 arch/x86/include/asm/current.h | 1 -
 arch/x86/include/asm/hardirq.h | 4 ++--
 arch/x86/kernel/irq.c          | 3 +++
 3 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h
index 8ba2c0f8bcaf9..f153c77853de1 100644
--- a/arch/x86/include/asm/current.h
+++ b/arch/x86/include/asm/current.h
@@ -16,7 +16,6 @@ struct pcpu_hot {
 	struct task_struct	*current_task;
 	unsigned long		top_of_stack;
 	void			*hardirq_stack_ptr;
-	u16			softirq_pending;
 #ifdef CONFIG_X86_64
 	bool			hardirq_stack_inuse;
 #else
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 6ffa8b75f4cd3..f00c09ffe6a95 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -3,7 +3,6 @@
 #define _ASM_X86_HARDIRQ_H
 
 #include <linux/threads.h>
-#include <asm/current.h>
 
 typedef struct {
 #if IS_ENABLED(CONFIG_KVM_INTEL)
@@ -66,7 +65,8 @@ extern u64 arch_irq_stat_cpu(unsigned int cpu);
 extern u64 arch_irq_stat(void);
 #define arch_irq_stat		arch_irq_stat
 
-#define local_softirq_pending_ref       pcpu_hot.softirq_pending
+DECLARE_PER_CPU_CACHE_HOT(u16, __softirq_pending);
+#define local_softirq_pending_ref       __softirq_pending
 
 #if IS_ENABLED(CONFIG_KVM_INTEL)
 /*
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index feca4f20b06aa..83a5252a473c3 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -33,6 +33,9 @@
 DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
 EXPORT_PER_CPU_SYMBOL(irq_stat);
 
+DEFINE_PER_CPU_CACHE_HOT(u16, __softirq_pending);
+EXPORT_PER_CPU_SYMBOL(__softirq_pending);
+
 atomic_t irq_err_count;
 
 /*

From c6a0918072eaa97df268c00c05822ea982a321b6 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Mon, 3 Mar 2025 11:52:42 -0500
Subject: [PATCH 0940/1173] x86/irq: Move irq stacks to percpu hot section

No functional change.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250303165246.2175811-8-brgerst@gmail.com
---
 arch/x86/include/asm/current.h   |  6 ------
 arch/x86/include/asm/irq_stack.h | 12 ++++++------
 arch/x86/include/asm/processor.h |  7 +++++++
 arch/x86/kernel/dumpstack_32.c   |  4 ++--
 arch/x86/kernel/dumpstack_64.c   |  2 +-
 arch/x86/kernel/irq.c            |  2 ++
 arch/x86/kernel/irq_32.c         | 12 +++++++-----
 arch/x86/kernel/irq_64.c         |  7 ++++---
 arch/x86/kernel/process_64.c     |  2 +-
 9 files changed, 30 insertions(+), 24 deletions(-)

diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h
index f153c77853de1..6fad5a4c21d7c 100644
--- a/arch/x86/include/asm/current.h
+++ b/arch/x86/include/asm/current.h
@@ -15,12 +15,6 @@ struct task_struct;
 struct pcpu_hot {
 	struct task_struct	*current_task;
 	unsigned long		top_of_stack;
-	void			*hardirq_stack_ptr;
-#ifdef CONFIG_X86_64
-	bool			hardirq_stack_inuse;
-#else
-	void			*softirq_stack_ptr;
-#endif
 };
 
 DECLARE_PER_CPU_CACHE_HOT(struct pcpu_hot, pcpu_hot);
diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h
index 562a547c29a5b..735c3a491f604 100644
--- a/arch/x86/include/asm/irq_stack.h
+++ b/arch/x86/include/asm/irq_stack.h
@@ -116,7 +116,7 @@
 	ASM_CALL_ARG2
 
 #define call_on_irqstack(func, asm_call, argconstr...)			\
-	call_on_stack(__this_cpu_read(pcpu_hot.hardirq_stack_ptr),	\
+	call_on_stack(__this_cpu_read(hardirq_stack_ptr),		\
 		      func, asm_call, argconstr)
 
 /* Macros to assert type correctness for run_*_on_irqstack macros */
@@ -135,7 +135,7 @@
 	 * User mode entry and interrupt on the irq stack do not	\
 	 * switch stacks. If from user mode the task stack is empty.	\
 	 */								\
-	if (user_mode(regs) || __this_cpu_read(pcpu_hot.hardirq_stack_inuse)) { \
+	if (user_mode(regs) || __this_cpu_read(hardirq_stack_inuse)) {	\
 		irq_enter_rcu();					\
 		func(c_args);						\
 		irq_exit_rcu();						\
@@ -146,9 +146,9 @@
 		 * places. Invoke the stack switch macro with the call	\
 		 * sequence which matches the above direct invocation.	\
 		 */							\
-		__this_cpu_write(pcpu_hot.hardirq_stack_inuse, true);	\
+		__this_cpu_write(hardirq_stack_inuse, true);		\
 		call_on_irqstack(func, asm_call, constr);		\
-		__this_cpu_write(pcpu_hot.hardirq_stack_inuse, false);	\
+		__this_cpu_write(hardirq_stack_inuse, false);		\
 	}								\
 }
 
@@ -212,9 +212,9 @@
  */
 #define do_softirq_own_stack()						\
 {									\
-	__this_cpu_write(pcpu_hot.hardirq_stack_inuse, true);		\
+	__this_cpu_write(hardirq_stack_inuse, true);			\
 	call_on_irqstack(__do_softirq, ASM_CALL_ARG0);			\
-	__this_cpu_write(pcpu_hot.hardirq_stack_inuse, false);		\
+	__this_cpu_write(hardirq_stack_inuse, false);			\
 }
 
 #endif
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index c241dbc1562c2..6bb6af0b54304 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -415,6 +415,13 @@ struct irq_stack {
 	char		stack[IRQ_STACK_SIZE];
 } __aligned(IRQ_STACK_SIZE);
 
+DECLARE_PER_CPU_CACHE_HOT(struct irq_stack *, hardirq_stack_ptr);
+#ifdef CONFIG_X86_64
+DECLARE_PER_CPU_CACHE_HOT(bool, hardirq_stack_inuse);
+#else
+DECLARE_PER_CPU_CACHE_HOT(struct irq_stack *, softirq_stack_ptr);
+#endif
+
 #ifdef CONFIG_X86_64
 static inline unsigned long cpu_kernelmode_gs_base(int cpu)
 {
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index b4905d5173fd3..722fd712e1cf0 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -37,7 +37,7 @@ const char *stack_type_name(enum stack_type type)
 
 static bool in_hardirq_stack(unsigned long *stack, struct stack_info *info)
 {
-	unsigned long *begin = (unsigned long *)this_cpu_read(pcpu_hot.hardirq_stack_ptr);
+	unsigned long *begin = (unsigned long *)this_cpu_read(hardirq_stack_ptr);
 	unsigned long *end   = begin + (THREAD_SIZE / sizeof(long));
 
 	/*
@@ -62,7 +62,7 @@ static bool in_hardirq_stack(unsigned long *stack, struct stack_info *info)
 
 static bool in_softirq_stack(unsigned long *stack, struct stack_info *info)
 {
-	unsigned long *begin = (unsigned long *)this_cpu_read(pcpu_hot.softirq_stack_ptr);
+	unsigned long *begin = (unsigned long *)this_cpu_read(softirq_stack_ptr);
 	unsigned long *end   = begin + (THREAD_SIZE / sizeof(long));
 
 	/*
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index f05339fee7785..6c5defd6569a3 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -134,7 +134,7 @@ static __always_inline bool in_exception_stack(unsigned long *stack, struct stac
 
 static __always_inline bool in_irq_stack(unsigned long *stack, struct stack_info *info)
 {
-	unsigned long *end = (unsigned long *)this_cpu_read(pcpu_hot.hardirq_stack_ptr);
+	unsigned long *end = (unsigned long *)this_cpu_read(hardirq_stack_ptr);
 	unsigned long *begin;
 
 	/*
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 83a5252a473c3..81f9b78e0f7ba 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -36,6 +36,8 @@ EXPORT_PER_CPU_SYMBOL(irq_stat);
 DEFINE_PER_CPU_CACHE_HOT(u16, __softirq_pending);
 EXPORT_PER_CPU_SYMBOL(__softirq_pending);
 
+DEFINE_PER_CPU_CACHE_HOT(struct irq_stack *, hardirq_stack_ptr);
+
 atomic_t irq_err_count;
 
 /*
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index d301208d35d02..c7a5d2960d575 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -49,6 +49,8 @@ static inline bool check_stack_overflow(void) { return false; }
 static inline void print_stack_overflow(void) { }
 #endif
 
+DEFINE_PER_CPU_CACHE_HOT(struct irq_stack *, softirq_stack_ptr);
+
 static void call_on_stack(void *func, void *stack)
 {
 	asm volatile("xchgl %[sp], %%esp\n"
@@ -70,7 +72,7 @@ static inline bool execute_on_irq_stack(bool overflow, struct irq_desc *desc)
 	u32 *isp, *prev_esp;
 
 	curstk = (struct irq_stack *) current_stack();
-	irqstk = __this_cpu_read(pcpu_hot.hardirq_stack_ptr);
+	irqstk = __this_cpu_read(hardirq_stack_ptr);
 
 	/*
 	 * this is where we switch to the IRQ stack. However, if we are
@@ -107,7 +109,7 @@ int irq_init_percpu_irqstack(unsigned int cpu)
 	int node = cpu_to_node(cpu);
 	struct page *ph, *ps;
 
-	if (per_cpu(pcpu_hot.hardirq_stack_ptr, cpu))
+	if (per_cpu(hardirq_stack_ptr, cpu))
 		return 0;
 
 	ph = alloc_pages_node(node, THREADINFO_GFP, THREAD_SIZE_ORDER);
@@ -119,8 +121,8 @@ int irq_init_percpu_irqstack(unsigned int cpu)
 		return -ENOMEM;
 	}
 
-	per_cpu(pcpu_hot.hardirq_stack_ptr, cpu) = page_address(ph);
-	per_cpu(pcpu_hot.softirq_stack_ptr, cpu) = page_address(ps);
+	per_cpu(hardirq_stack_ptr, cpu) = page_address(ph);
+	per_cpu(softirq_stack_ptr, cpu) = page_address(ps);
 	return 0;
 }
 
@@ -130,7 +132,7 @@ void do_softirq_own_stack(void)
 	struct irq_stack *irqstk;
 	u32 *isp, *prev_esp;
 
-	irqstk = __this_cpu_read(pcpu_hot.softirq_stack_ptr);
+	irqstk = __this_cpu_read(softirq_stack_ptr);
 
 	/* build the stack frame on the softirq stack */
 	isp = (u32 *) ((char *)irqstk + sizeof(*irqstk));
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 56bdeecd8ee02..ca78dce39361f 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -26,6 +26,7 @@
 #include <asm/io_apic.h>
 #include <asm/apic.h>
 
+DEFINE_PER_CPU_CACHE_HOT(bool, hardirq_stack_inuse);
 DEFINE_PER_CPU_PAGE_ALIGNED(struct irq_stack, irq_stack_backing_store) __visible;
 
 #ifdef CONFIG_VMAP_STACK
@@ -50,7 +51,7 @@ static int map_irq_stack(unsigned int cpu)
 		return -ENOMEM;
 
 	/* Store actual TOS to avoid adjustment in the hotpath */
-	per_cpu(pcpu_hot.hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE - 8;
+	per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE - 8;
 	return 0;
 }
 #else
@@ -63,14 +64,14 @@ static int map_irq_stack(unsigned int cpu)
 	void *va = per_cpu_ptr(&irq_stack_backing_store, cpu);
 
 	/* Store actual TOS to avoid adjustment in the hotpath */
-	per_cpu(pcpu_hot.hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE - 8;
+	per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE - 8;
 	return 0;
 }
 #endif
 
 int irq_init_percpu_irqstack(unsigned int cpu)
 {
-	if (per_cpu(pcpu_hot.hardirq_stack_ptr, cpu))
+	if (per_cpu(hardirq_stack_ptr, cpu))
 		return 0;
 	return map_irq_stack(cpu);
 }
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index f983d2a57ac3c..2f38416deb746 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -614,7 +614,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	int cpu = smp_processor_id();
 
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) &&
-		     this_cpu_read(pcpu_hot.hardirq_stack_inuse));
+		     this_cpu_read(hardirq_stack_inuse));
 
 	if (!test_tsk_thread_flag(prev_p, TIF_NEED_FPU_LOAD))
 		switch_fpu_prepare(prev_p, cpu);

From 385f72c83eb609652f02dc9ee415520c23bda629 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Mon, 3 Mar 2025 11:52:43 -0500
Subject: [PATCH 0941/1173] x86/percpu: Move top_of_stack to percpu hot section

No functional change.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250303165246.2175811-9-brgerst@gmail.com
---
 arch/x86/entry/entry_32.S        | 4 ++--
 arch/x86/entry/entry_64.S        | 6 +++---
 arch/x86/entry/entry_64_compat.S | 4 ++--
 arch/x86/include/asm/current.h   | 1 -
 arch/x86/include/asm/percpu.h    | 2 +-
 arch/x86/include/asm/processor.h | 9 +++++++--
 arch/x86/kernel/asm-offsets.c    | 1 -
 arch/x86/kernel/cpu/common.c     | 3 ++-
 arch/x86/kernel/process_32.c     | 4 ++--
 arch/x86/kernel/process_64.c     | 2 +-
 arch/x86/kernel/smpboot.c        | 2 +-
 arch/x86/kernel/vmlinux.lds.S    | 1 +
 12 files changed, 22 insertions(+), 17 deletions(-)

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 20be5758c2d2e..92c0b4a94e0ad 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -1153,7 +1153,7 @@ SYM_CODE_START(asm_exc_nmi)
 	 * is using the thread stack right now, so it's safe for us to use it.
 	 */
 	movl	%esp, %ebx
-	movl	PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %esp
+	movl	PER_CPU_VAR(cpu_current_top_of_stack), %esp
 	call	exc_nmi
 	movl	%ebx, %esp
 
@@ -1217,7 +1217,7 @@ SYM_CODE_START(rewind_stack_and_make_dead)
 	/* Prevent any naive code from trying to unwind to our caller. */
 	xorl	%ebp, %ebp
 
-	movl	PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %esi
+	movl	PER_CPU_VAR(cpu_current_top_of_stack), %esi
 	leal	-TOP_OF_KERNEL_STACK_PADDING-PTREGS_SIZE(%esi), %esp
 
 	call	make_task_dead
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 49d3b222fe99d..f40bdf97d390a 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -92,7 +92,7 @@ SYM_CODE_START(entry_SYSCALL_64)
 	/* tss.sp2 is scratch space. */
 	movq	%rsp, PER_CPU_VAR(cpu_tss_rw + TSS_sp2)
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
-	movq	PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rsp
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
 SYM_INNER_LABEL(entry_SYSCALL_64_safe_stack, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
@@ -1168,7 +1168,7 @@ SYM_CODE_START(asm_exc_nmi)
 	FENCE_SWAPGS_USER_ENTRY
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdx
 	movq	%rsp, %rdx
-	movq	PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rsp
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 	UNWIND_HINT_IRET_REGS base=%rdx offset=8
 	pushq	5*8(%rdx)	/* pt_regs->ss */
 	pushq	4*8(%rdx)	/* pt_regs->rsp */
@@ -1486,7 +1486,7 @@ SYM_CODE_START_NOALIGN(rewind_stack_and_make_dead)
 	/* Prevent any naive code from trying to unwind to our caller. */
 	xorl	%ebp, %ebp
 
-	movq	PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rax
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rax
 	leaq	-PTREGS_SIZE(%rax), %rsp
 	UNWIND_HINT_REGS
 
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index ed0a5f2dc1297..a45e1125fc6cf 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -57,7 +57,7 @@ SYM_CODE_START(entry_SYSENTER_compat)
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
 	popq	%rax
 
-	movq	PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rsp
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
 	/* Construct struct pt_regs on stack */
 	pushq	$__USER_DS		/* pt_regs->ss */
@@ -193,7 +193,7 @@ SYM_CODE_START(entry_SYSCALL_compat)
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
 
 	/* Switch to the kernel stack */
-	movq	PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rsp
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
 SYM_INNER_LABEL(entry_SYSCALL_compat_safe_stack, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h
index 6fad5a4c21d7c..3d1b123c2ee32 100644
--- a/arch/x86/include/asm/current.h
+++ b/arch/x86/include/asm/current.h
@@ -14,7 +14,6 @@ struct task_struct;
 
 struct pcpu_hot {
 	struct task_struct	*current_task;
-	unsigned long		top_of_stack;
 };
 
 DECLARE_PER_CPU_CACHE_HOT(struct pcpu_hot, pcpu_hot);
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 8a8cf86dded32..41517a7f7f1c5 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -551,7 +551,7 @@ do {									\
  * it is accessed while this_cpu_read_stable() allows the value to be cached.
  * this_cpu_read_stable() is more efficient and can be used if its value
  * is guaranteed to be valid across CPUs.  The current users include
- * pcpu_hot.current_task and pcpu_hot.top_of_stack, both of which are
+ * pcpu_hot.current_task and cpu_current_top_of_stack, both of which are
  * actually per-thread variables implemented as per-CPU variables and
  * thus stable for the duration of the respective task.
  */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 6bb6af0b54304..7a3918308a367 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -422,6 +422,11 @@ DECLARE_PER_CPU_CACHE_HOT(bool, hardirq_stack_inuse);
 DECLARE_PER_CPU_CACHE_HOT(struct irq_stack *, softirq_stack_ptr);
 #endif
 
+DECLARE_PER_CPU_CACHE_HOT(unsigned long, cpu_current_top_of_stack);
+/* const-qualified alias provided by the linker. */
+DECLARE_PER_CPU_CACHE_HOT(const unsigned long __percpu_seg_override,
+			  const_cpu_current_top_of_stack);
+
 #ifdef CONFIG_X86_64
 static inline unsigned long cpu_kernelmode_gs_base(int cpu)
 {
@@ -547,9 +552,9 @@ static __always_inline unsigned long current_top_of_stack(void)
 	 *  entry trampoline.
 	 */
 	if (IS_ENABLED(CONFIG_USE_X86_SEG_SUPPORT))
-		return this_cpu_read_const(const_pcpu_hot.top_of_stack);
+		return this_cpu_read_const(const_cpu_current_top_of_stack);
 
-	return this_cpu_read_stable(pcpu_hot.top_of_stack);
+	return this_cpu_read_stable(cpu_current_top_of_stack);
 }
 
 static __always_inline bool on_thread_stack(void)
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 6fae88f8ae1e7..54ace808defd2 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -107,7 +107,6 @@ static void __used common(void)
 	OFFSET(TSS_sp0, tss_struct, x86_tss.sp0);
 	OFFSET(TSS_sp1, tss_struct, x86_tss.sp1);
 	OFFSET(TSS_sp2, tss_struct, x86_tss.sp2);
-	OFFSET(X86_top_of_stack, pcpu_hot, top_of_stack);
 	OFFSET(X86_current_task, pcpu_hot, current_task);
 #if IS_ENABLED(CONFIG_CRYPTO_ARIA_AESNI_AVX_X86_64)
 	/* Offset for fields in aria_ctx */
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index fd224ae57d62e..51653e01a7161 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -2066,7 +2066,6 @@ __setup("setcpuid=", setup_setcpuid);
 
 DEFINE_PER_CPU_CACHE_HOT(struct pcpu_hot, pcpu_hot) = {
 	.current_task	= &init_task,
-	.top_of_stack	= TOP_OF_INIT_STACK,
 };
 EXPORT_PER_CPU_SYMBOL(pcpu_hot);
 EXPORT_PER_CPU_SYMBOL(const_pcpu_hot);
@@ -2074,6 +2073,8 @@ EXPORT_PER_CPU_SYMBOL(const_pcpu_hot);
 DEFINE_PER_CPU_CACHE_HOT(int, __preempt_count) = INIT_PREEMPT_COUNT;
 EXPORT_PER_CPU_SYMBOL(__preempt_count);
 
+DEFINE_PER_CPU_CACHE_HOT(unsigned long, cpu_current_top_of_stack) = TOP_OF_INIT_STACK;
+
 #ifdef CONFIG_X86_64
 /*
  * Note: Do not make this dependant on CONFIG_MITIGATION_CALL_DEPTH_TRACKING
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 2bdab416298ce..8ec44acb863be 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -190,13 +190,13 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	arch_end_context_switch(next_p);
 
 	/*
-	 * Reload esp0 and pcpu_hot.top_of_stack.  This changes
+	 * Reload esp0 and cpu_current_top_of_stack.  This changes
 	 * current_thread_info().  Refresh the SYSENTER configuration in
 	 * case prev or next is vm86.
 	 */
 	update_task_stack(next_p);
 	refresh_sysenter_cs(next);
-	this_cpu_write(pcpu_hot.top_of_stack,
+	this_cpu_write(cpu_current_top_of_stack,
 		       (unsigned long)task_stack_page(next_p) +
 		       THREAD_SIZE);
 
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 2f38416deb746..d8f4bcef8ee4a 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -669,7 +669,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	 * Switch the PDA and FPU contexts.
 	 */
 	raw_cpu_write(pcpu_hot.current_task, next_p);
-	raw_cpu_write(pcpu_hot.top_of_stack, task_top_of_stack(next_p));
+	raw_cpu_write(cpu_current_top_of_stack, task_top_of_stack(next_p));
 
 	switch_fpu_finish(next_p);
 
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index c5aabddf55734..c3a26e60e3c40 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -832,7 +832,7 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle)
 
 #ifdef CONFIG_X86_32
 	/* Stack for startup_32 can be just as for start_secondary onwards */
-	per_cpu(pcpu_hot.top_of_stack, cpu) = task_top_of_stack(idle);
+	per_cpu(cpu_current_top_of_stack, cpu) = task_top_of_stack(idle);
 #endif
 	return 0;
 }
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 0ef9870ea52ec..475f6717f27ad 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -44,6 +44,7 @@ ENTRY(phys_startup_64)
 
 jiffies = jiffies_64;
 const_pcpu_hot = pcpu_hot;
+const_cpu_current_top_of_stack = cpu_current_top_of_stack;
 
 #if defined(CONFIG_X86_64)
 /*

From a1e4cc0155ad577adc3a2c563fc5eec625945ce7 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Mon, 3 Mar 2025 11:52:44 -0500
Subject: [PATCH 0942/1173] x86/percpu: Move current_task to percpu hot section

No functional change.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250303165246.2175811-10-brgerst@gmail.com
---
 arch/x86/include/asm/current.h | 17 ++++++-----------
 arch/x86/include/asm/percpu.h  |  2 +-
 arch/x86/kernel/asm-offsets.c  |  1 -
 arch/x86/kernel/cpu/common.c   |  8 +++-----
 arch/x86/kernel/head_64.S      |  4 ++--
 arch/x86/kernel/process_32.c   |  2 +-
 arch/x86/kernel/process_64.c   |  2 +-
 arch/x86/kernel/smpboot.c      |  2 +-
 arch/x86/kernel/vmlinux.lds.S  |  2 +-
 scripts/gdb/linux/cpus.py      |  2 +-
 10 files changed, 17 insertions(+), 25 deletions(-)

diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h
index 3d1b123c2ee32..dea7d8b854f0e 100644
--- a/arch/x86/include/asm/current.h
+++ b/arch/x86/include/asm/current.h
@@ -12,22 +12,17 @@
 
 struct task_struct;
 
-struct pcpu_hot {
-	struct task_struct	*current_task;
-};
-
-DECLARE_PER_CPU_CACHE_HOT(struct pcpu_hot, pcpu_hot);
-
-/* const-qualified alias to pcpu_hot, aliased by linker. */
-DECLARE_PER_CPU_CACHE_HOT(const struct pcpu_hot __percpu_seg_override,
-			const_pcpu_hot);
+DECLARE_PER_CPU_CACHE_HOT(struct task_struct *, current_task);
+/* const-qualified alias provided by the linker. */
+DECLARE_PER_CPU_CACHE_HOT(struct task_struct * const __percpu_seg_override,
+			  const_current_task);
 
 static __always_inline struct task_struct *get_current(void)
 {
 	if (IS_ENABLED(CONFIG_USE_X86_SEG_SUPPORT))
-		return this_cpu_read_const(const_pcpu_hot.current_task);
+		return this_cpu_read_const(const_current_task);
 
-	return this_cpu_read_stable(pcpu_hot.current_task);
+	return this_cpu_read_stable(current_task);
 }
 
 #define current get_current()
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 41517a7f7f1c5..8cc9548205b00 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -551,7 +551,7 @@ do {									\
  * it is accessed while this_cpu_read_stable() allows the value to be cached.
  * this_cpu_read_stable() is more efficient and can be used if its value
  * is guaranteed to be valid across CPUs.  The current users include
- * pcpu_hot.current_task and cpu_current_top_of_stack, both of which are
+ * current_task and cpu_current_top_of_stack, both of which are
  * actually per-thread variables implemented as per-CPU variables and
  * thus stable for the duration of the respective task.
  */
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 54ace808defd2..ad4ea6fb3b6cb 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -107,7 +107,6 @@ static void __used common(void)
 	OFFSET(TSS_sp0, tss_struct, x86_tss.sp0);
 	OFFSET(TSS_sp1, tss_struct, x86_tss.sp1);
 	OFFSET(TSS_sp2, tss_struct, x86_tss.sp2);
-	OFFSET(X86_current_task, pcpu_hot, current_task);
 #if IS_ENABLED(CONFIG_CRYPTO_ARIA_AESNI_AVX_X86_64)
 	/* Offset for fields in aria_ctx */
 	BLANK();
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 51653e01a7161..3f45fdd48bdb9 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -2064,11 +2064,9 @@ static __init int setup_setcpuid(char *arg)
 }
 __setup("setcpuid=", setup_setcpuid);
 
-DEFINE_PER_CPU_CACHE_HOT(struct pcpu_hot, pcpu_hot) = {
-	.current_task	= &init_task,
-};
-EXPORT_PER_CPU_SYMBOL(pcpu_hot);
-EXPORT_PER_CPU_SYMBOL(const_pcpu_hot);
+DEFINE_PER_CPU_CACHE_HOT(struct task_struct *, current_task) = &init_task;
+EXPORT_PER_CPU_SYMBOL(current_task);
+EXPORT_PER_CPU_SYMBOL(const_current_task);
 
 DEFINE_PER_CPU_CACHE_HOT(int, __preempt_count) = INIT_PREEMPT_COUNT;
 EXPORT_PER_CPU_SYMBOL(__preempt_count);
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 2843b0a56198d..fefe2a25cf025 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -322,7 +322,7 @@ SYM_INNER_LABEL(common_startup_64, SYM_L_LOCAL)
 	 *
 	 * RDX contains the per-cpu offset
 	 */
-	movq	pcpu_hot + X86_current_task(%rdx), %rax
+	movq	current_task(%rdx), %rax
 	movq	TASK_threadsp(%rax), %rsp
 
 	/*
@@ -433,7 +433,7 @@ SYM_CODE_START(soft_restart_cpu)
 	UNWIND_HINT_END_OF_STACK
 
 	/* Find the idle task stack */
-	movq	PER_CPU_VAR(pcpu_hot + X86_current_task), %rcx
+	movq	PER_CPU_VAR(current_task), %rcx
 	movq	TASK_threadsp(%rcx), %rsp
 
 	jmp	.Ljump_to_C_code
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 8ec44acb863be..4636ef3599737 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -206,7 +206,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	if (prev->gs | next->gs)
 		loadsegment(gs, next->gs);
 
-	raw_cpu_write(pcpu_hot.current_task, next_p);
+	raw_cpu_write(current_task, next_p);
 
 	switch_fpu_finish(next_p);
 
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index d8f4bcef8ee4a..7196ca7048be0 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -668,7 +668,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	/*
 	 * Switch the PDA and FPU contexts.
 	 */
-	raw_cpu_write(pcpu_hot.current_task, next_p);
+	raw_cpu_write(current_task, next_p);
 	raw_cpu_write(cpu_current_top_of_stack, task_top_of_stack(next_p));
 
 	switch_fpu_finish(next_p);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index c3a26e60e3c40..42ca131bebbc3 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -822,7 +822,7 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle)
 	/* Just in case we booted with a single CPU. */
 	alternatives_enable_smp();
 
-	per_cpu(pcpu_hot.current_task, cpu) = idle;
+	per_cpu(current_task, cpu) = idle;
 	cpu_init_stack_canary(cpu, idle);
 
 	/* Initialize the interrupt stack(s) */
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 475f6717f27ad..31f9102b107f1 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -43,7 +43,7 @@ ENTRY(phys_startup_64)
 #endif
 
 jiffies = jiffies_64;
-const_pcpu_hot = pcpu_hot;
+const_current_task = current_task;
 const_cpu_current_top_of_stack = cpu_current_top_of_stack;
 
 #if defined(CONFIG_X86_64)
diff --git a/scripts/gdb/linux/cpus.py b/scripts/gdb/linux/cpus.py
index 13eb8b3901b8f..8f7c4fb78c2cc 100644
--- a/scripts/gdb/linux/cpus.py
+++ b/scripts/gdb/linux/cpus.py
@@ -164,7 +164,7 @@ def get_current_task(cpu):
             var_ptr = gdb.parse_and_eval("(struct task_struct *)cpu_tasks[0].task")
             return var_ptr.dereference()
         else:
-            var_ptr = gdb.parse_and_eval("&pcpu_hot.current_task")
+            var_ptr = gdb.parse_and_eval("&current_task")
             return per_cpu(var_ptr, cpu).dereference()
     elif utils.is_target_arch("aarch64"):
         current_task_addr = gdb.parse_and_eval("(unsigned long)$SP_EL0")

From f3856cd343b6371530c9af3c97354cdc003f3203 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Mon, 3 Mar 2025 11:52:45 -0500
Subject: [PATCH 0943/1173] x86/stackprotector: Move __stack_chk_guard to
 percpu hot section

No functional change.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250303165246.2175811-11-brgerst@gmail.com
---
 arch/x86/include/asm/stackprotector.h | 2 +-
 arch/x86/kernel/cpu/common.c          | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index d43fb589fcf66..cd761b14eb029 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/arch/x86/include/asm/stackprotector.h
@@ -20,7 +20,7 @@
 
 #include <linux/sched.h>
 
-DECLARE_PER_CPU(unsigned long, __stack_chk_guard);
+DECLARE_PER_CPU_CACHE_HOT(unsigned long, __stack_chk_guard);
 
 /*
  * Initialize the stackprotector canary value.
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 3f45fdd48bdb9..5809534ecc983 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -2147,7 +2147,7 @@ void syscall_init(void)
 #endif /* CONFIG_X86_64 */
 
 #ifdef CONFIG_STACKPROTECTOR
-DEFINE_PER_CPU(unsigned long, __stack_chk_guard);
+DEFINE_PER_CPU_CACHE_HOT(unsigned long, __stack_chk_guard);
 #ifndef CONFIG_SMP
 EXPORT_PER_CPU_SYMBOL(__stack_chk_guard);
 #endif

From 06aa03056f90a67ce6e6b78c748801319904215c Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Mon, 3 Mar 2025 11:52:46 -0500
Subject: [PATCH 0944/1173] x86/smp: Move this_cpu_off to percpu hot section

No functional change.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250303165246.2175811-12-brgerst@gmail.com
---
 arch/x86/include/asm/percpu.h  | 2 +-
 arch/x86/kernel/setup_percpu.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 8cc9548205b00..462d071c87d46 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -586,7 +586,7 @@ do {									\
 #include <asm-generic/percpu.h>
 
 /* We can use this directly for local CPU (faster). */
-DECLARE_PER_CPU_READ_MOSTLY(unsigned long, this_cpu_off);
+DECLARE_PER_CPU_CACHE_HOT(unsigned long, this_cpu_off);
 
 #endif /* !__ASSEMBLY__ */
 
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 175afc3ffb128..bfa48e7a32a24 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -26,7 +26,7 @@
 DEFINE_PER_CPU_CACHE_HOT(int, cpu_number);
 EXPORT_PER_CPU_SYMBOL(cpu_number);
 
-DEFINE_PER_CPU_READ_MOSTLY(unsigned long, this_cpu_off);
+DEFINE_PER_CPU_CACHE_HOT(unsigned long, this_cpu_off);
 EXPORT_PER_CPU_SYMBOL(this_cpu_off);
 
 unsigned long __per_cpu_offset[NR_CPUS] __ro_after_init;

From 6d536cad0d55e71442b6d65500f74eb85544269e Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Tue, 4 Mar 2025 18:34:36 +0100
Subject: [PATCH 0945/1173] x86/percpu: Fix __per_cpu_hot_end marker

Make __per_cpu_hot_end marker point to the end of the percpu cache
hot data, not to the end of the percpu cache hot section.

This fixes CONFIG_MPENTIUM4 case where X86_L1_CACHE_SHIFT
is set to 7 (128 bytes).

Also update assert message accordingly.

Reported-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Brian Gerst <brgerst@gmail.com>
Link: https://lore.kernel.org/r/20250304173455.89361-1-ubizjak@gmail.com

Closes: https://lore.kernel.org/lkml/Z8a-NVJs-pm5W-mG@gmail.com/
---
 arch/x86/kernel/vmlinux.lds.S     | 2 +-
 include/asm-generic/vmlinux.lds.h | 3 +--
 2 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 31f9102b107f1..ccdc45e5b7596 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -331,7 +331,7 @@ SECTIONS
 	}
 
 	PERCPU_SECTION(L1_CACHE_BYTES)
-	ASSERT(__per_cpu_hot_end - __per_cpu_hot_start <= 64, "percpu cache hot section too large")
+	ASSERT(__per_cpu_hot_end - __per_cpu_hot_start <= 64, "percpu cache hot data too large")
 
 	RUNTIME_CONST_VARIABLES
 	RUNTIME_CONST(ptr, USER_PTR_MAX)
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index c4e8fac502543..4925441bc4714 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -1072,9 +1072,8 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
 	. = ALIGN(cacheline);						\
 	__per_cpu_hot_start = .;					\
 	*(SORT_BY_ALIGNMENT(.data..percpu..hot.*))			\
-	__per_cpu_hot_pad = .;						\
-	. = ALIGN(cacheline);						\
 	__per_cpu_hot_end = .;						\
+	. = ALIGN(cacheline);						\
 	*(.data..percpu..read_mostly)					\
 	. = ALIGN(cacheline);						\
 	*(.data..percpu)						\

From 30bfc151f0c1ec80c27a80a7651b2c15c648ad16 Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst <dev@lankhorst.se>
Date: Tue, 10 Dec 2024 09:31:02 +0100
Subject: [PATCH 0946/1173] drm/xe: Remove double pageflip
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This is already handled below in the code by fixup_initial_plane_config.

Fixes: a8153627520a ("drm/i915: Try to relocate the BIOS fb to the start of ggtt")
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Vinod Govindapillai <vinod.govindapillai@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241210083111.230484-3-dev@lankhorst.se
Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
(cherry picked from commit 2218704997979fbf11765281ef752f07c5cf25bb)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/display/xe_plane_initial.c | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/drivers/gpu/drm/xe/display/xe_plane_initial.c b/drivers/gpu/drm/xe/display/xe_plane_initial.c
index 2eb9633f163a7..2a2f250fa495d 100644
--- a/drivers/gpu/drm/xe/display/xe_plane_initial.c
+++ b/drivers/gpu/drm/xe/display/xe_plane_initial.c
@@ -194,8 +194,6 @@ intel_find_initial_plane_obj(struct intel_crtc *crtc,
 		to_intel_plane(crtc->base.primary);
 	struct intel_plane_state *plane_state =
 		to_intel_plane_state(plane->base.state);
-	struct intel_crtc_state *crtc_state =
-		to_intel_crtc_state(crtc->base.state);
 	struct drm_framebuffer *fb;
 	struct i915_vma *vma;
 
@@ -241,14 +239,6 @@ intel_find_initial_plane_obj(struct intel_crtc *crtc,
 	atomic_or(plane->frontbuffer_bit, &to_intel_frontbuffer(fb)->bits);
 
 	plane_config->vma = vma;
-
-	/*
-	 * Flip to the newly created mapping ASAP, so we can re-use the
-	 * first part of GGTT for WOPCM, prevent flickering, and prevent
-	 * the lookup of sysmem scratch pages.
-	 */
-	plane->check_plane(crtc_state, plane_state);
-	plane->async_flip(NULL, plane, crtc_state, plane_state, true);
 	return;
 
 nofb:

From d1039a3c12fffe501c5379c7eb1372eaab318e0a Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Wed, 26 Feb 2025 15:56:26 +0200
Subject: [PATCH 0947/1173] drm/i915/mst: update max stream count to match
 number of pipes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We create the stream encoders and attach connectors for each pipe we
have. As the number of pipes has increased, we've failed to update the
topology manager maximum number of payloads to match that. Bump up the
max stream count to match number of pipes, enabling the fourth stream on
platforms that support four pipes.

Cc: stable@vger.kernel.org
Cc: Imre Deak <imre.deak@intel.com>
Cc: Ville Syrjala <ville.syrjala@linux.intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250226135626.1956012-1-jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
(cherry picked from commit 15bccbfb78d63a2a621b30caff8b9424160c6c89)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/display/intel_dp_mst.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index a65cf97ad12df..86d6185fda50a 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -1867,7 +1867,8 @@ intel_dp_mst_encoder_init(struct intel_digital_port *dig_port, int conn_base_id)
 	/* create encoders */
 	mst_stream_encoders_create(dig_port);
 	ret = drm_dp_mst_topology_mgr_init(&intel_dp->mst_mgr, display->drm,
-					   &intel_dp->aux, 16, 3, conn_base_id);
+					   &intel_dp->aux, 16,
+					   INTEL_NUM_PIPES(display), conn_base_id);
 	if (ret) {
 		intel_dp->mst_mgr.cbs = NULL;
 		return ret;

From 475d06e00b7496c7915d87f7ae67af26738e4649 Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Wed, 26 Feb 2025 17:47:49 +0000
Subject: [PATCH 0948/1173] drm/xe/userptr: properly setup pfn_flags_mask
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently we just leave it uninitialised, which at first looks harmless,
however we also don't zero out the pfn array, and with pfn_flags_mask
the idea is to be able set individual flags for a given range of pfn or
completely ignore them, outside of default_flags. So here we end up with
pfn[i] & pfn_flags_mask, and if both are uninitialised we might get back
an unexpected flags value, like asking for read only with default_flags,
but getting back write on top, leading to potentially bogus behaviour.

To fix this ensure we zero the pfn_flags_mask, such that hmm only
considers the default_flags and not also the initial pfn[i] value.

v2 (Thomas):
 - Prefer proper initializer.

Fixes: 81e058a3e7fd ("drm/xe: Introduce helper to populate userptr")
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@intel.com>
Cc: <stable@vger.kernel.org> # v6.10+
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Tejas Upadhyay <tejas.upadhyay@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250226174748.294285-2-matthew.auld@intel.com
(cherry picked from commit dd8c01e42f4c5c1eaf02f003d7d588ba6706aa71)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_hmm.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_hmm.c b/drivers/gpu/drm/xe/xe_hmm.c
index 0898344678801..2e4ae61567d8d 100644
--- a/drivers/gpu/drm/xe/xe_hmm.c
+++ b/drivers/gpu/drm/xe/xe_hmm.c
@@ -166,13 +166,20 @@ int xe_hmm_userptr_populate_range(struct xe_userptr_vma *uvma,
 {
 	unsigned long timeout =
 		jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT);
-	unsigned long *pfns, flags = HMM_PFN_REQ_FAULT;
+	unsigned long *pfns;
 	struct xe_userptr *userptr;
 	struct xe_vma *vma = &uvma->vma;
 	u64 userptr_start = xe_vma_userptr(vma);
 	u64 userptr_end = userptr_start + xe_vma_size(vma);
 	struct xe_vm *vm = xe_vma_vm(vma);
-	struct hmm_range hmm_range;
+	struct hmm_range hmm_range = {
+		.pfn_flags_mask = 0, /* ignore pfns */
+		.default_flags = HMM_PFN_REQ_FAULT,
+		.start = userptr_start,
+		.end = userptr_end,
+		.notifier = &uvma->userptr.notifier,
+		.dev_private_owner = vm->xe,
+	};
 	bool write = !xe_vma_read_only(vma);
 	unsigned long notifier_seq;
 	u64 npages;
@@ -199,19 +206,14 @@ int xe_hmm_userptr_populate_range(struct xe_userptr_vma *uvma,
 		return -ENOMEM;
 
 	if (write)
-		flags |= HMM_PFN_REQ_WRITE;
+		hmm_range.default_flags |= HMM_PFN_REQ_WRITE;
 
 	if (!mmget_not_zero(userptr->notifier.mm)) {
 		ret = -EFAULT;
 		goto free_pfns;
 	}
 
-	hmm_range.default_flags = flags;
 	hmm_range.hmm_pfns = pfns;
-	hmm_range.notifier = &userptr->notifier;
-	hmm_range.start = userptr_start;
-	hmm_range.end = userptr_end;
-	hmm_range.dev_private_owner = vm->xe;
 
 	while (true) {
 		hmm_range.notifier_seq = mmu_interval_read_begin(&userptr->notifier);

From 54f94dc7f6b4db45dbc23b4db3d20c7194e2c54f Mon Sep 17 00:00:00 2001
From: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Date: Thu, 27 Feb 2025 10:13:00 +0000
Subject: [PATCH 0949/1173] drm/xe: Fix GT "for each engine" workarounds

Any rules using engine matching are currently broken due RTP processing
happening too in early init, before the list of hardware engines has been
initialised.

Fix this by moving workaround processing to later in the driver probe
sequence, to just before the processed list is used for the first time.

Looking at the debugfs gt0/workarounds on ADL-P we notice 14011060649
should be present while we see, before:

 GT Workarounds
     14011059788
     14015795083

And with the patch:

 GT Workarounds
     14011060649
     14011059788
     14015795083

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: stable@vger.kernel.org # v6.11+
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250227101304.46660-2-tvrtko.ursulin@igalia.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit 25d434cef791e03cf40680f5441b576c639bfa84)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_gt.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index 5d6fb79957b63..9f4f27d1ef4a9 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -380,9 +380,7 @@ int xe_gt_init_early(struct xe_gt *gt)
 	if (err)
 		return err;
 
-	xe_wa_process_gt(gt);
 	xe_wa_process_oob(gt);
-	xe_tuning_process_gt(gt);
 
 	xe_force_wake_init_gt(gt, gt_to_fw(gt));
 	spin_lock_init(&gt->global_invl_lock);
@@ -474,6 +472,8 @@ static int all_fw_domain_init(struct xe_gt *gt)
 	}
 
 	xe_gt_mcr_set_implicit_defaults(gt);
+	xe_wa_process_gt(gt);
+	xe_tuning_process_gt(gt);
 	xe_reg_sr_apply_mmio(&gt->reg_sr, gt);
 
 	err = xe_gt_clock_init(gt);

From 778b94d7ac17b5800aa857222911f09cc986b509 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Fri, 28 Feb 2025 11:01:53 -0600
Subject: [PATCH 0950/1173] ACPI: platform_profile: Add support for hidden
 choices
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When two drivers don't support all the same profiles the legacy interface
only exports the common profiles.

This causes problems for cases where one driver uses low-power but another
uses quiet because the result is that neither is exported to sysfs.

To allow two drivers to disagree, add support for "hidden choices".
Hidden choices are platform profiles that a driver supports to be
compatible with the platform profile of another driver.

Fixes: 688834743d67 ("ACPI: platform_profile: Allow multiple handlers")
Reported-by: Antheas Kapenekakis <lkml@antheas.dev>
Closes: https://lore.kernel.org/platform-driver-x86/e64b771e-3255-42ad-9257-5b8fc6c24ac9@gmx.de/T/#mc068042dd29df36c16c8af92664860fc4763974b
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Tested-by: Antheas Kapenekakis <lkml@antheas.dev>
Tested-by: Derek J. Clark <derekjohn.clark@gmail.com>
Acked-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://patch.msgid.link/20250228170155.2623386-2-superm1@kernel.org
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/platform_profile.c  | 94 +++++++++++++++++++++++++-------
 include/linux/platform_profile.h |  3 +
 2 files changed, 76 insertions(+), 21 deletions(-)

diff --git a/drivers/acpi/platform_profile.c b/drivers/acpi/platform_profile.c
index 2ad53cc6aae53..ef9444482db19 100644
--- a/drivers/acpi/platform_profile.c
+++ b/drivers/acpi/platform_profile.c
@@ -21,9 +21,15 @@ struct platform_profile_handler {
 	struct device dev;
 	int minor;
 	unsigned long choices[BITS_TO_LONGS(PLATFORM_PROFILE_LAST)];
+	unsigned long hidden_choices[BITS_TO_LONGS(PLATFORM_PROFILE_LAST)];
 	const struct platform_profile_ops *ops;
 };
 
+struct aggregate_choices_data {
+	unsigned long aggregate[BITS_TO_LONGS(PLATFORM_PROFILE_LAST)];
+	int count;
+};
+
 static const char * const profile_names[] = {
 	[PLATFORM_PROFILE_LOW_POWER] = "low-power",
 	[PLATFORM_PROFILE_COOL] = "cool",
@@ -73,7 +79,7 @@ static int _store_class_profile(struct device *dev, void *data)
 
 	lockdep_assert_held(&profile_lock);
 	handler = to_pprof_handler(dev);
-	if (!test_bit(*bit, handler->choices))
+	if (!test_bit(*bit, handler->choices) && !test_bit(*bit, handler->hidden_choices))
 		return -EOPNOTSUPP;
 
 	return handler->ops->profile_set(dev, *bit);
@@ -239,21 +245,44 @@ static const struct class platform_profile_class = {
 /**
  * _aggregate_choices - Aggregate the available profile choices
  * @dev: The device
- * @data: The available profile choices
+ * @arg: struct aggregate_choices_data
  *
  * Return: 0 on success, -errno on failure
  */
-static int _aggregate_choices(struct device *dev, void *data)
+static int _aggregate_choices(struct device *dev, void *arg)
 {
+	unsigned long tmp[BITS_TO_LONGS(PLATFORM_PROFILE_LAST)];
+	struct aggregate_choices_data *data = arg;
 	struct platform_profile_handler *handler;
-	unsigned long *aggregate = data;
 
 	lockdep_assert_held(&profile_lock);
 	handler = to_pprof_handler(dev);
-	if (test_bit(PLATFORM_PROFILE_LAST, aggregate))
-		bitmap_copy(aggregate, handler->choices, PLATFORM_PROFILE_LAST);
+	bitmap_or(tmp, handler->choices, handler->hidden_choices, PLATFORM_PROFILE_LAST);
+	if (test_bit(PLATFORM_PROFILE_LAST, data->aggregate))
+		bitmap_copy(data->aggregate, tmp, PLATFORM_PROFILE_LAST);
 	else
-		bitmap_and(aggregate, handler->choices, aggregate, PLATFORM_PROFILE_LAST);
+		bitmap_and(data->aggregate, tmp, data->aggregate, PLATFORM_PROFILE_LAST);
+	data->count++;
+
+	return 0;
+}
+
+/**
+ * _remove_hidden_choices - Remove hidden choices from aggregate data
+ * @dev: The device
+ * @arg: struct aggregate_choices_data
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int _remove_hidden_choices(struct device *dev, void *arg)
+{
+	struct aggregate_choices_data *data = arg;
+	struct platform_profile_handler *handler;
+
+	lockdep_assert_held(&profile_lock);
+	handler = to_pprof_handler(dev);
+	bitmap_andnot(data->aggregate, handler->choices,
+		      handler->hidden_choices, PLATFORM_PROFILE_LAST);
 
 	return 0;
 }
@@ -270,22 +299,31 @@ static ssize_t platform_profile_choices_show(struct device *dev,
 					     struct device_attribute *attr,
 					     char *buf)
 {
-	unsigned long aggregate[BITS_TO_LONGS(PLATFORM_PROFILE_LAST)];
+	struct aggregate_choices_data data = {
+		.aggregate = { [0 ... BITS_TO_LONGS(PLATFORM_PROFILE_LAST) - 1] = ~0UL },
+		.count = 0,
+	};
 	int err;
 
-	set_bit(PLATFORM_PROFILE_LAST, aggregate);
+	set_bit(PLATFORM_PROFILE_LAST, data.aggregate);
 	scoped_cond_guard(mutex_intr, return -ERESTARTSYS, &profile_lock) {
 		err = class_for_each_device(&platform_profile_class, NULL,
-					    aggregate, _aggregate_choices);
+					    &data, _aggregate_choices);
 		if (err)
 			return err;
+		if (data.count == 1) {
+			err = class_for_each_device(&platform_profile_class, NULL,
+						    &data, _remove_hidden_choices);
+			if (err)
+				return err;
+		}
 	}
 
 	/* no profile handler registered any more */
-	if (bitmap_empty(aggregate, PLATFORM_PROFILE_LAST))
+	if (bitmap_empty(data.aggregate, PLATFORM_PROFILE_LAST))
 		return -EINVAL;
 
-	return _commmon_choices_show(aggregate, buf);
+	return _commmon_choices_show(data.aggregate, buf);
 }
 
 /**
@@ -373,7 +411,10 @@ static ssize_t platform_profile_store(struct device *dev,
 				      struct device_attribute *attr,
 				      const char *buf, size_t count)
 {
-	unsigned long choices[BITS_TO_LONGS(PLATFORM_PROFILE_LAST)];
+	struct aggregate_choices_data data = {
+		.aggregate = { [0 ... BITS_TO_LONGS(PLATFORM_PROFILE_LAST) - 1] = ~0UL },
+		.count = 0,
+	};
 	int ret;
 	int i;
 
@@ -381,13 +422,13 @@ static ssize_t platform_profile_store(struct device *dev,
 	i = sysfs_match_string(profile_names, buf);
 	if (i < 0 || i == PLATFORM_PROFILE_CUSTOM)
 		return -EINVAL;
-	set_bit(PLATFORM_PROFILE_LAST, choices);
+	set_bit(PLATFORM_PROFILE_LAST, data.aggregate);
 	scoped_cond_guard(mutex_intr, return -ERESTARTSYS, &profile_lock) {
 		ret = class_for_each_device(&platform_profile_class, NULL,
-					    choices, _aggregate_choices);
+					    &data, _aggregate_choices);
 		if (ret)
 			return ret;
-		if (!test_bit(i, choices))
+		if (!test_bit(i, data.aggregate))
 			return -EOPNOTSUPP;
 
 		ret = class_for_each_device(&platform_profile_class, NULL, &i,
@@ -453,12 +494,15 @@ EXPORT_SYMBOL_GPL(platform_profile_notify);
  */
 int platform_profile_cycle(void)
 {
+	struct aggregate_choices_data data = {
+		.aggregate = { [0 ... BITS_TO_LONGS(PLATFORM_PROFILE_LAST) - 1] = ~0UL },
+		.count = 0,
+	};
 	enum platform_profile_option next = PLATFORM_PROFILE_LAST;
 	enum platform_profile_option profile = PLATFORM_PROFILE_LAST;
-	unsigned long choices[BITS_TO_LONGS(PLATFORM_PROFILE_LAST)];
 	int err;
 
-	set_bit(PLATFORM_PROFILE_LAST, choices);
+	set_bit(PLATFORM_PROFILE_LAST, data.aggregate);
 	scoped_cond_guard(mutex_intr, return -ERESTARTSYS, &profile_lock) {
 		err = class_for_each_device(&platform_profile_class, NULL,
 					    &profile, _aggregate_profiles);
@@ -470,14 +514,14 @@ int platform_profile_cycle(void)
 			return -EINVAL;
 
 		err = class_for_each_device(&platform_profile_class, NULL,
-					    choices, _aggregate_choices);
+					    &data, _aggregate_choices);
 		if (err)
 			return err;
 
 		/* never iterate into a custom if all drivers supported it */
-		clear_bit(PLATFORM_PROFILE_CUSTOM, choices);
+		clear_bit(PLATFORM_PROFILE_CUSTOM, data.aggregate);
 
-		next = find_next_bit_wrap(choices,
+		next = find_next_bit_wrap(data.aggregate,
 					  PLATFORM_PROFILE_LAST,
 					  profile + 1);
 
@@ -532,6 +576,14 @@ struct device *platform_profile_register(struct device *dev, const char *name,
 		return ERR_PTR(-EINVAL);
 	}
 
+	if (ops->hidden_choices) {
+		err = ops->hidden_choices(drvdata, pprof->hidden_choices);
+		if (err) {
+			dev_err(dev, "platform_profile hidden_choices failed\n");
+			return ERR_PTR(err);
+		}
+	}
+
 	guard(mutex)(&profile_lock);
 
 	/* create class interface for individual handler */
diff --git a/include/linux/platform_profile.h b/include/linux/platform_profile.h
index 8ab5b0e8eb2c1..8c9df7dadd5d3 100644
--- a/include/linux/platform_profile.h
+++ b/include/linux/platform_profile.h
@@ -33,6 +33,8 @@ enum platform_profile_option {
  * @probe: Callback to setup choices available to the new class device. These
  *	   choices will only be enforced when setting a new profile, not when
  *	   getting the current one.
+ * @hidden_choices: Callback to setup choices that are not visible to the user
+ *		    but can be set by the driver.
  * @profile_get: Callback that will be called when showing the current platform
  *		 profile in sysfs.
  * @profile_set: Callback that will be called when storing a new platform
@@ -40,6 +42,7 @@ enum platform_profile_option {
  */
 struct platform_profile_ops {
 	int (*probe)(void *drvdata, unsigned long *choices);
+	int (*hidden_choices)(void *drvdata, unsigned long *choices);
 	int (*profile_get)(struct device *dev, enum platform_profile_option *profile);
 	int (*profile_set)(struct device *dev, enum platform_profile_option profile);
 };

From 44e94fece5170ed9110564efec592d0e88830a28 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Fri, 28 Feb 2025 11:01:54 -0600
Subject: [PATCH 0951/1173] platform/x86/amd: pmf: Add 'quiet' to hidden
 choices
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When amd-pmf and asus-wmi are both bound no low power option shows
up in sysfs.  Add a hidden choice for amd-pmf to support 'quiet' mode
to let both bind.

Fixes: 688834743d67 ("ACPI: platform_profile: Allow multiple handlers")
Suggested-by: Antheas Kapenekakis <lkml@antheas.dev>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Tested-by: Antheas Kapenekakis <lkml@antheas.dev>
Tested-by: Derek J. Clark <derekjohn.clark@gmail.com>
Acked-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://patch.msgid.link/20250228170155.2623386-3-superm1@kernel.org
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/platform/x86/amd/pmf/sps.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/platform/x86/amd/pmf/sps.c b/drivers/platform/x86/amd/pmf/sps.c
index e6cf0b22dac33..3a0079c17cb17 100644
--- a/drivers/platform/x86/amd/pmf/sps.c
+++ b/drivers/platform/x86/amd/pmf/sps.c
@@ -303,6 +303,7 @@ int amd_pmf_get_pprof_modes(struct amd_pmf_dev *pmf)
 		mode = POWER_MODE_BALANCED_POWER;
 		break;
 	case PLATFORM_PROFILE_LOW_POWER:
+	case PLATFORM_PROFILE_QUIET:
 		mode = POWER_MODE_POWER_SAVER;
 		break;
 	default:
@@ -387,6 +388,13 @@ static int amd_pmf_profile_set(struct device *dev,
 	return 0;
 }
 
+static int amd_pmf_hidden_choices(void *drvdata, unsigned long *choices)
+{
+	set_bit(PLATFORM_PROFILE_QUIET, choices);
+
+	return 0;
+}
+
 static int amd_pmf_profile_probe(void *drvdata, unsigned long *choices)
 {
 	set_bit(PLATFORM_PROFILE_LOW_POWER, choices);
@@ -398,6 +406,7 @@ static int amd_pmf_profile_probe(void *drvdata, unsigned long *choices)
 
 static const struct platform_profile_ops amd_pmf_profile_ops = {
 	.probe = amd_pmf_profile_probe,
+	.hidden_choices = amd_pmf_hidden_choices,
 	.profile_get = amd_pmf_profile_get,
 	.profile_set = amd_pmf_profile_set,
 };

From 9a43102daf64dd0d172d8b39836dbc1dba4da1ea Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Fri, 28 Feb 2025 11:01:55 -0600
Subject: [PATCH 0952/1173] platform/x86/amd: pmf: Add balanced-performance to
 hidden choices
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Acer's WMI driver uses balanced-performance but AMD-PMF doesn't.
In case a machine binds with both drivers let amd-pmf use
balanced-performance as well.

Fixes: 688834743d67 ("ACPI: platform_profile: Allow multiple handlers")
Suggested-by: Antheas Kapenekakis <lkml@antheas.dev>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Tested-by: Antheas Kapenekakis <lkml@antheas.dev>
Tested-by: Derek J. Clark <derekjohn.clark@gmail.com>
Acked-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://patch.msgid.link/20250228170155.2623386-4-superm1@kernel.org
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/platform/x86/amd/pmf/sps.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/platform/x86/amd/pmf/sps.c b/drivers/platform/x86/amd/pmf/sps.c
index 3a0079c17cb17..d3083383f11fb 100644
--- a/drivers/platform/x86/amd/pmf/sps.c
+++ b/drivers/platform/x86/amd/pmf/sps.c
@@ -297,6 +297,7 @@ int amd_pmf_get_pprof_modes(struct amd_pmf_dev *pmf)
 
 	switch (pmf->current_profile) {
 	case PLATFORM_PROFILE_PERFORMANCE:
+	case PLATFORM_PROFILE_BALANCED_PERFORMANCE:
 		mode = POWER_MODE_PERFORMANCE;
 		break;
 	case PLATFORM_PROFILE_BALANCED:
@@ -391,6 +392,7 @@ static int amd_pmf_profile_set(struct device *dev,
 static int amd_pmf_hidden_choices(void *drvdata, unsigned long *choices)
 {
 	set_bit(PLATFORM_PROFILE_QUIET, choices);
+	set_bit(PLATFORM_PROFILE_BALANCED_PERFORMANCE, choices);
 
 	return 0;
 }

From 723aa55c08c9d1e0734e39a815fd41272eac8269 Mon Sep 17 00:00:00 2001
From: Wentao Guan <guanwentao@uniontech.com>
Date: Fri, 14 Feb 2025 19:04:18 +0800
Subject: [PATCH 0953/1173] HID: i2c-hid: improve i2c_hid_get_report error
 message

We have two places to print "failed to set a report to ...",
use "get a report from" instead of "set a report to", it makes
people who knows less about the module to know where the error
happened.

Before:
i2c_hid_acpi i2c-FTSC1000:00: failed to set a report to device: -11

After:
i2c_hid_acpi i2c-FTSC1000:00: failed to get a report from device: -11

Signed-off-by: Wentao Guan <guanwentao@uniontech.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/i2c-hid/i2c-hid-core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c
index 75544448c2393..d3912e3f2f13a 100644
--- a/drivers/hid/i2c-hid/i2c-hid-core.c
+++ b/drivers/hid/i2c-hid/i2c-hid-core.c
@@ -290,7 +290,7 @@ static int i2c_hid_get_report(struct i2c_hid *ihid,
 			     ihid->rawbuf, recv_len + sizeof(__le16));
 	if (error) {
 		dev_err(&ihid->client->dev,
-			"failed to set a report to device: %d\n", error);
+			"failed to get a report from device: %d\n", error);
 		return error;
 	}
 

From 221cea1003d8a412e5ec64a58df7ab19b654f490 Mon Sep 17 00:00:00 2001
From: Alex Henrie <alexhenrie24@gmail.com>
Date: Sun, 23 Feb 2025 22:36:30 -0700
Subject: [PATCH 0954/1173] HID: apple: disable Fn key handling on the Omoton
 KB066

Remove the fixup to make the Omoton KB066's F6 key F6 when not holding
Fn. That was really just a hack to allow typing F6 in fnmode>0, and it
didn't fix any of the other F keys that were likewise untypable in
fnmode>0. Instead, because the Omoton's Fn key is entirely internal to
the keyboard, completely disable Fn key translation when an Omoton is
detected, which will prevent the hid-apple driver from interfering with
the keyboard's built-in Fn key handling. All of the F keys, including
F6, are then typable when Fn is held.

The Omoton KB066 and the Apple A1255 both have HID product code
05ac:022c. The self-reported name of every original A1255 when they left
the factory was "Apple Wireless Keyboard". By default, Mac OS changes
the name to "<username>'s keyboard" when pairing with the keyboard, but
Mac OS allows the user to set the internal name of Apple keyboards to
anything they like. The Omoton KB066's name, on the other hand, is not
configurable: It is always "Bluetooth Keyboard". Because that name is so
generic that a user might conceivably use the same name for a real Apple
keyboard, detect Omoton keyboards based on both having that exact name
and having HID product code 022c.

Fixes: 819083cb6eed ("HID: apple: fix up the F6 key on the Omoton KB066 keyboard")
Signed-off-by: Alex Henrie <alexhenrie24@gmail.com>
Reviewed-by: Aditya Garg <gargaditya08@live.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-apple.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c
index 49812a76b7edd..d900dd05c335c 100644
--- a/drivers/hid/hid-apple.c
+++ b/drivers/hid/hid-apple.c
@@ -378,6 +378,12 @@ static bool apple_is_non_apple_keyboard(struct hid_device *hdev)
 	return false;
 }
 
+static bool apple_is_omoton_kb066(struct hid_device *hdev)
+{
+	return hdev->product == USB_DEVICE_ID_APPLE_ALU_WIRELESS_ANSI &&
+		strcmp(hdev->name, "Bluetooth Keyboard") == 0;
+}
+
 static inline void apple_setup_key_translation(struct input_dev *input,
 		const struct apple_key_translation *table)
 {
@@ -546,9 +552,6 @@ static int hidinput_apple_event(struct hid_device *hid, struct input_dev *input,
 		}
 	}
 
-	if (usage->hid == 0xc0301) /* Omoton KB066 quirk */
-		code = KEY_F6;
-
 	if (usage->code != code) {
 		input_event_with_scancode(input, usage->type, code, usage->hid, value);
 
@@ -728,7 +731,7 @@ static int apple_input_configured(struct hid_device *hdev,
 {
 	struct apple_sc *asc = hid_get_drvdata(hdev);
 
-	if ((asc->quirks & APPLE_HAS_FN) && !asc->fn_found) {
+	if (((asc->quirks & APPLE_HAS_FN) && !asc->fn_found) || apple_is_omoton_kb066(hdev)) {
 		hid_info(hdev, "Fn key not found (Apple Wireless Keyboard clone?), disabling Fn key handling\n");
 		asc->quirks &= ~APPLE_HAS_FN;
 	}

From 2ff5baa9b5275e3acafdf7f2089f74cccb2f38d1 Mon Sep 17 00:00:00 2001
From: Daniil Dulov <d.dulov@aladdin.ru>
Date: Mon, 24 Feb 2025 20:30:30 +0300
Subject: [PATCH 0955/1173] HID: appleir: Fix potential NULL dereference at raw
 event handle

Syzkaller reports a NULL pointer dereference issue in input_event().

BUG: KASAN: null-ptr-deref in instrument_atomic_read include/linux/instrumented.h:68 [inline]
BUG: KASAN: null-ptr-deref in _test_bit include/asm-generic/bitops/instrumented-non-atomic.h:141 [inline]
BUG: KASAN: null-ptr-deref in is_event_supported drivers/input/input.c:67 [inline]
BUG: KASAN: null-ptr-deref in input_event+0x42/0xa0 drivers/input/input.c:395
Read of size 8 at addr 0000000000000028 by task syz-executor199/2949

CPU: 0 UID: 0 PID: 2949 Comm: syz-executor199 Not tainted 6.13.0-rc4-syzkaller-00076-gf097a36ef88d #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/13/2024
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:94 [inline]
 dump_stack_lvl+0x116/0x1f0 lib/dump_stack.c:120
 kasan_report+0xd9/0x110 mm/kasan/report.c:602
 check_region_inline mm/kasan/generic.c:183 [inline]
 kasan_check_range+0xef/0x1a0 mm/kasan/generic.c:189
 instrument_atomic_read include/linux/instrumented.h:68 [inline]
 _test_bit include/asm-generic/bitops/instrumented-non-atomic.h:141 [inline]
 is_event_supported drivers/input/input.c:67 [inline]
 input_event+0x42/0xa0 drivers/input/input.c:395
 input_report_key include/linux/input.h:439 [inline]
 key_down drivers/hid/hid-appleir.c:159 [inline]
 appleir_raw_event+0x3e5/0x5e0 drivers/hid/hid-appleir.c:232
 __hid_input_report.constprop.0+0x312/0x440 drivers/hid/hid-core.c:2111
 hid_ctrl+0x49f/0x550 drivers/hid/usbhid/hid-core.c:484
 __usb_hcd_giveback_urb+0x389/0x6e0 drivers/usb/core/hcd.c:1650
 usb_hcd_giveback_urb+0x396/0x450 drivers/usb/core/hcd.c:1734
 dummy_timer+0x17f7/0x3960 drivers/usb/gadget/udc/dummy_hcd.c:1993
 __run_hrtimer kernel/time/hrtimer.c:1739 [inline]
 __hrtimer_run_queues+0x20a/0xae0 kernel/time/hrtimer.c:1803
 hrtimer_run_softirq+0x17d/0x350 kernel/time/hrtimer.c:1820
 handle_softirqs+0x206/0x8d0 kernel/softirq.c:561
 __do_softirq kernel/softirq.c:595 [inline]
 invoke_softirq kernel/softirq.c:435 [inline]
 __irq_exit_rcu+0xfa/0x160 kernel/softirq.c:662
 irq_exit_rcu+0x9/0x30 kernel/softirq.c:678
 instr_sysvec_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1049 [inline]
 sysvec_apic_timer_interrupt+0x90/0xb0 arch/x86/kernel/apic/apic.c:1049
 </IRQ>
 <TASK>
 asm_sysvec_apic_timer_interrupt+0x1a/0x20 arch/x86/include/asm/idtentry.h:702
 __mod_timer+0x8f6/0xdc0 kernel/time/timer.c:1185
 add_timer+0x62/0x90 kernel/time/timer.c:1295
 schedule_timeout+0x11f/0x280 kernel/time/sleep_timeout.c:98
 usbhid_wait_io+0x1c7/0x380 drivers/hid/usbhid/hid-core.c:645
 usbhid_init_reports+0x19f/0x390 drivers/hid/usbhid/hid-core.c:784
 hiddev_ioctl+0x1133/0x15b0 drivers/hid/usbhid/hiddev.c:794
 vfs_ioctl fs/ioctl.c:51 [inline]
 __do_sys_ioctl fs/ioctl.c:906 [inline]
 __se_sys_ioctl fs/ioctl.c:892 [inline]
 __x64_sys_ioctl+0x190/0x200 fs/ioctl.c:892
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0xcd/0x250 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
 </TASK>

This happens due to the malformed report items sent by the emulated device
which results in a report, that has no fields, being added to the report list.
Due to this appleir_input_configured() is never called, hidinput_connect()
fails which results in the HID_CLAIMED_INPUT flag is not being set. However,
it  does not make appleir_probe() fail and lets the event callback to be
called without the associated input device.

Thus, add a check for the HID_CLAIMED_INPUT flag and leave the event hook
early if the driver didn't claim any input_dev for some reason. Moreover,
some other hid drivers accessing input_dev in their event callbacks do have
similar checks, too.

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

Fixes: 9a4a5574ce42 ("HID: appleir: add support for Apple ir devices")
Cc: stable@vger.kernel.org
Signed-off-by: Daniil Dulov <d.dulov@aladdin.ru>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-appleir.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hid/hid-appleir.c b/drivers/hid/hid-appleir.c
index 8deded1857254..c45e5aa569d25 100644
--- a/drivers/hid/hid-appleir.c
+++ b/drivers/hid/hid-appleir.c
@@ -188,7 +188,7 @@ static int appleir_raw_event(struct hid_device *hid, struct hid_report *report,
 	static const u8 flatbattery[] = { 0x25, 0x87, 0xe0 };
 	unsigned long flags;
 
-	if (len != 5)
+	if (len != 5 || !(hid->claimed & HID_CLAIMED_INPUT))
 		goto out;
 
 	if (!memcmp(data, keydown, sizeof(keydown))) {

From a6a4f4e9b8018806cca30049b59a1c3c8b513701 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Thu, 27 Feb 2025 22:33:57 +0000
Subject: [PATCH 0956/1173] HID: debug: Fix spelling mistake "Messanger" ->
 "Messenger"

There is a spelling mistake in a literal string. Fix it.

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-debug.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c
index 541d682af15aa..8433306148d57 100644
--- a/drivers/hid/hid-debug.c
+++ b/drivers/hid/hid-debug.c
@@ -3450,7 +3450,7 @@ static const char *keys[KEY_MAX + 1] = {
 	[KEY_MACRO_RECORD_START] = "MacroRecordStart",
 	[KEY_MACRO_RECORD_STOP] = "MacroRecordStop",
 	[KEY_MARK_WAYPOINT] = "MarkWayPoint",	[KEY_MEDIA_REPEAT] = "MediaRepeat",
-	[KEY_MEDIA_TOP_MENU] = "MediaTopMenu",	[KEY_MESSENGER] = "Messanger",
+	[KEY_MEDIA_TOP_MENU] = "MediaTopMenu",	[KEY_MESSENGER] = "Messenger",
 	[KEY_NAV_CHART] = "NavChar",		[KEY_NAV_INFO] = "NavInfo",
 	[KEY_NEWS] = "News",			[KEY_NEXT_ELEMENT] = "NextElement",
 	[KEY_NEXT_FAVORITE] = "NextFavorite",	[KEY_NOTIFICATION_CENTER] = "NotificationCenter",

From e53fc232a65f7488ab75d03a5b95f06aaada7262 Mon Sep 17 00:00:00 2001
From: Vicki Pfau <vi@endrift.com>
Date: Thu, 27 Feb 2025 15:41:33 -0800
Subject: [PATCH 0957/1173] HID: hid-steam: Fix use-after-free when detaching
 device

When a hid-steam device is removed it must clean up the client_hdev used for
intercepting hidraw access. This can lead to scheduling deferred work to
reattach the input device. Though the cleanup cancels the deferred work, this
was done before the client_hdev itself is cleaned up, so it gets rescheduled.
This patch fixes the ordering to make sure the deferred work is properly
canceled.

Reported-by: syzbot+0154da2d403396b2bd59@syzkaller.appspotmail.com
Fixes: 79504249d7e2 ("HID: hid-steam: Move hidraw input (un)registering to work")
Signed-off-by: Vicki Pfau <vi@endrift.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-steam.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hid/hid-steam.c b/drivers/hid/hid-steam.c
index c9e65e9088b31..10460b7bde1a2 100644
--- a/drivers/hid/hid-steam.c
+++ b/drivers/hid/hid-steam.c
@@ -1327,11 +1327,11 @@ static void steam_remove(struct hid_device *hdev)
 		return;
 	}
 
+	hid_destroy_device(steam->client_hdev);
 	cancel_delayed_work_sync(&steam->mode_switch);
 	cancel_work_sync(&steam->work_connect);
 	cancel_work_sync(&steam->rumble_work);
 	cancel_work_sync(&steam->unregister_work);
-	hid_destroy_device(steam->client_hdev);
 	steam->client_hdev = NULL;
 	steam->client_opened = 0;
 	if (steam->quirks & STEAM_QUIRK_WIRELESS) {

From 0132c406705a466b95854ce1058f3d8354f90a42 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Fri, 28 Feb 2025 08:41:39 +0000
Subject: [PATCH 0958/1173] HID: intel-thc-hid: Fix spelling mistake "intput"
 -> "input"

There is a spelling mistake in a dev_err_once message. Fix it.

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Reviewed-by: Even Xu <even.xu@intel.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/intel-thc-hid/intel-quickspi/quickspi-protocol.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-protocol.c b/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-protocol.c
index 7373238ceb18b..918050af73e55 100644
--- a/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-protocol.c
+++ b/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-protocol.c
@@ -107,7 +107,7 @@ static int quickspi_get_device_descriptor(struct quickspi_device *qsdev)
 		return 0;
 	}
 
-	dev_err_once(qsdev->dev, "Unexpected intput report type: %d\n", input_rep_type);
+	dev_err_once(qsdev->dev, "Unexpected input report type: %d\n", input_rep_type);
 	return -EINVAL;
 }
 

From db52926fb0be40e1d588a346df73f5ea3a34a4c6 Mon Sep 17 00:00:00 2001
From: Even Xu <even.xu@intel.com>
Date: Tue, 4 Mar 2025 11:22:55 +0800
Subject: [PATCH 0959/1173] HID: Intel-thc-hid: Intel-quickspi: Correct device
 state after S4

During S4 retore flow, quickspi device was resetted by driver and state
was changed to RESETTED. It is needed to be change to ENABLED state
after S4 re-initialization finished, otherwise, device will run in wrong
state and HID input data will be dropped.

Signed-off-by: Even Xu <even.xu@intel.com>
Fixes: 6912aaf3fd24 ("HID: intel-thc-hid: intel-quickspi: Add PM implementation")
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/intel-thc-hid/intel-quickspi/pci-quickspi.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/hid/intel-thc-hid/intel-quickspi/pci-quickspi.c b/drivers/hid/intel-thc-hid/intel-quickspi/pci-quickspi.c
index 4641e818dfa44..6b2c7620be2b1 100644
--- a/drivers/hid/intel-thc-hid/intel-quickspi/pci-quickspi.c
+++ b/drivers/hid/intel-thc-hid/intel-quickspi/pci-quickspi.c
@@ -909,6 +909,8 @@ static int quickspi_restore(struct device *device)
 
 	thc_change_ltr_mode(qsdev->thc_hw, THC_LTR_MODE_ACTIVE);
 
+	qsdev->state = QUICKSPI_ENABLED;
+
 	return 0;
 }
 

From 5eb3dc1396aa7e315486b24df80df782912334b7 Mon Sep 17 00:00:00 2001
From: Luca Weiss <luca.weiss@fairphone.com>
Date: Thu, 27 Feb 2025 11:33:40 +0100
Subject: [PATCH 0960/1173] net: ipa: Fix v4.7 resource group names

In the downstream IPA driver there's only one group defined for source
and destination, and the destination group doesn't have a _DPL suffix.

Fixes: b310de784bac ("net: ipa: add IPA v4.7 support")
Signed-off-by: Luca Weiss <luca.weiss@fairphone.com>
Reviewed-by: Alex Elder <elder@riscstar.com>
Link: https://patch.msgid.link/20250227-ipa-v4-7-fixes-v1-1-a88dd8249d8a@fairphone.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ipa/data/ipa_data-v4.7.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ipa/data/ipa_data-v4.7.c b/drivers/net/ipa/data/ipa_data-v4.7.c
index c8c23d9be961b..7e315779e6648 100644
--- a/drivers/net/ipa/data/ipa_data-v4.7.c
+++ b/drivers/net/ipa/data/ipa_data-v4.7.c
@@ -28,12 +28,10 @@ enum ipa_resource_type {
 enum ipa_rsrc_group_id {
 	/* Source resource group identifiers */
 	IPA_RSRC_GROUP_SRC_UL_DL			= 0,
-	IPA_RSRC_GROUP_SRC_UC_RX_Q,
 	IPA_RSRC_GROUP_SRC_COUNT,	/* Last in set; not a source group */
 
 	/* Destination resource group identifiers */
-	IPA_RSRC_GROUP_DST_UL_DL_DPL			= 0,
-	IPA_RSRC_GROUP_DST_UNUSED_1,
+	IPA_RSRC_GROUP_DST_UL_DL			= 0,
 	IPA_RSRC_GROUP_DST_COUNT,	/* Last; not a destination group */
 };
 
@@ -81,7 +79,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = {
 		},
 		.endpoint = {
 			.config = {
-				.resource_group	= IPA_RSRC_GROUP_DST_UL_DL_DPL,
+				.resource_group	= IPA_RSRC_GROUP_DST_UL_DL,
 				.aggregation	= true,
 				.status_enable	= true,
 				.rx = {
@@ -128,7 +126,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = {
 		},
 		.endpoint = {
 			.config = {
-				.resource_group	= IPA_RSRC_GROUP_DST_UL_DL_DPL,
+				.resource_group	= IPA_RSRC_GROUP_DST_UL_DL,
 				.qmap		= true,
 				.aggregation	= true,
 				.rx = {
@@ -197,12 +195,12 @@ static const struct ipa_resource ipa_resource_src[] = {
 /* Destination resource configuration data for an SoC having IPA v4.7 */
 static const struct ipa_resource ipa_resource_dst[] = {
 	[IPA_RESOURCE_TYPE_DST_DATA_SECTORS] = {
-		.limits[IPA_RSRC_GROUP_DST_UL_DL_DPL] = {
+		.limits[IPA_RSRC_GROUP_DST_UL_DL] = {
 			.min = 7,	.max = 7,
 		},
 	},
 	[IPA_RESOURCE_TYPE_DST_DPS_DMARS] = {
-		.limits[IPA_RSRC_GROUP_DST_UL_DL_DPL] = {
+		.limits[IPA_RSRC_GROUP_DST_UL_DL] = {
 			.min = 2,	.max = 2,
 		},
 	},

From 6a2843aaf551d87beb92d774f7d5b8ae007fe774 Mon Sep 17 00:00:00 2001
From: Luca Weiss <luca.weiss@fairphone.com>
Date: Thu, 27 Feb 2025 11:33:41 +0100
Subject: [PATCH 0961/1173] net: ipa: Fix QSB data for v4.7

As per downstream reference, max_writes should be 12 and max_reads
should be 13.

Fixes: b310de784bac ("net: ipa: add IPA v4.7 support")
Signed-off-by: Luca Weiss <luca.weiss@fairphone.com>
Reviewed-by: Alex Elder <elder@riscstar.com>
Link: https://patch.msgid.link/20250227-ipa-v4-7-fixes-v1-2-a88dd8249d8a@fairphone.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ipa/data/ipa_data-v4.7.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ipa/data/ipa_data-v4.7.c b/drivers/net/ipa/data/ipa_data-v4.7.c
index 7e315779e6648..e63dcf8d45567 100644
--- a/drivers/net/ipa/data/ipa_data-v4.7.c
+++ b/drivers/net/ipa/data/ipa_data-v4.7.c
@@ -38,8 +38,8 @@ enum ipa_rsrc_group_id {
 /* QSB configuration data for an SoC having IPA v4.7 */
 static const struct ipa_qsb_data ipa_qsb_data[] = {
 	[IPA_QSB_MASTER_DDR] = {
-		.max_writes		= 8,
-		.max_reads		= 0,	/* no limit (hardware max) */
+		.max_writes		= 12,
+		.max_reads		= 13,
 		.max_reads_beats	= 120,
 	},
 };

From 934e69669e32eb653234898424ae007bae2f636e Mon Sep 17 00:00:00 2001
From: Luca Weiss <luca.weiss@fairphone.com>
Date: Thu, 27 Feb 2025 11:33:42 +0100
Subject: [PATCH 0962/1173] net: ipa: Enable checksum for
 IPA_ENDPOINT_AP_MODEM_{RX,TX} for v4.7

Enable the checksum option for these two endpoints in order to allow
mobile data to actually work. Without this, no packets seem to make it
through the IPA.

Fixes: b310de784bac ("net: ipa: add IPA v4.7 support")
Signed-off-by: Luca Weiss <luca.weiss@fairphone.com>
Reviewed-by: Alex Elder <elder@riscstar.com>
Link: https://patch.msgid.link/20250227-ipa-v4-7-fixes-v1-3-a88dd8249d8a@fairphone.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ipa/data/ipa_data-v4.7.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ipa/data/ipa_data-v4.7.c b/drivers/net/ipa/data/ipa_data-v4.7.c
index e63dcf8d45567..41f212209993f 100644
--- a/drivers/net/ipa/data/ipa_data-v4.7.c
+++ b/drivers/net/ipa/data/ipa_data-v4.7.c
@@ -104,6 +104,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = {
 			.filter_support	= true,
 			.config = {
 				.resource_group	= IPA_RSRC_GROUP_SRC_UL_DL,
+				.checksum       = true,
 				.qmap		= true,
 				.status_enable	= true,
 				.tx = {
@@ -127,6 +128,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = {
 		.endpoint = {
 			.config = {
 				.resource_group	= IPA_RSRC_GROUP_DST_UL_DL,
+				.checksum       = true,
 				.qmap		= true,
 				.aggregation	= true,
 				.rx = {

From 4c2d14c40a68678d885eab4008a0129646805bae Mon Sep 17 00:00:00 2001
From: Jiayuan Chen <jiayuan.chen@linux.dev>
Date: Fri, 28 Feb 2025 22:14:08 +0800
Subject: [PATCH 0963/1173] ppp: Fix KMSAN uninit-value warning with bpf

Syzbot caught an "KMSAN: uninit-value" warning [1], which is caused by the
ppp driver not initializing a 2-byte header when using socket filter.

The following code can generate a PPP filter BPF program:
'''
struct bpf_program fp;
pcap_t *handle;
handle = pcap_open_dead(DLT_PPP_PPPD, 65535);
pcap_compile(handle, &fp, "ip and outbound", 0, 0);
bpf_dump(&fp, 1);
'''
Its output is:
'''
(000) ldh [2]
(001) jeq #0x21 jt 2 jf 5
(002) ldb [0]
(003) jeq #0x1 jt 4 jf 5
(004) ret #65535
(005) ret #0
'''
Wen can find similar code at the following link:
https://github.com/ppp-project/ppp/blob/master/pppd/options.c#L1680
The maintainer of this code repository is also the original maintainer
of the ppp driver.

As you can see the BPF program skips 2 bytes of data and then reads the
'Protocol' field to determine if it's an IP packet. Then it read the first
byte of the first 2 bytes to determine the direction.

The issue is that only the first byte indicating direction is initialized
in current ppp driver code while the second byte is not initialized.

For normal BPF programs generated by libpcap, uninitialized data won't be
used, so it's not a problem. However, for carefully crafted BPF programs,
such as those generated by syzkaller [2], which start reading from offset
0, the uninitialized data will be used and caught by KMSAN.

[1] https://syzkaller.appspot.com/bug?extid=853242d9c9917165d791
[2] https://syzkaller.appspot.com/text?tag=ReproC&x=11994913980000

Cc: Paul Mackerras <paulus@samba.org>
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzbot+853242d9c9917165d791@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/bpf/000000000000dea025060d6bc3bc@google.com/
Signed-off-by: Jiayuan Chen <jiayuan.chen@linux.dev>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250228141408.393864-1-jiayuan.chen@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ppp/ppp_generic.c | 28 +++++++++++++++++++---------
 1 file changed, 19 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 4583e15ad03a0..1420c4efa48e6 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -72,6 +72,17 @@
 #define PPP_PROTO_LEN	2
 #define PPP_LCP_HDRLEN	4
 
+/* The filter instructions generated by libpcap are constructed
+ * assuming a four-byte PPP header on each packet, where the last
+ * 2 bytes are the protocol field defined in the RFC and the first
+ * byte of the first 2 bytes indicates the direction.
+ * The second byte is currently unused, but we still need to initialize
+ * it to prevent crafted BPF programs from reading them which would
+ * cause reading of uninitialized data.
+ */
+#define PPP_FILTER_OUTBOUND_TAG 0x0100
+#define PPP_FILTER_INBOUND_TAG  0x0000
+
 /*
  * An instance of /dev/ppp can be associated with either a ppp
  * interface unit or a ppp channel.  In both cases, file->private_data
@@ -1762,10 +1773,10 @@ ppp_send_frame(struct ppp *ppp, struct sk_buff *skb)
 
 	if (proto < 0x8000) {
 #ifdef CONFIG_PPP_FILTER
-		/* check if we should pass this packet */
-		/* the filter instructions are constructed assuming
-		   a four-byte PPP header on each packet */
-		*(u8 *)skb_push(skb, 2) = 1;
+		/* check if the packet passes the pass and active filters.
+		 * See comment for PPP_FILTER_OUTBOUND_TAG above.
+		 */
+		*(__be16 *)skb_push(skb, 2) = htons(PPP_FILTER_OUTBOUND_TAG);
 		if (ppp->pass_filter &&
 		    bpf_prog_run(ppp->pass_filter, skb) == 0) {
 			if (ppp->debug & 1)
@@ -2482,14 +2493,13 @@ ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb)
 		/* network protocol frame - give it to the kernel */
 
 #ifdef CONFIG_PPP_FILTER
-		/* check if the packet passes the pass and active filters */
-		/* the filter instructions are constructed assuming
-		   a four-byte PPP header on each packet */
 		if (ppp->pass_filter || ppp->active_filter) {
 			if (skb_unclone(skb, GFP_ATOMIC))
 				goto err;
-
-			*(u8 *)skb_push(skb, 2) = 0;
+			/* Check if the packet passes the pass and active filters.
+			 * See comment for PPP_FILTER_INBOUND_TAG above.
+			 */
+			*(__be16 *)skb_push(skb, 2) = htons(PPP_FILTER_INBOUND_TAG);
 			if (ppp->pass_filter &&
 			    bpf_prog_run(ppp->pass_filter, skb) == 0) {
 				if (ppp->debug & 1)

From 637399bf7e77797811adf340090b561a8f9d1213 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Sat, 1 Mar 2025 15:11:13 +0100
Subject: [PATCH 0964/1173] net: ethtool: netlink: Allow NULL nlattrs when
 getting a phy_device

ethnl_req_get_phydev() is used to lookup a phy_device, in the case an
ethtool netlink command targets a specific phydev within a netdev's
topology.

It takes as a parameter a const struct nlattr *header that's used for
error handling :

       if (!phydev) {
               NL_SET_ERR_MSG_ATTR(extack, header,
                                   "no phy matching phyindex");
               return ERR_PTR(-ENODEV);
       }

In the notify path after a ->set operation however, there's no request
attributes available.

The typical callsite for the above function looks like:

	phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_XXX_HEADER],
				      info->extack);

So, when tb is NULL (such as in the ethnl notify path), we have a nice
crash.

It turns out that there's only the PLCA command that is in that case, as
the other phydev-specific commands don't have a notification.

This commit fixes the crash by passing the cmd index and the nlattr
array separately, allowing NULL-checking it directly inside the helper.

Fixes: c15e065b46dc ("net: ethtool: Allow passing a phy index for some commands")
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: Kory Maincent <kory.maincent@bootlin.com>
Reported-by: Parthiban Veerasooran <parthiban.veerasooran@microchip.com>
Link: https://patch.msgid.link/20250301141114.97204-1-maxime.chevallier@bootlin.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ethtool/cabletest.c | 8 ++++----
 net/ethtool/linkstate.c | 2 +-
 net/ethtool/netlink.c   | 6 +++---
 net/ethtool/netlink.h   | 5 +++--
 net/ethtool/phy.c       | 2 +-
 net/ethtool/plca.c      | 6 +++---
 net/ethtool/pse-pd.c    | 4 ++--
 net/ethtool/stats.c     | 2 +-
 net/ethtool/strset.c    | 2 +-
 9 files changed, 19 insertions(+), 18 deletions(-)

diff --git a/net/ethtool/cabletest.c b/net/ethtool/cabletest.c
index f22051f33868a..84096f6b0236e 100644
--- a/net/ethtool/cabletest.c
+++ b/net/ethtool/cabletest.c
@@ -72,8 +72,8 @@ int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info)
 	dev = req_info.dev;
 
 	rtnl_lock();
-	phydev = ethnl_req_get_phydev(&req_info,
-				      tb[ETHTOOL_A_CABLE_TEST_HEADER],
+	phydev = ethnl_req_get_phydev(&req_info, tb,
+				      ETHTOOL_A_CABLE_TEST_HEADER,
 				      info->extack);
 	if (IS_ERR_OR_NULL(phydev)) {
 		ret = -EOPNOTSUPP;
@@ -339,8 +339,8 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info)
 		goto out_dev_put;
 
 	rtnl_lock();
-	phydev = ethnl_req_get_phydev(&req_info,
-				      tb[ETHTOOL_A_CABLE_TEST_TDR_HEADER],
+	phydev = ethnl_req_get_phydev(&req_info, tb,
+				      ETHTOOL_A_CABLE_TEST_TDR_HEADER,
 				      info->extack);
 	if (IS_ERR_OR_NULL(phydev)) {
 		ret = -EOPNOTSUPP;
diff --git a/net/ethtool/linkstate.c b/net/ethtool/linkstate.c
index af19e1bed303f..05a5f72c99fab 100644
--- a/net/ethtool/linkstate.c
+++ b/net/ethtool/linkstate.c
@@ -103,7 +103,7 @@ static int linkstate_prepare_data(const struct ethnl_req_info *req_base,
 	struct phy_device *phydev;
 	int ret;
 
-	phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_LINKSTATE_HEADER],
+	phydev = ethnl_req_get_phydev(req_base, tb, ETHTOOL_A_LINKSTATE_HEADER,
 				      info->extack);
 	if (IS_ERR(phydev)) {
 		ret = PTR_ERR(phydev);
diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index b4c45207fa32e..734849a573691 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -211,7 +211,7 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info,
 }
 
 struct phy_device *ethnl_req_get_phydev(const struct ethnl_req_info *req_info,
-					const struct nlattr *header,
+					struct nlattr **tb, unsigned int header,
 					struct netlink_ext_ack *extack)
 {
 	struct phy_device *phydev;
@@ -225,8 +225,8 @@ struct phy_device *ethnl_req_get_phydev(const struct ethnl_req_info *req_info,
 		return req_info->dev->phydev;
 
 	phydev = phy_link_topo_get_phy(req_info->dev, req_info->phy_index);
-	if (!phydev) {
-		NL_SET_ERR_MSG_ATTR(extack, header,
+	if (!phydev && tb) {
+		NL_SET_ERR_MSG_ATTR(extack, tb[header],
 				    "no phy matching phyindex");
 		return ERR_PTR(-ENODEV);
 	}
diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h
index ff69ca0715dea..ec6ab5443a6f2 100644
--- a/net/ethtool/netlink.h
+++ b/net/ethtool/netlink.h
@@ -275,7 +275,8 @@ static inline void ethnl_parse_header_dev_put(struct ethnl_req_info *req_info)
  * ethnl_req_get_phydev() - Gets the phy_device targeted by this request,
  *			    if any. Must be called under rntl_lock().
  * @req_info:	The ethnl request to get the phy from.
- * @header:	The netlink header, used for error reporting.
+ * @tb:		The netlink attributes array, for error reporting.
+ * @header:	The netlink header index, used for error reporting.
  * @extack:	The netlink extended ACK, for error reporting.
  *
  * The caller must hold RTNL, until it's done interacting with the returned
@@ -289,7 +290,7 @@ static inline void ethnl_parse_header_dev_put(struct ethnl_req_info *req_info)
  *	   is returned.
  */
 struct phy_device *ethnl_req_get_phydev(const struct ethnl_req_info *req_info,
-					const struct nlattr *header,
+					struct nlattr **tb, unsigned int header,
 					struct netlink_ext_ack *extack);
 
 /**
diff --git a/net/ethtool/phy.c b/net/ethtool/phy.c
index ed8f690f6bac8..e067cc234419d 100644
--- a/net/ethtool/phy.c
+++ b/net/ethtool/phy.c
@@ -125,7 +125,7 @@ static int ethnl_phy_parse_request(struct ethnl_req_info *req_base,
 	struct phy_req_info *req_info = PHY_REQINFO(req_base);
 	struct phy_device *phydev;
 
-	phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_PHY_HEADER],
+	phydev = ethnl_req_get_phydev(req_base, tb, ETHTOOL_A_PHY_HEADER,
 				      extack);
 	if (!phydev)
 		return 0;
diff --git a/net/ethtool/plca.c b/net/ethtool/plca.c
index d95d92f173a6d..e1f7820a6158f 100644
--- a/net/ethtool/plca.c
+++ b/net/ethtool/plca.c
@@ -62,7 +62,7 @@ static int plca_get_cfg_prepare_data(const struct ethnl_req_info *req_base,
 	struct phy_device *phydev;
 	int ret;
 
-	phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_PLCA_HEADER],
+	phydev = ethnl_req_get_phydev(req_base, tb, ETHTOOL_A_PLCA_HEADER,
 				      info->extack);
 	// check that the PHY device is available and connected
 	if (IS_ERR_OR_NULL(phydev)) {
@@ -152,7 +152,7 @@ ethnl_set_plca(struct ethnl_req_info *req_info, struct genl_info *info)
 	bool mod = false;
 	int ret;
 
-	phydev = ethnl_req_get_phydev(req_info, tb[ETHTOOL_A_PLCA_HEADER],
+	phydev = ethnl_req_get_phydev(req_info, tb, ETHTOOL_A_PLCA_HEADER,
 				      info->extack);
 	// check that the PHY device is available and connected
 	if (IS_ERR_OR_NULL(phydev))
@@ -211,7 +211,7 @@ static int plca_get_status_prepare_data(const struct ethnl_req_info *req_base,
 	struct phy_device *phydev;
 	int ret;
 
-	phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_PLCA_HEADER],
+	phydev = ethnl_req_get_phydev(req_base, tb, ETHTOOL_A_PLCA_HEADER,
 				      info->extack);
 	// check that the PHY device is available and connected
 	if (IS_ERR_OR_NULL(phydev)) {
diff --git a/net/ethtool/pse-pd.c b/net/ethtool/pse-pd.c
index 2819e2ba6be2d..4f6b99eab2a6c 100644
--- a/net/ethtool/pse-pd.c
+++ b/net/ethtool/pse-pd.c
@@ -64,7 +64,7 @@ static int pse_prepare_data(const struct ethnl_req_info *req_base,
 	if (ret < 0)
 		return ret;
 
-	phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_PSE_HEADER],
+	phydev = ethnl_req_get_phydev(req_base, tb, ETHTOOL_A_PSE_HEADER,
 				      info->extack);
 	if (IS_ERR(phydev))
 		return -ENODEV;
@@ -261,7 +261,7 @@ ethnl_set_pse(struct ethnl_req_info *req_info, struct genl_info *info)
 	struct phy_device *phydev;
 	int ret;
 
-	phydev = ethnl_req_get_phydev(req_info, tb[ETHTOOL_A_PSE_HEADER],
+	phydev = ethnl_req_get_phydev(req_info, tb, ETHTOOL_A_PSE_HEADER,
 				      info->extack);
 	ret = ethnl_set_pse_validate(phydev, info);
 	if (ret)
diff --git a/net/ethtool/stats.c b/net/ethtool/stats.c
index 038a2558f0520..3ca8eb2a3b314 100644
--- a/net/ethtool/stats.c
+++ b/net/ethtool/stats.c
@@ -138,7 +138,7 @@ static int stats_prepare_data(const struct ethnl_req_info *req_base,
 	struct phy_device *phydev;
 	int ret;
 
-	phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_STATS_HEADER],
+	phydev = ethnl_req_get_phydev(req_base, tb, ETHTOOL_A_STATS_HEADER,
 				      info->extack);
 	if (IS_ERR(phydev))
 		return PTR_ERR(phydev);
diff --git a/net/ethtool/strset.c b/net/ethtool/strset.c
index 6b76c05caba4d..f6a67109beda1 100644
--- a/net/ethtool/strset.c
+++ b/net/ethtool/strset.c
@@ -309,7 +309,7 @@ static int strset_prepare_data(const struct ethnl_req_info *req_base,
 		return 0;
 	}
 
-	phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_HEADER_FLAGS],
+	phydev = ethnl_req_get_phydev(req_base, tb, ETHTOOL_A_HEADER_FLAGS,
 				      info->extack);
 
 	/* phydev can be NULL, check for errors only */

From 022bfe24aad8937705704ff2e414b100cf0f2e1a Mon Sep 17 00:00:00 2001
From: Krister Johansen <kjlx@templeofstupid.com>
Date: Mon, 3 Mar 2025 18:10:13 +0100
Subject: [PATCH 0965/1173] mptcp: fix 'scheduling while atomic' in
 mptcp_pm_nl_append_new_local_addr

If multiple connection requests attempt to create an implicit mptcp
endpoint in parallel, more than one caller may end up in
mptcp_pm_nl_append_new_local_addr because none found the address in
local_addr_list during their call to mptcp_pm_nl_get_local_id.  In this
case, the concurrent new_local_addr calls may delete the address entry
created by the previous caller.  These deletes use synchronize_rcu, but
this is not permitted in some of the contexts where this function may be
called.  During packet recv, the caller may be in a rcu read critical
section and have preemption disabled.

An example stack:

   BUG: scheduling while atomic: swapper/2/0/0x00000302

   Call Trace:
   <IRQ>
   dump_stack_lvl (lib/dump_stack.c:117 (discriminator 1))
   dump_stack (lib/dump_stack.c:124)
   __schedule_bug (kernel/sched/core.c:5943)
   schedule_debug.constprop.0 (arch/x86/include/asm/preempt.h:33 kernel/sched/core.c:5970)
   __schedule (arch/x86/include/asm/jump_label.h:27 include/linux/jump_label.h:207 kernel/sched/features.h:29 kernel/sched/core.c:6621)
   schedule (arch/x86/include/asm/preempt.h:84 kernel/sched/core.c:6804 kernel/sched/core.c:6818)
   schedule_timeout (kernel/time/timer.c:2160)
   wait_for_completion (kernel/sched/completion.c:96 kernel/sched/completion.c:116 kernel/sched/completion.c:127 kernel/sched/completion.c:148)
   __wait_rcu_gp (include/linux/rcupdate.h:311 kernel/rcu/update.c:444)
   synchronize_rcu (kernel/rcu/tree.c:3609)
   mptcp_pm_nl_append_new_local_addr (net/mptcp/pm_netlink.c:966 net/mptcp/pm_netlink.c:1061)
   mptcp_pm_nl_get_local_id (net/mptcp/pm_netlink.c:1164)
   mptcp_pm_get_local_id (net/mptcp/pm.c:420)
   subflow_check_req (net/mptcp/subflow.c:98 net/mptcp/subflow.c:213)
   subflow_v4_route_req (net/mptcp/subflow.c:305)
   tcp_conn_request (net/ipv4/tcp_input.c:7216)
   subflow_v4_conn_request (net/mptcp/subflow.c:651)
   tcp_rcv_state_process (net/ipv4/tcp_input.c:6709)
   tcp_v4_do_rcv (net/ipv4/tcp_ipv4.c:1934)
   tcp_v4_rcv (net/ipv4/tcp_ipv4.c:2334)
   ip_protocol_deliver_rcu (net/ipv4/ip_input.c:205 (discriminator 1))
   ip_local_deliver_finish (include/linux/rcupdate.h:813 net/ipv4/ip_input.c:234)
   ip_local_deliver (include/linux/netfilter.h:314 include/linux/netfilter.h:308 net/ipv4/ip_input.c:254)
   ip_sublist_rcv_finish (include/net/dst.h:461 net/ipv4/ip_input.c:580)
   ip_sublist_rcv (net/ipv4/ip_input.c:640)
   ip_list_rcv (net/ipv4/ip_input.c:675)
   __netif_receive_skb_list_core (net/core/dev.c:5583 net/core/dev.c:5631)
   netif_receive_skb_list_internal (net/core/dev.c:5685 net/core/dev.c:5774)
   napi_complete_done (include/linux/list.h:37 include/net/gro.h:449 include/net/gro.h:444 net/core/dev.c:6114)
   igb_poll (drivers/net/ethernet/intel/igb/igb_main.c:8244) igb
   __napi_poll (net/core/dev.c:6582)
   net_rx_action (net/core/dev.c:6653 net/core/dev.c:6787)
   handle_softirqs (kernel/softirq.c:553)
   __irq_exit_rcu (kernel/softirq.c:588 kernel/softirq.c:427 kernel/softirq.c:636)
   irq_exit_rcu (kernel/softirq.c:651)
   common_interrupt (arch/x86/kernel/irq.c:247 (discriminator 14))
   </IRQ>

This problem seems particularly prevalent if the user advertises an
endpoint that has a different external vs internal address.  In the case
where the external address is advertised and multiple connections
already exist, multiple subflow SYNs arrive in parallel which tends to
trigger the race during creation of the first local_addr_list entries
which have the internal address instead.

Fix by skipping the replacement of an existing implicit local address if
called via mptcp_pm_nl_get_local_id.

Fixes: d045b9eb95a9 ("mptcp: introduce implicit endpoints")
Cc: stable@vger.kernel.org
Suggested-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Krister Johansen <kjlx@templeofstupid.com>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250303-net-mptcp-fix-sched-while-atomic-v1-1-f6a216c5a74c@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm_netlink.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index c0e47f4f7b1aa..7868207c4e9d9 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -977,7 +977,7 @@ static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry)
 
 static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
 					     struct mptcp_pm_addr_entry *entry,
-					     bool needs_id)
+					     bool needs_id, bool replace)
 {
 	struct mptcp_pm_addr_entry *cur, *del_entry = NULL;
 	unsigned int addr_max;
@@ -1017,6 +1017,17 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
 			if (entry->addr.id)
 				goto out;
 
+			/* allow callers that only need to look up the local
+			 * addr's id to skip replacement. This allows them to
+			 * avoid calling synchronize_rcu in the packet recv
+			 * path.
+			 */
+			if (!replace) {
+				kfree(entry);
+				ret = cur->addr.id;
+				goto out;
+			}
+
 			pernet->addrs--;
 			entry->addr.id = cur->addr.id;
 			list_del_rcu(&cur->list);
@@ -1165,7 +1176,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc
 	entry->ifindex = 0;
 	entry->flags = MPTCP_PM_ADDR_FLAG_IMPLICIT;
 	entry->lsk = NULL;
-	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, true);
+	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, true, false);
 	if (ret < 0)
 		kfree(entry);
 
@@ -1433,7 +1444,8 @@ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry,
-						!mptcp_pm_has_addr_attr_id(attr, info));
+						!mptcp_pm_has_addr_attr_id(attr, info),
+						true);
 	if (ret < 0) {
 		GENL_SET_ERR_MSG_FMT(info, "too many addresses or duplicate one: %d", ret);
 		goto out_free;

From b33a534610067ade2bdaf2052900aaad99701353 Mon Sep 17 00:00:00 2001
From: Oscar Maes <oscmaes92@gmail.com>
Date: Mon, 3 Mar 2025 16:56:19 +0100
Subject: [PATCH 0966/1173] vlan: enforce underlying device type

Currently, VLAN devices can be created on top of non-ethernet devices.

Besides the fact that it doesn't make much sense, this also causes a
bug which leaks the address of a kernel function to usermode.

When creating a VLAN device, we initialize GARP (garp_init_applicant)
and MRP (mrp_init_applicant) for the underlying device.

As part of the initialization process, we add the multicast address of
each applicant to the underlying device, by calling dev_mc_add.

__dev_mc_add uses dev->addr_len to determine the length of the new
multicast address.

This causes an out-of-bounds read if dev->addr_len is greater than 6,
since the multicast addresses provided by GARP and MRP are only 6
bytes long.

This behaviour can be reproduced using the following commands:

ip tunnel add gretest mode ip6gre local ::1 remote ::2 dev lo
ip l set up dev gretest
ip link add link gretest name vlantest type vlan id 100

Then, the following command will display the address of garp_pdu_rcv:

ip maddr show | grep 01:80:c2:00:00:21

Fix the bug by enforcing the type of the underlying device during VLAN
device initialization.

Fixes: 22bedad3ce11 ("net: convert multicast list to list_head")
Reported-by: syzbot+91161fe81857b396c8a0@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/000000000000ca9a81061a01ec20@google.com/
Signed-off-by: Oscar Maes <oscmaes92@gmail.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://patch.msgid.link/20250303155619.8918-1-oscmaes92@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/8021q/vlan.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index e45187b882206..41be38264493d 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -131,7 +131,8 @@ int vlan_check_real_dev(struct net_device *real_dev,
 {
 	const char *name = real_dev->name;
 
-	if (real_dev->features & NETIF_F_VLAN_CHALLENGED) {
+	if (real_dev->features & NETIF_F_VLAN_CHALLENGED ||
+	    real_dev->type != ARPHRD_ETHER) {
 		pr_info("VLANs not supported on %s\n", name);
 		NL_SET_ERR_MSG_MOD(extack, "VLANs not supported on device");
 		return -EOPNOTSUPP;

From f739365158a33549cf1827968b12a370ab75589e Mon Sep 17 00:00:00 2001
From: Charles Han <hanchunchao@inspur.com>
Date: Wed, 5 Mar 2025 14:35:14 +0800
Subject: [PATCH 0967/1173] x86/delay: Fix inconsistent whitespace

Smatch warns about this whitespace damage:

	arch/x86/lib/delay.c:134 delay_halt_mwaitx() warn: inconsistent indenting

Signed-off-by: Charles Han <hanchunchao@inspur.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250305063515.3951-1-hanchunchao@inspur.com
---
 arch/x86/lib/delay.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c
index 23f81ca3f06b4..e86eda2c0b040 100644
--- a/arch/x86/lib/delay.c
+++ b/arch/x86/lib/delay.c
@@ -131,7 +131,7 @@ static void delay_halt_mwaitx(u64 unused, u64 cycles)
 	 * Use cpu_tss_rw as a cacheline-aligned, seldom accessed per-cpu
 	 * variable as the monitor target.
 	 */
-	 __monitorx(raw_cpu_ptr(&cpu_tss_rw), 0, 0);
+	__monitorx(raw_cpu_ptr(&cpu_tss_rw), 0, 0);
 
 	/*
 	 * AMD, like Intel, supports the EAX hint and EAX=0xf means, do not

From 0d3e0dfd68fb9e6b0ec865be9f3377cc3ff55733 Mon Sep 17 00:00:00 2001
From: Jarkko Sakkinen <jarkko@kernel.org>
Date: Wed, 5 Mar 2025 07:00:05 +0200
Subject: [PATCH 0968/1173] x86/sgx: Fix size overflows in sgx_encl_create()

The total size calculated for EPC can overflow u64 given the added up page
for SECS.  Further, the total size calculated for shmem can overflow even
when the EPC size stays within limits of u64, given that it adds the extra
space for 128 byte PCMD structures (one for each page).

Address this by pre-evaluating the micro-architectural requirement of
SGX: the address space size must be power of two. This is eventually
checked up by ECREATE but the pre-check has the additional benefit of
making sure that there is some space for additional data.

Fixes: 888d24911787 ("x86/sgx: Add SGX_IOC_ENCLAVE_CREATE")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Dave Hansen <dave.hansen@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Link: https://lore.kernel.org/r/20250305050006.43896-1-jarkko@kernel.org

Closes: https://lore.kernel.org/linux-sgx/c87e01a0-e7dd-4749-a348-0980d3444f04@stanley.mountain/
---
 arch/x86/kernel/cpu/sgx/ioctl.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c
index b65ab214bdf57..776a20172867e 100644
--- a/arch/x86/kernel/cpu/sgx/ioctl.c
+++ b/arch/x86/kernel/cpu/sgx/ioctl.c
@@ -64,6 +64,13 @@ static int sgx_encl_create(struct sgx_encl *encl, struct sgx_secs *secs)
 	struct file *backing;
 	long ret;
 
+	/*
+	 * ECREATE would detect this too, but checking here also ensures
+	 * that the 'encl_size' calculations below can never overflow.
+	 */
+	if (!is_power_of_2(secs->size))
+		return -EINVAL;
+
 	va_page = sgx_encl_grow(encl, true);
 	if (IS_ERR(va_page))
 		return PTR_ERR(va_page);

From ca0dedaff92307591f66c9206933fbdfe87add10 Mon Sep 17 00:00:00 2001
From: Kailang Yang <kailang@realtek.com>
Date: Wed, 5 Mar 2025 13:54:34 +0800
Subject: [PATCH 0969/1173] ALSA: hda/realtek: update ALC222 depop optimize

Add ALC222 its own depop functions for alc_init and alc_shutup.

[note: this fixes pop noise issues on the models with two headphone
 jacks -- tiwai ]

Signed-off-by: Kailang Yang <kailang@realtek.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 76 +++++++++++++++++++++++++++++++++++
 1 file changed, 76 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 697a38e41e166..4ca457e7ca9dd 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -3843,6 +3843,79 @@ static void alc225_shutup(struct hda_codec *codec)
 	}
 }
 
+static void alc222_init(struct hda_codec *codec)
+{
+	struct alc_spec *spec = codec->spec;
+	hda_nid_t hp_pin = alc_get_hp_pin(spec);
+	bool hp1_pin_sense, hp2_pin_sense;
+
+	if (!hp_pin)
+		return;
+
+	msleep(30);
+
+	hp1_pin_sense = snd_hda_jack_detect(codec, hp_pin);
+	hp2_pin_sense = snd_hda_jack_detect(codec, 0x14);
+
+	if (hp1_pin_sense || hp2_pin_sense) {
+		msleep(2);
+
+		if (hp1_pin_sense)
+			snd_hda_codec_write(codec, hp_pin, 0,
+				    AC_VERB_SET_PIN_WIDGET_CONTROL, PIN_OUT);
+		if (hp2_pin_sense)
+			snd_hda_codec_write(codec, 0x14, 0,
+				    AC_VERB_SET_PIN_WIDGET_CONTROL, PIN_OUT);
+		msleep(75);
+
+		if (hp1_pin_sense)
+			snd_hda_codec_write(codec, hp_pin, 0,
+				    AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_UNMUTE);
+		if (hp2_pin_sense)
+			snd_hda_codec_write(codec, 0x14, 0,
+				    AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_UNMUTE);
+
+		msleep(75);
+	}
+}
+
+static void alc222_shutup(struct hda_codec *codec)
+{
+	struct alc_spec *spec = codec->spec;
+	hda_nid_t hp_pin = alc_get_hp_pin(spec);
+	bool hp1_pin_sense, hp2_pin_sense;
+
+	if (!hp_pin)
+		hp_pin = 0x21;
+
+	hp1_pin_sense = snd_hda_jack_detect(codec, hp_pin);
+	hp2_pin_sense = snd_hda_jack_detect(codec, 0x14);
+
+	if (hp1_pin_sense || hp2_pin_sense) {
+		msleep(2);
+
+		if (hp1_pin_sense)
+			snd_hda_codec_write(codec, hp_pin, 0,
+				    AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE);
+		if (hp2_pin_sense)
+			snd_hda_codec_write(codec, 0x14, 0,
+				    AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE);
+
+		msleep(75);
+
+		if (hp1_pin_sense)
+			snd_hda_codec_write(codec, hp_pin, 0,
+				    AC_VERB_SET_PIN_WIDGET_CONTROL, 0x0);
+		if (hp2_pin_sense)
+			snd_hda_codec_write(codec, 0x14, 0,
+				    AC_VERB_SET_PIN_WIDGET_CONTROL, 0x0);
+
+		msleep(75);
+	}
+	alc_auto_setup_eapd(codec, false);
+	alc_shutup_pins(codec);
+}
+
 static void alc_default_init(struct hda_codec *codec)
 {
 	struct alc_spec *spec = codec->spec;
@@ -11907,8 +11980,11 @@ static int patch_alc269(struct hda_codec *codec)
 		spec->codec_variant = ALC269_TYPE_ALC300;
 		spec->gen.mixer_nid = 0; /* no loopback on ALC300 */
 		break;
+	case 0x10ec0222:
 	case 0x10ec0623:
 		spec->codec_variant = ALC269_TYPE_ALC623;
+		spec->shutup = alc222_shutup;
+		spec->init_hook = alc222_init;
 		break;
 	case 0x10ec0700:
 	case 0x10ec0701:

From 1ee5aa765c22a0577ec552d460bf2035300b4b51 Mon Sep 17 00:00:00 2001
From: Hoku Ishibe <me@hokuishi.be>
Date: Sun, 23 Feb 2025 21:05:17 -0500
Subject: [PATCH 0970/1173] ALSA: hda: intel: Add Dell ALC3271 to power_save
 denylist

Dell XPS 13 7390 with the Realtek ALC3271 codec experiences
persistent humming noise when the power_save mode is enabled.
This issue occurs when the codec enters power saving mode,
leading to unwanted noise from the speakers.

This patch adds the affected model (PCI ID 0x1028:0x0962) to the
power_save denylist to ensure power_save is disabled by default,
preventing power-off related noise issues.

Steps to Reproduce
1. Boot the system with `snd_hda_intel` loaded.
2. Verify that `power_save` mode is enabled:
```sh
cat /sys/module/snd_hda_intel/parameters/power_save
````
output: 10 (default power save timeout)
3. Wait for the power save timeout
4. Observe a persistent humming noise from the speakers
5. Disable `power_save` manually:
```sh
echo 0 | sudo tee /sys/module/snd_hda_intel/parameters/power_save
````
6. Confirm that the noise disappears immediately.

This issue has been observed on my system, and this patch
successfully eliminates the unwanted noise. If other users
experience similar issues, additional reports would be helpful.

Signed-off-by: Hoku Ishibe <me@hokuishi.be>
Cc: <stable@vger.kernel.org>
Link: https://patch.msgid.link/20250224020517.51035-1-me@hokuishi.be
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/hda_intel.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 67540e0373099..e67c22c59f02b 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -2232,6 +2232,8 @@ static const struct snd_pci_quirk power_save_denylist[] = {
 	SND_PCI_QUIRK(0x1631, 0xe017, "Packard Bell NEC IMEDIA 5204", 0),
 	/* KONTRON SinglePC may cause a stall at runtime resume */
 	SND_PCI_QUIRK(0x1734, 0x1232, "KONTRON SinglePC", 0),
+	/* Dell ALC3271 */
+	SND_PCI_QUIRK(0x1028, 0x0962, "Dell ALC3271", 0),
 	{}
 };
 

From 50dc696c3a482ea35bd0691f728d47e40b668483 Mon Sep 17 00:00:00 2001
From: Aiden Ma <jiaheng.ma@foxmail.com>
Date: Tue, 4 Mar 2025 19:54:01 +0800
Subject: [PATCH 0971/1173] doc: correcting two prefix errors in idmappings.rst

Add the 'k' prefix to id 21000. And id `u1000` in the third
idmapping should be mapped to `k31000`, not `u31000`.

Signed-off-by: Aiden Ma <jiaheng.ma@foxmail.com>
Link: https://lore.kernel.org/r/tencent_4E7B1F143E8051530C21FCADF4E014DCBB06@qq.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 Documentation/filesystems/idmappings.rst | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/filesystems/idmappings.rst b/Documentation/filesystems/idmappings.rst
index 77930c77fcfe6..2a206129f8284 100644
--- a/Documentation/filesystems/idmappings.rst
+++ b/Documentation/filesystems/idmappings.rst
@@ -63,8 +63,8 @@ what id ``k11000`` corresponds to in the second or third idmapping. The
 straightforward algorithm to use is to apply the inverse of the first idmapping,
 mapping ``k11000`` up to ``u1000``. Afterwards, we can map ``u1000`` down using
 either the second idmapping mapping or third idmapping mapping. The second
-idmapping would map ``u1000`` down to ``21000``. The third idmapping would map
-``u1000`` down to ``u31000``.
+idmapping would map ``u1000`` down to ``k21000``. The third idmapping would map
+``u1000`` down to ``k31000``.
 
 If we were given the same task for the following three idmappings::
 

From da02f54e81db2f7bf6af9d1d0cfc5b41ec6d0dcb Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 5 Feb 2025 11:21:28 +0100
Subject: [PATCH 0972/1173] perf/core: Clean up perf_try_init_event()

Make sure that perf_try_init_event() doesn't leave event->pmu nor
event->destroy set on failure.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Ravi Bangoria <ravi.bangoria@amd.com>
Link: https://lore.kernel.org/r/20250205102449.110145835@infradead.org
---
 kernel/events/core.c | 65 ++++++++++++++++++++++++++------------------
 1 file changed, 38 insertions(+), 27 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index b2334d27511b6..f159dbab45300 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -12109,40 +12109,51 @@ static int perf_try_init_event(struct pmu *pmu, struct perf_event *event)
 	if (ctx)
 		perf_event_ctx_unlock(event->group_leader, ctx);
 
-	if (!ret) {
-		if (!(pmu->capabilities & PERF_PMU_CAP_EXTENDED_REGS) &&
-		    has_extended_regs(event))
-			ret = -EOPNOTSUPP;
+	if (ret)
+		goto err_pmu;
 
-		if (pmu->capabilities & PERF_PMU_CAP_NO_EXCLUDE &&
-		    event_has_any_exclude_flag(event))
-			ret = -EINVAL;
+	if (!(pmu->capabilities & PERF_PMU_CAP_EXTENDED_REGS) &&
+	    has_extended_regs(event)) {
+		ret = -EOPNOTSUPP;
+		goto err_destroy;
+	}
 
-		if (pmu->scope != PERF_PMU_SCOPE_NONE && event->cpu >= 0) {
-			const struct cpumask *cpumask = perf_scope_cpu_topology_cpumask(pmu->scope, event->cpu);
-			struct cpumask *pmu_cpumask = perf_scope_cpumask(pmu->scope);
-			int cpu;
-
-			if (pmu_cpumask && cpumask) {
-				cpu = cpumask_any_and(pmu_cpumask, cpumask);
-				if (cpu >= nr_cpu_ids)
-					ret = -ENODEV;
-				else
-					event->event_caps |= PERF_EV_CAP_READ_SCOPE;
-			} else {
-				ret = -ENODEV;
-			}
-		}
+	if (pmu->capabilities & PERF_PMU_CAP_NO_EXCLUDE &&
+	    event_has_any_exclude_flag(event)) {
+		ret = -EINVAL;
+		goto err_destroy;
+	}
 
-		if (ret && event->destroy)
-			event->destroy(event);
+	if (pmu->scope != PERF_PMU_SCOPE_NONE && event->cpu >= 0) {
+		const struct cpumask *cpumask;
+		struct cpumask *pmu_cpumask;
+		int cpu;
+
+		cpumask = perf_scope_cpu_topology_cpumask(pmu->scope, event->cpu);
+		pmu_cpumask = perf_scope_cpumask(pmu->scope);
+
+		ret = -ENODEV;
+		if (!pmu_cpumask || !cpumask)
+			goto err_destroy;
+
+		cpu = cpumask_any_and(pmu_cpumask, cpumask);
+		if (cpu >= nr_cpu_ids)
+			goto err_destroy;
+
+		event->event_caps |= PERF_EV_CAP_READ_SCOPE;
 	}
 
-	if (ret) {
-		event->pmu = NULL;
-		module_put(pmu->module);
+	return 0;
+
+err_destroy:
+	if (event->destroy) {
+		event->destroy(event);
+		event->destroy = NULL;
 	}
 
+err_pmu:
+	event->pmu = NULL;
+	module_put(pmu->module);
 	return ret;
 }
 

From 9ba93cb8212d62bccd8b41b8adb6656abf37280a Mon Sep 17 00:00:00 2001
From: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Date: Wed, 5 Mar 2025 10:28:41 +0530
Subject: [PATCH 0973/1173] platform/x86/amd/pmf: Propagate PMF-TA return codes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In the amd_pmf_invoke_cmd_init() function within the PMF driver ensure
that the actual result from the PMF-TA is returned rather than a generic
EIO. This change allows for proper handling of errors originating from the
PMF-TA.

Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Co-developed-by: Patil Rajesh Reddy <Patil.Reddy@amd.com>
Signed-off-by: Patil Rajesh Reddy <Patil.Reddy@amd.com>
Signed-off-by: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Link: https://lore.kernel.org/r/20250305045842.4117767-1-Shyam-sundar.S-k@amd.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/amd/pmf/tee-if.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/platform/x86/amd/pmf/tee-if.c b/drivers/platform/x86/amd/pmf/tee-if.c
index 8c88769ea1d87..b404764550c4c 100644
--- a/drivers/platform/x86/amd/pmf/tee-if.c
+++ b/drivers/platform/x86/amd/pmf/tee-if.c
@@ -323,7 +323,7 @@ static int amd_pmf_start_policy_engine(struct amd_pmf_dev *dev)
 	} else {
 		dev_err(dev->dev, "ta invoke cmd init failed err: %x\n", res);
 		dev->smart_pc_enabled = false;
-		return -EIO;
+		return res;
 	}
 
 	return 0;

From 376a8c2a144397d9cf2a67d403dd64f4a7ff9104 Mon Sep 17 00:00:00 2001
From: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Date: Wed, 5 Mar 2025 10:28:42 +0530
Subject: [PATCH 0974/1173] platform/x86/amd/pmf: Update PMF Driver for
 Compatibility with new PMF-TA
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The PMF driver allocates a shared memory buffer using
tee_shm_alloc_kernel_buf() for communication with the PMF-TA.

The latest PMF-TA version introduces new structures with OEM debug
information and additional policy input conditions for evaluating the
policy binary. Consequently, the shared memory size must be increased to
ensure compatibility between the PMF driver and the updated PMF-TA.

To do so, introduce the new PMF-TA UUID and update the PMF shared memory
configuration to ensure compatibility with the latest PMF-TA version.
Additionally, export the TA UUID.

These updates will result in modifications to the prototypes of
amd_pmf_tee_init() and amd_pmf_ta_open_session().

Link: https://lore.kernel.org/all/55ac865f-b1c7-fa81-51c4-d211c7963e7e@linux.intel.com/
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Co-developed-by: Patil Rajesh Reddy <Patil.Reddy@amd.com>
Signed-off-by: Patil Rajesh Reddy <Patil.Reddy@amd.com>
Signed-off-by: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Link: https://lore.kernel.org/r/20250305045842.4117767-2-Shyam-sundar.S-k@amd.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/amd/pmf/pmf.h    |  5 ++-
 drivers/platform/x86/amd/pmf/tee-if.c | 50 +++++++++++++++++++--------
 2 files changed, 40 insertions(+), 15 deletions(-)

diff --git a/drivers/platform/x86/amd/pmf/pmf.h b/drivers/platform/x86/amd/pmf/pmf.h
index 41b2b91b8fdc6..e6bdee68ccf34 100644
--- a/drivers/platform/x86/amd/pmf/pmf.h
+++ b/drivers/platform/x86/amd/pmf/pmf.h
@@ -106,9 +106,12 @@ struct cookie_header {
 #define PMF_TA_IF_VERSION_MAJOR				1
 #define TA_PMF_ACTION_MAX					32
 #define TA_PMF_UNDO_MAX						8
-#define TA_OUTPUT_RESERVED_MEM				906
+#define TA_OUTPUT_RESERVED_MEM				922
 #define MAX_OPERATION_PARAMS					4
 
+#define TA_ERROR_CRYPTO_INVALID_PARAM				0x20002
+#define TA_ERROR_CRYPTO_BIN_TOO_LARGE				0x2000d
+
 #define PMF_IF_V1		1
 #define PMF_IF_V2		2
 
diff --git a/drivers/platform/x86/amd/pmf/tee-if.c b/drivers/platform/x86/amd/pmf/tee-if.c
index b404764550c4c..ceaff1ebb7b93 100644
--- a/drivers/platform/x86/amd/pmf/tee-if.c
+++ b/drivers/platform/x86/amd/pmf/tee-if.c
@@ -27,8 +27,11 @@ module_param(pb_side_load, bool, 0444);
 MODULE_PARM_DESC(pb_side_load, "Sideload policy binaries debug policy failures");
 #endif
 
-static const uuid_t amd_pmf_ta_uuid = UUID_INIT(0x6fd93b77, 0x3fb8, 0x524d,
-						0xb1, 0x2d, 0xc5, 0x29, 0xb1, 0x3d, 0x85, 0x43);
+static const uuid_t amd_pmf_ta_uuid[] = { UUID_INIT(0xd9b39bf2, 0x66bd, 0x4154, 0xaf, 0xb8, 0x8a,
+						    0xcc, 0x2b, 0x2b, 0x60, 0xd6),
+					  UUID_INIT(0x6fd93b77, 0x3fb8, 0x524d, 0xb1, 0x2d, 0xc5,
+						    0x29, 0xb1, 0x3d, 0x85, 0x43),
+					};
 
 static const char *amd_pmf_uevent_as_str(unsigned int state)
 {
@@ -321,7 +324,7 @@ static int amd_pmf_start_policy_engine(struct amd_pmf_dev *dev)
 		 */
 		schedule_delayed_work(&dev->pb_work, msecs_to_jiffies(pb_actions_ms * 3));
 	} else {
-		dev_err(dev->dev, "ta invoke cmd init failed err: %x\n", res);
+		dev_dbg(dev->dev, "ta invoke cmd init failed err: %x\n", res);
 		dev->smart_pc_enabled = false;
 		return res;
 	}
@@ -390,12 +393,12 @@ static int amd_pmf_amdtee_ta_match(struct tee_ioctl_version_data *ver, const voi
 	return ver->impl_id == TEE_IMPL_ID_AMDTEE;
 }
 
-static int amd_pmf_ta_open_session(struct tee_context *ctx, u32 *id)
+static int amd_pmf_ta_open_session(struct tee_context *ctx, u32 *id, const uuid_t *uuid)
 {
 	struct tee_ioctl_open_session_arg sess_arg = {};
 	int rc;
 
-	export_uuid(sess_arg.uuid, &amd_pmf_ta_uuid);
+	export_uuid(sess_arg.uuid, uuid);
 	sess_arg.clnt_login = TEE_IOCTL_LOGIN_PUBLIC;
 	sess_arg.num_params = 0;
 
@@ -434,7 +437,7 @@ static int amd_pmf_register_input_device(struct amd_pmf_dev *dev)
 	return 0;
 }
 
-static int amd_pmf_tee_init(struct amd_pmf_dev *dev)
+static int amd_pmf_tee_init(struct amd_pmf_dev *dev, const uuid_t *uuid)
 {
 	u32 size;
 	int ret;
@@ -445,7 +448,7 @@ static int amd_pmf_tee_init(struct amd_pmf_dev *dev)
 		return PTR_ERR(dev->tee_ctx);
 	}
 
-	ret = amd_pmf_ta_open_session(dev->tee_ctx, &dev->session_id);
+	ret = amd_pmf_ta_open_session(dev->tee_ctx, &dev->session_id, uuid);
 	if (ret) {
 		dev_err(dev->dev, "Failed to open TA session (%d)\n", ret);
 		ret = -EINVAL;
@@ -489,7 +492,8 @@ static void amd_pmf_tee_deinit(struct amd_pmf_dev *dev)
 
 int amd_pmf_init_smart_pc(struct amd_pmf_dev *dev)
 {
-	int ret;
+	bool status;
+	int ret, i;
 
 	ret = apmf_check_smart_pc(dev);
 	if (ret) {
@@ -502,10 +506,6 @@ int amd_pmf_init_smart_pc(struct amd_pmf_dev *dev)
 		return -ENODEV;
 	}
 
-	ret = amd_pmf_tee_init(dev);
-	if (ret)
-		return ret;
-
 	INIT_DELAYED_WORK(&dev->pb_work, amd_pmf_invoke_cmd);
 
 	ret = amd_pmf_set_dram_addr(dev, true);
@@ -534,8 +534,30 @@ int amd_pmf_init_smart_pc(struct amd_pmf_dev *dev)
 		goto error;
 	}
 
-	ret = amd_pmf_start_policy_engine(dev);
-	if (ret)
+	for (i = 0; i < ARRAY_SIZE(amd_pmf_ta_uuid); i++) {
+		ret = amd_pmf_tee_init(dev, &amd_pmf_ta_uuid[i]);
+		if (ret)
+			return ret;
+
+		ret = amd_pmf_start_policy_engine(dev);
+		switch (ret) {
+		case TA_PMF_TYPE_SUCCESS:
+			status = true;
+			break;
+		case TA_ERROR_CRYPTO_INVALID_PARAM:
+		case TA_ERROR_CRYPTO_BIN_TOO_LARGE:
+			amd_pmf_tee_deinit(dev);
+			status = false;
+			break;
+		default:
+			goto error;
+		}
+
+		if (status)
+			break;
+	}
+
+	if (!status && !pb_side_load)
 		goto error;
 
 	if (pb_side_load)

From 12f65d1203507f7db3ba59930fe29a3b8eee9945 Mon Sep 17 00:00:00 2001
From: Koichiro Den <koichiro.den@canonical.com>
Date: Mon, 24 Feb 2025 23:31:26 +0900
Subject: [PATCH 0975/1173] gpio: aggregator: protect driver attr handlers
 against module unload

Both new_device_store and delete_device_store touch module global
resources (e.g. gpio_aggregator_lock). To prevent race conditions with
module unload, a reference needs to be held.

Add try_module_get() in these handlers.

For new_device_store, this eliminates what appears to be the most dangerous
scenario: if an id is allocated from gpio_aggregator_idr but
platform_device_register has not yet been called or completed, a concurrent
module unload could fail to unregister/delete the device, leaving behind a
dangling platform device/GPIO forwarder. This can result in various issues.
The following simple reproducer demonstrates these problems:

  #!/bin/bash
  while :; do
    # note: whether 'gpiochip0 0' exists or not does not matter.
    echo 'gpiochip0 0' > /sys/bus/platform/drivers/gpio-aggregator/new_device
  done &
  while :; do
    modprobe gpio-aggregator
    modprobe -r gpio-aggregator
  done &
  wait

  Starting with the following warning, several kinds of warnings will appear
  and the system may become unstable:

  ------------[ cut here ]------------
  list_del corruption, ffff888103e2e980->next is LIST_POISON1 (dead000000000100)
  WARNING: CPU: 1 PID: 1327 at lib/list_debug.c:56 __list_del_entry_valid_or_report+0xa3/0x120
  [...]
  RIP: 0010:__list_del_entry_valid_or_report+0xa3/0x120
  [...]
  Call Trace:
   <TASK>
   ? __list_del_entry_valid_or_report+0xa3/0x120
   ? __warn.cold+0x93/0xf2
   ? __list_del_entry_valid_or_report+0xa3/0x120
   ? report_bug+0xe6/0x170
   ? __irq_work_queue_local+0x39/0xe0
   ? handle_bug+0x58/0x90
   ? exc_invalid_op+0x13/0x60
   ? asm_exc_invalid_op+0x16/0x20
   ? __list_del_entry_valid_or_report+0xa3/0x120
   gpiod_remove_lookup_table+0x22/0x60
   new_device_store+0x315/0x350 [gpio_aggregator]
   kernfs_fop_write_iter+0x137/0x1f0
   vfs_write+0x262/0x430
   ksys_write+0x60/0xd0
   do_syscall_64+0x6c/0x180
   entry_SYSCALL_64_after_hwframe+0x76/0x7e
   [...]
   </TASK>
  ---[ end trace 0000000000000000 ]---

Fixes: 828546e24280 ("gpio: Add GPIO Aggregator")
Cc: stable@vger.kernel.org
Signed-off-by: Koichiro Den <koichiro.den@canonical.com>
Link: https://lore.kernel.org/r/20250224143134.3024598-2-koichiro.den@canonical.com
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpio-aggregator.c | 20 +++++++++++++++++---
 1 file changed, 17 insertions(+), 3 deletions(-)

diff --git a/drivers/gpio/gpio-aggregator.c b/drivers/gpio/gpio-aggregator.c
index 65f41cc3eafcc..d668ddb2e81d3 100644
--- a/drivers/gpio/gpio-aggregator.c
+++ b/drivers/gpio/gpio-aggregator.c
@@ -119,10 +119,15 @@ static ssize_t new_device_store(struct device_driver *driver, const char *buf,
 	struct platform_device *pdev;
 	int res, id;
 
+	if (!try_module_get(THIS_MODULE))
+		return -ENOENT;
+
 	/* kernfs guarantees string termination, so count + 1 is safe */
 	aggr = kzalloc(sizeof(*aggr) + count + 1, GFP_KERNEL);
-	if (!aggr)
-		return -ENOMEM;
+	if (!aggr) {
+		res = -ENOMEM;
+		goto put_module;
+	}
 
 	memcpy(aggr->args, buf, count + 1);
 
@@ -161,6 +166,7 @@ static ssize_t new_device_store(struct device_driver *driver, const char *buf,
 	}
 
 	aggr->pdev = pdev;
+	module_put(THIS_MODULE);
 	return count;
 
 remove_table:
@@ -175,6 +181,8 @@ static ssize_t new_device_store(struct device_driver *driver, const char *buf,
 	kfree(aggr->lookups);
 free_ga:
 	kfree(aggr);
+put_module:
+	module_put(THIS_MODULE);
 	return res;
 }
 
@@ -203,13 +211,19 @@ static ssize_t delete_device_store(struct device_driver *driver,
 	if (error)
 		return error;
 
+	if (!try_module_get(THIS_MODULE))
+		return -ENOENT;
+
 	mutex_lock(&gpio_aggregator_lock);
 	aggr = idr_remove(&gpio_aggregator_idr, id);
 	mutex_unlock(&gpio_aggregator_lock);
-	if (!aggr)
+	if (!aggr) {
+		module_put(THIS_MODULE);
 		return -ENOENT;
+	}
 
 	gpio_aggregator_free(aggr);
+	module_put(THIS_MODULE);
 	return count;
 }
 static DRIVER_ATTR_WO(delete_device);

From f02c41f87cfe61440c18bf77d1ef0a884b9ee2b5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Niklas=20S=C3=B6derlund?=
 <niklas.soderlund+renesas@ragnatech.se>
Date: Tue, 21 Jan 2025 14:58:33 +0100
Subject: [PATCH 0976/1173] gpio: rcar: Use raw_spinlock to protect register
 access
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use raw_spinlock in order to fix spurious messages about invalid context
when spinlock debugging is enabled. The lock is only used to serialize
register access.

    [    4.239592] =============================
    [    4.239595] [ BUG: Invalid wait context ]
    [    4.239599] 6.13.0-rc7-arm64-renesas-05496-gd088502a519f #35 Not tainted
    [    4.239603] -----------------------------
    [    4.239606] kworker/u8:5/76 is trying to lock:
    [    4.239609] ffff0000091898a0 (&p->lock){....}-{3:3}, at: gpio_rcar_config_interrupt_input_mode+0x34/0x164
    [    4.239641] other info that might help us debug this:
    [    4.239643] context-{5:5}
    [    4.239646] 5 locks held by kworker/u8:5/76:
    [    4.239651]  #0: ffff0000080fb148 ((wq_completion)async){+.+.}-{0:0}, at: process_one_work+0x190/0x62c
    [    4.250180] OF: /soc/sound@ec500000/ports/port@0/endpoint: Read of boolean property 'frame-master' with a value.
    [    4.254094]  #1: ffff80008299bd80 ((work_completion)(&entry->work)){+.+.}-{0:0}, at: process_one_work+0x1b8/0x62c
    [    4.254109]  #2: ffff00000920c8f8
    [    4.258345] OF: /soc/sound@ec500000/ports/port@1/endpoint: Read of boolean property 'bitclock-master' with a value.
    [    4.264803]  (&dev->mutex){....}-{4:4}, at: __device_attach_async_helper+0x3c/0xdc
    [    4.264820]  #3: ffff00000a50ca40 (request_class#2){+.+.}-{4:4}, at: __setup_irq+0xa0/0x690
    [    4.264840]  #4:
    [    4.268872] OF: /soc/sound@ec500000/ports/port@1/endpoint: Read of boolean property 'frame-master' with a value.
    [    4.273275] ffff00000a50c8c8 (lock_class){....}-{2:2}, at: __setup_irq+0xc4/0x690
    [    4.296130] renesas_sdhi_internal_dmac ee100000.mmc: mmc1 base at 0x00000000ee100000, max clock rate 200 MHz
    [    4.304082] stack backtrace:
    [    4.304086] CPU: 1 UID: 0 PID: 76 Comm: kworker/u8:5 Not tainted 6.13.0-rc7-arm64-renesas-05496-gd088502a519f #35
    [    4.304092] Hardware name: Renesas Salvator-X 2nd version board based on r8a77965 (DT)
    [    4.304097] Workqueue: async async_run_entry_fn
    [    4.304106] Call trace:
    [    4.304110]  show_stack+0x14/0x20 (C)
    [    4.304122]  dump_stack_lvl+0x6c/0x90
    [    4.304131]  dump_stack+0x14/0x1c
    [    4.304138]  __lock_acquire+0xdfc/0x1584
    [    4.426274]  lock_acquire+0x1c4/0x33c
    [    4.429942]  _raw_spin_lock_irqsave+0x5c/0x80
    [    4.434307]  gpio_rcar_config_interrupt_input_mode+0x34/0x164
    [    4.440061]  gpio_rcar_irq_set_type+0xd4/0xd8
    [    4.444422]  __irq_set_trigger+0x5c/0x178
    [    4.448435]  __setup_irq+0x2e4/0x690
    [    4.452012]  request_threaded_irq+0xc4/0x190
    [    4.456285]  devm_request_threaded_irq+0x7c/0xf4
    [    4.459398] ata1: link resume succeeded after 1 retries
    [    4.460902]  mmc_gpiod_request_cd_irq+0x68/0xe0
    [    4.470660]  mmc_start_host+0x50/0xac
    [    4.474327]  mmc_add_host+0x80/0xe4
    [    4.477817]  tmio_mmc_host_probe+0x2b0/0x440
    [    4.482094]  renesas_sdhi_probe+0x488/0x6f4
    [    4.486281]  renesas_sdhi_internal_dmac_probe+0x60/0x78
    [    4.491509]  platform_probe+0x64/0xd8
    [    4.495178]  really_probe+0xb8/0x2a8
    [    4.498756]  __driver_probe_device+0x74/0x118
    [    4.503116]  driver_probe_device+0x3c/0x154
    [    4.507303]  __device_attach_driver+0xd4/0x160
    [    4.511750]  bus_for_each_drv+0x84/0xe0
    [    4.515588]  __device_attach_async_helper+0xb0/0xdc
    [    4.520470]  async_run_entry_fn+0x30/0xd8
    [    4.524481]  process_one_work+0x210/0x62c
    [    4.528494]  worker_thread+0x1ac/0x340
    [    4.532245]  kthread+0x10c/0x110
    [    4.535476]  ret_from_fork+0x10/0x20

Signed-off-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250121135833.3769310-1-niklas.soderlund+renesas@ragnatech.se
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpio-rcar.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/gpio/gpio-rcar.c b/drivers/gpio/gpio-rcar.c
index 2ecee3269a0cc..8e0544e924886 100644
--- a/drivers/gpio/gpio-rcar.c
+++ b/drivers/gpio/gpio-rcar.c
@@ -40,7 +40,7 @@ struct gpio_rcar_info {
 
 struct gpio_rcar_priv {
 	void __iomem *base;
-	spinlock_t lock;
+	raw_spinlock_t lock;
 	struct device *dev;
 	struct gpio_chip gpio_chip;
 	unsigned int irq_parent;
@@ -123,7 +123,7 @@ static void gpio_rcar_config_interrupt_input_mode(struct gpio_rcar_priv *p,
 	 * "Setting Level-Sensitive Interrupt Input Mode"
 	 */
 
-	spin_lock_irqsave(&p->lock, flags);
+	raw_spin_lock_irqsave(&p->lock, flags);
 
 	/* Configure positive or negative logic in POSNEG */
 	gpio_rcar_modify_bit(p, POSNEG, hwirq, !active_high_rising_edge);
@@ -142,7 +142,7 @@ static void gpio_rcar_config_interrupt_input_mode(struct gpio_rcar_priv *p,
 	if (!level_trigger)
 		gpio_rcar_write(p, INTCLR, BIT(hwirq));
 
-	spin_unlock_irqrestore(&p->lock, flags);
+	raw_spin_unlock_irqrestore(&p->lock, flags);
 }
 
 static int gpio_rcar_irq_set_type(struct irq_data *d, unsigned int type)
@@ -246,7 +246,7 @@ static void gpio_rcar_config_general_input_output_mode(struct gpio_chip *chip,
 	 * "Setting General Input Mode"
 	 */
 
-	spin_lock_irqsave(&p->lock, flags);
+	raw_spin_lock_irqsave(&p->lock, flags);
 
 	/* Configure positive logic in POSNEG */
 	gpio_rcar_modify_bit(p, POSNEG, gpio, false);
@@ -261,7 +261,7 @@ static void gpio_rcar_config_general_input_output_mode(struct gpio_chip *chip,
 	if (p->info.has_outdtsel && output)
 		gpio_rcar_modify_bit(p, OUTDTSEL, gpio, false);
 
-	spin_unlock_irqrestore(&p->lock, flags);
+	raw_spin_unlock_irqrestore(&p->lock, flags);
 }
 
 static int gpio_rcar_request(struct gpio_chip *chip, unsigned offset)
@@ -347,7 +347,7 @@ static int gpio_rcar_get_multiple(struct gpio_chip *chip, unsigned long *mask,
 		return 0;
 	}
 
-	spin_lock_irqsave(&p->lock, flags);
+	raw_spin_lock_irqsave(&p->lock, flags);
 	outputs = gpio_rcar_read(p, INOUTSEL);
 	m = outputs & bankmask;
 	if (m)
@@ -356,7 +356,7 @@ static int gpio_rcar_get_multiple(struct gpio_chip *chip, unsigned long *mask,
 	m = ~outputs & bankmask;
 	if (m)
 		val |= gpio_rcar_read(p, INDT) & m;
-	spin_unlock_irqrestore(&p->lock, flags);
+	raw_spin_unlock_irqrestore(&p->lock, flags);
 
 	bits[0] = val;
 	return 0;
@@ -367,9 +367,9 @@ static void gpio_rcar_set(struct gpio_chip *chip, unsigned offset, int value)
 	struct gpio_rcar_priv *p = gpiochip_get_data(chip);
 	unsigned long flags;
 
-	spin_lock_irqsave(&p->lock, flags);
+	raw_spin_lock_irqsave(&p->lock, flags);
 	gpio_rcar_modify_bit(p, OUTDT, offset, value);
-	spin_unlock_irqrestore(&p->lock, flags);
+	raw_spin_unlock_irqrestore(&p->lock, flags);
 }
 
 static void gpio_rcar_set_multiple(struct gpio_chip *chip, unsigned long *mask,
@@ -386,12 +386,12 @@ static void gpio_rcar_set_multiple(struct gpio_chip *chip, unsigned long *mask,
 	if (!bankmask)
 		return;
 
-	spin_lock_irqsave(&p->lock, flags);
+	raw_spin_lock_irqsave(&p->lock, flags);
 	val = gpio_rcar_read(p, OUTDT);
 	val &= ~bankmask;
 	val |= (bankmask & bits[0]);
 	gpio_rcar_write(p, OUTDT, val);
-	spin_unlock_irqrestore(&p->lock, flags);
+	raw_spin_unlock_irqrestore(&p->lock, flags);
 }
 
 static int gpio_rcar_direction_output(struct gpio_chip *chip, unsigned offset,
@@ -505,7 +505,7 @@ static int gpio_rcar_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	p->dev = dev;
-	spin_lock_init(&p->lock);
+	raw_spin_lock_init(&p->lock);
 
 	/* Get device configuration from DT node */
 	ret = gpio_rcar_parse_dt(p, &npins);

From 6697f819a10b238ccf01998c3f203d65d8374696 Mon Sep 17 00:00:00 2001
From: Yuezhang Mo <Yuezhang.Mo@sony.com>
Date: Fri, 22 Nov 2024 10:50:55 +0800
Subject: [PATCH 0977/1173] exfat: fix just enough dentries but allocate a new
 cluster to dir

This commit fixes the condition for allocating cluster to parent
directory to avoid allocating new cluster to parent directory when
there are just enough empty directory entries at the end of the
parent directory.

Fixes: af02c72d0b62 ("exfat: convert exfat_find_empty_entry() to use dentry cache")
Signed-off-by: Yuezhang Mo <Yuezhang.Mo@sony.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
---
 fs/exfat/namei.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c
index 691dd77b6ab5f..5b16181a4c2e9 100644
--- a/fs/exfat/namei.c
+++ b/fs/exfat/namei.c
@@ -232,7 +232,7 @@ static int exfat_search_empty_slot(struct super_block *sb,
 		dentry = 0;
 	}
 
-	while (dentry + num_entries < total_entries &&
+	while (dentry + num_entries <= total_entries &&
 	       clu.dir != EXFAT_EOF_CLUSTER) {
 		i = dentry & (dentries_per_clu - 1);
 

From 9da33619e0ca53627641bc97d1b93ec741299111 Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Fri, 31 Jan 2025 12:55:55 +0900
Subject: [PATCH 0978/1173] exfat: fix soft lockup in exfat_clear_bitmap

bitmap clear loop will take long time in __exfat_free_cluster()
if data size of file/dir enty is invalid.
If cluster bit in bitmap is already clear, stop clearing bitmap go to
out of loop.

Fixes: 31023864e67a ("exfat: add fat entry operations")
Reported-by: Kun Hu <huk23@m.fudan.edu.cn>, Jiaji Qin <jjtan24@m.fudan.edu.cn>
Reviewed-by: Sungjong Seo <sj1557.seo@samsung.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
---
 fs/exfat/balloc.c   | 10 ++++++++--
 fs/exfat/exfat_fs.h |  2 +-
 fs/exfat/fatent.c   | 11 +++++++----
 3 files changed, 16 insertions(+), 7 deletions(-)

diff --git a/fs/exfat/balloc.c b/fs/exfat/balloc.c
index ce9be95c9172f..9ff825f1502d5 100644
--- a/fs/exfat/balloc.c
+++ b/fs/exfat/balloc.c
@@ -141,7 +141,7 @@ int exfat_set_bitmap(struct inode *inode, unsigned int clu, bool sync)
 	return 0;
 }
 
-void exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync)
+int exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync)
 {
 	int i, b;
 	unsigned int ent_idx;
@@ -150,13 +150,17 @@ void exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync)
 	struct exfat_mount_options *opts = &sbi->options;
 
 	if (!is_valid_cluster(sbi, clu))
-		return;
+		return -EIO;
 
 	ent_idx = CLUSTER_TO_BITMAP_ENT(clu);
 	i = BITMAP_OFFSET_SECTOR_INDEX(sb, ent_idx);
 	b = BITMAP_OFFSET_BIT_IN_SECTOR(sb, ent_idx);
 
+	if (!test_bit_le(b, sbi->vol_amap[i]->b_data))
+		return -EIO;
+
 	clear_bit_le(b, sbi->vol_amap[i]->b_data);
+
 	exfat_update_bh(sbi->vol_amap[i], sync);
 
 	if (opts->discard) {
@@ -171,6 +175,8 @@ void exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync)
 			opts->discard = 0;
 		}
 	}
+
+	return 0;
 }
 
 /*
diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h
index 78be6964a8a08..d30ce18a88b7a 100644
--- a/fs/exfat/exfat_fs.h
+++ b/fs/exfat/exfat_fs.h
@@ -456,7 +456,7 @@ int exfat_count_num_clusters(struct super_block *sb,
 int exfat_load_bitmap(struct super_block *sb);
 void exfat_free_bitmap(struct exfat_sb_info *sbi);
 int exfat_set_bitmap(struct inode *inode, unsigned int clu, bool sync);
-void exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync);
+int exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync);
 unsigned int exfat_find_free_bitmap(struct super_block *sb, unsigned int clu);
 int exfat_count_used_clusters(struct super_block *sb, unsigned int *ret_count);
 int exfat_trim_fs(struct inode *inode, struct fstrim_range *range);
diff --git a/fs/exfat/fatent.c b/fs/exfat/fatent.c
index 9e5492ac409b0..6f3651c6ca91e 100644
--- a/fs/exfat/fatent.c
+++ b/fs/exfat/fatent.c
@@ -175,6 +175,7 @@ static int __exfat_free_cluster(struct inode *inode, struct exfat_chain *p_chain
 		BITMAP_OFFSET_SECTOR_INDEX(sb, CLUSTER_TO_BITMAP_ENT(clu));
 
 	if (p_chain->flags == ALLOC_NO_FAT_CHAIN) {
+		int err;
 		unsigned int last_cluster = p_chain->dir + p_chain->size - 1;
 		do {
 			bool sync = false;
@@ -189,7 +190,9 @@ static int __exfat_free_cluster(struct inode *inode, struct exfat_chain *p_chain
 				cur_cmap_i = next_cmap_i;
 			}
 
-			exfat_clear_bitmap(inode, clu, (sync && IS_DIRSYNC(inode)));
+			err = exfat_clear_bitmap(inode, clu, (sync && IS_DIRSYNC(inode)));
+			if (err)
+				break;
 			clu++;
 			num_clusters++;
 		} while (num_clusters < p_chain->size);
@@ -210,12 +213,13 @@ static int __exfat_free_cluster(struct inode *inode, struct exfat_chain *p_chain
 				cur_cmap_i = next_cmap_i;
 			}
 
-			exfat_clear_bitmap(inode, clu, (sync && IS_DIRSYNC(inode)));
+			if (exfat_clear_bitmap(inode, clu, (sync && IS_DIRSYNC(inode))))
+				break;
 			clu = n_clu;
 			num_clusters++;
 
 			if (err)
-				goto dec_used_clus;
+				break;
 
 			if (num_clusters >= sbi->num_clusters - EXFAT_FIRST_CLUSTER) {
 				/*
@@ -229,7 +233,6 @@ static int __exfat_free_cluster(struct inode *inode, struct exfat_chain *p_chain
 		} while (clu != EXFAT_EOF_CLUSTER);
 	}
 
-dec_used_clus:
 	sbi->used_clusters -= num_clusters;
 	return 0;
 }

From fda94a9919fd632033979ad7765a99ae3cab9289 Mon Sep 17 00:00:00 2001
From: Eric Sandeen <sandeen@redhat.com>
Date: Tue, 11 Feb 2025 14:14:21 -0600
Subject: [PATCH 0979/1173] exfat: short-circuit zero-byte writes in
 exfat_file_write_iter

When generic_write_checks() returns zero, it means that
iov_iter_count() is zero, and there is no work to do.

Simply return success like all other filesystems do, rather than
proceeding down the write path, which today yields an -EFAULT in
generic_perform_write() via the
(fault_in_iov_iter_readable(i, bytes) == bytes) check when bytes
== 0.

Fixes: 11a347fb6cef ("exfat: change to get file size from DataLength")
Reported-by: Noah <kernel-org-10@maxgrass.eu>
Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Reviewed-by: Yuezhang Mo <Yuezhang.Mo@sony.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
---
 fs/exfat/file.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/exfat/file.c b/fs/exfat/file.c
index 05b51e7217838..807349d8ea050 100644
--- a/fs/exfat/file.c
+++ b/fs/exfat/file.c
@@ -587,7 +587,7 @@ static ssize_t exfat_file_write_iter(struct kiocb *iocb, struct iov_iter *iter)
 	valid_size = ei->valid_size;
 
 	ret = generic_write_checks(iocb, iter);
-	if (ret < 0)
+	if (ret <= 0)
 		goto unlock;
 
 	if (iocb->ki_flags & IOCB_DIRECT) {

From 13940cef95491472760ca261b6713692ece9b946 Mon Sep 17 00:00:00 2001
From: Yuezhang Mo <Yuezhang.Mo@sony.com>
Date: Sat, 8 Feb 2025 17:16:58 +0800
Subject: [PATCH 0980/1173] exfat: add a check for invalid data size

Add a check for invalid data size to avoid corrupted filesystem
from being further corrupted.

Signed-off-by: Yuezhang Mo <Yuezhang.Mo@sony.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
---
 fs/exfat/namei.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c
index 5b16181a4c2e9..8b30027d82512 100644
--- a/fs/exfat/namei.c
+++ b/fs/exfat/namei.c
@@ -646,6 +646,11 @@ static int exfat_find(struct inode *dir, struct qstr *qname,
 	info->valid_size = le64_to_cpu(ep2->dentry.stream.valid_size);
 	info->size = le64_to_cpu(ep2->dentry.stream.size);
 
+	if (unlikely(EXFAT_B_TO_CLU_ROUND_UP(info->size, sbi) > sbi->used_clusters)) {
+		exfat_fs_error(sb, "data size is invalid(%lld)", info->size);
+		return -EIO;
+	}
+
 	info->start_clu = le32_to_cpu(ep2->dentry.stream.start_clu);
 	if (!is_valid_cluster(sbi, info->start_clu) && info->size) {
 		exfat_warn(sb, "start_clu is invalid cluster(0x%x)",

From 3c9231ea6497dfc50ac0ef69fff484da27d0df66 Mon Sep 17 00:00:00 2001
From: Jason Xing <kerneljasonxing@gmail.com>
Date: Tue, 4 Mar 2025 08:44:29 +0800
Subject: [PATCH 0981/1173] net-timestamp: support TCP GSO case for a few
 missing flags

When I read through the TSO codes, I found out that we probably
miss initializing the tx_flags of last seg when TSO is turned
off, which means at the following points no more timestamp
(for this last one) will be generated. There are three flags
to be handled in this patch:
1. SKBTX_HW_TSTAMP
2. SKBTX_BPF
3. SKBTX_SCHED_TSTAMP
Note that SKBTX_BPF[1] was added in 6.14.0-rc2 by commit
6b98ec7e882af ("bpf: Add BPF_SOCK_OPS_TSTAMP_SCHED_CB callback")
and only belongs to net-next branch material for now. The common
issue of the above three flags can be fixed by this single patch.

This patch initializes the tx_flags to SKBTX_ANY_TSTAMP like what
the UDP GSO does to make the newly segmented last skb inherit the
tx_flags so that requested timestamp will be generated in each
certain layer, or else that last one has zero value of tx_flags
which leads to no timestamp at all.

Fixes: 4ed2d765dfacc ("net-timestamp: TCP timestamping")
Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_offload.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 2308665b51c53..2dfac79dc78b8 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -13,12 +13,15 @@
 #include <net/tcp.h>
 #include <net/protocol.h>
 
-static void tcp_gso_tstamp(struct sk_buff *skb, unsigned int ts_seq,
+static void tcp_gso_tstamp(struct sk_buff *skb, struct sk_buff *gso_skb,
 			   unsigned int seq, unsigned int mss)
 {
+	u32 flags = skb_shinfo(gso_skb)->tx_flags & SKBTX_ANY_TSTAMP;
+	u32 ts_seq = skb_shinfo(gso_skb)->tskey;
+
 	while (skb) {
 		if (before(ts_seq, seq + mss)) {
-			skb_shinfo(skb)->tx_flags |= SKBTX_SW_TSTAMP;
+			skb_shinfo(skb)->tx_flags |= flags;
 			skb_shinfo(skb)->tskey = ts_seq;
 			return;
 		}
@@ -193,8 +196,8 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 	th = tcp_hdr(skb);
 	seq = ntohl(th->seq);
 
-	if (unlikely(skb_shinfo(gso_skb)->tx_flags & SKBTX_SW_TSTAMP))
-		tcp_gso_tstamp(segs, skb_shinfo(gso_skb)->tskey, seq, mss);
+	if (unlikely(skb_shinfo(gso_skb)->tx_flags & SKBTX_ANY_TSTAMP))
+		tcp_gso_tstamp(segs, gso_skb, seq, mss);
 
 	newcheck = ~csum_fold(csum_add(csum_unfold(th->check), delta));
 

From 5ac60242b0173be83709603ebaf27a473f16c4e4 Mon Sep 17 00:00:00 2001
From: Uday Shankar <ushankar@purestorage.com>
Date: Tue, 4 Mar 2025 14:34:26 -0700
Subject: [PATCH 0982/1173] ublk: set_params: properly check if parameters can
 be applied

The parameters set by the set_params call are only applied to the block
device in the start_dev call. So if a device has already been started, a
subsequently issued set_params on that device will not have the desired
effect, and should return an error. There is an existing check for this
- set_params fails on devices in the LIVE state. But this check is not
sufficient to cover the recovery case. In this case, the device will be
in the QUIESCED or FAIL_IO states, so set_params will succeed. But this
success is misleading, because the parameters will not be applied, since
the device has already been started (by a previous ublk server). The bit
UB_STATE_USED is set on completion of the start_dev; use it to detect
and fail set_params commands which arrive too late to be applied (after
start_dev).

Signed-off-by: Uday Shankar <ushankar@purestorage.com>
Fixes: 0aa73170eba5 ("ublk_drv: add SET_PARAMS/GET_PARAMS control command")
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250304-set_params-v1-1-17b5e0887606@purestorage.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/ublk_drv.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 529085181f355..ca9a67b5b537a 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -2715,9 +2715,12 @@ static int ublk_ctrl_set_params(struct ublk_device *ub,
 	if (ph.len > sizeof(struct ublk_params))
 		ph.len = sizeof(struct ublk_params);
 
-	/* parameters can only be changed when device isn't live */
 	mutex_lock(&ub->mutex);
-	if (ub->dev_info.state == UBLK_S_DEV_LIVE) {
+	if (test_bit(UB_STATE_USED, &ub->state)) {
+		/*
+		 * Parameters can only be changed when device hasn't
+		 * been started yet
+		 */
 		ret = -EACCES;
 	} else if (copy_from_user(&ub->params, argp, ph.len)) {
 		ret = -EFAULT;

From e06472bab2a5393430cc2fbc3211cd3602422c1e Mon Sep 17 00:00:00 2001
From: Olivier Gayot <olivier.gayot@canonical.com>
Date: Wed, 5 Mar 2025 10:21:54 +0800
Subject: [PATCH 0983/1173] block: fix conversion of GPT partition name to
 7-bit
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The utf16_le_to_7bit function claims to, naively, convert a UTF-16
string to a 7-bit ASCII string. By naively, we mean that it:
 * drops the first byte of every character in the original UTF-16 string
 * checks if all characters are printable, and otherwise replaces them
   by exclamation mark "!".

This means that theoretically, all characters outside the 7-bit ASCII
range should be replaced by another character. Examples:

 * lower-case alpha (ɒ) 0x0252 becomes 0x52 (R)
 * ligature OE (œ) 0x0153 becomes 0x53 (S)
 * hangul letter pieup (ㅂ) 0x3142 becomes 0x42 (B)
 * upper-case gamma (Ɣ) 0x0194 becomes 0x94 (not printable) so gets
   replaced by "!"

The result of this conversion for the GPT partition name is passed to
user-space as PARTNAME via udev, which is confusing and feels questionable.

However, there is a flaw in the conversion function itself. By dropping
one byte of each character and using isprint() to check if the remaining
byte corresponds to a printable character, we do not actually guarantee
that the resulting character is 7-bit ASCII.

This happens because we pass 8-bit characters to isprint(), which
in the kernel returns 1 for many values > 0x7f - as defined in ctype.c.

This results in many values which should be replaced by "!" to be kept
as-is, despite not being valid 7-bit ASCII. Examples:

 * e with acute accent (é) 0x00E9 becomes 0xE9 - kept as-is because
   isprint(0xE9) returns 1.
 * euro sign (€) 0x20AC becomes 0xAC - kept as-is because isprint(0xAC)
   returns 1.

This way has broken pyudev utility[1], fixes it by using a mask of 7 bits
instead of 8 bits before calling isprint.

Link: https://github.com/pyudev/pyudev/issues/490#issuecomment-2685794648 [1]
Link: https://lore.kernel.org/linux-block/4cac90c2-e414-4ebb-ae62-2a4589d9dc6e@canonical.com/
Cc: Mulhern <amulhern@redhat.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: stable@vger.kernel.org
Signed-off-by: Olivier Gayot <olivier.gayot@canonical.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250305022154.3903128-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/partitions/efi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/block/partitions/efi.c b/block/partitions/efi.c
index 5e9be13a56a82..7acba66eed481 100644
--- a/block/partitions/efi.c
+++ b/block/partitions/efi.c
@@ -682,7 +682,7 @@ static void utf16_le_to_7bit(const __le16 *in, unsigned int size, u8 *out)
 	out[size] = 0;
 
 	while (i < size) {
-		u8 c = le16_to_cpu(in[i]) & 0xff;
+		u8 c = le16_to_cpu(in[i]) & 0x7f;
 
 		if (c && !isprint(c))
 			c = '!';

From dc9a260e96d57cc60482a147205e60de35833d08 Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@surriel.com>
Date: Tue, 25 Feb 2025 22:00:37 -0500
Subject: [PATCH 0984/1173] x86/mm: Add INVLPGB feature and Kconfig entry

In addition, the CPU advertises the maximum number of pages that can be
shot down with one INVLPGB instruction in CPUID. Save that information
for later use.

  [ bp: use cpu_has(), typos, massage. ]

Signed-off-by: Rik van Riel <riel@surriel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20250226030129.530345-3-riel@surriel.com
---
 arch/x86/Kconfig.cpu                     | 4 ++++
 arch/x86/include/asm/cpufeatures.h       | 1 +
 arch/x86/include/asm/disabled-features.h | 8 +++++++-
 arch/x86/include/asm/tlbflush.h          | 3 +++
 arch/x86/kernel/cpu/amd.c                | 6 ++++++
 5 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 2a7279d80460a..25c55cc17c5e0 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -401,6 +401,10 @@ menuconfig PROCESSOR_SELECT
 	  This lets you choose what x86 vendor support code your kernel
 	  will include.
 
+config BROADCAST_TLB_FLUSH
+	def_bool y
+	depends on CPU_SUP_AMD && 64BIT
+
 config CPU_SUP_INTEL
 	default y
 	bool "Support Intel processors" if PROCESSOR_SELECT
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 508c0dad116bc..8770dc185fe91 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -338,6 +338,7 @@
 #define X86_FEATURE_CLZERO		(13*32+ 0) /* "clzero" CLZERO instruction */
 #define X86_FEATURE_IRPERF		(13*32+ 1) /* "irperf" Instructions Retired Count */
 #define X86_FEATURE_XSAVEERPTR		(13*32+ 2) /* "xsaveerptr" Always save/restore FP error pointers */
+#define X86_FEATURE_INVLPGB		(13*32+ 3) /* INVLPGB and TLBSYNC instructions supported */
 #define X86_FEATURE_RDPRU		(13*32+ 4) /* "rdpru" Read processor register at user level */
 #define X86_FEATURE_WBNOINVD		(13*32+ 9) /* "wbnoinvd" WBNOINVD instruction */
 #define X86_FEATURE_AMD_IBPB		(13*32+12) /* Indirect Branch Prediction Barrier */
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index c492bdc97b059..be8c38855068f 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -129,6 +129,12 @@
 #define DISABLE_SEV_SNP		(1 << (X86_FEATURE_SEV_SNP & 31))
 #endif
 
+#ifdef CONFIG_BROADCAST_TLB_FLUSH
+#define DISABLE_INVLPGB		0
+#else
+#define DISABLE_INVLPGB		(1 << (X86_FEATURE_INVLPGB & 31))
+#endif
+
 /*
  * Make sure to add features to the correct mask
  */
@@ -146,7 +152,7 @@
 #define DISABLED_MASK11	(DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET| \
 			 DISABLE_CALL_DEPTH_TRACKING|DISABLE_USER_SHSTK)
 #define DISABLED_MASK12	(DISABLE_FRED|DISABLE_LAM)
-#define DISABLED_MASK13	0
+#define DISABLED_MASK13	(DISABLE_INVLPGB)
 #define DISABLED_MASK14	0
 #define DISABLED_MASK15	0
 #define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP| \
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 3da6451397485..855c13da2045a 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -183,6 +183,9 @@ static inline void cr4_init_shadow(void)
 extern unsigned long mmu_cr4_features;
 extern u32 *trampoline_cr4_features;
 
+/* How many pages can be invalidated with one INVLPGB. */
+extern u16 invlpgb_count_max;
+
 extern void initialize_tlbstate_and_flush(void);
 
 /*
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 54194f5995de3..7a72ef47a9838 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -29,6 +29,8 @@
 
 #include "cpu.h"
 
+u16 invlpgb_count_max __ro_after_init;
+
 static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
 {
 	u32 gprs[8] = { 0 };
@@ -1139,6 +1141,10 @@ static void cpu_detect_tlb_amd(struct cpuinfo_x86 *c)
 		tlb_lli_2m[ENTRIES] = eax & mask;
 
 	tlb_lli_4m[ENTRIES] = tlb_lli_2m[ENTRIES] >> 1;
+
+	/* Max number of pages INVLPGB can invalidate in one shot */
+	if (cpu_has(c, X86_FEATURE_INVLPGB))
+		invlpgb_count_max = (cpuid_edx(0x80000008) & 0xffff) + 1;
 }
 
 static const struct cpu_dev amd_cpu_dev = {

From 6272c3a217e5837c72c6714d1e7eddd34254fac3 Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@surriel.com>
Date: Fri, 28 Feb 2025 20:32:30 +0100
Subject: [PATCH 0985/1173]  x86/mm: Add INVLPGB support code

Add helper functions and definitions needed to use broadcast TLB
invalidation on AMD CPUs.

  [ bp:
      - Cleanup commit message
      - Improve and expand comments
      - push the preemption guards inside the invlpgb* helpers
      - merge improvements from dhansen
      - add !CONFIG_BROADCAST_TLB_FLUSH function stubs because Clang
	can't do DCE properly yet and looks at the inline asm and
	complains about it getting a u64 argument on 32-bit code ]

Signed-off-by: Rik van Riel <riel@surriel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20250226030129.530345-4-riel@surriel.com
---
 arch/x86/include/asm/tlb.h | 132 +++++++++++++++++++++++++++++++++++++
 1 file changed, 132 insertions(+)

diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h
index 77f52bc1578a7..31f6db40fa0d0 100644
--- a/arch/x86/include/asm/tlb.h
+++ b/arch/x86/include/asm/tlb.h
@@ -6,6 +6,9 @@
 static inline void tlb_flush(struct mmu_gather *tlb);
 
 #include <asm-generic/tlb.h>
+#include <linux/kernel.h>
+#include <vdso/bits.h>
+#include <vdso/page.h>
 
 static inline void tlb_flush(struct mmu_gather *tlb)
 {
@@ -25,4 +28,133 @@ static inline void invlpg(unsigned long addr)
 	asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
 }
 
+enum addr_stride {
+	PTE_STRIDE = 0,
+	PMD_STRIDE = 1
+};
+
+#ifdef CONFIG_BROADCAST_TLB_FLUSH
+/*
+ * INVLPGB does broadcast TLB invalidation across all the CPUs in the system.
+ *
+ * The INVLPGB instruction is weakly ordered, and a batch of invalidations can
+ * be done in a parallel fashion.
+ *
+ * The instruction takes the number of extra pages to invalidate, beyond
+ * the first page, while __invlpgb gets the more human readable number of
+ * pages to invalidate.
+ *
+ * The bits in rax[0:2] determine respectively which components of the address
+ * (VA, PCID, ASID) get compared when flushing. If neither bits are set, *any*
+ * address in the specified range matches.
+ *
+ * TLBSYNC is used to ensure that pending INVLPGB invalidations initiated from
+ * this CPU have completed.
+ */
+static inline void __invlpgb(unsigned long asid, unsigned long pcid,
+			     unsigned long addr, u16 nr_pages,
+			     enum addr_stride stride, u8 flags)
+{
+	u32 edx = (pcid << 16) | asid;
+	u32 ecx = (stride << 31) | (nr_pages - 1);
+	u64 rax = addr | flags;
+
+	/* The low bits in rax are for flags. Verify addr is clean. */
+	VM_WARN_ON_ONCE(addr & ~PAGE_MASK);
+
+	/* INVLPGB; supported in binutils >= 2.36. */
+	asm volatile(".byte 0x0f, 0x01, 0xfe" :: "a" (rax), "c" (ecx), "d" (edx));
+}
+
+static inline void __invlpgb_all(unsigned long asid, unsigned long pcid, u8 flags)
+{
+	__invlpgb(asid, pcid, 0, 1, 0, flags);
+}
+
+static inline void __tlbsync(void)
+{
+	/*
+	 * TLBSYNC waits for INVLPGB instructions originating on the same CPU
+	 * to have completed. Print a warning if the task has been migrated,
+	 * and might not be waiting on all the INVLPGBs issued during this TLB
+	 * invalidation sequence.
+	 */
+	cant_migrate();
+
+	/* TLBSYNC: supported in binutils >= 0.36. */
+	asm volatile(".byte 0x0f, 0x01, 0xff" ::: "memory");
+}
+#else
+/* Some compilers (I'm looking at you clang!) simply can't do DCE */
+static inline void __invlpgb(unsigned long asid, unsigned long pcid,
+			     unsigned long addr, u16 nr_pages,
+			     enum addr_stride s, u8 flags) { }
+static inline void __invlpgb_all(unsigned long asid, unsigned long pcid, u8 flags) { }
+static inline void __tlbsync(void) { }
+#endif
+
+/*
+ * INVLPGB can be targeted by virtual address, PCID, ASID, or any combination
+ * of the three. For example:
+ * - FLAG_VA | FLAG_INCLUDE_GLOBAL: invalidate all TLB entries at the address
+ * - FLAG_PCID:			    invalidate all TLB entries matching the PCID
+ *
+ * The first is used to invalidate (kernel) mappings at a particular
+ * address across all processes.
+ *
+ * The latter invalidates all TLB entries matching a PCID.
+ */
+#define INVLPGB_FLAG_VA			BIT(0)
+#define INVLPGB_FLAG_PCID		BIT(1)
+#define INVLPGB_FLAG_ASID		BIT(2)
+#define INVLPGB_FLAG_INCLUDE_GLOBAL	BIT(3)
+#define INVLPGB_FLAG_FINAL_ONLY		BIT(4)
+#define INVLPGB_FLAG_INCLUDE_NESTED	BIT(5)
+
+/* The implied mode when all bits are clear: */
+#define INVLPGB_MODE_ALL_NONGLOBALS	0UL
+
+static inline void invlpgb_flush_user_nr_nosync(unsigned long pcid,
+						unsigned long addr,
+						u16 nr, bool stride)
+{
+	enum addr_stride str = stride ? PMD_STRIDE : PTE_STRIDE;
+	u8 flags = INVLPGB_FLAG_PCID | INVLPGB_FLAG_VA;
+
+	__invlpgb(0, pcid, addr, nr, str, flags);
+}
+
+/* Flush all mappings for a given PCID, not including globals. */
+static inline void invlpgb_flush_single_pcid_nosync(unsigned long pcid)
+{
+	__invlpgb_all(0, pcid, INVLPGB_FLAG_PCID);
+}
+
+/* Flush all mappings, including globals, for all PCIDs. */
+static inline void invlpgb_flush_all(void)
+{
+	/*
+	 * TLBSYNC at the end needs to make sure all flushes done on the
+	 * current CPU have been executed system-wide. Therefore, make
+	 * sure nothing gets migrated in-between but disable preemption
+	 * as it is cheaper.
+	 */
+	guard(preempt)();
+	__invlpgb_all(0, 0, INVLPGB_FLAG_INCLUDE_GLOBAL);
+	__tlbsync();
+}
+
+/* Flush addr, including globals, for all PCIDs. */
+static inline void invlpgb_flush_addr_nosync(unsigned long addr, u16 nr)
+{
+	__invlpgb(0, 0, addr, nr, PTE_STRIDE, INVLPGB_FLAG_INCLUDE_GLOBAL);
+}
+
+/* Flush all mappings for all PCIDs except globals. */
+static inline void invlpgb_flush_all_nonglobals(void)
+{
+	guard(preempt)();
+	__invlpgb_all(0, 0, INVLPGB_MODE_ALL_NONGLOBALS);
+	__tlbsync();
+}
 #endif /* _ASM_X86_TLB_H */

From ccc19c694b0fe063a90dd27470e9f4ba22990ea1 Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@surriel.com>
Date: Tue, 25 Feb 2025 22:00:39 -0500
Subject: [PATCH 0986/1173] x86/mm: Use INVLPGB for kernel TLB flushes

Use broadcast TLB invalidation for kernel addresses when available.
Remove the need to send IPIs for kernel TLB flushes.

   [ bp: Integrate dhansen's comments additions, merge the
     flush_tlb_all() change into this one too. ]

Signed-off-by: Rik van Riel <riel@surriel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20250226030129.530345-5-riel@surriel.com
---
 arch/x86/mm/tlb.c | 48 +++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 44 insertions(+), 4 deletions(-)

diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index dbcb5c968ff9e..8cd084bc3d987 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -1064,7 +1064,6 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 	mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, end);
 }
 
-
 static void do_flush_tlb_all(void *info)
 {
 	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
@@ -1074,7 +1073,32 @@ static void do_flush_tlb_all(void *info)
 void flush_tlb_all(void)
 {
 	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
-	on_each_cpu(do_flush_tlb_all, NULL, 1);
+
+	/* First try (faster) hardware-assisted TLB invalidation. */
+	if (cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		invlpgb_flush_all();
+	else
+		/* Fall back to the IPI-based invalidation. */
+		on_each_cpu(do_flush_tlb_all, NULL, 1);
+}
+
+/* Flush an arbitrarily large range of memory with INVLPGB. */
+static void invlpgb_kernel_range_flush(struct flush_tlb_info *info)
+{
+	unsigned long addr, nr;
+
+	for (addr = info->start; addr < info->end; addr += nr << PAGE_SHIFT) {
+		nr = (info->end - addr) >> PAGE_SHIFT;
+
+		/*
+		 * INVLPGB has a limit on the size of ranges it can
+		 * flush. Break up large flushes.
+		 */
+		nr = clamp_val(nr, 1, invlpgb_count_max);
+
+		invlpgb_flush_addr_nosync(addr, nr);
+	}
+	__tlbsync();
 }
 
 static void do_kernel_range_flush(void *info)
@@ -1087,6 +1111,22 @@ static void do_kernel_range_flush(void *info)
 		flush_tlb_one_kernel(addr);
 }
 
+static void kernel_tlb_flush_all(struct flush_tlb_info *info)
+{
+	if (cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		invlpgb_flush_all();
+	else
+		on_each_cpu(do_flush_tlb_all, NULL, 1);
+}
+
+static void kernel_tlb_flush_range(struct flush_tlb_info *info)
+{
+	if (cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		invlpgb_kernel_range_flush(info);
+	else
+		on_each_cpu(do_kernel_range_flush, info, 1);
+}
+
 void flush_tlb_kernel_range(unsigned long start, unsigned long end)
 {
 	struct flush_tlb_info *info;
@@ -1097,9 +1137,9 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end)
 				  TLB_GENERATION_INVALID);
 
 	if (info->end == TLB_FLUSH_ALL)
-		on_each_cpu(do_flush_tlb_all, NULL, 1);
+		kernel_tlb_flush_all(info);
 	else
-		on_each_cpu(do_kernel_range_flush, info, 1);
+		kernel_tlb_flush_range(info);
 
 	put_flush_tlb_info();
 }

From 0b3a2f246a5bf016b80a136a9f8c24d886107dc3 Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@surriel.com>
Date: Tue, 25 Feb 2025 22:00:41 -0500
Subject: [PATCH 0987/1173] x86/mm: Use broadcast TLB flushing in page reclaim

Page reclaim tracks only the CPU(s) where the TLB needs to be flushed, rather
than all the individual mappings that may be getting invalidated.

Use broadcast TLB flushing when that is available.

  [ bp: Massage commit message. ]

Signed-off-by: Rik van Riel <riel@surriel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20250226030129.530345-7-riel@surriel.com
---
 arch/x86/mm/tlb.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 8cd084bc3d987..76b4a88afb563 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -1320,7 +1320,9 @@ void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
 	 * a local TLB flush is needed. Optimize this use-case by calling
 	 * flush_tlb_func_local() directly in this case.
 	 */
-	if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids) {
+	if (cpu_feature_enabled(X86_FEATURE_INVLPGB)) {
+		invlpgb_flush_all_nonglobals();
+	} else if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids) {
 		flush_tlb_multi(&batch->cpumask, info);
 	} else if (cpumask_test_cpu(cpu, &batch->cpumask)) {
 		lockdep_assert_irqs_enabled();

From 6a7a65ddfd6d78ca2f075b0fe0a582792081fc03 Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@surriel.com>
Date: Tue, 25 Feb 2025 22:00:42 -0500
Subject: [PATCH 0988/1173] x86/mm: Add global ASID allocation helper functions

Add functions to manage global ASID space. Multithreaded processes that are
simultaneously active on 4 or more CPUs can get a global ASID, resulting in the
same PCID being used for that process on every CPU.

This in turn will allow the kernel to use hardware-assisted TLB flushing
through AMD INVLPGB or Intel RAR for these processes.

  [ bp:
   - Extend use_global_asid() comment
   - s/X86_BROADCAST_TLB_FLUSH/BROADCAST_TLB_FLUSH/g
   - other touchups ]

Signed-off-by: Rik van Riel <riel@surriel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20250226030129.530345-8-riel@surriel.com
---
 arch/x86/include/asm/mmu.h         |  12 +++
 arch/x86/include/asm/mmu_context.h |   2 +
 arch/x86/include/asm/tlbflush.h    |  37 +++++++
 arch/x86/mm/tlb.c                  | 154 ++++++++++++++++++++++++++++-
 4 files changed, 202 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 3b496cdcb74b3..8b8055a8eb9ee 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -69,6 +69,18 @@ typedef struct {
 	u16 pkey_allocation_map;
 	s16 execute_only_pkey;
 #endif
+
+#ifdef CONFIG_BROADCAST_TLB_FLUSH
+	/*
+	 * The global ASID will be a non-zero value when the process has
+	 * the same ASID across all CPUs, allowing it to make use of
+	 * hardware-assisted remote TLB invalidation like AMD INVLPGB.
+	 */
+	u16 global_asid;
+
+	/* The process is transitioning to a new global ASID number. */
+	bool asid_transition;
+#endif
 } mm_context_t;
 
 #define INIT_MM_CONTEXT(mm)						\
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 795fdd53bd0a6..a2c70e495b1b1 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -139,6 +139,8 @@ static inline void mm_reset_untag_mask(struct mm_struct *mm)
 #define enter_lazy_tlb enter_lazy_tlb
 extern void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk);
 
+extern void mm_free_global_asid(struct mm_struct *mm);
+
 /*
  * Init a new mm.  Used on mm copies, like at fork()
  * and on mm's that are brand-new, like at execve().
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 855c13da2045a..f7b374bcdc0b5 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -6,6 +6,7 @@
 #include <linux/mmu_notifier.h>
 #include <linux/sched.h>
 
+#include <asm/barrier.h>
 #include <asm/processor.h>
 #include <asm/cpufeature.h>
 #include <asm/special_insns.h>
@@ -234,6 +235,42 @@ void flush_tlb_one_kernel(unsigned long addr);
 void flush_tlb_multi(const struct cpumask *cpumask,
 		      const struct flush_tlb_info *info);
 
+static inline bool is_dyn_asid(u16 asid)
+{
+	return asid < TLB_NR_DYN_ASIDS;
+}
+
+#ifdef CONFIG_BROADCAST_TLB_FLUSH
+static inline u16 mm_global_asid(struct mm_struct *mm)
+{
+	u16 asid;
+
+	if (!cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		return 0;
+
+	asid = smp_load_acquire(&mm->context.global_asid);
+
+	/* mm->context.global_asid is either 0, or a global ASID */
+	VM_WARN_ON_ONCE(asid && is_dyn_asid(asid));
+
+	return asid;
+}
+
+static inline void mm_assign_global_asid(struct mm_struct *mm, u16 asid)
+{
+	/*
+	 * Notably flush_tlb_mm_range() -> broadcast_tlb_flush() ->
+	 * finish_asid_transition() needs to observe asid_transition = true
+	 * once it observes global_asid.
+	 */
+	mm->context.asid_transition = true;
+	smp_store_release(&mm->context.global_asid, asid);
+}
+#else
+static inline u16 mm_global_asid(struct mm_struct *mm) { return 0; }
+static inline void mm_assign_global_asid(struct mm_struct *mm, u16 asid) { }
+#endif /* CONFIG_BROADCAST_TLB_FLUSH */
+
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #endif
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 76b4a88afb563..6c24d967b77d3 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -74,13 +74,15 @@
  * use different names for each of them:
  *
  * ASID  - [0, TLB_NR_DYN_ASIDS-1]
- *         the canonical identifier for an mm
+ *         the canonical identifier for an mm, dynamically allocated on each CPU
+ *         [TLB_NR_DYN_ASIDS, MAX_ASID_AVAILABLE-1]
+ *         the canonical, global identifier for an mm, identical across all CPUs
  *
- * kPCID - [1, TLB_NR_DYN_ASIDS]
+ * kPCID - [1, MAX_ASID_AVAILABLE]
  *         the value we write into the PCID part of CR3; corresponds to the
  *         ASID+1, because PCID 0 is special.
  *
- * uPCID - [2048 + 1, 2048 + TLB_NR_DYN_ASIDS]
+ * uPCID - [2048 + 1, 2048 + MAX_ASID_AVAILABLE]
  *         for KPTI each mm has two address spaces and thus needs two
  *         PCID values, but we can still do with a single ASID denomination
  *         for each mm. Corresponds to kPCID + 2048.
@@ -251,6 +253,152 @@ static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen,
 	*need_flush = true;
 }
 
+/*
+ * Global ASIDs are allocated for multi-threaded processes that are
+ * active on multiple CPUs simultaneously, giving each of those
+ * processes the same PCID on every CPU, for use with hardware-assisted
+ * TLB shootdown on remote CPUs, like AMD INVLPGB or Intel RAR.
+ *
+ * These global ASIDs are held for the lifetime of the process.
+ */
+static DEFINE_RAW_SPINLOCK(global_asid_lock);
+static u16 last_global_asid = MAX_ASID_AVAILABLE;
+static DECLARE_BITMAP(global_asid_used, MAX_ASID_AVAILABLE);
+static DECLARE_BITMAP(global_asid_freed, MAX_ASID_AVAILABLE);
+static int global_asid_available = MAX_ASID_AVAILABLE - TLB_NR_DYN_ASIDS - 1;
+
+/*
+ * When the search for a free ASID in the global ASID space reaches
+ * MAX_ASID_AVAILABLE, a global TLB flush guarantees that previously
+ * freed global ASIDs are safe to re-use.
+ *
+ * This way the global flush only needs to happen at ASID rollover
+ * time, and not at ASID allocation time.
+ */
+static void reset_global_asid_space(void)
+{
+	lockdep_assert_held(&global_asid_lock);
+
+	invlpgb_flush_all_nonglobals();
+
+	/*
+	 * The TLB flush above makes it safe to re-use the previously
+	 * freed global ASIDs.
+	 */
+	bitmap_andnot(global_asid_used, global_asid_used,
+			global_asid_freed, MAX_ASID_AVAILABLE);
+	bitmap_clear(global_asid_freed, 0, MAX_ASID_AVAILABLE);
+
+	/* Restart the search from the start of global ASID space. */
+	last_global_asid = TLB_NR_DYN_ASIDS;
+}
+
+static u16 allocate_global_asid(void)
+{
+	u16 asid;
+
+	lockdep_assert_held(&global_asid_lock);
+
+	/* The previous allocation hit the edge of available address space */
+	if (last_global_asid >= MAX_ASID_AVAILABLE - 1)
+		reset_global_asid_space();
+
+	asid = find_next_zero_bit(global_asid_used, MAX_ASID_AVAILABLE, last_global_asid);
+
+	if (asid >= MAX_ASID_AVAILABLE && !global_asid_available) {
+		/* This should never happen. */
+		VM_WARN_ONCE(1, "Unable to allocate global ASID despite %d available\n",
+				global_asid_available);
+		return 0;
+	}
+
+	/* Claim this global ASID. */
+	__set_bit(asid, global_asid_used);
+	last_global_asid = asid;
+	global_asid_available--;
+	return asid;
+}
+
+/*
+ * Check whether a process is currently active on more than @threshold CPUs.
+ * This is a cheap estimation on whether or not it may make sense to assign
+ * a global ASID to this process, and use broadcast TLB invalidation.
+ */
+static bool mm_active_cpus_exceeds(struct mm_struct *mm, int threshold)
+{
+	int count = 0;
+	int cpu;
+
+	/* This quick check should eliminate most single threaded programs. */
+	if (cpumask_weight(mm_cpumask(mm)) <= threshold)
+		return false;
+
+	/* Slower check to make sure. */
+	for_each_cpu(cpu, mm_cpumask(mm)) {
+		/* Skip the CPUs that aren't really running this process. */
+		if (per_cpu(cpu_tlbstate.loaded_mm, cpu) != mm)
+			continue;
+
+		if (per_cpu(cpu_tlbstate_shared.is_lazy, cpu))
+			continue;
+
+		if (++count > threshold)
+			return true;
+	}
+	return false;
+}
+
+/*
+ * Assign a global ASID to the current process, protecting against
+ * races between multiple threads in the process.
+ */
+static void use_global_asid(struct mm_struct *mm)
+{
+	u16 asid;
+
+	guard(raw_spinlock_irqsave)(&global_asid_lock);
+
+	/* This process is already using broadcast TLB invalidation. */
+	if (mm_global_asid(mm))
+		return;
+
+	/*
+	 * The last global ASID was consumed while waiting for the lock.
+	 *
+	 * If this fires, a more aggressive ASID reuse scheme might be
+	 * needed.
+	 */
+	if (!global_asid_available) {
+		VM_WARN_ONCE(1, "Ran out of global ASIDs\n");
+		return;
+	}
+
+	asid = allocate_global_asid();
+	if (!asid)
+		return;
+
+	mm_assign_global_asid(mm, asid);
+}
+
+void mm_free_global_asid(struct mm_struct *mm)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		return;
+
+	if (!mm_global_asid(mm))
+		return;
+
+	guard(raw_spinlock_irqsave)(&global_asid_lock);
+
+	/* The global ASID can be re-used only after flush at wrap-around. */
+#ifdef CONFIG_BROADCAST_TLB_FLUSH
+	__set_bit(mm->context.global_asid, global_asid_freed);
+
+	mm->context.global_asid = 0;
+	global_asid_available++;
+#endif
+}
+
 /*
  * Given an ASID, flush the corresponding user ASID.  We can delay this
  * until the next time we switch to it.

From aac0a3aefb99eeaa26c6ddbd4fa208a794648a36 Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@surriel.com>
Date: Tue, 25 Feb 2025 22:00:43 -0500
Subject: [PATCH 0989/1173] x86/mm: Handle global ASID context switch and TLB
 flush

Do context switch and TLB flush support for processes that use a global
ASID and PCID across all CPUs.

At both context switch time and TLB flush time, it needs to be checked whether
a task is switching to a global ASID, and, if so, reload the TLB with the new
ASID as appropriate.

In both code paths, the TLB flush is avoided if a global ASID is used, because
the global ASIDs are always kept up to date across CPUs, even when the
process is not running on a CPU.

  [ bp:
   - Massage
   - :%s/\<static_cpu_has\>/cpu_feature_enabled/cgi
  ]

Signed-off-by: Rik van Riel <riel@surriel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20250226030129.530345-9-riel@surriel.com
---
 arch/x86/include/asm/tlbflush.h | 14 ++++++
 arch/x86/mm/tlb.c               | 77 ++++++++++++++++++++++++++++++---
 2 files changed, 84 insertions(+), 7 deletions(-)

diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index f7b374bcdc0b5..1f61a39a87769 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -240,6 +240,11 @@ static inline bool is_dyn_asid(u16 asid)
 	return asid < TLB_NR_DYN_ASIDS;
 }
 
+static inline bool is_global_asid(u16 asid)
+{
+	return !is_dyn_asid(asid);
+}
+
 #ifdef CONFIG_BROADCAST_TLB_FLUSH
 static inline u16 mm_global_asid(struct mm_struct *mm)
 {
@@ -266,9 +271,18 @@ static inline void mm_assign_global_asid(struct mm_struct *mm, u16 asid)
 	mm->context.asid_transition = true;
 	smp_store_release(&mm->context.global_asid, asid);
 }
+
+static inline bool mm_in_asid_transition(struct mm_struct *mm)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		return false;
+
+	return mm && READ_ONCE(mm->context.asid_transition);
+}
 #else
 static inline u16 mm_global_asid(struct mm_struct *mm) { return 0; }
 static inline void mm_assign_global_asid(struct mm_struct *mm, u16 asid) { }
+static inline bool mm_in_asid_transition(struct mm_struct *mm) { return false; }
 #endif /* CONFIG_BROADCAST_TLB_FLUSH */
 
 #ifdef CONFIG_PARAVIRT
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 6c24d967b77d3..b5681e6f2333e 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -227,6 +227,20 @@ static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen,
 		return;
 	}
 
+	/*
+	 * TLB consistency for global ASIDs is maintained with hardware assisted
+	 * remote TLB flushing. Global ASIDs are always up to date.
+	 */
+	if (cpu_feature_enabled(X86_FEATURE_INVLPGB)) {
+		u16 global_asid = mm_global_asid(next);
+
+		if (global_asid) {
+			*new_asid = global_asid;
+			*need_flush = false;
+			return;
+		}
+	}
+
 	if (this_cpu_read(cpu_tlbstate.invalidate_other))
 		clear_asid_other();
 
@@ -399,6 +413,23 @@ void mm_free_global_asid(struct mm_struct *mm)
 #endif
 }
 
+/*
+ * Is the mm transitioning from a CPU-local ASID to a global ASID?
+ */
+static bool mm_needs_global_asid(struct mm_struct *mm, u16 asid)
+{
+	u16 global_asid = mm_global_asid(mm);
+
+	if (!cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		return false;
+
+	/* Process is transitioning to a global ASID */
+	if (global_asid && asid != global_asid)
+		return true;
+
+	return false;
+}
+
 /*
  * Given an ASID, flush the corresponding user ASID.  We can delay this
  * until the next time we switch to it.
@@ -704,7 +735,8 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
 	 */
 	if (prev == next) {
 		/* Not actually switching mm's */
-		VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) !=
+		VM_WARN_ON(is_dyn_asid(prev_asid) &&
+			   this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) !=
 			   next->context.ctx_id);
 
 		/*
@@ -721,6 +753,20 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
 				 !cpumask_test_cpu(cpu, mm_cpumask(next))))
 			cpumask_set_cpu(cpu, mm_cpumask(next));
 
+		/* Check if the current mm is transitioning to a global ASID */
+		if (mm_needs_global_asid(next, prev_asid)) {
+			next_tlb_gen = atomic64_read(&next->context.tlb_gen);
+			choose_new_asid(next, next_tlb_gen, &new_asid, &need_flush);
+			goto reload_tlb;
+		}
+
+		/*
+		 * Broadcast TLB invalidation keeps this ASID up to date
+		 * all the time.
+		 */
+		if (is_global_asid(prev_asid))
+			return;
+
 		/*
 		 * If the CPU is not in lazy TLB mode, we are just switching
 		 * from one thread in a process to another thread in the same
@@ -754,6 +800,13 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
 		 */
 		cond_mitigation(tsk);
 
+		/*
+		 * Let nmi_uaccess_okay() and finish_asid_transition()
+		 * know that CR3 is changing.
+		 */
+		this_cpu_write(cpu_tlbstate.loaded_mm, LOADED_MM_SWITCHING);
+		barrier();
+
 		/*
 		 * Leave this CPU in prev's mm_cpumask. Atomic writes to
 		 * mm_cpumask can be expensive under contention. The CPU
@@ -768,14 +821,12 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
 		next_tlb_gen = atomic64_read(&next->context.tlb_gen);
 
 		choose_new_asid(next, next_tlb_gen, &new_asid, &need_flush);
-
-		/* Let nmi_uaccess_okay() know that we're changing CR3. */
-		this_cpu_write(cpu_tlbstate.loaded_mm, LOADED_MM_SWITCHING);
-		barrier();
 	}
 
+reload_tlb:
 	new_lam = mm_lam_cr3_mask(next);
 	if (need_flush) {
+		VM_WARN_ON_ONCE(is_global_asid(new_asid));
 		this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
 		this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
 		load_new_mm_cr3(next->pgd, new_asid, new_lam, true);
@@ -894,7 +945,7 @@ static void flush_tlb_func(void *info)
 	const struct flush_tlb_info *f = info;
 	struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm);
 	u32 loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
-	u64 local_tlb_gen = this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].tlb_gen);
+	u64 local_tlb_gen;
 	bool local = smp_processor_id() == f->initiating_cpu;
 	unsigned long nr_invalidate = 0;
 	u64 mm_tlb_gen;
@@ -917,6 +968,16 @@ static void flush_tlb_func(void *info)
 	if (unlikely(loaded_mm == &init_mm))
 		return;
 
+	/* Reload the ASID if transitioning into or out of a global ASID */
+	if (mm_needs_global_asid(loaded_mm, loaded_mm_asid)) {
+		switch_mm_irqs_off(NULL, loaded_mm, NULL);
+		loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
+	}
+
+	/* Broadcast ASIDs are always kept up to date with INVLPGB. */
+	if (is_global_asid(loaded_mm_asid))
+		return;
+
 	VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].ctx_id) !=
 		   loaded_mm->context.ctx_id);
 
@@ -934,6 +995,8 @@ static void flush_tlb_func(void *info)
 		return;
 	}
 
+	local_tlb_gen = this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].tlb_gen);
+
 	if (unlikely(f->new_tlb_gen != TLB_GENERATION_INVALID &&
 		     f->new_tlb_gen <= local_tlb_gen)) {
 		/*
@@ -1101,7 +1164,7 @@ STATIC_NOPV void native_flush_tlb_multi(const struct cpumask *cpumask,
 	 * up on the new contents of what used to be page tables, while
 	 * doing a speculative memory access.
 	 */
-	if (info->freed_tables)
+	if (info->freed_tables || mm_in_asid_transition(info->mm))
 		on_each_cpu_mask(cpumask, flush_tlb_func, (void *)info, true);
 	else
 		on_each_cpu_cond_mask(should_flush_tlb, flush_tlb_func,

From 26a3633bfddfcdd57f5f2e3d157806d68aff5ac4 Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@surriel.com>
Date: Tue, 25 Feb 2025 22:00:44 -0500
Subject: [PATCH 0990/1173] x86/mm: Add global ASID process exit helpers

A global ASID is allocated for the lifetime of a process. Free the global ASID
at process exit time.

  [ bp: Massage, create helpers, hide details inside them. ]

Signed-off-by: Rik van Riel <riel@surriel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20250226030129.530345-10-riel@surriel.com
---
 arch/x86/include/asm/mmu_context.h | 8 +++++++-
 arch/x86/include/asm/tlbflush.h    | 9 +++++++++
 2 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index a2c70e495b1b1..2398058b6e83c 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -2,7 +2,6 @@
 #ifndef _ASM_X86_MMU_CONTEXT_H
 #define _ASM_X86_MMU_CONTEXT_H
 
-#include <asm/desc.h>
 #include <linux/atomic.h>
 #include <linux/mm_types.h>
 #include <linux/pkeys.h>
@@ -13,6 +12,7 @@
 #include <asm/paravirt.h>
 #include <asm/debugreg.h>
 #include <asm/gsseg.h>
+#include <asm/desc.h>
 
 extern atomic64_t last_mm_ctx_id;
 
@@ -139,6 +139,9 @@ static inline void mm_reset_untag_mask(struct mm_struct *mm)
 #define enter_lazy_tlb enter_lazy_tlb
 extern void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk);
 
+#define mm_init_global_asid mm_init_global_asid
+extern void mm_init_global_asid(struct mm_struct *mm);
+
 extern void mm_free_global_asid(struct mm_struct *mm);
 
 /*
@@ -163,6 +166,8 @@ static inline int init_new_context(struct task_struct *tsk,
 		mm->context.execute_only_pkey = -1;
 	}
 #endif
+
+	mm_init_global_asid(mm);
 	mm_reset_untag_mask(mm);
 	init_new_context_ldt(mm);
 	return 0;
@@ -172,6 +177,7 @@ static inline int init_new_context(struct task_struct *tsk,
 static inline void destroy_context(struct mm_struct *mm)
 {
 	destroy_context_ldt(mm);
+	mm_free_global_asid(mm);
 }
 
 extern void switch_mm(struct mm_struct *prev, struct mm_struct *next,
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 1f61a39a87769..e6c3be06dd21c 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -261,6 +261,14 @@ static inline u16 mm_global_asid(struct mm_struct *mm)
 	return asid;
 }
 
+static inline void mm_init_global_asid(struct mm_struct *mm)
+{
+	if (cpu_feature_enabled(X86_FEATURE_INVLPGB)) {
+		mm->context.global_asid = 0;
+		mm->context.asid_transition = false;
+	}
+}
+
 static inline void mm_assign_global_asid(struct mm_struct *mm, u16 asid)
 {
 	/*
@@ -281,6 +289,7 @@ static inline bool mm_in_asid_transition(struct mm_struct *mm)
 }
 #else
 static inline u16 mm_global_asid(struct mm_struct *mm) { return 0; }
+static inline void mm_init_global_asid(struct mm_struct *mm) { }
 static inline void mm_assign_global_asid(struct mm_struct *mm, u16 asid) { }
 static inline bool mm_in_asid_transition(struct mm_struct *mm) { return false; }
 #endif /* CONFIG_BROADCAST_TLB_FLUSH */

From 3b4035ddbfc8e4521f85569998a7569668cccf51 Mon Sep 17 00:00:00 2001
From: Zecheng Li <zecheng@google.com>
Date: Tue, 4 Mar 2025 21:40:31 +0000
Subject: [PATCH 0991/1173] sched/fair: Fix potential memory corruption in
 child_cfs_rq_on_list

child_cfs_rq_on_list attempts to convert a 'prev' pointer to a cfs_rq.
This 'prev' pointer can originate from struct rq's leaf_cfs_rq_list,
making the conversion invalid and potentially leading to memory
corruption. Depending on the relative positions of leaf_cfs_rq_list and
the task group (tg) pointer within the struct, this can cause a memory
fault or access garbage data.

The issue arises in list_add_leaf_cfs_rq, where both
cfs_rq->leaf_cfs_rq_list and rq->leaf_cfs_rq_list are added to the same
leaf list. Also, rq->tmp_alone_branch can be set to rq->leaf_cfs_rq_list.

This adds a check `if (prev == &rq->leaf_cfs_rq_list)` after the main
conditional in child_cfs_rq_on_list. This ensures that the container_of
operation will convert a correct cfs_rq struct.

This check is sufficient because only cfs_rqs on the same CPU are added
to the list, so verifying the 'prev' pointer against the current rq's list
head is enough.

Fixes a potential memory corruption issue that due to current struct
layout might not be manifesting as a crash but could lead to unpredictable
behavior when the layout changes.

Fixes: fdaba61ef8a2 ("sched/fair: Ensure that the CFS parent is added after unthrottling")
Signed-off-by: Zecheng Li <zecheng@google.com>
Reviewed-and-tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20250304214031.2882646-1-zecheng@google.com
---
 kernel/sched/fair.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1c0ef435a7aae..c798d27952431 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4045,15 +4045,17 @@ static inline bool child_cfs_rq_on_list(struct cfs_rq *cfs_rq)
 {
 	struct cfs_rq *prev_cfs_rq;
 	struct list_head *prev;
+	struct rq *rq = rq_of(cfs_rq);
 
 	if (cfs_rq->on_list) {
 		prev = cfs_rq->leaf_cfs_rq_list.prev;
 	} else {
-		struct rq *rq = rq_of(cfs_rq);
-
 		prev = rq->tmp_alone_branch;
 	}
 
+	if (prev == &rq->leaf_cfs_rq_list)
+		return false;
+
 	prev_cfs_rq = container_of(prev, struct cfs_rq, leaf_cfs_rq_list);
 
 	return (prev_cfs_rq->tg->parent == cfs_rq->tg);

From 374c9faac5a763a05bc3f68ad9f73dab3c6aec90 Mon Sep 17 00:00:00 2001
From: Ma Ke <make24@iscas.ac.cn>
Date: Wed, 26 Feb 2025 16:37:31 +0800
Subject: [PATCH 0992/1173] drm/amd/display: Fix null check for
 pipe_ctx->plane_state in resource_build_scaling_params

Null pointer dereference issue could occur when pipe_ctx->plane_state
is null. The fix adds a check to ensure 'pipe_ctx->plane_state' is not
null before accessing. This prevents a null pointer dereference.

Found by code review.

Fixes: 3be5262e353b ("drm/amd/display: Rename more dc_surface stuff to plane_state")
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Ma Ke <make24@iscas.ac.cn>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 63e6a77ccf239337baa9b1e7787cde9fa0462092)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/dc/core/dc_resource.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index 520a34a42827b..a45037cb4cc01 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -1455,7 +1455,8 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 	DC_LOGGER_INIT(pipe_ctx->stream->ctx->logger);
 
 	/* Invalid input */
-	if (!plane_state->dst_rect.width ||
+	if (!plane_state ||
+			!plane_state->dst_rect.width ||
 			!plane_state->dst_rect.height ||
 			!plane_state->src_rect.width ||
 			!plane_state->src_rect.height) {

From fd617ea3b79d2116d53f76cdb5a3601c0ba6e42f Mon Sep 17 00:00:00 2001
From: Andrew Martin <Andrew.Martin@amd.com>
Date: Fri, 28 Feb 2025 11:26:48 -0500
Subject: [PATCH 0993/1173] drm/amdkfd: Fix NULL Pointer Dereference in KFD
 queue

Through KFD IOCTL Fuzzing we encountered a NULL pointer derefrence
when calling kfd_queue_acquire_buffers.

Fixes: 629568d25fea ("drm/amdkfd: Validate queue cwsr area and eop buffer size")
Signed-off-by: Andrew Martin <Andrew.Martin@amd.com>
Reviewed-by: Philip Yang <Philip.Yang@amd.com>
Signed-off-by: Andrew Martin <Andrew.Martin@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 049e5bf3c8406f87c3d8e1958e0a16804fa1d530)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdkfd/kfd_queue.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
index ecccd7adbab4d..24396a2c77bd0 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
@@ -266,8 +266,8 @@ int kfd_queue_acquire_buffers(struct kfd_process_device *pdd, struct queue_prope
 	/* EOP buffer is not required for all ASICs */
 	if (properties->eop_ring_buffer_address) {
 		if (properties->eop_ring_buffer_size != topo_dev->node_props.eop_buffer_size) {
-			pr_debug("queue eop bo size 0x%lx not equal to node eop buf size 0x%x\n",
-				properties->eop_buf_bo->tbo.base.size,
+			pr_debug("queue eop bo size 0x%x not equal to node eop buf size 0x%x\n",
+				properties->eop_ring_buffer_size,
 				topo_dev->node_props.eop_buffer_size);
 			err = -EINVAL;
 			goto out_err_unreserve;

From c27c66afc449b80f3b4b84d123358c0248f2cf63 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Wed, 5 Mar 2025 07:08:09 -1000
Subject: [PATCH 0994/1173] fs/pipe: Fix pipe_occupancy() with 16-bit indexes

The pipe_occupancy() logic implicitly relied on the natural unsigned
modulo arithmetic in C, but that doesn't work for the new 'pipe_index_t'
case, since any arithmetic will be done in 'int' (and here we had also
made it 'unsigned int' due to the function call boundary).

So make the modulo arithmetic explicit by casting the result to the
proper type.

Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Mateusz Guzik <mjguzik@gmail.com>
Cc: Manfred Spraul <manfred@colorfullife.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Swapnil Sapkal <swapnil.sapkal@amd.com>
Cc: Alexey Gladkov <legion@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Link: https://lore.kernel.org/all/CAHk-=wjyHsGLx=rxg6PKYBNkPYAejgo7=CbyL3=HGLZLsAaJFQ@mail.gmail.com/
Fixes: 3d252160b818 ("fs/pipe: Read pipe->{head,tail} atomically outside pipe->mutex")
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/pipe_fs_i.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index 3cc4f8eab853f..1f013ed7577ef 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -192,7 +192,7 @@ static inline bool pipe_empty(unsigned int head, unsigned int tail)
  */
 static inline unsigned int pipe_occupancy(unsigned int head, unsigned int tail)
 {
-	return head - tail;
+	return (pipe_index_t)(head - tail);
 }
 
 /**

From cfced12f5100e50d56bc587299393fd33c1169a9 Mon Sep 17 00:00:00 2001
From: K Prateek Nayak <kprateek.nayak@amd.com>
Date: Wed, 5 Mar 2025 11:23:01 +0000
Subject: [PATCH 0995/1173] include/linux/pipe_fs_i: Add htmldoc annotation for
 "head_tail" member

Add htmldoc annotation for the newly introduced "head_tail" member
describing it to be a union of the pipe_inode_info's @head and @tail
members.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Closes: https://lore.kernel.org/lkml/20250305204609.5e64768e@canb.auug.org.au/
Fixes: 3d252160b818 ("fs/pipe: Read pipe->{head,tail} atomically outside pipe->mutex")
Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/pipe_fs_i.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index 1f013ed7577ef..05ccbc5d01294 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -65,6 +65,7 @@ union pipe_index {
  *	@wr_wait: writer wait point in case of full pipe
  *	@head: The point of buffer production
  *	@tail: The point of buffer consumption
+ *	@head_tail: unsigned long union of @head and @tail
  *	@note_loss: The next read() should insert a data-lost message
  *	@max_usage: The maximum number of slots that may be used in the ring
  *	@ring_size: total number of buffers (should be a power of 2)

From 5e7adc81ae1b27ff565714d2933b291cf1e1271f Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Wed, 5 Mar 2025 13:31:34 +0100
Subject: [PATCH 0996/1173] perf/x86: Annotate struct bts_buffer::buf with
 __counted_by()

Add the __counted_by() compiler attribute to the flexible array member
buf to improve access bounds-checking via CONFIG_UBSAN_BOUNDS and
CONFIG_FORTIFY_SOURCE.

No functional changes intended.

Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250305123134.215577-2-thorsten.blum@linux.dev
---
 arch/x86/events/intel/bts.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index 8e09319544975..953868da82fb4 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -58,7 +58,7 @@ struct bts_buffer {
 	local_t		head;
 	unsigned long	end;
 	void		**data_pages;
-	struct bts_phys	buf[];
+	struct bts_phys	buf[] __counted_by(nr_bufs);
 };
 
 static struct pmu bts_pmu;

From 29ffeb73b216ce3eff10229eb077cf9b7812119d Mon Sep 17 00:00:00 2001
From: Richard Thier <u9vata@gmail.com>
Date: Mon, 17 Jun 2019 23:46:27 +0200
Subject: [PATCH 0997/1173] drm/radeon: Fix rs400_gpu_init for ATI mobility
 radeon Xpress 200M
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

num_gb_pipes was set to a wrong value using r420_pipe_config

This have lead to HyperZ glitches on fast Z clearing.

Closes: https://bugs.freedesktop.org/show_bug.cgi?id=110897
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Richard Thier <u9vata@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 044e59a85c4d84e3c8d004c486e5c479640563a6)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/radeon/r300.c        |  3 ++-
 drivers/gpu/drm/radeon/radeon_asic.h |  1 +
 drivers/gpu/drm/radeon/rs400.c       | 18 ++++++++++++++++--
 3 files changed, 19 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c
index 05c13102a8cb8..d22889fbfa9c8 100644
--- a/drivers/gpu/drm/radeon/r300.c
+++ b/drivers/gpu/drm/radeon/r300.c
@@ -359,7 +359,8 @@ int r300_mc_wait_for_idle(struct radeon_device *rdev)
 	return -1;
 }
 
-static void r300_gpu_init(struct radeon_device *rdev)
+/* rs400_gpu_init also calls this! */
+void r300_gpu_init(struct radeon_device *rdev)
 {
 	uint32_t gb_tile_config, tmp;
 
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index 1e00f6b99f94b..8f5e07834fcc6 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -165,6 +165,7 @@ void r200_set_safe_registers(struct radeon_device *rdev);
  */
 extern int r300_init(struct radeon_device *rdev);
 extern void r300_fini(struct radeon_device *rdev);
+extern void r300_gpu_init(struct radeon_device *rdev);
 extern int r300_suspend(struct radeon_device *rdev);
 extern int r300_resume(struct radeon_device *rdev);
 extern int r300_asic_reset(struct radeon_device *rdev, bool hard);
diff --git a/drivers/gpu/drm/radeon/rs400.c b/drivers/gpu/drm/radeon/rs400.c
index d6c18fd740ec6..13cd0a688a65c 100644
--- a/drivers/gpu/drm/radeon/rs400.c
+++ b/drivers/gpu/drm/radeon/rs400.c
@@ -256,8 +256,22 @@ int rs400_mc_wait_for_idle(struct radeon_device *rdev)
 
 static void rs400_gpu_init(struct radeon_device *rdev)
 {
-	/* FIXME: is this correct ? */
-	r420_pipes_init(rdev);
+	/* Earlier code was calling r420_pipes_init and then
+	 * rs400_mc_wait_for_idle(rdev). The problem is that
+	 * at least on my Mobility Radeon Xpress 200M RC410 card
+	 * that ends up in this code path ends up num_gb_pipes == 3
+	 * while the card seems to have only one pipe. With the
+	 * r420 pipe initialization method.
+	 *
+	 * Problems shown up as HyperZ glitches, see:
+	 * https://bugs.freedesktop.org/show_bug.cgi?id=110897
+	 *
+	 * Delegating initialization to r300 code seems to work
+	 * and results in proper pipe numbers. The rs400 cards
+	 * are said to be not r400, but r300 kind of cards.
+	 */
+	r300_gpu_init(rdev);
+
 	if (rs400_mc_wait_for_idle(rdev)) {
 		pr_warn("rs400: Failed to wait MC idle while programming pipes. Bad things might happen. %08x\n",
 			RREG32(RADEON_MC_STATUS));

From da552bda987420e877500fdd90bd0172e3bf412b Mon Sep 17 00:00:00 2001
From: Kenneth Feng <kenneth.feng@amd.com>
Date: Fri, 28 Feb 2025 17:02:11 +0800
Subject: [PATCH 0998/1173] drm/amd/pm: always allow ih interrupt from fw

always allow ih interrupt from fw on smu v14 based on
the interface requirement

Signed-off-by: Kenneth Feng <kenneth.feng@amd.com>
Reviewed-by: Yang Wang <kevinyang.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit a3199eba46c54324193607d9114a1e321292d7a1)
Cc: stable@vger.kernel.org # 6.12.x
---
 drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c | 12 +-----------
 1 file changed, 1 insertion(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
index 9b2f4fe1578b8..ddb6444406d28 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
@@ -1895,16 +1895,6 @@ static int smu_v14_0_allow_ih_interrupt(struct smu_context *smu)
 				    NULL);
 }
 
-static int smu_v14_0_process_pending_interrupt(struct smu_context *smu)
-{
-	int ret = 0;
-
-	if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_ACDC_BIT))
-		ret = smu_v14_0_allow_ih_interrupt(smu);
-
-	return ret;
-}
-
 int smu_v14_0_enable_thermal_alert(struct smu_context *smu)
 {
 	int ret = 0;
@@ -1916,7 +1906,7 @@ int smu_v14_0_enable_thermal_alert(struct smu_context *smu)
 	if (ret)
 		return ret;
 
-	return smu_v14_0_process_pending_interrupt(smu);
+	return smu_v14_0_allow_ih_interrupt(smu);
 }
 
 int smu_v14_0_disable_thermal_alert(struct smu_context *smu)

From 0d2d0f3d93ddd6556f23c917d910becd9925ddeb Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Wed, 5 Mar 2025 07:35:40 -1000
Subject: [PATCH 0999/1173] fs/pipe: remove buggy and unused 'helper' function

While looking for incorrect users of the pipe head/tail fields (see
commit c27c66afc449: "fs/pipe: Fix pipe_occupancy() with 16-bit
indexes"), I found a bug in pipe_discard_from() that looked entirely
broken.

However, the fix is trivial: this buggy function isn't actually called
by anything, so let's just remove it ASAP.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/pipe_fs_i.h | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index 05ccbc5d01294..e572e6fc4f81f 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -281,15 +281,6 @@ static inline bool pipe_buf_try_steal(struct pipe_inode_info *pipe,
 	return buf->ops->try_steal(pipe, buf);
 }
 
-static inline void pipe_discard_from(struct pipe_inode_info *pipe,
-		unsigned int old_head)
-{
-	unsigned int mask = pipe->ring_size - 1;
-
-	while (pipe->head > old_head)
-		pipe_buf_release(pipe, &pipe->bufs[--pipe->head & mask]);
-}
-
 /* Differs from PIPE_BUF in that PIPE_SIZE is the length of the actual
    memory allocation, whereas PIPE_BUF makes atomicity guarantees.  */
 #define PIPE_SIZE		PAGE_SIZE

From 528361c49962708a60f51a1afafeb00987cebedf Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Wed, 5 Mar 2025 18:52:59 +0300
Subject: [PATCH 1000/1173] nvme-tcp: fix signedness bug in
 nvme_tcp_init_connection()

The kernel_recvmsg() function returns an int which could be either
negative error codes or the number of bytes received.  The problem is
that the condition:

        if (ret < sizeof(*icresp)) {

is type promoted to type unsigned long and negative values are treated
as high positive values which is success, when they should be treated as
failure.  Handle invalid positive returns separately from negative
error codes to avoid this problem.

Fixes: 578539e09690 ("nvme-tcp: fix connect failure on receiving partial ICResp PDU")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Caleb Sander Mateos <csander@purestorage.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/tcp.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 23f11527d29d0..327f3f2f5399c 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1521,11 +1521,11 @@ static int nvme_tcp_init_connection(struct nvme_tcp_queue *queue)
 	msg.msg_flags = MSG_WAITALL;
 	ret = kernel_recvmsg(queue->sock, &msg, &iov, 1,
 			iov.iov_len, msg.msg_flags);
-	if (ret < sizeof(*icresp)) {
+	if (ret >= 0 && ret < sizeof(*icresp))
+		ret = -ECONNRESET;
+	if (ret < 0) {
 		pr_warn("queue %d: failed to receive icresp, error %d\n",
 			nvme_tcp_queue_id(queue), ret);
-		if (ret >= 0)
-			ret = -ECONNRESET;
 		goto free_icresp;
 	}
 	ret = -ENOTCONN;

From f2c11231b57b5163bf16cdfd65271d53d61dd996 Mon Sep 17 00:00:00 2001
From: Stefan Binding <sbinding@opensource.cirrus.com>
Date: Wed, 5 Mar 2025 17:06:45 +0000
Subject: [PATCH 1001/1173] ALSA: hda/realtek: Add support for ASUS ROG Strix
 G814 Laptop using CS35L41 HDA

Add support for ASUS G814PH/PM/PP and G814FH/FM/FP.

Laptops use 2 CS35L41 Amps with HDA, using Internal boost, with I2C.

Signed-off-by: Stefan Binding <sbinding@opensource.cirrus.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/20250305170714.755794-2-sbinding@opensource.cirrus.com
---
 sound/pci/hda/patch_realtek.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 4ca457e7ca9dd..e7612ab492172 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10784,6 +10784,8 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x3a40, "ASUS G814JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
 	SND_PCI_QUIRK(0x1043, 0x3a50, "ASUS G834JYR/JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
 	SND_PCI_QUIRK(0x1043, 0x3a60, "ASUS G634JYR/JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
+	SND_PCI_QUIRK(0x1043, 0x3e00, "ASUS G814FH/FM/FP", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x1043, 0x3e20, "ASUS G814PH/PM/PP", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x3e30, "ASUS TP3607SA", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x1043, 0x3ee0, "ASUS Strix G815_JHR_JMR_JPR", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x1043, 0x3ef0, "ASUS Strix G635LR_LW_LX", ALC287_FIXUP_TAS2781_I2C),

From 16dc157346dd4404b02b42e73b88604be3652039 Mon Sep 17 00:00:00 2001
From: Stefan Binding <sbinding@opensource.cirrus.com>
Date: Wed, 5 Mar 2025 17:06:46 +0000
Subject: [PATCH 1002/1173] ALSA: hda/realtek: Add support for ASUS ROG Strix
 GA603 Laptops using CS35L41 HDA

Add support for ASUS GA603KP, GA603KM and GA603KH.

Laptops use 2 CS35L41 Amps with HDA, using Internal boost, with I2C

Signed-off-by: Stefan Binding <sbinding@opensource.cirrus.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/20250305170714.755794-3-sbinding@opensource.cirrus.com
---
 sound/pci/hda/patch_realtek.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index e7612ab492172..aa9b6e474f69b 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10784,6 +10784,8 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x3a40, "ASUS G814JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
 	SND_PCI_QUIRK(0x1043, 0x3a50, "ASUS G834JYR/JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
 	SND_PCI_QUIRK(0x1043, 0x3a60, "ASUS G634JYR/JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
+	SND_PCI_QUIRK(0x1043, 0x3d78, "ASUS GA603KH", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x1043, 0x3d88, "ASUS GA603KM", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x3e00, "ASUS G814FH/FM/FP", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x3e20, "ASUS G814PH/PM/PP", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x3e30, "ASUS TP3607SA", ALC287_FIXUP_TAS2781_I2C),

From 9120b2b4ad0dad2f6bbb6bcacd0456f806fda62d Mon Sep 17 00:00:00 2001
From: Stefan Binding <sbinding@opensource.cirrus.com>
Date: Wed, 5 Mar 2025 17:06:47 +0000
Subject: [PATCH 1003/1173] ALSA: hda/realtek: Add support for ASUS ROG Strix
 G614 Laptops using CS35L41 HDA

Add support for ASUS G614PH/PM/PP and G614FH/FM/FP.

Laptops use 2 CS35L41 Amps with HDA, using Internal boost, with I2C

Signed-off-by: Stefan Binding <sbinding@opensource.cirrus.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/20250305170714.755794-4-sbinding@opensource.cirrus.com
---
 sound/pci/hda/patch_realtek.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index aa9b6e474f69b..c2ebcd2958c3f 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10676,7 +10676,9 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8e1a, "HP ZBook Firefly 14 G12A", ALC285_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
+	SND_PCI_QUIRK(0x1043, 0x1054, "ASUS G614FH/FM/FP", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
+	SND_PCI_QUIRK(0x1043, 0x1074, "ASUS G614PH/PM/PP", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x10a1, "ASUS UX391UA", ALC294_FIXUP_ASUS_SPK),
 	SND_PCI_QUIRK(0x1043, 0x10a4, "ASUS TP3407SA", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x1043, 0x10c0, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC),

From 859a11917001424776e1cca02b762efcabb4044e Mon Sep 17 00:00:00 2001
From: Stefan Binding <sbinding@opensource.cirrus.com>
Date: Wed, 5 Mar 2025 17:06:48 +0000
Subject: [PATCH 1004/1173] ALSA: hda/realtek: Add support for various ASUS
 Laptops using CS35L41 HDA

Add support for ASUS B3405CVA, B5405CVA, B5605CVA, B3605CVA.

Laptops use 2 CS35L41 Amps with HDA, using Internal boost, with SPI

Signed-off-by: Stefan Binding <sbinding@opensource.cirrus.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/20250305170714.755794-5-sbinding@opensource.cirrus.com
---
 sound/pci/hda/patch_realtek.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index c2ebcd2958c3f..bf89900ec5f50 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10692,6 +10692,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x125e, "ASUS Q524UQK", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x1271, "ASUS X430UN", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x1290, "ASUS X441SA", ALC233_FIXUP_EAPD_COEF_AND_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1043, 0x1294, "ASUS B3405CVA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x12a0, "ASUS X441UV", ALC233_FIXUP_EAPD_COEF_AND_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x12a3, "Asus N7691ZM", ALC269_FIXUP_ASUS_N7601ZM),
 	SND_PCI_QUIRK(0x1043, 0x12af, "ASUS UX582ZS", ALC245_FIXUP_CS35L41_SPI_2),
@@ -10779,6 +10780,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1f63, "ASUS P5405CSA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1f92, "ASUS ROG Flow X16", ALC289_FIXUP_ASUS_GA401),
 	SND_PCI_QUIRK(0x1043, 0x1fb3, "ASUS ROG Flow Z13 GZ302EA", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x1043, 0x3011, "ASUS B5605CVA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2),
 	SND_PCI_QUIRK(0x1043, 0x31d0, "ASUS Zen AIO 27 Z272SD_A272SD", ALC274_FIXUP_ASUS_ZEN_AIO_27),
 	SND_PCI_QUIRK(0x1043, 0x3a20, "ASUS G614JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
@@ -10797,6 +10799,8 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x3f10, "ASUS Strix G835LR_LW_LX", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x1043, 0x3f20, "ASUS Strix G615LR_LW", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x1043, 0x3f30, "ASUS Strix G815LR_LW", ALC287_FIXUP_TAS2781_I2C),
+	SND_PCI_QUIRK(0x1043, 0x3fd0, "ASUS B3605CVA", ALC245_FIXUP_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x3ff0, "ASUS B5405CVA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x831a, "ASUS P901", ALC269_FIXUP_STEREO_DMIC),
 	SND_PCI_QUIRK(0x1043, 0x834a, "ASUS S101", ALC269_FIXUP_STEREO_DMIC),
 	SND_PCI_QUIRK(0x1043, 0x8398, "ASUS P1005", ALC269_FIXUP_STEREO_DMIC),

From 7ab61d0a9a35e32497bcf2233310fec79ee3338f Mon Sep 17 00:00:00 2001
From: Stefan Binding <sbinding@opensource.cirrus.com>
Date: Wed, 5 Mar 2025 17:06:49 +0000
Subject: [PATCH 1005/1173] ALSA: hda/realtek: Add support for ASUS B3405 and
 B3605 Laptops using CS35L41 HDA

Add support for ASUS B3405CCA / P3405CCA, B3605CCA / P3605CCA,
B3405CCA, B3605CCA.

Laptops use 2 CS35L41 Amps with HDA, using Internal boost, with SPI

Signed-off-by: Stefan Binding <sbinding@opensource.cirrus.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/20250305170714.755794-6-sbinding@opensource.cirrus.com
---
 sound/pci/hda/patch_realtek.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index bf89900ec5f50..53d2a267d7989 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10696,6 +10696,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x12a0, "ASUS X441UV", ALC233_FIXUP_EAPD_COEF_AND_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x12a3, "Asus N7691ZM", ALC269_FIXUP_ASUS_N7601ZM),
 	SND_PCI_QUIRK(0x1043, 0x12af, "ASUS UX582ZS", ALC245_FIXUP_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x12b4, "ASUS B3405CCA / P3405CCA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x12e0, "ASUS X541SA", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x12f0, "ASUS X541UV", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1313, "Asus K42JZ", ALC269VB_FIXUP_ASUS_MIC_NO_PRESENCE),
@@ -10782,7 +10783,10 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1fb3, "ASUS ROG Flow Z13 GZ302EA", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x3011, "ASUS B5605CVA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2),
+	SND_PCI_QUIRK(0x1043, 0x3061, "ASUS B3405CCA", ALC245_FIXUP_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x30c1, "ASUS B3605CCA / P3605CCA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x31d0, "ASUS Zen AIO 27 Z272SD_A272SD", ALC274_FIXUP_ASUS_ZEN_AIO_27),
+	SND_PCI_QUIRK(0x1043, 0x31f1, "ASUS B3605CCA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x3a20, "ASUS G614JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
 	SND_PCI_QUIRK(0x1043, 0x3a30, "ASUS G814JVR/JIR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
 	SND_PCI_QUIRK(0x1043, 0x3a40, "ASUS G814JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),

From c86dd79a7c338fff9bebb9503857e07db9845eca Mon Sep 17 00:00:00 2001
From: Stefan Binding <sbinding@opensource.cirrus.com>
Date: Wed, 5 Mar 2025 17:06:50 +0000
Subject: [PATCH 1006/1173] ALSA: hda/realtek: Add support for ASUS B5405 and
 B5605 Laptops using CS35L41 HDA

Add support for ASUS B5605CCA and B5405CCA.

Laptops use 2 CS35L41 Amps with HDA, using Internal boost, with SPI

Signed-off-by: Stefan Binding <sbinding@opensource.cirrus.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/20250305170714.755794-7-sbinding@opensource.cirrus.com
---
 sound/pci/hda/patch_realtek.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 53d2a267d7989..f67ab69c9997c 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10784,8 +10784,12 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x3011, "ASUS B5605CVA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2),
 	SND_PCI_QUIRK(0x1043, 0x3061, "ASUS B3405CCA", ALC245_FIXUP_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x3071, "ASUS B5405CCA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x30c1, "ASUS B3605CCA / P3605CCA", ALC245_FIXUP_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x30d1, "ASUS B5405CCA", ALC245_FIXUP_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x30e1, "ASUS B5605CCA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x31d0, "ASUS Zen AIO 27 Z272SD_A272SD", ALC274_FIXUP_ASUS_ZEN_AIO_27),
+	SND_PCI_QUIRK(0x1043, 0x31e1, "ASUS B5605CCA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x31f1, "ASUS B3605CCA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x3a20, "ASUS G614JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
 	SND_PCI_QUIRK(0x1043, 0x3a30, "ASUS G814JVR/JIR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),

From 8463d2adbe1901247937fcdfe4b525130f6db10b Mon Sep 17 00:00:00 2001
From: Stefan Binding <sbinding@opensource.cirrus.com>
Date: Wed, 5 Mar 2025 17:06:51 +0000
Subject: [PATCH 1007/1173] ALSA: hda/realtek: Add support for ASUS Zenbook
 UM3406KA Laptops using CS35L41 HDA

Laptop uses 2 CS35L41 Amps with HDA, using External boost with I2C

Signed-off-by: Stefan Binding <sbinding@opensource.cirrus.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/20250305170714.755794-8-sbinding@opensource.cirrus.com
---
 sound/pci/hda/patch_realtek.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index f67ab69c9997c..d2a1f836dbbf7 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10686,6 +10686,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x10d3, "ASUS K6500ZC", ALC294_FIXUP_ASUS_SPK),
 	SND_PCI_QUIRK(0x1043, 0x1154, "ASUS TP3607SH", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x1043, 0x115d, "Asus 1015E", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
+	SND_PCI_QUIRK(0x1043, 0x1194, "ASUS UM3406KA", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x11c0, "ASUS X556UR", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x1204, "ASUS Strix G615JHR_JMR_JPR", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x1043, 0x1214, "ASUS Strix G615LH_LM_LP", ALC287_FIXUP_TAS2781_I2C),

From e775e2a060d99180edc5366fb9f4299d0f07b66c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Fri, 28 Feb 2025 08:30:55 +0100
Subject: [PATCH 1008/1173] drm/xe/vm: Validate userptr during gpu vma
 prefetching
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If a userptr vma subject to prefetching was already invalidated
or invalidated during the prefetch operation, the operation would
repeatedly return -EAGAIN which would typically cause an infinite
loop.

Validate the userptr to ensure this doesn't happen.

v2:
- Don't fallthrough from UNMAP to PREFETCH (Matthew Brost)

Fixes: 5bd24e78829a ("drm/xe/vm: Subclass userptr vmas")
Fixes: 617eebb9c480 ("drm/xe: Fix array of binds")
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: <stable@vger.kernel.org> # v6.9+
Suggested-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250228073058.59510-2-thomas.hellstrom@linux.intel.com
(cherry picked from commit 03c346d4d0d85d210d549d43c8cfb3dfb7f20e0a)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_vm.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 30259eba450b5..d2cd227e4d694 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -2286,8 +2286,17 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct drm_gpuva_ops *ops,
 			break;
 		}
 		case DRM_GPUVA_OP_UNMAP:
+			xe_vma_ops_incr_pt_update_ops(vops, op->tile_mask);
+			break;
 		case DRM_GPUVA_OP_PREFETCH:
-			/* FIXME: Need to skip some prefetch ops */
+			vma = gpuva_to_vma(op->base.prefetch.va);
+
+			if (xe_vma_is_userptr(vma)) {
+				err = xe_vma_userptr_pin_pages(to_userptr_vma(vma));
+				if (err)
+					return err;
+			}
+
 			xe_vma_ops_incr_pt_update_ops(vops, op->tile_mask);
 			break;
 		default:

From 1414d95d5805b1dc221d22db9b8dc5287ef083bc Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Fri, 28 Feb 2025 08:30:56 +0100
Subject: [PATCH 1009/1173] drm/xe/vm: Fix a misplaced #endif
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix a (harmless) misplaced #endif leading to declarations
appearing multiple times.

Fixes: 0eb2a18a8fad ("drm/xe: Implement VM snapshot support for BO's and userptr")
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: José Roberto de Souza <jose.souza@intel.com>
Cc: <stable@vger.kernel.org> # v6.12+
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Tejas Upadhyay <tejas.upadhyay@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250228073058.59510-3-thomas.hellstrom@linux.intel.com
(cherry picked from commit fcc20a4c752214b3e25632021c57d7d1d71ee1dd)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_vm.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
index 23adb74428815..256a837c2704a 100644
--- a/drivers/gpu/drm/xe/xe_vm.h
+++ b/drivers/gpu/drm/xe/xe_vm.h
@@ -274,9 +274,9 @@ static inline void vm_dbg(const struct drm_device *dev,
 			  const char *format, ...)
 { /* noop */ }
 #endif
-#endif
 
 struct xe_vm_snapshot *xe_vm_snapshot_capture(struct xe_vm *vm);
 void xe_vm_snapshot_capture_delayed(struct xe_vm_snapshot *snap);
 void xe_vm_snapshot_print(struct xe_vm_snapshot *snap, struct drm_printer *p);
 void xe_vm_snapshot_free(struct xe_vm_snapshot *snap);
+#endif

From 84211b1c0db6b9dbe0020fa97192fb9661617f24 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Fri, 28 Feb 2025 08:30:57 +0100
Subject: [PATCH 1010/1173] drm/xe: Fix fault mode invalidation with unbind
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix fault mode invalidation racing with unbind leading to the
PTE zapping potentially traversing an invalid page-table tree.
Do this by holding the notifier lock across PTE zapping. This
might transfer any contention waiting on the notifier seqlock
read side to the notifier lock read side, but that shouldn't be
a major problem.

At the same time get rid of the open-coded invalidation in the bind
code by relying on the notifier even when the vma bind is not
yet committed.

Finally let userptr invalidation call a dedicated xe_vm function
performing a full invalidation.

Fixes: e8babb280b5e ("drm/xe: Convert multiple bind ops into single job")
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: <stable@vger.kernel.org> # v6.12+
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250228073058.59510-4-thomas.hellstrom@linux.intel.com
(cherry picked from commit 100a5b8dadfca50d91d9a4c9fc01431b42a25cab)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_pt.c       | 38 ++++----------
 drivers/gpu/drm/xe/xe_vm.c       | 85 +++++++++++++++++++++-----------
 drivers/gpu/drm/xe/xe_vm.h       |  8 +++
 drivers/gpu/drm/xe/xe_vm_types.h |  4 +-
 4 files changed, 75 insertions(+), 60 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index 1ddcc7e79a93e..12a627a23eb45 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -1213,42 +1213,22 @@ static int vma_check_userptr(struct xe_vm *vm, struct xe_vma *vma,
 		return 0;
 
 	uvma = to_userptr_vma(vma);
-	notifier_seq = uvma->userptr.notifier_seq;
+	if (xe_pt_userptr_inject_eagain(uvma))
+		xe_vma_userptr_force_invalidate(uvma);
 
-	if (uvma->userptr.initial_bind && !xe_vm_in_fault_mode(vm))
-		return 0;
+	notifier_seq = uvma->userptr.notifier_seq;
 
 	if (!mmu_interval_read_retry(&uvma->userptr.notifier,
-				     notifier_seq) &&
-	    !xe_pt_userptr_inject_eagain(uvma))
+				     notifier_seq))
 		return 0;
 
-	if (xe_vm_in_fault_mode(vm)) {
+	if (xe_vm_in_fault_mode(vm))
 		return -EAGAIN;
-	} else {
-		spin_lock(&vm->userptr.invalidated_lock);
-		list_move_tail(&uvma->userptr.invalidate_link,
-			       &vm->userptr.invalidated);
-		spin_unlock(&vm->userptr.invalidated_lock);
-
-		if (xe_vm_in_preempt_fence_mode(vm)) {
-			struct dma_resv_iter cursor;
-			struct dma_fence *fence;
-			long err;
-
-			dma_resv_iter_begin(&cursor, xe_vm_resv(vm),
-					    DMA_RESV_USAGE_BOOKKEEP);
-			dma_resv_for_each_fence_unlocked(&cursor, fence)
-				dma_fence_enable_sw_signaling(fence);
-			dma_resv_iter_end(&cursor);
-
-			err = dma_resv_wait_timeout(xe_vm_resv(vm),
-						    DMA_RESV_USAGE_BOOKKEEP,
-						    false, MAX_SCHEDULE_TIMEOUT);
-			XE_WARN_ON(err <= 0);
-		}
-	}
 
+	/*
+	 * Just continue the operation since exec or rebind worker
+	 * will take care of rebinding.
+	 */
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index d2cd227e4d694..d54aaa5eaff38 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -579,51 +579,26 @@ static void preempt_rebind_work_func(struct work_struct *w)
 	trace_xe_vm_rebind_worker_exit(vm);
 }
 
-static bool vma_userptr_invalidate(struct mmu_interval_notifier *mni,
-				   const struct mmu_notifier_range *range,
-				   unsigned long cur_seq)
+static void __vma_userptr_invalidate(struct xe_vm *vm, struct xe_userptr_vma *uvma)
 {
-	struct xe_userptr *userptr = container_of(mni, typeof(*userptr), notifier);
-	struct xe_userptr_vma *uvma = container_of(userptr, typeof(*uvma), userptr);
+	struct xe_userptr *userptr = &uvma->userptr;
 	struct xe_vma *vma = &uvma->vma;
-	struct xe_vm *vm = xe_vma_vm(vma);
 	struct dma_resv_iter cursor;
 	struct dma_fence *fence;
 	long err;
 
-	xe_assert(vm->xe, xe_vma_is_userptr(vma));
-	trace_xe_vma_userptr_invalidate(vma);
-
-	if (!mmu_notifier_range_blockable(range))
-		return false;
-
-	vm_dbg(&xe_vma_vm(vma)->xe->drm,
-	       "NOTIFIER: addr=0x%016llx, range=0x%016llx",
-		xe_vma_start(vma), xe_vma_size(vma));
-
-	down_write(&vm->userptr.notifier_lock);
-	mmu_interval_set_seq(mni, cur_seq);
-
-	/* No need to stop gpu access if the userptr is not yet bound. */
-	if (!userptr->initial_bind) {
-		up_write(&vm->userptr.notifier_lock);
-		return true;
-	}
-
 	/*
 	 * Tell exec and rebind worker they need to repin and rebind this
 	 * userptr.
 	 */
 	if (!xe_vm_in_fault_mode(vm) &&
-	    !(vma->gpuva.flags & XE_VMA_DESTROYED) && vma->tile_present) {
+	    !(vma->gpuva.flags & XE_VMA_DESTROYED)) {
 		spin_lock(&vm->userptr.invalidated_lock);
 		list_move_tail(&userptr->invalidate_link,
 			       &vm->userptr.invalidated);
 		spin_unlock(&vm->userptr.invalidated_lock);
 	}
 
-	up_write(&vm->userptr.notifier_lock);
-
 	/*
 	 * Preempt fences turn into schedule disables, pipeline these.
 	 * Note that even in fault mode, we need to wait for binds and
@@ -641,11 +616,35 @@ static bool vma_userptr_invalidate(struct mmu_interval_notifier *mni,
 				    false, MAX_SCHEDULE_TIMEOUT);
 	XE_WARN_ON(err <= 0);
 
-	if (xe_vm_in_fault_mode(vm)) {
+	if (xe_vm_in_fault_mode(vm) && userptr->initial_bind) {
 		err = xe_vm_invalidate_vma(vma);
 		XE_WARN_ON(err);
 	}
+}
 
+static bool vma_userptr_invalidate(struct mmu_interval_notifier *mni,
+				   const struct mmu_notifier_range *range,
+				   unsigned long cur_seq)
+{
+	struct xe_userptr_vma *uvma = container_of(mni, typeof(*uvma), userptr.notifier);
+	struct xe_vma *vma = &uvma->vma;
+	struct xe_vm *vm = xe_vma_vm(vma);
+
+	xe_assert(vm->xe, xe_vma_is_userptr(vma));
+	trace_xe_vma_userptr_invalidate(vma);
+
+	if (!mmu_notifier_range_blockable(range))
+		return false;
+
+	vm_dbg(&xe_vma_vm(vma)->xe->drm,
+	       "NOTIFIER: addr=0x%016llx, range=0x%016llx",
+		xe_vma_start(vma), xe_vma_size(vma));
+
+	down_write(&vm->userptr.notifier_lock);
+	mmu_interval_set_seq(mni, cur_seq);
+
+	__vma_userptr_invalidate(vm, uvma);
+	up_write(&vm->userptr.notifier_lock);
 	trace_xe_vma_userptr_invalidate_complete(vma);
 
 	return true;
@@ -655,6 +654,34 @@ static const struct mmu_interval_notifier_ops vma_userptr_notifier_ops = {
 	.invalidate = vma_userptr_invalidate,
 };
 
+#if IS_ENABLED(CONFIG_DRM_XE_USERPTR_INVAL_INJECT)
+/**
+ * xe_vma_userptr_force_invalidate() - force invalidate a userptr
+ * @uvma: The userptr vma to invalidate
+ *
+ * Perform a forced userptr invalidation for testing purposes.
+ */
+void xe_vma_userptr_force_invalidate(struct xe_userptr_vma *uvma)
+{
+	struct xe_vm *vm = xe_vma_vm(&uvma->vma);
+
+	/* Protect against concurrent userptr pinning */
+	lockdep_assert_held(&vm->lock);
+	/* Protect against concurrent notifiers */
+	lockdep_assert_held(&vm->userptr.notifier_lock);
+	/*
+	 * Protect against concurrent instances of this function and
+	 * the critical exec sections
+	 */
+	xe_vm_assert_held(vm);
+
+	if (!mmu_interval_read_retry(&uvma->userptr.notifier,
+				     uvma->userptr.notifier_seq))
+		uvma->userptr.notifier_seq -= 2;
+	__vma_userptr_invalidate(vm, uvma);
+}
+#endif
+
 int xe_vm_userptr_pin(struct xe_vm *vm)
 {
 	struct xe_userptr_vma *uvma, *next;
diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
index 256a837c2704a..b882bfb31bd05 100644
--- a/drivers/gpu/drm/xe/xe_vm.h
+++ b/drivers/gpu/drm/xe/xe_vm.h
@@ -279,4 +279,12 @@ struct xe_vm_snapshot *xe_vm_snapshot_capture(struct xe_vm *vm);
 void xe_vm_snapshot_capture_delayed(struct xe_vm_snapshot *snap);
 void xe_vm_snapshot_print(struct xe_vm_snapshot *snap, struct drm_printer *p);
 void xe_vm_snapshot_free(struct xe_vm_snapshot *snap);
+
+#if IS_ENABLED(CONFIG_DRM_XE_USERPTR_INVAL_INJECT)
+void xe_vma_userptr_force_invalidate(struct xe_userptr_vma *uvma);
+#else
+static inline void xe_vma_userptr_force_invalidate(struct xe_userptr_vma *uvma)
+{
+}
+#endif
 #endif
diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h
index 7f9a303e51d89..d2511819cdf43 100644
--- a/drivers/gpu/drm/xe/xe_vm_types.h
+++ b/drivers/gpu/drm/xe/xe_vm_types.h
@@ -227,8 +227,8 @@ struct xe_vm {
 		 * up for revalidation. Protected from access with the
 		 * @invalidated_lock. Removing items from the list
 		 * additionally requires @lock in write mode, and adding
-		 * items to the list requires the @userptr.notifer_lock in
-		 * write mode.
+		 * items to the list requires either the @userptr.notifer_lock in
+		 * write mode, OR @lock in write mode.
 		 */
 		struct list_head invalidated;
 	} userptr;

From ae482ec8cd1a85bde3307f71921a7780086fbec0 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Fri, 28 Feb 2025 08:30:58 +0100
Subject: [PATCH 1011/1173] drm/xe: Add staging tree for VM binds
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Concurrent VM bind staging and zapping of PTEs from a userptr notifier
do not work because the view of PTEs is not stable. VM binds cannot
acquire the notifier lock during staging, as memory allocations are
required. To resolve this race condition, use a staging tree for VM
binds that is committed only under the userptr notifier lock during the
final step of the bind. This ensures a consistent view of the PTEs in
the userptr notifier.

A follow up may only use staging for VM in fault mode as this is the
only mode in which the above race exists.

v3:
 - Drop zap PTE change (Thomas)
 - s/xe_pt_entry/xe_pt_entry_staging (Thomas)

Suggested-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: <stable@vger.kernel.org>
Fixes: e8babb280b5e ("drm/xe: Convert multiple bind ops into single job")
Fixes: a708f6501c69 ("drm/xe: Update PT layer with better error handling")
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250228073058.59510-5-thomas.hellstrom@linux.intel.com
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
(cherry picked from commit 6f39b0c5ef0385eae586760d10b9767168037aa5)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_pt.c      | 58 +++++++++++++++++++++++----------
 drivers/gpu/drm/xe/xe_pt_walk.c |  3 +-
 drivers/gpu/drm/xe/xe_pt_walk.h |  4 +++
 3 files changed, 46 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index 12a627a23eb45..dc24baa840924 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -28,6 +28,8 @@ struct xe_pt_dir {
 	struct xe_pt pt;
 	/** @children: Array of page-table child nodes */
 	struct xe_ptw *children[XE_PDES];
+	/** @staging: Array of page-table staging nodes */
+	struct xe_ptw *staging[XE_PDES];
 };
 
 #if IS_ENABLED(CONFIG_DRM_XE_DEBUG_VM)
@@ -48,9 +50,10 @@ static struct xe_pt_dir *as_xe_pt_dir(struct xe_pt *pt)
 	return container_of(pt, struct xe_pt_dir, pt);
 }
 
-static struct xe_pt *xe_pt_entry(struct xe_pt_dir *pt_dir, unsigned int index)
+static struct xe_pt *
+xe_pt_entry_staging(struct xe_pt_dir *pt_dir, unsigned int index)
 {
-	return container_of(pt_dir->children[index], struct xe_pt, base);
+	return container_of(pt_dir->staging[index], struct xe_pt, base);
 }
 
 static u64 __xe_pt_empty_pte(struct xe_tile *tile, struct xe_vm *vm,
@@ -125,6 +128,7 @@ struct xe_pt *xe_pt_create(struct xe_vm *vm, struct xe_tile *tile,
 	}
 	pt->bo = bo;
 	pt->base.children = level ? as_xe_pt_dir(pt)->children : NULL;
+	pt->base.staging = level ? as_xe_pt_dir(pt)->staging : NULL;
 
 	if (vm->xef)
 		xe_drm_client_add_bo(vm->xef->client, pt->bo);
@@ -206,8 +210,8 @@ void xe_pt_destroy(struct xe_pt *pt, u32 flags, struct llist_head *deferred)
 		struct xe_pt_dir *pt_dir = as_xe_pt_dir(pt);
 
 		for (i = 0; i < XE_PDES; i++) {
-			if (xe_pt_entry(pt_dir, i))
-				xe_pt_destroy(xe_pt_entry(pt_dir, i), flags,
+			if (xe_pt_entry_staging(pt_dir, i))
+				xe_pt_destroy(xe_pt_entry_staging(pt_dir, i), flags,
 					      deferred);
 		}
 	}
@@ -376,8 +380,10 @@ xe_pt_insert_entry(struct xe_pt_stage_bind_walk *xe_walk, struct xe_pt *parent,
 		/* Continue building a non-connected subtree. */
 		struct iosys_map *map = &parent->bo->vmap;
 
-		if (unlikely(xe_child))
+		if (unlikely(xe_child)) {
 			parent->base.children[offset] = &xe_child->base;
+			parent->base.staging[offset] = &xe_child->base;
+		}
 
 		xe_pt_write(xe_walk->vm->xe, map, offset, pte);
 		parent->num_live++;
@@ -614,6 +620,7 @@ xe_pt_stage_bind(struct xe_tile *tile, struct xe_vma *vma,
 			.ops = &xe_pt_stage_bind_ops,
 			.shifts = xe_normal_pt_shifts,
 			.max_level = XE_PT_HIGHEST_LEVEL,
+			.staging = true,
 		},
 		.vm = xe_vma_vm(vma),
 		.tile = tile,
@@ -873,7 +880,7 @@ static void xe_pt_cancel_bind(struct xe_vma *vma,
 	}
 }
 
-static void xe_pt_commit_locks_assert(struct xe_vma *vma)
+static void xe_pt_commit_prepare_locks_assert(struct xe_vma *vma)
 {
 	struct xe_vm *vm = xe_vma_vm(vma);
 
@@ -885,6 +892,16 @@ static void xe_pt_commit_locks_assert(struct xe_vma *vma)
 	xe_vm_assert_held(vm);
 }
 
+static void xe_pt_commit_locks_assert(struct xe_vma *vma)
+{
+	struct xe_vm *vm = xe_vma_vm(vma);
+
+	xe_pt_commit_prepare_locks_assert(vma);
+
+	if (xe_vma_is_userptr(vma))
+		lockdep_assert_held_read(&vm->userptr.notifier_lock);
+}
+
 static void xe_pt_commit(struct xe_vma *vma,
 			 struct xe_vm_pgtable_update *entries,
 			 u32 num_entries, struct llist_head *deferred)
@@ -895,13 +912,17 @@ static void xe_pt_commit(struct xe_vma *vma,
 
 	for (i = 0; i < num_entries; i++) {
 		struct xe_pt *pt = entries[i].pt;
+		struct xe_pt_dir *pt_dir;
 
 		if (!pt->level)
 			continue;
 
+		pt_dir = as_xe_pt_dir(pt);
 		for (j = 0; j < entries[i].qwords; j++) {
 			struct xe_pt *oldpte = entries[i].pt_entries[j].pt;
+			int j_ = j + entries[i].ofs;
 
+			pt_dir->children[j_] = pt_dir->staging[j_];
 			xe_pt_destroy(oldpte, xe_vma_vm(vma)->flags, deferred);
 		}
 	}
@@ -913,7 +934,7 @@ static void xe_pt_abort_bind(struct xe_vma *vma,
 {
 	int i, j;
 
-	xe_pt_commit_locks_assert(vma);
+	xe_pt_commit_prepare_locks_assert(vma);
 
 	for (i = num_entries - 1; i >= 0; --i) {
 		struct xe_pt *pt = entries[i].pt;
@@ -928,10 +949,10 @@ static void xe_pt_abort_bind(struct xe_vma *vma,
 		pt_dir = as_xe_pt_dir(pt);
 		for (j = 0; j < entries[i].qwords; j++) {
 			u32 j_ = j + entries[i].ofs;
-			struct xe_pt *newpte = xe_pt_entry(pt_dir, j_);
+			struct xe_pt *newpte = xe_pt_entry_staging(pt_dir, j_);
 			struct xe_pt *oldpte = entries[i].pt_entries[j].pt;
 
-			pt_dir->children[j_] = oldpte ? &oldpte->base : 0;
+			pt_dir->staging[j_] = oldpte ? &oldpte->base : 0;
 			xe_pt_destroy(newpte, xe_vma_vm(vma)->flags, NULL);
 		}
 	}
@@ -943,7 +964,7 @@ static void xe_pt_commit_prepare_bind(struct xe_vma *vma,
 {
 	u32 i, j;
 
-	xe_pt_commit_locks_assert(vma);
+	xe_pt_commit_prepare_locks_assert(vma);
 
 	for (i = 0; i < num_entries; i++) {
 		struct xe_pt *pt = entries[i].pt;
@@ -961,10 +982,10 @@ static void xe_pt_commit_prepare_bind(struct xe_vma *vma,
 			struct xe_pt *newpte = entries[i].pt_entries[j].pt;
 			struct xe_pt *oldpte = NULL;
 
-			if (xe_pt_entry(pt_dir, j_))
-				oldpte = xe_pt_entry(pt_dir, j_);
+			if (xe_pt_entry_staging(pt_dir, j_))
+				oldpte = xe_pt_entry_staging(pt_dir, j_);
 
-			pt_dir->children[j_] = &newpte->base;
+			pt_dir->staging[j_] = &newpte->base;
 			entries[i].pt_entries[j].pt = oldpte;
 		}
 	}
@@ -1494,6 +1515,7 @@ static unsigned int xe_pt_stage_unbind(struct xe_tile *tile, struct xe_vma *vma,
 			.ops = &xe_pt_stage_unbind_ops,
 			.shifts = xe_normal_pt_shifts,
 			.max_level = XE_PT_HIGHEST_LEVEL,
+			.staging = true,
 		},
 		.tile = tile,
 		.modified_start = xe_vma_start(vma),
@@ -1535,7 +1557,7 @@ static void xe_pt_abort_unbind(struct xe_vma *vma,
 {
 	int i, j;
 
-	xe_pt_commit_locks_assert(vma);
+	xe_pt_commit_prepare_locks_assert(vma);
 
 	for (i = num_entries - 1; i >= 0; --i) {
 		struct xe_vm_pgtable_update *entry = &entries[i];
@@ -1548,7 +1570,7 @@ static void xe_pt_abort_unbind(struct xe_vma *vma,
 			continue;
 
 		for (j = entry->ofs; j < entry->ofs + entry->qwords; j++)
-			pt_dir->children[j] =
+			pt_dir->staging[j] =
 				entries[i].pt_entries[j - entry->ofs].pt ?
 				&entries[i].pt_entries[j - entry->ofs].pt->base : NULL;
 	}
@@ -1561,7 +1583,7 @@ xe_pt_commit_prepare_unbind(struct xe_vma *vma,
 {
 	int i, j;
 
-	xe_pt_commit_locks_assert(vma);
+	xe_pt_commit_prepare_locks_assert(vma);
 
 	for (i = 0; i < num_entries; ++i) {
 		struct xe_vm_pgtable_update *entry = &entries[i];
@@ -1575,8 +1597,8 @@ xe_pt_commit_prepare_unbind(struct xe_vma *vma,
 		pt_dir = as_xe_pt_dir(pt);
 		for (j = entry->ofs; j < entry->ofs + entry->qwords; j++) {
 			entry->pt_entries[j - entry->ofs].pt =
-				xe_pt_entry(pt_dir, j);
-			pt_dir->children[j] = NULL;
+				xe_pt_entry_staging(pt_dir, j);
+			pt_dir->staging[j] = NULL;
 		}
 	}
 }
diff --git a/drivers/gpu/drm/xe/xe_pt_walk.c b/drivers/gpu/drm/xe/xe_pt_walk.c
index b8b3d2aea4923..be602a763ff32 100644
--- a/drivers/gpu/drm/xe/xe_pt_walk.c
+++ b/drivers/gpu/drm/xe/xe_pt_walk.c
@@ -74,7 +74,8 @@ int xe_pt_walk_range(struct xe_ptw *parent, unsigned int level,
 		     u64 addr, u64 end, struct xe_pt_walk *walk)
 {
 	pgoff_t offset = xe_pt_offset(addr, level, walk);
-	struct xe_ptw **entries = parent->children ? parent->children : NULL;
+	struct xe_ptw **entries = walk->staging ? (parent->staging ?: NULL) :
+		(parent->children ?: NULL);
 	const struct xe_pt_walk_ops *ops = walk->ops;
 	enum page_walk_action action;
 	struct xe_ptw *child;
diff --git a/drivers/gpu/drm/xe/xe_pt_walk.h b/drivers/gpu/drm/xe/xe_pt_walk.h
index 5ecc4d2f0f653..5c02c244f7de3 100644
--- a/drivers/gpu/drm/xe/xe_pt_walk.h
+++ b/drivers/gpu/drm/xe/xe_pt_walk.h
@@ -11,12 +11,14 @@
 /**
  * struct xe_ptw - base class for driver pagetable subclassing.
  * @children: Pointer to an array of children if any.
+ * @staging: Pointer to an array of staging if any.
  *
  * Drivers could subclass this, and if it's a page-directory, typically
  * embed an array of xe_ptw pointers.
  */
 struct xe_ptw {
 	struct xe_ptw **children;
+	struct xe_ptw **staging;
 };
 
 /**
@@ -41,6 +43,8 @@ struct xe_pt_walk {
 	 * as shared pagetables.
 	 */
 	bool shared_pt_mode;
+	/** @staging: Walk staging PT structure */
+	bool staging;
 };
 
 /**

From e3e2e7fc4cd8414c9a966ef1b344db543f8614f4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Tue, 4 Mar 2025 18:33:40 +0100
Subject: [PATCH 1012/1173] drm/xe/hmm: Style- and include fixes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add proper #ifndef around the xe_hmm.h header, proper spacing
and since the documentation mostly follows kerneldoc format,
make it kerneldoc. Also prepare for upcoming -stable fixes.

Fixes: 81e058a3e7fd ("drm/xe: Introduce helper to populate userptr")
Cc: Oak Zeng <oak.zeng@intel.com>
Cc: <stable@vger.kernel.org> # v6.10+
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Acked-by: Matthew Brost <Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250304173342.22009-2-thomas.hellstrom@linux.intel.com
(cherry picked from commit bbe2b06b55bc061c8fcec034ed26e88287f39143)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_hmm.c | 9 +++------
 drivers/gpu/drm/xe/xe_hmm.h | 5 +++++
 2 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_hmm.c b/drivers/gpu/drm/xe/xe_hmm.c
index 2e4ae61567d8d..6ddcf88d8a393 100644
--- a/drivers/gpu/drm/xe/xe_hmm.c
+++ b/drivers/gpu/drm/xe/xe_hmm.c
@@ -19,11 +19,10 @@ static u64 xe_npages_in_range(unsigned long start, unsigned long end)
 	return (end - start) >> PAGE_SHIFT;
 }
 
-/*
+/**
  * xe_mark_range_accessed() - mark a range is accessed, so core mm
  * have such information for memory eviction or write back to
  * hard disk
- *
  * @range: the range to mark
  * @write: if write to this range, we mark pages in this range
  * as dirty
@@ -43,11 +42,10 @@ static void xe_mark_range_accessed(struct hmm_range *range, bool write)
 	}
 }
 
-/*
+/**
  * xe_build_sg() - build a scatter gather table for all the physical pages/pfn
  * in a hmm_range. dma-map pages if necessary. dma-address is save in sg table
  * and will be used to program GPU page table later.
- *
  * @xe: the xe device who will access the dma-address in sg table
  * @range: the hmm range that we build the sg table from. range->hmm_pfns[]
  * has the pfn numbers of pages that back up this hmm address range.
@@ -112,9 +110,8 @@ static int xe_build_sg(struct xe_device *xe, struct hmm_range *range,
 	return ret;
 }
 
-/*
+/**
  * xe_hmm_userptr_free_sg() - Free the scatter gather table of userptr
- *
  * @uvma: the userptr vma which hold the scatter gather table
  *
  * With function xe_userptr_populate_range, we allocate storage of
diff --git a/drivers/gpu/drm/xe/xe_hmm.h b/drivers/gpu/drm/xe/xe_hmm.h
index 909dc2bdcd97e..9602cb7d976dd 100644
--- a/drivers/gpu/drm/xe/xe_hmm.h
+++ b/drivers/gpu/drm/xe/xe_hmm.h
@@ -3,9 +3,14 @@
  * Copyright © 2024 Intel Corporation
  */
 
+#ifndef _XE_HMM_H_
+#define _XE_HMM_H_
+
 #include <linux/types.h>
 
 struct xe_userptr_vma;
 
 int xe_hmm_userptr_populate_range(struct xe_userptr_vma *uvma, bool is_mm_mmap_locked);
+
 void xe_hmm_userptr_free_sg(struct xe_userptr_vma *uvma);
+#endif

From 0a98219bcc961edd3388960576e4353e123b4a51 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Tue, 4 Mar 2025 18:33:41 +0100
Subject: [PATCH 1013/1173] drm/xe/hmm: Don't dereference struct page pointers
 without notifier lock
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The pnfs that we obtain from hmm_range_fault() point to pages that
we don't have a reference on, and the guarantee that they are still
in the cpu page-tables is that the notifier lock must be held and the
notifier seqno is still valid.

So while building the sg table and marking the pages accesses / dirty
we need to hold this lock with a validated seqno.

However, the lock is reclaim tainted which makes
sg_alloc_table_from_pages_segment() unusable, since it internally
allocates memory.

Instead build the sg-table manually. For the non-iommu case
this might lead to fewer coalesces, but if that's a problem it can
be fixed up later in the resource cursor code. For the iommu case,
the whole sg-table may still be coalesced to a single contigous
device va region.

This avoids marking pages that we don't own dirty and accessed, and
it also avoid dereferencing struct pages that we don't own.

v2:
- Use assert to check whether hmm pfns are valid (Matthew Auld)
- Take into account that large pages may cross range boundaries
  (Matthew Auld)

v3:
- Don't unnecessarily check for a non-freed sg-table. (Matthew Auld)
- Add a missing up_read() in an error path. (Matthew Auld)

Fixes: 81e058a3e7fd ("drm/xe: Introduce helper to populate userptr")
Cc: Oak Zeng <oak.zeng@intel.com>
Cc: <stable@vger.kernel.org> # v6.10+
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Acked-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250304173342.22009-3-thomas.hellstrom@linux.intel.com
(cherry picked from commit ea3e66d280ce2576664a862693d1da8fd324c317)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_hmm.c | 112 +++++++++++++++++++++++++++---------
 1 file changed, 86 insertions(+), 26 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_hmm.c b/drivers/gpu/drm/xe/xe_hmm.c
index 6ddcf88d8a393..be284b852307e 100644
--- a/drivers/gpu/drm/xe/xe_hmm.c
+++ b/drivers/gpu/drm/xe/xe_hmm.c
@@ -42,6 +42,42 @@ static void xe_mark_range_accessed(struct hmm_range *range, bool write)
 	}
 }
 
+static int xe_alloc_sg(struct xe_device *xe, struct sg_table *st,
+		       struct hmm_range *range, struct rw_semaphore *notifier_sem)
+{
+	unsigned long i, npages, hmm_pfn;
+	unsigned long num_chunks = 0;
+	int ret;
+
+	/* HMM docs says this is needed. */
+	ret = down_read_interruptible(notifier_sem);
+	if (ret)
+		return ret;
+
+	if (mmu_interval_read_retry(range->notifier, range->notifier_seq)) {
+		up_read(notifier_sem);
+		return -EAGAIN;
+	}
+
+	npages = xe_npages_in_range(range->start, range->end);
+	for (i = 0; i < npages;) {
+		unsigned long len;
+
+		hmm_pfn = range->hmm_pfns[i];
+		xe_assert(xe, hmm_pfn & HMM_PFN_VALID);
+
+		len = 1UL << hmm_pfn_to_map_order(hmm_pfn);
+
+		/* If order > 0 the page may extend beyond range->start */
+		len -= (hmm_pfn & ~HMM_PFN_FLAGS) & (len - 1);
+		i += len;
+		num_chunks++;
+	}
+	up_read(notifier_sem);
+
+	return sg_alloc_table(st, num_chunks, GFP_KERNEL);
+}
+
 /**
  * xe_build_sg() - build a scatter gather table for all the physical pages/pfn
  * in a hmm_range. dma-map pages if necessary. dma-address is save in sg table
@@ -50,6 +86,7 @@ static void xe_mark_range_accessed(struct hmm_range *range, bool write)
  * @range: the hmm range that we build the sg table from. range->hmm_pfns[]
  * has the pfn numbers of pages that back up this hmm address range.
  * @st: pointer to the sg table.
+ * @notifier_sem: The xe notifier lock.
  * @write: whether we write to this range. This decides dma map direction
  * for system pages. If write we map it bi-diretional; otherwise
  * DMA_TO_DEVICE
@@ -76,38 +113,41 @@ static void xe_mark_range_accessed(struct hmm_range *range, bool write)
  * Returns 0 if successful; -ENOMEM if fails to allocate memory
  */
 static int xe_build_sg(struct xe_device *xe, struct hmm_range *range,
-		       struct sg_table *st, bool write)
+		       struct sg_table *st,
+		       struct rw_semaphore *notifier_sem,
+		       bool write)
 {
+	unsigned long npages = xe_npages_in_range(range->start, range->end);
 	struct device *dev = xe->drm.dev;
-	struct page **pages;
-	u64 i, npages;
-	int ret;
+	struct scatterlist *sgl;
+	struct page *page;
+	unsigned long i, j;
 
-	npages = xe_npages_in_range(range->start, range->end);
-	pages = kvmalloc_array(npages, sizeof(*pages), GFP_KERNEL);
-	if (!pages)
-		return -ENOMEM;
+	lockdep_assert_held(notifier_sem);
 
-	for (i = 0; i < npages; i++) {
-		pages[i] = hmm_pfn_to_page(range->hmm_pfns[i]);
-		xe_assert(xe, !is_device_private_page(pages[i]));
-	}
+	i = 0;
+	for_each_sg(st->sgl, sgl, st->nents, j) {
+		unsigned long hmm_pfn, size;
 
-	ret = sg_alloc_table_from_pages_segment(st, pages, npages, 0, npages << PAGE_SHIFT,
-						xe_sg_segment_size(dev), GFP_KERNEL);
-	if (ret)
-		goto free_pages;
+		hmm_pfn = range->hmm_pfns[i];
+		page = hmm_pfn_to_page(hmm_pfn);
+		xe_assert(xe, !is_device_private_page(page));
+
+		size = 1UL << hmm_pfn_to_map_order(hmm_pfn);
+		size -= page_to_pfn(page) & (size - 1);
+		i += size;
 
-	ret = dma_map_sgtable(dev, st, write ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE,
-			      DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_NO_KERNEL_MAPPING);
-	if (ret) {
-		sg_free_table(st);
-		st = NULL;
+		if (unlikely(j == st->nents - 1)) {
+			if (i > npages)
+				size -= (i - npages);
+			sg_mark_end(sgl);
+		}
+		sg_set_page(sgl, page, size << PAGE_SHIFT, 0);
 	}
+	xe_assert(xe, i == npages);
 
-free_pages:
-	kvfree(pages);
-	return ret;
+	return dma_map_sgtable(dev, st, write ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE,
+			       DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_NO_KERNEL_MAPPING);
 }
 
 /**
@@ -237,16 +277,36 @@ int xe_hmm_userptr_populate_range(struct xe_userptr_vma *uvma,
 	if (ret)
 		goto free_pfns;
 
-	ret = xe_build_sg(vm->xe, &hmm_range, &userptr->sgt, write);
+	ret = xe_alloc_sg(vm->xe, &userptr->sgt, &hmm_range, &vm->userptr.notifier_lock);
 	if (ret)
 		goto free_pfns;
 
+	ret = down_read_interruptible(&vm->userptr.notifier_lock);
+	if (ret)
+		goto free_st;
+
+	if (mmu_interval_read_retry(hmm_range.notifier, hmm_range.notifier_seq)) {
+		ret = -EAGAIN;
+		goto out_unlock;
+	}
+
+	ret = xe_build_sg(vm->xe, &hmm_range, &userptr->sgt,
+			  &vm->userptr.notifier_lock, write);
+	if (ret)
+		goto out_unlock;
+
 	xe_mark_range_accessed(&hmm_range, write);
 	userptr->sg = &userptr->sgt;
 	userptr->notifier_seq = hmm_range.notifier_seq;
+	up_read(&vm->userptr.notifier_lock);
+	kvfree(pfns);
+	return 0;
 
+out_unlock:
+	up_read(&vm->userptr.notifier_lock);
+free_st:
+	sg_free_table(&userptr->sgt);
 free_pfns:
 	kvfree(pfns);
 	return ret;
 }
-

From 333b8906336174478efbbfc1e24a89e3397ffe65 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Tue, 4 Mar 2025 18:33:42 +0100
Subject: [PATCH 1014/1173] drm/xe/userptr: Unmap userptrs in the mmu notifier
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If userptr pages are freed after a call to the xe mmu notifier,
the device will not be blocked out from theoretically accessing
these pages unless they are also unmapped from the iommu, and
this violates some aspects of the iommu-imposed security.

Ensure that userptrs are unmapped in the mmu notifier to
mitigate this. A naive attempt would try to free the sg table, but
the sg table itself may be accessed by a concurrent bind
operation, so settle for only unmapping.

v3:
- Update lockdep asserts.
- Fix a typo (Matthew Auld)

Fixes: 81e058a3e7fd ("drm/xe: Introduce helper to populate userptr")
Cc: Oak Zeng <oak.zeng@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: <stable@vger.kernel.org> # v6.10+
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Acked-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250304173342.22009-4-thomas.hellstrom@linux.intel.com
(cherry picked from commit ba767b9d01a2c552d76cf6f46b125d50ec4147a6)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_hmm.c      | 51 ++++++++++++++++++++++++++------
 drivers/gpu/drm/xe/xe_hmm.h      |  2 ++
 drivers/gpu/drm/xe/xe_vm.c       |  4 +++
 drivers/gpu/drm/xe/xe_vm_types.h |  4 +++
 4 files changed, 52 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_hmm.c b/drivers/gpu/drm/xe/xe_hmm.c
index be284b852307e..392102515f3d8 100644
--- a/drivers/gpu/drm/xe/xe_hmm.c
+++ b/drivers/gpu/drm/xe/xe_hmm.c
@@ -150,6 +150,45 @@ static int xe_build_sg(struct xe_device *xe, struct hmm_range *range,
 			       DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_NO_KERNEL_MAPPING);
 }
 
+static void xe_hmm_userptr_set_mapped(struct xe_userptr_vma *uvma)
+{
+	struct xe_userptr *userptr = &uvma->userptr;
+	struct xe_vm *vm = xe_vma_vm(&uvma->vma);
+
+	lockdep_assert_held_write(&vm->lock);
+	lockdep_assert_held(&vm->userptr.notifier_lock);
+
+	mutex_lock(&userptr->unmap_mutex);
+	xe_assert(vm->xe, !userptr->mapped);
+	userptr->mapped = true;
+	mutex_unlock(&userptr->unmap_mutex);
+}
+
+void xe_hmm_userptr_unmap(struct xe_userptr_vma *uvma)
+{
+	struct xe_userptr *userptr = &uvma->userptr;
+	struct xe_vma *vma = &uvma->vma;
+	bool write = !xe_vma_read_only(vma);
+	struct xe_vm *vm = xe_vma_vm(vma);
+	struct xe_device *xe = vm->xe;
+
+	if (!lockdep_is_held_type(&vm->userptr.notifier_lock, 0) &&
+	    !lockdep_is_held_type(&vm->lock, 0) &&
+	    !(vma->gpuva.flags & XE_VMA_DESTROYED)) {
+		/* Don't unmap in exec critical section. */
+		xe_vm_assert_held(vm);
+		/* Don't unmap while mapping the sg. */
+		lockdep_assert_held(&vm->lock);
+	}
+
+	mutex_lock(&userptr->unmap_mutex);
+	if (userptr->sg && userptr->mapped)
+		dma_unmap_sgtable(xe->drm.dev, userptr->sg,
+				  write ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE, 0);
+	userptr->mapped = false;
+	mutex_unlock(&userptr->unmap_mutex);
+}
+
 /**
  * xe_hmm_userptr_free_sg() - Free the scatter gather table of userptr
  * @uvma: the userptr vma which hold the scatter gather table
@@ -161,16 +200,9 @@ static int xe_build_sg(struct xe_device *xe, struct hmm_range *range,
 void xe_hmm_userptr_free_sg(struct xe_userptr_vma *uvma)
 {
 	struct xe_userptr *userptr = &uvma->userptr;
-	struct xe_vma *vma = &uvma->vma;
-	bool write = !xe_vma_read_only(vma);
-	struct xe_vm *vm = xe_vma_vm(vma);
-	struct xe_device *xe = vm->xe;
-	struct device *dev = xe->drm.dev;
-
-	xe_assert(xe, userptr->sg);
-	dma_unmap_sgtable(dev, userptr->sg,
-			  write ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE, 0);
 
+	xe_assert(xe_vma_vm(&uvma->vma)->xe, userptr->sg);
+	xe_hmm_userptr_unmap(uvma);
 	sg_free_table(userptr->sg);
 	userptr->sg = NULL;
 }
@@ -297,6 +329,7 @@ int xe_hmm_userptr_populate_range(struct xe_userptr_vma *uvma,
 
 	xe_mark_range_accessed(&hmm_range, write);
 	userptr->sg = &userptr->sgt;
+	xe_hmm_userptr_set_mapped(uvma);
 	userptr->notifier_seq = hmm_range.notifier_seq;
 	up_read(&vm->userptr.notifier_lock);
 	kvfree(pfns);
diff --git a/drivers/gpu/drm/xe/xe_hmm.h b/drivers/gpu/drm/xe/xe_hmm.h
index 9602cb7d976dd..0ea98d8e7bbc7 100644
--- a/drivers/gpu/drm/xe/xe_hmm.h
+++ b/drivers/gpu/drm/xe/xe_hmm.h
@@ -13,4 +13,6 @@ struct xe_userptr_vma;
 int xe_hmm_userptr_populate_range(struct xe_userptr_vma *uvma, bool is_mm_mmap_locked);
 
 void xe_hmm_userptr_free_sg(struct xe_userptr_vma *uvma);
+
+void xe_hmm_userptr_unmap(struct xe_userptr_vma *uvma);
 #endif
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index d54aaa5eaff38..ec6ec18ab3faa 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -620,6 +620,8 @@ static void __vma_userptr_invalidate(struct xe_vm *vm, struct xe_userptr_vma *uv
 		err = xe_vm_invalidate_vma(vma);
 		XE_WARN_ON(err);
 	}
+
+	xe_hmm_userptr_unmap(uvma);
 }
 
 static bool vma_userptr_invalidate(struct mmu_interval_notifier *mni,
@@ -1039,6 +1041,7 @@ static struct xe_vma *xe_vma_create(struct xe_vm *vm,
 			INIT_LIST_HEAD(&userptr->invalidate_link);
 			INIT_LIST_HEAD(&userptr->repin_link);
 			vma->gpuva.gem.offset = bo_offset_or_userptr;
+			mutex_init(&userptr->unmap_mutex);
 
 			err = mmu_interval_notifier_insert(&userptr->notifier,
 							   current->mm,
@@ -1080,6 +1083,7 @@ static void xe_vma_destroy_late(struct xe_vma *vma)
 		 * them anymore
 		 */
 		mmu_interval_notifier_remove(&userptr->notifier);
+		mutex_destroy(&userptr->unmap_mutex);
 		xe_vm_put(vm);
 	} else if (xe_vma_is_null(vma)) {
 		xe_vm_put(vm);
diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h
index d2511819cdf43..a4b4091cfd0da 100644
--- a/drivers/gpu/drm/xe/xe_vm_types.h
+++ b/drivers/gpu/drm/xe/xe_vm_types.h
@@ -59,12 +59,16 @@ struct xe_userptr {
 	struct sg_table *sg;
 	/** @notifier_seq: notifier sequence number */
 	unsigned long notifier_seq;
+	/** @unmap_mutex: Mutex protecting dma-unmapping */
+	struct mutex unmap_mutex;
 	/**
 	 * @initial_bind: user pointer has been bound at least once.
 	 * write: vm->userptr.notifier_lock in read mode and vm->resv held.
 	 * read: vm->userptr.notifier_lock in write mode or vm->resv held.
 	 */
 	bool initial_bind;
+	/** @mapped: Whether the @sgt sg-table is dma-mapped. Protected by @unmap_mutex. */
+	bool mapped;
 #if IS_ENABLED(CONFIG_DRM_XE_USERPTR_INVAL_INJECT)
 	u32 divisor;
 #endif

From bcb0fda3c2da9fe4721d3e73d80e778c038e7d27 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Wed, 5 Mar 2025 14:03:34 -0700
Subject: [PATCH 1015/1173] io_uring/rw: ensure reissue path is correctly
 handled for IOPOLL

The IOPOLL path posts CQEs when the io_kiocb is marked as completed,
so it cannot rely on the usual retry that non-IOPOLL requests do for
read/write requests.

If -EAGAIN is received and the request should be retried, go through
the normal completion path and let the normal flush logic catch it and
reissue it, like what is done for !IOPOLL reads or writes.

Fixes: d803d123948f ("io_uring/rw: handle -EAGAIN retry at IO completion time")
Reported-by: John Garry <john.g.garry@oracle.com>
Link: https://lore.kernel.org/io-uring/2b43ccfa-644d-4a09-8f8f-39ad71810f41@oracle.com/
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/rw.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/io_uring/rw.c b/io_uring/rw.c
index 9edc6baebd01c..e5528cebcd066 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -560,11 +560,10 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res)
 	if (kiocb->ki_flags & IOCB_WRITE)
 		io_req_end_write(req);
 	if (unlikely(res != req->cqe.res)) {
-		if (res == -EAGAIN && io_rw_should_reissue(req)) {
+		if (res == -EAGAIN && io_rw_should_reissue(req))
 			req->flags |= REQ_F_REISSUE | REQ_F_BL_NO_RECYCLE;
-			return;
-		}
-		req->cqe.res = res;
+		else
+			req->cqe.res = res;
 	}
 
 	/* order with io_iopoll_complete() checking ->iopoll_completed */

From f37ff575b1fe47ff3eeccf751455b4ab05306008 Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@surriel.com>
Date: Tue, 25 Feb 2025 22:00:45 -0500
Subject: [PATCH 1016/1173] x86/mm: Enable broadcast TLB invalidation for
 multi-threaded processes

There is not enough room in the 12-bit ASID address space to hand out
broadcast ASIDs to every process. Only hand out broadcast ASIDs to processes
when they are observed to be simultaneously running on 4 or more CPUs.

This also allows single threaded process to continue using the cheaper, local
TLB invalidation instructions like INVLPGB.

Due to the structure of flush_tlb_mm_range(), the INVLPGB flushing is done in
a generically named broadcast_tlb_flush() function which can later also be
used for Intel RAR.

Combined with the removal of unnecessary lru_add_drain calls() (see
https://lore.kernel.org/r/20241219153253.3da9e8aa@fangorn) this results in
a nice performance boost for the will-it-scale tlb_flush2_threads test on an
AMD Milan system with 36 cores:

  - vanilla kernel:           527k loops/second
  - lru_add_drain removal:    731k loops/second
  - only INVLPGB:             527k loops/second
  - lru_add_drain + INVLPGB: 1157k loops/second

Profiling with only the INVLPGB changes showed while TLB invalidation went
down from 40% of the total CPU time to only around 4% of CPU time, the
contention simply moved to the LRU lock.

Fixing both at the same time about doubles the number of iterations per second
from this case.

Comparing will-it-scale tlb_flush2_threads with several different numbers of
threads on a 72 CPU AMD Milan shows similar results. The number represents the
total number of loops per second across all the threads:

  threads	tip		INVLPGB

  1		315k		304k
  2		423k		424k
  4		644k		1032k
  8		652k		1267k
  16		737k		1368k
  32		759k		1199k
  64		636k		1094k
  72		609k		993k

1 and 2 thread performance is similar with and without INVLPGB, because
INVLPGB is only used on processes using 4 or more CPUs simultaneously.

The number is the median across 5 runs.

Some numbers closer to real world performance can be found at Phoronix, thanks
to Michael:

https://www.phoronix.com/news/AMD-INVLPGB-Linux-Benefits

  [ bp:
   - Massage
   - :%s/\<static_cpu_has\>/cpu_feature_enabled/cgi
   - :%s/\<clear_asid_transition\>/mm_clear_asid_transition/cgi
   - Fold in a 0day bot fix: https://lore.kernel.org/oe-kbuild-all/202503040000.GtiWUsBm-lkp@intel.com
   ]

Signed-off-by: Rik van Riel <riel@surriel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Nadav Amit <nadav.amit@gmail.com>
Link: https://lore.kernel.org/r/20250226030129.530345-11-riel@surriel.com
---
 arch/x86/include/asm/tlbflush.h |   6 ++
 arch/x86/mm/tlb.c               | 104 +++++++++++++++++++++++++++++++-
 2 files changed, 109 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index e6c3be06dd21c..7cad283d502d0 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -280,6 +280,11 @@ static inline void mm_assign_global_asid(struct mm_struct *mm, u16 asid)
 	smp_store_release(&mm->context.global_asid, asid);
 }
 
+static inline void mm_clear_asid_transition(struct mm_struct *mm)
+{
+	WRITE_ONCE(mm->context.asid_transition, false);
+}
+
 static inline bool mm_in_asid_transition(struct mm_struct *mm)
 {
 	if (!cpu_feature_enabled(X86_FEATURE_INVLPGB))
@@ -291,6 +296,7 @@ static inline bool mm_in_asid_transition(struct mm_struct *mm)
 static inline u16 mm_global_asid(struct mm_struct *mm) { return 0; }
 static inline void mm_init_global_asid(struct mm_struct *mm) { }
 static inline void mm_assign_global_asid(struct mm_struct *mm, u16 asid) { }
+static inline void mm_clear_asid_transition(struct mm_struct *mm) { }
 static inline bool mm_in_asid_transition(struct mm_struct *mm) { return false; }
 #endif /* CONFIG_BROADCAST_TLB_FLUSH */
 
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index b5681e6f2333e..0efd99053c09d 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -430,6 +430,105 @@ static bool mm_needs_global_asid(struct mm_struct *mm, u16 asid)
 	return false;
 }
 
+/*
+ * x86 has 4k ASIDs (2k when compiled with KPTI), but the largest x86
+ * systems have over 8k CPUs. Because of this potential ASID shortage,
+ * global ASIDs are handed out to processes that have frequent TLB
+ * flushes and are active on 4 or more CPUs simultaneously.
+ */
+static void consider_global_asid(struct mm_struct *mm)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		return;
+
+	/* Check every once in a while. */
+	if ((current->pid & 0x1f) != (jiffies & 0x1f))
+		return;
+
+	/*
+	 * Assign a global ASID if the process is active on
+	 * 4 or more CPUs simultaneously.
+	 */
+	if (mm_active_cpus_exceeds(mm, 3))
+		use_global_asid(mm);
+}
+
+static void finish_asid_transition(struct flush_tlb_info *info)
+{
+	struct mm_struct *mm = info->mm;
+	int bc_asid = mm_global_asid(mm);
+	int cpu;
+
+	if (!mm_in_asid_transition(mm))
+		return;
+
+	for_each_cpu(cpu, mm_cpumask(mm)) {
+		/*
+		 * The remote CPU is context switching. Wait for that to
+		 * finish, to catch the unlikely case of it switching to
+		 * the target mm with an out of date ASID.
+		 */
+		while (READ_ONCE(per_cpu(cpu_tlbstate.loaded_mm, cpu)) == LOADED_MM_SWITCHING)
+			cpu_relax();
+
+		if (READ_ONCE(per_cpu(cpu_tlbstate.loaded_mm, cpu)) != mm)
+			continue;
+
+		/*
+		 * If at least one CPU is not using the global ASID yet,
+		 * send a TLB flush IPI. The IPI should cause stragglers
+		 * to transition soon.
+		 *
+		 * This can race with the CPU switching to another task;
+		 * that results in a (harmless) extra IPI.
+		 */
+		if (READ_ONCE(per_cpu(cpu_tlbstate.loaded_mm_asid, cpu)) != bc_asid) {
+			flush_tlb_multi(mm_cpumask(info->mm), info);
+			return;
+		}
+	}
+
+	/* All the CPUs running this process are using the global ASID. */
+	mm_clear_asid_transition(mm);
+}
+
+static void broadcast_tlb_flush(struct flush_tlb_info *info)
+{
+	bool pmd = info->stride_shift == PMD_SHIFT;
+	unsigned long asid = mm_global_asid(info->mm);
+	unsigned long addr = info->start;
+
+	/*
+	 * TLB flushes with INVLPGB are kicked off asynchronously.
+	 * The inc_mm_tlb_gen() guarantees page table updates are done
+	 * before these TLB flushes happen.
+	 */
+	if (info->end == TLB_FLUSH_ALL) {
+		invlpgb_flush_single_pcid_nosync(kern_pcid(asid));
+		/* Do any CPUs supporting INVLPGB need PTI? */
+		if (cpu_feature_enabled(X86_FEATURE_PTI))
+			invlpgb_flush_single_pcid_nosync(user_pcid(asid));
+	} else do {
+		unsigned long nr = 1;
+
+		if (info->stride_shift <= PMD_SHIFT) {
+			nr = (info->end - addr) >> info->stride_shift;
+			nr = clamp_val(nr, 1, invlpgb_count_max);
+		}
+
+		invlpgb_flush_user_nr_nosync(kern_pcid(asid), addr, nr, pmd);
+		if (cpu_feature_enabled(X86_FEATURE_PTI))
+			invlpgb_flush_user_nr_nosync(user_pcid(asid), addr, nr, pmd);
+
+		addr += nr << info->stride_shift;
+	} while (addr < info->end);
+
+	finish_asid_transition(info);
+
+	/* Wait for the INVLPGBs kicked off above to finish. */
+	__tlbsync();
+}
+
 /*
  * Given an ASID, flush the corresponding user ASID.  We can delay this
  * until the next time we switch to it.
@@ -1260,9 +1359,12 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 	 * a local TLB flush is needed. Optimize this use-case by calling
 	 * flush_tlb_func_local() directly in this case.
 	 */
-	if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids) {
+	if (mm_global_asid(mm)) {
+		broadcast_tlb_flush(info);
+	} else if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids) {
 		info->trim_cpumask = should_trim_cpumask(mm);
 		flush_tlb_multi(mm_cpumask(mm), info);
+		consider_global_asid(mm);
 	} else if (mm == this_cpu_read(cpu_tlbstate.loaded_mm)) {
 		lockdep_assert_irqs_enabled();
 		local_irq_disable();

From b95ef870dcd67c0fbfc57f808c4a0efd0bc2f144 Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@surriel.com>
Date: Tue, 25 Feb 2025 22:00:47 -0500
Subject: [PATCH 1017/1173] x86/mm: Enable AMD translation cache extensions

With AMD TCE (translation cache extensions) only the intermediate mappings
that cover the address range zapped by INVLPG / INVLPGB get invalidated,
rather than all intermediate mappings getting zapped at every TLB invalidation.

This can help reduce the TLB miss rate, by keeping more intermediate mappings
in the cache.

From the AMD manual:

Translation Cache Extension (TCE) Bit. Bit 15, read/write. Setting this bit to
1 changes how the INVLPG, INVLPGB, and INVPCID instructions operate on TLB
entries. When this bit is 0, these instructions remove the target PTE from the
TLB as well as all upper-level table entries that are cached in the TLB,
whether or not they are associated with the target PTE.  When this bit is set,
these instructions will remove the target PTE and only those upper-level
entries that lead to the target PTE in the page table hierarchy, leaving
unrelated upper-level entries intact.

  [ bp: use cpu_has()... I know, it is a mess. ]

Signed-off-by: Rik van Riel <riel@surriel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20250226030129.530345-13-riel@surriel.com
---
 arch/x86/include/asm/msr-index.h       | 2 ++
 arch/x86/kernel/cpu/amd.c              | 4 ++++
 tools/arch/x86/include/asm/msr-index.h | 2 ++
 3 files changed, 8 insertions(+)

diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 72765b2fe0d87..1aacd6b68fab7 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -25,6 +25,7 @@
 #define _EFER_SVME		12 /* Enable virtualization */
 #define _EFER_LMSLE		13 /* Long Mode Segment Limit Enable */
 #define _EFER_FFXSR		14 /* Enable Fast FXSAVE/FXRSTOR */
+#define _EFER_TCE		15 /* Enable Translation Cache Extensions */
 #define _EFER_AUTOIBRS		21 /* Enable Automatic IBRS */
 
 #define EFER_SCE		(1<<_EFER_SCE)
@@ -34,6 +35,7 @@
 #define EFER_SVME		(1<<_EFER_SVME)
 #define EFER_LMSLE		(1<<_EFER_LMSLE)
 #define EFER_FFXSR		(1<<_EFER_FFXSR)
+#define EFER_TCE		(1<<_EFER_TCE)
 #define EFER_AUTOIBRS		(1<<_EFER_AUTOIBRS)
 
 /*
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 7a72ef47a9838..705853315c0d8 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -1075,6 +1075,10 @@ static void init_amd(struct cpuinfo_x86 *c)
 
 	/* AMD CPUs don't need fencing after x2APIC/TSC_DEADLINE MSR writes. */
 	clear_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE);
+
+	/* Enable Translation Cache Extension */
+	if (cpu_has(c, X86_FEATURE_TCE))
+		msr_set_bit(MSR_EFER, _EFER_TCE);
 }
 
 #ifdef CONFIG_X86_32
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 3ae84c3b8e6db..dc1c1057f26e4 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -25,6 +25,7 @@
 #define _EFER_SVME		12 /* Enable virtualization */
 #define _EFER_LMSLE		13 /* Long Mode Segment Limit Enable */
 #define _EFER_FFXSR		14 /* Enable Fast FXSAVE/FXRSTOR */
+#define _EFER_TCE		15 /* Enable Translation Cache Extensions */
 #define _EFER_AUTOIBRS		21 /* Enable Automatic IBRS */
 
 #define EFER_SCE		(1<<_EFER_SCE)
@@ -34,6 +35,7 @@
 #define EFER_SVME		(1<<_EFER_SVME)
 #define EFER_LMSLE		(1<<_EFER_LMSLE)
 #define EFER_FFXSR		(1<<_EFER_FFXSR)
+#define EFER_TCE		(1<<_EFER_TCE)
 #define EFER_AUTOIBRS		(1<<_EFER_AUTOIBRS)
 
 /*

From 0896acd80782ec49c6d36e576fcd53786f0a2bfb Mon Sep 17 00:00:00 2001
From: Tom Lendacky <thomas.lendacky@amd.com>
Date: Tue, 4 Mar 2025 12:59:56 +0100
Subject: [PATCH 1018/1173] x86/mm: Always set the ASID valid bit for the
 INVLPGB instruction

When executing the INVLPGB instruction on a bare-metal host or hypervisor, if
the ASID valid bit is not set, the instruction will flush the TLB entries that
match the specified criteria for any ASID, not just the those of the host. If
virtual machines are running on the system, this may result in inadvertent
flushes of guest TLB entries.

When executing the INVLPGB instruction in a guest and the INVLPGB instruction is
not intercepted by the hypervisor, the hardware will replace the requested ASID
with the guest ASID and set the ASID valid bit before doing the broadcast
invalidation. Thus a guest is only able to flush its own TLB entries.

So to limit the host TLB flushing reach, always set the ASID valid bit using an
ASID value of 0 (which represents the host/hypervisor). This will will result in
the desired effect in both host and guest.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20250304120449.GHZ8bsYYyEBOKQIxBm@fat_crate.local
---
 arch/x86/include/asm/tlb.h | 58 +++++++++++++++++++++-----------------
 1 file changed, 32 insertions(+), 26 deletions(-)

diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h
index 31f6db40fa0d0..866ea78ba156a 100644
--- a/arch/x86/include/asm/tlb.h
+++ b/arch/x86/include/asm/tlb.h
@@ -33,6 +33,27 @@ enum addr_stride {
 	PMD_STRIDE = 1
 };
 
+/*
+ * INVLPGB can be targeted by virtual address, PCID, ASID, or any combination
+ * of the three. For example:
+ * - FLAG_VA | FLAG_INCLUDE_GLOBAL: invalidate all TLB entries at the address
+ * - FLAG_PCID:			    invalidate all TLB entries matching the PCID
+ *
+ * The first is used to invalidate (kernel) mappings at a particular
+ * address across all processes.
+ *
+ * The latter invalidates all TLB entries matching a PCID.
+ */
+#define INVLPGB_FLAG_VA			BIT(0)
+#define INVLPGB_FLAG_PCID		BIT(1)
+#define INVLPGB_FLAG_ASID		BIT(2)
+#define INVLPGB_FLAG_INCLUDE_GLOBAL	BIT(3)
+#define INVLPGB_FLAG_FINAL_ONLY		BIT(4)
+#define INVLPGB_FLAG_INCLUDE_NESTED	BIT(5)
+
+/* The implied mode when all bits are clear: */
+#define INVLPGB_MODE_ALL_NONGLOBALS	0UL
+
 #ifdef CONFIG_BROADCAST_TLB_FLUSH
 /*
  * INVLPGB does broadcast TLB invalidation across all the CPUs in the system.
@@ -40,14 +61,20 @@ enum addr_stride {
  * The INVLPGB instruction is weakly ordered, and a batch of invalidations can
  * be done in a parallel fashion.
  *
- * The instruction takes the number of extra pages to invalidate, beyond
- * the first page, while __invlpgb gets the more human readable number of
- * pages to invalidate.
+ * The instruction takes the number of extra pages to invalidate, beyond the
+ * first page, while __invlpgb gets the more human readable number of pages to
+ * invalidate.
  *
  * The bits in rax[0:2] determine respectively which components of the address
  * (VA, PCID, ASID) get compared when flushing. If neither bits are set, *any*
  * address in the specified range matches.
  *
+ * Since it is desired to only flush TLB entries for the ASID that is executing
+ * the instruction (a host/hypervisor or a guest), the ASID valid bit should
+ * always be set. On a host/hypervisor, the hardware will use the ASID value
+ * specified in EDX[15:0] (which should be 0). On a guest, the hardware will
+ * use the actual ASID value of the guest.
+ *
  * TLBSYNC is used to ensure that pending INVLPGB invalidations initiated from
  * this CPU have completed.
  */
@@ -55,9 +82,9 @@ static inline void __invlpgb(unsigned long asid, unsigned long pcid,
 			     unsigned long addr, u16 nr_pages,
 			     enum addr_stride stride, u8 flags)
 {
-	u32 edx = (pcid << 16) | asid;
+	u64 rax = addr | flags | INVLPGB_FLAG_ASID;
 	u32 ecx = (stride << 31) | (nr_pages - 1);
-	u64 rax = addr | flags;
+	u32 edx = (pcid << 16) | asid;
 
 	/* The low bits in rax are for flags. Verify addr is clean. */
 	VM_WARN_ON_ONCE(addr & ~PAGE_MASK);
@@ -93,27 +120,6 @@ static inline void __invlpgb_all(unsigned long asid, unsigned long pcid, u8 flag
 static inline void __tlbsync(void) { }
 #endif
 
-/*
- * INVLPGB can be targeted by virtual address, PCID, ASID, or any combination
- * of the three. For example:
- * - FLAG_VA | FLAG_INCLUDE_GLOBAL: invalidate all TLB entries at the address
- * - FLAG_PCID:			    invalidate all TLB entries matching the PCID
- *
- * The first is used to invalidate (kernel) mappings at a particular
- * address across all processes.
- *
- * The latter invalidates all TLB entries matching a PCID.
- */
-#define INVLPGB_FLAG_VA			BIT(0)
-#define INVLPGB_FLAG_PCID		BIT(1)
-#define INVLPGB_FLAG_ASID		BIT(2)
-#define INVLPGB_FLAG_INCLUDE_GLOBAL	BIT(3)
-#define INVLPGB_FLAG_FINAL_ONLY		BIT(4)
-#define INVLPGB_FLAG_INCLUDE_NESTED	BIT(5)
-
-/* The implied mode when all bits are clear: */
-#define INVLPGB_MODE_ALL_NONGLOBALS	0UL
-
 static inline void invlpgb_flush_user_nr_nosync(unsigned long pcid,
 						unsigned long addr,
 						u16 nr, bool stride)

From ccc2f5a436fbb0ae1fb598932a9b8e48423c1959 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 4 Mar 2025 09:50:23 +0100
Subject: [PATCH 1019/1173] net: dsa: mt7530: Fix traffic flooding for MMIO
 devices

On MMIO devices (e.g. MT7988 or EN7581) unicast traffic received on lanX
port is flooded on all other user ports if the DSA switch is configured
without VLAN support since PORT_MATRIX in PCR regs contains all user
ports. Similar to MDIO devices (e.g. MT7530 and MT7531) fix the issue
defining default VLAN-ID 0 for MT7530 MMIO devices.

Fixes: 110c18bfed414 ("net: dsa: mt7530: introduce driver for MT7988 built-in switch")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Reviewed-by: Chester A. Unal <chester.a.unal@arinc9.com>
Link: https://patch.msgid.link/20250304-mt7988-flooding-fix-v1-1-905523ae83e9@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/mt7530.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index 1c83af805209c..5883eb93efb11 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -2591,7 +2591,8 @@ mt7531_setup_common(struct dsa_switch *ds)
 	if (ret < 0)
 		return ret;
 
-	return 0;
+	/* Setup VLAN ID 0 for VLAN-unaware bridges */
+	return mt7530_setup_vlan0(priv);
 }
 
 static int
@@ -2687,11 +2688,6 @@ mt7531_setup(struct dsa_switch *ds)
 	if (ret)
 		return ret;
 
-	/* Setup VLAN ID 0 for VLAN-unaware bridges */
-	ret = mt7530_setup_vlan0(priv);
-	if (ret)
-		return ret;
-
 	ds->assisted_learning_on_cpu_port = true;
 	ds->mtu_enforcement_ingress = true;
 

From 0a7565ee6ec31eb16c0476adbfc1af3f2271cb6b Mon Sep 17 00:00:00 2001
From: John Hubbard <jhubbard@nvidia.com>
Date: Thu, 13 Feb 2025 19:38:50 -0800
Subject: [PATCH 1020/1173] Revert "selftests/mm: remove local __NR_*
 definitions"

This reverts commit a5c6bc590094a1a73cf6fa3f505e1945d2bf2461.

The general approach described in commit e076eaca5906 ("selftests: break
the dependency upon local header files") was taken one step too far here:
it should not have been extended to include the syscall numbers.  This is
because doing so would require per-arch support in tools/include/uapi, and
no such support exists.

This revert fixes two separate reports of test failures, from Dave
Hansen[1], and Li Wang[2].  An excerpt of Dave's report:

Before this commit (a5c6bc590094a1a73cf6fa3f505e1945d2bf2461) things are
fine.  But after, I get:

	running PKEY tests for unsupported CPU/OS

An excerpt of Li's report:

    I just found that mlock2_() return a wrong value in mlock2-test

[1] https://lore.kernel.org/dc585017-6740-4cab-a536-b12b37a7582d@intel.com
[2] https://lore.kernel.org/CAEemH2eW=UMu9+turT2jRie7+6ewUazXmA6kL+VBo3cGDGU6RA@mail.gmail.com

Link: https://lkml.kernel.org/r/20250214033850.235171-1-jhubbard@nvidia.com
Fixes: a5c6bc590094 ("selftests/mm: remove local __NR_* definitions")
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Li Wang <liwang@redhat.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jeff Xu <jeffxu@chromium.org>
Cc: Andrei Vagin <avagin@google.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Kees Cook <kees@kernel.org>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Muhammad Usama Anjum <usama.anjum@collabora.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Rich Felker <dalias@libc.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/testing/selftests/mm/hugepage-mremap.c      |  2 +-
 tools/testing/selftests/mm/ksm_functional_tests.c |  8 +++++++-
 tools/testing/selftests/mm/memfd_secret.c         | 14 +++++++++++++-
 tools/testing/selftests/mm/mkdirty.c              |  8 +++++++-
 tools/testing/selftests/mm/mlock2.h               |  1 -
 tools/testing/selftests/mm/protection_keys.c      |  2 +-
 tools/testing/selftests/mm/uffd-common.c          |  4 ++++
 tools/testing/selftests/mm/uffd-stress.c          | 15 ++++++++++++++-
 tools/testing/selftests/mm/uffd-unit-tests.c      | 14 +++++++++++++-
 9 files changed, 60 insertions(+), 8 deletions(-)

diff --git a/tools/testing/selftests/mm/hugepage-mremap.c b/tools/testing/selftests/mm/hugepage-mremap.c
index ada9156cc497b..c463d1c09c9b4 100644
--- a/tools/testing/selftests/mm/hugepage-mremap.c
+++ b/tools/testing/selftests/mm/hugepage-mremap.c
@@ -15,7 +15,7 @@
 #define _GNU_SOURCE
 #include <stdlib.h>
 #include <stdio.h>
-#include <asm-generic/unistd.h>
+#include <unistd.h>
 #include <sys/mman.h>
 #include <errno.h>
 #include <fcntl.h> /* Definition of O_* constants */
diff --git a/tools/testing/selftests/mm/ksm_functional_tests.c b/tools/testing/selftests/mm/ksm_functional_tests.c
index 66b4e111b5a27..b61803e36d1cf 100644
--- a/tools/testing/selftests/mm/ksm_functional_tests.c
+++ b/tools/testing/selftests/mm/ksm_functional_tests.c
@@ -11,7 +11,7 @@
 #include <string.h>
 #include <stdbool.h>
 #include <stdint.h>
-#include <asm-generic/unistd.h>
+#include <unistd.h>
 #include <errno.h>
 #include <fcntl.h>
 #include <sys/mman.h>
@@ -369,6 +369,7 @@ static void test_unmerge_discarded(void)
 	munmap(map, size);
 }
 
+#ifdef __NR_userfaultfd
 static void test_unmerge_uffd_wp(void)
 {
 	struct uffdio_writeprotect uffd_writeprotect;
@@ -429,6 +430,7 @@ static void test_unmerge_uffd_wp(void)
 unmap:
 	munmap(map, size);
 }
+#endif
 
 /* Verify that KSM can be enabled / queried with prctl. */
 static void test_prctl(void)
@@ -684,7 +686,9 @@ int main(int argc, char **argv)
 		exit(test_child_ksm());
 	}
 
+#ifdef __NR_userfaultfd
 	tests++;
+#endif
 
 	ksft_print_header();
 	ksft_set_plan(tests);
@@ -696,7 +700,9 @@ int main(int argc, char **argv)
 	test_unmerge();
 	test_unmerge_zero_pages();
 	test_unmerge_discarded();
+#ifdef __NR_userfaultfd
 	test_unmerge_uffd_wp();
+#endif
 
 	test_prot_none();
 
diff --git a/tools/testing/selftests/mm/memfd_secret.c b/tools/testing/selftests/mm/memfd_secret.c
index 74c911aa3aea9..9a0597310a765 100644
--- a/tools/testing/selftests/mm/memfd_secret.c
+++ b/tools/testing/selftests/mm/memfd_secret.c
@@ -17,7 +17,7 @@
 
 #include <stdlib.h>
 #include <string.h>
-#include <asm-generic/unistd.h>
+#include <unistd.h>
 #include <errno.h>
 #include <stdio.h>
 #include <fcntl.h>
@@ -28,6 +28,8 @@
 #define pass(fmt, ...) ksft_test_result_pass(fmt, ##__VA_ARGS__)
 #define skip(fmt, ...) ksft_test_result_skip(fmt, ##__VA_ARGS__)
 
+#ifdef __NR_memfd_secret
+
 #define PATTERN	0x55
 
 static const int prot = PROT_READ | PROT_WRITE;
@@ -332,3 +334,13 @@ int main(int argc, char *argv[])
 
 	ksft_finished();
 }
+
+#else /* __NR_memfd_secret */
+
+int main(int argc, char *argv[])
+{
+	printf("skip: skipping memfd_secret test (missing __NR_memfd_secret)\n");
+	return KSFT_SKIP;
+}
+
+#endif /* __NR_memfd_secret */
diff --git a/tools/testing/selftests/mm/mkdirty.c b/tools/testing/selftests/mm/mkdirty.c
index af2fce496912b..09feeb4536460 100644
--- a/tools/testing/selftests/mm/mkdirty.c
+++ b/tools/testing/selftests/mm/mkdirty.c
@@ -9,7 +9,7 @@
  */
 #include <fcntl.h>
 #include <signal.h>
-#include <asm-generic/unistd.h>
+#include <unistd.h>
 #include <string.h>
 #include <errno.h>
 #include <stdlib.h>
@@ -265,6 +265,7 @@ static void test_pte_mapped_thp(void)
 	munmap(mmap_mem, mmap_size);
 }
 
+#ifdef __NR_userfaultfd
 static void test_uffdio_copy(void)
 {
 	struct uffdio_register uffdio_register;
@@ -322,6 +323,7 @@ static void test_uffdio_copy(void)
 	munmap(dst, pagesize);
 	free(src);
 }
+#endif /* __NR_userfaultfd */
 
 int main(void)
 {
@@ -334,7 +336,9 @@ int main(void)
 			       thpsize / 1024);
 		tests += 3;
 	}
+#ifdef __NR_userfaultfd
 	tests += 1;
+#endif /* __NR_userfaultfd */
 
 	ksft_print_header();
 	ksft_set_plan(tests);
@@ -364,7 +368,9 @@ int main(void)
 	if (thpsize)
 		test_pte_mapped_thp();
 	/* Placing a fresh page via userfaultfd may set the PTE dirty. */
+#ifdef __NR_userfaultfd
 	test_uffdio_copy();
+#endif /* __NR_userfaultfd */
 
 	err = ksft_get_fail_cnt();
 	if (err)
diff --git a/tools/testing/selftests/mm/mlock2.h b/tools/testing/selftests/mm/mlock2.h
index 1e5731bab499a..4417eaa5cfb78 100644
--- a/tools/testing/selftests/mm/mlock2.h
+++ b/tools/testing/selftests/mm/mlock2.h
@@ -3,7 +3,6 @@
 #include <errno.h>
 #include <stdio.h>
 #include <stdlib.h>
-#include <asm-generic/unistd.h>
 
 static int mlock2_(void *start, size_t len, int flags)
 {
diff --git a/tools/testing/selftests/mm/protection_keys.c b/tools/testing/selftests/mm/protection_keys.c
index a4683f2476f27..35565af308af6 100644
--- a/tools/testing/selftests/mm/protection_keys.c
+++ b/tools/testing/selftests/mm/protection_keys.c
@@ -42,7 +42,7 @@
 #include <sys/wait.h>
 #include <sys/stat.h>
 #include <fcntl.h>
-#include <asm-generic/unistd.h>
+#include <unistd.h>
 #include <sys/ptrace.h>
 #include <setjmp.h>
 
diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c
index 717539eddf987..7ad6ba660c7d6 100644
--- a/tools/testing/selftests/mm/uffd-common.c
+++ b/tools/testing/selftests/mm/uffd-common.c
@@ -673,7 +673,11 @@ int uffd_open_dev(unsigned int flags)
 
 int uffd_open_sys(unsigned int flags)
 {
+#ifdef __NR_userfaultfd
 	return syscall(__NR_userfaultfd, flags);
+#else
+	return -1;
+#endif
 }
 
 int uffd_open(unsigned int flags)
diff --git a/tools/testing/selftests/mm/uffd-stress.c b/tools/testing/selftests/mm/uffd-stress.c
index a4b83280998ab..944d559ade21f 100644
--- a/tools/testing/selftests/mm/uffd-stress.c
+++ b/tools/testing/selftests/mm/uffd-stress.c
@@ -33,10 +33,11 @@
  * pthread_mutex_lock will also verify the atomicity of the memory
  * transfer (UFFDIO_COPY).
  */
-#include <asm-generic/unistd.h>
+
 #include "uffd-common.h"
 
 uint64_t features;
+#ifdef __NR_userfaultfd
 
 #define BOUNCE_RANDOM		(1<<0)
 #define BOUNCE_RACINGFAULTS	(1<<1)
@@ -471,3 +472,15 @@ int main(int argc, char **argv)
 	       nr_pages, nr_pages_per_cpu);
 	return userfaultfd_stress();
 }
+
+#else /* __NR_userfaultfd */
+
+#warning "missing __NR_userfaultfd definition"
+
+int main(void)
+{
+	printf("skip: Skipping userfaultfd test (missing __NR_userfaultfd)\n");
+	return KSFT_SKIP;
+}
+
+#endif /* __NR_userfaultfd */
diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c
index 9ff71fa1f9bf0..74c8bc02b5063 100644
--- a/tools/testing/selftests/mm/uffd-unit-tests.c
+++ b/tools/testing/selftests/mm/uffd-unit-tests.c
@@ -5,11 +5,12 @@
  *  Copyright (C) 2015-2023  Red Hat, Inc.
  */
 
-#include <asm-generic/unistd.h>
 #include "uffd-common.h"
 
 #include "../../../../mm/gup_test.h"
 
+#ifdef __NR_userfaultfd
+
 /* The unit test doesn't need a large or random size, make it 32MB for now */
 #define  UFFD_TEST_MEM_SIZE               (32UL << 20)
 
@@ -1558,3 +1559,14 @@ int main(int argc, char *argv[])
 	return ksft_get_fail_cnt() ? KSFT_FAIL : KSFT_PASS;
 }
 
+#else /* __NR_userfaultfd */
+
+#warning "missing __NR_userfaultfd definition"
+
+int main(void)
+{
+	printf("Skipping %s (missing __NR_userfaultfd)\n", __file__);
+	return KSFT_SKIP;
+}
+
+#endif /* __NR_userfaultfd */

From 349db086a66051bc6114b64b4446787c20ac3f00 Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Mon, 17 Feb 2025 10:23:04 -0800
Subject: [PATCH 1021/1173] selftests/damon/damos_quota_goal: handle minimum
 quota that cannot be further reduced

damos_quota_goal.py selftest see if DAMOS quota goals tuning feature
increases or reduces the effective size quota for given score as expected.
The tuning feature sets the minimum quota size as one byte, so if the
effective size quota is already one, we cannot expect it further be
reduced.  However the test is not aware of the edge case, and fails since
it shown no expected change of the effective quota.  Handle the case by
updating the failure logic for no change to see if it was the case, and
simply skips to next test input.

Link: https://lkml.kernel.org/r/20250217182304.45215-1-sj@kernel.org
Fixes: f1c07c0a1662 ("selftests/damon: add a test for DAMOS quota goal")
Signed-off-by: SeongJae Park <sj@kernel.org>
Reported-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202502171423.b28a918d-lkp@intel.com
Cc: Shuah Khan <shuah@kernel.org>
Cc: <stable@vger.kernel.org>	[6.10.x]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/testing/selftests/damon/damos_quota_goal.py | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/testing/selftests/damon/damos_quota_goal.py b/tools/testing/selftests/damon/damos_quota_goal.py
index 18246f3b62f7e..f76e0412b564c 100755
--- a/tools/testing/selftests/damon/damos_quota_goal.py
+++ b/tools/testing/selftests/damon/damos_quota_goal.py
@@ -63,6 +63,9 @@ def main():
             if last_effective_bytes != 0 else -1.0))
 
         if last_effective_bytes == goal.effective_bytes:
+            # effective quota was already minimum that cannot be more reduced
+            if expect_increase is False and last_effective_bytes == 1:
+                continue
             print('efective bytes not changed: %d' % goal.effective_bytes)
             exit(1)
 

From 7277dd0a0ba4f8259f7abe37c4b7280fbfc2a182 Mon Sep 17 00:00:00 2001
From: Haoxiang Li <haoxiang_li2024@163.com>
Date: Tue, 18 Feb 2025 00:00:17 +0800
Subject: [PATCH 1022/1173] m68k: sun3: add check for __pgd_alloc()

Add check for the return value of __pgd_alloc() in pgd_alloc() to prevent
null pointer dereference.

Link: https://lkml.kernel.org/r/20250217160017.2375536-1-haoxiang_li2024@163.com
Fixes: a9b3c355c2e6 ("asm-generic: pgalloc: provide generic __pgd_{alloc,free}")
Signed-off-by: Haoxiang Li <haoxiang_li2024@163.com>
Reviewed-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Kevin Brodsky <kevin.brodsky@arm.com>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Sam Creasey <sammy@sammy.net>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/m68k/include/asm/sun3_pgalloc.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/m68k/include/asm/sun3_pgalloc.h b/arch/m68k/include/asm/sun3_pgalloc.h
index f1ae4ed890db5..80afc3a187249 100644
--- a/arch/m68k/include/asm/sun3_pgalloc.h
+++ b/arch/m68k/include/asm/sun3_pgalloc.h
@@ -44,8 +44,10 @@ static inline pgd_t * pgd_alloc(struct mm_struct *mm)
 	pgd_t *new_pgd;
 
 	new_pgd = __pgd_alloc(mm, 0);
-	memcpy(new_pgd, swapper_pg_dir, PAGE_SIZE);
-	memset(new_pgd, 0, (PAGE_OFFSET >> PGDIR_SHIFT));
+	if (likely(new_pgd != NULL)) {
+		memcpy(new_pgd, swapper_pg_dir, PAGE_SIZE);
+		memset(new_pgd, 0, (PAGE_OFFSET >> PGDIR_SHIFT));
+	}
 	return new_pgd;
 }
 

From a564ccfe300fa6a065beda06ab7f3c140d6b4d63 Mon Sep 17 00:00:00 2001
From: Qi Zheng <zhengqi.arch@bytedance.com>
Date: Mon, 17 Feb 2025 10:49:24 +0800
Subject: [PATCH 1023/1173] arm: pgtable: fix NULL pointer dereference issue

When update_mmu_cache_range() is called by update_mmu_cache(), the vmf
parameter is NULL, which will cause a NULL pointer dereference issue in
adjust_pte():

Unable to handle kernel NULL pointer dereference at virtual address 00000030 when read
Hardware name: Atmel AT91SAM9
PC is at update_mmu_cache_range+0x1e0/0x278
LR is at pte_offset_map_rw_nolock+0x18/0x2c
Call trace:
 update_mmu_cache_range from remove_migration_pte+0x29c/0x2ec
 remove_migration_pte from rmap_walk_file+0xcc/0x130
 rmap_walk_file from remove_migration_ptes+0x90/0xa4
 remove_migration_ptes from migrate_pages_batch+0x6d4/0x858
 migrate_pages_batch from migrate_pages+0x188/0x488
 migrate_pages from compact_zone+0x56c/0x954
 compact_zone from compact_node+0x90/0xf0
 compact_node from kcompactd+0x1d4/0x204
 kcompactd from kthread+0x120/0x12c
 kthread from ret_from_fork+0x14/0x38
Exception stack(0xc0d8bfb0 to 0xc0d8bff8)

To fix it, do not rely on whether 'ptl' is equal to decide whether to hold
the pte lock, but decide it by whether CONFIG_SPLIT_PTE_PTLOCKS is
enabled.  In addition, if two vmas map to the same PTE page, there is no
need to hold the pte lock again, otherwise a deadlock will occur.  Just
add the need_lock parameter to let adjust_pte() know this information.

Link: https://lkml.kernel.org/r/20250217024924.57996-1-zhengqi.arch@bytedance.com
Fixes: fc9c45b71f43 ("arm: adjust_pte() use pte_offset_map_rw_nolock()")
Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
Reported-by: Ezra Buehler <ezra.buehler@husqvarnagroup.com>
Closes: https://lore.kernel.org/lkml/CAM1KZSmZ2T_riHvay+7cKEFxoPgeVpHkVFTzVVEQ1BO0cLkHEQ@mail.gmail.com/
Acked-by: David Hildenbrand <david@redhat.com>
Tested-by: Ezra Buehler <ezra.buehler@husqvarnagroup.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Russel King <linux@armlinux.org.uk>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/arm/mm/fault-armv.c | 37 +++++++++++++++++++++++++------------
 1 file changed, 25 insertions(+), 12 deletions(-)

diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c
index 2bec87c3327d2..39fd5df733178 100644
--- a/arch/arm/mm/fault-armv.c
+++ b/arch/arm/mm/fault-armv.c
@@ -62,7 +62,7 @@ static int do_adjust_pte(struct vm_area_struct *vma, unsigned long address,
 }
 
 static int adjust_pte(struct vm_area_struct *vma, unsigned long address,
-		      unsigned long pfn, struct vm_fault *vmf)
+		      unsigned long pfn, bool need_lock)
 {
 	spinlock_t *ptl;
 	pgd_t *pgd;
@@ -99,12 +99,11 @@ static int adjust_pte(struct vm_area_struct *vma, unsigned long address,
 	if (!pte)
 		return 0;
 
-	/*
-	 * If we are using split PTE locks, then we need to take the page
-	 * lock here.  Otherwise we are using shared mm->page_table_lock
-	 * which is already locked, thus cannot take it.
-	 */
-	if (ptl != vmf->ptl) {
+	if (need_lock) {
+		/*
+		 * Use nested version here to indicate that we are already
+		 * holding one similar spinlock.
+		 */
 		spin_lock_nested(ptl, SINGLE_DEPTH_NESTING);
 		if (unlikely(!pmd_same(pmdval, pmdp_get_lockless(pmd)))) {
 			pte_unmap_unlock(pte, ptl);
@@ -114,7 +113,7 @@ static int adjust_pte(struct vm_area_struct *vma, unsigned long address,
 
 	ret = do_adjust_pte(vma, address, pfn, pte);
 
-	if (ptl != vmf->ptl)
+	if (need_lock)
 		spin_unlock(ptl);
 	pte_unmap(pte);
 
@@ -123,9 +122,10 @@ static int adjust_pte(struct vm_area_struct *vma, unsigned long address,
 
 static void
 make_coherent(struct address_space *mapping, struct vm_area_struct *vma,
-	      unsigned long addr, pte_t *ptep, unsigned long pfn,
-	      struct vm_fault *vmf)
+	      unsigned long addr, pte_t *ptep, unsigned long pfn)
 {
+	const unsigned long pmd_start_addr = ALIGN_DOWN(addr, PMD_SIZE);
+	const unsigned long pmd_end_addr = pmd_start_addr + PMD_SIZE;
 	struct mm_struct *mm = vma->vm_mm;
 	struct vm_area_struct *mpnt;
 	unsigned long offset;
@@ -141,6 +141,14 @@ make_coherent(struct address_space *mapping, struct vm_area_struct *vma,
 	 */
 	flush_dcache_mmap_lock(mapping);
 	vma_interval_tree_foreach(mpnt, &mapping->i_mmap, pgoff, pgoff) {
+		/*
+		 * If we are using split PTE locks, then we need to take the pte
+		 * lock. Otherwise we are using shared mm->page_table_lock which
+		 * is already locked, thus cannot take it.
+		 */
+		bool need_lock = IS_ENABLED(CONFIG_SPLIT_PTE_PTLOCKS);
+		unsigned long mpnt_addr;
+
 		/*
 		 * If this VMA is not in our MM, we can ignore it.
 		 * Note that we intentionally mask out the VMA
@@ -151,7 +159,12 @@ make_coherent(struct address_space *mapping, struct vm_area_struct *vma,
 		if (!(mpnt->vm_flags & VM_MAYSHARE))
 			continue;
 		offset = (pgoff - mpnt->vm_pgoff) << PAGE_SHIFT;
-		aliases += adjust_pte(mpnt, mpnt->vm_start + offset, pfn, vmf);
+		mpnt_addr = mpnt->vm_start + offset;
+
+		/* Avoid deadlocks by not grabbing the same PTE lock again. */
+		if (mpnt_addr >= pmd_start_addr && mpnt_addr < pmd_end_addr)
+			need_lock = false;
+		aliases += adjust_pte(mpnt, mpnt_addr, pfn, need_lock);
 	}
 	flush_dcache_mmap_unlock(mapping);
 	if (aliases)
@@ -194,7 +207,7 @@ void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma,
 		__flush_dcache_folio(mapping, folio);
 	if (mapping) {
 		if (cache_is_vivt())
-			make_coherent(mapping, vma, addr, ptep, pfn, vmf);
+			make_coherent(mapping, vma, addr, ptep, pfn);
 		else if (vma->vm_flags & VM_EXEC)
 			__flush_icache_all();
 	}

From b81679b1633aa43c0d973adfa816d78c1ed0d032 Mon Sep 17 00:00:00 2001
From: Ma Wupeng <mawupeng1@huawei.com>
Date: Mon, 17 Feb 2025 09:43:27 +0800
Subject: [PATCH 1024/1173] mm: memory-failure: update ttu flag inside
 unmap_poisoned_folio

Patch series "mm: memory_failure: unmap poisoned folio during migrate
properly", v3.

Fix two bugs during folio migration if the folio is poisoned.


This patch (of 3):

Commit 6da6b1d4a7df ("mm/hwpoison: convert TTU_IGNORE_HWPOISON to
TTU_HWPOISON") introduce TTU_HWPOISON to replace TTU_IGNORE_HWPOISON in
order to stop send SIGBUS signal when accessing an error page after a
memory error on a clean folio.  However during page migration, anon folio
must be set with TTU_HWPOISON during unmap_*().  For pagecache we need
some policy just like the one in hwpoison_user_mappings to set this flag.
So move this policy from hwpoison_user_mappings to unmap_poisoned_folio to
handle this warning properly.

Warning will be produced during unamp poison folio with the following log:

  ------------[ cut here ]------------
  WARNING: CPU: 1 PID: 365 at mm/rmap.c:1847 try_to_unmap_one+0x8fc/0xd3c
  Modules linked in:
  CPU: 1 UID: 0 PID: 365 Comm: bash Tainted: G        W          6.13.0-rc1-00018-gacdb4bbda7ab #42
  Tainted: [W]=WARN
  Hardware name: QEMU QEMU Virtual Machine, BIOS 0.0.0 02/06/2015
  pstate: 20400005 (nzCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
  pc : try_to_unmap_one+0x8fc/0xd3c
  lr : try_to_unmap_one+0x3dc/0xd3c
  Call trace:
   try_to_unmap_one+0x8fc/0xd3c (P)
   try_to_unmap_one+0x3dc/0xd3c (L)
   rmap_walk_anon+0xdc/0x1f8
   rmap_walk+0x3c/0x58
   try_to_unmap+0x88/0x90
   unmap_poisoned_folio+0x30/0xa8
   do_migrate_range+0x4a0/0x568
   offline_pages+0x5a4/0x670
   memory_block_action+0x17c/0x374
   memory_subsys_offline+0x3c/0x78
   device_offline+0xa4/0xd0
   state_store+0x8c/0xf0
   dev_attr_store+0x18/0x2c
   sysfs_kf_write+0x44/0x54
   kernfs_fop_write_iter+0x118/0x1a8
   vfs_write+0x3a8/0x4bc
   ksys_write+0x6c/0xf8
   __arm64_sys_write+0x1c/0x28
   invoke_syscall+0x44/0x100
   el0_svc_common.constprop.0+0x40/0xe0
   do_el0_svc+0x1c/0x28
   el0_svc+0x30/0xd0
   el0t_64_sync_handler+0xc8/0xcc
   el0t_64_sync+0x198/0x19c
  ---[ end trace 0000000000000000 ]---

[mawupeng1@huawei.com: unmap_poisoned_folio(): remove shadowed local `mapping', per Miaohe]
  Link: https://lkml.kernel.org/r/20250219060653.3849083-1-mawupeng1@huawei.com
Link: https://lkml.kernel.org/r/20250217014329.3610326-1-mawupeng1@huawei.com
Link: https://lkml.kernel.org/r/20250217014329.3610326-2-mawupeng1@huawei.com
Fixes: 6da6b1d4a7df ("mm/hwpoison: convert TTU_IGNORE_HWPOISON to TTU_HWPOISON")
Signed-off-by: Ma Wupeng <mawupeng1@huawei.com>
Suggested-by: David Hildenbrand <david@redhat.com>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Miaohe Lin <linmiaohe@huawei.com>
Cc: Ma Wupeng <mawupeng1@huawei.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/internal.h       |  5 ++--
 mm/memory-failure.c | 63 ++++++++++++++++++++++-----------------------
 mm/memory_hotplug.c |  3 ++-
 3 files changed, 36 insertions(+), 35 deletions(-)

diff --git a/mm/internal.h b/mm/internal.h
index 109ef30fee11f..20b3535935a31 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1115,7 +1115,7 @@ static inline int find_next_best_node(int node, nodemask_t *used_node_mask)
  * mm/memory-failure.c
  */
 #ifdef CONFIG_MEMORY_FAILURE
-void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu);
+int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill);
 void shake_folio(struct folio *folio);
 extern int hwpoison_filter(struct page *p);
 
@@ -1138,8 +1138,9 @@ unsigned long page_mapped_in_vma(const struct page *page,
 		struct vm_area_struct *vma);
 
 #else
-static inline void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
+static inline int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill)
 {
+	return -EBUSY;
 }
 #endif
 
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 995a15eb67e2c..327e02fdc029d 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1556,11 +1556,35 @@ static int get_hwpoison_page(struct page *p, unsigned long flags)
 	return ret;
 }
 
-void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
+int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill)
 {
-	if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) {
-		struct address_space *mapping;
+	enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_SYNC | TTU_HWPOISON;
+	struct address_space *mapping;
+
+	if (folio_test_swapcache(folio)) {
+		pr_err("%#lx: keeping poisoned page in swap cache\n", pfn);
+		ttu &= ~TTU_HWPOISON;
+	}
 
+	/*
+	 * Propagate the dirty bit from PTEs to struct page first, because we
+	 * need this to decide if we should kill or just drop the page.
+	 * XXX: the dirty test could be racy: set_page_dirty() may not always
+	 * be called inside page lock (it's recommended but not enforced).
+	 */
+	mapping = folio_mapping(folio);
+	if (!must_kill && !folio_test_dirty(folio) && mapping &&
+	    mapping_can_writeback(mapping)) {
+		if (folio_mkclean(folio)) {
+			folio_set_dirty(folio);
+		} else {
+			ttu &= ~TTU_HWPOISON;
+			pr_info("%#lx: corrupted page was clean: dropped without side effects\n",
+				pfn);
+		}
+	}
+
+	if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) {
 		/*
 		 * For hugetlb folios in shared mappings, try_to_unmap
 		 * could potentially call huge_pmd_unshare.  Because of
@@ -1572,7 +1596,7 @@ void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
 		if (!mapping) {
 			pr_info("%#lx: could not lock mapping for mapped hugetlb folio\n",
 				folio_pfn(folio));
-			return;
+			return -EBUSY;
 		}
 
 		try_to_unmap(folio, ttu|TTU_RMAP_LOCKED);
@@ -1580,6 +1604,8 @@ void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
 	} else {
 		try_to_unmap(folio, ttu);
 	}
+
+	return folio_mapped(folio) ? -EBUSY : 0;
 }
 
 /*
@@ -1589,8 +1615,6 @@ void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
 static bool hwpoison_user_mappings(struct folio *folio, struct page *p,
 		unsigned long pfn, int flags)
 {
-	enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_SYNC | TTU_HWPOISON;
-	struct address_space *mapping;
 	LIST_HEAD(tokill);
 	bool unmap_success;
 	int forcekill;
@@ -1613,29 +1637,6 @@ static bool hwpoison_user_mappings(struct folio *folio, struct page *p,
 	if (!folio_mapped(folio))
 		return true;
 
-	if (folio_test_swapcache(folio)) {
-		pr_err("%#lx: keeping poisoned page in swap cache\n", pfn);
-		ttu &= ~TTU_HWPOISON;
-	}
-
-	/*
-	 * Propagate the dirty bit from PTEs to struct page first, because we
-	 * need this to decide if we should kill or just drop the page.
-	 * XXX: the dirty test could be racy: set_page_dirty() may not always
-	 * be called inside page lock (it's recommended but not enforced).
-	 */
-	mapping = folio_mapping(folio);
-	if (!(flags & MF_MUST_KILL) && !folio_test_dirty(folio) && mapping &&
-	    mapping_can_writeback(mapping)) {
-		if (folio_mkclean(folio)) {
-			folio_set_dirty(folio);
-		} else {
-			ttu &= ~TTU_HWPOISON;
-			pr_info("%#lx: corrupted page was clean: dropped without side effects\n",
-				pfn);
-		}
-	}
-
 	/*
 	 * First collect all the processes that have the page
 	 * mapped in dirty form.  This has to be done before try_to_unmap,
@@ -1643,9 +1644,7 @@ static bool hwpoison_user_mappings(struct folio *folio, struct page *p,
 	 */
 	collect_procs(folio, p, &tokill, flags & MF_ACTION_REQUIRED);
 
-	unmap_poisoned_folio(folio, ttu);
-
-	unmap_success = !folio_mapped(folio);
+	unmap_success = !unmap_poisoned_folio(folio, pfn, flags & MF_MUST_KILL);
 	if (!unmap_success)
 		pr_err("%#lx: failed to unmap page (folio mapcount=%d)\n",
 		       pfn, folio_mapcount(folio));
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index e3655f07dd6e3..e7e47838fd494 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1833,7 +1833,8 @@ static void do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 			if (WARN_ON(folio_test_lru(folio)))
 				folio_isolate_lru(folio);
 			if (folio_mapped(folio))
-				unmap_poisoned_folio(folio, TTU_IGNORE_MLOCK);
+				unmap_poisoned_folio(folio, pfn, false);
+
 			continue;
 		}
 

From 773b9a6aa6d38894b95088e3ed6f8a701d9f50fd Mon Sep 17 00:00:00 2001
From: Ma Wupeng <mawupeng1@huawei.com>
Date: Mon, 17 Feb 2025 09:43:28 +0800
Subject: [PATCH 1025/1173] mm: memory-hotplug: check folio ref count first in
 do_migrate_range

If a folio has an increased reference count, folio_try_get() will acquire
it, perform necessary operations, and then release it.  In the case of a
poisoned folio without an elevated reference count (which is unlikely for
memory-failure), folio_try_get() will simply bypass it.

Therefore, relocate the folio_try_get() function, responsible for checking
and acquiring this reference count at first.

Link: https://lkml.kernel.org/r/20250217014329.3610326-3-mawupeng1@huawei.com
Signed-off-by: Ma Wupeng <mawupeng1@huawei.com>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/memory_hotplug.c | 20 +++++++-------------
 1 file changed, 7 insertions(+), 13 deletions(-)

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index e7e47838fd494..a6abd8d4a09c6 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1822,12 +1822,12 @@ static void do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 		if (folio_test_large(folio))
 			pfn = folio_pfn(folio) + folio_nr_pages(folio) - 1;
 
-		/*
-		 * HWPoison pages have elevated reference counts so the migration would
-		 * fail on them. It also doesn't make any sense to migrate them in the
-		 * first place. Still try to unmap such a page in case it is still mapped
-		 * (keep the unmap as the catch all safety net).
-		 */
+		if (!folio_try_get(folio))
+			continue;
+
+		if (unlikely(page_folio(page) != folio))
+			goto put_folio;
+
 		if (folio_test_hwpoison(folio) ||
 		    (folio_test_large(folio) && folio_test_has_hwpoisoned(folio))) {
 			if (WARN_ON(folio_test_lru(folio)))
@@ -1835,14 +1835,8 @@ static void do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 			if (folio_mapped(folio))
 				unmap_poisoned_folio(folio, pfn, false);
 
-			continue;
-		}
-
-		if (!folio_try_get(folio))
-			continue;
-
-		if (unlikely(page_folio(page) != folio))
 			goto put_folio;
+		}
 
 		if (!isolate_folio_to_list(folio, &source)) {
 			if (__ratelimit(&migrate_rs)) {

From af288a426c3e3552b62595c6138ec6371a17dbba Mon Sep 17 00:00:00 2001
From: Ma Wupeng <mawupeng1@huawei.com>
Date: Mon, 17 Feb 2025 09:43:29 +0800
Subject: [PATCH 1026/1173] hwpoison, memory_hotplug: lock folio before unmap
 hwpoisoned folio

Commit b15c87263a69 ("hwpoison, memory_hotplug: allow hwpoisoned pages to
be offlined) add page poison checks in do_migrate_range in order to make
offline hwpoisoned page possible by introducing isolate_lru_page and
try_to_unmap for hwpoisoned page.  However folio lock must be held before
calling try_to_unmap.  Add it to fix this problem.

Warning will be produced if folio is not locked during unmap:

  ------------[ cut here ]------------
  kernel BUG at ./include/linux/swapops.h:400!
  Internal error: Oops - BUG: 00000000f2000800 [#1] PREEMPT SMP
  Modules linked in:
  CPU: 4 UID: 0 PID: 411 Comm: bash Tainted: G        W          6.13.0-rc1-00016-g3c434c7ee82a-dirty #41
  Tainted: [W]=WARN
  Hardware name: QEMU QEMU Virtual Machine, BIOS 0.0.0 02/06/2015
  pstate: 40400005 (nZcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
  pc : try_to_unmap_one+0xb08/0xd3c
  lr : try_to_unmap_one+0x3dc/0xd3c
  Call trace:
   try_to_unmap_one+0xb08/0xd3c (P)
   try_to_unmap_one+0x3dc/0xd3c (L)
   rmap_walk_anon+0xdc/0x1f8
   rmap_walk+0x3c/0x58
   try_to_unmap+0x88/0x90
   unmap_poisoned_folio+0x30/0xa8
   do_migrate_range+0x4a0/0x568
   offline_pages+0x5a4/0x670
   memory_block_action+0x17c/0x374
   memory_subsys_offline+0x3c/0x78
   device_offline+0xa4/0xd0
   state_store+0x8c/0xf0
   dev_attr_store+0x18/0x2c
   sysfs_kf_write+0x44/0x54
   kernfs_fop_write_iter+0x118/0x1a8
   vfs_write+0x3a8/0x4bc
   ksys_write+0x6c/0xf8
   __arm64_sys_write+0x1c/0x28
   invoke_syscall+0x44/0x100
   el0_svc_common.constprop.0+0x40/0xe0
   do_el0_svc+0x1c/0x28
   el0_svc+0x30/0xd0
   el0t_64_sync_handler+0xc8/0xcc
   el0t_64_sync+0x198/0x19c
  Code: f9407be0 b5fff320 d4210000 17ffff97 (d4210000)
  ---[ end trace 0000000000000000 ]---

Link: https://lkml.kernel.org/r/20250217014329.3610326-4-mawupeng1@huawei.com
Fixes: b15c87263a69 ("hwpoison, memory_hotplug: allow hwpoisoned pages to be offlined")
Signed-off-by: Ma Wupeng <mawupeng1@huawei.com>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/memory_hotplug.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index a6abd8d4a09c6..16cf9e17077e3 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1832,8 +1832,11 @@ static void do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 		    (folio_test_large(folio) && folio_test_has_hwpoisoned(folio))) {
 			if (WARN_ON(folio_test_lru(folio)))
 				folio_isolate_lru(folio);
-			if (folio_mapped(folio))
+			if (folio_mapped(folio)) {
+				folio_lock(folio);
 				unmap_poisoned_folio(folio, pfn, false);
+				folio_unlock(folio);
+			}
 
 			goto put_folio;
 		}

From 04ec365e3fdf136ba5f9053b02fb6c3368a22e83 Mon Sep 17 00:00:00 2001
From: Ujwal Kundur <ujwal.kundur@gmail.com>
Date: Sat, 15 Feb 2025 16:21:07 +0530
Subject: [PATCH 1027/1173] Documentation: fix doc link to fault-injection.rst

Fix incorrect reference to fault-injection docs

Link: https://lkml.kernel.org/r/20250215105106.734-1-ujwal.kundur@gmail.com
Signed-off-by: Ujwal Kundur <ujwal.kundur@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 lib/Kconfig.debug | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 1af972a92d06f..35796c290ca35 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -2103,7 +2103,7 @@ config FAIL_SKB_REALLOC
 	  reallocated, catching possible invalid pointers to the skb.
 
 	  For more information, check
-	  Documentation/dev-tools/fault-injection/fault-injection.rst
+	  Documentation/fault-injection/fault-injection.rst
 
 config FAULT_INJECTION_CONFIGFS
 	bool "Configfs interface for fault-injection capabilities"

From 19fac3c93991502a22c5132824c40b6a2e64b136 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Tue, 18 Feb 2025 10:14:11 +0100
Subject: [PATCH 1028/1173] dma: kmsan: export kmsan_handle_dma() for modules

kmsan_handle_dma() is used by virtio_ring() which can be built as a
module.  kmsan_handle_dma() needs to be exported otherwise building the
virtio_ring fails.

Export kmsan_handle_dma for modules.

Link: https://lkml.kernel.org/r/20250218091411.MMS3wBN9@linutronix.de
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202502150634.qjxwSeJR-lkp@intel.com/
Fixes: 7ade4f10779c ("dma: kmsan: unpoison DMA mappings")
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Alexander Potapenko <glider@google.com>
Cc: Dmitriy Vyukov <dvyukov@google.com>
Cc: Macro Elver <elver@google.com>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/kmsan/hooks.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/mm/kmsan/hooks.c b/mm/kmsan/hooks.c
index 3ea50f09311fd..3df45c25c1f62 100644
--- a/mm/kmsan/hooks.c
+++ b/mm/kmsan/hooks.c
@@ -357,6 +357,7 @@ void kmsan_handle_dma(struct page *page, size_t offset, size_t size,
 		size -= to_go;
 	}
 }
+EXPORT_SYMBOL_GPL(kmsan_handle_dma);
 
 void kmsan_handle_dma_sg(struct scatterlist *sg, int nents,
 			 enum dma_data_direction dir)

From c3e998398de48a7528842f05858a3a6bb21002e6 Mon Sep 17 00:00:00 2001
From: gao xu <gaoxu2@honor.com>
Date: Wed, 19 Feb 2025 01:56:28 +0000
Subject: [PATCH 1029/1173] mm: fix possible NULL pointer dereference in
 __swap_duplicate

Add a NULL check on the return value of swp_swap_info in __swap_duplicate
to prevent crashes caused by NULL pointer dereference.

The reason why swp_swap_info() returns NULL is unclear; it may be due
to CPU cache issues or DDR bit flips.  The probability of this issue is
very small - it has been observed to occur approximately 1 in 500,000
times per week.  The stack info we encountered is as follows:

Unable to handle kernel NULL pointer dereference at virtual address
0000000000000058
[RB/E]rb_sreason_str_set: sreason_str set null_pointer
Mem abort info:
  ESR = 0x0000000096000005
  EC = 0x25: DABT (current EL), IL = 32 bits
  SET = 0, FnV = 0
  EA = 0, S1PTW = 0
  FSC = 0x05: level 1 translation fault
Data abort info:
  ISV = 0, ISS = 0x00000005, ISS2 = 0x00000000
  CM = 0, WnR = 0, TnD = 0, TagAccess = 0
  GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
user pgtable: 4k pages, 39-bit VAs, pgdp=00000008a80e5000
[0000000000000058] pgd=0000000000000000, p4d=0000000000000000,
pud=0000000000000000
Internal error: Oops: 0000000096000005 [#1] PREEMPT SMP
Skip md ftrace buffer dump for: 0x1609e0
...
pc : swap_duplicate+0x44/0x164
lr : copy_page_range+0x508/0x1e78
sp : ffffffc0f2a699e0
x29: ffffffc0f2a699e0 x28: ffffff8a5b28d388 x27: ffffff8b06603388
x26: ffffffdf7291fe70 x25: 0000000000000006 x24: 0000000000100073
x23: 00000000002d2d2f x22: 0000000000000008 x21: 0000000000000000
x20: 00000000002d2d2f x19: 18000000002d2d2f x18: ffffffdf726faec0
x17: 0000000000000000 x16: 0010000000000001 x15: 0040000000000001
x14: 0400000000000001 x13: ff7ffffffffffb7f x12: ffeffffffffffbff
x11: ffffff8a5c7e1898 x10: 0000000000000018 x9 : 0000000000000006
x8 : 1800000000000000 x7 : 0000000000000000 x6 : ffffff8057c01f10
x5 : 000000000000a318 x4 : 0000000000000000 x3 : 0000000000000000
x2 : 0000006daf200000 x1 : 0000000000000001 x0 : 18000000002d2d2f
Call trace:
 swap_duplicate+0x44/0x164
 copy_page_range+0x508/0x1e78
 copy_process+0x1278/0x21cc
 kernel_clone+0x90/0x438
 __arm64_sys_clone+0x5c/0x8c
 invoke_syscall+0x58/0x110
 do_el0_svc+0x8c/0xe0
 el0_svc+0x38/0x9c
 el0t_64_sync_handler+0x44/0xec
 el0t_64_sync+0x1a8/0x1ac
Code: 9139c35a 71006f3f 54000568 f8797b55 (f9402ea8)
---[ end trace 0000000000000000 ]---
Kernel panic - not syncing: Oops: Fatal exception
SMP: stopping secondary CPUs

The patch seems to only provide a workaround, but there are no more
effective software solutions to handle the bit flips problem.  This path
will change the issue from a system crash to a process exception, thereby
reducing the impact on the entire machine.

akpm: this is probably a kernel bug, but this patch keeps the system
running and doesn't reduce that bug's debuggability.

Link: https://lkml.kernel.org/r/e223b0e6ba2f4924984b1917cc717bd5@honor.com
Signed-off-by: gao xu <gaoxu2@honor.com>
Reviewed-by: Barry Song <baohua@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Yosry Ahmed <yosry.ahmed@linux.dev>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/swapfile.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/mm/swapfile.c b/mm/swapfile.c
index ba19430dd4ead..fab99d67026aa 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -3542,6 +3542,10 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage, int nr)
 	int err, i;
 
 	si = swp_swap_info(entry);
+	if (WARN_ON_ONCE(!si)) {
+		pr_err("%s%08lx\n", Bad_file, entry.val);
+		return -EINVAL;
+	}
 
 	offset = swp_offset(entry);
 	VM_WARN_ON(nr > SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER);

From 67bab13307c83fb742c2556b06cdc39dbad27f07 Mon Sep 17 00:00:00 2001
From: Ge Yang <yangge1116@126.com>
Date: Wed, 19 Feb 2025 11:46:44 +0800
Subject: [PATCH 1030/1173] mm/hugetlb: wait for hugetlb folios to be freed

Since the introduction of commit c77c0a8ac4c52 ("mm/hugetlb: defer freeing
of huge pages if in non-task context"), which supports deferring the
freeing of hugetlb pages, the allocation of contiguous memory through
cma_alloc() may fail probabilistically.

In the CMA allocation process, if it is found that the CMA area is
occupied by in-use hugetlb folios, these in-use hugetlb folios need to be
migrated to another location.  When there are no available hugetlb folios
in the free hugetlb pool during the migration of in-use hugetlb folios,
new folios are allocated from the buddy system.  A temporary state is set
on the newly allocated folio.  Upon completion of the hugetlb folio
migration, the temporary state is transferred from the new folios to the
old folios.  Normally, when the old folios with the temporary state are
freed, it is directly released back to the buddy system.  However, due to
the deferred freeing of hugetlb pages, the PageBuddy() check fails,
ultimately leading to the failure of cma_alloc().

Here is a simplified call trace illustrating the process:
cma_alloc()
    ->__alloc_contig_migrate_range() // Migrate in-use hugetlb folios
        ->unmap_and_move_huge_page()
            ->folio_putback_hugetlb() // Free old folios
    ->test_pages_isolated()
        ->__test_page_isolated_in_pageblock()
             ->PageBuddy(page) // Check if the page is in buddy

To resolve this issue, we have implemented a function named
wait_for_freed_hugetlb_folios().  This function ensures that the hugetlb
folios are properly released back to the buddy system after their
migration is completed.  By invoking wait_for_freed_hugetlb_folios()
before calling PageBuddy(), we ensure that PageBuddy() will succeed.

Link: https://lkml.kernel.org/r/1739936804-18199-1-git-send-email-yangge1116@126.com
Fixes: c77c0a8ac4c5 ("mm/hugetlb: defer freeing of huge pages if in non-task context")
Signed-off-by: Ge Yang <yangge1116@126.com>
Reviewed-by: Muchun Song <muchun.song@linux.dev>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Barry Song <21cnbao@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/hugetlb.h |  5 +++++
 mm/hugetlb.c            |  8 ++++++++
 mm/page_isolation.c     | 10 ++++++++++
 3 files changed, 23 insertions(+)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index ec8c0ccc8f959..dbe76d4f1bfc8 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -682,6 +682,7 @@ struct huge_bootmem_page {
 
 int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list);
 int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn);
+void wait_for_freed_hugetlb_folios(void);
 struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 				unsigned long addr, bool cow_from_owner);
 struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid,
@@ -1066,6 +1067,10 @@ static inline int replace_free_hugepage_folios(unsigned long start_pfn,
 	return 0;
 }
 
+static inline void wait_for_freed_hugetlb_folios(void)
+{
+}
+
 static inline struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 					   unsigned long addr,
 					   bool cow_from_owner)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 163190e89ea16..811b29f77abf8 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2943,6 +2943,14 @@ int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn)
 	return ret;
 }
 
+void wait_for_freed_hugetlb_folios(void)
+{
+	if (llist_empty(&hpage_freelist))
+		return;
+
+	flush_work(&free_hpage_work);
+}
+
 typedef enum {
 	/*
 	 * For either 0/1: we checked the per-vma resv map, and one resv
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index c608e9d728655..a051a29e95ad0 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -607,6 +607,16 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
 	struct zone *zone;
 	int ret;
 
+	/*
+	 * Due to the deferred freeing of hugetlb folios, the hugepage folios may
+	 * not immediately release to the buddy system. This can cause PageBuddy()
+	 * to fail in __test_page_isolated_in_pageblock(). To ensure that the
+	 * hugetlb folios are properly released back to the buddy system, we
+	 * invoke the wait_for_freed_hugetlb_folios() function to wait for the
+	 * release to complete.
+	 */
+	wait_for_freed_hugetlb_folios();
+
 	/*
 	 * Note: pageblock_nr_pages != MAX_PAGE_ORDER. Then, chunks of free
 	 * pages are not aligned to pageblock_nr_pages.

From 47b16d0462a460000b8f05dfb1292377ac48f3ca Mon Sep 17 00:00:00 2001
From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Date: Sat, 22 Feb 2025 16:19:52 +0000
Subject: [PATCH 1031/1173] mm: abort vma_modify() on merge out of memory
 failure

The remainder of vma_modify() relies upon the vmg state remaining pristine
after a merge attempt.

Usually this is the case, however in the one edge case scenario of a merge
attempt failing not due to the specified range being unmergeable, but
rather due to an out of memory error arising when attempting to commit the
merge, this assumption becomes untrue.

This results in vmg->start, end being modified, and thus the proceeding
attempts to split the VMA will be done with invalid start/end values.

Thankfully, it is likely practically impossible for us to hit this in
reality, as it would require a maple tree node pre-allocation failure that
would likely never happen due to it being 'too small to fail', i.e.  the
kernel would simply keep retrying reclaim until it succeeded.

However, this scenario remains theoretically possible, and what we are
doing here is wrong so we must correct it.

The safest option is, when this scenario occurs, to simply give up the
operation.  If we cannot allocate memory to merge, then we cannot allocate
memory to split either (perhaps moreso!).

Any scenario where this would be happening would be under very extreme
(likely fatal) memory pressure, so it's best we give up early.

So there is no doubt it is appropriate to simply bail out in this
scenario.

However, in general we must if at all possible never assume VMG state is
stable after a merge attempt, since merge operations update VMG fields.
As a result, additionally also make this clear by storing start, end in
local variables.

The issue was reported originally by syzkaller, and by Brad Spengler (via
an off-list discussion), and in both instances it manifested as a
triggering of the assert:

	VM_WARN_ON_VMG(start >= end, vmg);

In vma_merge_existing_range().

It seems at least one scenario in which this is occurring is one in which
the merge being attempted is due to an madvise() across multiple VMAs
which looks like this:

        start     end
          |<------>|
     |----------|------|
     |   vma    | next |
     |----------|------|

When madvise_walk_vmas() is invoked, we first find vma in the above
(determining prev to be equal to vma as we are offset into vma), and then
enter the loop.

We determine the end of vma that forms part of the range we are
madvise()'ing by setting 'tmp' to this value:

		/* Here vma->vm_start <= start < (end|vma->vm_end) */
		tmp = vma->vm_end;

We then invoke the madvise() operation via visit(), letting prev get
updated to point to vma as part of the operation:

		/* Here vma->vm_start <= start < tmp <= (end|vma->vm_end). */
		error = visit(vma, &prev, start, tmp, arg);

Where the visit() function pointer in this instance is
madvise_vma_behavior().

As observed in syzkaller reports, it is ultimately madvise_update_vma()
that is invoked, calling vma_modify_flags_name() and vma_modify() in turn.

Then, in vma_modify(), we attempt the merge:

	merged = vma_merge_existing_range(vmg);
	if (merged)
		return merged;

We invoke this with vmg->start, end set to start, tmp as such:

        start  tmp
          |<--->|
     |----------|------|
     |   vma    | next |
     |----------|------|

We find ourselves in the merge right scenario, but the one in which we
cannot remove the middle (we are offset into vma).

Here we have a special case where vmg->start, end get set to perhaps
unintuitive values - we intended to shrink the middle VMA and expand the
next.

This means vmg->start, end are set to...  vma->vm_start, start.

Now the commit_merge() fails, and vmg->start, end are left like this.
This means we return to the rest of vma_modify() with vmg->start, end
(here denoted as start', end') set as:

  start' end'
     |<-->|
     |----------|------|
     |   vma    | next |
     |----------|------|

So we now erroneously try to split accordingly.  This is where the
unfortunate stuff begins.

We start with:

	/* Split any preceding portion of the VMA. */
	if (vma->vm_start < vmg->start) {
		...
	}

This doesn't trigger as we are no longer offset into vma at the start.

But then we invoke:

	/* Split any trailing portion of the VMA. */
	if (vma->vm_end > vmg->end) {
		...
	}

Which does get invoked. This leaves us with:

  start' end'
     |<-->|
     |----|-----|------|
     | vma| new | next |
     |----|-----|------|

We then return ultimately to madvise_walk_vmas().  Here 'new' is unknown,
and putting back the values known in this function we are faced with:

        start tmp end
          |     |  |
     |----|-----|------|
     | vma| new | next |
     |----|-----|------|
      prev

Then:

		start = tmp;

So:

             start end
                |  |
     |----|-----|------|
     | vma| new | next |
     |----|-----|------|
      prev

The following code does not cause anything to happen:

		if (prev && start < prev->vm_end)
			start = prev->vm_end;
		if (start >= end)
			break;

And then we invoke:

		if (prev)
			vma = find_vma(mm, prev->vm_end);

Which is where a problem occurs - we don't know about 'new' so we
essentially look for the vma after prev, which is new, whereas we actually
intended to discover next!

So we end up with:

             start end
                |  |
     |----|-----|------|
     |prev| vma | next |
     |----|-----|------|

And we have successfully bypassed all of the checks madvise_walk_vmas()
has to ensure early exit should we end up moving out of range.

We loop around, and hit:

		/* Here vma->vm_start <= start < (end|vma->vm_end) */
		tmp = vma->vm_end;

Oh dear. Now we have:

              tmp
             start end
                |  |
     |----|-----|------|
     |prev| vma | next |
     |----|-----|------|

We then invoke:

		/* Here vma->vm_start <= start < tmp <= (end|vma->vm_end). */
		error = visit(vma, &prev, start, tmp, arg);

Where start == tmp. That is, a zero range. This is not good.

We invoke visit() which is madvise_vma_behavior() which does not check the
range (for good reason, it assumes all checks have been done before it was
called), which in turn finally calls madvise_update_vma().

The madvise_update_vma() function calls vma_modify_flags_name() in turn,
which ultimately invokes vma_modify() with...  start == end.

vma_modify() calls vma_merge_existing_range() and finally we hit:

	VM_WARN_ON_VMG(start >= end, vmg);

Which triggers, as start == end.

While it might be useful to add some CONFIG_DEBUG_VM asserts in these
instances to catch this kind of error, since we have just eliminated any
possibility of that happening, we will add such asserts separately as to
reduce churn and aid backporting.

Link: https://lkml.kernel.org/r/20250222161952.41957-1-lorenzo.stoakes@oracle.com
Fixes: 2f1c6611b0a8 ("mm: introduce vma_merge_struct and abstract vma_merge(),vma_modify()")
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Tested-by: Brad Spengler <brad.spengler@opensrcsec.com>
Reported-by: Brad Spengler <brad.spengler@opensrcsec.com>
Reported-by: syzbot+46423ed8fa1f1148c6e4@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/linux-mm/6774c98f.050a0220.25abdd.0991.GAE@google.com/
Cc: Jann Horn <jannh@google.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/vma.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/mm/vma.c b/mm/vma.c
index af1d549b179c9..96bcb372c90e4 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -1509,24 +1509,28 @@ int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm,
 static struct vm_area_struct *vma_modify(struct vma_merge_struct *vmg)
 {
 	struct vm_area_struct *vma = vmg->vma;
+	unsigned long start = vmg->start;
+	unsigned long end = vmg->end;
 	struct vm_area_struct *merged;
 
 	/* First, try to merge. */
 	merged = vma_merge_existing_range(vmg);
 	if (merged)
 		return merged;
+	if (vmg_nomem(vmg))
+		return ERR_PTR(-ENOMEM);
 
 	/* Split any preceding portion of the VMA. */
-	if (vma->vm_start < vmg->start) {
-		int err = split_vma(vmg->vmi, vma, vmg->start, 1);
+	if (vma->vm_start < start) {
+		int err = split_vma(vmg->vmi, vma, start, 1);
 
 		if (err)
 			return ERR_PTR(err);
 	}
 
 	/* Split any trailing portion of the VMA. */
-	if (vma->vm_end > vmg->end) {
-		int err = split_vma(vmg->vmi, vma, vmg->end, 0);
+	if (vma->vm_end > end) {
+		int err = split_vma(vmg->vmi, vma, end, 0);
 
 		if (err)
 			return ERR_PTR(err);

From 51f271c1940fc9a5f77931ec603b457ea293bd56 Mon Sep 17 00:00:00 2001
From: Kemeng Shi <shikemeng@huaweicloud.com>
Date: Mon, 24 Feb 2025 19:39:10 +0800
Subject: [PATCH 1032/1173] mm: swap: add back full cluster when no entry is
 reclaimed

If no swap cache is reclaimed, cluster taken off from full_clusters list
will not be put in any list and we can't reclaime HAS_CACHE slots
efficiently.  Do relocate_cluster for such cluster to avoid inefficiency.

Link: https://lkml.kernel.org/r/20250224113910.522439-1-shikemeng@huaweicloud.com
Fixes: 3b644773eefd ("mm, swap: reduce contention on device lock")
Signed-off-by: Kemeng Shi <shikemeng@huaweicloud.com>
Reviewed-by: Kairui Song <kasong@tencent.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/swapfile.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/mm/swapfile.c b/mm/swapfile.c
index fab99d67026aa..a6c41c7ffb037 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -858,6 +858,10 @@ static void swap_reclaim_full_clusters(struct swap_info_struct *si, bool force)
 			offset++;
 		}
 
+		/* in case no swap cache is reclaimed */
+		if (ci->flags == CLUSTER_FLAG_NONE)
+			relocate_cluster(si, ci);
+
 		unlock_cluster(ci);
 		if (to_scan <= 0)
 			break;

From 7a2e7ae5d13658ada38898e5a3a8a40a7910db06 Mon Sep 17 00:00:00 2001
From: Kemeng Shi <shikemeng@huaweicloud.com>
Date: Sun, 23 Feb 2025 00:08:46 +0800
Subject: [PATCH 1033/1173] mm: swap: use correct step in loop to wait all
 clusters in wait_for_allocation()

Use correct step in loop to wait all clusters in wait_for_allocation().
If we miss some cluster in wait_for_allocation(), use after free may occur
as follows:

shmem_writepage                  swapoff
 folio_alloc_swap
  get_swap_pages
   scan_swap_map_slots
    cluster_alloc_swap_entry
     alloc_swap_scan_cluster
      cluster_alloc_range
       /* SWP_WRITEOK is valid */
       if (!(si->flags & SWP_WRITEOK))

                                  ...
                                  del_from_avail_list(p, true);
                                  ...
                                  /* miss the cluster in shmem_writepage */
                                  wait_for_allocation()
                                  ...
                                  try_to_unuse()

       memset(si->swap_map + start, usage, nr_pages);
       swap_range_alloc(si, nr_pages);
       ci->count += nr_pages;
       /* return a valid entry */

                                  ...
                                  exit_swap_address_space(p->type);
                                  ...

 ...
 add_to_swap_cache
  /* dereference swap_address_space(entry) which is NULL */
  xas_lock_irq(&xas);

Link: https://lkml.kernel.org/r/20250222160850.505274-3-shikemeng@huaweicloud.com
Fixes: 9a0ddeb79880 ("mm, swap: hold a reference during scan and cleanup flag usage")
Signed-off-by: Kemeng Shi <shikemeng@huaweicloud.com>
Reviewed-by: Kairui Song <kasong@tencent.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/swapfile.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/mm/swapfile.c b/mm/swapfile.c
index a6c41c7ffb037..6460b6cb36c99 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2645,7 +2645,6 @@ static void wait_for_allocation(struct swap_info_struct *si)
 	for (offset = 0; offset < end; offset += SWAPFILE_CLUSTER) {
 		ci = lock_cluster(si, offset);
 		unlock_cluster(ci);
-		offset += SWAPFILE_CLUSTER;
 	}
 }
 

From 57d910cffaa0be981f558ff603e2d896b36b8241 Mon Sep 17 00:00:00 2001
From: Kemeng Shi <shikemeng@huaweicloud.com>
Date: Sun, 23 Feb 2025 00:08:47 +0800
Subject: [PATCH 1034/1173] mm, swap: avoid BUG_ON in relocate_cluster()

If allocation is racy with swapoff, we may call free_cluster for cluster
already in free list and trigger BUG_ON() as following:

Allocation                        Swapoff
cluster_alloc_swap_entry
 ...
 /* may get a free cluster with offset */
 offset = xxx;
 if (offset)
  ci = lock_cluster(si, offset);

                                  ...
                                   del_from_avail_list(p, true);
                                    si->flags &= ~SWP_WRITEOK;

  alloc_swap_scan_cluster(si, ci, ...)
   ...
   /* failed to alloc entry from free entry */
   if (!cluster_alloc_range(...))
    break;
   ...
   /* add back a free cluster */
   relocate_cluster(si, ci);
    if (!ci->count)
     free_cluster(si, ci);
      VM_BUG_ON(ci->flags == CLUSTER_FLAG_FREE);

To prevent the BUG_ON(), call free_cluster() for free cluster to move the
cluster to tail of list.

Check cluster is not free before calling free_cluster() in
relocate_cluster() to avoid BUG_ON().

Link: https://lkml.kernel.org/r/20250222160850.505274-4-shikemeng@huaweicloud.com
Fixes: 3b644773eefd ("mm, swap: reduce contention on device lock")
Signed-off-by: Kemeng Shi <shikemeng@huaweicloud.com>
Reviewed-by: Kairui Song <kasong@tencent.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/swapfile.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/mm/swapfile.c b/mm/swapfile.c
index 6460b6cb36c99..df7c4e8b089ca 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -653,7 +653,8 @@ static void relocate_cluster(struct swap_info_struct *si,
 		return;
 
 	if (!ci->count) {
-		free_cluster(si, ci);
+		if (ci->flags != CLUSTER_FLAG_FREE)
+			free_cluster(si, ci);
 	} else if (ci->count != SWAPFILE_CLUSTER) {
 		if (ci->flags != CLUSTER_FLAG_FRAG)
 			move_cluster(si, ci, &si->frag_clusters[ci->order],

From ce6d9c1c2b5cc785016faa11b48b6cd317eb367e Mon Sep 17 00:00:00 2001
From: Mike Snitzer <snitzer@kernel.org>
Date: Mon, 24 Feb 2025 21:20:02 -0500
Subject: [PATCH 1035/1173] NFS: fix nfs_release_folio() to not deadlock via
 kcompactd writeback

Add PF_KCOMPACTD flag and current_is_kcompactd() helper to check for it so
nfs_release_folio() can skip calling nfs_wb_folio() from kcompactd.

Otherwise NFS can deadlock waiting for kcompactd enduced writeback which
recurses back to NFS (which triggers writeback to NFSD via NFS loopback
mount on the same host, NFSD blocks waiting for XFS's call to
__filemap_get_folio):

6070.550357] INFO: task kcompactd0:58 blocked for more than 4435 seconds.

{---
[58] "kcompactd0"
[<0>] folio_wait_bit+0xe8/0x200
[<0>] folio_wait_writeback+0x2b/0x80
[<0>] nfs_wb_folio+0x80/0x1b0 [nfs]
[<0>] nfs_release_folio+0x68/0x130 [nfs]
[<0>] split_huge_page_to_list_to_order+0x362/0x840
[<0>] migrate_pages_batch+0x43d/0xb90
[<0>] migrate_pages_sync+0x9a/0x240
[<0>] migrate_pages+0x93c/0x9f0
[<0>] compact_zone+0x8e2/0x1030
[<0>] compact_node+0xdb/0x120
[<0>] kcompactd+0x121/0x2e0
[<0>] kthread+0xcf/0x100
[<0>] ret_from_fork+0x31/0x40
[<0>] ret_from_fork_asm+0x1a/0x30
---}

[akpm@linux-foundation.org: fix build]
Link: https://lkml.kernel.org/r/20250225022002.26141-1-snitzer@kernel.org
Fixes: 96780ca55e3c ("NFS: fix up nfs_release_folio() to try to release the page")
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
Cc: Anna Schumaker <anna.schumaker@oracle.com>
Cc: Trond Myklebust <trond.myklebust@hammerspace.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/nfs/file.c              | 3 ++-
 include/linux/compaction.h | 5 +++++
 include/linux/sched.h      | 2 +-
 mm/compaction.c            | 3 +++
 4 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 1bb646752e466..033feeab8c346 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -29,6 +29,7 @@
 #include <linux/pagemap.h>
 #include <linux/gfp.h>
 #include <linux/swap.h>
+#include <linux/compaction.h>
 
 #include <linux/uaccess.h>
 #include <linux/filelock.h>
@@ -457,7 +458,7 @@ static bool nfs_release_folio(struct folio *folio, gfp_t gfp)
 	/* If the private flag is set, then the folio is not freeable */
 	if (folio_test_private(folio)) {
 		if ((current_gfp_context(gfp) & GFP_KERNEL) != GFP_KERNEL ||
-		    current_is_kswapd())
+		    current_is_kswapd() || current_is_kcompactd())
 			return false;
 		if (nfs_wb_folio(folio->mapping->host, folio) < 0)
 			return false;
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index e947764960496..7bf0c521db634 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -80,6 +80,11 @@ static inline unsigned long compact_gap(unsigned int order)
 	return 2UL << order;
 }
 
+static inline int current_is_kcompactd(void)
+{
+	return current->flags & PF_KCOMPACTD;
+}
+
 #ifdef CONFIG_COMPACTION
 
 extern unsigned int extfrag_for_order(struct zone *zone, unsigned int order);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9632e3318e0d6..9c15365a30c08 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1701,7 +1701,7 @@ extern struct pid *cad_pid;
 #define PF_USED_MATH		0x00002000	/* If unset the fpu must be initialized before use */
 #define PF_USER_WORKER		0x00004000	/* Kernel thread cloned from userspace thread */
 #define PF_NOFREEZE		0x00008000	/* This thread should not be frozen */
-#define PF__HOLE__00010000	0x00010000
+#define PF_KCOMPACTD		0x00010000	/* I am kcompactd */
 #define PF_KSWAPD		0x00020000	/* I am kswapd */
 #define PF_MEMALLOC_NOFS	0x00040000	/* All allocations inherit GFP_NOFS. See memalloc_nfs_save() */
 #define PF_MEMALLOC_NOIO	0x00080000	/* All allocations inherit GFP_NOIO. See memalloc_noio_save() */
diff --git a/mm/compaction.c b/mm/compaction.c
index 12ed8425fa175..a3203d97123ea 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -3181,6 +3181,7 @@ static int kcompactd(void *p)
 	long default_timeout = msecs_to_jiffies(HPAGE_FRAG_CHECK_INTERVAL_MSEC);
 	long timeout = default_timeout;
 
+	current->flags |= PF_KCOMPACTD;
 	set_freezable();
 
 	pgdat->kcompactd_max_order = 0;
@@ -3237,6 +3238,8 @@ static int kcompactd(void *p)
 			pgdat->proactive_compact_trigger = false;
 	}
 
+	current->flags &= ~PF_KCOMPACTD;
+
 	return 0;
 }
 

From c29564d8b46f64f5e6e6f1c9c02f7761b7b90963 Mon Sep 17 00:00:00 2001
From: Su Hui <suhui@nfschina.com>
Date: Fri, 21 Feb 2025 15:16:25 +0800
Subject: [PATCH 1036/1173] include/linux/log2.h: mark is_power_of_2() with
 __always_inline

When building kernel with randconfig, there is an error:

In function `kvm_is_cr4_bit_set',inlined from
`kvm_update_cpuid_runtime' at arch/x86/kvm/cpuid.c:310:9:

include/linux/compiler_types.h:542:38: error: call to
`__compiletime_assert_380' declared with attribute error:
BUILD_BUG_ON failed: !is_power_of_2(cr4_bit).

'!is_power_of_2(X86_CR4_OSXSAVE)' is False, but gcc treats is_power_of_2()
as non-inline function and a compilation error happens. Fix this by marking
is_power_of_2() with __always_inline.

Link: https://lkml.kernel.org/r/20250221071624.1356899-1-suhui@nfschina.com
Signed-off-by: Su Hui <suhui@nfschina.com>
Cc: Binbin Wu <binbin.wu@linux.intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Sean Christopherson <seanjc@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/log2.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/log2.h b/include/linux/log2.h
index 9f30d087a1281..1366cb688a6d9 100644
--- a/include/linux/log2.h
+++ b/include/linux/log2.h
@@ -41,7 +41,7 @@ int __ilog2_u64(u64 n)
  * *not* considered a power of two.
  * Return: true if @n is a power of 2, otherwise false.
  */
-static inline __attribute__((const))
+static __always_inline __attribute__((const))
 bool is_power_of_2(unsigned long n)
 {
 	return (n != 0 && ((n & (n - 1)) == 0));

From 1c684d77dfbcf926e0dd28f6d260e8fdd8a58e85 Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Tue, 25 Feb 2025 14:23:31 -0800
Subject: [PATCH 1037/1173] selftests/damon/damos_quota: make real expectation
 of quota exceeds

Patch series "selftests/damon: three fixes for false results".

Fix three DAMON selftest bugs that cause two and one false positive
failures and successes.


This patch (of 3):

damos_quota.py assumes the quota will always exceeded.  But whether quota
will be exceeded or not depend on the monitoring results.  Actually the
monitored workload has chaning access pattern and hence sometimes the
quota may not really be exceeded.  As a result, false positive test
failures happen.  Expect how much time the quota will be exceeded by
checking the monitoring results, and use it instead of the naive
assumption.

Link: https://lkml.kernel.org/r/20250225222333.505646-1-sj@kernel.org
Link: https://lkml.kernel.org/r/20250225222333.505646-2-sj@kernel.org
Fixes: 51f58c9da14b ("selftests/damon: add a test for DAMOS quota")
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/testing/selftests/damon/damos_quota.py | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/damon/damos_quota.py b/tools/testing/selftests/damon/damos_quota.py
index 7d4c6bb2e3cd2..57c4937aaed28 100755
--- a/tools/testing/selftests/damon/damos_quota.py
+++ b/tools/testing/selftests/damon/damos_quota.py
@@ -51,16 +51,19 @@ def main():
         nr_quota_exceeds = scheme.stats.qt_exceeds
 
     wss_collected.sort()
+    nr_expected_quota_exceeds = 0
     for wss in wss_collected:
         if wss > sz_quota:
             print('quota is not kept: %s > %s' % (wss, sz_quota))
             print('collected samples are as below')
             print('\n'.join(['%d' % wss for wss in wss_collected]))
             exit(1)
+        if wss == sz_quota:
+            nr_expected_quota_exceeds += 1
 
-    if nr_quota_exceeds < len(wss_collected):
-        print('quota is not always exceeded: %d > %d' %
-              (len(wss_collected), nr_quota_exceeds))
+    if nr_quota_exceeds < nr_expected_quota_exceeds:
+        print('quota is exceeded less than expected: %d < %d' %
+              (nr_quota_exceeds, nr_expected_quota_exceeds))
         exit(1)
 
 if __name__ == '__main__':

From 695469c07a65547acb6e229b3fdf6aaa881817e3 Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Tue, 25 Feb 2025 14:23:32 -0800
Subject: [PATCH 1038/1173] selftests/damon/damon_nr_regions: set ops update
 for merge results check to 100ms

damon_nr_regions.py updates max_nr_regions to a number smaller than
expected number of real regions and confirms DAMON respect the harsh
limit.  To give time for DAMON to make changes for the regions, 3
aggregation intervals (300 milliseconds) are given.

The internal mechanism works with not only the max_nr_regions, but also
sz_limit, though.  It avoids merging region if that casn make region of
size larger than sz_limit.  In the test, sz_limit is set too small to
achive the new max_nr_regions, unless it is updated for the new
min_nr_regions.  But the update is done only once per operations set
update interval, which is one second by default.

Hence, the test randomly incurs false positive failures.  Fix it by
setting the ops interval same to aggregation interval, to make sure
sz_limit is updated by the time of the check.

Link: https://lkml.kernel.org/r/20250225222333.505646-3-sj@kernel.org
Fixes: 8bf890c81612 ("selftests/damon/damon_nr_regions: test online-tuned max_nr_regions")
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/testing/selftests/damon/damon_nr_regions.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/damon/damon_nr_regions.py b/tools/testing/selftests/damon/damon_nr_regions.py
index 2e8a74aff5431..6f1c1d88e3091 100755
--- a/tools/testing/selftests/damon/damon_nr_regions.py
+++ b/tools/testing/selftests/damon/damon_nr_regions.py
@@ -109,6 +109,7 @@ def main():
     attrs = kdamonds.kdamonds[0].contexts[0].monitoring_attrs
     attrs.min_nr_regions = 3
     attrs.max_nr_regions = 7
+    attrs.update_us = 100000
     err = kdamonds.kdamonds[0].commit()
     if err is not None:
         proc.terminate()

From 582ccf78f6090d88b1c7066b1e90b3d9ec952d08 Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Tue, 25 Feb 2025 14:23:33 -0800
Subject: [PATCH 1039/1173] selftests/damon/damon_nr_regions: sort collected
 regiosn before checking with min/max boundaries

damon_nr_regions.py starts DAMON, periodically collect number of regions
in snapshots, and see if it is in the requested range.  The check code
assumes the numbers are sorted on the collection list, but there is no
such guarantee.  Hence this can result in false positive test success.
Sort the list before doing the check.

Link: https://lkml.kernel.org/r/20250225222333.505646-4-sj@kernel.org
Fixes: 781497347d1b ("selftests/damon: implement test for min/max_nr_regions")
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/testing/selftests/damon/damon_nr_regions.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/damon/damon_nr_regions.py b/tools/testing/selftests/damon/damon_nr_regions.py
index 6f1c1d88e3091..58f3291fed12a 100755
--- a/tools/testing/selftests/damon/damon_nr_regions.py
+++ b/tools/testing/selftests/damon/damon_nr_regions.py
@@ -65,6 +65,7 @@ def test_nr_regions(real_nr_regions, min_nr_regions, max_nr_regions):
 
     test_name = 'nr_regions test with %d/%d/%d real/min/max nr_regions' % (
             real_nr_regions, min_nr_regions, max_nr_regions)
+    collected_nr_regions.sort()
     if (collected_nr_regions[0] < min_nr_regions or
         collected_nr_regions[-1] > max_nr_regions):
         print('fail %s' % test_name)

From c50f8e6053b0503375c2975bf47f182445aebb4c Mon Sep 17 00:00:00 2001
From: Barry Song <v-songbaohua@oppo.com>
Date: Wed, 26 Feb 2025 13:14:00 +1300
Subject: [PATCH 1040/1173] mm: fix kernel BUG when userfaultfd_move encounters
 swapcache

userfaultfd_move() checks whether the PTE entry is present or a
swap entry.

- If the PTE entry is present, move_present_pte() handles folio
  migration by setting:

  src_folio->index = linear_page_index(dst_vma, dst_addr);

- If the PTE entry is a swap entry, move_swap_pte() simply copies
  the PTE to the new dst_addr.

This approach is incorrect because, even if the PTE is a swap entry,
it can still reference a folio that remains in the swap cache.

This creates a race window between steps 2 and 4.
 1. add_to_swap: The folio is added to the swapcache.
 2. try_to_unmap: PTEs are converted to swap entries.
 3. pageout: The folio is written back.
 4. Swapcache is cleared.
If userfaultfd_move() occurs in the window between steps 2 and 4,
after the swap PTE has been moved to the destination, accessing the
destination triggers do_swap_page(), which may locate the folio in
the swapcache. However, since the folio's index has not been updated
to match the destination VMA, do_swap_page() will detect a mismatch.

This can result in two critical issues depending on the system
configuration.

If KSM is disabled, both small and large folios can trigger a BUG
during the add_rmap operation due to:

 page_pgoff(folio, page) != linear_page_index(vma, address)

[   13.336953] page: refcount:6 mapcount:1 mapping:00000000f43db19c index:0xffffaf150 pfn:0x4667c
[   13.337520] head: order:2 mapcount:1 entire_mapcount:0 nr_pages_mapped:1 pincount:0
[   13.337716] memcg:ffff00000405f000
[   13.337849] anon flags: 0x3fffc0000020459(locked|uptodate|dirty|owner_priv_1|head|swapbacked|node=0|zone=0|lastcpupid=0xffff)
[   13.338630] raw: 03fffc0000020459 ffff80008507b538 ffff80008507b538 ffff000006260361
[   13.338831] raw: 0000000ffffaf150 0000000000004000 0000000600000000 ffff00000405f000
[   13.339031] head: 03fffc0000020459 ffff80008507b538 ffff80008507b538 ffff000006260361
[   13.339204] head: 0000000ffffaf150 0000000000004000 0000000600000000 ffff00000405f000
[   13.339375] head: 03fffc0000000202 fffffdffc0199f01 ffffffff00000000 0000000000000001
[   13.339546] head: 0000000000000004 0000000000000000 00000000ffffffff 0000000000000000
[   13.339736] page dumped because: VM_BUG_ON_PAGE(page_pgoff(folio, page) != linear_page_index(vma, address))
[   13.340190] ------------[ cut here ]------------
[   13.340316] kernel BUG at mm/rmap.c:1380!
[   13.340683] Internal error: Oops - BUG: 00000000f2000800 [#1] PREEMPT SMP
[   13.340969] Modules linked in:
[   13.341257] CPU: 1 UID: 0 PID: 107 Comm: a.out Not tainted 6.14.0-rc3-gcf42737e247a-dirty #299
[   13.341470] Hardware name: linux,dummy-virt (DT)
[   13.341671] pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[   13.341815] pc : __page_check_anon_rmap+0xa0/0xb0
[   13.341920] lr : __page_check_anon_rmap+0xa0/0xb0
[   13.342018] sp : ffff80008752bb20
[   13.342093] x29: ffff80008752bb20 x28: fffffdffc0199f00 x27: 0000000000000001
[   13.342404] x26: 0000000000000000 x25: 0000000000000001 x24: 0000000000000001
[   13.342575] x23: 0000ffffaf0d0000 x22: 0000ffffaf0d0000 x21: fffffdffc0199f00
[   13.342731] x20: fffffdffc0199f00 x19: ffff000006210700 x18: 00000000ffffffff
[   13.342881] x17: 6c203d2120296567 x16: 6170202c6f696c6f x15: 662866666f67705f
[   13.343033] x14: 6567617028454741 x13: 2929737365726464 x12: ffff800083728ab0
[   13.343183] x11: ffff800082996bf8 x10: 0000000000000fd7 x9 : ffff80008011bc40
[   13.343351] x8 : 0000000000017fe8 x7 : 00000000fffff000 x6 : ffff8000829eebf8
[   13.343498] x5 : c0000000fffff000 x4 : 0000000000000000 x3 : 0000000000000000
[   13.343645] x2 : 0000000000000000 x1 : ffff0000062db980 x0 : 000000000000005f
[   13.343876] Call trace:
[   13.344045]  __page_check_anon_rmap+0xa0/0xb0 (P)
[   13.344234]  folio_add_anon_rmap_ptes+0x22c/0x320
[   13.344333]  do_swap_page+0x1060/0x1400
[   13.344417]  __handle_mm_fault+0x61c/0xbc8
[   13.344504]  handle_mm_fault+0xd8/0x2e8
[   13.344586]  do_page_fault+0x20c/0x770
[   13.344673]  do_translation_fault+0xb4/0xf0
[   13.344759]  do_mem_abort+0x48/0xa0
[   13.344842]  el0_da+0x58/0x130
[   13.344914]  el0t_64_sync_handler+0xc4/0x138
[   13.345002]  el0t_64_sync+0x1ac/0x1b0
[   13.345208] Code: aa1503e0 f000f801 910f6021 97ff5779 (d4210000)
[   13.345504] ---[ end trace 0000000000000000 ]---
[   13.345715] note: a.out[107] exited with irqs disabled
[   13.345954] note: a.out[107] exited with preempt_count 2

If KSM is enabled, Peter Xu also discovered that do_swap_page() may
trigger an unexpected CoW operation for small folios because
ksm_might_need_to_copy() allocates a new folio when the folio index
does not match linear_page_index(vma, addr).

This patch also checks the swapcache when handling swap entries. If a
match is found in the swapcache, it processes it similarly to a present
PTE.
However, there are some differences. For example, the folio is no longer
exclusive because folio_try_share_anon_rmap_pte() is performed during
unmapping.
Furthermore, in the case of swapcache, the folio has already been
unmapped, eliminating the risk of concurrent rmap walks and removing the
need to acquire src_folio's anon_vma or lock.

Note that for large folios, in the swapcache handling path, we directly
return -EBUSY since split_folio() will return -EBUSY regardless if
the folio is under writeback or unmapped. This is not an urgent issue,
so a follow-up patch may address it separately.

[v-songbaohua@oppo.com: minor cleanup according to Peter Xu]
  Link: https://lkml.kernel.org/r/20250226024411.47092-1-21cnbao@gmail.com
Link: https://lkml.kernel.org/r/20250226001400.9129-1-21cnbao@gmail.com
Fixes: adef440691ba ("userfaultfd: UFFDIO_MOVE uABI")
Signed-off-by: Barry Song <v-songbaohua@oppo.com>
Acked-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Brian Geffon <bgeffon@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Kalesh Singh <kaleshsingh@google.com>
Cc: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Nicolas Geoffray <ngeoffray@google.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: ZhangPeng <zhangpeng362@huawei.com>
Cc: Tangquan Zheng <zhengtangquan@oppo.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/userfaultfd.c | 74 ++++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 66 insertions(+), 8 deletions(-)

diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index af3dfc3633dbe..c45b672e10d17 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -18,6 +18,7 @@
 #include <asm/tlbflush.h>
 #include <asm/tlb.h>
 #include "internal.h"
+#include "swap.h"
 
 static __always_inline
 bool validate_dst_vma(struct vm_area_struct *dst_vma, unsigned long dst_end)
@@ -1076,16 +1077,14 @@ static int move_present_pte(struct mm_struct *mm,
 	return err;
 }
 
-static int move_swap_pte(struct mm_struct *mm,
+static int move_swap_pte(struct mm_struct *mm, struct vm_area_struct *dst_vma,
 			 unsigned long dst_addr, unsigned long src_addr,
 			 pte_t *dst_pte, pte_t *src_pte,
 			 pte_t orig_dst_pte, pte_t orig_src_pte,
 			 pmd_t *dst_pmd, pmd_t dst_pmdval,
-			 spinlock_t *dst_ptl, spinlock_t *src_ptl)
+			 spinlock_t *dst_ptl, spinlock_t *src_ptl,
+			 struct folio *src_folio)
 {
-	if (!pte_swp_exclusive(orig_src_pte))
-		return -EBUSY;
-
 	double_pt_lock(dst_ptl, src_ptl);
 
 	if (!is_pte_pages_stable(dst_pte, src_pte, orig_dst_pte, orig_src_pte,
@@ -1094,6 +1093,16 @@ static int move_swap_pte(struct mm_struct *mm,
 		return -EAGAIN;
 	}
 
+	/*
+	 * The src_folio resides in the swapcache, requiring an update to its
+	 * index and mapping to align with the dst_vma, where a swap-in may
+	 * occur and hit the swapcache after moving the PTE.
+	 */
+	if (src_folio) {
+		folio_move_anon_rmap(src_folio, dst_vma);
+		src_folio->index = linear_page_index(dst_vma, dst_addr);
+	}
+
 	orig_src_pte = ptep_get_and_clear(mm, src_addr, src_pte);
 	set_pte_at(mm, dst_addr, dst_pte, orig_src_pte);
 	double_pt_unlock(dst_ptl, src_ptl);
@@ -1141,6 +1150,7 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd,
 			  __u64 mode)
 {
 	swp_entry_t entry;
+	struct swap_info_struct *si = NULL;
 	pte_t orig_src_pte, orig_dst_pte;
 	pte_t src_folio_pte;
 	spinlock_t *src_ptl, *dst_ptl;
@@ -1322,6 +1332,8 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd,
 				       orig_dst_pte, orig_src_pte, dst_pmd,
 				       dst_pmdval, dst_ptl, src_ptl, src_folio);
 	} else {
+		struct folio *folio = NULL;
+
 		entry = pte_to_swp_entry(orig_src_pte);
 		if (non_swap_entry(entry)) {
 			if (is_migration_entry(entry)) {
@@ -1335,9 +1347,53 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd,
 			goto out;
 		}
 
-		err = move_swap_pte(mm, dst_addr, src_addr, dst_pte, src_pte,
-				    orig_dst_pte, orig_src_pte, dst_pmd,
-				    dst_pmdval, dst_ptl, src_ptl);
+		if (!pte_swp_exclusive(orig_src_pte)) {
+			err = -EBUSY;
+			goto out;
+		}
+
+		si = get_swap_device(entry);
+		if (unlikely(!si)) {
+			err = -EAGAIN;
+			goto out;
+		}
+		/*
+		 * Verify the existence of the swapcache. If present, the folio's
+		 * index and mapping must be updated even when the PTE is a swap
+		 * entry. The anon_vma lock is not taken during this process since
+		 * the folio has already been unmapped, and the swap entry is
+		 * exclusive, preventing rmap walks.
+		 *
+		 * For large folios, return -EBUSY immediately, as split_folio()
+		 * also returns -EBUSY when attempting to split unmapped large
+		 * folios in the swapcache. This issue needs to be resolved
+		 * separately to allow proper handling.
+		 */
+		if (!src_folio)
+			folio = filemap_get_folio(swap_address_space(entry),
+					swap_cache_index(entry));
+		if (!IS_ERR_OR_NULL(folio)) {
+			if (folio_test_large(folio)) {
+				err = -EBUSY;
+				folio_put(folio);
+				goto out;
+			}
+			src_folio = folio;
+			src_folio_pte = orig_src_pte;
+			if (!folio_trylock(src_folio)) {
+				pte_unmap(&orig_src_pte);
+				pte_unmap(&orig_dst_pte);
+				src_pte = dst_pte = NULL;
+				put_swap_device(si);
+				si = NULL;
+				/* now we can block and wait */
+				folio_lock(src_folio);
+				goto retry;
+			}
+		}
+		err = move_swap_pte(mm, dst_vma, dst_addr, src_addr, dst_pte, src_pte,
+				orig_dst_pte, orig_src_pte, dst_pmd, dst_pmdval,
+				dst_ptl, src_ptl, src_folio);
 	}
 
 out:
@@ -1354,6 +1410,8 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd,
 	if (src_pte)
 		pte_unmap(src_pte);
 	mmu_notifier_invalidate_range_end(&range);
+	if (si)
+		put_swap_device(si);
 
 	return err;
 }

From 058313515d5aab10d0a01dd634f92ed4a4e71d4c Mon Sep 17 00:00:00 2001
From: Baolin Wang <baolin.wang@linux.alibaba.com>
Date: Tue, 25 Feb 2025 17:52:55 +0800
Subject: [PATCH 1041/1173] mm: shmem: fix potential data corruption during
 shmem swapin

Alex and Kairui reported some issues (system hang or data corruption) when
swapping out or swapping in large shmem folios.  This is especially easy
to reproduce when the tmpfs is mount with the 'huge=within_size'
parameter.  Thanks to Kairui's reproducer, the issue can be easily
replicated.

The root cause of the problem is that swap readahead may asynchronously
swap in order 0 folios into the swap cache, while the shmem mapping can
still store large swap entries.  Then an order 0 folio is inserted into
the shmem mapping without splitting the large swap entry, which overwrites
the original large swap entry, leading to data corruption.

When getting a folio from the swap cache, we should split the large swap
entry stored in the shmem mapping if the orders do not match, to fix this
issue.

Link: https://lkml.kernel.org/r/2fe47c557e74e9df5fe2437ccdc6c9115fa1bf70.1740476943.git.baolin.wang@linux.alibaba.com
Fixes: 809bc86517cc ("mm: shmem: support large folio swap out")
Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Reported-by: Alex Xu (Hello71) <alex_y_xu@yahoo.ca>
Reported-by: Kairui Song <ryncsn@gmail.com>
Closes: https://lore.kernel.org/all/1738717785.im3r5g2vxc.none@localhost/
Tested-by: Kairui Song <kasong@tencent.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Lance Yang <ioworker0@gmail.com>
Cc: Matthew Wilcow <willy@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/shmem.c | 31 +++++++++++++++++++++++++++----
 1 file changed, 27 insertions(+), 4 deletions(-)

diff --git a/mm/shmem.c b/mm/shmem.c
index 4ea6109a80431..cebbac97a2219 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2253,7 +2253,7 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
 	struct folio *folio = NULL;
 	bool skip_swapcache = false;
 	swp_entry_t swap;
-	int error, nr_pages;
+	int error, nr_pages, order, split_order;
 
 	VM_BUG_ON(!*foliop || !xa_is_value(*foliop));
 	swap = radix_to_swp_entry(*foliop);
@@ -2272,10 +2272,9 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
 
 	/* Look it up and read it in.. */
 	folio = swap_cache_get_folio(swap, NULL, 0);
+	order = xa_get_order(&mapping->i_pages, index);
 	if (!folio) {
-		int order = xa_get_order(&mapping->i_pages, index);
 		bool fallback_order0 = false;
-		int split_order;
 
 		/* Or update major stats only when swapin succeeds?? */
 		if (fault_type) {
@@ -2339,6 +2338,29 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
 			error = -ENOMEM;
 			goto failed;
 		}
+	} else if (order != folio_order(folio)) {
+		/*
+		 * Swap readahead may swap in order 0 folios into swapcache
+		 * asynchronously, while the shmem mapping can still stores
+		 * large swap entries. In such cases, we should split the
+		 * large swap entry to prevent possible data corruption.
+		 */
+		split_order = shmem_split_large_entry(inode, index, swap, gfp);
+		if (split_order < 0) {
+			error = split_order;
+			goto failed;
+		}
+
+		/*
+		 * If the large swap entry has already been split, it is
+		 * necessary to recalculate the new swap entry based on
+		 * the old order alignment.
+		 */
+		if (split_order > 0) {
+			pgoff_t offset = index - round_down(index, 1 << split_order);
+
+			swap = swp_entry(swp_type(swap), swp_offset(swap) + offset);
+		}
 	}
 
 alloced:
@@ -2346,7 +2368,8 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
 	folio_lock(folio);
 	if ((!skip_swapcache && !folio_test_swapcache(folio)) ||
 	    folio->swap.val != swap.val ||
-	    !shmem_confirm_swap(mapping, index, swap)) {
+	    !shmem_confirm_swap(mapping, index, swap) ||
+	    xa_get_order(&mapping->i_pages, index) != folio_order(folio)) {
 		error = -EEXIST;
 		goto unlock;
 	}

From ea6de4f8f8f32e54662118a97c441a6ad7b24345 Mon Sep 17 00:00:00 2001
From: Sun YangKai <sunk67188@gmail.com>
Date: Wed, 26 Feb 2025 23:32:43 +0800
Subject: [PATCH 1042/1173] mm: zswap: use ATOMIC_LONG_INIT to initialize
 zswap_stored_pages

This is currently the only atomic_long_t variable initialized by
ATOMIC_INIT macro found in the kernel by using `grep -r atomic_long_t |
grep ATOMIC_INIT`

This was introduced in 6e1fa555ec77, in which we modified the type of
zswap_stored_pages to atomic_long_t, but didn't change the initialization.

Link: https://lkml.kernel.org/r/20250226153253.19179-1-sunk67188@gmail.com
Fixes: 6e1fa555ec77 ("mm: zswap: modify zswap_stored_pages to be atomic_long_t")
Signed-off-by: Sun YangKai <sunk67188@gmail.com>
Acked-by: Yosry Ahmed <yosry.ahmed@linux.dev>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kanchana P Sridhar <kanchana.p.sridhar@intel.com>
Cc: Nhat Pham <nphamcs@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/zswap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/zswap.c b/mm/zswap.c
index ac9d299e7d0c1..23365e76a3ce3 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -43,7 +43,7 @@
 * statistics
 **********************************/
 /* The number of compressed pages currently stored in zswap */
-atomic_long_t zswap_stored_pages = ATOMIC_INIT(0);
+atomic_long_t zswap_stored_pages = ATOMIC_LONG_INIT(0);
 
 /*
  * The statistics below are not protected from concurrent access for

From 37b338eed10581784e854d4262da05c8d960c748 Mon Sep 17 00:00:00 2001
From: Suren Baghdasaryan <surenb@google.com>
Date: Wed, 26 Feb 2025 10:55:08 -0800
Subject: [PATCH 1043/1173] userfaultfd: do not block on locking a large folio
 with raised refcount

Lokesh recently raised an issue about UFFDIO_MOVE getting into a deadlock
state when it goes into split_folio() with raised folio refcount.
split_folio() expects the reference count to be exactly mapcount +
num_pages_in_folio + 1 (see can_split_folio()) and fails with EAGAIN
otherwise.

If multiple processes are trying to move the same large folio, they raise
the refcount (all tasks succeed in that) then one of them succeeds in
locking the folio, while others will block in folio_lock() while keeping
the refcount raised.  The winner of this race will proceed with calling
split_folio() and will fail returning EAGAIN to the caller and unlocking
the folio.  The next competing process will get the folio locked and will
go through the same flow.  In the meantime the original winner will be
retried and will block in folio_lock(), getting into the queue of waiting
processes only to repeat the same path.  All this results in a livelock.

An easy fix would be to avoid waiting for the folio lock while holding
folio refcount, similar to madvise_free_huge_pmd() where folio lock is
acquired before raising the folio refcount.  Since we lock and take a
refcount of the folio while holding the PTE lock, changing the order of
these operations should not break anything.

Modify move_pages_pte() to try locking the folio first and if that fails
and the folio is large then return EAGAIN without touching the folio
refcount.  If the folio is single-page then split_folio() is not called,
so we don't have this issue.  Lokesh has a reproducer [1] and I verified
that this change fixes the issue.

[1] https://github.com/lokeshgidra/uffd_move_ioctl_deadlock

[akpm@linux-foundation.org: reflow comment to 80 cols, s/end/end up/]
Link: https://lkml.kernel.org/r/20250226185510.2732648-2-surenb@google.com
Fixes: adef440691ba ("userfaultfd: UFFDIO_MOVE uABI")
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Reported-by: Lokesh Gidra <lokeshgidra@google.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Acked-by: Liam R. Howlett <Liam.Howlett@Oracle.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Barry Song <21cnbao@gmail.com>
Cc: Barry Song <v-songbaohua@oppo.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Kalesh Singh <kaleshsingh@google.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Matthew Wilcow (Oracle) <willy@infradead.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/userfaultfd.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index c45b672e10d17..f5c6b3454f76b 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -1250,6 +1250,7 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd,
 		 */
 		if (!src_folio) {
 			struct folio *folio;
+			bool locked;
 
 			/*
 			 * Pin the page while holding the lock to be sure the
@@ -1269,12 +1270,26 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd,
 				goto out;
 			}
 
+			locked = folio_trylock(folio);
+			/*
+			 * We avoid waiting for folio lock with a raised
+			 * refcount for large folios because extra refcounts
+			 * will result in split_folio() failing later and
+			 * retrying.  If multiple tasks are trying to move a
+			 * large folio we can end up livelocking.
+			 */
+			if (!locked && folio_test_large(folio)) {
+				spin_unlock(src_ptl);
+				err = -EAGAIN;
+				goto out;
+			}
+
 			folio_get(folio);
 			src_folio = folio;
 			src_folio_pte = orig_src_pte;
 			spin_unlock(src_ptl);
 
-			if (!folio_trylock(src_folio)) {
+			if (!locked) {
 				pte_unmap(&orig_src_pte);
 				pte_unmap(&orig_dst_pte);
 				src_pte = dst_pte = NULL;

From 927e926d72d9155fde3264459fe9bfd7b5e40d28 Mon Sep 17 00:00:00 2001
From: Suren Baghdasaryan <surenb@google.com>
Date: Wed, 26 Feb 2025 10:55:09 -0800
Subject: [PATCH 1044/1173] userfaultfd: fix PTE unmapping stack-allocated PTE
 copies

Current implementation of move_pages_pte() copies source and destination
PTEs in order to detect concurrent changes to PTEs involved in the move.
However these copies are also used to unmap the PTEs, which will fail if
CONFIG_HIGHPTE is enabled because the copies are allocated on the stack.
Fix this by using the actual PTEs which were kmap()ed.

Link: https://lkml.kernel.org/r/20250226185510.2732648-3-surenb@google.com
Fixes: adef440691ba ("userfaultfd: UFFDIO_MOVE uABI")
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Reported-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Barry Song <21cnbao@gmail.com>
Cc: Barry Song <v-songbaohua@oppo.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Kalesh Singh <kaleshsingh@google.com>
Cc: Liam R. Howlett <Liam.Howlett@Oracle.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Matthew Wilcow (Oracle) <willy@infradead.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/userfaultfd.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index f5c6b3454f76b..d06453fa8abae 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -1290,8 +1290,8 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd,
 			spin_unlock(src_ptl);
 
 			if (!locked) {
-				pte_unmap(&orig_src_pte);
-				pte_unmap(&orig_dst_pte);
+				pte_unmap(src_pte);
+				pte_unmap(dst_pte);
 				src_pte = dst_pte = NULL;
 				/* now we can block and wait */
 				folio_lock(src_folio);
@@ -1307,8 +1307,8 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd,
 		/* at this point we have src_folio locked */
 		if (folio_test_large(src_folio)) {
 			/* split_folio() can block */
-			pte_unmap(&orig_src_pte);
-			pte_unmap(&orig_dst_pte);
+			pte_unmap(src_pte);
+			pte_unmap(dst_pte);
 			src_pte = dst_pte = NULL;
 			err = split_folio(src_folio);
 			if (err)
@@ -1333,8 +1333,8 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd,
 				goto out;
 			}
 			if (!anon_vma_trylock_write(src_anon_vma)) {
-				pte_unmap(&orig_src_pte);
-				pte_unmap(&orig_dst_pte);
+				pte_unmap(src_pte);
+				pte_unmap(dst_pte);
 				src_pte = dst_pte = NULL;
 				/* now we can block and wait */
 				anon_vma_lock_write(src_anon_vma);
@@ -1352,8 +1352,8 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd,
 		entry = pte_to_swp_entry(orig_src_pte);
 		if (non_swap_entry(entry)) {
 			if (is_migration_entry(entry)) {
-				pte_unmap(&orig_src_pte);
-				pte_unmap(&orig_dst_pte);
+				pte_unmap(src_pte);
+				pte_unmap(dst_pte);
 				src_pte = dst_pte = NULL;
 				migration_entry_wait(mm, src_pmd, src_addr);
 				err = -EAGAIN;
@@ -1396,8 +1396,8 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd,
 			src_folio = folio;
 			src_folio_pte = orig_src_pte;
 			if (!folio_trylock(src_folio)) {
-				pte_unmap(&orig_src_pte);
-				pte_unmap(&orig_dst_pte);
+				pte_unmap(src_pte);
+				pte_unmap(dst_pte);
 				src_pte = dst_pte = NULL;
 				put_swap_device(si);
 				si = NULL;

From adae46ac1e38a288b14f0298e27412adcba83f8e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ricardo=20Ca=C3=B1uelo=20Navarro?= <rcn@igalia.com>
Date: Wed, 26 Feb 2025 13:26:27 +0100
Subject: [PATCH 1045/1173] mm: shmem: remove unnecessary warning in
 shmem_writepage()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Although the scenario where shmem_writepage() is called with info->flags &
VM_LOCKED is unlikely to happen, it's still possible, as evidenced by
syzbot [1].  However, the warning in this case isn't necessary because the
situation is already handled correctly [2].

[2] https://lore.kernel.org/lkml/8afe1f7f-31a2-4fc0-1fbd-f9ba8a116fe3@google.com/

Link: https://lkml.kernel.org/r/20250226-20250221-warning-in-shmem_writepage-v1-1-5ad19420e17e@igalia.com
Fixes: 9a976f0c847b ("shmem: skip page split if we're not reclaiming")
Signed-off-by: Ricardo Cañuelo Navarro <rcn@igalia.com>
Reported-by: Pengfei Xu <pengfei.xu@intel.com>
Closes: https://lore.kernel.org/lkml/ZZ9PShXjKJkVelNm@xpf.sh.intel.com/ [1]
Suggested-by: Hugh Dickins <hughd@google.com>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Florent Revest <revest@chromium.org>
Cc: Christian Brauner <brauner@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Florent Revest <revest@chromium.org>
Cc: Luis Chamberalin <mcgrof@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/shmem.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/shmem.c b/mm/shmem.c
index cebbac97a2219..3fcd1690eedd7 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1548,7 +1548,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 	if (WARN_ON_ONCE(!wbc->for_reclaim))
 		goto redirty;
 
-	if (WARN_ON_ONCE((info->flags & VM_LOCKED) || sbinfo->noswap))
+	if ((info->flags & VM_LOCKED) || sbinfo->noswap)
 		goto redirty;
 
 	if (!total_swap_pages)

From 3685024edd270f7c791f993157d65d3c928f3d6e Mon Sep 17 00:00:00 2001
From: Ryan Roberts <ryan.roberts@arm.com>
Date: Wed, 26 Feb 2025 12:16:09 +0000
Subject: [PATCH 1046/1173] mm: don't skip arch_sync_kernel_mappings() in error
 paths

Fix callers that previously skipped calling arch_sync_kernel_mappings() if
an error occurred during a pgtable update.  The call is still required to
sync any pgtable updates that may have occurred prior to hitting the error
condition.

These are theoretical bugs discovered during code review.

Link: https://lkml.kernel.org/r/20250226121610.2401743-1-ryan.roberts@arm.com
Fixes: 2ba3e6947aed ("mm/vmalloc: track which page-table levels were modified")
Fixes: 0c95cba49255 ("mm: apply_to_pte_range warn and fail if a large pte is encountered")
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christop Hellwig <hch@infradead.org>
Cc: "Uladzislau Rezki (Sony)" <urezki@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/memory.c  | 6 ++++--
 mm/vmalloc.c | 4 ++--
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index b4d3d4893267c..55d0d49546273 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3051,8 +3051,10 @@ static int __apply_to_page_range(struct mm_struct *mm, unsigned long addr,
 		next = pgd_addr_end(addr, end);
 		if (pgd_none(*pgd) && !create)
 			continue;
-		if (WARN_ON_ONCE(pgd_leaf(*pgd)))
-			return -EINVAL;
+		if (WARN_ON_ONCE(pgd_leaf(*pgd))) {
+			err = -EINVAL;
+			break;
+		}
 		if (!pgd_none(*pgd) && WARN_ON_ONCE(pgd_bad(*pgd))) {
 			if (!create)
 				continue;
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index a6e7acebe9adf..61981ee1c9d2f 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -586,13 +586,13 @@ static int vmap_small_pages_range_noflush(unsigned long addr, unsigned long end,
 			mask |= PGTBL_PGD_MODIFIED;
 		err = vmap_pages_p4d_range(pgd, addr, next, prot, pages, &nr, &mask);
 		if (err)
-			return err;
+			break;
 	} while (pgd++, addr = next, addr != end);
 
 	if (mask & ARCH_PAGE_TABLE_SYNC_MASK)
 		arch_sync_kernel_mappings(start, end);
 
-	return 0;
+	return err;
 }
 
 /*

From 34b82f33cf3f03bc39e9a205a913d790e1520ade Mon Sep 17 00:00:00 2001
From: Brian Geffon <bgeffon@google.com>
Date: Wed, 26 Feb 2025 11:23:41 -0500
Subject: [PATCH 1047/1173] mm: fix finish_fault() handling for large folios

When handling faults for anon shmem finish_fault() will attempt to install
ptes for the entire folio.  Unfortunately if it encounters a single
non-pte_none entry in that range it will bail, even if the pte that
triggered the fault is still pte_none.  When this situation happens the
fault will be retried endlessly never making forward progress.

This patch fixes this behavior and if it detects that a pte in the range
is not pte_none it will fall back to setting a single pte.

[bgeffon@google.com: tweak whitespace]
  Link: https://lkml.kernel.org/r/20250227133236.1296853-1-bgeffon@google.com
Link: https://lkml.kernel.org/r/20250226162341.915535-1-bgeffon@google.com
Fixes: 43e027e41423 ("mm: memory: extend finish_fault() to support large folio")
Signed-off-by: Brian Geffon <bgeffon@google.com>
Suggested-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Reported-by: Marek Maslanka <mmaslanka@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickens <hughd@google.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Matthew Wilcow (Oracle) <willy@infradead.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/memory.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index 55d0d49546273..b9661ccfa64fd 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -5185,7 +5185,11 @@ vm_fault_t finish_fault(struct vm_fault *vmf)
 	bool is_cow = (vmf->flags & FAULT_FLAG_WRITE) &&
 		      !(vma->vm_flags & VM_SHARED);
 	int type, nr_pages;
-	unsigned long addr = vmf->address;
+	unsigned long addr;
+	bool needs_fallback = false;
+
+fallback:
+	addr = vmf->address;
 
 	/* Did we COW the page? */
 	if (is_cow)
@@ -5224,7 +5228,8 @@ vm_fault_t finish_fault(struct vm_fault *vmf)
 	 * approach also applies to non-anonymous-shmem faults to avoid
 	 * inflating the RSS of the process.
 	 */
-	if (!vma_is_anon_shmem(vma) || unlikely(userfaultfd_armed(vma))) {
+	if (!vma_is_anon_shmem(vma) || unlikely(userfaultfd_armed(vma)) ||
+	    unlikely(needs_fallback)) {
 		nr_pages = 1;
 	} else if (nr_pages > 1) {
 		pgoff_t idx = folio_page_idx(folio, page);
@@ -5260,9 +5265,9 @@ vm_fault_t finish_fault(struct vm_fault *vmf)
 		ret = VM_FAULT_NOPAGE;
 		goto unlock;
 	} else if (nr_pages > 1 && !pte_range_none(vmf->pte, nr_pages)) {
-		update_mmu_tlb_range(vma, addr, vmf->pte, nr_pages);
-		ret = VM_FAULT_NOPAGE;
-		goto unlock;
+		needs_fallback = true;
+		pte_unmap_unlock(vmf->pte, vmf->ptl);
+		goto fallback;
 	}
 
 	folio_ref_add(folio, nr_pages - 1);

From eae116d1f0449ade3269ca47a67432622f5c6438 Mon Sep 17 00:00:00 2001
From: Gabriel Krisman Bertazi <krisman@suse.de>
Date: Tue, 25 Feb 2025 22:22:58 -0500
Subject: [PATCH 1048/1173] Revert "mm/page_alloc.c: don't show protection in
 zone's ->lowmem_reserve[] for empty zone"

Commit 96a5c186efff ("mm/page_alloc.c: don't show protection in zone's
->lowmem_reserve[] for empty zone") removes the protection of lower zones
from allocations targeting memory-less high zones.  This had an unintended
impact on the pattern of reclaims because it makes the high-zone-targeted
allocation more likely to succeed in lower zones, which adds pressure to
said zones.  I.e, the following corresponding checks in
zone_watermark_ok/zone_watermark_fast are less likely to trigger:

        if (free_pages <= min + z->lowmem_reserve[highest_zoneidx])
                return false;

As a result, we are observing an increase in reclaim and kswapd scans, due
to the increased pressure.  This was initially observed as increased
latency in filesystem operations when benchmarking with fio on a machine
with some memory-less zones, but it has since been associated with
increased contention in locks related to memory reclaim.  By reverting
this patch, the original performance was recovered on that machine.

The original commit was introduced as a clarification of the
/proc/zoneinfo output, so it doesn't seem there are usecases depending on
it, making the revert a simple solution.

For reference, I collected vmstat with and without this patch on a freshly
booted system running intensive randread io from an nvme for 5 minutes.  I
got:

rpm-6.12.0-slfo.1.2 ->  pgscan_kswapd 5629543865
Patched             ->  pgscan_kswapd 33580844

33M scans is similar to what we had in kernels predating this patch.
These numbers is fairly representative of the workload on this machine, as
measured in several runs.  So we are talking about a 2-order of magnitude
increase.

Link: https://lkml.kernel.org/r/20250226032258.234099-1-krisman@suse.de
Fixes: 96a5c186efff ("mm/page_alloc.c: don't show protection in zone's ->lowmem_reserve[] for empty zone")
Signed-off-by: Gabriel Krisman Bertazi <krisman@suse.de>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Baoquan He <bhe@redhat.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/page_alloc.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 579789600a3c7..fe986e6de7a01 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5849,11 +5849,10 @@ static void setup_per_zone_lowmem_reserve(void)
 
 			for (j = i + 1; j < MAX_NR_ZONES; j++) {
 				struct zone *upper_zone = &pgdat->node_zones[j];
-				bool empty = !zone_managed_pages(upper_zone);
 
 				managed_pages += zone_managed_pages(upper_zone);
 
-				if (clear || empty)
+				if (clear)
 					zone->lowmem_reserve[j] = 0;
 				else
 					zone->lowmem_reserve[j] = managed_pages / ratio;

From 88f5a9a945bf25df1f90032baf95457370c2206e Mon Sep 17 00:00:00 2001
From: Sumit Garg <sumit.garg@linaro.org>
Date: Thu, 27 Feb 2025 17:02:28 +0530
Subject: [PATCH 1049/1173] MAINTAINERS: .mailmap: update Sumit Garg's email
 address

Update Sumit Garg's email address to @kernel.org.

Link: https://lkml.kernel.org/r/20250227113228.1809449-1-sumit.garg@linaro.org
Signed-off-by: Sumit Garg <sumit.garg@linaro.org>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Jarkko Sakkinen <jarkko@kernel.org>
Cc: Jens Wiklander <jens.wiklander@linaro.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 .mailmap    | 1 +
 MAINTAINERS | 6 +++---
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/.mailmap b/.mailmap
index a897c16d3baef..4a93909286d8b 100644
--- a/.mailmap
+++ b/.mailmap
@@ -689,6 +689,7 @@ Subbaraman Narayanamurthy <quic_subbaram@quicinc.com> <subbaram@codeaurora.org>
 Subhash Jadavani <subhashj@codeaurora.org>
 Sudarshan Rajagopalan <quic_sudaraja@quicinc.com> <sudaraja@codeaurora.org>
 Sudeep Holla <sudeep.holla@arm.com> Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com>
+Sumit Garg <sumit.garg@kernel.org> <sumit.garg@linaro.org>
 Sumit Semwal <sumit.semwal@ti.com>
 Surabhi Vishnoi <quic_svishnoi@quicinc.com> <svishnoi@codeaurora.org>
 Sven Eckelmann <sven@narfation.org> <seckelmann@datto.com>
diff --git a/MAINTAINERS b/MAINTAINERS
index 4e17764cb6ed4..5e1be7b25912e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12864,7 +12864,7 @@ F:	include/keys/trusted_dcp.h
 F:	security/keys/trusted-keys/trusted_dcp.c
 
 KEYS-TRUSTED-TEE
-M:	Sumit Garg <sumit.garg@linaro.org>
+M:	Sumit Garg <sumit.garg@kernel.org>
 L:	linux-integrity@vger.kernel.org
 L:	keyrings@vger.kernel.org
 S:	Supported
@@ -17658,7 +17658,7 @@ F:	Documentation/ABI/testing/sysfs-bus-optee-devices
 F:	drivers/tee/optee/
 
 OP-TEE RANDOM NUMBER GENERATOR (RNG) DRIVER
-M:	Sumit Garg <sumit.garg@linaro.org>
+M:	Sumit Garg <sumit.garg@kernel.org>
 L:	op-tee@lists.trustedfirmware.org
 S:	Maintained
 F:	drivers/char/hw_random/optee-rng.c
@@ -23268,7 +23268,7 @@ F:	include/media/i2c/tw9910.h
 
 TEE SUBSYSTEM
 M:	Jens Wiklander <jens.wiklander@linaro.org>
-R:	Sumit Garg <sumit.garg@linaro.org>
+R:	Sumit Garg <sumit.garg@kernel.org>
 L:	op-tee@lists.trustedfirmware.org
 S:	Maintained
 F:	Documentation/ABI/testing/sysfs-class-tee

From b2ef51c74b0171fde7eb69b6152d3d2f743ef269 Mon Sep 17 00:00:00 2001
From: Haoxiang Li <haoxiang_li2024@163.com>
Date: Thu, 27 Feb 2025 15:34:09 +0800
Subject: [PATCH 1050/1173] rapidio: fix an API misues when rio_add_net() fails

rio_add_net() calls device_register() and fails when device_register()
fails.  Thus, put_device() should be used rather than kfree().  Add
"mport->net = NULL;" to avoid a use after free issue.

Link: https://lkml.kernel.org/r/20250227073409.3696854-1-haoxiang_li2024@163.com
Fixes: e8de370188d0 ("rapidio: add mport char device driver")
Signed-off-by: Haoxiang Li <haoxiang_li2024@163.com>
Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
Cc: Alexandre Bounine <alex.bou9@gmail.com>
Cc: Matt Porter <mporter@kernel.crashing.org>
Cc: Yang Yingliang <yangyingliang@huawei.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 drivers/rapidio/devices/rio_mport_cdev.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c
index 27afbb9d544b7..cbf531d0ba688 100644
--- a/drivers/rapidio/devices/rio_mport_cdev.c
+++ b/drivers/rapidio/devices/rio_mport_cdev.c
@@ -1742,7 +1742,8 @@ static int rio_mport_add_riodev(struct mport_cdev_priv *priv,
 		err = rio_add_net(net);
 		if (err) {
 			rmcd_debug(RDEV, "failed to register net, err=%d", err);
-			kfree(net);
+			put_device(&net->dev);
+			mport->net = NULL;
 			goto cleanup;
 		}
 	}

From e842f9a1edf306bf36fe2a4d847a0b0d458770de Mon Sep 17 00:00:00 2001
From: Haoxiang Li <haoxiang_li2024@163.com>
Date: Thu, 27 Feb 2025 12:11:31 +0800
Subject: [PATCH 1051/1173] rapidio: add check for rio_add_net() in
 rio_scan_alloc_net()

The return value of rio_add_net() should be checked.  If it fails,
put_device() should be called to free the memory and give up the reference
initialized in rio_add_net().

Link: https://lkml.kernel.org/r/20250227041131.3680761-1-haoxiang_li2024@163.com
Fixes: e6b585ca6e81 ("rapidio: move net allocation into core code")
Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Signed-off-by: Haoxiang Li <haoxiang_li2024@163.com>
Cc: Alexandre Bounine <alex.bou9@gmail.com>
Cc: Matt Porter <mporter@kernel.crashing.org>
Cc: Dan Carpenter <dan.carpenter@linaro.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 drivers/rapidio/rio-scan.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/rapidio/rio-scan.c b/drivers/rapidio/rio-scan.c
index fdcf742b2adbc..c12941f71e2cb 100644
--- a/drivers/rapidio/rio-scan.c
+++ b/drivers/rapidio/rio-scan.c
@@ -871,7 +871,10 @@ static struct rio_net *rio_scan_alloc_net(struct rio_mport *mport,
 		dev_set_name(&net->dev, "rnet_%d", net->id);
 		net->dev.parent = &mport->dev;
 		net->dev.release = rio_scan_release_dev;
-		rio_add_net(net);
+		if (rio_add_net(net)) {
+			put_device(&net->dev);
+			net = NULL;
+		}
 	}
 
 	return net;

From 8fe9ed44dc29fba0786b7e956d2e87179e407582 Mon Sep 17 00:00:00 2001
From: Hao Zhang <zhanghao1@kylinos.cn>
Date: Thu, 27 Feb 2025 11:41:29 +0800
Subject: [PATCH 1052/1173] mm/page_alloc: fix uninitialized variable

The variable "compact_result" is not initialized in function
__alloc_pages_slowpath().  It causes should_compact_retry() to use an
uninitialized value.

Initialize variable "compact_result" with the value COMPACT_SKIPPED.

BUG: KMSAN: uninit-value in __alloc_pages_slowpath+0xee8/0x16c0 mm/page_alloc.c:4416
 __alloc_pages_slowpath+0xee8/0x16c0 mm/page_alloc.c:4416
 __alloc_frozen_pages_noprof+0xa4c/0xe00 mm/page_alloc.c:4752
 alloc_pages_mpol+0x4cd/0x890 mm/mempolicy.c:2270
 alloc_frozen_pages_noprof mm/mempolicy.c:2341 [inline]
 alloc_pages_noprof mm/mempolicy.c:2361 [inline]
 folio_alloc_noprof+0x1dc/0x350 mm/mempolicy.c:2371
 filemap_alloc_folio_noprof+0xa6/0x440 mm/filemap.c:1019
 __filemap_get_folio+0xb9a/0x1840 mm/filemap.c:1970
 grow_dev_folio fs/buffer.c:1039 [inline]
 grow_buffers fs/buffer.c:1105 [inline]
 __getblk_slow fs/buffer.c:1131 [inline]
 bdev_getblk+0x2c9/0xab0 fs/buffer.c:1431
 getblk_unmovable include/linux/buffer_head.h:369 [inline]
 ext4_getblk+0x3b7/0xe50 fs/ext4/inode.c:864
 ext4_bread_batch+0x9f/0x7d0 fs/ext4/inode.c:933
 __ext4_find_entry+0x1ebb/0x36c0 fs/ext4/namei.c:1627
 ext4_lookup_entry fs/ext4/namei.c:1729 [inline]
 ext4_lookup+0x189/0xb40 fs/ext4/namei.c:1797
 __lookup_slow+0x538/0x710 fs/namei.c:1793
 lookup_slow+0x6a/0xd0 fs/namei.c:1810
 walk_component fs/namei.c:2114 [inline]
 link_path_walk+0xf29/0x1420 fs/namei.c:2479
 path_openat+0x30f/0x6250 fs/namei.c:3985
 do_filp_open+0x268/0x600 fs/namei.c:4016
 do_sys_openat2+0x1bf/0x2f0 fs/open.c:1428
 do_sys_open fs/open.c:1443 [inline]
 __do_sys_openat fs/open.c:1459 [inline]
 __se_sys_openat fs/open.c:1454 [inline]
 __x64_sys_openat+0x2a1/0x310 fs/open.c:1454
 x64_sys_call+0x36f5/0x3c30 arch/x86/include/generated/asm/syscalls_64.h:258
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0xcd/0x1e0 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Local variable compact_result created at:
 __alloc_pages_slowpath+0x66/0x16c0 mm/page_alloc.c:4218
 __alloc_frozen_pages_noprof+0xa4c/0xe00 mm/page_alloc.c:4752

Link: https://lkml.kernel.org/r/tencent_ED1032321D6510B145CDBA8CBA0093178E09@qq.com
Reported-by: syzbot+0cfd5e38e96a5596f2b6@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=0cfd5e38e96a5596f2b6
Signed-off-by: Hao Zhang <zhanghao1@kylinos.cn>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/page_alloc.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index fe986e6de7a01..94917c729120f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4243,6 +4243,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 restart:
 	compaction_retries = 0;
 	no_progress_loops = 0;
+	compact_result = COMPACT_SKIPPED;
 	compact_priority = DEF_COMPACT_PRIORITY;
 	cpuset_mems_cookie = read_mems_allowed_begin();
 	zonelist_iter_cookie = zonelist_iter_begin();

From 80da96d735094ea22985ced98bc57fe3a4422921 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 4 Mar 2025 14:41:57 +0100
Subject: [PATCH 1053/1173] drm/bochs: Fix DPMS regression

The recent rewrite with the use of regular atomic helpers broke the
DPMS unblanking on X11.  Fix it by moving the call of
bochs_hw_blank(false) from CRTC mode_set_nofb() to atomic_enable().

Fixes: 2037174993c8 ("drm/bochs: Use regular atomic helpers")
Link: https://bugzilla.suse.com/show_bug.cgi?id=1238209
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Reviewed-by: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Link: https://patchwork.freedesktop.org/patch/msgid/20250304134203.20534-1-tiwai@suse.de
---
 drivers/gpu/drm/tiny/bochs.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/tiny/bochs.c b/drivers/gpu/drm/tiny/bochs.c
index c67e1f9067859..8706763af8fba 100644
--- a/drivers/gpu/drm/tiny/bochs.c
+++ b/drivers/gpu/drm/tiny/bochs.c
@@ -335,8 +335,6 @@ static void bochs_hw_setmode(struct bochs_device *bochs, struct drm_display_mode
 			 bochs->xres, bochs->yres, bochs->bpp,
 			 bochs->yres_virtual);
 
-	bochs_hw_blank(bochs, false);
-
 	bochs_dispi_write(bochs, VBE_DISPI_INDEX_ENABLE,      0);
 	bochs_dispi_write(bochs, VBE_DISPI_INDEX_BPP,         bochs->bpp);
 	bochs_dispi_write(bochs, VBE_DISPI_INDEX_XRES,        bochs->xres);
@@ -506,6 +504,9 @@ static int bochs_crtc_helper_atomic_check(struct drm_crtc *crtc,
 static void bochs_crtc_helper_atomic_enable(struct drm_crtc *crtc,
 					    struct drm_atomic_state *state)
 {
+	struct bochs_device *bochs = to_bochs_device(crtc->dev);
+
+	bochs_hw_blank(bochs, false);
 }
 
 static void bochs_crtc_helper_atomic_disable(struct drm_crtc *crtc,

From d385c8bceb14665e935419334aa3d3fac2f10456 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Michal=20Koutn=C3=BD?= <mkoutny@suse.com>
Date: Wed, 5 Mar 2025 15:58:49 +0100
Subject: [PATCH 1054/1173] pid: Do not set pid_max in new pid namespaces
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It is already difficult for users to troubleshoot which of multiple pid
limits restricts their workload. The per-(hierarchical-)NS pid_max would
contribute to the confusion.
Also, the implementation copies the limit upon creation from
parent, this pattern showed cumbersome with some attributes in legacy
cgroup controllers -- it's subject to race condition between parent's
limit modification and children creation and once copied it must be
changed in the descendant.

Let's do what other places do (ucounts or cgroup limits) -- create new
pid namespaces without any limit at all. The global limit (actually any
ancestor's limit) is still effectively in place, we avoid the
set/unshare race and bumps of global (ancestral) limit have the desired
effect on pid namespace that do not care.

Link: https://lore.kernel.org/r/20240408145819.8787-1-mkoutny@suse.com/
Link: https://lore.kernel.org/r/20250221170249.890014-1-mkoutny@suse.com/
Fixes: 7863dcc72d0f4 ("pid: allow pid_max to be set per pid namespace")
Signed-off-by: Michal Koutný <mkoutny@suse.com>
Link: https://lore.kernel.org/r/20250305145849.55491-1-mkoutny@suse.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 kernel/pid_namespace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 8f6cfec87555a..7098ed44e717d 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -107,7 +107,7 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns
 		goto out_free_idr;
 	ns->ns.ops = &pidns_operations;
 
-	ns->pid_max = parent_pid_ns->pid_max;
+	ns->pid_max = PID_MAX_LIMIT;
 	err = register_pidns_sysctls(ns);
 	if (err)
 		goto out_free_inum;

From 14672f059d83f591afb2ee1fff56858efe055e5a Mon Sep 17 00:00:00 2001
From: Shrikanth Hegde <sshegde@linux.ibm.com>
Date: Thu, 6 Mar 2025 10:59:53 +0530
Subject: [PATCH 1055/1173] sched/deadline: Use online cpus for validating
 runtime

The ftrace selftest reported a failure because writing -1 to
sched_rt_runtime_us returns -EBUSY. This happens when the possible
CPUs are different from active CPUs.

Active CPUs are part of one root domain, while remaining CPUs are part
of def_root_domain. Since active cpumask is being used, this results in
cpus=0 when a non active CPUs is used in the loop.

Fix it by looping over the online CPUs instead for validating the
bandwidth calculations.

Signed-off-by: Shrikanth Hegde <sshegde@linux.ibm.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Juri Lelli <juri.lelli@redhat.com>
Link: https://lore.kernel.org/r/20250306052954.452005-2-sshegde@linux.ibm.com
---
 kernel/sched/deadline.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 38e4537790af7..ff4df16b5186d 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -3189,7 +3189,7 @@ int sched_dl_global_validate(void)
 	 * value smaller than the currently allocated bandwidth in
 	 * any of the root_domains.
 	 */
-	for_each_possible_cpu(cpu) {
+	for_each_online_cpu(cpu) {
 		rcu_read_lock_sched();
 
 		if (dl_bw_visited(cpu, gen))

From b1536481c81fb604074da799e4f2d2038a1663f7 Mon Sep 17 00:00:00 2001
From: Shrikanth Hegde <sshegde@linux.ibm.com>
Date: Thu, 6 Mar 2025 10:59:54 +0530
Subject: [PATCH 1056/1173] sched/rt: Update limit of sched_rt sysctl in
 documentation

By default fair_server dl_server allocates 5% of the bandwidth to the root
domain. Due to this writing any value less than 5% fails due to -EBUSY:

  $ cat /proc/sys/kernel/sched_rt_period_us
  1000000

  $ echo 49999 > /proc/sys/kernel/sched_rt_runtime_us
  -bash: echo: write error: Device or resource busy

  $ echo 50000 > /proc/sys/kernel/sched_rt_runtime_us
  $

Since the sched_rt_runtime_us allows -1 as the minimum, put this
restriction in the documentation.

One should check average of runtime/period in
/sys/kernel/debug/sched/fair_server/cpuX/* for exact value.

Signed-off-by: Shrikanth Hegde <sshegde@linux.ibm.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Juri Lelli <juri.lelli@redhat.com>
Link: https://lore.kernel.org/r/20250306052954.452005-3-sshegde@linux.ibm.com
---
 Documentation/scheduler/sched-rt-group.rst | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/scheduler/sched-rt-group.rst b/Documentation/scheduler/sched-rt-group.rst
index 80b05a3009ea2..ab464335d3204 100644
--- a/Documentation/scheduler/sched-rt-group.rst
+++ b/Documentation/scheduler/sched-rt-group.rst
@@ -102,6 +102,9 @@ The system wide settings are configured under the /proc virtual file system:
   * sched_rt_period_us takes values from 1 to INT_MAX.
   * sched_rt_runtime_us takes values from -1 to sched_rt_period_us.
   * A run time of -1 specifies runtime == period, ie. no limit.
+  * sched_rt_runtime_us/sched_rt_period_us > 0.05 inorder to preserve
+    bandwidth for fair dl_server. For accurate value check average of
+    runtime/period in /sys/kernel/debug/sched/fair_server/cpuX/
 
 
 2.2 Default behaviour

From cf7ee25e70c6edfac4553d6b671e8b19db1d9573 Mon Sep 17 00:00:00 2001
From: Matt Johnston <matt@codeconstruct.com.au>
Date: Tue, 4 Mar 2025 13:59:51 +0800
Subject: [PATCH 1057/1173] mctp i3c: handle NULL header address

daddr can be NULL if there is no neighbour table entry present,
in that case the tx packet should be dropped.

saddr will usually be set by MCTP core, but check for NULL in case a
packet is transmitted by a different protocol.

Signed-off-by: Matt Johnston <matt@codeconstruct.com.au>
Fixes: c8755b29b58e ("mctp i3c: MCTP I3C driver")
Link: https://patch.msgid.link/20250304-mctp-i3c-null-v1-1-4416bbd56540@codeconstruct.com.au
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/mctp/mctp-i3c.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/mctp/mctp-i3c.c b/drivers/net/mctp/mctp-i3c.c
index d247fe483c588..c1e72253063b5 100644
--- a/drivers/net/mctp/mctp-i3c.c
+++ b/drivers/net/mctp/mctp-i3c.c
@@ -507,6 +507,9 @@ static int mctp_i3c_header_create(struct sk_buff *skb, struct net_device *dev,
 {
 	struct mctp_i3c_internal_hdr *ihdr;
 
+	if (!daddr || !saddr)
+		return -EINVAL;
+
 	skb_push(skb, sizeof(struct mctp_i3c_internal_hdr));
 	skb_reset_mac_header(skb);
 	ihdr = (void *)skb_mac_header(skb);

From 0e7633d7b95b67f1758aea19f8e85621c5f506a3 Mon Sep 17 00:00:00 2001
From: Justin Iurman <justin.iurman@uliege.be>
Date: Tue, 4 Mar 2025 19:10:39 +0100
Subject: [PATCH 1058/1173] net: ipv6: fix dst ref loop in ila lwtunnel

This patch follows commit 92191dd10730 ("net: ipv6: fix dst ref loops in
rpl, seg6 and ioam6 lwtunnels") and, on a second thought, the same patch
is also needed for ila (even though the config that triggered the issue
was pathological, but still, we don't want that to happen).

Fixes: 79ff2fc31e0f ("ila: Cache a route to translated address")
Cc: Tom Herbert <tom@herbertland.com>
Signed-off-by: Justin Iurman <justin.iurman@uliege.be>
Link: https://patch.msgid.link/20250304181039.35951-1-justin.iurman@uliege.be
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv6/ila/ila_lwt.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c
index ff7e734e335b0..ac4bcc623603a 100644
--- a/net/ipv6/ila/ila_lwt.c
+++ b/net/ipv6/ila/ila_lwt.c
@@ -88,7 +88,8 @@ static int ila_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 			goto drop;
 		}
 
-		if (ilwt->connected) {
+		/* cache only if we don't create a dst reference loop */
+		if (ilwt->connected && orig_dst->lwtstate != dst->lwtstate) {
 			local_bh_disable();
 			dst_cache_set_ip6(&ilwt->dst_cache, dst, &fl6.saddr);
 			local_bh_enable();

From 5da15a9c11c1c47ef573e6805b60a7d8a1687a2a Mon Sep 17 00:00:00 2001
From: Justin Iurman <justin.iurman@uliege.be>
Date: Wed, 5 Mar 2025 09:16:55 +0100
Subject: [PATCH 1059/1173] net: ipv6: fix missing dst ref drop in ila lwtunnel

Add missing skb_dst_drop() to drop reference to the old dst before
adding the new dst to the skb.

Fixes: 79ff2fc31e0f ("ila: Cache a route to translated address")
Cc: Tom Herbert <tom@herbertland.com>
Signed-off-by: Justin Iurman <justin.iurman@uliege.be>
Link: https://patch.msgid.link/20250305081655.19032-1-justin.iurman@uliege.be
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv6/ila/ila_lwt.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c
index ac4bcc623603a..7d574f5132e2f 100644
--- a/net/ipv6/ila/ila_lwt.c
+++ b/net/ipv6/ila/ila_lwt.c
@@ -96,6 +96,7 @@ static int ila_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 		}
 	}
 
+	skb_dst_drop(skb);
 	skb_dst_set(skb, dst);
 	return dst_output(net, sk, skb);
 

From ef69de53c46a4b526442f6bc5970fc14f7a0bb32 Mon Sep 17 00:00:00 2001
From: Zeng Heng <zengheng4@huawei.com>
Date: Fri, 25 Oct 2024 15:42:03 +0800
Subject: [PATCH 1060/1173] x86/platform/olpc: Remove unused variable 'len' in
 olpc_dt_compatible_match()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The following build warning highlights some unused code:

  arch/x86/platform/olpc/olpc_dt.c: In function ‘olpc_dt_compatible_match’:
  arch/x86/platform/olpc/olpc_dt.c:222:12: warning: variable ‘len’ set but not used [-Wunused-but-set-variable]

The compiler is right, the local variable 'len' is set but never used,
so remove it.

Fixes: a7a9bacb9a32 ("x86/platform/olpc: Use a correct version when making up a battery node")
Signed-off-by: Zeng Heng <zengheng4@huawei.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20241025074203.1921344-1-zengheng4@huawei.com
---
 arch/x86/platform/olpc/olpc_dt.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/x86/platform/olpc/olpc_dt.c b/arch/x86/platform/olpc/olpc_dt.c
index cf5dca2dbb91d..e108ce7dad6a1 100644
--- a/arch/x86/platform/olpc/olpc_dt.c
+++ b/arch/x86/platform/olpc/olpc_dt.c
@@ -215,13 +215,12 @@ static u32 __init olpc_dt_get_board_revision(void)
 static int __init olpc_dt_compatible_match(phandle node, const char *compat)
 {
 	char buf[64], *p;
-	int plen, len;
+	int plen;
 
 	plen = olpc_dt_getproperty(node, "compatible", buf, sizeof(buf));
 	if (plen <= 0)
 		return 0;
 
-	len = strlen(compat);
 	for (p = buf; p < buf + plen; p += strlen(p) + 1) {
 		if (strcmp(p, compat) == 0)
 			return 1;

From c84f87de474c9aec84f706ceb732b70751122746 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Tue, 4 Mar 2025 17:33:42 +0200
Subject: [PATCH 1061/1173] x86/runtime-const: Add the RUNTIME_CONST_PTR
 assembly macro

Add an assembly macro to refer runtime cost. It hides linker magic and
makes assembly more readable.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250304153342.2016569-1-kirill.shutemov@linux.intel.com
---
 arch/x86/include/asm/runtime-const.h | 13 +++++++++++++
 arch/x86/lib/getuser.S               |  7 ++-----
 2 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/asm/runtime-const.h b/arch/x86/include/asm/runtime-const.h
index 6652ebddfd02f..8d983cfd06ea6 100644
--- a/arch/x86/include/asm/runtime-const.h
+++ b/arch/x86/include/asm/runtime-const.h
@@ -2,6 +2,18 @@
 #ifndef _ASM_RUNTIME_CONST_H
 #define _ASM_RUNTIME_CONST_H
 
+#ifdef __ASSEMBLY__
+
+.macro RUNTIME_CONST_PTR sym reg
+	movq	$0x0123456789abcdef, %\reg
+	1:
+	.pushsection runtime_ptr_\sym, "a"
+	.long	1b - 8 - .
+	.popsection
+.endm
+
+#else /* __ASSEMBLY__ */
+
 #define runtime_const_ptr(sym) ({				\
 	typeof(sym) __ret;					\
 	asm_inline("mov %1,%0\n1:\n"				\
@@ -58,4 +70,5 @@ static inline void runtime_const_fixup(void (*fn)(void *, unsigned long),
 	}
 }
 
+#endif /* __ASSEMBLY__ */
 #endif
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index 89ecd57c9d423..853a2e6287698 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -34,16 +34,13 @@
 #include <asm/thread_info.h>
 #include <asm/asm.h>
 #include <asm/smap.h>
+#include <asm/runtime-const.h>
 
 #define ASM_BARRIER_NOSPEC ALTERNATIVE "", "lfence", X86_FEATURE_LFENCE_RDTSC
 
 .macro check_range size:req
 .if IS_ENABLED(CONFIG_X86_64)
-	movq $0x0123456789abcdef,%rdx
-  1:
-  .pushsection runtime_ptr_USER_PTR_MAX,"a"
-	.long 1b - 8 - .
-  .popsection
+	RUNTIME_CONST_PTR USER_PTR_MAX, rdx
 	cmp %rdx, %rax
 	cmova %rdx, %rax
 .else

From d6834d9c990333bfa433bc1816e2417f268eebbe Mon Sep 17 00:00:00 2001
From: Li Huafei <lihuafei1@huawei.com>
Date: Tue, 22 Oct 2024 03:30:03 +0800
Subject: [PATCH 1062/1173] watchdog/hardlockup/perf: Fix perf_event memory
 leak

During stress-testing, we found a kmemleak report for perf_event:

  unreferenced object 0xff110001410a33e0 (size 1328):
    comm "kworker/4:11", pid 288, jiffies 4294916004
    hex dump (first 32 bytes):
      b8 be c2 3b 02 00 11 ff 22 01 00 00 00 00 ad de  ...;....".......
      f0 33 0a 41 01 00 11 ff f0 33 0a 41 01 00 11 ff  .3.A.....3.A....
    backtrace (crc 24eb7b3a):
      [<00000000e211b653>] kmem_cache_alloc_node_noprof+0x269/0x2e0
      [<000000009d0985fa>] perf_event_alloc+0x5f/0xcf0
      [<00000000084ad4a2>] perf_event_create_kernel_counter+0x38/0x1b0
      [<00000000fde96401>] hardlockup_detector_event_create+0x50/0xe0
      [<0000000051183158>] watchdog_hardlockup_enable+0x17/0x70
      [<00000000ac89727f>] softlockup_start_fn+0x15/0x40
      ...

Our stress test includes CPU online and offline cycles, and updating the
watchdog configuration.

After reading the code, I found that there may be a race between cleaning up
perf_event after updating watchdog and disabling event when the CPU goes offline:

  CPU0                          CPU1                           CPU2
  (update watchdog)                                            (hotplug offline CPU1)

  ...                                                          _cpu_down(CPU1)
  cpus_read_lock()                                             // waiting for cpu lock
    softlockup_start_all
      smp_call_on_cpu(CPU1)
                                softlockup_start_fn
                                ...
                                  watchdog_hardlockup_enable(CPU1)
                                    perf create E1
                                    watchdog_ev[CPU1] = E1
  cpus_read_unlock()
                                                               cpus_write_lock()
                                                               cpuhp_kick_ap_work(CPU1)
                                cpuhp_thread_fun
                                ...
                                  watchdog_hardlockup_disable(CPU1)
                                    watchdog_ev[CPU1] = NULL
                                    dead_event[CPU1] = E1
  __lockup_detector_cleanup
    for each dead_events_mask
      release each dead_event
      /*
       * CPU1 has not been added to
       * dead_events_mask, then E1
       * will not be released
       */
                                    CPU1 -> dead_events_mask
    cpumask_clear(&dead_events_mask)
    // dead_events_mask is cleared, E1 is leaked

In this case, the leaked perf_event E1 matches the perf_event leak
reported by kmemleak. Due to the low probability of problem recurrence
(only reported once), I added some hack delays in the code:

  static void __lockup_detector_reconfigure(void)
  {
    ...
          watchdog_hardlockup_start();
          cpus_read_unlock();
  +       mdelay(100);
          /*
           * Must be called outside the cpus locked section to prevent
           * recursive locking in the perf code.
    ...
  }

  void watchdog_hardlockup_disable(unsigned int cpu)
  {
    ...
                  perf_event_disable(event);
                  this_cpu_write(watchdog_ev, NULL);
                  this_cpu_write(dead_event, event);
  +               mdelay(100);
                  cpumask_set_cpu(smp_processor_id(), &dead_events_mask);
                  atomic_dec(&watchdog_cpus);
    ...
  }

  void hardlockup_detector_perf_cleanup(void)
  {
    ...
                          perf_event_release_kernel(event);
                  per_cpu(dead_event, cpu) = NULL;
          }
  +       mdelay(100);
          cpumask_clear(&dead_events_mask);
  }

Then, simultaneously performing CPU on/off and switching watchdog, it is
almost certain to reproduce this leak.

The problem here is that releasing perf_event is not within the CPU
hotplug read-write lock. Commit:

  941154bd6937 ("watchdog/hardlockup/perf: Prevent CPU hotplug deadlock")

introduced deferred release to solve the deadlock caused by calling
get_online_cpus() when releasing perf_event. Later, commit:

  efe951d3de91 ("perf/x86: Fix perf,x86,cpuhp deadlock")

removed the get_online_cpus() call on the perf_event release path to solve
another deadlock problem.

Therefore, it is now possible to move the release of perf_event back
into the CPU hotplug read-write lock, and release the event immediately
after disabling it.

Fixes: 941154bd6937 ("watchdog/hardlockup/perf: Prevent CPU hotplug deadlock")
Signed-off-by: Li Huafei <lihuafei1@huawei.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20241021193004.308303-1-lihuafei1@huawei.com
---
 include/linux/nmi.h    |  4 ----
 kernel/cpu.c           |  5 -----
 kernel/watchdog.c      | 25 -------------------------
 kernel/watchdog_perf.c | 28 +---------------------------
 4 files changed, 1 insertion(+), 61 deletions(-)

diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index a8dfb38c9bb6f..e78fa535f61dd 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -17,7 +17,6 @@
 void lockup_detector_init(void);
 void lockup_detector_retry_init(void);
 void lockup_detector_soft_poweroff(void);
-void lockup_detector_cleanup(void);
 
 extern int watchdog_user_enabled;
 extern int watchdog_thresh;
@@ -37,7 +36,6 @@ extern int sysctl_hardlockup_all_cpu_backtrace;
 static inline void lockup_detector_init(void) { }
 static inline void lockup_detector_retry_init(void) { }
 static inline void lockup_detector_soft_poweroff(void) { }
-static inline void lockup_detector_cleanup(void) { }
 #endif /* !CONFIG_LOCKUP_DETECTOR */
 
 #ifdef CONFIG_SOFTLOCKUP_DETECTOR
@@ -104,12 +102,10 @@ void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs);
 #if defined(CONFIG_HARDLOCKUP_DETECTOR_PERF)
 extern void hardlockup_detector_perf_stop(void);
 extern void hardlockup_detector_perf_restart(void);
-extern void hardlockup_detector_perf_cleanup(void);
 extern void hardlockup_config_perf_event(const char *str);
 #else
 static inline void hardlockup_detector_perf_stop(void) { }
 static inline void hardlockup_detector_perf_restart(void) { }
-static inline void hardlockup_detector_perf_cleanup(void) { }
 static inline void hardlockup_config_perf_event(const char *str) { }
 #endif
 
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 07455d25329c9..ad755db29efd4 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1453,11 +1453,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen,
 
 out:
 	cpus_write_unlock();
-	/*
-	 * Do post unplug cleanup. This is still protected against
-	 * concurrent CPU hotplug via cpu_add_remove_lock.
-	 */
-	lockup_detector_cleanup();
 	arch_smt_update();
 	return ret;
 }
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index b2da7de39d06d..18156023e4614 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -347,8 +347,6 @@ static int __init watchdog_thresh_setup(char *str)
 }
 __setup("watchdog_thresh=", watchdog_thresh_setup);
 
-static void __lockup_detector_cleanup(void);
-
 #ifdef CONFIG_SOFTLOCKUP_DETECTOR_INTR_STORM
 enum stats_per_group {
 	STATS_SYSTEM,
@@ -886,11 +884,6 @@ static void __lockup_detector_reconfigure(void)
 
 	watchdog_hardlockup_start();
 	cpus_read_unlock();
-	/*
-	 * Must be called outside the cpus locked section to prevent
-	 * recursive locking in the perf code.
-	 */
-	__lockup_detector_cleanup();
 }
 
 void lockup_detector_reconfigure(void)
@@ -940,24 +933,6 @@ static inline void lockup_detector_setup(void)
 }
 #endif /* !CONFIG_SOFTLOCKUP_DETECTOR */
 
-static void __lockup_detector_cleanup(void)
-{
-	lockdep_assert_held(&watchdog_mutex);
-	hardlockup_detector_perf_cleanup();
-}
-
-/**
- * lockup_detector_cleanup - Cleanup after cpu hotplug or sysctl changes
- *
- * Caller must not hold the cpu hotplug rwsem.
- */
-void lockup_detector_cleanup(void)
-{
-	mutex_lock(&watchdog_mutex);
-	__lockup_detector_cleanup();
-	mutex_unlock(&watchdog_mutex);
-}
-
 /**
  * lockup_detector_soft_poweroff - Interface to stop lockup detector(s)
  *
diff --git a/kernel/watchdog_perf.c b/kernel/watchdog_perf.c
index 59c1d86a73a24..2fdb96eaf4933 100644
--- a/kernel/watchdog_perf.c
+++ b/kernel/watchdog_perf.c
@@ -21,8 +21,6 @@
 #include <linux/perf_event.h>
 
 static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
-static DEFINE_PER_CPU(struct perf_event *, dead_event);
-static struct cpumask dead_events_mask;
 
 static atomic_t watchdog_cpus = ATOMIC_INIT(0);
 
@@ -181,36 +179,12 @@ void watchdog_hardlockup_disable(unsigned int cpu)
 
 	if (event) {
 		perf_event_disable(event);
+		perf_event_release_kernel(event);
 		this_cpu_write(watchdog_ev, NULL);
-		this_cpu_write(dead_event, event);
-		cpumask_set_cpu(smp_processor_id(), &dead_events_mask);
 		atomic_dec(&watchdog_cpus);
 	}
 }
 
-/**
- * hardlockup_detector_perf_cleanup - Cleanup disabled events and destroy them
- *
- * Called from lockup_detector_cleanup(). Serialized by the caller.
- */
-void hardlockup_detector_perf_cleanup(void)
-{
-	int cpu;
-
-	for_each_cpu(cpu, &dead_events_mask) {
-		struct perf_event *event = per_cpu(dead_event, cpu);
-
-		/*
-		 * Required because for_each_cpu() reports  unconditionally
-		 * CPU0 as set on UP kernels. Sigh.
-		 */
-		if (event)
-			perf_event_release_kernel(event);
-		per_cpu(dead_event, cpu) = NULL;
-	}
-	cpumask_clear(&dead_events_mask);
-}
-
 /**
  * hardlockup_detector_perf_stop - Globally stop watchdog events
  *

From 05763885e327f0e257ee8b96b30ac1b95f7dd532 Mon Sep 17 00:00:00 2001
From: Li Huafei <lihuafei1@huawei.com>
Date: Tue, 22 Oct 2024 03:30:04 +0800
Subject: [PATCH 1063/1173] watchdog/hardlockup/perf: Warn if watchdog_ev is
 leaked

When creating a new perf_event for the hardlockup watchdog, it should not
happen that the old perf_event is not released.

Introduce a WARN_ONCE() that should never trigger.

[ mingo: Changed the type of the warning to WARN_ONCE(). ]

Signed-off-by: Li Huafei <lihuafei1@huawei.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20241021193004.308303-2-lihuafei1@huawei.com
---
 kernel/watchdog_perf.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/watchdog_perf.c b/kernel/watchdog_perf.c
index 2fdb96eaf4933..a78ff092d6360 100644
--- a/kernel/watchdog_perf.c
+++ b/kernel/watchdog_perf.c
@@ -144,6 +144,7 @@ static int hardlockup_detector_event_create(void)
 			 PTR_ERR(evt));
 		return PTR_ERR(evt);
 	}
+	WARN_ONCE(this_cpu_read(watchdog_ev), "unexpected watchdog_ev leak");
 	this_cpu_write(watchdog_ev, evt);
 	return 0;
 }

From fa6192adc32f4fdfe5b74edd5b210e12afd6ecc0 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 12 Feb 2025 23:04:33 +0100
Subject: [PATCH 1064/1173] uprobes/x86: Harden uretprobe syscall trampoline
 check

Jann reported a possible issue when trampoline_check_ip returns
address near the bottom of the address space that is allowed to
call into the syscall if uretprobes are not set up:

   https://lore.kernel.org/bpf/202502081235.5A6F352985@keescook/T/#m9d416df341b8fbc11737dacbcd29f0054413cbbf

Though the mmap minimum address restrictions will typically prevent
creating mappings there, let's make sure uretprobe syscall checks
for that.

Fixes: ff474a78cef5 ("uprobe: Add uretprobe syscall to speed up return probe")
Reported-by: Jann Horn <jannh@google.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Kees Cook <kees@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250212220433.3624297-1-jolsa@kernel.org
---
 arch/x86/kernel/uprobes.c | 14 +++++++++-----
 include/linux/uprobes.h   |  2 ++
 kernel/events/uprobes.c   |  2 +-
 3 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 5a952c5ea66bc..9194695662b26 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -357,19 +357,23 @@ void *arch_uprobe_trampoline(unsigned long *psize)
 	return &insn;
 }
 
-static unsigned long trampoline_check_ip(void)
+static unsigned long trampoline_check_ip(unsigned long tramp)
 {
-	unsigned long tramp = uprobe_get_trampoline_vaddr();
-
 	return tramp + (uretprobe_syscall_check - uretprobe_trampoline_entry);
 }
 
 SYSCALL_DEFINE0(uretprobe)
 {
 	struct pt_regs *regs = task_pt_regs(current);
-	unsigned long err, ip, sp, r11_cx_ax[3];
+	unsigned long err, ip, sp, r11_cx_ax[3], tramp;
+
+	/* If there's no trampoline, we are called from wrong place. */
+	tramp = uprobe_get_trampoline_vaddr();
+	if (unlikely(tramp == UPROBE_NO_TRAMPOLINE_VADDR))
+		goto sigill;
 
-	if (regs->ip != trampoline_check_ip())
+	/* Make sure the ip matches the only allowed sys_uretprobe caller. */
+	if (unlikely(regs->ip != trampoline_check_ip(tramp)))
 		goto sigill;
 
 	err = copy_from_user(r11_cx_ax, (void __user *)regs->sp, sizeof(r11_cx_ax));
diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index a40efdda9052b..2e46b69ff0a6f 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -39,6 +39,8 @@ struct page;
 
 #define MAX_URETPROBE_DEPTH		64
 
+#define UPROBE_NO_TRAMPOLINE_VADDR	(~0UL)
+
 struct uprobe_consumer {
 	/*
 	 * handler() can return UPROBE_HANDLER_REMOVE to signal the need to
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 921ad91621362..70c84b9d7be3b 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -2169,8 +2169,8 @@ void uprobe_copy_process(struct task_struct *t, unsigned long flags)
  */
 unsigned long uprobe_get_trampoline_vaddr(void)
 {
+	unsigned long trampoline_vaddr = UPROBE_NO_TRAMPOLINE_VADDR;
 	struct xol_area *area;
-	unsigned long trampoline_vaddr = -1;
 
 	/* Pairs with xol_add_vma() smp_store_release() */
 	area = READ_ONCE(current->mm->uprobes_state.xol_area); /* ^^^ */

From b5e3956535466187657563b754ba0f1da8626c7f Mon Sep 17 00:00:00 2001
From: Inochi Amaoto <inochiama@gmail.com>
Date: Thu, 6 Mar 2025 14:39:51 +0800
Subject: [PATCH 1065/1173] kbuild: install-extmod-build: Fix build when
 specifying KBUILD_OUTPUT

Since commit 5f73e7d0386d ("kbuild: refactor cross-compiling
linux-headers package"), the linux-headers pacman package fails
to build when "O=" is set. The build system complains:

/mnt/chroot/linux/scripts/Makefile.build:41: mnt/chroots/linux-mainline/pacman/linux-upstream/pkg/linux-upstream-headers/usr//lib/modules/6.14.0-rc3-00350-g771dba31fffc/build/scripts/Makefile: No such file or directory

This is because the "srcroot" variable is set to "." and the
"build" variable is set to the absolute path. This makes the
"src" variables point to wrong directory.

Change the "build" variable to a relative path to "." to
fix build.

Fixes: 5f73e7d0386d ("kbuild: refactor cross-compiling linux-headers package")
Signed-off-by: Inochi Amaoto <inochiama@gmail.com>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/package/install-extmod-build | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/package/install-extmod-build b/scripts/package/install-extmod-build
index 2966473b46609..b96538787f3d9 100755
--- a/scripts/package/install-extmod-build
+++ b/scripts/package/install-extmod-build
@@ -63,7 +63,7 @@ if [ "${CC}" != "${HOSTCC}" ]; then
 	# Clear VPATH and srcroot because the source files reside in the output
 	# directory.
 	# shellcheck disable=SC2016 # $(MAKE) and $(build) will be expanded by Make
-	"${MAKE}" run-command KBUILD_RUN_COMMAND='+$(MAKE) HOSTCC='"${CC}"' VPATH= srcroot=. $(build)='"${destdir}"/scripts
+	"${MAKE}" run-command KBUILD_RUN_COMMAND='+$(MAKE) HOSTCC='"${CC}"' VPATH= srcroot=. $(build)='"$(realpath --relative-base=. "${destdir}")"/scripts
 
 	rm -f "${destdir}/scripts/Kbuild"
 fi

From d02198550423a0b695e7a24ec77153209ad45b09 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Tue, 4 Mar 2025 12:49:54 -0800
Subject: [PATCH 1066/1173] x86/fpu: Improve crypto performance by making
 kernel-mode FPU reliably usable in softirqs

Background:
===========

Currently kernel-mode FPU is not always usable in softirq context on
x86, since softirqs can nest inside a kernel-mode FPU section in task
context, and nested use of kernel-mode FPU is not supported.

Therefore, x86 SIMD-optimized code that can be called in softirq context
has to sometimes fall back to non-SIMD code.  There are two options for
the fallback, both of which are pretty terrible:

  (a) Use a scalar fallback.  This can be 10-100x slower than vectorized
      code because it cannot use specialized instructions like AES, SHA,
      or carryless multiplication.

  (b) Execute the request asynchronously using a kworker.  In other
      words, use the "crypto SIMD helper" in crypto/simd.c.

Currently most of the x86 en/decryption code (skcipher and aead
algorithms) uses option (b), since this avoids the slow scalar fallback
and it is easier to wire up.  But option (b) is still really bad for its
own reasons:

  - Punting the request to a kworker is bad for performance too.

  - It forces the algorithm to be marked as asynchronous
    (CRYPTO_ALG_ASYNC), preventing it from being used by crypto API
    users who request a synchronous algorithm.  That's another huge
    performance problem, which is especially unfortunate for users who
    don't even do en/decryption in softirq context.

  - It makes all en/decryption operations take a detour through
    crypto/simd.c.  That involves additional checks and an additional
    indirect call, which slow down en/decryption for *everyone*.

Fortunately, the skcipher and aead APIs are only usable in task and
softirq context in the first place.  Thus, if kernel-mode FPU were to be
reliably usable in softirq context, no fallback would be needed.
Indeed, other architectures such as arm, arm64, and riscv have already
done this.

Changes implemented:
====================

Therefore, this patch updates x86 accordingly to reliably support
kernel-mode FPU in softirqs.

This is done by just disabling softirq processing in kernel-mode FPU
sections (when hardirqs are not already disabled), as that prevents the
nesting that was problematic.

This will delay some softirqs slightly, but only ones that would have
otherwise been nested inside a task context kernel-mode FPU section.
Any such softirqs would have taken the slow fallback path before if they
tried to do any en/decryption.  Now these softirqs will just run at the
end of the task context kernel-mode FPU section (since local_bh_enable()
runs pending softirqs) and will no longer take the slow fallback path.

Alternatives considered:
========================

- Make kernel-mode FPU sections fully preemptible.  This would require
  growing task_struct by another struct fpstate which is more than 2K.

- Make softirqs save/restore the kernel-mode FPU state to a per-CPU
  struct fpstate when nested use is detected.  Somewhat interesting, but
  seems unnecessary when a simpler solution exists.

Performance results:
====================

I did some benchmarks with AES-XTS encryption of 16-byte messages (which is
unrealistically small, but this makes it easier to see the overhead of
kernel-mode FPU...).  The baseline was 384 MB/s.  Removing the use of
crypto/simd.c, which this work makes possible, increases it to 487 MB/s,
a +27% improvement in throughput.

CPU was AMD Ryzen 9 9950X (Zen 5).  No debugging options were enabled.

[ mingo: Prettified the changelog and added performance results. ]

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Uros Bizjak <ubizjak@gmail.com>
Link: https://lore.kernel.org/r/20250304204954.3901-1-ebiggers@kernel.org
---
 arch/x86/include/asm/fpu/api.h | 17 +++++++----------
 arch/x86/kernel/fpu/core.c     | 17 +++++++++++++----
 2 files changed, 20 insertions(+), 14 deletions(-)

diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index f86ad3335529d..f42de5f05e7eb 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -16,10 +16,9 @@
 
 /*
  * Use kernel_fpu_begin/end() if you intend to use FPU in kernel context. It
- * disables preemption so be careful if you intend to use it for long periods
- * of time.
- * If you intend to use the FPU in irq/softirq you need to check first with
- * irq_fpu_usable() if it is possible.
+ * disables preemption and softirq processing, so be careful if you intend to
+ * use it for long periods of time.  Kernel-mode FPU cannot be used in all
+ * contexts -- see irq_fpu_usable() for details.
  */
 
 /* Kernel FPU states to initialize in kernel_fpu_begin_mask() */
@@ -50,10 +49,10 @@ static inline void kernel_fpu_begin(void)
 }
 
 /*
- * Use fpregs_lock() while editing CPU's FPU registers or fpu->fpstate.
- * A context switch will (and softirq might) save CPU's FPU registers to
- * fpu->fpstate.regs and set TIF_NEED_FPU_LOAD leaving CPU's FPU registers in
- * a random state.
+ * Use fpregs_lock() while editing CPU's FPU registers or fpu->fpstate, or while
+ * using the FPU in kernel mode.  A context switch will (and softirq might) save
+ * CPU's FPU registers to fpu->fpstate.regs and set TIF_NEED_FPU_LOAD leaving
+ * CPU's FPU registers in a random state.
  *
  * local_bh_disable() protects against both preemption and soft interrupts
  * on !RT kernels.
@@ -63,8 +62,6 @@ static inline void kernel_fpu_begin(void)
  * preemptible. Disabling preemption is the right choice here as bottom
  * half processing is always in thread context on RT kernels so it
  * implicitly prevents bottom half processing as well.
- *
- * Disabling preemption also serializes against kernel_fpu_begin().
  */
 static inline void fpregs_lock(void)
 {
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 36df548acc403..422c98ca6eb86 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -60,9 +60,16 @@ bool irq_fpu_usable(void)
 	if (WARN_ON_ONCE(in_nmi()))
 		return false;
 
-	/* In kernel FPU usage already active? */
-	if (this_cpu_read(in_kernel_fpu))
+	/*
+	 * In kernel FPU usage already active?  This detects any explicitly
+	 * nested usage in task or softirq context, which is unsupported.  It
+	 * also detects attempted usage in a hardirq that has interrupted a
+	 * kernel-mode FPU section.
+	 */
+	if (this_cpu_read(in_kernel_fpu)) {
+		WARN_ON_FPU(!in_hardirq());
 		return false;
+	}
 
 	/*
 	 * When not in NMI or hard interrupt context, FPU can be used in:
@@ -420,7 +427,8 @@ EXPORT_SYMBOL_GPL(fpu_copy_uabi_to_guest_fpstate);
 
 void kernel_fpu_begin_mask(unsigned int kfpu_mask)
 {
-	preempt_disable();
+	if (!irqs_disabled())
+		fpregs_lock();
 
 	WARN_ON_FPU(!irq_fpu_usable());
 	WARN_ON_FPU(this_cpu_read(in_kernel_fpu));
@@ -448,7 +456,8 @@ void kernel_fpu_end(void)
 	WARN_ON_FPU(!this_cpu_read(in_kernel_fpu));
 
 	this_cpu_write(in_kernel_fpu, false);
-	preempt_enable();
+	if (!irqs_disabled())
+		fpregs_unlock();
 }
 EXPORT_SYMBOL_GPL(kernel_fpu_end);
 

From 35d99c68af40a8ca175babc5a89ef7e2226fb3ca Mon Sep 17 00:00:00 2001
From: Haoxiang Li <haoxiang_li2024@163.com>
Date: Mon, 3 Mar 2025 10:42:33 +0800
Subject: [PATCH 1067/1173] btrfs: fix a leaked chunk map issue in
 read_one_chunk()

Add btrfs_free_chunk_map() to free the memory allocated
by btrfs_alloc_chunk_map() if btrfs_add_chunk_map() fails.

Fixes: 7dc66abb5a47 ("btrfs: use a dedicated data structure for chunk maps")
CC: stable@vger.kernel.org
Reviewed-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Haoxiang Li <haoxiang_li2024@163.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/volumes.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index f6ae76815e4b5..6f8dcf59b5257 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -7151,6 +7151,7 @@ static int read_one_chunk(struct btrfs_key *key, struct extent_buffer *leaf,
 		btrfs_err(fs_info,
 			  "failed to add chunk map, start=%llu len=%llu: %d",
 			  map->start, map->chunk_len, ret);
+		btrfs_free_chunk_map(map);
 	}
 
 	return ret;

From 391b41f983bf7ff853de44704d8e14e7cc648a9b Mon Sep 17 00:00:00 2001
From: Fabrizio Castro <fabrizio.castro.jz@renesas.com>
Date: Wed, 5 Mar 2025 16:37:50 +0000
Subject: [PATCH 1068/1173] gpio: rcar: Fix missing of_node_put() call

of_parse_phandle_with_fixed_args() requires its caller to
call into of_node_put() on the node pointer from the output
structure, but such a call is currently missing.

Call into of_node_put() to rectify that.

Fixes: 159f8a0209af ("gpio-rcar: Add DT support")
Signed-off-by: Fabrizio Castro <fabrizio.castro.jz@renesas.com>
Reviewed-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20250305163753.34913-2-fabrizio.castro.jz@renesas.com
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpio-rcar.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/gpio/gpio-rcar.c b/drivers/gpio/gpio-rcar.c
index 8e0544e924886..a7a1cdf7ac66d 100644
--- a/drivers/gpio/gpio-rcar.c
+++ b/drivers/gpio/gpio-rcar.c
@@ -468,7 +468,12 @@ static int gpio_rcar_parse_dt(struct gpio_rcar_priv *p, unsigned int *npins)
 	p->info = *info;
 
 	ret = of_parse_phandle_with_fixed_args(np, "gpio-ranges", 3, 0, &args);
-	*npins = ret == 0 ? args.args[2] : RCAR_MAX_GPIO_PER_BANK;
+	if (ret) {
+		*npins = RCAR_MAX_GPIO_PER_BANK;
+	} else {
+		*npins = args.args[2];
+		of_node_put(args.np);
+	}
 
 	if (*npins == 0 || *npins > RCAR_MAX_GPIO_PER_BANK) {
 		dev_warn(p->dev, "Invalid number of gpio lines %u, using %u\n",

From ff712188daa3fe3ce7e11e530b4dca3826dae14a Mon Sep 17 00:00:00 2001
From: Miao Li <limiao@kylinos.cn>
Date: Tue, 4 Mar 2025 15:07:57 +0800
Subject: [PATCH 1069/1173] usb: quirks: Add DELAY_INIT and NO_LPM for Prolific
 Mass Storage Card Reader

When used on Huawei hisi platforms, Prolific Mass Storage Card Reader
which the VID:PID is in 067b:2731 might fail to enumerate at boot time
and doesn't work well with LPM enabled, combination quirks:
	USB_QUIRK_DELAY_INIT + USB_QUIRK_NO_LPM
fixed the problems.

Signed-off-by: Miao Li <limiao@kylinos.cn>
Cc: stable <stable@kernel.org>
Link: https://lore.kernel.org/r/20250304070757.139473-1-limiao870622@163.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/quirks.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index dfcfc142bd5e1..8efbacc5bc341 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -341,6 +341,10 @@ static const struct usb_device_id usb_quirk_list[] = {
 	{ USB_DEVICE(0x0638, 0x0a13), .driver_info =
 	  USB_QUIRK_STRING_FETCH_255 },
 
+	/* Prolific Single-LUN Mass Storage Card Reader */
+	{ USB_DEVICE(0x067b, 0x2731), .driver_info = USB_QUIRK_DELAY_INIT |
+	  USB_QUIRK_NO_LPM },
+
 	/* Saitek Cyborg Gold Joystick */
 	{ USB_DEVICE(0x06a3, 0x0006), .driver_info =
 			USB_QUIRK_CONFIG_INTF_STRINGS },

From b13abcb7ddd8d38de769486db5bd917537b32ab1 Mon Sep 17 00:00:00 2001
From: Andrei Kuchynski <akuchynski@chromium.org>
Date: Wed, 5 Mar 2025 11:17:39 +0000
Subject: [PATCH 1070/1173] usb: typec: ucsi: Fix NULL pointer access

Resources should be released only after all threads that utilize them
have been destroyed.
This commit ensures that resources are not released prematurely by waiting
for the associated workqueue to complete before deallocating them.

Cc: stable <stable@kernel.org>
Fixes: b9aa02ca39a4 ("usb: typec: ucsi: Add polling mechanism for partner tasks like alt mode checking")
Signed-off-by: Andrei Kuchynski <akuchynski@chromium.org>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20250305111739.1489003-2-akuchynski@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/ucsi/ucsi.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c
index 7a56d3f840d75..2a2915b0a645f 100644
--- a/drivers/usb/typec/ucsi/ucsi.c
+++ b/drivers/usb/typec/ucsi/ucsi.c
@@ -1825,11 +1825,11 @@ static int ucsi_init(struct ucsi *ucsi)
 
 err_unregister:
 	for (con = connector; con->port; con++) {
+		if (con->wq)
+			destroy_workqueue(con->wq);
 		ucsi_unregister_partner(con);
 		ucsi_unregister_altmodes(con, UCSI_RECIPIENT_CON);
 		ucsi_unregister_port_psy(con);
-		if (con->wq)
-			destroy_workqueue(con->wq);
 
 		usb_power_delivery_unregister_capabilities(con->port_sink_caps);
 		con->port_sink_caps = NULL;
@@ -2013,10 +2013,6 @@ void ucsi_unregister(struct ucsi *ucsi)
 
 	for (i = 0; i < ucsi->cap.num_connectors; i++) {
 		cancel_work_sync(&ucsi->connector[i].work);
-		ucsi_unregister_partner(&ucsi->connector[i]);
-		ucsi_unregister_altmodes(&ucsi->connector[i],
-					 UCSI_RECIPIENT_CON);
-		ucsi_unregister_port_psy(&ucsi->connector[i]);
 
 		if (ucsi->connector[i].wq) {
 			struct ucsi_work *uwork;
@@ -2032,6 +2028,11 @@ void ucsi_unregister(struct ucsi *ucsi)
 			destroy_workqueue(ucsi->connector[i].wq);
 		}
 
+		ucsi_unregister_partner(&ucsi->connector[i]);
+		ucsi_unregister_altmodes(&ucsi->connector[i],
+					 UCSI_RECIPIENT_CON);
+		ucsi_unregister_port_psy(&ucsi->connector[i]);
+
 		usb_power_delivery_unregister_capabilities(ucsi->connector[i].port_sink_caps);
 		ucsi->connector[i].port_sink_caps = NULL;
 		usb_power_delivery_unregister_capabilities(ucsi->connector[i].port_source_caps);

From 74d42bdb3a4673b1c10d1f457184e4d3c9cb0196 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Thu, 6 Mar 2025 07:30:42 -1000
Subject: [PATCH 1071/1173] fs/pipe: express 'pipe_empty()' in terms of
 'pipe_occupancy()'

That's what 'pipe_full()' does, so it's more consistent. But more
importantly it gets the type limits right when the pipe head and tail
are no longer necessarily 'unsigned int'.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/pipe_fs_i.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index e572e6fc4f81f..4d0a2267e6efc 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -177,23 +177,23 @@ static inline bool pipe_has_watch_queue(const struct pipe_inode_info *pipe)
 }
 
 /**
- * pipe_empty - Return true if the pipe is empty
+ * pipe_occupancy - Return number of slots used in the pipe
  * @head: The pipe ring head pointer
  * @tail: The pipe ring tail pointer
  */
-static inline bool pipe_empty(unsigned int head, unsigned int tail)
+static inline unsigned int pipe_occupancy(unsigned int head, unsigned int tail)
 {
-	return head == tail;
+	return (pipe_index_t)(head - tail);
 }
 
 /**
- * pipe_occupancy - Return number of slots used in the pipe
+ * pipe_empty - Return true if the pipe is empty
  * @head: The pipe ring head pointer
  * @tail: The pipe ring tail pointer
  */
-static inline unsigned int pipe_occupancy(unsigned int head, unsigned int tail)
+static inline bool pipe_empty(unsigned int head, unsigned int tail)
 {
-	return (pipe_index_t)(head - tail);
+	return !pipe_occupancy(head, tail);
 }
 
 /**

From d810d4c27bf34c719243bab9feb0d843edc09fd7 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Thu, 6 Mar 2025 07:33:58 -1000
Subject: [PATCH 1072/1173] fs/pipe: do not open-code pipe head/tail logic in
 FIONREAD

Rasmus points out that we do indeed have other cases of breakage from
the type changes that were introduced on 32-bit targets in order to read
the pipe head and tail values atomically (commit 3d252160b818: "fs/pipe:
Read pipe->{head,tail} atomically outside pipe->mutex").

Fix it up by using the proper helper functions that now deal with the
pipe buffer index types properly.  This makes the code simpler and more
obvious.

The compiler does the CSE and loop hoisting of the pipe ring size
masking that we used to do manually, so open-coding this was never a
good idea.

Reported-by: Rasmus Villemoes <ravi@prevas.dk>
Link: https://lore.kernel.org/all/87cyeu5zgk.fsf@prevas.dk/
Fixes: 3d252160b818 ("fs/pipe: Read pipe->{head,tail} atomically outside pipe->mutex")Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Mateusz Guzik <mjguzik@gmail.com>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Swapnil Sapkal <swapnil.sapkal@amd.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/pipe.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/fs/pipe.c b/fs/pipe.c
index e8e6698f36981..5c872775a6db9 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -614,7 +614,7 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from)
 static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	struct pipe_inode_info *pipe = filp->private_data;
-	unsigned int count, head, tail, mask;
+	unsigned int count, head, tail;
 
 	switch (cmd) {
 	case FIONREAD:
@@ -622,10 +622,9 @@ static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		count = 0;
 		head = pipe->head;
 		tail = pipe->tail;
-		mask = pipe->ring_size - 1;
 
-		while (tail != head) {
-			count += pipe->bufs[tail & mask].len;
+		while (!pipe_empty(head, tail)) {
+			count += pipe_buf(pipe, tail)->len;
 			tail++;
 		}
 		mutex_unlock(&pipe->mutex);

From ebb0f38bb47f74b29e267babdbcd2c47d5292aa8 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Thu, 6 Mar 2025 07:53:25 -1000
Subject: [PATCH 1073/1173] fs/pipe: fix pipe buffer index use in FUSE

This was another case that Rasmus pointed out where the direct access to
the pipe head and tail pointers broke on 32-bit configurations due to
the type changes.

As with the pipe FIONREAD case, fix it by using the appropriate helper
functions that deal with the right pipe index sizing.

Reported-by: Rasmus Villemoes <ravi@prevas.dk>
Link: https://lore.kernel.org/all/878qpi5wz4.fsf@prevas.dk/
Fixes: 3d252160b818 ("fs/pipe: Read pipe->{head,tail} atomically outside pipe->mutex")Cc: Oleg >
Cc: Mateusz Guzik <mjguzik@gmail.com>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Swapnil Sapkal <swapnil.sapkal@amd.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/fuse/dev.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 2b2d1b7555444..3c9caafca9e29 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -2107,7 +2107,7 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
 				     struct file *out, loff_t *ppos,
 				     size_t len, unsigned int flags)
 {
-	unsigned int head, tail, mask, count;
+	unsigned int head, tail, count;
 	unsigned nbuf;
 	unsigned idx;
 	struct pipe_buffer *bufs;
@@ -2124,8 +2124,7 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
 
 	head = pipe->head;
 	tail = pipe->tail;
-	mask = pipe->ring_size - 1;
-	count = head - tail;
+	count = pipe_occupancy(head, tail);
 
 	bufs = kvmalloc_array(count, sizeof(struct pipe_buffer), GFP_KERNEL);
 	if (!bufs) {
@@ -2135,8 +2134,8 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
 
 	nbuf = 0;
 	rem = 0;
-	for (idx = tail; idx != head && rem < len; idx++)
-		rem += pipe->bufs[idx & mask].len;
+	for (idx = tail; !pipe_empty(head, idx) && rem < len; idx++)
+		rem += pipe_buf(pipe, idx)->len;
 
 	ret = -EINVAL;
 	if (rem < len)
@@ -2147,10 +2146,10 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
 		struct pipe_buffer *ibuf;
 		struct pipe_buffer *obuf;
 
-		if (WARN_ON(nbuf >= count || tail == head))
+		if (WARN_ON(nbuf >= count || pipe_empty(head, tail)))
 			goto out_free;
 
-		ibuf = &pipe->bufs[tail & mask];
+		ibuf = pipe_buf(pipe, tail);
 		obuf = &bufs[nbuf];
 
 		if (rem >= ibuf->len) {

From c00b413a96261faef4ce22329153c6abd4acef25 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Thu, 6 Mar 2025 16:59:16 +0100
Subject: [PATCH 1074/1173] x86/boot: Sanitize boot params before parsing
 command line

The 5-level paging code parses the command line to look for the 'no5lvl'
string, and does so very early, before sanitize_boot_params() has been
called and has been given the opportunity to wipe bogus data from the
fields in boot_params that are not covered by struct setup_header, and
are therefore supposed to be initialized to zero by the bootloader.

This triggers an early boot crash when using syslinux-efi to boot a
recent kernel built with CONFIG_X86_5LEVEL=y and CONFIG_EFI_STUB=n, as
the 0xff padding that now fills the unused PE/COFF header is copied into
boot_params by the bootloader, and interpreted as the top half of the
command line pointer.

Fix this by sanitizing the boot_params before use. Note that there is no
harm in calling this more than once; subsequent invocations are able to
spot that the boot_params have already been cleaned up.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: <stable@vger.kernel.org> # v6.1+
Link: https://lore.kernel.org/r/20250306155915.342465-2-ardb+git@google.com
Closes: https://lore.kernel.org/all/202503041549.35913.ulrich.gemkow@ikr.uni-stuttgart.de
---
 arch/x86/boot/compressed/pgtable_64.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c
index c882e1f67af01..d8c5de40669d3 100644
--- a/arch/x86/boot/compressed/pgtable_64.c
+++ b/arch/x86/boot/compressed/pgtable_64.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "misc.h"
 #include <asm/bootparam.h>
+#include <asm/bootparam_utils.h>
 #include <asm/e820/types.h>
 #include <asm/processor.h>
 #include "pgtable.h"
@@ -107,6 +108,7 @@ asmlinkage void configure_5level_paging(struct boot_params *bp, void *pgtable)
 	bool l5_required = false;
 
 	/* Initialize boot_params. Required for cmdline_find_option_bool(). */
+	sanitize_boot_params(bp);
 	boot_params_ptr = bp;
 
 	/*

From aa3942d4d12ef57f031faa2772fe410c24191e36 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Thu, 6 Mar 2025 15:52:11 +0100
Subject: [PATCH 1075/1173] x86/kexec: Merge x86_32 and x86_64 code using
 macros from <asm/asm.h>

Merge common x86_32 and x86_64 code in crash_setup_regs()
using macros from <asm/asm.h>.

The compiled object files before and after the patch are unchanged.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: David Woodhouse <dwmw@amazon.co.uk>
Cc: Baoquan He <bhe@redhat.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Dave Young <dyoung@redhat.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Link: https://lore.kernel.org/r/20250306145227.55819-1-ubizjak@gmail.com
---
 arch/x86/include/asm/kexec.h | 58 ++++++++++++++++--------------------
 1 file changed, 25 insertions(+), 33 deletions(-)

diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index 8ad187462b68e..e3589d6aec24f 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -18,6 +18,7 @@
 #include <linux/string.h>
 #include <linux/kernel.h>
 
+#include <asm/asm.h>
 #include <asm/page.h>
 #include <asm/ptrace.h>
 
@@ -71,41 +72,32 @@ static inline void crash_setup_regs(struct pt_regs *newregs,
 	if (oldregs) {
 		memcpy(newregs, oldregs, sizeof(*newregs));
 	} else {
+		asm volatile("mov %%" _ASM_BX ",%0" : "=m"(newregs->bx));
+		asm volatile("mov %%" _ASM_CX ",%0" : "=m"(newregs->cx));
+		asm volatile("mov %%" _ASM_DX ",%0" : "=m"(newregs->dx));
+		asm volatile("mov %%" _ASM_SI ",%0" : "=m"(newregs->si));
+		asm volatile("mov %%" _ASM_DI ",%0" : "=m"(newregs->di));
+		asm volatile("mov %%" _ASM_BP ",%0" : "=m"(newregs->bp));
+		asm volatile("mov %%" _ASM_AX ",%0" : "=m"(newregs->ax));
+		asm volatile("mov %%" _ASM_SP ",%0" : "=m"(newregs->sp));
+#ifdef CONFIG_X86_64
+		asm volatile("mov %%r8,%0" : "=m"(newregs->r8));
+		asm volatile("mov %%r9,%0" : "=m"(newregs->r9));
+		asm volatile("mov %%r10,%0" : "=m"(newregs->r10));
+		asm volatile("mov %%r11,%0" : "=m"(newregs->r11));
+		asm volatile("mov %%r12,%0" : "=m"(newregs->r12));
+		asm volatile("mov %%r13,%0" : "=m"(newregs->r13));
+		asm volatile("mov %%r14,%0" : "=m"(newregs->r14));
+		asm volatile("mov %%r15,%0" : "=m"(newregs->r15));
+#endif
+		asm volatile("mov %%ss,%k0" : "=a"(newregs->ss));
+		asm volatile("mov %%cs,%k0" : "=a"(newregs->cs));
 #ifdef CONFIG_X86_32
-		asm volatile("movl %%ebx,%0" : "=m"(newregs->bx));
-		asm volatile("movl %%ecx,%0" : "=m"(newregs->cx));
-		asm volatile("movl %%edx,%0" : "=m"(newregs->dx));
-		asm volatile("movl %%esi,%0" : "=m"(newregs->si));
-		asm volatile("movl %%edi,%0" : "=m"(newregs->di));
-		asm volatile("movl %%ebp,%0" : "=m"(newregs->bp));
-		asm volatile("movl %%eax,%0" : "=m"(newregs->ax));
-		asm volatile("movl %%esp,%0" : "=m"(newregs->sp));
-		asm volatile("movl %%ss, %%eax;" :"=a"(newregs->ss));
-		asm volatile("movl %%cs, %%eax;" :"=a"(newregs->cs));
-		asm volatile("movl %%ds, %%eax;" :"=a"(newregs->ds));
-		asm volatile("movl %%es, %%eax;" :"=a"(newregs->es));
-		asm volatile("pushfl; popl %0" :"=m"(newregs->flags));
-#else
-		asm volatile("movq %%rbx,%0" : "=m"(newregs->bx));
-		asm volatile("movq %%rcx,%0" : "=m"(newregs->cx));
-		asm volatile("movq %%rdx,%0" : "=m"(newregs->dx));
-		asm volatile("movq %%rsi,%0" : "=m"(newregs->si));
-		asm volatile("movq %%rdi,%0" : "=m"(newregs->di));
-		asm volatile("movq %%rbp,%0" : "=m"(newregs->bp));
-		asm volatile("movq %%rax,%0" : "=m"(newregs->ax));
-		asm volatile("movq %%rsp,%0" : "=m"(newregs->sp));
-		asm volatile("movq %%r8,%0" : "=m"(newregs->r8));
-		asm volatile("movq %%r9,%0" : "=m"(newregs->r9));
-		asm volatile("movq %%r10,%0" : "=m"(newregs->r10));
-		asm volatile("movq %%r11,%0" : "=m"(newregs->r11));
-		asm volatile("movq %%r12,%0" : "=m"(newregs->r12));
-		asm volatile("movq %%r13,%0" : "=m"(newregs->r13));
-		asm volatile("movq %%r14,%0" : "=m"(newregs->r14));
-		asm volatile("movq %%r15,%0" : "=m"(newregs->r15));
-		asm volatile("movl %%ss, %%eax;" :"=a"(newregs->ss));
-		asm volatile("movl %%cs, %%eax;" :"=a"(newregs->cs));
-		asm volatile("pushfq; popq %0" :"=m"(newregs->flags));
+		asm volatile("mov %%ds,%k0" : "=a"(newregs->ds));
+		asm volatile("mov %%es,%k0" : "=a"(newregs->es));
 #endif
+		asm volatile("pushf\n\t"
+			     "pop %0" : "=m"(newregs->flags));
 		newregs->ip = _THIS_IP_;
 	}
 }

From fd881d0a085fc54354414aed990ccf05f282ba53 Mon Sep 17 00:00:00 2001
From: Michael Jeanson <mjeanson@efficios.com>
Date: Thu, 6 Mar 2025 16:12:21 -0500
Subject: [PATCH 1076/1173] rseq: Fix segfault on registration when rseq_cs is
 non-zero

The rseq_cs field is documented as being set to 0 by user-space prior to
registration, however this is not currently enforced by the kernel. This
can result in a segfault on return to user-space if the value stored in
the rseq_cs field doesn't point to a valid struct rseq_cs.

The correct solution to this would be to fail the rseq registration when
the rseq_cs field is non-zero. However, some older versions of glibc
will reuse the rseq area of previous threads without clearing the
rseq_cs field and will also terminate the process if the rseq
registration fails in a secondary thread. This wasn't caught in testing
because in this case the leftover rseq_cs does point to a valid struct
rseq_cs.

What we can do is clear the rseq_cs field on registration when it's
non-zero which will prevent segfaults on registration and won't break
the glibc versions that reuse rseq areas on thread creation.

Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250306211223.109455-1-mjeanson@efficios.com
---
 kernel/rseq.c | 60 ++++++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 48 insertions(+), 12 deletions(-)

diff --git a/kernel/rseq.c b/kernel/rseq.c
index a7d81229eda04..b7a1ec327e811 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -236,6 +236,29 @@ static int rseq_reset_rseq_cpu_node_id(struct task_struct *t)
 	return -EFAULT;
 }
 
+/*
+ * Get the user-space pointer value stored in the 'rseq_cs' field.
+ */
+static int rseq_get_rseq_cs_ptr_val(struct rseq __user *rseq, u64 *rseq_cs)
+{
+	if (!rseq_cs)
+		return -EFAULT;
+
+#ifdef CONFIG_64BIT
+	if (get_user(*rseq_cs, &rseq->rseq_cs))
+		return -EFAULT;
+#else
+	if (copy_from_user(rseq_cs, &rseq->rseq_cs, sizeof(*rseq_cs)))
+		return -EFAULT;
+#endif
+
+	return 0;
+}
+
+/*
+ * If the rseq_cs field of 'struct rseq' contains a valid pointer to
+ * user-space, copy 'struct rseq_cs' from user-space and validate its fields.
+ */
 static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs)
 {
 	struct rseq_cs __user *urseq_cs;
@@ -244,17 +267,16 @@ static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs)
 	u32 sig;
 	int ret;
 
-#ifdef CONFIG_64BIT
-	if (get_user(ptr, &t->rseq->rseq_cs))
-		return -EFAULT;
-#else
-	if (copy_from_user(&ptr, &t->rseq->rseq_cs, sizeof(ptr)))
-		return -EFAULT;
-#endif
+	ret = rseq_get_rseq_cs_ptr_val(t->rseq, &ptr);
+	if (ret)
+		return ret;
+
+	/* If the rseq_cs pointer is NULL, return a cleared struct rseq_cs. */
 	if (!ptr) {
 		memset(rseq_cs, 0, sizeof(*rseq_cs));
 		return 0;
 	}
+	/* Check that the pointer value fits in the user-space process space. */
 	if (ptr >= TASK_SIZE)
 		return -EINVAL;
 	urseq_cs = (struct rseq_cs __user *)(unsigned long)ptr;
@@ -330,7 +352,7 @@ static int rseq_need_restart(struct task_struct *t, u32 cs_flags)
 	return !!event_mask;
 }
 
-static int clear_rseq_cs(struct task_struct *t)
+static int clear_rseq_cs(struct rseq __user *rseq)
 {
 	/*
 	 * The rseq_cs field is set to NULL on preemption or signal
@@ -341,9 +363,9 @@ static int clear_rseq_cs(struct task_struct *t)
 	 * Set rseq_cs to NULL.
 	 */
 #ifdef CONFIG_64BIT
-	return put_user(0UL, &t->rseq->rseq_cs);
+	return put_user(0UL, &rseq->rseq_cs);
 #else
-	if (clear_user(&t->rseq->rseq_cs, sizeof(t->rseq->rseq_cs)))
+	if (clear_user(&rseq->rseq_cs, sizeof(rseq->rseq_cs)))
 		return -EFAULT;
 	return 0;
 #endif
@@ -375,11 +397,11 @@ static int rseq_ip_fixup(struct pt_regs *regs)
 	 * Clear the rseq_cs pointer and return.
 	 */
 	if (!in_rseq_cs(ip, &rseq_cs))
-		return clear_rseq_cs(t);
+		return clear_rseq_cs(t->rseq);
 	ret = rseq_need_restart(t, rseq_cs.flags);
 	if (ret <= 0)
 		return ret;
-	ret = clear_rseq_cs(t);
+	ret = clear_rseq_cs(t->rseq);
 	if (ret)
 		return ret;
 	trace_rseq_ip_fixup(ip, rseq_cs.start_ip, rseq_cs.post_commit_offset,
@@ -453,6 +475,7 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len,
 		int, flags, u32, sig)
 {
 	int ret;
+	u64 rseq_cs;
 
 	if (flags & RSEQ_FLAG_UNREGISTER) {
 		if (flags & ~RSEQ_FLAG_UNREGISTER)
@@ -507,6 +530,19 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len,
 		return -EINVAL;
 	if (!access_ok(rseq, rseq_len))
 		return -EFAULT;
+
+	/*
+	 * If the rseq_cs pointer is non-NULL on registration, clear it to
+	 * avoid a potential segfault on return to user-space. The proper thing
+	 * to do would have been to fail the registration but this would break
+	 * older libcs that reuse the rseq area for new threads without
+	 * clearing the fields.
+	 */
+	if (rseq_get_rseq_cs_ptr_val(rseq, &rseq_cs))
+	        return -EFAULT;
+	if (rseq_cs && clear_rseq_cs(rseq))
+		return -EFAULT;
+
 #ifdef CONFIG_DEBUG_RSEQ
 	/*
 	 * Initialize the in-kernel rseq fields copy for validation of

From 7a310c644cf571fbdb1d447a1dc39cf048634589 Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Thu, 6 Mar 2025 13:11:02 +0800
Subject: [PATCH 1077/1173] perf/x86/intel/bts: Check if bts_ctx is allocated
 when calling BTS functions

bts_ctx might not be allocated, for example if the CPU has X86_FEATURE_PTI,
but intel_bts_disable/enable_local() and intel_bts_interrupt() are called
unconditionally from intel_pmu_handle_irq() and crash on bts_ctx.

So check if bts_ctx is allocated when calling BTS functions.

Fixes: 3acfcefa795c ("perf/x86/intel/bts: Allocate bts_ctx only if necessary")
Reported-by: Jiri Olsa <olsajiri@gmail.com>
Tested-by: Jiri Olsa <jolsa@kernel.org>
Suggested-by: Adrian Hunter <adrian.hunter@intel.com>
Suggested-by: Dave Hansen <dave.hansen@intel.com>
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250306051102.2642-1-lirongqing@baidu.com
---
 arch/x86/events/intel/bts.c | 25 ++++++++++++++++++++-----
 1 file changed, 20 insertions(+), 5 deletions(-)

diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index 953868da82fb4..39a987d5eb6e0 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -338,9 +338,14 @@ static void bts_event_stop(struct perf_event *event, int flags)
 
 void intel_bts_enable_local(void)
 {
-	struct bts_ctx *bts = this_cpu_ptr(bts_ctx);
-	int state = READ_ONCE(bts->state);
+	struct bts_ctx *bts;
+	int state;
 
+	if (!bts_ctx)
+		return;
+
+	bts = this_cpu_ptr(bts_ctx);
+	state = READ_ONCE(bts->state);
 	/*
 	 * Here we transition from INACTIVE to ACTIVE;
 	 * if we instead are STOPPED from the interrupt handler,
@@ -358,7 +363,12 @@ void intel_bts_enable_local(void)
 
 void intel_bts_disable_local(void)
 {
-	struct bts_ctx *bts = this_cpu_ptr(bts_ctx);
+	struct bts_ctx *bts;
+
+	if (!bts_ctx)
+		return;
+
+	bts = this_cpu_ptr(bts_ctx);
 
 	/*
 	 * Here we transition from ACTIVE to INACTIVE;
@@ -450,12 +460,17 @@ bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle)
 int intel_bts_interrupt(void)
 {
 	struct debug_store *ds = this_cpu_ptr(&cpu_hw_events)->ds;
-	struct bts_ctx *bts = this_cpu_ptr(bts_ctx);
-	struct perf_event *event = bts->handle.event;
+	struct bts_ctx *bts;
+	struct perf_event *event;
 	struct bts_buffer *buf;
 	s64 old_head;
 	int err = -ENOSPC, handled = 0;
 
+	if (!bts_ctx)
+		return 0;
+
+	bts = this_cpu_ptr(bts_ctx);
+	event = bts->handle.event;
 	/*
 	 * The only surefire way of knowing if this NMI is ours is by checking
 	 * the write ptr against the PMI threshold.

From 33255c161ac4be003ac87c434ebc49645d18a929 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Fri, 28 Feb 2025 20:07:58 -0500
Subject: [PATCH 1078/1173] bcachefs: Fix bch2_dev_journal_alloc() spuriously
 failing

Previously, we fixed journal resize spuriousl failing with
-BCH_ERR_open_buckets_empty, but initial journal allocation was missed
because it didn't invoke the "block on allocator" loop at all.

Factor out the "loop on allocator" code to fix that.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/journal.c | 59 +++++++++++++++++++++++--------------------
 1 file changed, 32 insertions(+), 27 deletions(-)

diff --git a/fs/bcachefs/journal.c b/fs/bcachefs/journal.c
index 5dabbf3c0965c..05b1250619ecc 100644
--- a/fs/bcachefs/journal.c
+++ b/fs/bcachefs/journal.c
@@ -1021,8 +1021,8 @@ struct journal_buf *bch2_next_write_buffer_flush_journal_buf(struct journal *j,
 
 /* allocate journal on a device: */
 
-static int __bch2_set_nr_journal_buckets(struct bch_dev *ca, unsigned nr,
-					 bool new_fs, struct closure *cl)
+static int bch2_set_nr_journal_buckets_iter(struct bch_dev *ca, unsigned nr,
+					    bool new_fs, struct closure *cl)
 {
 	struct bch_fs *c = ca->fs;
 	struct journal_device *ja = &ca->journal;
@@ -1150,26 +1150,20 @@ static int __bch2_set_nr_journal_buckets(struct bch_dev *ca, unsigned nr,
 	return ret;
 }
 
-/*
- * Allocate more journal space at runtime - not currently making use if it, but
- * the code works:
- */
-int bch2_set_nr_journal_buckets(struct bch_fs *c, struct bch_dev *ca,
-				unsigned nr)
+static int bch2_set_nr_journal_buckets_loop(struct bch_fs *c, struct bch_dev *ca,
+					    unsigned nr, bool new_fs)
 {
 	struct journal_device *ja = &ca->journal;
-	struct closure cl;
 	int ret = 0;
 
+	struct closure cl;
 	closure_init_stack(&cl);
 
-	down_write(&c->state_lock);
-
 	/* don't handle reducing nr of buckets yet: */
 	if (nr < ja->nr)
-		goto unlock;
+		return 0;
 
-	while (ja->nr < nr) {
+	while (!ret && ja->nr < nr) {
 		struct disk_reservation disk_res = { 0, 0, 0 };
 
 		/*
@@ -1182,27 +1176,38 @@ int bch2_set_nr_journal_buckets(struct bch_fs *c, struct bch_dev *ca,
 		 * filesystem-wide allocation will succeed, this is a device
 		 * specific allocation - we can hang here:
 		 */
+		if (!new_fs) {
+			ret = bch2_disk_reservation_get(c, &disk_res,
+							bucket_to_sector(ca, nr - ja->nr), 1, 0);
+			if (ret)
+				break;
+		}
 
-		ret = bch2_disk_reservation_get(c, &disk_res,
-						bucket_to_sector(ca, nr - ja->nr), 1, 0);
-		if (ret)
-			break;
+		ret = bch2_set_nr_journal_buckets_iter(ca, nr, new_fs, &cl);
 
-		ret = __bch2_set_nr_journal_buckets(ca, nr, false, &cl);
+		if (ret == -BCH_ERR_bucket_alloc_blocked ||
+		    ret == -BCH_ERR_open_buckets_empty)
+			ret = 0; /* wait and retry */
 
 		bch2_disk_reservation_put(c, &disk_res);
-
 		closure_sync(&cl);
-
-		if (ret &&
-		    ret != -BCH_ERR_bucket_alloc_blocked &&
-		    ret != -BCH_ERR_open_buckets_empty)
-			break;
 	}
 
-	bch_err_fn(c, ret);
-unlock:
+	return ret;
+}
+
+/*
+ * Allocate more journal space at runtime - not currently making use if it, but
+ * the code works:
+ */
+int bch2_set_nr_journal_buckets(struct bch_fs *c, struct bch_dev *ca,
+				unsigned nr)
+{
+	down_write(&c->state_lock);
+	int ret = bch2_set_nr_journal_buckets_loop(c, ca, nr, false);
 	up_write(&c->state_lock);
+
+	bch_err_fn(c, ret);
 	return ret;
 }
 
@@ -1228,7 +1233,7 @@ int bch2_dev_journal_alloc(struct bch_dev *ca, bool new_fs)
 		     min(1 << 13,
 			 (1 << 24) / ca->mi.bucket_size));
 
-	ret = __bch2_set_nr_journal_buckets(ca, nr, new_fs, NULL);
+	ret = bch2_set_nr_journal_buckets_loop(ca->fs, ca, nr, new_fs);
 err:
 	bch_err_fn(ca, ret);
 	return ret;

From 8ba73f53dc5b7545776e09e6982115dcbcbabec4 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Fri, 28 Feb 2025 11:34:41 -0500
Subject: [PATCH 1079/1173] bcachefs: copygc now skips non-rw devices

There's no point in doing copygc on non-rw devices: the fragmentation
doesn't matter if we're not writing to them, and we may not have
anywhere to put the data on our other devices.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/movinggc.c | 25 ++++++++++++-------------
 1 file changed, 12 insertions(+), 13 deletions(-)

diff --git a/fs/bcachefs/movinggc.c b/fs/bcachefs/movinggc.c
index 21805509ab9e6..6718dc37c5a35 100644
--- a/fs/bcachefs/movinggc.c
+++ b/fs/bcachefs/movinggc.c
@@ -74,20 +74,14 @@ static int bch2_bucket_is_movable(struct btree_trans *trans,
 				  struct move_bucket *b, u64 time)
 {
 	struct bch_fs *c = trans->c;
-	struct btree_iter iter;
-	struct bkey_s_c k;
-	struct bch_alloc_v4 _a;
-	const struct bch_alloc_v4 *a;
-	int ret;
 
-	if (bch2_bucket_is_open(trans->c,
-				b->k.bucket.inode,
-				b->k.bucket.offset))
+	if (bch2_bucket_is_open(c, b->k.bucket.inode, b->k.bucket.offset))
 		return 0;
 
-	k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_alloc,
-			       b->k.bucket, BTREE_ITER_cached);
-	ret = bkey_err(k);
+	struct btree_iter iter;
+	struct bkey_s_c k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_alloc,
+				       b->k.bucket, BTREE_ITER_cached);
+	int ret = bkey_err(k);
 	if (ret)
 		return ret;
 
@@ -95,13 +89,18 @@ static int bch2_bucket_is_movable(struct btree_trans *trans,
 	if (!ca)
 		goto out;
 
-	a = bch2_alloc_to_v4(k, &_a);
+	if (ca->mi.state != BCH_MEMBER_STATE_rw ||
+	    !bch2_dev_is_online(ca))
+		goto out_put;
+
+	struct bch_alloc_v4 _a;
+	const struct bch_alloc_v4 *a = bch2_alloc_to_v4(k, &_a);
 	b->k.gen	= a->gen;
 	b->sectors	= bch2_bucket_sectors_dirty(*a);
 	u64 lru_idx	= alloc_lru_idx_fragmentation(*a, ca);
 
 	ret = lru_idx && lru_idx <= time;
-
+out_put:
 	bch2_dev_put(ca);
 out:
 	bch2_trans_iter_exit(trans, &iter);

From e7112524e5e885181cc5ae4d258f33b9dbe0b907 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 6 Mar 2025 08:27:51 -0800
Subject: [PATCH 1080/1173] block: Name the RQF flags enum

Commit 5f89154e8e9e3445f9b59 ("block: Use enum to define RQF_x bit
indexes") converted the RQF flags to an anonymous enum, which was
a beneficial change. This patch goes one step further by naming the enum
as "rqf_flags".

This naming enables exporting these flags to BPF clients, eliminating
the need to duplicate these flags in BPF code. Instead, BPF clients can
now access the same kernel-side values through CO:RE (Compile Once, Run
Everywhere), as shown in this example:

    rqf_stats = bpf_core_enum_value(enum rqf_flags, __RQF_STATS)

Suggested-by: Yonghong Song <yonghong.song@linux.dev>
Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://lore.kernel.org/r/20250306-rqf_flags-v1-1-bbd64918b406@debian.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blk-mq.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index fa2a76cc2f73d..71f4f0cc3dac6 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -28,7 +28,7 @@ typedef enum rq_end_io_ret (rq_end_io_fn)(struct request *, blk_status_t);
 typedef __u32 __bitwise req_flags_t;
 
 /* Keep rqf_name[] in sync with the definitions below */
-enum {
+enum rqf_flags {
 	/* drive already may have started this one */
 	__RQF_STARTED,
 	/* request for flush sequence */

From 00a7d39898c8010bfd5ff62af31ca5db34421b38 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Thu, 6 Mar 2025 18:25:35 -1000
Subject: [PATCH 1081/1173] fs/pipe: add simpler helpers for common cases

The fix to atomically read the pipe head and tail state when not holding
the pipe mutex has caused a number of headaches due to the size change
of the involved types.

It turns out that we don't have _that_ many places that access these
fields directly and were affected, but we have more than we strictly
should have, because our low-level helper functions have been designed
to have intimate knowledge of how the pipes work.

And as a result, that random noise of direct 'pipe->head' and
'pipe->tail' accesses makes it harder to pinpoint any actual potential
problem spots remaining.

For example, we didn't have a "is the pipe full" helper function, but
instead had a "given these pipe buffer indexes and this pipe size, is
the pipe full".  That's because some low-level pipe code does actually
want that much more complicated interface.

But most other places literally just want a "is the pipe full" helper,
and not having it meant that those places ended up being unnecessarily
much too aware of this all.

It would have been much better if only the very core pipe code that
cared had been the one aware of this all.

So let's fix it - better late than never.  This just introduces the
trivial wrappers for "is this pipe full or empty" and to get how many
pipe buffers are used, so that instead of writing

        if (pipe_full(pipe->head, pipe->tail, pipe->max_usage))

the places that literally just want to know if a pipe is full can just
say

        if (pipe_is_full(pipe))

instead.  The existing trivial cases were converted with a 'sed' script.

This cuts down on the places that access pipe->head and pipe->tail
directly outside of the pipe code (and core splice code) quite a lot.

The splice code in particular still revels in doing the direct low-level
accesses, and the fuse fuse_dev_splice_write() code also seems a bit
unnecessarily eager to go very low-level, but it's at least a bit better
than it used to be.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/char/virtio_console.c |  4 ++--
 fs/fuse/dev.c                 |  2 +-
 fs/pipe.c                     |  6 +++---
 fs/splice.c                   | 20 ++++++++++----------
 include/linux/pipe_fs_i.h     | 27 +++++++++++++++++++++++++++
 mm/filemap.c                  |  7 +++----
 mm/shmem.c                    |  6 +++---
 7 files changed, 49 insertions(+), 23 deletions(-)

diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 24442485e73e7..18f92dd44d456 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -923,14 +923,14 @@ static ssize_t port_fops_splice_write(struct pipe_inode_info *pipe,
 
 	pipe_lock(pipe);
 	ret = 0;
-	if (pipe_empty(pipe->head, pipe->tail))
+	if (pipe_is_empty(pipe))
 		goto error_out;
 
 	ret = wait_port_writable(port, filp->f_flags & O_NONBLOCK);
 	if (ret < 0)
 		goto error_out;
 
-	occupancy = pipe_occupancy(pipe->head, pipe->tail);
+	occupancy = pipe_buf_usage(pipe);
 	buf = alloc_buf(port->portdev->vdev, 0, occupancy);
 
 	if (!buf) {
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 3c9caafca9e29..2c3a4d09e500f 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -1457,7 +1457,7 @@ static ssize_t fuse_dev_splice_read(struct file *in, loff_t *ppos,
 	if (ret < 0)
 		goto out;
 
-	if (pipe_occupancy(pipe->head, pipe->tail) + cs.nr_segs > pipe->max_usage) {
+	if (pipe_buf_usage(pipe) + cs.nr_segs > pipe->max_usage) {
 		ret = -EIO;
 		goto out;
 	}
diff --git a/fs/pipe.c b/fs/pipe.c
index 5c872775a6db9..4d0799e4e7196 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -394,7 +394,7 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to)
 		wake_next_reader = true;
 		mutex_lock(&pipe->mutex);
 	}
-	if (pipe_empty(pipe->head, pipe->tail))
+	if (pipe_is_empty(pipe))
 		wake_next_reader = false;
 	mutex_unlock(&pipe->mutex);
 
@@ -577,11 +577,11 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from)
 		kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
 		wait_event_interruptible_exclusive(pipe->wr_wait, pipe_writable(pipe));
 		mutex_lock(&pipe->mutex);
-		was_empty = pipe_empty(pipe->head, pipe->tail);
+		was_empty = pipe_is_empty(pipe);
 		wake_next_writer = true;
 	}
 out:
-	if (pipe_full(pipe->head, pipe->tail, pipe->max_usage))
+	if (pipe_is_full(pipe))
 		wake_next_writer = false;
 	mutex_unlock(&pipe->mutex);
 
diff --git a/fs/splice.c b/fs/splice.c
index 28cfa63aa2364..23fa5561b9441 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -331,7 +331,7 @@ ssize_t copy_splice_read(struct file *in, loff_t *ppos,
 	int i;
 
 	/* Work out how much data we can actually add into the pipe */
-	used = pipe_occupancy(pipe->head, pipe->tail);
+	used = pipe_buf_usage(pipe);
 	npages = max_t(ssize_t, pipe->max_usage - used, 0);
 	len = min_t(size_t, len, npages * PAGE_SIZE);
 	npages = DIV_ROUND_UP(len, PAGE_SIZE);
@@ -527,7 +527,7 @@ static int splice_from_pipe_next(struct pipe_inode_info *pipe, struct splice_des
 		return -ERESTARTSYS;
 
 repeat:
-	while (pipe_empty(pipe->head, pipe->tail)) {
+	while (pipe_is_empty(pipe)) {
 		if (!pipe->writers)
 			return 0;
 
@@ -820,7 +820,7 @@ ssize_t splice_to_socket(struct pipe_inode_info *pipe, struct file *out,
 		if (signal_pending(current))
 			break;
 
-		while (pipe_empty(pipe->head, pipe->tail)) {
+		while (pipe_is_empty(pipe)) {
 			ret = 0;
 			if (!pipe->writers)
 				goto out;
@@ -968,7 +968,7 @@ static ssize_t do_splice_read(struct file *in, loff_t *ppos,
 		return 0;
 
 	/* Don't try to read more the pipe has space for. */
-	p_space = pipe->max_usage - pipe_occupancy(pipe->head, pipe->tail);
+	p_space = pipe->max_usage - pipe_buf_usage(pipe);
 	len = min_t(size_t, len, p_space << PAGE_SHIFT);
 
 	if (unlikely(len > MAX_RW_COUNT))
@@ -1080,7 +1080,7 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd,
 	more = sd->flags & SPLICE_F_MORE;
 	sd->flags |= SPLICE_F_MORE;
 
-	WARN_ON_ONCE(!pipe_empty(pipe->head, pipe->tail));
+	WARN_ON_ONCE(!pipe_is_empty(pipe));
 
 	while (len) {
 		size_t read_len;
@@ -1268,7 +1268,7 @@ static int wait_for_space(struct pipe_inode_info *pipe, unsigned flags)
 			send_sig(SIGPIPE, current, 0);
 			return -EPIPE;
 		}
-		if (!pipe_full(pipe->head, pipe->tail, pipe->max_usage))
+		if (!pipe_is_full(pipe))
 			return 0;
 		if (flags & SPLICE_F_NONBLOCK)
 			return -EAGAIN;
@@ -1652,13 +1652,13 @@ static int ipipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
 	 * Check the pipe occupancy without the inode lock first. This function
 	 * is speculative anyways, so missing one is ok.
 	 */
-	if (!pipe_empty(pipe->head, pipe->tail))
+	if (!pipe_is_empty(pipe))
 		return 0;
 
 	ret = 0;
 	pipe_lock(pipe);
 
-	while (pipe_empty(pipe->head, pipe->tail)) {
+	while (pipe_is_empty(pipe)) {
 		if (signal_pending(current)) {
 			ret = -ERESTARTSYS;
 			break;
@@ -1688,13 +1688,13 @@ static int opipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
 	 * Check pipe occupancy without the inode lock first. This function
 	 * is speculative anyways, so missing one is ok.
 	 */
-	if (!pipe_full(pipe->head, pipe->tail, pipe->max_usage))
+	if (!pipe_is_full(pipe))
 		return 0;
 
 	ret = 0;
 	pipe_lock(pipe);
 
-	while (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) {
+	while (pipe_is_full(pipe)) {
 		if (!pipe->readers) {
 			send_sig(SIGPIPE, current, 0);
 			ret = -EPIPE;
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index 4d0a2267e6efc..b698758000f8b 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -208,6 +208,33 @@ static inline bool pipe_full(unsigned int head, unsigned int tail,
 	return pipe_occupancy(head, tail) >= limit;
 }
 
+/**
+ * pipe_is_full - Return true if the pipe is full
+ * @pipe: the pipe
+ */
+static inline bool pipe_is_full(const struct pipe_inode_info *pipe)
+{
+	return pipe_full(pipe->head, pipe->tail, pipe->max_usage);
+}
+
+/**
+ * pipe_is_empty - Return true if the pipe is empty
+ * @pipe: the pipe
+ */
+static inline bool pipe_is_empty(const struct pipe_inode_info *pipe)
+{
+	return pipe_empty(pipe->head, pipe->tail);
+}
+
+/**
+ * pipe_buf_usage - Return how many pipe buffers are in use
+ * @pipe: the pipe
+ */
+static inline unsigned int pipe_buf_usage(const struct pipe_inode_info *pipe)
+{
+	return pipe_occupancy(pipe->head, pipe->tail);
+}
+
 /**
  * pipe_buf - Return the pipe buffer for the specified slot in the pipe ring
  * @pipe: The pipe to access
diff --git a/mm/filemap.c b/mm/filemap.c
index d4564a79eb353..2974691fdfad2 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2897,8 +2897,7 @@ size_t splice_folio_into_pipe(struct pipe_inode_info *pipe,
 	size = min(size, folio_size(folio) - offset);
 	offset %= PAGE_SIZE;
 
-	while (spliced < size &&
-	       !pipe_full(pipe->head, pipe->tail, pipe->max_usage)) {
+	while (spliced < size && !pipe_is_full(pipe)) {
 		struct pipe_buffer *buf = pipe_head_buf(pipe);
 		size_t part = min_t(size_t, PAGE_SIZE - offset, size - spliced);
 
@@ -2955,7 +2954,7 @@ ssize_t filemap_splice_read(struct file *in, loff_t *ppos,
 	iocb.ki_pos = *ppos;
 
 	/* Work out how much data we can actually add into the pipe */
-	used = pipe_occupancy(pipe->head, pipe->tail);
+	used = pipe_buf_usage(pipe);
 	npages = max_t(ssize_t, pipe->max_usage - used, 0);
 	len = min_t(size_t, len, npages * PAGE_SIZE);
 
@@ -3015,7 +3014,7 @@ ssize_t filemap_splice_read(struct file *in, loff_t *ppos,
 			total_spliced += n;
 			*ppos += n;
 			in->f_ra.prev_pos = *ppos;
-			if (pipe_full(pipe->head, pipe->tail, pipe->max_usage))
+			if (pipe_is_full(pipe))
 				goto out;
 		}
 
diff --git a/mm/shmem.c b/mm/shmem.c
index 4ea6109a80431..20032a333d80c 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3487,7 +3487,7 @@ static size_t splice_zeropage_into_pipe(struct pipe_inode_info *pipe,
 
 	size = min_t(size_t, size, PAGE_SIZE - offset);
 
-	if (!pipe_full(pipe->head, pipe->tail, pipe->max_usage)) {
+	if (!pipe_is_full(pipe)) {
 		struct pipe_buffer *buf = pipe_head_buf(pipe);
 
 		*buf = (struct pipe_buffer) {
@@ -3514,7 +3514,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
 	int error = 0;
 
 	/* Work out how much data we can actually add into the pipe */
-	used = pipe_occupancy(pipe->head, pipe->tail);
+	used = pipe_buf_usage(pipe);
 	npages = max_t(ssize_t, pipe->max_usage - used, 0);
 	len = min_t(size_t, len, npages * PAGE_SIZE);
 
@@ -3601,7 +3601,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
 		total_spliced += n;
 		*ppos += n;
 		in->f_ra.prev_pos = *ppos;
-		if (pipe_full(pipe->head, pipe->tail, pipe->max_usage))
+		if (pipe_is_full(pipe))
 			break;
 
 		cond_resched();

From be494a35683e1cbba58395eacb00d4b5cd4e23a3 Mon Sep 17 00:00:00 2001
From: Andre Przywara <andre.przywara@arm.com>
Date: Fri, 7 Mar 2025 00:57:02 +0000
Subject: [PATCH 1082/1173] dt-bindings: irq: sun7i-nmi: Document the Allwinner
 A523 NMI controller

The Allwinner A523 SoC contains an NMI controller very close to the one
used in the recent Allwinner SoCs, but it adds another bit that needs to
be toggled to actually deliver the IRQs. Sigh.

Add the A523 specific name to the list of allowed compatible strings.

Signed-off-by: Andre Przywara <andre.przywara@arm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://lore.kernel.org/all/20250307005712.16828-6-andre.przywara@arm.com
---
 .../interrupt-controller/allwinner,sun7i-a20-sc-nmi.yaml         | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/interrupt-controller/allwinner,sun7i-a20-sc-nmi.yaml b/Documentation/devicetree/bindings/interrupt-controller/allwinner,sun7i-a20-sc-nmi.yaml
index f49b43f45f3d9..06e3621a8c06c 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/allwinner,sun7i-a20-sc-nmi.yaml
+++ b/Documentation/devicetree/bindings/interrupt-controller/allwinner,sun7i-a20-sc-nmi.yaml
@@ -26,6 +26,7 @@ properties:
         deprecated: true
       - const: allwinner,sun7i-a20-sc-nmi
       - const: allwinner,sun9i-a80-nmi
+      - const: allwinner,sun55i-a523-nmi
       - items:
           - enum:
               - allwinner,sun8i-v3s-nmi

From 922ac17c7b47fd0345690046a396f7e324dc733e Mon Sep 17 00:00:00 2001
From: Andre Przywara <andre.przywara@arm.com>
Date: Fri, 7 Mar 2025 00:57:03 +0000
Subject: [PATCH 1083/1173] irqchip/sunxi-nmi: Support Allwinner A523 NMI
 controller

The NMI controller in the Allwinner A523 is almost compatible to the
previous versions of this IP, but requires the extra bit 31 to be set in
the enable register to actually report the NMI.

Add a mask to allow such an enable bit to be specified, and add this to
the per-SoC data structure. As this struct was just for different register
offsets so far, it was consequently named "reg_offs", which is now no
longer applicable, so rename this to the more generic "data" on the way,
and move the existing offsets into a struct of its own.

Also add the respective Allwinner A523 compatible string, and set bit 31
in its enable mask, to add support for this SoC.

[ tglx: Mop up some coding style along with it ]

Signed-off-by: Andre Przywara <andre.przywara@arm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250307005712.16828-7-andre.przywara@arm.com
---
 drivers/irqchip/irq-sunxi-nmi.c | 85 +++++++++++++++++++--------------
 1 file changed, 50 insertions(+), 35 deletions(-)

diff --git a/drivers/irqchip/irq-sunxi-nmi.c b/drivers/irqchip/irq-sunxi-nmi.c
index 0b43121520243..01b0d83217285 100644
--- a/drivers/irqchip/irq-sunxi-nmi.c
+++ b/drivers/irqchip/irq-sunxi-nmi.c
@@ -48,32 +48,41 @@ enum {
 	SUNXI_SRC_TYPE_EDGE_RISING,
 };
 
-struct sunxi_sc_nmi_reg_offs {
-	u32 ctrl;
-	u32 pend;
-	u32 enable;
+struct sunxi_sc_nmi_data {
+	struct {
+		u32	ctrl;
+		u32	pend;
+		u32	enable;
+	} reg_offs;
+	u32		enable_val;
 };
 
-static const struct sunxi_sc_nmi_reg_offs sun6i_reg_offs __initconst = {
-	.ctrl	= SUN6I_NMI_CTRL,
-	.pend	= SUN6I_NMI_PENDING,
-	.enable	= SUN6I_NMI_ENABLE,
+static const struct sunxi_sc_nmi_data sun6i_data __initconst = {
+	.reg_offs.ctrl		= SUN6I_NMI_CTRL,
+	.reg_offs.pend		= SUN6I_NMI_PENDING,
+	.reg_offs.enable	= SUN6I_NMI_ENABLE,
 };
 
-static const struct sunxi_sc_nmi_reg_offs sun7i_reg_offs __initconst = {
-	.ctrl	= SUN7I_NMI_CTRL,
-	.pend	= SUN7I_NMI_PENDING,
-	.enable	= SUN7I_NMI_ENABLE,
+static const struct sunxi_sc_nmi_data sun7i_data __initconst = {
+	.reg_offs.ctrl		= SUN7I_NMI_CTRL,
+	.reg_offs.pend		= SUN7I_NMI_PENDING,
+	.reg_offs.enable	= SUN7I_NMI_ENABLE,
 };
 
-static const struct sunxi_sc_nmi_reg_offs sun9i_reg_offs __initconst = {
-	.ctrl	= SUN9I_NMI_CTRL,
-	.pend	= SUN9I_NMI_PENDING,
-	.enable	= SUN9I_NMI_ENABLE,
+static const struct sunxi_sc_nmi_data sun9i_data __initconst = {
+	.reg_offs.ctrl		= SUN9I_NMI_CTRL,
+	.reg_offs.pend		= SUN9I_NMI_PENDING,
+	.reg_offs.enable	= SUN9I_NMI_ENABLE,
 };
 
-static inline void sunxi_sc_nmi_write(struct irq_chip_generic *gc, u32 off,
-				      u32 val)
+static const struct sunxi_sc_nmi_data sun55i_a523_data __initconst = {
+	.reg_offs.ctrl		= SUN9I_NMI_CTRL,
+	.reg_offs.pend		= SUN9I_NMI_PENDING,
+	.reg_offs.enable	= SUN9I_NMI_ENABLE,
+	.enable_val		= BIT(31),
+};
+
+static inline void sunxi_sc_nmi_write(struct irq_chip_generic *gc, u32 off, u32 val)
 {
 	irq_reg_writel(gc, val, off);
 }
@@ -143,15 +152,13 @@ static int sunxi_sc_nmi_set_type(struct irq_data *data, unsigned int flow_type)
 }
 
 static int __init sunxi_sc_nmi_irq_init(struct device_node *node,
-					const struct sunxi_sc_nmi_reg_offs *reg_offs)
+					const struct sunxi_sc_nmi_data *data)
 {
-	struct irq_domain *domain;
+	unsigned int irq, clr = IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_NOAUTOEN;
 	struct irq_chip_generic *gc;
-	unsigned int irq;
-	unsigned int clr = IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_NOAUTOEN;
+	struct irq_domain *domain;
 	int ret;
 
-
 	domain = irq_domain_add_linear(node, 1, &irq_generic_chip_ops, NULL);
 	if (!domain) {
 		pr_err("Could not register interrupt domain.\n");
@@ -186,27 +193,28 @@ static int __init sunxi_sc_nmi_irq_init(struct device_node *node,
 	gc->chip_types[0].chip.irq_unmask	= irq_gc_mask_set_bit;
 	gc->chip_types[0].chip.irq_eoi		= irq_gc_ack_set_bit;
 	gc->chip_types[0].chip.irq_set_type	= sunxi_sc_nmi_set_type;
-	gc->chip_types[0].chip.flags		= IRQCHIP_EOI_THREADED | IRQCHIP_EOI_IF_HANDLED |
+	gc->chip_types[0].chip.flags		= IRQCHIP_EOI_THREADED |
+						  IRQCHIP_EOI_IF_HANDLED |
 						  IRQCHIP_SKIP_SET_WAKE;
-	gc->chip_types[0].regs.ack		= reg_offs->pend;
-	gc->chip_types[0].regs.mask		= reg_offs->enable;
-	gc->chip_types[0].regs.type		= reg_offs->ctrl;
+	gc->chip_types[0].regs.ack		= data->reg_offs.pend;
+	gc->chip_types[0].regs.mask		= data->reg_offs.enable;
+	gc->chip_types[0].regs.type		= data->reg_offs.ctrl;
 
 	gc->chip_types[1].type			= IRQ_TYPE_EDGE_BOTH;
 	gc->chip_types[1].chip.irq_ack		= irq_gc_ack_set_bit;
 	gc->chip_types[1].chip.irq_mask		= irq_gc_mask_clr_bit;
 	gc->chip_types[1].chip.irq_unmask	= irq_gc_mask_set_bit;
 	gc->chip_types[1].chip.irq_set_type	= sunxi_sc_nmi_set_type;
-	gc->chip_types[1].regs.ack		= reg_offs->pend;
-	gc->chip_types[1].regs.mask		= reg_offs->enable;
-	gc->chip_types[1].regs.type		= reg_offs->ctrl;
+	gc->chip_types[1].regs.ack		= data->reg_offs.pend;
+	gc->chip_types[1].regs.mask		= data->reg_offs.enable;
+	gc->chip_types[1].regs.type		= data->reg_offs.ctrl;
 	gc->chip_types[1].handler		= handle_edge_irq;
 
 	/* Disable any active interrupts */
-	sunxi_sc_nmi_write(gc, reg_offs->enable, 0);
+	sunxi_sc_nmi_write(gc, data->reg_offs.enable, data->enable_val);
 
 	/* Clear any pending NMI interrupts */
-	sunxi_sc_nmi_write(gc, reg_offs->pend, SUNXI_NMI_IRQ_BIT);
+	sunxi_sc_nmi_write(gc, data->reg_offs.pend, SUNXI_NMI_IRQ_BIT);
 
 	irq_set_chained_handler_and_data(irq, sunxi_sc_nmi_handle_irq, domain);
 
@@ -221,20 +229,27 @@ static int __init sunxi_sc_nmi_irq_init(struct device_node *node,
 static int __init sun6i_sc_nmi_irq_init(struct device_node *node,
 					struct device_node *parent)
 {
-	return sunxi_sc_nmi_irq_init(node, &sun6i_reg_offs);
+	return sunxi_sc_nmi_irq_init(node, &sun6i_data);
 }
 IRQCHIP_DECLARE(sun6i_sc_nmi, "allwinner,sun6i-a31-sc-nmi", sun6i_sc_nmi_irq_init);
 
 static int __init sun7i_sc_nmi_irq_init(struct device_node *node,
 					struct device_node *parent)
 {
-	return sunxi_sc_nmi_irq_init(node, &sun7i_reg_offs);
+	return sunxi_sc_nmi_irq_init(node, &sun7i_data);
 }
 IRQCHIP_DECLARE(sun7i_sc_nmi, "allwinner,sun7i-a20-sc-nmi", sun7i_sc_nmi_irq_init);
 
 static int __init sun9i_nmi_irq_init(struct device_node *node,
 				     struct device_node *parent)
 {
-	return sunxi_sc_nmi_irq_init(node, &sun9i_reg_offs);
+	return sunxi_sc_nmi_irq_init(node, &sun9i_data);
 }
 IRQCHIP_DECLARE(sun9i_nmi, "allwinner,sun9i-a80-nmi", sun9i_nmi_irq_init);
+
+static int __init sun55i_nmi_irq_init(struct device_node *node,
+				      struct device_node *parent)
+{
+	return sunxi_sc_nmi_irq_init(node, &sun55i_a523_data);
+}
+IRQCHIP_DECLARE(sun55i_nmi, "allwinner,sun55i-a523-nmi", sun55i_nmi_irq_init);

From 7db5fd6b751fbcaca253efc4de68f4346299948f Mon Sep 17 00:00:00 2001
From: Shengjiu Wang <shengjiu.wang@nxp.com>
Date: Wed, 5 Mar 2025 17:55:22 +0800
Subject: [PATCH 1084/1173] irqchip/imx-irqsteer: Support up to 960 input
 interrupts

The irqsteer IP routes groups of input interrupts to a dedicated system
interrupt per group. Each group handles 64 input interrupts.

The current driver is limited to 8 groups, i.e. 512 input interrupts, which
is sufficient for the existing i.MX SoCs. The upcoming i.MX94 family
extends the irqsteer IP to 15 groups, i.e. 960 interrupts.

Extending the group limit to 15 enables this, but the new SoCs are not
guaranteed to utilize all 15 groups. Unused groups have no mapping for the
underlying output interrupt, which makes the probe function fail as it
expects a valid mapping for each group output.

Remove this limitation and stop the mapping loop, when no valid mapping is
detected.

[ tglx: Massage change log ]

Signed-off-by: Shengjiu Wang <shengjiu.wang@nxp.com>
Signed-off-by: Jacky Bai <ping.bai@nxp.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Ye Li <ye.li@nxp.com>
Reviewed-by: Peng Fan <peng.fan@nxp.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://lore.kernel.org/all/20250305095522.2177843-1-ping.bai@nxp.com
---
 drivers/irqchip/irq-imx-irqsteer.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/irqchip/irq-imx-irqsteer.c b/drivers/irqchip/irq-imx-irqsteer.c
index b0e9788c00454..afbfcce3b1e3b 100644
--- a/drivers/irqchip/irq-imx-irqsteer.c
+++ b/drivers/irqchip/irq-imx-irqsteer.c
@@ -24,7 +24,7 @@
 #define CHAN_MINTDIS(t)		(CTRL_STRIDE_OFF(t, 3) + 0x4)
 #define CHAN_MASTRSTAT(t)	(CTRL_STRIDE_OFF(t, 3) + 0x8)
 
-#define CHAN_MAX_OUTPUT_INT	0x8
+#define CHAN_MAX_OUTPUT_INT	0xF
 
 struct irqsteer_data {
 	void __iomem		*regs;
@@ -228,10 +228,8 @@ static int imx_irqsteer_probe(struct platform_device *pdev)
 
 	for (i = 0; i < data->irq_count; i++) {
 		data->irq[i] = irq_of_parse_and_map(np, i);
-		if (!data->irq[i]) {
-			ret = -EINVAL;
-			goto out;
-		}
+		if (!data->irq[i])
+			break;
 
 		irq_set_chained_handler_and_data(data->irq[i],
 						 imx_irqsteer_irq_handler,
@@ -254,9 +252,13 @@ static void imx_irqsteer_remove(struct platform_device *pdev)
 	struct irqsteer_data *irqsteer_data = platform_get_drvdata(pdev);
 	int i;
 
-	for (i = 0; i < irqsteer_data->irq_count; i++)
+	for (i = 0; i < irqsteer_data->irq_count; i++) {
+		if (!irqsteer_data->irq[i])
+			break;
+
 		irq_set_chained_handler_and_data(irqsteer_data->irq[i],
 						 NULL, NULL);
+	}
 
 	irq_domain_remove(irqsteer_data->domain);
 

From c929d08df8bee855528b9d15b853c892c54e1eee Mon Sep 17 00:00:00 2001
From: Maksim Davydov <davydov-max@yandex-team.ru>
Date: Wed, 15 Jan 2025 16:17:04 +0300
Subject: [PATCH 1085/1173] x86/split_lock: Fix the delayed detection logic

If the warning mode with disabled mitigation mode is used, then on each
CPU where the split lock occurred detection will be disabled in order to
make progress and delayed work will be scheduled, which then will enable
detection back.

Now it turns out that all CPUs use one global delayed work structure.
This leads to the fact that if a split lock occurs on several CPUs
at the same time (within 2 jiffies), only one CPU will schedule delayed
work, but the rest will not.

The return value of schedule_delayed_work_on() would have shown this,
but it is not checked in the code.

A diagram that can help to understand the bug reproduction:

 - sld_update_msr() enables/disables SLD on both CPUs on the same core

 - schedule_delayed_work_on() internally checks WORK_STRUCT_PENDING_BIT.
   If a work has the 'pending' status, then schedule_delayed_work_on()
   will return an error code and, most importantly, the work will not
   be placed in the workqueue.

Let's say we have a multicore system on which split_lock_mitigate=0 and
a multithreaded application is running that calls splitlock in multiple
threads. Due to the fact that sld_update_msr() affects the entire core
(both CPUs), we will consider 2 CPUs from different cores. Let the 2
threads of this application schedule to CPU0 (core 0) and to CPU 2
(core 1), then:

|                                 ||                                   |
|             CPU 0 (core 0)      ||          CPU 2 (core 1)           |
|_________________________________||___________________________________|
|                                 ||                                   |
| 1) SPLIT LOCK occured           ||                                   |
|                                 ||                                   |
| 2) split_lock_warn()            ||                                   |
|                                 ||                                   |
| 3) sysctl_sld_mitigate == 0     ||                                   |
|    (work = &sl_reenable)        ||                                   |
|                                 ||                                   |
| 4) schedule_delayed_work_on()   ||                                   |
|    (reenable will be called     ||                                   |
|     after 2 jiffies on CPU 0)   ||                                   |
|                                 ||                                   |
| 5) disable SLD for core 0       ||                                   |
|                                 ||                                   |
|    -------------------------    ||                                   |
|                                 ||                                   |
|                                 || 6) SPLIT LOCK occured             |
|                                 ||                                   |
|                                 || 7) split_lock_warn()              |
|                                 ||                                   |
|                                 || 8) sysctl_sld_mitigate == 0       |
|                                 ||    (work = &sl_reenable,          |
|                                 ||     the same address as in 3) )   |
|                                 ||                                   |
|            2 jiffies            || 9) schedule_delayed_work_on()     |
|                                 ||    fials because the work is in   |
|                                 ||    the pending state since 4).    |
|                                 ||    The work wasn't placed to the  |
|                                 ||    workqueue. reenable won't be   |
|                                 ||    called on CPU 2                |
|                                 ||                                   |
|                                 || 10) disable SLD for core 0        |
|                                 ||                                   |
|                                 ||     From now on SLD will          |
|                                 ||     never be reenabled on core 1  |
|                                 ||                                   |
|    -------------------------    ||                                   |
|                                 ||                                   |
|    11) enable SLD for core 0 by ||                                   |
|        __split_lock_reenable    ||                                   |
|                                 ||                                   |

If the application threads can be scheduled to all processor cores,
then over time there will be only one core left, on which SLD will be
enabled and split lock will be able to be detected; and on all other
cores SLD will be disabled all the time.

Most likely, this bug has not been noticed for so long because
sysctl_sld_mitigate default value is 1, and in this case a semaphore
is used that does not allow 2 different cores to have SLD disabled at
the same time, that is, strictly only one work is placed in the
workqueue.

In order to fix the warning mode with disabled mitigation mode,
delayed work has to be per-CPU. Implement it.

Fixes: 727209376f49 ("x86/split_lock: Add sysctl to control the misery mode")
Signed-off-by: Maksim Davydov <davydov-max@yandex-team.ru>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Guilherme G. Piccoli <gpiccoli@igalia.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Link: https://lore.kernel.org/r/20250115131704.132609-1-davydov-max@yandex-team.ru
---
 arch/x86/kernel/cpu/bus_lock.c | 20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/cpu/bus_lock.c b/arch/x86/kernel/cpu/bus_lock.c
index 6cba85c79d42d..97222efb4d2a6 100644
--- a/arch/x86/kernel/cpu/bus_lock.c
+++ b/arch/x86/kernel/cpu/bus_lock.c
@@ -192,7 +192,13 @@ static void __split_lock_reenable(struct work_struct *work)
 {
 	sld_update_msr(true);
 }
-static DECLARE_DELAYED_WORK(sl_reenable, __split_lock_reenable);
+/*
+ * In order for each CPU to schedule its delayed work independently of the
+ * others, delayed work struct must be per-CPU. This is not required when
+ * sysctl_sld_mitigate is enabled because of the semaphore that limits
+ * the number of simultaneously scheduled delayed works to 1.
+ */
+static DEFINE_PER_CPU(struct delayed_work, sl_reenable);
 
 /*
  * If a CPU goes offline with pending delayed work to re-enable split lock
@@ -213,7 +219,7 @@ static int splitlock_cpu_offline(unsigned int cpu)
 
 static void split_lock_warn(unsigned long ip)
 {
-	struct delayed_work *work;
+	struct delayed_work *work = NULL;
 	int cpu;
 
 	if (!current->reported_split_lock)
@@ -235,11 +241,17 @@ static void split_lock_warn(unsigned long ip)
 		if (down_interruptible(&buslock_sem) == -EINTR)
 			return;
 		work = &sl_reenable_unlock;
-	} else {
-		work = &sl_reenable;
 	}
 
 	cpu = get_cpu();
+
+	if (!work) {
+		work = this_cpu_ptr(&sl_reenable);
+		/* Deferred initialization of per-CPU struct */
+		if (!work->work.func)
+			INIT_DELAYED_WORK(work, __split_lock_reenable);
+	}
+
 	schedule_delayed_work_on(cpu, work, 2);
 
 	/* Disable split lock detection on this CPU to make progress */

From 14cb5d83068ecf15d2da6f7d0e9ea9edbcbc0457 Mon Sep 17 00:00:00 2001
From: Andrew Cooper <andrew.cooper3@citrix.com>
Date: Fri, 7 Mar 2025 00:28:46 +0000
Subject: [PATCH 1086/1173] x86/amd_nb: Use rdmsr_safe() in
 amd_get_mmconfig_range()

Xen doesn't offer MSR_FAM10H_MMIO_CONF_BASE to all guests.  This results
in the following warning:

  unchecked MSR access error: RDMSR from 0xc0010058 at rIP: 0xffffffff8101d19f (xen_do_read_msr+0x7f/0xa0)
  Call Trace:
   xen_read_msr+0x1e/0x30
   amd_get_mmconfig_range+0x2b/0x80
   quirk_amd_mmconfig_area+0x28/0x100
   pnp_fixup_device+0x39/0x50
   __pnp_add_device+0xf/0x150
   pnp_add_device+0x3d/0x100
   pnpacpi_add_device_handler+0x1f9/0x280
   acpi_ns_get_device_callback+0x104/0x1c0
   acpi_ns_walk_namespace+0x1d0/0x260
   acpi_get_devices+0x8a/0xb0
   pnpacpi_init+0x50/0x80
   do_one_initcall+0x46/0x2e0
   kernel_init_freeable+0x1da/0x2f0
   kernel_init+0x16/0x1b0
   ret_from_fork+0x30/0x50
   ret_from_fork_asm+0x1b/0x30

based on quirks for a "PNP0c01" device.  Treating MMCFG as disabled is the
right course of action, so no change is needed there.

This was most likely exposed by fixing the Xen MSR accessors to not be
silently-safe.

Fixes: 3fac3734c43a ("xen/pv: support selecting safe/unsafe msr accesses")
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250307002846.3026685-1-andrew.cooper3@citrix.com
---
 arch/x86/kernel/amd_nb.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 11fac09e3a8cb..67e773744edb2 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -143,7 +143,6 @@ bool __init early_is_amd_nb(u32 device)
 
 struct resource *amd_get_mmconfig_range(struct resource *res)
 {
-	u32 address;
 	u64 base, msr;
 	unsigned int segn_busn_bits;
 
@@ -151,13 +150,11 @@ struct resource *amd_get_mmconfig_range(struct resource *res)
 	    boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
 		return NULL;
 
-	/* assume all cpus from fam10h have mmconfig */
-	if (boot_cpu_data.x86 < 0x10)
+	/* Assume CPUs from Fam10h have mmconfig, although not all VMs do */
+	if (boot_cpu_data.x86 < 0x10 ||
+	    rdmsrl_safe(MSR_FAM10H_MMIO_CONF_BASE, &msr))
 		return NULL;
 
-	address = MSR_FAM10H_MMIO_CONF_BASE;
-	rdmsrl(address, msr);
-
 	/* mmconfig is not enabled */
 	if (!(msr & FAM10H_MMIO_CONF_ENABLE))
 		return NULL;

From ac7c06acaa3738b38e83815ac0f07140ad320f13 Mon Sep 17 00:00:00 2001
From: Nikunj A Dadhania <nikunj@amd.com>
Date: Thu, 6 Mar 2025 19:17:21 +1100
Subject: [PATCH 1087/1173] virt: sev-guest: Allocate request data dynamically

Commit

  ae596615d93d ("virt: sev-guest: Reduce the scope of SNP command mutex")

narrowed the command mutex scope to snp_send_guest_request().  However,
GET_REPORT, GET_DERIVED_KEY, and GET_EXT_REPORT share the req structure in
snp_guest_dev. Without the mutex protection, concurrent requests can overwrite
each other's data. Fix it by dynamically allocating the request structure.

Fixes: ae596615d93d ("virt: sev-guest: Reduce the scope of SNP command mutex")
Closes: https://github.com/AMDESE/AMDSEV/issues/265
Reported-by: andreas.stuehrk@yaxi.tech
Signed-off-by: Nikunj A Dadhania <nikunj@amd.com>
Signed-off-by: Alexey Kardashevskiy <aik@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250307013700.437505-2-aik@amd.com
---
 drivers/virt/coco/sev-guest/sev-guest.c | 24 +++++++++++++++---------
 1 file changed, 15 insertions(+), 9 deletions(-)

diff --git a/drivers/virt/coco/sev-guest/sev-guest.c b/drivers/virt/coco/sev-guest/sev-guest.c
index 264b6523fe52f..23ac177472beb 100644
--- a/drivers/virt/coco/sev-guest/sev-guest.c
+++ b/drivers/virt/coco/sev-guest/sev-guest.c
@@ -38,12 +38,6 @@ struct snp_guest_dev {
 	struct miscdevice misc;
 
 	struct snp_msg_desc *msg_desc;
-
-	union {
-		struct snp_report_req report;
-		struct snp_derived_key_req derived_key;
-		struct snp_ext_report_req ext_report;
-	} req;
 };
 
 /*
@@ -71,7 +65,7 @@ struct snp_req_resp {
 
 static int get_report(struct snp_guest_dev *snp_dev, struct snp_guest_request_ioctl *arg)
 {
-	struct snp_report_req *report_req = &snp_dev->req.report;
+	struct snp_report_req *report_req __free(kfree) = NULL;
 	struct snp_msg_desc *mdesc = snp_dev->msg_desc;
 	struct snp_report_resp *report_resp;
 	struct snp_guest_req req = {};
@@ -80,6 +74,10 @@ static int get_report(struct snp_guest_dev *snp_dev, struct snp_guest_request_io
 	if (!arg->req_data || !arg->resp_data)
 		return -EINVAL;
 
+	report_req = kzalloc(sizeof(*report_req), GFP_KERNEL_ACCOUNT);
+	if (!report_req)
+		return -ENOMEM;
+
 	if (copy_from_user(report_req, (void __user *)arg->req_data, sizeof(*report_req)))
 		return -EFAULT;
 
@@ -116,7 +114,7 @@ static int get_report(struct snp_guest_dev *snp_dev, struct snp_guest_request_io
 
 static int get_derived_key(struct snp_guest_dev *snp_dev, struct snp_guest_request_ioctl *arg)
 {
-	struct snp_derived_key_req *derived_key_req = &snp_dev->req.derived_key;
+	struct snp_derived_key_req *derived_key_req __free(kfree) = NULL;
 	struct snp_derived_key_resp derived_key_resp = {0};
 	struct snp_msg_desc *mdesc = snp_dev->msg_desc;
 	struct snp_guest_req req = {};
@@ -136,6 +134,10 @@ static int get_derived_key(struct snp_guest_dev *snp_dev, struct snp_guest_reque
 	if (sizeof(buf) < resp_len)
 		return -ENOMEM;
 
+	derived_key_req = kzalloc(sizeof(*derived_key_req), GFP_KERNEL_ACCOUNT);
+	if (!derived_key_req)
+		return -ENOMEM;
+
 	if (copy_from_user(derived_key_req, (void __user *)arg->req_data,
 			   sizeof(*derived_key_req)))
 		return -EFAULT;
@@ -168,7 +170,7 @@ static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_reques
 			  struct snp_req_resp *io)
 
 {
-	struct snp_ext_report_req *report_req = &snp_dev->req.ext_report;
+	struct snp_ext_report_req *report_req __free(kfree) = NULL;
 	struct snp_msg_desc *mdesc = snp_dev->msg_desc;
 	struct snp_report_resp *report_resp;
 	struct snp_guest_req req = {};
@@ -178,6 +180,10 @@ static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_reques
 	if (sockptr_is_null(io->req_data) || sockptr_is_null(io->resp_data))
 		return -EINVAL;
 
+	report_req = kzalloc(sizeof(*report_req), GFP_KERNEL_ACCOUNT);
+	if (!report_req)
+		return -ENOMEM;
+
 	if (copy_from_sockptr(report_req, io->req_data, sizeof(*report_req)))
 		return -EFAULT;
 

From 3e385c0d6ce88ac9916dcf84267bd5855d830748 Mon Sep 17 00:00:00 2001
From: Alexey Kardashevskiy <aik@amd.com>
Date: Fri, 7 Mar 2025 12:37:00 +1100
Subject: [PATCH 1088/1173] virt: sev-guest: Move SNP Guest Request data pages
 handling under snp_cmd_mutex

Compared to the SNP Guest Request, the "Extended" version adds data pages for
receiving certificates. If not enough pages provided, the HV can report to the
VM how much is needed so the VM can reallocate and repeat.

Commit

  ae596615d93d ("virt: sev-guest: Reduce the scope of SNP command mutex")

moved handling of the allocated/desired pages number out of scope of said
mutex and create a possibility for a race (multiple instances trying to
trigger Extended request in a VM) as there is just one instance of
snp_msg_desc per /dev/sev-guest and no locking other than snp_cmd_mutex.

Fix the issue by moving the data blob/size and the GHCB input struct
(snp_req_data) into snp_guest_req which is allocated on stack now and accessed
by the GHCB caller under that mutex.

Stop allocating SEV_FW_BLOB_MAX_SIZE in snp_msg_alloc() as only one of four
callers needs it. Free the received blob in get_ext_report() right after it is
copied to the userspace. Possible future users of snp_send_guest_request() are
likely to have different ideas about the buffer size anyways.

Fixes: ae596615d93d ("virt: sev-guest: Reduce the scope of SNP command mutex")
Signed-off-by: Alexey Kardashevskiy <aik@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Nikunj A Dadhania <nikunj@amd.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250307013700.437505-3-aik@amd.com
---
 arch/x86/coco/sev/core.c                | 23 ++++++-----------
 arch/x86/include/asm/sev.h              |  6 ++---
 drivers/virt/coco/sev-guest/sev-guest.c | 34 ++++++++++++++++++++-----
 3 files changed, 39 insertions(+), 24 deletions(-)

diff --git a/arch/x86/coco/sev/core.c b/arch/x86/coco/sev/core.c
index 82492efc5d949..96c7bc698e6b6 100644
--- a/arch/x86/coco/sev/core.c
+++ b/arch/x86/coco/sev/core.c
@@ -2853,19 +2853,8 @@ struct snp_msg_desc *snp_msg_alloc(void)
 	if (!mdesc->response)
 		goto e_free_request;
 
-	mdesc->certs_data = alloc_shared_pages(SEV_FW_BLOB_MAX_SIZE);
-	if (!mdesc->certs_data)
-		goto e_free_response;
-
-	/* initial the input address for guest request */
-	mdesc->input.req_gpa = __pa(mdesc->request);
-	mdesc->input.resp_gpa = __pa(mdesc->response);
-	mdesc->input.data_gpa = __pa(mdesc->certs_data);
-
 	return mdesc;
 
-e_free_response:
-	free_shared_pages(mdesc->response, sizeof(struct snp_guest_msg));
 e_free_request:
 	free_shared_pages(mdesc->request, sizeof(struct snp_guest_msg));
 e_unmap:
@@ -2885,7 +2874,6 @@ void snp_msg_free(struct snp_msg_desc *mdesc)
 	kfree(mdesc->ctx);
 	free_shared_pages(mdesc->response, sizeof(struct snp_guest_msg));
 	free_shared_pages(mdesc->request, sizeof(struct snp_guest_msg));
-	free_shared_pages(mdesc->certs_data, SEV_FW_BLOB_MAX_SIZE);
 	iounmap((__force void __iomem *)mdesc->secrets);
 
 	memset(mdesc, 0, sizeof(*mdesc));
@@ -3054,7 +3042,7 @@ static int __handle_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_r
 	 * sequence number must be incremented or the VMPCK must be deleted to
 	 * prevent reuse of the IV.
 	 */
-	rc = snp_issue_guest_request(req, &mdesc->input, rio);
+	rc = snp_issue_guest_request(req, &req->input, rio);
 	switch (rc) {
 	case -ENOSPC:
 		/*
@@ -3064,7 +3052,7 @@ static int __handle_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_r
 		 * order to increment the sequence number and thus avoid
 		 * IV reuse.
 		 */
-		override_npages = mdesc->input.data_npages;
+		override_npages = req->input.data_npages;
 		req->exit_code	= SVM_VMGEXIT_GUEST_REQUEST;
 
 		/*
@@ -3120,7 +3108,7 @@ static int __handle_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_r
 	}
 
 	if (override_npages)
-		mdesc->input.data_npages = override_npages;
+		req->input.data_npages = override_npages;
 
 	return rc;
 }
@@ -3158,6 +3146,11 @@ int snp_send_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_req *req
 	 */
 	memcpy(mdesc->request, &mdesc->secret_request, sizeof(mdesc->secret_request));
 
+	/* Initialize the input address for guest request */
+	req->input.req_gpa = __pa(mdesc->request);
+	req->input.resp_gpa = __pa(mdesc->response);
+	req->input.data_gpa = req->certs_data ? __pa(req->certs_data) : 0;
+
 	rc = __handle_guest_request(mdesc, req, rio);
 	if (rc) {
 		if (rc == -EIO &&
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index 1581246491b54..ba7999f66abe6 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -203,6 +203,9 @@ struct snp_guest_req {
 	unsigned int vmpck_id;
 	u8 msg_version;
 	u8 msg_type;
+
+	struct snp_req_data input;
+	void *certs_data;
 };
 
 /*
@@ -263,9 +266,6 @@ struct snp_msg_desc {
 	struct snp_guest_msg secret_request, secret_response;
 
 	struct snp_secrets_page *secrets;
-	struct snp_req_data input;
-
-	void *certs_data;
 
 	struct aesgcm_ctx *ctx;
 
diff --git a/drivers/virt/coco/sev-guest/sev-guest.c b/drivers/virt/coco/sev-guest/sev-guest.c
index 23ac177472beb..70fbc9a3e703d 100644
--- a/drivers/virt/coco/sev-guest/sev-guest.c
+++ b/drivers/virt/coco/sev-guest/sev-guest.c
@@ -176,6 +176,7 @@ static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_reques
 	struct snp_guest_req req = {};
 	int ret, npages = 0, resp_len;
 	sockptr_t certs_address;
+	struct page *page;
 
 	if (sockptr_is_null(io->req_data) || sockptr_is_null(io->resp_data))
 		return -EINVAL;
@@ -209,8 +210,20 @@ static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_reques
 	 * the host. If host does not supply any certs in it, then copy
 	 * zeros to indicate that certificate data was not provided.
 	 */
-	memset(mdesc->certs_data, 0, report_req->certs_len);
 	npages = report_req->certs_len >> PAGE_SHIFT;
+	page = alloc_pages(GFP_KERNEL_ACCOUNT | __GFP_ZERO,
+			   get_order(report_req->certs_len));
+	if (!page)
+		return -ENOMEM;
+
+	req.certs_data = page_address(page);
+	ret = set_memory_decrypted((unsigned long)req.certs_data, npages);
+	if (ret) {
+		pr_err("failed to mark page shared, ret=%d\n", ret);
+		__free_pages(page, get_order(report_req->certs_len));
+		return -EFAULT;
+	}
+
 cmd:
 	/*
 	 * The intermediate response buffer is used while decrypting the
@@ -219,10 +232,12 @@ static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_reques
 	 */
 	resp_len = sizeof(report_resp->data) + mdesc->ctx->authsize;
 	report_resp = kzalloc(resp_len, GFP_KERNEL_ACCOUNT);
-	if (!report_resp)
-		return -ENOMEM;
+	if (!report_resp) {
+		ret = -ENOMEM;
+		goto e_free_data;
+	}
 
-	mdesc->input.data_npages = npages;
+	req.input.data_npages = npages;
 
 	req.msg_version = arg->msg_version;
 	req.msg_type = SNP_MSG_REPORT_REQ;
@@ -237,7 +252,7 @@ static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_reques
 
 	/* If certs length is invalid then copy the returned length */
 	if (arg->vmm_error == SNP_GUEST_VMM_ERR_INVALID_LEN) {
-		report_req->certs_len = mdesc->input.data_npages << PAGE_SHIFT;
+		report_req->certs_len = req.input.data_npages << PAGE_SHIFT;
 
 		if (copy_to_sockptr(io->req_data, report_req, sizeof(*report_req)))
 			ret = -EFAULT;
@@ -246,7 +261,7 @@ static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_reques
 	if (ret)
 		goto e_free;
 
-	if (npages && copy_to_sockptr(certs_address, mdesc->certs_data, report_req->certs_len)) {
+	if (npages && copy_to_sockptr(certs_address, req.certs_data, report_req->certs_len)) {
 		ret = -EFAULT;
 		goto e_free;
 	}
@@ -256,6 +271,13 @@ static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_reques
 
 e_free:
 	kfree(report_resp);
+e_free_data:
+	if (npages) {
+		if (set_memory_encrypted((unsigned long)req.certs_data, npages))
+			WARN_ONCE(ret, "failed to restore encryption mask (leak it)\n");
+		else
+			__free_pages(page, get_order(report_req->certs_len));
+	}
 	return ret;
 }
 

From 9c54baab4401db249d6938806b812231e0259380 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Fri, 7 Mar 2025 17:48:02 +0100
Subject: [PATCH 1089/1173] x86/boot: Drop CRC-32 checksum and the build tool
 that generates it

Apart from some sanity checks on the size of setup.bin, the only
remaining task carried out by the arch/x86/boot/tools/build.c build tool
is generating the CRC-32 checksum of the bzImage. This feature was added
in commit

  7d6e737c8d2698b6 ("x86: add a crc32 checksum to the kernel image.")

without any motivation (or any commit log text, for that matter). This
checksum is not verified by any known bootloader, and given that

 a) the checksum of the entire bzImage is reported by most tools (zlib,
    rhash) as 0xffffffff and not 0x0 as documented,

 b) the checksum is corrupted when the image is signed for secure boot,
    which means that no distro ships x86 images with valid CRCs,

it seems quite unlikely that this checksum is being used, so let's just
drop it, along with the tool that generates it.

Instead, use simple file concatenation and truncation to combine the two
pieces into bzImage, and replace the checks on the size of the setup
block with a couple of ASSERT()s in the linker script.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ian Campbell <ijc@hellion.org.uk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250307164801.885261-2-ardb+git@google.com
---
 Documentation/arch/x86/boot.rst        |  10 -
 arch/x86/boot/Makefile                 |   7 +-
 arch/x86/boot/compressed/vmlinux.lds.S |   3 +-
 arch/x86/boot/setup.ld                 |   2 +
 arch/x86/boot/tools/.gitignore         |   2 -
 arch/x86/boot/tools/build.c            | 247 -------------------------
 6 files changed, 5 insertions(+), 266 deletions(-)
 delete mode 100644 arch/x86/boot/tools/.gitignore
 delete mode 100644 arch/x86/boot/tools/build.c

diff --git a/Documentation/arch/x86/boot.rst b/Documentation/arch/x86/boot.rst
index 76f53d3450e73..77e6163288db0 100644
--- a/Documentation/arch/x86/boot.rst
+++ b/Documentation/arch/x86/boot.rst
@@ -1038,16 +1038,6 @@ Offset/size:	0x000c/4
   This field contains maximal allowed type for setup_data and setup_indirect structs.
 
 
-The Image Checksum
-==================
-
-From boot protocol version 2.08 onwards the CRC-32 is calculated over
-the entire file using the characteristic polynomial 0x04C11DB7 and an
-initial remainder of 0xffffffff.  The checksum is appended to the
-file; therefore the CRC of the file up to the limit specified in the
-syssize field of the header is always 0.
-
-
 The Kernel Command Line
 =======================
 
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 9cc0ff6e9067d..8589471b65a16 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -35,7 +35,6 @@ setup-y		+= video-vesa.o
 setup-y		+= video-bios.o
 
 targets		+= $(setup-y)
-hostprogs	:= tools/build
 hostprogs	+= mkcpustr
 
 HOST_EXTRACFLAGS += -I$(srctree)/tools/include \
@@ -61,11 +60,9 @@ KBUILD_CFLAGS	+= $(CONFIG_CC_IMPLICIT_FALLTHROUGH)
 $(obj)/bzImage: asflags-y  := $(SVGA_MODE)
 
 quiet_cmd_image = BUILD   $@
-silent_redirect_image = >/dev/null
-cmd_image = $(obj)/tools/build $(obj)/setup.bin $(obj)/vmlinux.bin \
-			       $(obj)/zoffset.h $@ $($(quiet)redirect_image)
+      cmd_image = cp $< $@; truncate -s %4K $@; cat $(obj)/vmlinux.bin >>$@
 
-$(obj)/bzImage: $(obj)/setup.bin $(obj)/vmlinux.bin $(obj)/tools/build FORCE
+$(obj)/bzImage: $(obj)/setup.bin $(obj)/vmlinux.bin FORCE
 	$(call if_changed,image)
 	@$(kecho) 'Kernel: $@ is ready' ' (#'$(or $(KBUILD_BUILD_VERSION),`cat .version`)')'
 
diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S
index 083ec6d7722a1..48d0b51845571 100644
--- a/arch/x86/boot/compressed/vmlinux.lds.S
+++ b/arch/x86/boot/compressed/vmlinux.lds.S
@@ -48,8 +48,7 @@ SECTIONS
 		*(.data)
 		*(.data.*)
 
-		/* Add 4 bytes of extra space for a CRC-32 checksum */
-		. = ALIGN(. + 4, 0x200);
+		. = ALIGN(0x200);
 		_edata = . ;
 	}
 	. = ALIGN(L1_CACHE_BYTES);
diff --git a/arch/x86/boot/setup.ld b/arch/x86/boot/setup.ld
index 3a2d1360abb01..e1d594a602045 100644
--- a/arch/x86/boot/setup.ld
+++ b/arch/x86/boot/setup.ld
@@ -45,6 +45,8 @@ SECTIONS
 
 		setup_size = ALIGN(ABSOLUTE(.), 4096);
 		setup_sects = ABSOLUTE(setup_size / 512);
+		ASSERT(setup_sects >= 5, "The setup must be at least 5 sectors in size");
+		ASSERT(setup_sects <= 64, "The setup must be at most 64 sectors in size");
 	}
 
 	. = ALIGN(16);
diff --git a/arch/x86/boot/tools/.gitignore b/arch/x86/boot/tools/.gitignore
deleted file mode 100644
index ae91f4d0d78b5..0000000000000
--- a/arch/x86/boot/tools/.gitignore
+++ /dev/null
@@ -1,2 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-build
diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c
deleted file mode 100644
index 10311d77c67f8..0000000000000
--- a/arch/x86/boot/tools/build.c
+++ /dev/null
@@ -1,247 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- *  Copyright (C) 1991, 1992  Linus Torvalds
- *  Copyright (C) 1997 Martin Mares
- *  Copyright (C) 2007 H. Peter Anvin
- */
-
-/*
- * This file builds a disk-image from three different files:
- *
- * - setup: 8086 machine code, sets up system parm
- * - system: 80386 code for actual system
- * - zoffset.h: header with ZO_* defines
- *
- * It does some checking that all files are of the correct type, and writes
- * the result to the specified destination, removing headers and padding to
- * the right amount. It also writes some system data to stdout.
- */
-
-/*
- * Changes by tytso to allow root device specification
- * High loaded stuff by Hans Lermen & Werner Almesberger, Feb. 1996
- * Cross compiling fixes by Gertjan van Wingerde, July 1996
- * Rewritten by Martin Mares, April 1997
- * Substantially overhauled by H. Peter Anvin, April 2007
- */
-
-#include <stdio.h>
-#include <string.h>
-#include <stdlib.h>
-#include <stdarg.h>
-#include <sys/types.h>
-#include <sys/stat.h>
-#include <unistd.h>
-#include <fcntl.h>
-#include <sys/mman.h>
-#include <tools/le_byteshift.h>
-
-typedef unsigned char  u8;
-typedef unsigned short u16;
-typedef unsigned int   u32;
-
-/* Minimal number of setup sectors */
-#define SETUP_SECT_MIN 5
-#define SETUP_SECT_MAX 64
-
-/* This must be large enough to hold the entire setup */
-u8 buf[SETUP_SECT_MAX*512];
-
-static unsigned long _edata;
-
-/*----------------------------------------------------------------------*/
-
-static const u32 crctab32[] = {
-	0x00000000, 0x77073096, 0xee0e612c, 0x990951ba, 0x076dc419,
-	0x706af48f, 0xe963a535, 0x9e6495a3, 0x0edb8832, 0x79dcb8a4,
-	0xe0d5e91e, 0x97d2d988, 0x09b64c2b, 0x7eb17cbd, 0xe7b82d07,
-	0x90bf1d91, 0x1db71064, 0x6ab020f2, 0xf3b97148, 0x84be41de,
-	0x1adad47d, 0x6ddde4eb, 0xf4d4b551, 0x83d385c7, 0x136c9856,
-	0x646ba8c0, 0xfd62f97a, 0x8a65c9ec, 0x14015c4f, 0x63066cd9,
-	0xfa0f3d63, 0x8d080df5, 0x3b6e20c8, 0x4c69105e, 0xd56041e4,
-	0xa2677172, 0x3c03e4d1, 0x4b04d447, 0xd20d85fd, 0xa50ab56b,
-	0x35b5a8fa, 0x42b2986c, 0xdbbbc9d6, 0xacbcf940, 0x32d86ce3,
-	0x45df5c75, 0xdcd60dcf, 0xabd13d59, 0x26d930ac, 0x51de003a,
-	0xc8d75180, 0xbfd06116, 0x21b4f4b5, 0x56b3c423, 0xcfba9599,
-	0xb8bda50f, 0x2802b89e, 0x5f058808, 0xc60cd9b2, 0xb10be924,
-	0x2f6f7c87, 0x58684c11, 0xc1611dab, 0xb6662d3d, 0x76dc4190,
-	0x01db7106, 0x98d220bc, 0xefd5102a, 0x71b18589, 0x06b6b51f,
-	0x9fbfe4a5, 0xe8b8d433, 0x7807c9a2, 0x0f00f934, 0x9609a88e,
-	0xe10e9818, 0x7f6a0dbb, 0x086d3d2d, 0x91646c97, 0xe6635c01,
-	0x6b6b51f4, 0x1c6c6162, 0x856530d8, 0xf262004e, 0x6c0695ed,
-	0x1b01a57b, 0x8208f4c1, 0xf50fc457, 0x65b0d9c6, 0x12b7e950,
-	0x8bbeb8ea, 0xfcb9887c, 0x62dd1ddf, 0x15da2d49, 0x8cd37cf3,
-	0xfbd44c65, 0x4db26158, 0x3ab551ce, 0xa3bc0074, 0xd4bb30e2,
-	0x4adfa541, 0x3dd895d7, 0xa4d1c46d, 0xd3d6f4fb, 0x4369e96a,
-	0x346ed9fc, 0xad678846, 0xda60b8d0, 0x44042d73, 0x33031de5,
-	0xaa0a4c5f, 0xdd0d7cc9, 0x5005713c, 0x270241aa, 0xbe0b1010,
-	0xc90c2086, 0x5768b525, 0x206f85b3, 0xb966d409, 0xce61e49f,
-	0x5edef90e, 0x29d9c998, 0xb0d09822, 0xc7d7a8b4, 0x59b33d17,
-	0x2eb40d81, 0xb7bd5c3b, 0xc0ba6cad, 0xedb88320, 0x9abfb3b6,
-	0x03b6e20c, 0x74b1d29a, 0xead54739, 0x9dd277af, 0x04db2615,
-	0x73dc1683, 0xe3630b12, 0x94643b84, 0x0d6d6a3e, 0x7a6a5aa8,
-	0xe40ecf0b, 0x9309ff9d, 0x0a00ae27, 0x7d079eb1, 0xf00f9344,
-	0x8708a3d2, 0x1e01f268, 0x6906c2fe, 0xf762575d, 0x806567cb,
-	0x196c3671, 0x6e6b06e7, 0xfed41b76, 0x89d32be0, 0x10da7a5a,
-	0x67dd4acc, 0xf9b9df6f, 0x8ebeeff9, 0x17b7be43, 0x60b08ed5,
-	0xd6d6a3e8, 0xa1d1937e, 0x38d8c2c4, 0x4fdff252, 0xd1bb67f1,
-	0xa6bc5767, 0x3fb506dd, 0x48b2364b, 0xd80d2bda, 0xaf0a1b4c,
-	0x36034af6, 0x41047a60, 0xdf60efc3, 0xa867df55, 0x316e8eef,
-	0x4669be79, 0xcb61b38c, 0xbc66831a, 0x256fd2a0, 0x5268e236,
-	0xcc0c7795, 0xbb0b4703, 0x220216b9, 0x5505262f, 0xc5ba3bbe,
-	0xb2bd0b28, 0x2bb45a92, 0x5cb36a04, 0xc2d7ffa7, 0xb5d0cf31,
-	0x2cd99e8b, 0x5bdeae1d, 0x9b64c2b0, 0xec63f226, 0x756aa39c,
-	0x026d930a, 0x9c0906a9, 0xeb0e363f, 0x72076785, 0x05005713,
-	0x95bf4a82, 0xe2b87a14, 0x7bb12bae, 0x0cb61b38, 0x92d28e9b,
-	0xe5d5be0d, 0x7cdcefb7, 0x0bdbdf21, 0x86d3d2d4, 0xf1d4e242,
-	0x68ddb3f8, 0x1fda836e, 0x81be16cd, 0xf6b9265b, 0x6fb077e1,
-	0x18b74777, 0x88085ae6, 0xff0f6a70, 0x66063bca, 0x11010b5c,
-	0x8f659eff, 0xf862ae69, 0x616bffd3, 0x166ccf45, 0xa00ae278,
-	0xd70dd2ee, 0x4e048354, 0x3903b3c2, 0xa7672661, 0xd06016f7,
-	0x4969474d, 0x3e6e77db, 0xaed16a4a, 0xd9d65adc, 0x40df0b66,
-	0x37d83bf0, 0xa9bcae53, 0xdebb9ec5, 0x47b2cf7f, 0x30b5ffe9,
-	0xbdbdf21c, 0xcabac28a, 0x53b39330, 0x24b4a3a6, 0xbad03605,
-	0xcdd70693, 0x54de5729, 0x23d967bf, 0xb3667a2e, 0xc4614ab8,
-	0x5d681b02, 0x2a6f2b94, 0xb40bbe37, 0xc30c8ea1, 0x5a05df1b,
-	0x2d02ef8d
-};
-
-static u32 partial_crc32_one(u8 c, u32 crc)
-{
-	return crctab32[(crc ^ c) & 0xff] ^ (crc >> 8);
-}
-
-static u32 partial_crc32(const u8 *s, int len, u32 crc)
-{
-	while (len--)
-		crc = partial_crc32_one(*s++, crc);
-	return crc;
-}
-
-static void die(const char * str, ...)
-{
-	va_list args;
-	va_start(args, str);
-	vfprintf(stderr, str, args);
-	va_end(args);
-	fputc('\n', stderr);
-	exit(1);
-}
-
-static void usage(void)
-{
-	die("Usage: build setup system zoffset.h image");
-}
-
-/*
- * Parse zoffset.h and find the entry points. We could just #include zoffset.h
- * but that would mean tools/build would have to be rebuilt every time. It's
- * not as if parsing it is hard...
- */
-#define PARSE_ZOFS(p, sym) do { \
-	if (!strncmp(p, "#define ZO_" #sym " ", 11+sizeof(#sym)))	\
-		sym = strtoul(p + 11 + sizeof(#sym), NULL, 16);		\
-} while (0)
-
-static void parse_zoffset(char *fname)
-{
-	FILE *file;
-	char *p;
-	int c;
-
-	file = fopen(fname, "r");
-	if (!file)
-		die("Unable to open `%s': %m", fname);
-	c = fread(buf, 1, sizeof(buf) - 1, file);
-	if (ferror(file))
-		die("read-error on `zoffset.h'");
-	fclose(file);
-	buf[c] = 0;
-
-	p = (char *)buf;
-
-	while (p && *p) {
-		PARSE_ZOFS(p, _edata);
-
-		p = strchr(p, '\n');
-		while (p && (*p == '\r' || *p == '\n'))
-			p++;
-	}
-}
-
-int main(int argc, char ** argv)
-{
-	unsigned int i, sz, setup_sectors;
-	int c;
-	struct stat sb;
-	FILE *file, *dest;
-	int fd;
-	void *kernel;
-	u32 crc = 0xffffffffUL;
-
-	if (argc != 5)
-		usage();
-	parse_zoffset(argv[3]);
-
-	dest = fopen(argv[4], "w");
-	if (!dest)
-		die("Unable to write `%s': %m", argv[4]);
-
-	/* Copy the setup code */
-	file = fopen(argv[1], "r");
-	if (!file)
-		die("Unable to open `%s': %m", argv[1]);
-	c = fread(buf, 1, sizeof(buf), file);
-	if (ferror(file))
-		die("read-error on `setup'");
-	if (c < 1024)
-		die("The setup must be at least 1024 bytes");
-	if (get_unaligned_le16(&buf[510]) != 0xAA55)
-		die("Boot block hasn't got boot flag (0xAA55)");
-	fclose(file);
-
-	/* Pad unused space with zeros */
-	setup_sectors = (c + 4095) / 4096;
-	setup_sectors *= 8;
-	if (setup_sectors < SETUP_SECT_MIN)
-		setup_sectors = SETUP_SECT_MIN;
-	i = setup_sectors*512;
-	memset(buf+c, 0, i-c);
-
-	/* Open and stat the kernel file */
-	fd = open(argv[2], O_RDONLY);
-	if (fd < 0)
-		die("Unable to open `%s': %m", argv[2]);
-	if (fstat(fd, &sb))
-		die("Unable to stat `%s': %m", argv[2]);
-	if (_edata != sb.st_size)
-		die("Unexpected file size `%s': %u != %u", argv[2], _edata,
-		    sb.st_size);
-	sz = _edata - 4;
-	kernel = mmap(NULL, sz, PROT_READ, MAP_SHARED, fd, 0);
-	if (kernel == MAP_FAILED)
-		die("Unable to mmap '%s': %m", argv[2]);
-
-	crc = partial_crc32(buf, i, crc);
-	if (fwrite(buf, 1, i, dest) != i)
-		die("Writing setup failed");
-
-	/* Copy the kernel code */
-	crc = partial_crc32(kernel, sz, crc);
-	if (fwrite(kernel, 1, sz, dest) != sz)
-		die("Writing kernel failed");
-
-	/* Write the CRC */
-	put_unaligned_le32(crc, buf);
-	if (fwrite(buf, 1, 4, dest) != 4)
-		die("Writing CRC failed");
-
-	/* Catch any delayed write failures */
-	if (fclose(dest))
-		die("Writing image failed");
-
-	close(fd);
-
-	/* Everything is OK */
-	return 0;
-}

From 6914f7e2e25fac9d1d2b62c208eaa5f2bf810fe9 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Thu, 6 Mar 2025 23:00:16 +0100
Subject: [PATCH 1090/1173] x86/mm: Define PTRS_PER_PMD for assembly code too

Andy reported the following build warning from head_32.S:

  In file included from arch/x86/kernel/head_32.S:29:
  arch/x86/include/asm/pgtable_32.h:59:5: error: "PTRS_PER_PMD" is not defined, evaluates to 0 [-Werror=undef]
       59 | #if PTRS_PER_PMD > 1

The reason is that on 2-level i386 paging the folded in PMD's
PTRS_PER_PMD constant is not defined in assembly headers,
only in generic MM C headers.

Instead of trying to fish out the definition from the generic
headers, just define it - it even has a comment for it already...

Reported-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Tested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/Z8oa8AUVyi2HWfo9@gmail.com
---
 arch/x86/include/asm/pgtable-2level_types.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/pgtable-2level_types.h b/arch/x86/include/asm/pgtable-2level_types.h
index 7f6ccff0ba727..4a12c276b1812 100644
--- a/arch/x86/include/asm/pgtable-2level_types.h
+++ b/arch/x86/include/asm/pgtable-2level_types.h
@@ -23,17 +23,17 @@ typedef union {
 #define ARCH_PAGE_TABLE_SYNC_MASK	PGTBL_PMD_MODIFIED
 
 /*
- * traditional i386 two-level paging structure:
+ * Traditional i386 two-level paging structure:
  */
 
 #define PGDIR_SHIFT	22
 #define PTRS_PER_PGD	1024
 
-
 /*
- * the i386 is two-level, so we don't really have any
- * PMD directory physically.
+ * The i386 is two-level, so we don't really have any
+ * PMD directory physically:
  */
+#define PTRS_PER_PMD	1
 
 #define PTRS_PER_PTE	1024
 

From 966944f3711665db13e214fef6d02982c49bb972 Mon Sep 17 00:00:00 2001
From: Mitchell Levy <levymitchell0@gmail.com>
Date: Fri, 7 Mar 2025 15:27:00 -0800
Subject: [PATCH 1091/1173] rust: lockdep: Remove support for dynamically
 allocated LockClassKeys

Currently, dynamically allocated LockCLassKeys can be used from the Rust
side without having them registered. This is a soundness issue, so
remove them.

Fixes: 6ea5aa08857a ("rust: sync: introduce `LockClassKey`")
Suggested-by: Alice Ryhl <aliceryhl@google.com>
Signed-off-by: Mitchell Levy <levymitchell0@gmail.com>
Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250307232717.1759087-11-boqun.feng@gmail.com
---
 rust/kernel/sync.rs | 16 ++++------------
 1 file changed, 4 insertions(+), 12 deletions(-)

diff --git a/rust/kernel/sync.rs b/rust/kernel/sync.rs
index 3498fb344dc93..16eab9138b2ba 100644
--- a/rust/kernel/sync.rs
+++ b/rust/kernel/sync.rs
@@ -30,28 +30,20 @@ pub struct LockClassKey(Opaque<bindings::lock_class_key>);
 unsafe impl Sync for LockClassKey {}
 
 impl LockClassKey {
-    /// Creates a new lock class key.
-    pub const fn new() -> Self {
-        Self(Opaque::uninit())
-    }
-
     pub(crate) fn as_ptr(&self) -> *mut bindings::lock_class_key {
         self.0.get()
     }
 }
 
-impl Default for LockClassKey {
-    fn default() -> Self {
-        Self::new()
-    }
-}
-
 /// Defines a new static lock class and returns a pointer to it.
 #[doc(hidden)]
 #[macro_export]
 macro_rules! static_lock_class {
     () => {{
-        static CLASS: $crate::sync::LockClassKey = $crate::sync::LockClassKey::new();
+        static CLASS: $crate::sync::LockClassKey =
+            // SAFETY: lockdep expects uninitialized memory when it's handed a statically allocated
+            // lock_class_key
+            unsafe { ::core::mem::MaybeUninit::uninit().assume_init() };
         &CLASS
     }};
 }

From b3c5ec8b79bf6bc49cc4850d0949d712830283d7 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 7 Mar 2025 15:26:51 -0800
Subject: [PATCH 1092/1173] locking/rtmutex: Use the 'struct' keyword in
 kernel-doc comment

Add the "struct" keyword to prevent a kernel-doc warning:

  rtmutex_common.h:67: warning: cannot understand function prototype: 'struct rt_wake_q_head '

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Waiman Long <longman@redhat.com>
Link: https://lore.kernel.org/r/20250307232717.1759087-2-boqun.feng@gmail.com
---
 kernel/locking/rtmutex_common.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h
index c38a2d2d4a7ee..78dd3d8c65544 100644
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -59,8 +59,8 @@ struct rt_mutex_waiter {
 };
 
 /**
- * rt_wake_q_head - Wrapper around regular wake_q_head to support
- *		    "sleeping" spinlocks on RT
+ * struct rt_wake_q_head - Wrapper around regular wake_q_head to support
+ *			   "sleeping" spinlocks on RT
  * @head:		The regular wake_q_head for sleeping lock variants
  * @rtlock_task:	Task pointer for RT lock (spin/rwlock) wakeups
  */

From 85b2b9c16d053364e2004883140538e73b333cdb Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Fri, 7 Mar 2025 15:26:52 -0800
Subject: [PATCH 1093/1173] locking/semaphore: Use wake_q to wake up processes
 outside lock critical section

A circular lock dependency splat has been seen involving down_trylock():

  ======================================================
  WARNING: possible circular locking dependency detected
  6.12.0-41.el10.s390x+debug
  ------------------------------------------------------
  dd/32479 is trying to acquire lock:
  0015a20accd0d4f8 ((console_sem).lock){-.-.}-{2:2}, at: down_trylock+0x26/0x90

  but task is already holding lock:
  000000017e461698 (&zone->lock){-.-.}-{2:2}, at: rmqueue_bulk+0xac/0x8f0

  the existing dependency chain (in reverse order) is:
  -> #4 (&zone->lock){-.-.}-{2:2}:
  -> #3 (hrtimer_bases.lock){-.-.}-{2:2}:
  -> #2 (&rq->__lock){-.-.}-{2:2}:
  -> #1 (&p->pi_lock){-.-.}-{2:2}:
  -> #0 ((console_sem).lock){-.-.}-{2:2}:

The console_sem -> pi_lock dependency is due to calling try_to_wake_up()
while holding the console_sem raw_spinlock. This dependency can be broken
by using wake_q to do the wakeup instead of calling try_to_wake_up()
under the console_sem lock. This will also make the semaphore's
raw_spinlock become a terminal lock without taking any further locks
underneath it.

The hrtimer_bases.lock is a raw_spinlock while zone->lock is a
spinlock. The hrtimer_bases.lock -> zone->lock dependency happens via
the debug_objects_fill_pool() helper function in the debugobjects code.

  -> #4 (&zone->lock){-.-.}-{2:2}:
         __lock_acquire+0xe86/0x1cc0
         lock_acquire.part.0+0x258/0x630
         lock_acquire+0xb8/0xe0
         _raw_spin_lock_irqsave+0xb4/0x120
         rmqueue_bulk+0xac/0x8f0
         __rmqueue_pcplist+0x580/0x830
         rmqueue_pcplist+0xfc/0x470
         rmqueue.isra.0+0xdec/0x11b0
         get_page_from_freelist+0x2ee/0xeb0
         __alloc_pages_noprof+0x2c2/0x520
         alloc_pages_mpol_noprof+0x1fc/0x4d0
         alloc_pages_noprof+0x8c/0xe0
         allocate_slab+0x320/0x460
         ___slab_alloc+0xa58/0x12b0
         __slab_alloc.isra.0+0x42/0x60
         kmem_cache_alloc_noprof+0x304/0x350
         fill_pool+0xf6/0x450
         debug_object_activate+0xfe/0x360
         enqueue_hrtimer+0x34/0x190
         __run_hrtimer+0x3c8/0x4c0
         __hrtimer_run_queues+0x1b2/0x260
         hrtimer_interrupt+0x316/0x760
         do_IRQ+0x9a/0xe0
         do_irq_async+0xf6/0x160

Normally a raw_spinlock to spinlock dependency is not legitimate
and will be warned if CONFIG_PROVE_RAW_LOCK_NESTING is enabled,
but debug_objects_fill_pool() is an exception as it explicitly
allows this dependency for non-PREEMPT_RT kernel without causing
PROVE_RAW_LOCK_NESTING lockdep splat. As a result, this dependency is
legitimate and not a bug.

Anyway, semaphore is the only locking primitive left that is still
using try_to_wake_up() to do wakeup inside critical section, all the
other locking primitives had been migrated to use wake_q to do wakeup
outside of the critical section. It is also possible that there are
other circular locking dependencies involving printk/console_sem or
other existing/new semaphores lurking somewhere which may show up in
the future. Let just do the migration now to wake_q to avoid headache
like this.

Reported-by: yzbot+ed801a886dfdbfe7136d@syzkaller.appspotmail.com
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250307232717.1759087-3-boqun.feng@gmail.com
---
 kernel/locking/semaphore.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/kernel/locking/semaphore.c b/kernel/locking/semaphore.c
index 34bfae72f2952..de9117c0e671e 100644
--- a/kernel/locking/semaphore.c
+++ b/kernel/locking/semaphore.c
@@ -29,6 +29,7 @@
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/wake_q.h>
 #include <linux/semaphore.h>
 #include <linux/spinlock.h>
 #include <linux/ftrace.h>
@@ -38,7 +39,7 @@ static noinline void __down(struct semaphore *sem);
 static noinline int __down_interruptible(struct semaphore *sem);
 static noinline int __down_killable(struct semaphore *sem);
 static noinline int __down_timeout(struct semaphore *sem, long timeout);
-static noinline void __up(struct semaphore *sem);
+static noinline void __up(struct semaphore *sem, struct wake_q_head *wake_q);
 
 /**
  * down - acquire the semaphore
@@ -183,13 +184,16 @@ EXPORT_SYMBOL(down_timeout);
 void __sched up(struct semaphore *sem)
 {
 	unsigned long flags;
+	DEFINE_WAKE_Q(wake_q);
 
 	raw_spin_lock_irqsave(&sem->lock, flags);
 	if (likely(list_empty(&sem->wait_list)))
 		sem->count++;
 	else
-		__up(sem);
+		__up(sem, &wake_q);
 	raw_spin_unlock_irqrestore(&sem->lock, flags);
+	if (!wake_q_empty(&wake_q))
+		wake_up_q(&wake_q);
 }
 EXPORT_SYMBOL(up);
 
@@ -269,11 +273,12 @@ static noinline int __sched __down_timeout(struct semaphore *sem, long timeout)
 	return __down_common(sem, TASK_UNINTERRUPTIBLE, timeout);
 }
 
-static noinline void __sched __up(struct semaphore *sem)
+static noinline void __sched __up(struct semaphore *sem,
+				  struct wake_q_head *wake_q)
 {
 	struct semaphore_waiter *waiter = list_first_entry(&sem->wait_list,
 						struct semaphore_waiter, list);
 	list_del(&waiter->list);
 	waiter->up = true;
-	wake_up_process(waiter->task);
+	wake_q_add(wake_q, waiter->task);
 }

From b76b44fb656100fcd8482d9102d35d1b6a5129e9 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Fri, 7 Mar 2025 15:26:53 -0800
Subject: [PATCH 1094/1173] locking/lock_events: Add locking events for rtmutex
 slow paths

Add locking events for rtlock_slowlock() and rt_mutex_slowlock() for
profiling the slow path behavior of rt_spin_lock() and rt_mutex_lock().

Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250307232717.1759087-4-boqun.feng@gmail.com
---
 kernel/locking/lock_events_list.h | 21 +++++++++++++++++++++
 kernel/locking/rtmutex.c          | 29 ++++++++++++++++++++++++-----
 2 files changed, 45 insertions(+), 5 deletions(-)

diff --git a/kernel/locking/lock_events_list.h b/kernel/locking/lock_events_list.h
index 97fb6f3f840aa..80b11f194c9f7 100644
--- a/kernel/locking/lock_events_list.h
+++ b/kernel/locking/lock_events_list.h
@@ -67,3 +67,24 @@ LOCK_EVENT(rwsem_rlock_handoff)	/* # of read lock handoffs		*/
 LOCK_EVENT(rwsem_wlock)		/* # of write locks acquired		*/
 LOCK_EVENT(rwsem_wlock_fail)	/* # of failed write lock acquisitions	*/
 LOCK_EVENT(rwsem_wlock_handoff)	/* # of write lock handoffs		*/
+
+/*
+ * Locking events for rtlock_slowlock()
+ */
+LOCK_EVENT(rtlock_slowlock)	/* # of rtlock_slowlock() calls		*/
+LOCK_EVENT(rtlock_slow_acq1)	/* # of locks acquired after wait_lock	*/
+LOCK_EVENT(rtlock_slow_acq2)	/* # of locks acquired in for loop	*/
+LOCK_EVENT(rtlock_slow_sleep)	/* # of sleeps				*/
+LOCK_EVENT(rtlock_slow_wake)	/* # of wakeup's			*/
+
+/*
+ * Locking events for rt_mutex_slowlock()
+ */
+LOCK_EVENT(rtmutex_slowlock)	/* # of rt_mutex_slowlock() calls	*/
+LOCK_EVENT(rtmutex_slow_block)	/* # of rt_mutex_slowlock_block() calls	*/
+LOCK_EVENT(rtmutex_slow_acq1)	/* # of locks acquired after wait_lock	*/
+LOCK_EVENT(rtmutex_slow_acq2)	/* # of locks acquired at the end	*/
+LOCK_EVENT(rtmutex_slow_acq3)	/* # of locks acquired in *block()	*/
+LOCK_EVENT(rtmutex_slow_sleep)	/* # of sleeps				*/
+LOCK_EVENT(rtmutex_slow_wake)	/* # of wakeup's			*/
+LOCK_EVENT(rtmutex_deadlock)	/* # of rt_mutex_handle_deadlock()'s	*/
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 4a8df1800cbbd..c80902eacd797 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -27,6 +27,7 @@
 #include <trace/events/lock.h>
 
 #include "rtmutex_common.h"
+#include "lock_events.h"
 
 #ifndef WW_RT
 # define build_ww_mutex()	(false)
@@ -1612,10 +1613,13 @@ static int __sched rt_mutex_slowlock_block(struct rt_mutex_base *lock,
 	struct task_struct *owner;
 	int ret = 0;
 
+	lockevent_inc(rtmutex_slow_block);
 	for (;;) {
 		/* Try to acquire the lock: */
-		if (try_to_take_rt_mutex(lock, current, waiter))
+		if (try_to_take_rt_mutex(lock, current, waiter)) {
+			lockevent_inc(rtmutex_slow_acq3);
 			break;
+		}
 
 		if (timeout && !timeout->task) {
 			ret = -ETIMEDOUT;
@@ -1638,8 +1642,10 @@ static int __sched rt_mutex_slowlock_block(struct rt_mutex_base *lock,
 			owner = NULL;
 		raw_spin_unlock_irq_wake(&lock->wait_lock, wake_q);
 
-		if (!owner || !rtmutex_spin_on_owner(lock, waiter, owner))
+		if (!owner || !rtmutex_spin_on_owner(lock, waiter, owner)) {
+			lockevent_inc(rtmutex_slow_sleep);
 			rt_mutex_schedule();
+		}
 
 		raw_spin_lock_irq(&lock->wait_lock);
 		set_current_state(state);
@@ -1694,6 +1700,7 @@ static int __sched __rt_mutex_slowlock(struct rt_mutex_base *lock,
 	int ret;
 
 	lockdep_assert_held(&lock->wait_lock);
+	lockevent_inc(rtmutex_slowlock);
 
 	/* Try to acquire the lock again: */
 	if (try_to_take_rt_mutex(lock, current, NULL)) {
@@ -1701,6 +1708,7 @@ static int __sched __rt_mutex_slowlock(struct rt_mutex_base *lock,
 			__ww_mutex_check_waiters(rtm, ww_ctx, wake_q);
 			ww_mutex_lock_acquired(ww, ww_ctx);
 		}
+		lockevent_inc(rtmutex_slow_acq1);
 		return 0;
 	}
 
@@ -1719,10 +1727,12 @@ static int __sched __rt_mutex_slowlock(struct rt_mutex_base *lock,
 				__ww_mutex_check_waiters(rtm, ww_ctx, wake_q);
 			ww_mutex_lock_acquired(ww, ww_ctx);
 		}
+		lockevent_inc(rtmutex_slow_acq2);
 	} else {
 		__set_current_state(TASK_RUNNING);
 		remove_waiter(lock, waiter);
 		rt_mutex_handle_deadlock(ret, chwalk, lock, waiter);
+		lockevent_inc(rtmutex_deadlock);
 	}
 
 	/*
@@ -1751,6 +1761,7 @@ static inline int __rt_mutex_slowlock_locked(struct rt_mutex_base *lock,
 				  &waiter, wake_q);
 
 	debug_rt_mutex_free_waiter(&waiter);
+	lockevent_cond_inc(rtmutex_slow_wake, !wake_q_empty(wake_q));
 	return ret;
 }
 
@@ -1823,9 +1834,12 @@ static void __sched rtlock_slowlock_locked(struct rt_mutex_base *lock,
 	struct task_struct *owner;
 
 	lockdep_assert_held(&lock->wait_lock);
+	lockevent_inc(rtlock_slowlock);
 
-	if (try_to_take_rt_mutex(lock, current, NULL))
+	if (try_to_take_rt_mutex(lock, current, NULL)) {
+		lockevent_inc(rtlock_slow_acq1);
 		return;
+	}
 
 	rt_mutex_init_rtlock_waiter(&waiter);
 
@@ -1838,8 +1852,10 @@ static void __sched rtlock_slowlock_locked(struct rt_mutex_base *lock,
 
 	for (;;) {
 		/* Try to acquire the lock again */
-		if (try_to_take_rt_mutex(lock, current, &waiter))
+		if (try_to_take_rt_mutex(lock, current, &waiter)) {
+			lockevent_inc(rtlock_slow_acq2);
 			break;
+		}
 
 		if (&waiter == rt_mutex_top_waiter(lock))
 			owner = rt_mutex_owner(lock);
@@ -1847,8 +1863,10 @@ static void __sched rtlock_slowlock_locked(struct rt_mutex_base *lock,
 			owner = NULL;
 		raw_spin_unlock_irq_wake(&lock->wait_lock, wake_q);
 
-		if (!owner || !rtmutex_spin_on_owner(lock, &waiter, owner))
+		if (!owner || !rtmutex_spin_on_owner(lock, &waiter, owner)) {
+			lockevent_inc(rtlock_slow_sleep);
 			schedule_rtlock();
+		}
 
 		raw_spin_lock_irq(&lock->wait_lock);
 		set_current_state(TASK_RTLOCK_WAIT);
@@ -1865,6 +1883,7 @@ static void __sched rtlock_slowlock_locked(struct rt_mutex_base *lock,
 	debug_rt_mutex_free_waiter(&waiter);
 
 	trace_contention_end(lock, 0);
+	lockevent_cond_inc(rtlock_slow_wake, !wake_q_empty(wake_q));
 }
 
 static __always_inline void __sched rtlock_slowlock(struct rt_mutex_base *lock)

From a94d32446ab5e85c7ba97e48a8c9bd85be4fe889 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Fri, 7 Mar 2025 15:26:54 -0800
Subject: [PATCH 1095/1173] locking/lock_events: Add locking events for lockdep

Add some lock events to lockdep to profile its behavior.

Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250307232717.1759087-5-boqun.feng@gmail.com
---
 kernel/locking/lock_events_list.h | 7 +++++++
 kernel/locking/lockdep.c          | 8 +++++++-
 2 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/kernel/locking/lock_events_list.h b/kernel/locking/lock_events_list.h
index 80b11f194c9f7..9ef9850aeebe6 100644
--- a/kernel/locking/lock_events_list.h
+++ b/kernel/locking/lock_events_list.h
@@ -88,3 +88,10 @@ LOCK_EVENT(rtmutex_slow_acq3)	/* # of locks acquired in *block()	*/
 LOCK_EVENT(rtmutex_slow_sleep)	/* # of sleeps				*/
 LOCK_EVENT(rtmutex_slow_wake)	/* # of wakeup's			*/
 LOCK_EVENT(rtmutex_deadlock)	/* # of rt_mutex_handle_deadlock()'s	*/
+
+/*
+ * Locking events for lockdep
+ */
+LOCK_EVENT(lockdep_acquire)
+LOCK_EVENT(lockdep_lock)
+LOCK_EVENT(lockdep_nocheck)
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 4470680f02269..8436f017c74d8 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -61,6 +61,7 @@
 #include <asm/sections.h>
 
 #include "lockdep_internals.h"
+#include "lock_events.h"
 
 #include <trace/events/lock.h>
 
@@ -170,6 +171,7 @@ static struct task_struct *lockdep_selftest_task_struct;
 static int graph_lock(void)
 {
 	lockdep_lock();
+	lockevent_inc(lockdep_lock);
 	/*
 	 * Make sure that if another CPU detected a bug while
 	 * walking the graph we dont change it (while the other
@@ -5091,8 +5093,12 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	if (unlikely(lock->key == &__lockdep_no_track__))
 		return 0;
 
-	if (!prove_locking || lock->key == &__lockdep_no_validate__)
+	lockevent_inc(lockdep_acquire);
+
+	if (!prove_locking || lock->key == &__lockdep_no_validate__) {
 		check = 0;
+		lockevent_inc(lockdep_nocheck);
+	}
 
 	if (subclass < NR_LOCKDEP_CACHING_CLASSES)
 		class = lock->class_cache[subclass];

From ee57ab5a32129f599ee1d358548dbebcb5e45953 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Fri, 7 Mar 2025 15:26:55 -0800
Subject: [PATCH 1096/1173] locking/lockdep: Disable KASAN instrumentation of
 lockdep.c

Both KASAN and LOCKDEP are commonly enabled in building a debug kernel.
Each of them can significantly slow down the speed of a debug kernel.
Enabling KASAN instrumentation of the LOCKDEP code will further slow
things down.

Since LOCKDEP is a high overhead debugging tool, it will never get
enabled in a production kernel. The LOCKDEP code is also pretty mature
and is unlikely to get major changes. There is also a possibility of
recursion similar to KCSAN.

To evaluate the performance impact of disabling KASAN instrumentation
of lockdep.c, the time to do a parallel build of the Linux defconfig
kernel was used as the benchmark. Two x86-64 systems (Skylake & Zen 2)
and an arm64 system were used as test beds. Two sets of non-RT and RT
kernels with similar configurations except mainly CONFIG_PREEMPT_RT
were used for evaluation.

For the Skylake system:

  Kernel			Run time	    Sys time
  ------			--------	    --------
  Non-debug kernel (baseline)	0m47.642s	      4m19.811s

  [CONFIG_KASAN_INLINE=y]
  Debug kernel			2m11.108s (x2.8)     38m20.467s (x8.9)
  Debug kernel (patched)	1m49.602s (x2.3)     31m28.501s (x7.3)
  Debug kernel
  (patched + mitigations=off)	1m30.988s (x1.9)     26m41.993s (x6.2)

  RT kernel (baseline)		0m54.871s	      7m15.340s

  [CONFIG_KASAN_INLINE=n]
  RT debug kernel		6m07.151s (x6.7)    135m47.428s (x18.7)
  RT debug kernel (patched)	3m42.434s (x4.1)     74m51.636s (x10.3)
  RT debug kernel
  (patched + mitigations=off)	2m40.383s (x2.9)     57m54.369s (x8.0)

  [CONFIG_KASAN_INLINE=y]
  RT debug kernel		3m22.155s (x3.7)     77m53.018s (x10.7)
  RT debug kernel (patched)	2m36.700s (x2.9)     54m31.195s (x7.5)
  RT debug kernel
  (patched + mitigations=off)	2m06.110s (x2.3)     45m49.493s (x6.3)

For the Zen 2 system:

  Kernel			Run time	    Sys time
  ------			--------	    --------
  Non-debug kernel (baseline)	1m42.806s	     39m48.714s

  [CONFIG_KASAN_INLINE=y]
  Debug kernel			4m04.524s (x2.4)    125m35.904s (x3.2)
  Debug kernel (patched)	3m56.241s (x2.3)    127m22.378s (x3.2)
  Debug kernel
  (patched + mitigations=off)	2m38.157s (x1.5)     92m35.680s (x2.3)

  RT kernel (baseline)		 1m51.500s	     14m56.322s

  [CONFIG_KASAN_INLINE=n]
  RT debug kernel		16m04.962s (x8.7)   244m36.463s (x16.4)
  RT debug kernel (patched)	 9m09.073s (x4.9)   129m28.439s (x8.7)
  RT debug kernel
  (patched + mitigations=off)	 3m31.662s (x1.9)    51m01.391s (x3.4)

For the arm64 system:

  Kernel			Run time	    Sys time
  ------			--------	    --------
  Non-debug kernel (baseline)	1m56.844s	      8m47.150s
  Debug kernel			3m54.774s (x2.0)     92m30.098s (x10.5)
  Debug kernel (patched)	3m32.429s (x1.8)     77m40.779s (x8.8)

  RT kernel (baseline)		 4m01.641s	     18m16.777s

  [CONFIG_KASAN_INLINE=n]
  RT debug kernel		19m32.977s (x4.9)   304m23.965s (x16.7)
  RT debug kernel (patched)	16m28.354s (x4.1)   234m18.149s (x12.8)

Turning the mitigations off doesn't seems to have any noticeable impact
on the performance of the arm64 system. So the mitigation=off entries
aren't included.

For the x86 CPUs, CPU mitigations has a much bigger
impact on performance, especially the RT debug kernel with
CONFIG_KASAN_INLINE=n. The SRSO mitigation in Zen 2 has an especially
big impact on the debug kernel. It is also the majority of the slowdown
with mitigations on. It is because the patched RET instruction slows
down function returns. A lot of helper functions that are normally
compiled out or inlined may become real function calls in the debug
kernel.

With !CONFIG_KASAN_INLINE, the KASAN instrumentation inserts a
lot of __asan_loadX*() and __kasan_check_read() function calls to memory
access portion of the code. The lockdep's __lock_acquire() function,
for instance, has 66 __asan_loadX*() and 6 __kasan_check_read() calls
added with KASAN instrumentation. Of course, the actual numbers may vary
depending on the compiler used and the exact version of the lockdep code.

With the Skylake test system, the parallel kernel build times reduction
of the RT debug kernel with this patch are:

 CONFIG_KASAN_INLINE=n: -37%
 CONFIG_KASAN_INLINE=y: -22%

The time reduction is less with CONFIG_KASAN_INLINE=y, but it is still
significant.

Setting CONFIG_KASAN_INLINE=y can result in a significant performance
improvement. The major drawback is a significant increase in the size
of kernel text. In the case of vmlinux, its text size increases from
45997948 to 67606807. That is a 47% size increase (about 21 Mbytes). The
size increase of other kernel modules should be similar.

With the newly added rtmutex and lockdep lock events, the relevant
event counts for the test runs with the Skylake system were:

  Event type		Debug kernel	RT debug kernel
  ----------		------------	---------------
  lockdep_acquire	1,968,663,277	5,425,313,953
  rtlock_slowlock	     -		  401,701,156
  rtmutex_slowlock	     -		      139,672

The __lock_acquire() calls in the RT debug kernel are x2.8 times of the
non-RT debug kernel with the same workload. Since the __lock_acquire()
function is a big hitter in term of performance slowdown, this makes
the RT debug kernel much slower than the non-RT one. The average lock
nesting depth is likely to be higher in the RT debug kernel too leading
to longer execution time in the __lock_acquire() function.

As the small advantage of enabling KASAN instrumentation to catch
potential memory access error in the lockdep debugging tool is probably
not worth the drawback of further slowing down a debug kernel, disable
KASAN instrumentation in the lockdep code to allow the debug kernels
to regain some performance back, especially for the RT debug kernels.

Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Marco Elver <elver@google.com>
Reviewed-by: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250307232717.1759087-6-boqun.feng@gmail.com
---
 kernel/locking/Makefile | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
index 0db4093d17b8a..a114949eeed5e 100644
--- a/kernel/locking/Makefile
+++ b/kernel/locking/Makefile
@@ -5,7 +5,8 @@ KCOV_INSTRUMENT		:= n
 
 obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o
 
-# Avoid recursion lockdep -> sanitizer -> ... -> lockdep.
+# Avoid recursion lockdep -> sanitizer -> ... -> lockdep & improve performance.
+KASAN_SANITIZE_lockdep.o := n
 KCSAN_SANITIZE_lockdep.o := n
 
 ifdef CONFIG_FUNCTION_TRACER

From de4b59d652646cf00cf632174348ca2266099edc Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Fri, 7 Mar 2025 15:26:56 -0800
Subject: [PATCH 1097/1173] locking/lockdep: Add kasan_check_byte() check in
 lock_acquire()

KASAN instrumentation of lockdep has been disabled, as we don't need
KASAN to check the validity of lockdep internal data structures and
incur unnecessary performance overhead. However, the lockdep_map pointer
passed in externally may not be valid (e.g. use-after-free) and we run
the risk of using garbage data resulting in false lockdep reports.

Add kasan_check_byte() call in lock_acquire() for non kernel core data
object to catch invalid lockdep_map and print out a KASAN report before
any lockdep splat, if any.

Suggested-by: Marco Elver <elver@google.com>
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Marco Elver <elver@google.com>
Reviewed-by: Andrey Konovalov <andreyknvl@gmail.com>
Link: https://lore.kernel.org/r/20250214195242.2480920-1-longman@redhat.com
Link: https://lore.kernel.org/r/20250307232717.1759087-7-boqun.feng@gmail.com
---
 kernel/locking/lockdep.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 8436f017c74d8..b15757e636261 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -57,6 +57,7 @@
 #include <linux/lockdep.h>
 #include <linux/context_tracking.h>
 #include <linux/console.h>
+#include <linux/kasan.h>
 
 #include <asm/sections.h>
 
@@ -5830,6 +5831,14 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	if (!debug_locks)
 		return;
 
+	/*
+	 * As KASAN instrumentation is disabled and lock_acquire() is usually
+	 * the first lockdep call when a task tries to acquire a lock, add
+	 * kasan_check_byte() here to check for use-after-free and other
+	 * memory errors.
+	 */
+	kasan_check_byte(lock);
+
 	if (unlikely(!lockdep_enabled())) {
 		/* XXX allow trylock from NMI ?!? */
 		if (lockdep_nmi() && !trylock) {

From 8f65291dae0e75941cf76e427088e5612c4d692e Mon Sep 17 00:00:00 2001
From: Alice Ryhl <aliceryhl@google.com>
Date: Fri, 7 Mar 2025 15:26:57 -0800
Subject: [PATCH 1098/1173] rust: sync: Add accessor for the lock behind a
 given guard

In order to assert a particular `Guard` is associated with a particular
`Lock`, add an accessor to obtain a reference to the underlying `Lock`
of a `Guard`.

Binder needs this assertion to ensure unsafe list operations are done
with the correct lock held.

[Boqun: Capitalize the title and reword the commit log]

Signed-off-by: Alice Ryhl <aliceryhl@google.com>
Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Fiona Behrens <me@kloenk.dev>
Link: https://lore.kernel.org/r/20250205-guard-get-lock-v2-1-ba32a8c1d5b7@google.com
Link: https://lore.kernel.org/r/20250307232717.1759087-8-boqun.feng@gmail.com
---
 rust/kernel/sync/lock.rs | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/rust/kernel/sync/lock.rs b/rust/kernel/sync/lock.rs
index eb80048e0110d..8e7e6d5f61e4c 100644
--- a/rust/kernel/sync/lock.rs
+++ b/rust/kernel/sync/lock.rs
@@ -199,7 +199,12 @@ pub struct Guard<'a, T: ?Sized, B: Backend> {
 // SAFETY: `Guard` is sync when the data protected by the lock is also sync.
 unsafe impl<T: Sync + ?Sized, B: Backend> Sync for Guard<'_, T, B> {}
 
-impl<T: ?Sized, B: Backend> Guard<'_, T, B> {
+impl<'a, T: ?Sized, B: Backend> Guard<'a, T, B> {
+    /// Returns the lock that this guard originates from.
+    pub fn lock_ref(&self) -> &'a Lock<T, B> {
+        self.lock
+    }
+
     pub(crate) fn do_unlocked<U>(&mut self, cb: impl FnOnce() -> U) -> U {
         // SAFETY: The caller owns the lock, so it is safe to unlock it.
         unsafe { B::unlock(self.lock.state.get(), &self.state) };

From c2849afafd08a1c3ad881129de48ebe1642f7675 Mon Sep 17 00:00:00 2001
From: Boqun Feng <boqun.feng@gmail.com>
Date: Fri, 7 Mar 2025 15:26:58 -0800
Subject: [PATCH 1099/1173] rust: sync: lock: Add an example for Guard::
 Lock_ref()

To provide examples on usage of `Guard::lock_ref()` along with the unit
test, an "assert a lock is held by a guard" example is added.

(Also apply feedback from Benno.)

Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Link: https://lore.kernel.org/r/20250223072114.3715-1-boqun.feng@gmail.com
Link: https://lore.kernel.org/r/20250307232717.1759087-9-boqun.feng@gmail.com
---
 rust/kernel/sync/lock.rs | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/rust/kernel/sync/lock.rs b/rust/kernel/sync/lock.rs
index 8e7e6d5f61e4c..f53e87d04cd26 100644
--- a/rust/kernel/sync/lock.rs
+++ b/rust/kernel/sync/lock.rs
@@ -201,6 +201,30 @@ unsafe impl<T: Sync + ?Sized, B: Backend> Sync for Guard<'_, T, B> {}
 
 impl<'a, T: ?Sized, B: Backend> Guard<'a, T, B> {
     /// Returns the lock that this guard originates from.
+    ///
+    /// # Examples
+    ///
+    /// The following example shows how to use [`Guard::lock_ref()`] to assert the corresponding
+    /// lock is held.
+    ///
+    /// ```
+    /// # use kernel::{new_spinlock, stack_pin_init, sync::lock::{Backend, Guard, Lock}};
+    ///
+    /// fn assert_held<T, B: Backend>(guard: &Guard<'_, T, B>, lock: &Lock<T, B>) {
+    ///     // Address-equal means the same lock.
+    ///     assert!(core::ptr::eq(guard.lock_ref(), lock));
+    /// }
+    ///
+    /// // Creates a new lock on the stack.
+    /// stack_pin_init!{
+    ///     let l = new_spinlock!(42)
+    /// }
+    ///
+    /// let g = l.lock();
+    ///
+    /// // `g` originates from `l`.
+    /// assert_held(&g, &l);
+    /// ```
     pub fn lock_ref(&self) -> &'a Lock<T, B> {
         self.lock
     }

From 70b9c8563c9c29102a785d4822f0d77d33fee808 Mon Sep 17 00:00:00 2001
From: Alice Ryhl <aliceryhl@google.com>
Date: Fri, 7 Mar 2025 15:26:59 -0800
Subject: [PATCH 1100/1173] rust: sync: condvar: Add
 wait_interruptible_freezable()

To support waiting for a `CondVar` as a freezable process, add a
wait_interruptible_freezable() function.

Binder needs this function in the appropriate places to freeze a process
where some of its threads are blocked on the Binder driver.

[ Boqun: Cleaned up the changelog and documentation. ]

Signed-off-by: Alice Ryhl <aliceryhl@google.com>
Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250307232717.1759087-10-boqun.feng@gmail.com
---
 rust/kernel/sync/condvar.rs | 23 ++++++++++++++++++++++-
 rust/kernel/task.rs         |  2 ++
 2 files changed, 24 insertions(+), 1 deletion(-)

diff --git a/rust/kernel/sync/condvar.rs b/rust/kernel/sync/condvar.rs
index 7df565038d7d0..5c1e546a26c32 100644
--- a/rust/kernel/sync/condvar.rs
+++ b/rust/kernel/sync/condvar.rs
@@ -11,7 +11,9 @@ use crate::{
     init::PinInit,
     pin_init,
     str::CStr,
-    task::{MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE, TASK_NORMAL, TASK_UNINTERRUPTIBLE},
+    task::{
+        MAX_SCHEDULE_TIMEOUT, TASK_FREEZABLE, TASK_INTERRUPTIBLE, TASK_NORMAL, TASK_UNINTERRUPTIBLE,
+    },
     time::Jiffies,
     types::Opaque,
 };
@@ -159,6 +161,25 @@ impl CondVar {
         crate::current!().signal_pending()
     }
 
+    /// Releases the lock and waits for a notification in interruptible and freezable mode.
+    ///
+    /// The process is allowed to be frozen during this sleep. No lock should be held when calling
+    /// this function, and there is a lockdep assertion for this. Freezing a task that holds a lock
+    /// can trivially deadlock vs another task that needs that lock to complete before it too can
+    /// hit freezable.
+    #[must_use = "wait_interruptible_freezable returns if a signal is pending, so the caller must check the return value"]
+    pub fn wait_interruptible_freezable<T: ?Sized, B: Backend>(
+        &self,
+        guard: &mut Guard<'_, T, B>,
+    ) -> bool {
+        self.wait_internal(
+            TASK_INTERRUPTIBLE | TASK_FREEZABLE,
+            guard,
+            MAX_SCHEDULE_TIMEOUT,
+        );
+        crate::current!().signal_pending()
+    }
+
     /// Releases the lock and waits for a notification in interruptible mode.
     ///
     /// Atomically releases the given lock (whose ownership is proven by the guard) and puts the
diff --git a/rust/kernel/task.rs b/rust/kernel/task.rs
index 07bc22a7645c0..ea43a3b8d9c57 100644
--- a/rust/kernel/task.rs
+++ b/rust/kernel/task.rs
@@ -23,6 +23,8 @@ pub const MAX_SCHEDULE_TIMEOUT: c_long = c_long::MAX;
 pub const TASK_INTERRUPTIBLE: c_int = bindings::TASK_INTERRUPTIBLE as c_int;
 /// Bitmask for tasks that are sleeping in an uninterruptible state.
 pub const TASK_UNINTERRUPTIBLE: c_int = bindings::TASK_UNINTERRUPTIBLE as c_int;
+/// Bitmask for tasks that are sleeping in a freezable state.
+pub const TASK_FREEZABLE: c_int = bindings::TASK_FREEZABLE as c_int;
 /// Convenience constant for waking up tasks regardless of whether they are in interruptible or
 /// uninterruptible sleep.
 pub const TASK_NORMAL: c_uint = bindings::TASK_NORMAL as c_uint;

From f73ca66f0d7f4371d172d6f5b1f9a00e367ba921 Mon Sep 17 00:00:00 2001
From: Mitchell Levy <levymitchell0@gmail.com>
Date: Fri, 7 Mar 2025 15:27:01 -0800
Subject: [PATCH 1101/1173] rust: lockdep: Use Pin for all LockClassKey usages

Reintroduce dynamically-allocated LockClassKeys such that they are
automatically (de)registered. Require that all usages of LockClassKeys
ensure that they are Pin'd.

Currently, only `'static` LockClassKeys are supported, so Pin is
redundant. However, it is intended that dynamically-allocated
LockClassKeys will eventually be supported, so using Pin from the outset
will make that change simpler.

Closes: https://github.com/Rust-for-Linux/linux/issues/1102
Suggested-by: Benno Lossin <benno.lossin@proton.me>
Suggested-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Mitchell Levy <levymitchell0@gmail.com>
Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Link: https://lore.kernel.org/r/20250307232717.1759087-12-boqun.feng@gmail.com
---
 rust/helpers/helpers.c          |  1 +
 rust/helpers/sync.c             | 13 ++++++++
 rust/kernel/sync.rs             | 57 +++++++++++++++++++++++++++++++--
 rust/kernel/sync/condvar.rs     |  5 ++-
 rust/kernel/sync/lock.rs        |  4 +--
 rust/kernel/sync/lock/global.rs |  5 +--
 rust/kernel/sync/poll.rs        |  2 +-
 rust/kernel/workqueue.rs        |  2 +-
 8 files changed, 77 insertions(+), 12 deletions(-)
 create mode 100644 rust/helpers/sync.c

diff --git a/rust/helpers/helpers.c b/rust/helpers/helpers.c
index 0640b7e115be1..4c1a10a419cf1 100644
--- a/rust/helpers/helpers.c
+++ b/rust/helpers/helpers.c
@@ -30,6 +30,7 @@
 #include "signal.c"
 #include "slab.c"
 #include "spinlock.c"
+#include "sync.c"
 #include "task.c"
 #include "uaccess.c"
 #include "vmalloc.c"
diff --git a/rust/helpers/sync.c b/rust/helpers/sync.c
new file mode 100644
index 0000000000000..ff7e68b488101
--- /dev/null
+++ b/rust/helpers/sync.c
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/lockdep.h>
+
+void rust_helper_lockdep_register_key(struct lock_class_key *k)
+{
+	lockdep_register_key(k);
+}
+
+void rust_helper_lockdep_unregister_key(struct lock_class_key *k)
+{
+	lockdep_unregister_key(k);
+}
diff --git a/rust/kernel/sync.rs b/rust/kernel/sync.rs
index 16eab9138b2ba..4104bc26471a4 100644
--- a/rust/kernel/sync.rs
+++ b/rust/kernel/sync.rs
@@ -5,6 +5,8 @@
 //! This module contains the kernel APIs related to synchronisation that have been ported or
 //! wrapped for usage by Rust code in the kernel.
 
+use crate::pin_init;
+use crate::prelude::*;
 use crate::types::Opaque;
 
 mod arc;
@@ -23,15 +25,64 @@ pub use locked_by::LockedBy;
 
 /// Represents a lockdep class. It's a wrapper around C's `lock_class_key`.
 #[repr(transparent)]
-pub struct LockClassKey(Opaque<bindings::lock_class_key>);
+#[pin_data(PinnedDrop)]
+pub struct LockClassKey {
+    #[pin]
+    inner: Opaque<bindings::lock_class_key>,
+}
 
 // SAFETY: `bindings::lock_class_key` is designed to be used concurrently from multiple threads and
 // provides its own synchronization.
 unsafe impl Sync for LockClassKey {}
 
 impl LockClassKey {
+    /// Initializes a dynamically allocated lock class key. In the common case of using a
+    /// statically allocated lock class key, the static_lock_class! macro should be used instead.
+    ///
+    /// # Example
+    /// ```
+    /// # use kernel::{c_str, stack_pin_init};
+    /// # use kernel::alloc::KBox;
+    /// # use kernel::types::ForeignOwnable;
+    /// # use kernel::sync::{LockClassKey, SpinLock};
+    ///
+    /// let key = KBox::pin_init(LockClassKey::new_dynamic(), GFP_KERNEL)?;
+    /// let key_ptr = key.into_foreign();
+    ///
+    /// {
+    ///     stack_pin_init!(let num: SpinLock<u32> = SpinLock::new(
+    ///         0,
+    ///         c_str!("my_spinlock"),
+    ///         // SAFETY: `key_ptr` is returned by the above `into_foreign()`, whose
+    ///         // `from_foreign()` has not yet been called.
+    ///         unsafe { <Pin<KBox<LockClassKey>> as ForeignOwnable>::borrow(key_ptr) }
+    ///     ));
+    /// }
+    ///
+    /// // SAFETY: We dropped `num`, the only use of the key, so the result of the previous
+    /// // `borrow` has also been dropped. Thus, it's safe to use from_foreign.
+    /// unsafe { drop(<Pin<KBox<LockClassKey>> as ForeignOwnable>::from_foreign(key_ptr)) };
+    ///
+    /// # Ok::<(), Error>(())
+    /// ```
+    pub fn new_dynamic() -> impl PinInit<Self> {
+        pin_init!(Self {
+            // SAFETY: lockdep_register_key expects an uninitialized block of memory
+            inner <- Opaque::ffi_init(|slot| unsafe { bindings::lockdep_register_key(slot) })
+        })
+    }
+
     pub(crate) fn as_ptr(&self) -> *mut bindings::lock_class_key {
-        self.0.get()
+        self.inner.get()
+    }
+}
+
+#[pinned_drop]
+impl PinnedDrop for LockClassKey {
+    fn drop(self: Pin<&mut Self>) {
+        // SAFETY: self.as_ptr was registered with lockdep and self is pinned, so the address
+        // hasn't changed. Thus, it's safe to pass to unregister.
+        unsafe { bindings::lockdep_unregister_key(self.as_ptr()) }
     }
 }
 
@@ -44,7 +95,7 @@ macro_rules! static_lock_class {
             // SAFETY: lockdep expects uninitialized memory when it's handed a statically allocated
             // lock_class_key
             unsafe { ::core::mem::MaybeUninit::uninit().assume_init() };
-        &CLASS
+        $crate::prelude::Pin::static_ref(&CLASS)
     }};
 }
 
diff --git a/rust/kernel/sync/condvar.rs b/rust/kernel/sync/condvar.rs
index 5c1e546a26c32..fbf68ada582f6 100644
--- a/rust/kernel/sync/condvar.rs
+++ b/rust/kernel/sync/condvar.rs
@@ -17,8 +17,7 @@ use crate::{
     time::Jiffies,
     types::Opaque,
 };
-use core::marker::PhantomPinned;
-use core::ptr;
+use core::{marker::PhantomPinned, pin::Pin, ptr};
 use macros::pin_data;
 
 /// Creates a [`CondVar`] initialiser with the given name and a newly-created lock class.
@@ -103,7 +102,7 @@ unsafe impl Sync for CondVar {}
 
 impl CondVar {
     /// Constructs a new condvar initialiser.
-    pub fn new(name: &'static CStr, key: &'static LockClassKey) -> impl PinInit<Self> {
+    pub fn new(name: &'static CStr, key: Pin<&'static LockClassKey>) -> impl PinInit<Self> {
         pin_init!(Self {
             _pin: PhantomPinned,
             // SAFETY: `slot` is valid while the closure is called and both `name` and `key` have
diff --git a/rust/kernel/sync/lock.rs b/rust/kernel/sync/lock.rs
index f53e87d04cd26..360a10a9216d6 100644
--- a/rust/kernel/sync/lock.rs
+++ b/rust/kernel/sync/lock.rs
@@ -12,7 +12,7 @@ use crate::{
     str::CStr,
     types::{NotThreadSafe, Opaque, ScopeGuard},
 };
-use core::{cell::UnsafeCell, marker::PhantomPinned};
+use core::{cell::UnsafeCell, marker::PhantomPinned, pin::Pin};
 use macros::pin_data;
 
 pub mod mutex;
@@ -129,7 +129,7 @@ unsafe impl<T: ?Sized + Send, B: Backend> Sync for Lock<T, B> {}
 
 impl<T, B: Backend> Lock<T, B> {
     /// Constructs a new lock initialiser.
-    pub fn new(t: T, name: &'static CStr, key: &'static LockClassKey) -> impl PinInit<Self> {
+    pub fn new(t: T, name: &'static CStr, key: Pin<&'static LockClassKey>) -> impl PinInit<Self> {
         pin_init!(Self {
             data: UnsafeCell::new(t),
             _pin: PhantomPinned,
diff --git a/rust/kernel/sync/lock/global.rs b/rust/kernel/sync/lock/global.rs
index 480ee724e3cc4..d65f94b5caf26 100644
--- a/rust/kernel/sync/lock/global.rs
+++ b/rust/kernel/sync/lock/global.rs
@@ -13,6 +13,7 @@ use crate::{
 use core::{
     cell::UnsafeCell,
     marker::{PhantomData, PhantomPinned},
+    pin::Pin,
 };
 
 /// Trait implemented for marker types for global locks.
@@ -26,7 +27,7 @@ pub trait GlobalLockBackend {
     /// The backend used for this global lock.
     type Backend: Backend + 'static;
     /// The class for this global lock.
-    fn get_lock_class() -> &'static LockClassKey;
+    fn get_lock_class() -> Pin<&'static LockClassKey>;
 }
 
 /// Type used for global locks.
@@ -270,7 +271,7 @@ macro_rules! global_lock {
             type Item = $valuety;
             type Backend = $crate::global_lock_inner!(backend $kind);
 
-            fn get_lock_class() -> &'static $crate::sync::LockClassKey {
+            fn get_lock_class() -> Pin<&'static $crate::sync::LockClassKey> {
                 $crate::static_lock_class!()
             }
         }
diff --git a/rust/kernel/sync/poll.rs b/rust/kernel/sync/poll.rs
index d5f17153b4244..c4934f82d68bd 100644
--- a/rust/kernel/sync/poll.rs
+++ b/rust/kernel/sync/poll.rs
@@ -89,7 +89,7 @@ pub struct PollCondVar {
 
 impl PollCondVar {
     /// Constructs a new condvar initialiser.
-    pub fn new(name: &'static CStr, key: &'static LockClassKey) -> impl PinInit<Self> {
+    pub fn new(name: &'static CStr, key: Pin<&'static LockClassKey>) -> impl PinInit<Self> {
         pin_init!(Self {
             inner <- CondVar::new(name, key),
         })
diff --git a/rust/kernel/workqueue.rs b/rust/kernel/workqueue.rs
index 0cd100d2aefb4..6b6f3ad089513 100644
--- a/rust/kernel/workqueue.rs
+++ b/rust/kernel/workqueue.rs
@@ -369,7 +369,7 @@ unsafe impl<T: ?Sized, const ID: u64> Sync for Work<T, ID> {}
 impl<T: ?Sized, const ID: u64> Work<T, ID> {
     /// Creates a new instance of [`Work`].
     #[inline]
-    pub fn new(name: &'static CStr, key: &'static LockClassKey) -> impl PinInit<Self>
+    pub fn new(name: &'static CStr, key: Pin<&'static LockClassKey>) -> impl PinInit<Self>
     where
         T: WorkItem<ID>,
     {

From da64a2359092ceec4f9dea5b329d0aef20104217 Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Sat, 8 Mar 2025 13:50:45 +0800
Subject: [PATCH 1102/1173] LoongArch: Convert unreachable() to BUG()

When compiling on LoongArch, there exists the following objtool warning
in arch/loongarch/kernel/machine_kexec.o:

  kexec_reboot() falls through to next function crash_shutdown_secondary()

Avoid using unreachable() as it can (and will in the absence of UBSAN)
generate fall-through code. Use BUG() so we get a "break BRK_BUG" trap
(with unreachable annotation).

Cc: stable@vger.kernel.org  # 6.12+
Acked-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kernel/machine_kexec.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/loongarch/kernel/machine_kexec.c b/arch/loongarch/kernel/machine_kexec.c
index 8ae641dc53bb7..f9381800e291c 100644
--- a/arch/loongarch/kernel/machine_kexec.c
+++ b/arch/loongarch/kernel/machine_kexec.c
@@ -126,14 +126,14 @@ void kexec_reboot(void)
 	/* All secondary cpus go to kexec_smp_wait */
 	if (smp_processor_id() > 0) {
 		relocated_kexec_smp_wait(NULL);
-		unreachable();
+		BUG();
 	}
 #endif
 
 	do_kexec = (void *)reboot_code_buffer;
 	do_kexec(efi_boot, cmdline_ptr, systable_ptr, start_addr, first_ind_entry);
 
-	unreachable();
+	BUG();
 }
 
 

From a0d3c8bcb9206ac207c7ad3182027c6b0a1319bb Mon Sep 17 00:00:00 2001
From: Yuli Wang <wangyuli@uniontech.com>
Date: Sat, 8 Mar 2025 13:51:32 +0800
Subject: [PATCH 1103/1173] LoongArch: Eliminate superfluous
 get_numa_distances_cnt()

In LoongArch, get_numa_distances_cnt() isn't in use, resulting in a
compiler warning.

Fix follow errors with clang-18 when W=1e:

arch/loongarch/kernel/acpi.c:259:28: error: unused function 'get_numa_distances_cnt' [-Werror,-Wunused-function]
  259 | static inline unsigned int get_numa_distances_cnt(struct acpi_table_slit *slit)
      |                            ^~~~~~~~~~~~~~~~~~~~~~
1 error generated.

Link: https://lore.kernel.org/all/Z7bHPVUH4lAezk0E@kernel.org/
Signed-off-by: Yuli Wang <wangyuli@uniontech.com>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kernel/acpi.c | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c
index 382a09a7152c3..1120ac2824f6e 100644
--- a/arch/loongarch/kernel/acpi.c
+++ b/arch/loongarch/kernel/acpi.c
@@ -249,18 +249,6 @@ static __init int setup_node(int pxm)
 	return acpi_map_pxm_to_node(pxm);
 }
 
-/*
- * Callback for SLIT parsing.  pxm_to_node() returns NUMA_NO_NODE for
- * I/O localities since SRAT does not list them.  I/O localities are
- * not supported at this point.
- */
-unsigned int numa_distance_cnt;
-
-static inline unsigned int get_numa_distances_cnt(struct acpi_table_slit *slit)
-{
-	return slit->locality_count;
-}
-
 void __init numa_set_distance(int from, int to, int distance)
 {
 	if ((u8)distance != distance || (from == to && distance != LOCAL_DISTANCE)) {

From c9117434c8f7523f0b77db4c5766f5011cc94677 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Sat, 8 Mar 2025 13:51:32 +0800
Subject: [PATCH 1104/1173] LoongArch: Use polling play_dead() when resuming
 from hibernation

When CONFIG_RANDOM_KMALLOC_CACHES or other randomization infrastructrue
enabled, the idle_task's stack may different between the booting kernel
and target kernel. So when resuming from hibernation, an ACTION_BOOT_CPU
IPI wakeup the idle instruction in arch_cpu_idle_dead() and jump to the
interrupt handler. But since the stack pointer is changed, the interrupt
handler cannot restore correct context.

So rename the current arch_cpu_idle_dead() to idle_play_dead(), make it
as the default version of play_dead(), and the new arch_cpu_idle_dead()
call play_dead() directly. For hibernation, implement an arch-specific
hibernate_resume_nonboot_cpu_disable() to use the polling version (idle
instruction is replace by nop, and irq is disabled) of play_dead(), i.e.
poll_play_dead(), to avoid IPI handler corrupting the idle_task's stack
when resuming from hibernation.

This solution is a little similar to commit 406f992e4a372dafbe3c ("x86 /
hibernate: Use hlt_play_dead() when resuming from hibernation").

Cc: stable@vger.kernel.org
Tested-by: Erpeng Xu <xuerpeng@uniontech.com>
Tested-by: Yuli Wang <wangyuli@uniontech.com>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kernel/smp.c | 47 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 46 insertions(+), 1 deletion(-)

diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c
index fbf747447f13f..4b24589c0b565 100644
--- a/arch/loongarch/kernel/smp.c
+++ b/arch/loongarch/kernel/smp.c
@@ -19,6 +19,7 @@
 #include <linux/smp.h>
 #include <linux/threads.h>
 #include <linux/export.h>
+#include <linux/suspend.h>
 #include <linux/syscore_ops.h>
 #include <linux/time.h>
 #include <linux/tracepoint.h>
@@ -423,7 +424,7 @@ void loongson_cpu_die(unsigned int cpu)
 	mb();
 }
 
-void __noreturn arch_cpu_idle_dead(void)
+static void __noreturn idle_play_dead(void)
 {
 	register uint64_t addr;
 	register void (*init_fn)(void);
@@ -447,6 +448,50 @@ void __noreturn arch_cpu_idle_dead(void)
 	BUG();
 }
 
+#ifdef CONFIG_HIBERNATION
+static void __noreturn poll_play_dead(void)
+{
+	register uint64_t addr;
+	register void (*init_fn)(void);
+
+	idle_task_exit();
+	__this_cpu_write(cpu_state, CPU_DEAD);
+
+	__smp_mb();
+	do {
+		__asm__ __volatile__("nop\n\t");
+		addr = iocsr_read64(LOONGARCH_IOCSR_MBUF0);
+	} while (addr == 0);
+
+	init_fn = (void *)TO_CACHE(addr);
+	iocsr_write32(0xffffffff, LOONGARCH_IOCSR_IPI_CLEAR);
+
+	init_fn();
+	BUG();
+}
+#endif
+
+static void (*play_dead)(void) = idle_play_dead;
+
+void __noreturn arch_cpu_idle_dead(void)
+{
+	play_dead();
+	BUG(); /* play_dead() doesn't return */
+}
+
+#ifdef CONFIG_HIBERNATION
+int hibernate_resume_nonboot_cpu_disable(void)
+{
+	int ret;
+
+	play_dead = poll_play_dead;
+	ret = suspend_disable_secondary_cpus();
+	play_dead = idle_play_dead;
+
+	return ret;
+}
+#endif
+
 #endif
 
 /*

From c8477bb0a8e7f6b2e47952b403c5cb67a6929e55 Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Sat, 8 Mar 2025 13:51:32 +0800
Subject: [PATCH 1105/1173] LoongArch: Set max_pfn with the PFN of the last
 page

The current max_pfn equals to zero. In this case, it causes user cannot
get some page information through /proc filesystem such as kpagecount.
The following message is displayed by stress-ng test suite with command
"stress-ng --verbose --physpage 1 -t 1".

 # stress-ng --verbose --physpage 1 -t 1
 stress-ng: error: [1691] physpage: cannot read page count for address 0x134ac000 in /proc/kpagecount, errno=22 (Invalid argument)
 stress-ng: error: [1691] physpage: cannot read page count for address 0x7ffff207c3a8 in /proc/kpagecount, errno=22 (Invalid argument)
 stress-ng: error: [1691] physpage: cannot read page count for address 0x134b0000 in /proc/kpagecount, errno=22 (Invalid argument)
 ...

After applying this patch, the kernel can pass the test.

 # stress-ng --verbose --physpage 1 -t 1
 stress-ng: debug: [1701] physpage: [1701] started (instance 0 on CPU 3)
 stress-ng: debug: [1701] physpage: [1701] exited (instance 0 on CPU 3)
 stress-ng: debug: [1700] physpage: [1701] terminated (success)

Cc: stable@vger.kernel.org  # 6.8+
Fixes: ff6c3d81f2e8 ("NUMA: optimize detection of memory with no node id assigned by firmware")
Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kernel/setup.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c
index edcfdfcad7d22..90cb3ca96f085 100644
--- a/arch/loongarch/kernel/setup.c
+++ b/arch/loongarch/kernel/setup.c
@@ -387,6 +387,9 @@ static void __init check_kernel_sections_mem(void)
  */
 static void __init arch_mem_init(char **cmdline_p)
 {
+	/* Recalculate max_low_pfn for "mem=xxx" */
+	max_pfn = max_low_pfn = PHYS_PFN(memblock_end_of_DRAM());
+
 	if (usermem)
 		pr_info("User-defined physical RAM map overwrite\n");
 

From 3109d5ff484b7bc7b955f166974c6776d91f247b Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Sat, 8 Mar 2025 13:51:32 +0800
Subject: [PATCH 1106/1173] LoongArch: Set hugetlb mmap base address aligned
 with pmd size

With ltp test case "testcases/bin/hugefork02", there is a dmesg error
report message such as:

 kernel BUG at mm/hugetlb.c:5550!
 Oops - BUG[#1]:
 CPU: 0 UID: 0 PID: 1517 Comm: hugefork02 Not tainted 6.14.0-rc2+ #241
 Hardware name: QEMU QEMU Virtual Machine, BIOS unknown 2/2/2022
 pc 90000000004eaf1c ra 9000000000485538 tp 900000010edbc000 sp 900000010edbf940
 a0 900000010edbfb00 a1 9000000108d20280 a2 00007fffe9474000 a3 00007ffff3474000
 a4 0000000000000000 a5 0000000000000003 a6 00000000003cadd3 a7 0000000000000000
 t0 0000000001ffffff t1 0000000001474000 t2 900000010ecd7900 t3 00007fffe9474000
 t4 00007fffe9474000 t5 0000000000000040 t6 900000010edbfb00 t7 0000000000000001
 t8 0000000000000005 u0 90000000004849d0 s9 900000010edbfa00 s0 9000000108d20280
 s1 00007fffe9474000 s2 0000000002000000 s3 9000000108d20280 s4 9000000002b38b10
 s5 900000010edbfb00 s6 00007ffff3474000 s7 0000000000000406 s8 900000010edbfa08
    ra: 9000000000485538 unmap_vmas+0x130/0x218
   ERA: 90000000004eaf1c __unmap_hugepage_range+0x6f4/0x7d0
  PRMD: 00000004 (PPLV0 +PIE -PWE)
  EUEN: 00000007 (+FPE +SXE +ASXE -BTE)
  ECFG: 00071c1d (LIE=0,2-4,10-12 VS=7)
 ESTAT: 000c0000 [BRK] (IS= ECode=12 EsubCode=0)
 PRID: 0014c010 (Loongson-64bit, Loongson-3A5000)
 Process hugefork02 (pid: 1517, threadinfo=00000000a670eaf4, task=000000007a95fc64)
 Call Trace:
 [<90000000004eaf1c>] __unmap_hugepage_range+0x6f4/0x7d0
 [<9000000000485534>] unmap_vmas+0x12c/0x218
 [<9000000000494068>] exit_mmap+0xe0/0x308
 [<900000000025fdc4>] mmput+0x74/0x180
 [<900000000026a284>] do_exit+0x294/0x898
 [<900000000026aa30>] do_group_exit+0x30/0x98
 [<900000000027bed4>] get_signal+0x83c/0x868
 [<90000000002457b4>] arch_do_signal_or_restart+0x54/0xfa0
 [<90000000015795e8>] irqentry_exit_to_user_mode+0xb8/0x138
 [<90000000002572d0>] tlb_do_page_fault_1+0x114/0x1b4

The problem is that base address allocated from hugetlbfs is not aligned
with pmd size. Here add a checking for hugetlbfs and align base address
with pmd size. After this patch the test case "testcases/bin/hugefork02"
passes to run.

This is similar to the commit 7f24cbc9c4d42db8a3c8484d1 ("mm/mmap: teach
generic_get_unmapped_area{_topdown} to handle hugetlb mappings").

Cc: stable@vger.kernel.org  # 6.13+
Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/mm/mmap.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/arch/loongarch/mm/mmap.c b/arch/loongarch/mm/mmap.c
index 914e82ff3f656..1df9e99582cc6 100644
--- a/arch/loongarch/mm/mmap.c
+++ b/arch/loongarch/mm/mmap.c
@@ -3,6 +3,7 @@
  * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
  */
 #include <linux/export.h>
+#include <linux/hugetlb.h>
 #include <linux/io.h>
 #include <linux/kfence.h>
 #include <linux/memblock.h>
@@ -63,8 +64,11 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp,
 	}
 
 	info.length = len;
-	info.align_mask = do_color_align ? (PAGE_MASK & SHM_ALIGN_MASK) : 0;
 	info.align_offset = pgoff << PAGE_SHIFT;
+	if (filp && is_file_hugepages(filp))
+		info.align_mask = huge_page_mask_align(filp);
+	else
+		info.align_mask = do_color_align ? (PAGE_MASK & SHM_ALIGN_MASK) : 0;
 
 	if (dir == DOWN) {
 		info.flags = VM_UNMAPPED_AREA_TOPDOWN;

From 6fb1867d5a44b0a061cf39d2492d23d314bcb8ce Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Sat, 8 Mar 2025 13:51:59 +0800
Subject: [PATCH 1107/1173] LoongArch: KVM: Add interrupt checking for AVEC

There is a newly added macro INT_AVEC with CSR ESTAT register, which is
bit 14 used for LoongArch AVEC support. AVEC interrupt status bit 14 is
supported with macro CSR_ESTAT_IS, so here replace the hard-coded value
0x1fff with macro CSR_ESTAT_IS so that the AVEC interrupt status is also
supported by KVM.

Cc: stable@vger.kernel.org
Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kvm/vcpu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c
index 20f941af3e9ea..9e1a9b4aa4c6a 100644
--- a/arch/loongarch/kvm/vcpu.c
+++ b/arch/loongarch/kvm/vcpu.c
@@ -311,7 +311,7 @@ static int kvm_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
 {
 	int ret = RESUME_GUEST;
 	unsigned long estat = vcpu->arch.host_estat;
-	u32 intr = estat & 0x1fff; /* Ignore NMI */
+	u32 intr = estat & CSR_ESTAT_IS;
 	u32 ecode = (estat & CSR_ESTAT_EXC) >> CSR_ESTAT_EXC_SHIFT;
 
 	vcpu->mode = OUTSIDE_GUEST_MODE;

From 78d7bc5a02e1468df53896df354fa80727f35b7d Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Sat, 8 Mar 2025 13:52:01 +0800
Subject: [PATCH 1108/1173] LoongArch: KVM: Reload guest CSR registers after
 sleep

On host, the HW guest CSR registers are lost after suspend and resume
operation. Since last_vcpu of boot CPU still records latest vCPU pointer
so that the guest CSR register skips to reload when boot CPU resumes and
vCPU is scheduled.

Here last_vcpu is cleared so that guest CSR registers will reload from
scheduled vCPU context after suspend and resume.

Cc: stable@vger.kernel.org
Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kvm/main.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/arch/loongarch/kvm/main.c b/arch/loongarch/kvm/main.c
index f6d3242b9234a..b6864d6e5ec8d 100644
--- a/arch/loongarch/kvm/main.c
+++ b/arch/loongarch/kvm/main.c
@@ -317,6 +317,13 @@ int kvm_arch_enable_virtualization_cpu(void)
 	kvm_debug("GCFG:%lx GSTAT:%lx GINTC:%lx GTLBC:%lx",
 		  read_csr_gcfg(), read_csr_gstat(), read_csr_gintc(), read_csr_gtlbc());
 
+	/*
+	 * HW Guest CSR registers are lost after CPU suspend and resume.
+	 * Clear last_vcpu so that Guest CSR registers forced to reload
+	 * from vCPU SW state.
+	 */
+	this_cpu_ptr(vmcs)->last_vcpu = NULL;
+
 	return 0;
 }
 

From 6bdbb73dc8d99fbb77f5db79dbb6f108708090b4 Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Sat, 8 Mar 2025 13:52:04 +0800
Subject: [PATCH 1109/1173] LoongArch: KVM: Fix GPA size issue about VM

Physical address space is 48 bit on Loongson-3A5000 physical machine,
however it is 47 bit for VM on Loongson-3A5000 system. Size of physical
address space of VM is the same with the size of virtual user space (a
half) of physical machine.

Variable cpu_vabits represents user address space, kernel address space
is not included (user space and kernel space are both a half of total).
Here cpu_vabits, rather than cpu_vabits - 1, is to represent the size of
guest physical address space.

Also there is strict checking about page fault GPA address, inject error
if it is larger than maximum GPA address of VM.

Cc: stable@vger.kernel.org
Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kvm/exit.c | 6 ++++++
 arch/loongarch/kvm/vm.c   | 6 +++++-
 2 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/arch/loongarch/kvm/exit.c b/arch/loongarch/kvm/exit.c
index c1e8ec5b941b2..ea321403644ad 100644
--- a/arch/loongarch/kvm/exit.c
+++ b/arch/loongarch/kvm/exit.c
@@ -669,6 +669,12 @@ static int kvm_handle_rdwr_fault(struct kvm_vcpu *vcpu, bool write)
 	struct kvm_run *run = vcpu->run;
 	unsigned long badv = vcpu->arch.badv;
 
+	/* Inject ADE exception if exceed max GPA size */
+	if (unlikely(badv >= vcpu->kvm->arch.gpa_size)) {
+		kvm_queue_exception(vcpu, EXCCODE_ADE, EXSUBCODE_ADEM);
+		return RESUME_GUEST;
+	}
+
 	ret = kvm_handle_mm_fault(vcpu, badv, write);
 	if (ret) {
 		/* Treat as MMIO */
diff --git a/arch/loongarch/kvm/vm.c b/arch/loongarch/kvm/vm.c
index b8b3e1972d6ea..edccfc8c9cd80 100644
--- a/arch/loongarch/kvm/vm.c
+++ b/arch/loongarch/kvm/vm.c
@@ -48,7 +48,11 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	if (kvm_pvtime_supported())
 		kvm->arch.pv_features |= BIT(KVM_FEATURE_STEAL_TIME);
 
-	kvm->arch.gpa_size = BIT(cpu_vabits - 1);
+	/*
+	 * cpu_vabits means user address space only (a half of total).
+	 * GPA size of VM is the same with the size of user address space.
+	 */
+	kvm->arch.gpa_size = BIT(cpu_vabits);
 	kvm->arch.root_level = CONFIG_PGTABLE_LEVELS - 1;
 	kvm->arch.invalid_ptes[0] = 0;
 	kvm->arch.invalid_ptes[1] = (unsigned long)invalid_pte_table;

From 0704bf439655c1f82ff7e623b1124a3c1cb8c907 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Mon, 3 Mar 2025 12:11:03 +0100
Subject: [PATCH 1110/1173] vdso: Introduce vdso/cache.h
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The vDSO implementation can only include headers from the vdso/
namespace. To enable the usage of ____cacheline_aligned from
the vDSO, move it and its dependencies into a new header vdso/cache.h.
Keep compatibility by including vdso/cache.h from linux/cache.h.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250303-vdso-clock-v1-1-c1b5c69a166f@linutronix.de
---
 include/linux/cache.h |  9 +--------
 include/vdso/cache.h  | 15 +++++++++++++++
 2 files changed, 16 insertions(+), 8 deletions(-)
 create mode 100644 include/vdso/cache.h

diff --git a/include/linux/cache.h b/include/linux/cache.h
index ca2a05682a54b..e69768f50d532 100644
--- a/include/linux/cache.h
+++ b/include/linux/cache.h
@@ -3,16 +3,13 @@
 #define __LINUX_CACHE_H
 
 #include <uapi/linux/kernel.h>
+#include <vdso/cache.h>
 #include <asm/cache.h>
 
 #ifndef L1_CACHE_ALIGN
 #define L1_CACHE_ALIGN(x) __ALIGN_KERNEL(x, L1_CACHE_BYTES)
 #endif
 
-#ifndef SMP_CACHE_BYTES
-#define SMP_CACHE_BYTES L1_CACHE_BYTES
-#endif
-
 /**
  * SMP_CACHE_ALIGN - align a value to the L2 cacheline size
  * @x: value to align
@@ -63,10 +60,6 @@
 #define __ro_after_init __section(".data..ro_after_init")
 #endif
 
-#ifndef ____cacheline_aligned
-#define ____cacheline_aligned __attribute__((__aligned__(SMP_CACHE_BYTES)))
-#endif
-
 #ifndef ____cacheline_aligned_in_smp
 #ifdef CONFIG_SMP
 #define ____cacheline_aligned_in_smp ____cacheline_aligned
diff --git a/include/vdso/cache.h b/include/vdso/cache.h
new file mode 100644
index 0000000000000..f89d48304bf8f
--- /dev/null
+++ b/include/vdso/cache.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __VDSO_CACHE_H
+#define __VDSO_CACHE_H
+
+#include <asm/cache.h>
+
+#ifndef SMP_CACHE_BYTES
+#define SMP_CACHE_BYTES L1_CACHE_BYTES
+#endif
+
+#ifndef ____cacheline_aligned
+#define ____cacheline_aligned __attribute__((__aligned__(SMP_CACHE_BYTES)))
+#endif
+
+#endif	/* __VDSO_ALIGN_H */

From b69b47a6b5f67ac1074e0a6baac7f07bdc3dceed Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Mon, 3 Mar 2025 12:11:04 +0100
Subject: [PATCH 1111/1173] arm64: Make asm/cache.h compatible with vDSO
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

asm/cache.h can be used during the vDSO build through vdso/cache.h.
Not all definitions in it are compatible with the vDSO, especially the
compat vDSO.

Hide the more complex definitions from the vDSO build.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250303-vdso-clock-v1-2-c1b5c69a166f@linutronix.de
---
 arch/arm64/include/asm/cache.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h
index 06a4670bdb0b9..99cd6546e72e3 100644
--- a/arch/arm64/include/asm/cache.h
+++ b/arch/arm64/include/asm/cache.h
@@ -35,7 +35,7 @@
 #define ARCH_DMA_MINALIGN	(128)
 #define ARCH_KMALLOC_MINALIGN	(8)
 
-#ifndef __ASSEMBLY__
+#if !defined(__ASSEMBLY__) && !defined(BUILD_VDSO)
 
 #include <linux/bitops.h>
 #include <linux/kasan-enabled.h>
@@ -118,6 +118,6 @@ static inline u32 __attribute_const__ read_cpuid_effective_cachetype(void)
 	return ctr;
 }
 
-#endif	/* __ASSEMBLY__ */
+#endif /* !defined(__ASSEMBLY__) && !defined(BUILD_VDSO) */
 
 #endif

From fa8152ca221110e14e43040bd442c8140bc2e03c Mon Sep 17 00:00:00 2001
From: Anna-Maria Behnsen <anna-maria@linutronix.de>
Date: Mon, 3 Mar 2025 12:11:05 +0100
Subject: [PATCH 1112/1173] vdso: Make vdso_time_data cacheline aligned
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

vdso_time_data is not cacheline aligned at the moment. When instantiating
an array, the start of the second array member is not cache line aligned.

This increases the number of the required cache lines which needs to be
read when handling e.g. CLOCK_MONOTONIC_RAW, because the data spawns an
extra cache line if the previous data does not end at a cache line
boundary.

Therefore make struct vdso_time_data cacheline aligned.

Signed-off-by: Anna-Maria Behnsen <anna-maria@linutronix.de>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250303-vdso-clock-v1-3-c1b5c69a166f@linutronix.de
---
 include/vdso/datapage.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/vdso/datapage.h b/include/vdso/datapage.h
index ed4fb4c06e3ee..dfd98f969f151 100644
--- a/include/vdso/datapage.h
+++ b/include/vdso/datapage.h
@@ -11,6 +11,7 @@
 
 #include <vdso/align.h>
 #include <vdso/bits.h>
+#include <vdso/cache.h>
 #include <vdso/clocksource.h>
 #include <vdso/ktime.h>
 #include <vdso/limits.h>
@@ -126,7 +127,7 @@ struct vdso_time_data {
 	u32			__unused;
 
 	struct arch_vdso_time_data arch_data;
-};
+} ____cacheline_aligned;
 
 /**
  * struct vdso_rng_data - vdso RNG state information

From a05f14de04e989f0bc32cea128243090e5e5d54b Mon Sep 17 00:00:00 2001
From: Anna-Maria Behnsen <anna-maria@linutronix.de>
Date: Mon, 3 Mar 2025 12:11:06 +0100
Subject: [PATCH 1113/1173] vdso/datapage: Define vdso_clock to prepare for
 multiple PTP clocks
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Multiple PTP clocks, which are independent of timekeeping, are required for
systems, which utilize PTP for synchronizing e.g. automation systems
independent of clock TAI.

PTP clocks are slow to access, but applications require fast access to the
relevant time similar to the regular timekeeping relevant clocks.

To prepare for that the VDSO data representation must be reworked. For
transition to the new structure of the vdso, add a define which maps
vdso_clock to vdso_data. This will be removed when all users are updated
step by step.

No functional change.

Signed-off-by: Anna-Maria Behnsen <anna-maria@linutronix.de>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250303-vdso-clock-v1-4-c1b5c69a166f@linutronix.de
---
 include/vdso/datapage.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/include/vdso/datapage.h b/include/vdso/datapage.h
index dfd98f969f151..1df22e8bb9b31 100644
--- a/include/vdso/datapage.h
+++ b/include/vdso/datapage.h
@@ -129,6 +129,8 @@ struct vdso_time_data {
 	struct arch_vdso_time_data arch_data;
 } ____cacheline_aligned;
 
+#define vdso_clock vdso_time_data
+
 /**
  * struct vdso_rng_data - vdso RNG state information
  * @generation:	counter representing the number of RNG reseeds

From e15bf9e34b5716e8c4a50b32a98752ff1f53d647 Mon Sep 17 00:00:00 2001
From: Anna-Maria Behnsen <anna-maria@linutronix.de>
Date: Mon, 3 Mar 2025 12:11:07 +0100
Subject: [PATCH 1114/1173] vdso/helpers: Prepare introduction of struct
 vdso_clock
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To support multiple PTP clocks, the VDSO data structure needs to be
reworked. All clock specific data will end up in struct vdso_clock and in
struct vdso_time_data there will be an array of VDSO clocks. For now,
vdso_clock is simply a define which maps vdso_clock to vdso_time_data.

Prepare all functions which need the pointer to the vdso_clock array to
work well after the structures get reworked. Replace the struct vdso_time_data
pointer with a struct vdso_clock pointer where applicable.

No functional change.

Signed-off-by: Anna-Maria Behnsen <anna-maria@linutronix.de>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250303-vdso-clock-v1-5-c1b5c69a166f@linutronix.de
---
 include/vdso/helpers.h | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/include/vdso/helpers.h b/include/vdso/helpers.h
index 41c3087070c7a..28f0707a46c62 100644
--- a/include/vdso/helpers.h
+++ b/include/vdso/helpers.h
@@ -7,49 +7,53 @@
 #include <asm/barrier.h>
 #include <vdso/datapage.h>
 
-static __always_inline u32 vdso_read_begin(const struct vdso_time_data *vd)
+static __always_inline u32 vdso_read_begin(const struct vdso_clock *vc)
 {
 	u32 seq;
 
-	while (unlikely((seq = READ_ONCE(vd->seq)) & 1))
+	while (unlikely((seq = READ_ONCE(vc->seq)) & 1))
 		cpu_relax();
 
 	smp_rmb();
 	return seq;
 }
 
-static __always_inline u32 vdso_read_retry(const struct vdso_time_data *vd,
+static __always_inline u32 vdso_read_retry(const struct vdso_clock *vc,
 					   u32 start)
 {
 	u32 seq;
 
 	smp_rmb();
-	seq = READ_ONCE(vd->seq);
+	seq = READ_ONCE(vc->seq);
 	return seq != start;
 }
 
 static __always_inline void vdso_write_begin(struct vdso_time_data *vd)
 {
+	struct vdso_clock *vc = vd;
+
 	/*
 	 * WRITE_ONCE() is required otherwise the compiler can validly tear
 	 * updates to vd[x].seq and it is possible that the value seen by the
 	 * reader is inconsistent.
 	 */
-	WRITE_ONCE(vd[CS_HRES_COARSE].seq, vd[CS_HRES_COARSE].seq + 1);
-	WRITE_ONCE(vd[CS_RAW].seq, vd[CS_RAW].seq + 1);
+	WRITE_ONCE(vc[CS_HRES_COARSE].seq, vc[CS_HRES_COARSE].seq + 1);
+	WRITE_ONCE(vc[CS_RAW].seq, vc[CS_RAW].seq + 1);
 	smp_wmb();
 }
 
 static __always_inline void vdso_write_end(struct vdso_time_data *vd)
 {
+	struct vdso_clock *vc = vd;
+
 	smp_wmb();
 	/*
 	 * WRITE_ONCE() is required otherwise the compiler can validly tear
 	 * updates to vd[x].seq and it is possible that the value seen by the
 	 * reader is inconsistent.
 	 */
-	WRITE_ONCE(vd[CS_HRES_COARSE].seq, vd[CS_HRES_COARSE].seq + 1);
-	WRITE_ONCE(vd[CS_RAW].seq, vd[CS_RAW].seq + 1);
+	WRITE_ONCE(vc[CS_HRES_COARSE].seq, vc[CS_HRES_COARSE].seq + 1);
+	WRITE_ONCE(vc[CS_RAW].seq, vc[CS_RAW].seq + 1);
 }
 
 #endif /* !__ASSEMBLY__ */

From cddb82d1c4de5649b6841a1b94a610f934c5dd5f Mon Sep 17 00:00:00 2001
From: Anna-Maria Behnsen <anna-maria@linutronix.de>
Date: Mon, 3 Mar 2025 12:11:08 +0100
Subject: [PATCH 1115/1173] vdso/gettimeofday: Prepare introduction of struct
 vdso_clock
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To support multiple PTP clocks, the VDSO data structure needs to be
reworked. All clock specific data will end up in struct vdso_clock and in
struct vdso_time_data there will be array of VDSO clocks. At the moment,
vdso_clock is simply a define which maps vdso_clock to vdso_time_data.

Prepare all functions which need the pointer to the vdso_clock array to
work correctly after introducing the new struct. Where applicable, replace
the struct vdso_time_data pointer by a struct vdso_clock pointer.

No functional change.

Signed-off-by: Anna-Maria Behnsen <anna-maria@linutronix.de>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250303-vdso-clock-v1-6-c1b5c69a166f@linutronix.de
---
 lib/vdso/gettimeofday.c | 24 +++++++++++++++---------
 1 file changed, 15 insertions(+), 9 deletions(-)

diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c
index 299f027116ee0..59369a4e9f25f 100644
--- a/lib/vdso/gettimeofday.c
+++ b/lib/vdso/gettimeofday.c
@@ -257,6 +257,7 @@ static __always_inline int
 __cvdso_clock_gettime_common(const struct vdso_time_data *vd, clockid_t clock,
 			     struct __kernel_timespec *ts)
 {
+	const struct vdso_clock *vc = vd;
 	u32 msk;
 
 	/* Check for negative values or invalid clocks */
@@ -269,15 +270,15 @@ __cvdso_clock_gettime_common(const struct vdso_time_data *vd, clockid_t clock,
 	 */
 	msk = 1U << clock;
 	if (likely(msk & VDSO_HRES))
-		vd = &vd[CS_HRES_COARSE];
+		vc = &vc[CS_HRES_COARSE];
 	else if (msk & VDSO_COARSE)
-		return do_coarse(&vd[CS_HRES_COARSE], clock, ts);
+		return do_coarse(&vc[CS_HRES_COARSE], clock, ts);
 	else if (msk & VDSO_RAW)
-		vd = &vd[CS_RAW];
+		vc = &vc[CS_RAW];
 	else
 		return -1;
 
-	return do_hres(vd, clock, ts);
+	return do_hres(vc, clock, ts);
 }
 
 static __maybe_unused int
@@ -328,11 +329,12 @@ static __maybe_unused int
 __cvdso_gettimeofday_data(const struct vdso_time_data *vd,
 			  struct __kernel_old_timeval *tv, struct timezone *tz)
 {
+	const struct vdso_clock *vc = vd;
 
 	if (likely(tv != NULL)) {
 		struct __kernel_timespec ts;
 
-		if (do_hres(&vd[CS_HRES_COARSE], CLOCK_REALTIME, &ts))
+		if (do_hres(&vc[CS_HRES_COARSE], CLOCK_REALTIME, &ts))
 			return gettimeofday_fallback(tv, tz);
 
 		tv->tv_sec = ts.tv_sec;
@@ -341,7 +343,7 @@ __cvdso_gettimeofday_data(const struct vdso_time_data *vd,
 
 	if (unlikely(tz != NULL)) {
 		if (IS_ENABLED(CONFIG_TIME_NS) &&
-		    vd->clock_mode == VDSO_CLOCKMODE_TIMENS)
+		    vc->clock_mode == VDSO_CLOCKMODE_TIMENS)
 			vd = __arch_get_vdso_u_timens_data(vd);
 
 		tz->tz_minuteswest = vd[CS_HRES_COARSE].tz_minuteswest;
@@ -361,13 +363,16 @@ __cvdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
 static __maybe_unused __kernel_old_time_t
 __cvdso_time_data(const struct vdso_time_data *vd, __kernel_old_time_t *time)
 {
+	const struct vdso_clock *vc = vd;
 	__kernel_old_time_t t;
 
 	if (IS_ENABLED(CONFIG_TIME_NS) &&
-	    vd->clock_mode == VDSO_CLOCKMODE_TIMENS)
+	    vc->clock_mode == VDSO_CLOCKMODE_TIMENS) {
 		vd = __arch_get_vdso_u_timens_data(vd);
+		vc = vd;
+	}
 
-	t = READ_ONCE(vd[CS_HRES_COARSE].basetime[CLOCK_REALTIME].sec);
+	t = READ_ONCE(vc[CS_HRES_COARSE].basetime[CLOCK_REALTIME].sec);
 
 	if (time)
 		*time = t;
@@ -386,6 +391,7 @@ static __maybe_unused
 int __cvdso_clock_getres_common(const struct vdso_time_data *vd, clockid_t clock,
 				struct __kernel_timespec *res)
 {
+	const struct vdso_clock *vc = vd;
 	u32 msk;
 	u64 ns;
 
@@ -394,7 +400,7 @@ int __cvdso_clock_getres_common(const struct vdso_time_data *vd, clockid_t clock
 		return -1;
 
 	if (IS_ENABLED(CONFIG_TIME_NS) &&
-	    vd->clock_mode == VDSO_CLOCKMODE_TIMENS)
+	    vc->clock_mode == VDSO_CLOCKMODE_TIMENS)
 		vd = __arch_get_vdso_u_timens_data(vd);
 
 	/*

From 64c3613ce31a1a58e43c2d86eafbb03364986450 Mon Sep 17 00:00:00 2001
From: Anna-Maria Behnsen <anna-maria@linutronix.de>
Date: Mon, 3 Mar 2025 12:11:09 +0100
Subject: [PATCH 1116/1173] vdso/gettimeofday: Prepare do_hres() for
 introduction of struct vdso_clock
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To support multiple PTP clocks, the VDSO data structure needs to be
reworked. All clock specific data will end up in struct vdso_clock and in
struct vdso_time_data there will be array of VDSO clocks. At the moment,
vdso_clock is simply a define which maps vdso_clock to vdso_time_data.

Prepare for the rework of these structures by adding a struct vdso_clock
pointer argument to do_hres(), and replace the struct vdso_time_data
pointer with the new pointer argument where applicable.

No functional change.

Signed-off-by: Anna-Maria Behnsen <anna-maria@linutronix.de>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250303-vdso-clock-v1-7-c1b5c69a166f@linutronix.de
---
 lib/vdso/gettimeofday.c | 33 +++++++++++++++++----------------
 1 file changed, 17 insertions(+), 16 deletions(-)

diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c
index 59369a4e9f25f..15611ab650232 100644
--- a/lib/vdso/gettimeofday.c
+++ b/lib/vdso/gettimeofday.c
@@ -139,10 +139,11 @@ static __always_inline int do_hres_timens(const struct vdso_time_data *vdns, clo
 }
 #endif
 
-static __always_inline int do_hres(const struct vdso_time_data *vd, clockid_t clk,
-				   struct __kernel_timespec *ts)
+static __always_inline
+int do_hres(const struct vdso_time_data *vd, const struct vdso_clock *vc,
+	    clockid_t clk, struct __kernel_timespec *ts)
 {
-	const struct vdso_timestamp *vdso_ts = &vd->basetime[clk];
+	const struct vdso_timestamp *vdso_ts = &vc->basetime[clk];
 	u64 cycles, sec, ns;
 	u32 seq;
 
@@ -154,31 +155,31 @@ static __always_inline int do_hres(const struct vdso_time_data *vd, clockid_t cl
 		/*
 		 * Open coded function vdso_read_begin() to handle
 		 * VDSO_CLOCKMODE_TIMENS. Time namespace enabled tasks have a
-		 * special VVAR page installed which has vd->seq set to 1 and
-		 * vd->clock_mode set to VDSO_CLOCKMODE_TIMENS. For non time
+		 * special VVAR page installed which has vc->seq set to 1 and
+		 * vc->clock_mode set to VDSO_CLOCKMODE_TIMENS. For non time
 		 * namespace affected tasks this does not affect performance
-		 * because if vd->seq is odd, i.e. a concurrent update is in
-		 * progress the extra check for vd->clock_mode is just a few
-		 * extra instructions while spin waiting for vd->seq to become
+		 * because if vc->seq is odd, i.e. a concurrent update is in
+		 * progress the extra check for vc->clock_mode is just a few
+		 * extra instructions while spin waiting for vc->seq to become
 		 * even again.
 		 */
-		while (unlikely((seq = READ_ONCE(vd->seq)) & 1)) {
+		while (unlikely((seq = READ_ONCE(vc->seq)) & 1)) {
 			if (IS_ENABLED(CONFIG_TIME_NS) &&
-			    vd->clock_mode == VDSO_CLOCKMODE_TIMENS)
+			    vc->clock_mode == VDSO_CLOCKMODE_TIMENS)
 				return do_hres_timens(vd, clk, ts);
 			cpu_relax();
 		}
 		smp_rmb();
 
-		if (unlikely(!vdso_clocksource_ok(vd)))
+		if (unlikely(!vdso_clocksource_ok(vc)))
 			return -1;
 
-		cycles = __arch_get_hw_counter(vd->clock_mode, vd);
+		cycles = __arch_get_hw_counter(vc->clock_mode, vd);
 		if (unlikely(!vdso_cycles_ok(cycles)))
 			return -1;
-		ns = vdso_calc_ns(vd, cycles, vdso_ts->nsec);
+		ns = vdso_calc_ns(vc, cycles, vdso_ts->nsec);
 		sec = vdso_ts->sec;
-	} while (unlikely(vdso_read_retry(vd, seq)));
+	} while (unlikely(vdso_read_retry(vc, seq)));
 
 	/*
 	 * Do this outside the loop: a race inside the loop could result
@@ -278,7 +279,7 @@ __cvdso_clock_gettime_common(const struct vdso_time_data *vd, clockid_t clock,
 	else
 		return -1;
 
-	return do_hres(vc, clock, ts);
+	return do_hres(vd, vc, clock, ts);
 }
 
 static __maybe_unused int
@@ -334,7 +335,7 @@ __cvdso_gettimeofday_data(const struct vdso_time_data *vd,
 	if (likely(tv != NULL)) {
 		struct __kernel_timespec ts;
 
-		if (do_hres(&vc[CS_HRES_COARSE], CLOCK_REALTIME, &ts))
+		if (do_hres(vd, &vc[CS_HRES_COARSE], CLOCK_REALTIME, &ts))
 			return gettimeofday_fallback(tv, tz);
 
 		tv->tv_sec = ts.tv_sec;

From 83a2a6b8cfc574dae4e3c65018392dcedc59079a Mon Sep 17 00:00:00 2001
From: Anna-Maria Behnsen <anna-maria@linutronix.de>
Date: Mon, 3 Mar 2025 12:11:10 +0100
Subject: [PATCH 1117/1173] vdso/gettimeofday: Prepare do_hres_timens() for
 introduction of struct vdso_clock
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To support multiple PTP clocks, the VDSO data structure needs to be
reworked. All clock specific data will end up in struct vdso_clock and in
struct vdso_time_data there will be array of VDSO clocks. At the moment,
vdso_clock is simply a define which maps vdso_clock to vdso_time_data.

Prepare for the rework of these structures by adding a struct vdso_clock
pointer argument to do_hres_timens(), and replace the struct vdso_time_data
pointer with the new pointer argument where applicable.

No functional change.

Signed-off-by: Anna-Maria Behnsen <anna-maria@linutronix.de>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250303-vdso-clock-v1-8-c1b5c69a166f@linutronix.de
---
 lib/vdso/gettimeofday.c | 35 ++++++++++++++++++-----------------
 1 file changed, 18 insertions(+), 17 deletions(-)

diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c
index 15611ab650232..e8d4b02bcb616 100644
--- a/lib/vdso/gettimeofday.c
+++ b/lib/vdso/gettimeofday.c
@@ -81,36 +81,36 @@ const struct vdso_time_data *__arch_get_vdso_u_timens_data(const struct vdso_tim
 }
 #endif /* CONFIG_GENERIC_VDSO_DATA_STORE */
 
-static __always_inline int do_hres_timens(const struct vdso_time_data *vdns, clockid_t clk,
-					  struct __kernel_timespec *ts)
+static __always_inline
+int do_hres_timens(const struct vdso_time_data *vdns, const struct vdso_clock *vcns,
+		   clockid_t clk, struct __kernel_timespec *ts)
 {
-	const struct timens_offset *offs = &vdns->offset[clk];
+	const struct vdso_time_data *vd = __arch_get_vdso_u_timens_data(vdns);
+	const struct timens_offset *offs = &vcns->offset[clk];
 	const struct vdso_timestamp *vdso_ts;
-	const struct vdso_time_data *vd;
+	const struct vdso_clock *vc = vd;
 	u64 cycles, ns;
 	u32 seq;
 	s64 sec;
 
-	vd = vdns - (clk == CLOCK_MONOTONIC_RAW ? CS_RAW : CS_HRES_COARSE);
-	vd = __arch_get_vdso_u_timens_data(vd);
 	if (clk != CLOCK_MONOTONIC_RAW)
-		vd = &vd[CS_HRES_COARSE];
+		vc = &vc[CS_HRES_COARSE];
 	else
-		vd = &vd[CS_RAW];
-	vdso_ts = &vd->basetime[clk];
+		vc = &vc[CS_RAW];
+	vdso_ts = &vc->basetime[clk];
 
 	do {
-		seq = vdso_read_begin(vd);
+		seq = vdso_read_begin(vc);
 
-		if (unlikely(!vdso_clocksource_ok(vd)))
+		if (unlikely(!vdso_clocksource_ok(vc)))
 			return -1;
 
-		cycles = __arch_get_hw_counter(vd->clock_mode, vd);
+		cycles = __arch_get_hw_counter(vc->clock_mode, vd);
 		if (unlikely(!vdso_cycles_ok(cycles)))
 			return -1;
-		ns = vdso_calc_ns(vd, cycles, vdso_ts->nsec);
+		ns = vdso_calc_ns(vc, cycles, vdso_ts->nsec);
 		sec = vdso_ts->sec;
-	} while (unlikely(vdso_read_retry(vd, seq)));
+	} while (unlikely(vdso_read_retry(vc, seq)));
 
 	/* Add the namespace offset */
 	sec += offs->sec;
@@ -132,8 +132,9 @@ const struct vdso_time_data *__arch_get_vdso_u_timens_data(const struct vdso_tim
 	return NULL;
 }
 
-static __always_inline int do_hres_timens(const struct vdso_time_data *vdns, clockid_t clk,
-					  struct __kernel_timespec *ts)
+static __always_inline
+int do_hres_timens(const struct vdso_time_data *vdns, const struct vdso_clock *vcns,
+		   clockid_t clk, struct __kernel_timespec *ts)
 {
 	return -EINVAL;
 }
@@ -166,7 +167,7 @@ int do_hres(const struct vdso_time_data *vd, const struct vdso_clock *vc,
 		while (unlikely((seq = READ_ONCE(vc->seq)) & 1)) {
 			if (IS_ENABLED(CONFIG_TIME_NS) &&
 			    vc->clock_mode == VDSO_CLOCKMODE_TIMENS)
-				return do_hres_timens(vd, clk, ts);
+				return do_hres_timens(vd, vc, clk, ts);
 			cpu_relax();
 		}
 		smp_rmb();

From 70067ae181f302990002aa9f54e2b8503cde7160 Mon Sep 17 00:00:00 2001
From: Anna-Maria Behnsen <anna-maria@linutronix.de>
Date: Mon, 3 Mar 2025 12:11:11 +0100
Subject: [PATCH 1118/1173] vdso/gettimeofday: Prepare do_coarse() for
 introduction of struct vdso_clock
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To support multiple PTP clocks, the VDSO data structure needs to be
reworked. All clock specific data will end up in struct vdso_clock and in
struct vdso_time_data there will be array of VDSO clocks. At the moment,
vdso_clock is simply a define which maps vdso_clock to vdso_time_data.

Prepare for the rework of these structures by adding a struct vdso_clock
pointer argument to do_coarse(), and replace the struct vdso_time_data
pointer with the new pointer argument where applicable.

No functional change.

Signed-off-by: Anna-Maria Behnsen <anna-maria@linutronix.de>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250303-vdso-clock-v1-9-c1b5c69a166f@linutronix.de
---
 lib/vdso/gettimeofday.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c
index e8d4b02bcb616..36ef7de097e61 100644
--- a/lib/vdso/gettimeofday.c
+++ b/lib/vdso/gettimeofday.c
@@ -229,10 +229,11 @@ static __always_inline int do_coarse_timens(const struct vdso_time_data *vdns, c
 }
 #endif
 
-static __always_inline int do_coarse(const struct vdso_time_data *vd, clockid_t clk,
-				     struct __kernel_timespec *ts)
+static __always_inline
+int do_coarse(const struct vdso_time_data *vd, const struct vdso_clock *vc,
+	      clockid_t clk, struct __kernel_timespec *ts)
 {
-	const struct vdso_timestamp *vdso_ts = &vd->basetime[clk];
+	const struct vdso_timestamp *vdso_ts = &vc->basetime[clk];
 	u32 seq;
 
 	do {
@@ -240,17 +241,17 @@ static __always_inline int do_coarse(const struct vdso_time_data *vd, clockid_t
 		 * Open coded function vdso_read_begin() to handle
 		 * VDSO_CLOCK_TIMENS. See comment in do_hres().
 		 */
-		while ((seq = READ_ONCE(vd->seq)) & 1) {
+		while ((seq = READ_ONCE(vc->seq)) & 1) {
 			if (IS_ENABLED(CONFIG_TIME_NS) &&
-			    vd->clock_mode == VDSO_CLOCKMODE_TIMENS)
-				return do_coarse_timens(vd, clk, ts);
+			    vc->clock_mode == VDSO_CLOCKMODE_TIMENS)
+				return do_coarse_timens(vc, clk, ts);
 			cpu_relax();
 		}
 		smp_rmb();
 
 		ts->tv_sec = vdso_ts->sec;
 		ts->tv_nsec = vdso_ts->nsec;
-	} while (unlikely(vdso_read_retry(vd, seq)));
+	} while (unlikely(vdso_read_retry(vc, seq)));
 
 	return 0;
 }
@@ -274,7 +275,7 @@ __cvdso_clock_gettime_common(const struct vdso_time_data *vd, clockid_t clock,
 	if (likely(msk & VDSO_HRES))
 		vc = &vc[CS_HRES_COARSE];
 	else if (msk & VDSO_COARSE)
-		return do_coarse(&vc[CS_HRES_COARSE], clock, ts);
+		return do_coarse(vd, &vc[CS_HRES_COARSE], clock, ts);
 	else if (msk & VDSO_RAW)
 		vc = &vc[CS_RAW];
 	else

From 8c3f5cb3d33bee748b0408418d0d2a627586a2b5 Mon Sep 17 00:00:00 2001
From: Anna-Maria Behnsen <anna-maria@linutronix.de>
Date: Mon, 3 Mar 2025 12:11:12 +0100
Subject: [PATCH 1119/1173] vdso/gettimeofday: Prepare do_coarse_timens() for
 introduction of struct vdso_clock
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To support multiple PTP clocks, the VDSO data structure needs to be
reworked. All clock specific data will end up in struct vdso_clock and in
struct vdso_time_data there will be array of VDSO clocks. At the moment,
vdso_clock is simply a define which maps vdso_clock to vdso_time_data.

Prepare for the rework of these structures by adding a struct vdso_clock
pointer argument to do_coarse_time_ns(), and replace the struct
vdso_time_data pointer with the new pointer argument where applicable.

No functional change.

Signed-off-by: Anna-Maria Behnsen <anna-maria@linutronix.de>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250303-vdso-clock-v1-10-c1b5c69a166f@linutronix.de
---
 lib/vdso/gettimeofday.c | 23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)

diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c
index 36ef7de097e61..03fa0393645ac 100644
--- a/lib/vdso/gettimeofday.c
+++ b/lib/vdso/gettimeofday.c
@@ -193,21 +193,25 @@ int do_hres(const struct vdso_time_data *vd, const struct vdso_clock *vc,
 }
 
 #ifdef CONFIG_TIME_NS
-static __always_inline int do_coarse_timens(const struct vdso_time_data *vdns, clockid_t clk,
-					    struct __kernel_timespec *ts)
+static __always_inline
+int do_coarse_timens(const struct vdso_time_data *vdns, const struct vdso_clock *vcns,
+		     clockid_t clk, struct __kernel_timespec *ts)
 {
 	const struct vdso_time_data *vd = __arch_get_vdso_u_timens_data(vdns);
-	const struct vdso_timestamp *vdso_ts = &vd->basetime[clk];
-	const struct timens_offset *offs = &vdns->offset[clk];
+	const struct timens_offset *offs = &vcns->offset[clk];
+	const struct vdso_timestamp *vdso_ts;
+	const struct vdso_clock *vc = vd;
 	u64 nsec;
 	s64 sec;
 	s32 seq;
 
+	vdso_ts = &vc->basetime[clk];
+
 	do {
-		seq = vdso_read_begin(vd);
+		seq = vdso_read_begin(vc);
 		sec = vdso_ts->sec;
 		nsec = vdso_ts->nsec;
-	} while (unlikely(vdso_read_retry(vd, seq)));
+	} while (unlikely(vdso_read_retry(vc, seq)));
 
 	/* Add the namespace offset */
 	sec += offs->sec;
@@ -222,8 +226,9 @@ static __always_inline int do_coarse_timens(const struct vdso_time_data *vdns, c
 	return 0;
 }
 #else
-static __always_inline int do_coarse_timens(const struct vdso_time_data *vdns, clockid_t clk,
-					    struct __kernel_timespec *ts)
+static __always_inline
+int do_coarse_timens(const struct vdso_time_data *vdns, const struct vdso_clock *vcns,
+		     clockid_t clk, struct __kernel_timespec *ts)
 {
 	return -1;
 }
@@ -244,7 +249,7 @@ int do_coarse(const struct vdso_time_data *vd, const struct vdso_clock *vc,
 		while ((seq = READ_ONCE(vc->seq)) & 1) {
 			if (IS_ENABLED(CONFIG_TIME_NS) &&
 			    vc->clock_mode == VDSO_CLOCKMODE_TIMENS)
-				return do_coarse_timens(vc, clk, ts);
+				return do_coarse_timens(vd, vc, clk, ts);
 			cpu_relax();
 		}
 		smp_rmb();

From 80801972a11b4c8610cd403e1f235e98cd799350 Mon Sep 17 00:00:00 2001
From: Anna-Maria Behnsen <anna-maria@linutronix.de>
Date: Mon, 3 Mar 2025 12:11:13 +0100
Subject: [PATCH 1120/1173] vdso/gettimeofday: Prepare helper functions for
 introduction of struct vdso_clock
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To support multiple PTP clocks, the VDSO data structure needs to be
reworked. All clock specific data will end up in struct vdso_clock and in
struct vdso_time_data there will be array of VDSO clocks. At the moment,
vdso_clock is simply a define which maps vdso_clock to vdso_time_data.

To prepare for the rework of the data structures, replace the struct
vdso_time_data pointer argument of the helper functions with struct
vdso_clock pointer where applicable.

No functional change.

Signed-off-by: Anna-Maria Behnsen <anna-maria@linutronix.de>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250303-vdso-clock-v1-11-c1b5c69a166f@linutronix.de
---
 lib/vdso/gettimeofday.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c
index 03fa0393645ac..c6ff693455865 100644
--- a/lib/vdso/gettimeofday.c
+++ b/lib/vdso/gettimeofday.c
@@ -17,12 +17,12 @@
 #endif
 
 #ifdef CONFIG_GENERIC_VDSO_OVERFLOW_PROTECT
-static __always_inline bool vdso_delta_ok(const struct vdso_time_data *vd, u64 delta)
+static __always_inline bool vdso_delta_ok(const struct vdso_clock *vc, u64 delta)
 {
-	return delta < vd->max_cycles;
+	return delta < vc->max_cycles;
 }
 #else
-static __always_inline bool vdso_delta_ok(const struct vdso_time_data *vd, u64 delta)
+static __always_inline bool vdso_delta_ok(const struct vdso_clock *vc, u64 delta)
 {
 	return true;
 }
@@ -39,14 +39,14 @@ static __always_inline u64 vdso_shift_ns(u64 ns, u32 shift)
  * Default implementation which works for all sane clocksources. That
  * obviously excludes x86/TSC.
  */
-static __always_inline u64 vdso_calc_ns(const struct vdso_time_data *vd, u64 cycles, u64 base)
+static __always_inline u64 vdso_calc_ns(const struct vdso_clock *vc, u64 cycles, u64 base)
 {
-	u64 delta = (cycles - vd->cycle_last) & VDSO_DELTA_MASK(vd);
+	u64 delta = (cycles - vc->cycle_last) & VDSO_DELTA_MASK(vc);
 
-	if (likely(vdso_delta_ok(vd, delta)))
-		return vdso_shift_ns((delta * vd->mult) + base, vd->shift);
+	if (likely(vdso_delta_ok(vc, delta)))
+		return vdso_shift_ns((delta * vc->mult) + base, vc->shift);
 
-	return mul_u64_u32_add_u64_shr(delta, vd->mult, base, vd->shift);
+	return mul_u64_u32_add_u64_shr(delta, vc->mult, base, vc->shift);
 }
 #endif /* vdso_calc_ns */
 
@@ -58,9 +58,9 @@ static inline bool __arch_vdso_hres_capable(void)
 #endif
 
 #ifndef vdso_clocksource_ok
-static inline bool vdso_clocksource_ok(const struct vdso_time_data *vd)
+static inline bool vdso_clocksource_ok(const struct vdso_clock *vc)
 {
-	return vd->clock_mode != VDSO_CLOCKMODE_NONE;
+	return vc->clock_mode != VDSO_CLOCKMODE_NONE;
 }
 #endif
 

From b5afbc106d7cbfa1ffbe7c8da2693e5effbba95e Mon Sep 17 00:00:00 2001
From: Anna-Maria Behnsen <anna-maria@linutronix.de>
Date: Mon, 3 Mar 2025 12:11:14 +0100
Subject: [PATCH 1121/1173] vdso/vsyscall: Prepare introduction of struct
 vdso_clock
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To support multiple PTP clocks, the VDSO data structure needs to be
reworked. All clock specific data will end up in struct vdso_clock and in
struct vdso_time_data there will be array of VDSO clocks. At the moment,
vdso_clock is simply a define which maps vdso_clock to vdso_time_data.

To prepare for the rework of the data structures, replace the struct
vdso_time_data pointer with a struct vdso_clock pointer where applicable.

No functional change.

Signed-off-by: Anna-Maria Behnsen <anna-maria@linutronix.de>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250303-vdso-clock-v1-12-c1b5c69a166f@linutronix.de
---
 kernel/time/vsyscall.c | 40 +++++++++++++++++++++-------------------
 1 file changed, 21 insertions(+), 19 deletions(-)

diff --git a/kernel/time/vsyscall.c b/kernel/time/vsyscall.c
index 418192296ef7d..dd85b41a70bee 100644
--- a/kernel/time/vsyscall.c
+++ b/kernel/time/vsyscall.c
@@ -18,25 +18,26 @@
 static inline void update_vdso_time_data(struct vdso_time_data *vdata, struct timekeeper *tk)
 {
 	struct vdso_timestamp *vdso_ts;
+	struct vdso_clock *vc = vdata;
 	u64 nsec, sec;
 
-	vdata[CS_HRES_COARSE].cycle_last	= tk->tkr_mono.cycle_last;
+	vc[CS_HRES_COARSE].cycle_last	= tk->tkr_mono.cycle_last;
 #ifdef CONFIG_GENERIC_VDSO_OVERFLOW_PROTECT
-	vdata[CS_HRES_COARSE].max_cycles	= tk->tkr_mono.clock->max_cycles;
+	vc[CS_HRES_COARSE].max_cycles	= tk->tkr_mono.clock->max_cycles;
 #endif
-	vdata[CS_HRES_COARSE].mask		= tk->tkr_mono.mask;
-	vdata[CS_HRES_COARSE].mult		= tk->tkr_mono.mult;
-	vdata[CS_HRES_COARSE].shift		= tk->tkr_mono.shift;
-	vdata[CS_RAW].cycle_last		= tk->tkr_raw.cycle_last;
+	vc[CS_HRES_COARSE].mask		= tk->tkr_mono.mask;
+	vc[CS_HRES_COARSE].mult		= tk->tkr_mono.mult;
+	vc[CS_HRES_COARSE].shift	= tk->tkr_mono.shift;
+	vc[CS_RAW].cycle_last		= tk->tkr_raw.cycle_last;
 #ifdef CONFIG_GENERIC_VDSO_OVERFLOW_PROTECT
-	vdata[CS_RAW].max_cycles		= tk->tkr_raw.clock->max_cycles;
+	vc[CS_RAW].max_cycles		= tk->tkr_raw.clock->max_cycles;
 #endif
-	vdata[CS_RAW].mask			= tk->tkr_raw.mask;
-	vdata[CS_RAW].mult			= tk->tkr_raw.mult;
-	vdata[CS_RAW].shift			= tk->tkr_raw.shift;
+	vc[CS_RAW].mask			= tk->tkr_raw.mask;
+	vc[CS_RAW].mult			= tk->tkr_raw.mult;
+	vc[CS_RAW].shift		= tk->tkr_raw.shift;
 
 	/* CLOCK_MONOTONIC */
-	vdso_ts		= &vdata[CS_HRES_COARSE].basetime[CLOCK_MONOTONIC];
+	vdso_ts		= &vc[CS_HRES_COARSE].basetime[CLOCK_MONOTONIC];
 	vdso_ts->sec	= tk->xtime_sec + tk->wall_to_monotonic.tv_sec;
 
 	nsec = tk->tkr_mono.xtime_nsec;
@@ -54,7 +55,7 @@ static inline void update_vdso_time_data(struct vdso_time_data *vdata, struct ti
 	nsec	+= (u64)tk->monotonic_to_boot.tv_nsec << tk->tkr_mono.shift;
 
 	/* CLOCK_BOOTTIME */
-	vdso_ts		= &vdata[CS_HRES_COARSE].basetime[CLOCK_BOOTTIME];
+	vdso_ts		= &vc[CS_HRES_COARSE].basetime[CLOCK_BOOTTIME];
 	vdso_ts->sec	= sec;
 
 	while (nsec >= (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) {
@@ -64,12 +65,12 @@ static inline void update_vdso_time_data(struct vdso_time_data *vdata, struct ti
 	vdso_ts->nsec	= nsec;
 
 	/* CLOCK_MONOTONIC_RAW */
-	vdso_ts		= &vdata[CS_RAW].basetime[CLOCK_MONOTONIC_RAW];
+	vdso_ts		= &vc[CS_RAW].basetime[CLOCK_MONOTONIC_RAW];
 	vdso_ts->sec	= tk->raw_sec;
 	vdso_ts->nsec	= tk->tkr_raw.xtime_nsec;
 
 	/* CLOCK_TAI */
-	vdso_ts		= &vdata[CS_HRES_COARSE].basetime[CLOCK_TAI];
+	vdso_ts		= &vc[CS_HRES_COARSE].basetime[CLOCK_TAI];
 	vdso_ts->sec	= tk->xtime_sec + (s64)tk->tai_offset;
 	vdso_ts->nsec	= tk->tkr_mono.xtime_nsec;
 }
@@ -78,6 +79,7 @@ void update_vsyscall(struct timekeeper *tk)
 {
 	struct vdso_time_data *vdata = vdso_k_time_data;
 	struct vdso_timestamp *vdso_ts;
+	struct vdso_clock *vc = vdata;
 	s32 clock_mode;
 	u64 nsec;
 
@@ -85,21 +87,21 @@ void update_vsyscall(struct timekeeper *tk)
 	vdso_write_begin(vdata);
 
 	clock_mode = tk->tkr_mono.clock->vdso_clock_mode;
-	vdata[CS_HRES_COARSE].clock_mode	= clock_mode;
-	vdata[CS_RAW].clock_mode		= clock_mode;
+	vc[CS_HRES_COARSE].clock_mode	= clock_mode;
+	vc[CS_RAW].clock_mode		= clock_mode;
 
 	/* CLOCK_REALTIME also required for time() */
-	vdso_ts		= &vdata[CS_HRES_COARSE].basetime[CLOCK_REALTIME];
+	vdso_ts		= &vc[CS_HRES_COARSE].basetime[CLOCK_REALTIME];
 	vdso_ts->sec	= tk->xtime_sec;
 	vdso_ts->nsec	= tk->tkr_mono.xtime_nsec;
 
 	/* CLOCK_REALTIME_COARSE */
-	vdso_ts		= &vdata[CS_HRES_COARSE].basetime[CLOCK_REALTIME_COARSE];
+	vdso_ts		= &vc[CS_HRES_COARSE].basetime[CLOCK_REALTIME_COARSE];
 	vdso_ts->sec	= tk->xtime_sec;
 	vdso_ts->nsec	= tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
 
 	/* CLOCK_MONOTONIC_COARSE */
-	vdso_ts		= &vdata[CS_HRES_COARSE].basetime[CLOCK_MONOTONIC_COARSE];
+	vdso_ts		= &vc[CS_HRES_COARSE].basetime[CLOCK_MONOTONIC_COARSE];
 	vdso_ts->sec	= tk->xtime_sec + tk->wall_to_monotonic.tv_sec;
 	nsec		= tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
 	nsec		= nsec + tk->wall_to_monotonic.tv_nsec;

From 0235220807033c7a1dc2a96cc23b6eae0dd11c81 Mon Sep 17 00:00:00 2001
From: Anna-Maria Behnsen <anna-maria@linutronix.de>
Date: Mon, 3 Mar 2025 12:11:15 +0100
Subject: [PATCH 1122/1173] vdso/namespace: Rename timens_setup_vdso_data() to
 reflect new vdso_clock struct
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To support multiple PTP clocks, the VDSO data structure needs to be
reworked. All clock specific data will end up in struct vdso_clock and in
struct vdso_time_data there will be array of VDSO clocks. At the moment,
vdso_clock is simply a define which maps vdso_clock to vdso_time_data.

For time namespaces, vdso_time_data needs to be set up. But only the clock
related part of the vdso_data thats requires this setup. To reflect the
future struct vdso_clock, rename timens_setup_vdso_data() to
timns_setup_vdso_clock_data().

No functional change.

Signed-off-by: Anna-Maria Behnsen <anna-maria@linutronix.de>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250303-vdso-clock-v1-13-c1b5c69a166f@linutronix.de
---
 kernel/time/namespace.c | 6 +++---
 lib/vdso/datastore.c    | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/kernel/time/namespace.c b/kernel/time/namespace.c
index 12f55aa539adb..f02430a73be8f 100644
--- a/kernel/time/namespace.c
+++ b/kernel/time/namespace.c
@@ -176,8 +176,8 @@ static struct timens_offset offset_from_ts(struct timespec64 off)
  * Timens page has vdso_time_data->clock_mode set to VDSO_CLOCKMODE_TIMENS which
  * enforces the time namespace handling path.
  */
-static void timens_setup_vdso_data(struct vdso_time_data *vdata,
-				   struct time_namespace *ns)
+static void timens_setup_vdso_clock_data(struct vdso_time_data *vdata,
+					 struct time_namespace *ns)
 {
 	struct timens_offset *offset = vdata->offset;
 	struct timens_offset monotonic = offset_from_ts(ns->offsets.monotonic);
@@ -238,7 +238,7 @@ static void timens_set_vvar_page(struct task_struct *task,
 	vdata = page_address(ns->vvar_page);
 
 	for (i = 0; i < CS_BASES; i++)
-		timens_setup_vdso_data(&vdata[i], ns);
+		timens_setup_vdso_clock_data(&vdata[i], ns);
 
 out:
 	mutex_unlock(&offset_lock);
diff --git a/lib/vdso/datastore.c b/lib/vdso/datastore.c
index e227fbbcb7969..4e350f56ace33 100644
--- a/lib/vdso/datastore.c
+++ b/lib/vdso/datastore.c
@@ -109,7 +109,7 @@ struct vm_area_struct *vdso_install_vvar_mapping(struct mm_struct *mm, unsigned
  * non-root time namespace. Whenever a task changes its namespace, the VVAR
  * page tables are cleared and then they will be re-faulted with a
  * corresponding layout.
- * See also the comment near timens_setup_vdso_data() for details.
+ * See also the comment near timens_setup_vdso_clock_data() for details.
  */
 int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
 {

From 5911e16cad61f1735c2f8c847dc43f03f8eaccd2 Mon Sep 17 00:00:00 2001
From: Anna-Maria Behnsen <anna-maria@linutronix.de>
Date: Mon, 3 Mar 2025 12:11:16 +0100
Subject: [PATCH 1123/1173] time/namespace: Prepare introduction of struct
 vdso_clock
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To support multiple PTP clocks, the VDSO data structure needs to be
reworked. All clock specific data will end up in struct vdso_clock and in
struct vdso_time_data there will be array of VDSO clocks. At the moment,
vdso_clock is simply a define which maps vdso_clock to vdso_time_data.

To prepare for the rework of the data structures, replace the struct
vdso_time_data pointer with a struct vdso_clock pointer where applicable.

No functional change.

Signed-off-by: Anna-Maria Behnsen <anna-maria@linutronix.de>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250303-vdso-clock-v1-14-c1b5c69a166f@linutronix.de
---
 kernel/time/namespace.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/kernel/time/namespace.c b/kernel/time/namespace.c
index f02430a73be8f..09bc4fb39f24c 100644
--- a/kernel/time/namespace.c
+++ b/kernel/time/namespace.c
@@ -165,26 +165,26 @@ static struct timens_offset offset_from_ts(struct timespec64 off)
  *     HVCLOCK
  *     VVAR
  *
- * The check for vdso_time_data->clock_mode is in the unlikely path of
+ * The check for vdso_clock->clock_mode is in the unlikely path of
  * the seq begin magic. So for the non-timens case most of the time
  * 'seq' is even, so the branch is not taken.
  *
  * If 'seq' is odd, i.e. a concurrent update is in progress, the extra check
- * for vdso_time_data->clock_mode is a non-issue. The task is spin waiting for the
+ * for vdso_clock->clock_mode is a non-issue. The task is spin waiting for the
  * update to finish and for 'seq' to become even anyway.
  *
- * Timens page has vdso_time_data->clock_mode set to VDSO_CLOCKMODE_TIMENS which
+ * Timens page has vdso_clock->clock_mode set to VDSO_CLOCKMODE_TIMENS which
  * enforces the time namespace handling path.
  */
-static void timens_setup_vdso_clock_data(struct vdso_time_data *vdata,
+static void timens_setup_vdso_clock_data(struct vdso_clock *vc,
 					 struct time_namespace *ns)
 {
-	struct timens_offset *offset = vdata->offset;
+	struct timens_offset *offset = vc->offset;
 	struct timens_offset monotonic = offset_from_ts(ns->offsets.monotonic);
 	struct timens_offset boottime = offset_from_ts(ns->offsets.boottime);
 
-	vdata->seq			= 1;
-	vdata->clock_mode		= VDSO_CLOCKMODE_TIMENS;
+	vc->seq				= 1;
+	vc->clock_mode			= VDSO_CLOCKMODE_TIMENS;
 	offset[CLOCK_MONOTONIC]		= monotonic;
 	offset[CLOCK_MONOTONIC_RAW]	= monotonic;
 	offset[CLOCK_MONOTONIC_COARSE]	= monotonic;
@@ -220,6 +220,7 @@ static void timens_set_vvar_page(struct task_struct *task,
 				struct time_namespace *ns)
 {
 	struct vdso_time_data *vdata;
+	struct vdso_clock *vc;
 	unsigned int i;
 
 	if (ns == &init_time_ns)
@@ -236,9 +237,10 @@ static void timens_set_vvar_page(struct task_struct *task,
 
 	ns->frozen_offsets = true;
 	vdata = page_address(ns->vvar_page);
+	vc = vdata;
 
 	for (i = 0; i < CS_BASES; i++)
-		timens_setup_vdso_clock_data(&vdata[i], ns);
+		timens_setup_vdso_clock_data(&vc[i], ns);
 
 out:
 	mutex_unlock(&offset_lock);

From bf0eff816e467f8decb9b3ac0218cc26060e359f Mon Sep 17 00:00:00 2001
From: Anna-Maria Behnsen <anna-maria@linutronix.de>
Date: Mon, 3 Mar 2025 12:11:17 +0100
Subject: [PATCH 1124/1173] x86/vdso: Prepare introduction of struct vdso_clock
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To support multiple PTP clocks, the VDSO data structure needs to be
reworked. All clock specific data will end up in struct vdso_clock and in
struct vdso_time_data there will be array of VDSO clocks. At the moment,
vdso_clock is simply a define which maps vdso_clock to vdso_time_data.

To prepare for the rework of the data structures, replace the struct
vdso_time_data pointer with a struct vdso_clock pointer where applicable.

No functional change.

Signed-off-by: Anna-Maria Behnsen <anna-maria@linutronix.de>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250303-vdso-clock-v1-15-c1b5c69a166f@linutronix.de
---
 arch/x86/include/asm/vdso/gettimeofday.h | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/arch/x86/include/asm/vdso/gettimeofday.h b/arch/x86/include/asm/vdso/gettimeofday.h
index edec796832e08..9e52cc46e1da9 100644
--- a/arch/x86/include/asm/vdso/gettimeofday.h
+++ b/arch/x86/include/asm/vdso/gettimeofday.h
@@ -261,7 +261,7 @@ static inline u64 __arch_get_hw_counter(s32 clock_mode,
 	return U64_MAX;
 }
 
-static inline bool arch_vdso_clocksource_ok(const struct vdso_time_data *vd)
+static inline bool arch_vdso_clocksource_ok(const struct vdso_clock *vc)
 {
 	return true;
 }
@@ -300,34 +300,34 @@ static inline bool arch_vdso_cycles_ok(u64 cycles)
  * declares everything with the MSB/Sign-bit set as invalid. Therefore the
  * effective mask is S64_MAX.
  */
-static __always_inline u64 vdso_calc_ns(const struct vdso_time_data *vd, u64 cycles, u64 base)
+static __always_inline u64 vdso_calc_ns(const struct vdso_clock *vc, u64 cycles, u64 base)
 {
-	u64 delta = cycles - vd->cycle_last;
+	u64 delta = cycles - vc->cycle_last;
 
 	/*
 	 * Negative motion and deltas which can cause multiplication
 	 * overflow require special treatment. This check covers both as
-	 * negative motion is guaranteed to be greater than @vd::max_cycles
+	 * negative motion is guaranteed to be greater than @vc::max_cycles
 	 * due to unsigned comparison.
 	 *
 	 * Due to the MSB/Sign-bit being used as invalid marker (see
 	 * arch_vdso_cycles_ok() above), the effective mask is S64_MAX, but that
 	 * case is also unlikely and will also take the unlikely path here.
 	 */
-	if (unlikely(delta > vd->max_cycles)) {
+	if (unlikely(delta > vc->max_cycles)) {
 		/*
 		 * Due to the above mentioned TSC wobbles, filter out
 		 * negative motion.  Per the above masking, the effective
 		 * sign bit is now bit 62.
 		 */
 		if (delta & (1ULL << 62))
-			return base >> vd->shift;
+			return base >> vc->shift;
 
 		/* Handle multiplication overflow gracefully */
-		return mul_u64_u32_add_u64_shr(delta & S64_MAX, vd->mult, base, vd->shift);
+		return mul_u64_u32_add_u64_shr(delta & S64_MAX, vc->mult, base, vc->shift);
 	}
 
-	return ((delta * vd->mult) + base) >> vd->shift;
+	return ((delta * vc->mult) + base) >> vc->shift;
 }
 #define vdso_calc_ns vdso_calc_ns
 

From 5340f3cb20989ec9562f7fcd65005e25b2365e6a Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Mon, 3 Mar 2025 12:11:18 +0100
Subject: [PATCH 1125/1173] arm64/vdso: Prepare introduction of struct
 vdso_clock
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To support multiple PTP clocks, the VDSO data structure needs to be
reworked. All clock specific data will end up in struct vdso_clock and in
struct vdso_time_data there will be array of VDSO clocks. At the moment,
vdso_clock is simply a define which maps vdso_clock to vdso_time_data.

To prepare for the rework of the data structures, replace the struct
vdso_time_data pointer with a struct vdso_clock pointer where applicable.

No functional change.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250303-vdso-clock-v1-16-c1b5c69a166f@linutronix.de
---
 arch/arm64/include/asm/vdso/compat_gettimeofday.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/include/asm/vdso/compat_gettimeofday.h b/arch/arm64/include/asm/vdso/compat_gettimeofday.h
index 957ee12fcc54b..2c6b90d26bc8f 100644
--- a/arch/arm64/include/asm/vdso/compat_gettimeofday.h
+++ b/arch/arm64/include/asm/vdso/compat_gettimeofday.h
@@ -155,9 +155,9 @@ static __always_inline const struct vdso_time_data *__arch_get_vdso_u_time_data(
 }
 #define __arch_get_vdso_u_time_data __arch_get_vdso_u_time_data
 
-static inline bool vdso_clocksource_ok(const struct vdso_time_data *vd)
+static inline bool vdso_clocksource_ok(const struct vdso_clock *vc)
 {
-	return vd->clock_mode == VDSO_CLOCKMODE_ARCHTIMER;
+	return vc->clock_mode == VDSO_CLOCKMODE_ARCHTIMER;
 }
 #define vdso_clocksource_ok	vdso_clocksource_ok
 

From ed0c10f34ffd94d6e0d37b830c232f7ca38ea174 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Mon, 3 Mar 2025 12:11:19 +0100
Subject: [PATCH 1126/1173] powerpc/vdso: Prepare introduction of struct
 vdso_clock
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To support multiple PTP clocks, the VDSO data structure needs to be
reworked. All clock specific data will end up in struct vdso_clock and in
struct vdso_time_data there will be array of VDSO clocks. At the moment,
vdso_clock is simply a define which maps vdso_clock to vdso_time_data.

To prepare for the rework of the data structures, replace the struct
vdso_time_data pointer with a struct vdso_clock pointer where applicable.

No functional change.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250303-vdso-clock-v1-17-c1b5c69a166f@linutronix.de
---
 arch/powerpc/include/asm/vdso/gettimeofday.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/vdso/gettimeofday.h b/arch/powerpc/include/asm/vdso/gettimeofday.h
index dc955f2e0cc51..99c9d6f43fde2 100644
--- a/arch/powerpc/include/asm/vdso/gettimeofday.h
+++ b/arch/powerpc/include/asm/vdso/gettimeofday.h
@@ -99,7 +99,7 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
 	return get_tb();
 }
 
-static inline bool vdso_clocksource_ok(const struct vdso_time_data *vd)
+static inline bool vdso_clocksource_ok(const struct vdso_clock *vc)
 {
 	return true;
 }

From 97a5a90ca234eaa3de8a6aa44d43de2827393019 Mon Sep 17 00:00:00 2001
From: Anna-Maria Behnsen <anna-maria@linutronix.de>
Date: Mon, 3 Mar 2025 12:11:20 +0100
Subject: [PATCH 1127/1173] vdso: Move architecture related data before
 basetime data
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Architecture related vdso data is required in the fast path when reading
CLOCK_MONOTONIC or CLOCK_REALTIME. At the moment, this information is
located at the end of the vdso_time_data structure, which is a suboptimal
cache layout.

Move the architecture specific VDSO data right before the basetime
information, which is always required. This change does not have an impact
on architectures with CONFIG_ARCH_HAS_VDSO_DATA=n. Architectures, which
have it enabled, gain a better cache layout.

Signed-off-by: Anna-Maria Behnsen <anna-maria@linutronix.de>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250303-vdso-clock-v1-18-c1b5c69a166f@linutronix.de
---
 include/vdso/datapage.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/include/vdso/datapage.h b/include/vdso/datapage.h
index 1df22e8bb9b31..bcd19c223783b 100644
--- a/include/vdso/datapage.h
+++ b/include/vdso/datapage.h
@@ -70,6 +70,8 @@ struct vdso_timestamp {
 
 /**
  * struct vdso_time_data - vdso datapage representation
+ * @arch_data:		architecture specific data (optional, defaults
+ *			to an empty struct)
  * @seq:		timebase sequence counter
  * @clock_mode:		clock mode
  * @cycle_last:		timebase at clocksource init
@@ -83,8 +85,6 @@ struct vdso_timestamp {
  * @tz_dsttime:		type of DST correction
  * @hrtimer_res:	hrtimer resolution
  * @__unused:		unused
- * @arch_data:		architecture specific data (optional, defaults
- *			to an empty struct)
  *
  * vdso_time_data will be accessed by 64 bit and compat code at the same time
  * so we should be careful before modifying this structure.
@@ -105,6 +105,8 @@ struct vdso_timestamp {
  * offset must be zero.
  */
 struct vdso_time_data {
+	struct arch_vdso_time_data arch_data;
+
 	u32			seq;
 
 	s32			clock_mode;
@@ -125,8 +127,6 @@ struct vdso_time_data {
 	s32			tz_dsttime;
 	u32			hrtimer_res;
 	u32			__unused;
-
-	struct arch_vdso_time_data arch_data;
 } ____cacheline_aligned;
 
 #define vdso_clock vdso_time_data

From 886653e36639177dd3ec2e7a4f0dc843d7def3f4 Mon Sep 17 00:00:00 2001
From: Anna-Maria Behnsen <anna-maria@linutronix.de>
Date: Mon, 3 Mar 2025 12:11:21 +0100
Subject: [PATCH 1128/1173] vdso: Rework struct vdso_time_data and introduce
 struct vdso_clock
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To support multiple PTP clocks, the VDSO data structure needs to be
reworked. All clock specific data will end up in struct vdso_clock and in
struct vdso_time_data there will be an array of VDSO clocks.

Now that all preparatory changes are in place:

Split the clock related struct members into a separate struct
vdso_clock. Make sure all users are aware, that vdso_time_data is no longer
initialized as an array and vdso_clock is now the array inside
vdso_data. Remove the vdso_clock define, which mapped it to vdso_time_data
for the transition.

Signed-off-by: Anna-Maria Behnsen <anna-maria@linutronix.de>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250303-vdso-clock-v1-19-c1b5c69a166f@linutronix.de
---
 .../include/asm/vdso/compat_gettimeofday.h    |  2 +-
 arch/arm64/include/asm/vdso/vsyscall.h        |  4 +-
 arch/s390/kernel/time.c                       | 11 +---
 include/asm-generic/vdso/vsyscall.h           |  2 +-
 include/vdso/datapage.h                       | 55 +++++++++++--------
 include/vdso/helpers.h                        |  4 +-
 kernel/time/namespace.c                       |  2 +-
 kernel/time/vsyscall.c                        | 11 ++--
 lib/vdso/datastore.c                          |  4 +-
 lib/vdso/gettimeofday.c                       | 16 +++---
 10 files changed, 57 insertions(+), 54 deletions(-)

diff --git a/arch/arm64/include/asm/vdso/compat_gettimeofday.h b/arch/arm64/include/asm/vdso/compat_gettimeofday.h
index 2c6b90d26bc8f..d60ea7a72a9cb 100644
--- a/arch/arm64/include/asm/vdso/compat_gettimeofday.h
+++ b/arch/arm64/include/asm/vdso/compat_gettimeofday.h
@@ -149,7 +149,7 @@ static __always_inline const struct vdso_time_data *__arch_get_vdso_u_time_data(
 	 * where __aarch64_get_vdso_u_time_data() is called, and then keep the
 	 * result in a register.
 	 */
-	asm volatile("mov %0, %1" : "=r"(ret) : "r"(vdso_u_time_data));
+	asm volatile("mov %0, %1" : "=r"(ret) : "r"(&vdso_u_time_data));
 
 	return ret;
 }
diff --git a/arch/arm64/include/asm/vdso/vsyscall.h b/arch/arm64/include/asm/vdso/vsyscall.h
index 3f65cbd00635a..de58951b8df6a 100644
--- a/arch/arm64/include/asm/vdso/vsyscall.h
+++ b/arch/arm64/include/asm/vdso/vsyscall.h
@@ -15,8 +15,8 @@
 static __always_inline
 void __arm64_update_vsyscall(struct vdso_time_data *vdata)
 {
-	vdata[CS_HRES_COARSE].mask	= VDSO_PRECISION_MASK;
-	vdata[CS_RAW].mask		= VDSO_PRECISION_MASK;
+	vdata->clock_data[CS_HRES_COARSE].mask	= VDSO_PRECISION_MASK;
+	vdata->clock_data[CS_RAW].mask		= VDSO_PRECISION_MASK;
 }
 #define __arch_update_vsyscall __arm64_update_vsyscall
 
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index 41ca3586b19f6..699a18f1c54eb 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -79,12 +79,10 @@ void __init time_early_init(void)
 {
 	struct ptff_qto qto;
 	struct ptff_qui qui;
-	int cs;
 
 	/* Initialize TOD steering parameters */
 	tod_steering_end = tod_clock_base.tod;
-	for (cs = 0; cs < CS_BASES; cs++)
-		vdso_k_time_data[cs].arch_data.tod_steering_end = tod_steering_end;
+	vdso_k_time_data->arch_data.tod_steering_end = tod_steering_end;
 
 	if (!test_facility(28))
 		return;
@@ -373,7 +371,6 @@ static void clock_sync_global(long delta)
 {
 	unsigned long now, adj;
 	struct ptff_qto qto;
-	int cs;
 
 	/* Fixup the monotonic sched clock. */
 	tod_clock_base.eitod += delta;
@@ -389,10 +386,8 @@ static void clock_sync_global(long delta)
 		panic("TOD clock sync offset %li is too large to drift\n",
 		      tod_steering_delta);
 	tod_steering_end = now + (abs(tod_steering_delta) << 15);
-	for (cs = 0; cs < CS_BASES; cs++) {
-		vdso_k_time_data[cs].arch_data.tod_steering_end = tod_steering_end;
-		vdso_k_time_data[cs].arch_data.tod_steering_delta = tod_steering_delta;
-	}
+	vdso_k_time_data->arch_data.tod_steering_end = tod_steering_end;
+	vdso_k_time_data->arch_data.tod_steering_delta = tod_steering_delta;
 
 	/* Update LPAR offset. */
 	if (ptff_query(PTFF_QTO) && ptff(&qto, sizeof(qto), PTFF_QTO) == 0)
diff --git a/include/asm-generic/vdso/vsyscall.h b/include/asm-generic/vdso/vsyscall.h
index 1fb3000f50364..b550afa15ecd1 100644
--- a/include/asm-generic/vdso/vsyscall.h
+++ b/include/asm-generic/vdso/vsyscall.h
@@ -9,7 +9,7 @@
 #ifndef __arch_get_vdso_u_time_data
 static __always_inline const struct vdso_time_data *__arch_get_vdso_u_time_data(void)
 {
-	return vdso_u_time_data;
+	return &vdso_u_time_data;
 }
 #endif
 
diff --git a/include/vdso/datapage.h b/include/vdso/datapage.h
index bcd19c223783b..1864e76e8f691 100644
--- a/include/vdso/datapage.h
+++ b/include/vdso/datapage.h
@@ -69,9 +69,7 @@ struct vdso_timestamp {
 };
 
 /**
- * struct vdso_time_data - vdso datapage representation
- * @arch_data:		architecture specific data (optional, defaults
- *			to an empty struct)
+ * struct vdso_clock - vdso per clocksource datapage representation
  * @seq:		timebase sequence counter
  * @clock_mode:		clock mode
  * @cycle_last:		timebase at clocksource init
@@ -81,17 +79,9 @@ struct vdso_timestamp {
  * @shift:		clocksource shift
  * @basetime[clock_id]:	basetime per clock_id
  * @offset[clock_id]:	time namespace offset per clock_id
- * @tz_minuteswest:	minutes west of Greenwich
- * @tz_dsttime:		type of DST correction
- * @hrtimer_res:	hrtimer resolution
- * @__unused:		unused
  *
- * vdso_time_data will be accessed by 64 bit and compat code at the same time
- * so we should be careful before modifying this structure.
- *
- * The ordering of the struct members is optimized to have fast access to the
- * often required struct members which are related to CLOCK_REALTIME and
- * CLOCK_MONOTONIC. This information is stored in the first cache lines.
+ * See also struct vdso_time_data for basic access and ordering information as
+ * struct vdso_clock is used there.
  *
  * @basetime is used to store the base time for the system wide time getter
  * VVAR page.
@@ -104,9 +94,7 @@ struct vdso_timestamp {
  * For clocks which are not affected by time namespace adjustment the
  * offset must be zero.
  */
-struct vdso_time_data {
-	struct arch_vdso_time_data arch_data;
-
+struct vdso_clock {
 	u32			seq;
 
 	s32			clock_mode;
@@ -122,14 +110,35 @@ struct vdso_time_data {
 		struct vdso_timestamp	basetime[VDSO_BASES];
 		struct timens_offset	offset[VDSO_BASES];
 	};
+};
 
-	s32			tz_minuteswest;
-	s32			tz_dsttime;
-	u32			hrtimer_res;
-	u32			__unused;
-} ____cacheline_aligned;
+/**
+ * struct vdso_time_data - vdso datapage representation
+ * @arch_data:		architecture specific data (optional, defaults
+ *			to an empty struct)
+ * @clock_data:		clocksource related data (array)
+ * @tz_minuteswest:	minutes west of Greenwich
+ * @tz_dsttime:		type of DST correction
+ * @hrtimer_res:	hrtimer resolution
+ * @__unused:		unused
+ *
+ * vdso_time_data will be accessed by 64 bit and compat code at the same time
+ * so we should be careful before modifying this structure.
+ *
+ * The ordering of the struct members is optimized to have fast acces to the
+ * often required struct members which are related to CLOCK_REALTIME and
+ * CLOCK_MONOTONIC. This information is stored in the first cache lines.
+ */
+struct vdso_time_data {
+	struct arch_vdso_time_data	arch_data;
 
-#define vdso_clock vdso_time_data
+	struct vdso_clock		clock_data[CS_BASES];
+
+	s32				tz_minuteswest;
+	s32				tz_dsttime;
+	u32				hrtimer_res;
+	u32				__unused;
+} ____cacheline_aligned;
 
 /**
  * struct vdso_rng_data - vdso RNG state information
@@ -151,7 +160,7 @@ struct vdso_rng_data {
  * relocation, and this is what we need.
  */
 #ifdef CONFIG_GENERIC_VDSO_DATA_STORE
-extern struct vdso_time_data vdso_u_time_data[CS_BASES] __attribute__((visibility("hidden")));
+extern struct vdso_time_data vdso_u_time_data __attribute__((visibility("hidden")));
 extern struct vdso_rng_data vdso_u_rng_data __attribute__((visibility("hidden")));
 extern struct vdso_arch_data vdso_u_arch_data __attribute__((visibility("hidden")));
 
diff --git a/include/vdso/helpers.h b/include/vdso/helpers.h
index 28f0707a46c62..0a98fed550ba6 100644
--- a/include/vdso/helpers.h
+++ b/include/vdso/helpers.h
@@ -30,7 +30,7 @@ static __always_inline u32 vdso_read_retry(const struct vdso_clock *vc,
 
 static __always_inline void vdso_write_begin(struct vdso_time_data *vd)
 {
-	struct vdso_clock *vc = vd;
+	struct vdso_clock *vc = vd->clock_data;
 
 	/*
 	 * WRITE_ONCE() is required otherwise the compiler can validly tear
@@ -44,7 +44,7 @@ static __always_inline void vdso_write_begin(struct vdso_time_data *vd)
 
 static __always_inline void vdso_write_end(struct vdso_time_data *vd)
 {
-	struct vdso_clock *vc = vd;
+	struct vdso_clock *vc = vd->clock_data;
 
 	smp_wmb();
 	/*
diff --git a/kernel/time/namespace.c b/kernel/time/namespace.c
index 09bc4fb39f24c..e3642278df433 100644
--- a/kernel/time/namespace.c
+++ b/kernel/time/namespace.c
@@ -237,7 +237,7 @@ static void timens_set_vvar_page(struct task_struct *task,
 
 	ns->frozen_offsets = true;
 	vdata = page_address(ns->vvar_page);
-	vc = vdata;
+	vc = vdata->clock_data;
 
 	for (i = 0; i < CS_BASES; i++)
 		timens_setup_vdso_clock_data(&vc[i], ns);
diff --git a/kernel/time/vsyscall.c b/kernel/time/vsyscall.c
index dd85b41a70bee..01c2ab1e89719 100644
--- a/kernel/time/vsyscall.c
+++ b/kernel/time/vsyscall.c
@@ -17,8 +17,8 @@
 
 static inline void update_vdso_time_data(struct vdso_time_data *vdata, struct timekeeper *tk)
 {
+	struct vdso_clock *vc = vdata->clock_data;
 	struct vdso_timestamp *vdso_ts;
-	struct vdso_clock *vc = vdata;
 	u64 nsec, sec;
 
 	vc[CS_HRES_COARSE].cycle_last	= tk->tkr_mono.cycle_last;
@@ -78,8 +78,8 @@ static inline void update_vdso_time_data(struct vdso_time_data *vdata, struct ti
 void update_vsyscall(struct timekeeper *tk)
 {
 	struct vdso_time_data *vdata = vdso_k_time_data;
+	struct vdso_clock *vc = vdata->clock_data;
 	struct vdso_timestamp *vdso_ts;
-	struct vdso_clock *vc = vdata;
 	s32 clock_mode;
 	u64 nsec;
 
@@ -109,9 +109,8 @@ void update_vsyscall(struct timekeeper *tk)
 
 	/*
 	 * Read without the seqlock held by clock_getres().
-	 * Note: No need to have a second copy.
 	 */
-	WRITE_ONCE(vdata[CS_HRES_COARSE].hrtimer_res, hrtimer_resolution);
+	WRITE_ONCE(vdata->hrtimer_res, hrtimer_resolution);
 
 	/*
 	 * If the current clocksource is not VDSO capable, then spare the
@@ -131,8 +130,8 @@ void update_vsyscall_tz(void)
 {
 	struct vdso_time_data *vdata = vdso_k_time_data;
 
-	vdata[CS_HRES_COARSE].tz_minuteswest = sys_tz.tz_minuteswest;
-	vdata[CS_HRES_COARSE].tz_dsttime = sys_tz.tz_dsttime;
+	vdata->tz_minuteswest = sys_tz.tz_minuteswest;
+	vdata->tz_dsttime = sys_tz.tz_dsttime;
 
 	__arch_sync_vdso_time_data(vdata);
 }
diff --git a/lib/vdso/datastore.c b/lib/vdso/datastore.c
index 4e350f56ace33..c715e217ec657 100644
--- a/lib/vdso/datastore.c
+++ b/lib/vdso/datastore.c
@@ -13,10 +13,10 @@
  */
 #ifdef CONFIG_HAVE_GENERIC_VDSO
 static union {
-	struct vdso_time_data	data[CS_BASES];
+	struct vdso_time_data	data;
 	u8			page[PAGE_SIZE];
 } vdso_time_data_store __page_aligned_data;
-struct vdso_time_data *vdso_k_time_data = vdso_time_data_store.data;
+struct vdso_time_data *vdso_k_time_data = &vdso_time_data_store.data;
 static_assert(sizeof(vdso_time_data_store) == PAGE_SIZE);
 #endif /* CONFIG_HAVE_GENERIC_VDSO */
 
diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c
index c6ff693455865..93ef801a97ef2 100644
--- a/lib/vdso/gettimeofday.c
+++ b/lib/vdso/gettimeofday.c
@@ -87,8 +87,8 @@ int do_hres_timens(const struct vdso_time_data *vdns, const struct vdso_clock *v
 {
 	const struct vdso_time_data *vd = __arch_get_vdso_u_timens_data(vdns);
 	const struct timens_offset *offs = &vcns->offset[clk];
+	const struct vdso_clock *vc = vd->clock_data;
 	const struct vdso_timestamp *vdso_ts;
-	const struct vdso_clock *vc = vd;
 	u64 cycles, ns;
 	u32 seq;
 	s64 sec;
@@ -199,8 +199,8 @@ int do_coarse_timens(const struct vdso_time_data *vdns, const struct vdso_clock
 {
 	const struct vdso_time_data *vd = __arch_get_vdso_u_timens_data(vdns);
 	const struct timens_offset *offs = &vcns->offset[clk];
+	const struct vdso_clock *vc = vd->clock_data;
 	const struct vdso_timestamp *vdso_ts;
-	const struct vdso_clock *vc = vd;
 	u64 nsec;
 	s64 sec;
 	s32 seq;
@@ -265,7 +265,7 @@ static __always_inline int
 __cvdso_clock_gettime_common(const struct vdso_time_data *vd, clockid_t clock,
 			     struct __kernel_timespec *ts)
 {
-	const struct vdso_clock *vc = vd;
+	const struct vdso_clock *vc = vd->clock_data;
 	u32 msk;
 
 	/* Check for negative values or invalid clocks */
@@ -337,7 +337,7 @@ static __maybe_unused int
 __cvdso_gettimeofday_data(const struct vdso_time_data *vd,
 			  struct __kernel_old_timeval *tv, struct timezone *tz)
 {
-	const struct vdso_clock *vc = vd;
+	const struct vdso_clock *vc = vd->clock_data;
 
 	if (likely(tv != NULL)) {
 		struct __kernel_timespec ts;
@@ -371,13 +371,13 @@ __cvdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
 static __maybe_unused __kernel_old_time_t
 __cvdso_time_data(const struct vdso_time_data *vd, __kernel_old_time_t *time)
 {
-	const struct vdso_clock *vc = vd;
+	const struct vdso_clock *vc = vd->clock_data;
 	__kernel_old_time_t t;
 
 	if (IS_ENABLED(CONFIG_TIME_NS) &&
 	    vc->clock_mode == VDSO_CLOCKMODE_TIMENS) {
 		vd = __arch_get_vdso_u_timens_data(vd);
-		vc = vd;
+		vc = vd->clock_data;
 	}
 
 	t = READ_ONCE(vc[CS_HRES_COARSE].basetime[CLOCK_REALTIME].sec);
@@ -399,7 +399,7 @@ static __maybe_unused
 int __cvdso_clock_getres_common(const struct vdso_time_data *vd, clockid_t clock,
 				struct __kernel_timespec *res)
 {
-	const struct vdso_clock *vc = vd;
+	const struct vdso_clock *vc = vd->clock_data;
 	u32 msk;
 	u64 ns;
 
@@ -420,7 +420,7 @@ int __cvdso_clock_getres_common(const struct vdso_time_data *vd, clockid_t clock
 		/*
 		 * Preserves the behaviour of posix_get_hrtimer_res().
 		 */
-		ns = READ_ONCE(vd[CS_HRES_COARSE].hrtimer_res);
+		ns = READ_ONCE(vd->hrtimer_res);
 	} else if (msk & VDSO_COARSE) {
 		/*
 		 * Preserves the behaviour of posix_get_coarse_res().

From 058a6bec37c6c3b826158f6d26b75de43816a880 Mon Sep 17 00:00:00 2001
From: "Borislav Petkov (AMD)" <bp@alien8.de>
Date: Fri, 7 Mar 2025 23:02:56 +0100
Subject: [PATCH 1129/1173] x86/microcode/AMD: Add some forgotten models to the
 SHA check
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add some more forgotten models to the SHA check.

Fixes: 50cef76d5cb0 ("x86/microcode/AMD: Load only SHA256-checksummed patches")
Reported-by: Toralf Förster <toralf.foerster@gmx.de>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Toralf Förster <toralf.foerster@gmx.de>
Link: https://lore.kernel.org/r/20250307220256.11816-1-bp@kernel.org
---
 arch/x86/kernel/cpu/microcode/amd.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 95ac1c6a84fbe..c69b1bc454834 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -175,23 +175,29 @@ static bool need_sha_check(u32 cur_rev)
 {
 	switch (cur_rev >> 8) {
 	case 0x80012: return cur_rev <= 0x800126f; break;
+	case 0x80082: return cur_rev <= 0x800820f; break;
 	case 0x83010: return cur_rev <= 0x830107c; break;
 	case 0x86001: return cur_rev <= 0x860010e; break;
 	case 0x86081: return cur_rev <= 0x8608108; break;
 	case 0x87010: return cur_rev <= 0x8701034; break;
 	case 0x8a000: return cur_rev <= 0x8a0000a; break;
+	case 0xa0010: return cur_rev <= 0xa00107a; break;
 	case 0xa0011: return cur_rev <= 0xa0011da; break;
 	case 0xa0012: return cur_rev <= 0xa001243; break;
+	case 0xa0082: return cur_rev <= 0xa00820e; break;
 	case 0xa1011: return cur_rev <= 0xa101153; break;
 	case 0xa1012: return cur_rev <= 0xa10124e; break;
 	case 0xa1081: return cur_rev <= 0xa108109; break;
 	case 0xa2010: return cur_rev <= 0xa20102f; break;
 	case 0xa2012: return cur_rev <= 0xa201212; break;
+	case 0xa4041: return cur_rev <= 0xa404109; break;
+	case 0xa5000: return cur_rev <= 0xa500013; break;
 	case 0xa6012: return cur_rev <= 0xa60120a; break;
 	case 0xa7041: return cur_rev <= 0xa704109; break;
 	case 0xa7052: return cur_rev <= 0xa705208; break;
 	case 0xa7080: return cur_rev <= 0xa708009; break;
 	case 0xa70c0: return cur_rev <= 0xa70C009; break;
+	case 0xaa001: return cur_rev <= 0xaa00116; break;
 	case 0xaa002: return cur_rev <= 0xaa00218; break;
 	default: break;
 	}

From 558fc8e1869ca6e1eb99a1e2b52f6c35424d4adf Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Fri, 7 Mar 2025 10:10:03 +0100
Subject: [PATCH 1130/1173] x86/boot: Do not test if AC and ID eflags are
 changeable on x86_64

The test for the changeabitily of AC and ID EFLAGS is used to
distinguish between i386 and i486 processors (AC) and to test
for CPUID instruction support (ID).

Skip these tests on x86_64 processors as they always supports CPUID.

Also change the return type of has_eflag() to bool.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Link: https://lore.kernel.org/r/20250307091022.181136-1-ubizjak@gmail.com
---
 arch/x86/boot/cpuflags.c | 26 +++++++++-----------------
 arch/x86/boot/cpuflags.h |  6 +++++-
 2 files changed, 14 insertions(+), 18 deletions(-)

diff --git a/arch/x86/boot/cpuflags.c b/arch/x86/boot/cpuflags.c
index d75237ba7ce94..2150a016176f2 100644
--- a/arch/x86/boot/cpuflags.c
+++ b/arch/x86/boot/cpuflags.c
@@ -29,40 +29,32 @@ static int has_fpu(void)
 	return fsw == 0 && (fcw & 0x103f) == 0x003f;
 }
 
+#ifdef CONFIG_X86_32
 /*
  * For building the 16-bit code we want to explicitly specify 32-bit
  * push/pop operations, rather than just saying 'pushf' or 'popf' and
- * letting the compiler choose. But this is also included from the
- * compressed/ directory where it may be 64-bit code, and thus needs
- * to be 'pushfq' or 'popfq' in that case.
+ * letting the compiler choose.
  */
-#ifdef __x86_64__
-#define PUSHF "pushfq"
-#define POPF "popfq"
-#else
-#define PUSHF "pushfl"
-#define POPF "popfl"
-#endif
-
-int has_eflag(unsigned long mask)
+bool has_eflag(unsigned long mask)
 {
 	unsigned long f0, f1;
 
-	asm volatile(PUSHF "	\n\t"
-		     PUSHF "	\n\t"
+	asm volatile("pushfl	\n\t"
+		     "pushfl	\n\t"
 		     "pop %0	\n\t"
 		     "mov %0,%1	\n\t"
 		     "xor %2,%1	\n\t"
 		     "push %1	\n\t"
-		     POPF "	\n\t"
-		     PUSHF "	\n\t"
+		     "popfl	\n\t"
+		     "pushfl	\n\t"
 		     "pop %1	\n\t"
-		     POPF
+		     "popfl"
 		     : "=&r" (f0), "=&r" (f1)
 		     : "ri" (mask));
 
 	return !!((f0^f1) & mask);
 }
+#endif
 
 void cpuid_count(u32 id, u32 count, u32 *a, u32 *b, u32 *c, u32 *d)
 {
diff --git a/arch/x86/boot/cpuflags.h b/arch/x86/boot/cpuflags.h
index fdcc2aa4c3c4a..a398d9204ad00 100644
--- a/arch/x86/boot/cpuflags.h
+++ b/arch/x86/boot/cpuflags.h
@@ -15,7 +15,11 @@ struct cpu_features {
 extern struct cpu_features cpu;
 extern u32 cpu_vendor[3];
 
-int has_eflag(unsigned long mask);
+#ifdef CONFIG_X86_32
+bool has_eflag(unsigned long mask);
+#else
+static inline bool has_eflag(unsigned long mask) { return true; }
+#endif
 void get_cpuflags(void);
 void cpuid_count(u32 id, u32 count, u32 *a, u32 *b, u32 *c, u32 *d);
 bool has_cpuflag(int flag);

From 80e54e84911a923c40d7bee33a34c1b4be148d7a Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 9 Mar 2025 13:45:25 -1000
Subject: [PATCH 1131/1173] Linux 6.14-rc6

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index 6a8e5be6b0043..1d6a9ec8a2ace 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 14
 SUBLEVEL = 0
-EXTRAVERSION = -rc5
+EXTRAVERSION = -rc6
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*

From dc6e8bfc0c9e27cbfed27c7ed50c71205a7c9551 Mon Sep 17 00:00:00 2001
From: "H. Peter Anvin (Intel)" <hpa@zytor.com>
Date: Fri, 28 Feb 2025 00:23:35 -0800
Subject: [PATCH 1132/1173] x86/cpufeatures: Add {REQUIRED,DISABLED} feature
 configs

Required and disabled feature masks completely rely on build configs,
i.e., once a build config is fixed, so are the feature masks.

To prepare for auto-generating the <asm/cpufeaturemasks.h> header
with required and disabled feature masks based on a build config,
add feature Kconfig items:

  - X86_REQUIRED_FEATURE_x
  - X86_DISABLED_FEATURE_x

each of which may be set to "y" if and only if its preconditions from
current build config are met.

Signed-off-by: H. Peter Anvin (Intel) <hpa@zytor.com>
Signed-off-by: Xin Li (Intel) <xin@zytor.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250228082338.73859-3-xin@zytor.com
---
 arch/x86/Kconfig             |   2 +
 arch/x86/Kconfig.cpufeatures | 201 +++++++++++++++++++++++++++++++++++
 2 files changed, 203 insertions(+)
 create mode 100644 arch/x86/Kconfig.cpufeatures

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 017035f461cf2..7caf2fdecd19b 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -3128,4 +3128,6 @@ config HAVE_ATOMIC_IOMAP
 
 source "arch/x86/kvm/Kconfig"
 
+source "arch/x86/Kconfig.cpufeatures"
+
 source "arch/x86/Kconfig.assembler"
diff --git a/arch/x86/Kconfig.cpufeatures b/arch/x86/Kconfig.cpufeatures
new file mode 100644
index 0000000000000..e12d5b7e39a25
--- /dev/null
+++ b/arch/x86/Kconfig.cpufeatures
@@ -0,0 +1,201 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# x86 feature bits (see arch/x86/include/asm/cpufeatures.h) that are
+# either REQUIRED to be enabled, or DISABLED (always ignored) for this
+# particular compile-time configuration.  The tests for these features
+# are turned into compile-time constants via the generated
+# <asm/cpufeaturemasks.h>.
+#
+# The naming of these variables *must* match asm/cpufeatures.h, e.g.,
+#     X86_FEATURE_ALWAYS <==> X86_REQUIRED_FEATURE_ALWAYS
+#     X86_FEATURE_FRED   <==> X86_DISABLED_FEATURE_FRED
+#
+# And these REQUIRED and DISABLED config options are manipulated in an
+# AWK script as the following example:
+#
+#                          +----------------------+
+#                          |    X86_FRED = y ?    |
+#                          +----------------------+
+#                              /             \
+#                           Y /               \ N
+#  +-------------------------------------+   +-------------------------------+
+#  | X86_DISABLED_FEATURE_FRED undefined |   | X86_DISABLED_FEATURE_FRED = y |
+#  +-------------------------------------+   +-------------------------------+
+#                                                        |
+#                                                        |
+#     +-------------------------------------------+      |
+#     | X86_FEATURE_FRED: feature word 12, bit 17 | ---->|
+#     +-------------------------------------------+      |
+#                                                        |
+#                                                        |
+#                                     +-------------------------------+
+#                                     | set bit 17 of DISABLED_MASK12 |
+#                                     +-------------------------------+
+#
+
+config X86_REQUIRED_FEATURE_ALWAYS
+	def_bool y
+
+config X86_REQUIRED_FEATURE_NOPL
+	def_bool y
+	depends on X86_64 || X86_P6_NOP
+
+config X86_REQUIRED_FEATURE_CX8
+	def_bool y
+	depends on X86_CX8
+
+# this should be set for all -march=.. options where the compiler
+# generates cmov.
+config X86_REQUIRED_FEATURE_CMOV
+	def_bool y
+	depends on X86_CMOV
+
+# this should be set for all -march= options where the compiler
+# generates movbe.
+config X86_REQUIRED_FEATURE_MOVBE
+	def_bool y
+	depends on MATOM
+
+config X86_REQUIRED_FEATURE_CPUID
+	def_bool y
+	depends on X86_64
+
+config X86_REQUIRED_FEATURE_UP
+	def_bool y
+	depends on !SMP
+
+config X86_REQUIRED_FEATURE_FPU
+	def_bool y
+	depends on !MATH_EMULATION
+
+config X86_REQUIRED_FEATURE_PAE
+	def_bool y
+	depends on X86_64 || X86_PAE
+
+config X86_REQUIRED_FEATURE_PSE
+	def_bool y
+	depends on X86_64 && !PARAVIRT_XXL
+
+config X86_REQUIRED_FEATURE_PGE
+	def_bool y
+	depends on X86_64 && !PARAVIRT_XXL
+
+config X86_REQUIRED_FEATURE_MSR
+	def_bool y
+	depends on X86_64
+
+config X86_REQUIRED_FEATURE_FXSR
+	def_bool y
+	depends on X86_64
+
+config X86_REQUIRED_FEATURE_XMM
+	def_bool y
+	depends on X86_64
+
+config X86_REQUIRED_FEATURE_XMM2
+	def_bool y
+	depends on X86_64
+
+config X86_REQUIRED_FEATURE_LM
+	def_bool y
+	depends on X86_64
+
+config X86_DISABLED_FEATURE_UMIP
+	def_bool y
+	depends on !X86_UMIP
+
+config X86_DISABLED_FEATURE_VME
+	def_bool y
+	depends on X86_64
+
+config X86_DISABLED_FEATURE_K6_MTRR
+	def_bool y
+	depends on X86_64
+
+config X86_DISABLED_FEATURE_CYRIX_ARR
+	def_bool y
+	depends on X86_64
+
+config X86_DISABLED_FEATURE_CENTAUR_MCR
+	def_bool y
+	depends on X86_64
+
+config X86_DISABLED_FEATURE_PCID
+	def_bool y
+	depends on !X86_64
+
+config X86_DISABLED_FEATURE_PKU
+	def_bool y
+	depends on !X86_INTEL_MEMORY_PROTECTION_KEYS
+
+config X86_DISABLED_FEATURE_OSPKE
+	def_bool y
+	depends on !X86_INTEL_MEMORY_PROTECTION_KEYS
+
+config X86_DISABLED_FEATURE_LA57
+	def_bool y
+	depends on !X86_5LEVEL
+
+config X86_DISABLED_FEATURE_PTI
+	def_bool y
+	depends on !MITIGATION_PAGE_TABLE_ISOLATION
+
+config X86_DISABLED_FEATURE_RETPOLINE
+	def_bool y
+	depends on !MITIGATION_RETPOLINE
+
+config X86_DISABLED_FEATURE_RETPOLINE_LFENCE
+	def_bool y
+	depends on !MITIGATION_RETPOLINE
+
+config X86_DISABLED_FEATURE_RETHUNK
+	def_bool y
+	depends on !MITIGATION_RETHUNK
+
+config X86_DISABLED_FEATURE_UNRET
+	def_bool y
+	depends on !MITIGATION_UNRET_ENTRY
+
+config X86_DISABLED_FEATURE_CALL_DEPTH
+	def_bool y
+	depends on !MITIGATION_CALL_DEPTH_TRACKING
+
+config X86_DISABLED_FEATURE_LAM
+	def_bool y
+	depends on !ADDRESS_MASKING
+
+config X86_DISABLED_FEATURE_ENQCMD
+	def_bool y
+	depends on !INTEL_IOMMU_SVM
+
+config X86_DISABLED_FEATURE_SGX
+	def_bool y
+	depends on !X86_SGX
+
+config X86_DISABLED_FEATURE_XENPV
+	def_bool y
+	depends on !XEN_PV
+
+config X86_DISABLED_FEATURE_TDX_GUEST
+	def_bool y
+	depends on !INTEL_TDX_GUEST
+
+config X86_DISABLED_FEATURE_USER_SHSTK
+	def_bool y
+	depends on !X86_USER_SHADOW_STACK
+
+config X86_DISABLED_FEATURE_IBT
+	def_bool y
+	depends on !X86_KERNEL_IBT
+
+config X86_DISABLED_FEATURE_FRED
+	def_bool y
+	depends on !X86_FRED
+
+config X86_DISABLED_FEATURE_SEV_SNP
+	def_bool y
+	depends on !KVM_AMD_SEV
+
+config X86_DISABLED_FEATURE_INVLPGB
+	def_bool y
+	depends on !BROADCAST_TLB_FLUSH

From 7a7bd24a0ca02dfe68bd8a7a567b3da3b716bd8d Mon Sep 17 00:00:00 2001
From: "H. Peter Anvin (Intel)" <hpa@zytor.com>
Date: Wed, 5 Mar 2025 10:47:22 -0800
Subject: [PATCH 1133/1173] x86/cpufeatures: Generate the
 <asm/cpufeaturemasks.h> header based on build config

Introduce an AWK script to auto-generate the <asm/cpufeaturemasks.h> header
with required and disabled feature masks based on <asm/cpufeatures.h>
and the current build config.

Thus for any CPU feature with a build config, e.g., X86_FRED, simply add:

  config X86_DISABLED_FEATURE_FRED
	def_bool y
	depends on !X86_FRED

to arch/x86/Kconfig.cpufeatures, instead of adding a conditional CPU
feature disable flag, e.g., DISABLE_FRED.

Lastly, the generated required and disabled feature masks will be added to
their corresponding feature masks for this particular compile-time
configuration.

  [ Xin: build integration improvements ]
  [ mingo: Improved changelog and comments ]

Signed-off-by: H. Peter Anvin (Intel) <hpa@zytor.com>
Signed-off-by: Xin Li (Intel) <xin@zytor.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Nikolay Borisov <nik.borisov@suse.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250305184725.3341760-3-xin@zytor.com
---
 arch/x86/Makefile                  | 15 ++++++
 arch/x86/boot/cpucheck.c           |  3 +-
 arch/x86/boot/cpuflags.c           |  1 -
 arch/x86/boot/mkcpustr.c           |  3 +-
 arch/x86/include/asm/Kbuild        |  1 +
 arch/x86/include/asm/cpufeature.h  |  1 +
 arch/x86/include/asm/cpufeatures.h |  8 ---
 arch/x86/kernel/verify_cpu.S       |  4 ++
 arch/x86/tools/cpufeaturemasks.awk | 81 ++++++++++++++++++++++++++++++
 9 files changed, 105 insertions(+), 12 deletions(-)
 create mode 100755 arch/x86/tools/cpufeaturemasks.awk

diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 8120085b00a4a..420f086315209 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -264,6 +264,21 @@ archscripts: scripts_basic
 archheaders:
 	$(Q)$(MAKE) $(build)=arch/x86/entry/syscalls all
 
+###
+# <asm/cpufeaturemasks.h> header generation
+
+cpufeaturemasks.hdr := arch/x86/include/generated/asm/cpufeaturemasks.h
+cpufeaturemasks.awk := $(srctree)/arch/x86/tools/cpufeaturemasks.awk
+cpufeatures_hdr := $(srctree)/arch/x86/include/asm/cpufeatures.h
+targets += $(cpufeaturemasks.hdr)
+quiet_cmd_gen_featuremasks = GEN     $@
+      cmd_gen_featuremasks = $(AWK) -f $(cpufeaturemasks.awk) $(cpufeatures_hdr) $(KCONFIG_CONFIG) > $@
+
+$(cpufeaturemasks.hdr): $(cpufeaturemasks.awk) $(cpufeatures_hdr) $(KCONFIG_CONFIG) FORCE
+	$(shell mkdir -p $(dir $@))
+	$(call if_changed,gen_featuremasks)
+archprepare: $(cpufeaturemasks.hdr)
+
 ###
 # Kernel objects
 
diff --git a/arch/x86/boot/cpucheck.c b/arch/x86/boot/cpucheck.c
index 0aae4d4ed6150..f82de8de5dc62 100644
--- a/arch/x86/boot/cpucheck.c
+++ b/arch/x86/boot/cpucheck.c
@@ -22,10 +22,11 @@
 # include "boot.h"
 #endif
 #include <linux/types.h>
+#include <asm/cpufeaturemasks.h>
 #include <asm/intel-family.h>
 #include <asm/processor-flags.h>
-#include <asm/required-features.h>
 #include <asm/msr-index.h>
+
 #include "string.h"
 #include "msr.h"
 
diff --git a/arch/x86/boot/cpuflags.c b/arch/x86/boot/cpuflags.c
index d75237ba7ce94..0cabdacb2a2fc 100644
--- a/arch/x86/boot/cpuflags.c
+++ b/arch/x86/boot/cpuflags.c
@@ -3,7 +3,6 @@
 #include "bitops.h"
 
 #include <asm/processor-flags.h>
-#include <asm/required-features.h>
 #include <asm/msr-index.h>
 #include "cpuflags.h"
 
diff --git a/arch/x86/boot/mkcpustr.c b/arch/x86/boot/mkcpustr.c
index da0ccc5de5380..22d730b227e38 100644
--- a/arch/x86/boot/mkcpustr.c
+++ b/arch/x86/boot/mkcpustr.c
@@ -12,8 +12,6 @@
 
 #include <stdio.h>
 
-#include "../include/asm/required-features.h"
-#include "../include/asm/disabled-features.h"
 #include "../include/asm/cpufeatures.h"
 #include "../include/asm/vmxfeatures.h"
 #include "../kernel/cpu/capflags.c"
@@ -23,6 +21,7 @@ int main(void)
 	int i, j;
 	const char *str;
 
+	printf("#include <asm/cpufeaturemasks.h>\n\n");
 	printf("static const char x86_cap_strs[] =\n");
 
 	for (i = 0; i < NCAPINTS; i++) {
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 58f4ddecc5fa2..4566000e15c44 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -8,6 +8,7 @@ generated-y += syscalls_x32.h
 generated-y += unistd_32_ia32.h
 generated-y += unistd_64_x32.h
 generated-y += xen-hypercalls.h
+generated-y += cpufeaturemasks.h
 
 generic-y += early_ioremap.h
 generic-y += fprobe.h
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index e955da397e0e2..d54db88fae93b 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -9,6 +9,7 @@
 #include <asm/asm.h>
 #include <linux/bitops.h>
 #include <asm/alternative.h>
+#include <asm/cpufeaturemasks.h>
 
 enum cpuid_leafs
 {
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 8770dc185fe91..c0462be0c5f60 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -2,14 +2,6 @@
 #ifndef _ASM_X86_CPUFEATURES_H
 #define _ASM_X86_CPUFEATURES_H
 
-#ifndef _ASM_X86_REQUIRED_FEATURES_H
-#include <asm/required-features.h>
-#endif
-
-#ifndef _ASM_X86_DISABLED_FEATURES_H
-#include <asm/disabled-features.h>
-#endif
-
 /*
  * Defines x86 CPU feature bits
  */
diff --git a/arch/x86/kernel/verify_cpu.S b/arch/x86/kernel/verify_cpu.S
index 1258a5872d128..37ad437924523 100644
--- a/arch/x86/kernel/verify_cpu.S
+++ b/arch/x86/kernel/verify_cpu.S
@@ -29,8 +29,12 @@
  */
 
 #include <asm/cpufeatures.h>
+#include <asm/cpufeaturemasks.h>
 #include <asm/msr-index.h>
 
+#define SSE_MASK	\
+	(REQUIRED_MASK0 & ((1<<(X86_FEATURE_XMM & 31)) | (1<<(X86_FEATURE_XMM2 & 31))))
+
 SYM_FUNC_START_LOCAL(verify_cpu)
 	pushf				# Save caller passed flags
 	push	$0			# Kill any dangerous flags
diff --git a/arch/x86/tools/cpufeaturemasks.awk b/arch/x86/tools/cpufeaturemasks.awk
new file mode 100755
index 0000000000000..59757ca3897a7
--- /dev/null
+++ b/arch/x86/tools/cpufeaturemasks.awk
@@ -0,0 +1,81 @@
+#!/usr/bin/awk
+#
+# Convert cpufeatures.h to a list of compile-time masks
+# Note: this blithely assumes that each word has at least one
+# feature defined in it; if not, something else is wrong!
+#
+
+BEGIN {
+	printf "#ifndef _ASM_X86_CPUFEATUREMASKS_H\n";
+	printf "#define _ASM_X86_CPUFEATUREMASKS_H\n\n";
+
+	file = 0
+}
+
+FNR == 1 {
+	++file;
+
+	# arch/x86/include/asm/cpufeatures.h
+	if (file == 1)
+		FS = "[ \t()*+]+";
+
+	# .config
+	if (file == 2)
+		FS = "=";
+}
+
+# Create a dictionary of sorts, containing all defined feature bits
+file == 1 && $1 ~ /^#define$/ && $2 ~ /^X86_FEATURE_/ {
+	nfeat = $3 * $4 + $5;
+	feat = $2;
+	sub(/^X86_FEATURE_/, "", feat);
+	feats[nfeat] = feat;
+}
+file == 1 && $1 ~ /^#define$/ && $2 == "NCAPINTS" {
+	ncapints = int($3);
+}
+
+# Create a dictionary featstat[REQUIRED|DISABLED, FEATURE_NAME] = on | off
+file == 2 && $1 ~ /^CONFIG_X86_(REQUIRED|DISABLED)_FEATURE_/ {
+	on = ($2 == "y");
+	if (split($1, fs, "CONFIG_X86_|_FEATURE_") == 3)
+		featstat[fs[2], fs[3]] = on;
+}
+
+END {
+	sets[1] = "REQUIRED";
+	sets[2] = "DISABLED";
+
+	for (ns in sets) {
+		s = sets[ns];
+
+		printf "/*\n";
+		printf " * %s features:\n", s;
+		printf " *\n";
+		fstr = "";
+		for (i = 0; i < ncapints; i++) {
+			mask = 0;
+			for (j = 0; j < 32; j++) {
+				feat = feats[i*32 + j];
+				if (featstat[s, feat]) {
+					nfstr = fstr " " feat;
+					if (length(nfstr) > 72) {
+						printf " *   %s\n", fstr;
+						nfstr = " " feat;
+					}
+					fstr = nfstr;
+					mask += (2 ^ j);
+				}
+			}
+			masks[i] = mask;
+		}
+		printf " *   %s\n */\n", fstr;
+
+		for (i = 0; i < ncapints; i++)
+			printf "#define %s_MASK%d\t0x%08xU\n", s, i, masks[i];
+
+		printf "#define %s_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != %d)\n\n", s, ncapints;
+	}
+
+	printf "#endif /* _ASM_X86_CPUFEATUREMASKS_H */\n";
+}

From 892a533b724688062d5cd873be044b5fa50e1568 Mon Sep 17 00:00:00 2001
From: "Xin Li (Intel)" <xin@zytor.com>
Date: Mon, 10 Mar 2025 08:32:12 +0100
Subject: [PATCH 1134/1173] x86/cpufeatures: Remove
 {disabled,required}-features.h

The functionalities of {disabled,required}-features.h have been replaced with
the auto-generated generated/<asm/cpufeaturemasks.h> header.

Thus they are no longer needed and can be removed.

None of the macros defined in {disabled,required}-features.h is used in tools,
delete them too.

Signed-off-by: Xin Li (Intel) <xin@zytor.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250305184725.3341760-4-xin@zytor.com
---
 arch/x86/include/asm/disabled-features.h      | 167 ------------------
 arch/x86/include/asm/required-features.h      | 105 -----------
 tools/arch/x86/include/asm/cpufeatures.h      |   8 -
 .../arch/x86/include/asm/disabled-features.h  | 161 -----------------
 .../arch/x86/include/asm/required-features.h  | 105 -----------
 tools/perf/check-headers.sh                   |   2 -
 6 files changed, 548 deletions(-)
 delete mode 100644 arch/x86/include/asm/disabled-features.h
 delete mode 100644 arch/x86/include/asm/required-features.h
 delete mode 100644 tools/arch/x86/include/asm/disabled-features.h
 delete mode 100644 tools/arch/x86/include/asm/required-features.h

diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
deleted file mode 100644
index be8c38855068f..0000000000000
--- a/arch/x86/include/asm/disabled-features.h
+++ /dev/null
@@ -1,167 +0,0 @@
-#ifndef _ASM_X86_DISABLED_FEATURES_H
-#define _ASM_X86_DISABLED_FEATURES_H
-
-/* These features, although they might be available in a CPU
- * will not be used because the compile options to support
- * them are not present.
- *
- * This code allows them to be checked and disabled at
- * compile time without an explicit #ifdef.  Use
- * cpu_feature_enabled().
- */
-
-#ifdef CONFIG_X86_UMIP
-# define DISABLE_UMIP	0
-#else
-# define DISABLE_UMIP	(1<<(X86_FEATURE_UMIP & 31))
-#endif
-
-#ifdef CONFIG_X86_64
-# define DISABLE_VME		(1<<(X86_FEATURE_VME & 31))
-# define DISABLE_K6_MTRR	(1<<(X86_FEATURE_K6_MTRR & 31))
-# define DISABLE_CYRIX_ARR	(1<<(X86_FEATURE_CYRIX_ARR & 31))
-# define DISABLE_CENTAUR_MCR	(1<<(X86_FEATURE_CENTAUR_MCR & 31))
-# define DISABLE_PCID		0
-#else
-# define DISABLE_VME		0
-# define DISABLE_K6_MTRR	0
-# define DISABLE_CYRIX_ARR	0
-# define DISABLE_CENTAUR_MCR	0
-# define DISABLE_PCID		(1<<(X86_FEATURE_PCID & 31))
-#endif /* CONFIG_X86_64 */
-
-#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
-# define DISABLE_PKU		0
-# define DISABLE_OSPKE		0
-#else
-# define DISABLE_PKU		(1<<(X86_FEATURE_PKU & 31))
-# define DISABLE_OSPKE		(1<<(X86_FEATURE_OSPKE & 31))
-#endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */
-
-#ifdef CONFIG_X86_5LEVEL
-# define DISABLE_LA57	0
-#else
-# define DISABLE_LA57	(1<<(X86_FEATURE_LA57 & 31))
-#endif
-
-#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
-# define DISABLE_PTI		0
-#else
-# define DISABLE_PTI		(1 << (X86_FEATURE_PTI & 31))
-#endif
-
-#ifdef CONFIG_MITIGATION_RETPOLINE
-# define DISABLE_RETPOLINE	0
-#else
-# define DISABLE_RETPOLINE	((1 << (X86_FEATURE_RETPOLINE & 31)) | \
-				 (1 << (X86_FEATURE_RETPOLINE_LFENCE & 31)))
-#endif
-
-#ifdef CONFIG_MITIGATION_RETHUNK
-# define DISABLE_RETHUNK	0
-#else
-# define DISABLE_RETHUNK	(1 << (X86_FEATURE_RETHUNK & 31))
-#endif
-
-#ifdef CONFIG_MITIGATION_UNRET_ENTRY
-# define DISABLE_UNRET		0
-#else
-# define DISABLE_UNRET		(1 << (X86_FEATURE_UNRET & 31))
-#endif
-
-#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING
-# define DISABLE_CALL_DEPTH_TRACKING	0
-#else
-# define DISABLE_CALL_DEPTH_TRACKING	(1 << (X86_FEATURE_CALL_DEPTH & 31))
-#endif
-
-#ifdef CONFIG_ADDRESS_MASKING
-# define DISABLE_LAM		0
-#else
-# define DISABLE_LAM		(1 << (X86_FEATURE_LAM & 31))
-#endif
-
-#ifdef CONFIG_INTEL_IOMMU_SVM
-# define DISABLE_ENQCMD		0
-#else
-# define DISABLE_ENQCMD		(1 << (X86_FEATURE_ENQCMD & 31))
-#endif
-
-#ifdef CONFIG_X86_SGX
-# define DISABLE_SGX	0
-#else
-# define DISABLE_SGX	(1 << (X86_FEATURE_SGX & 31))
-#endif
-
-#ifdef CONFIG_XEN_PV
-# define DISABLE_XENPV		0
-#else
-# define DISABLE_XENPV		(1 << (X86_FEATURE_XENPV & 31))
-#endif
-
-#ifdef CONFIG_INTEL_TDX_GUEST
-# define DISABLE_TDX_GUEST	0
-#else
-# define DISABLE_TDX_GUEST	(1 << (X86_FEATURE_TDX_GUEST & 31))
-#endif
-
-#ifdef CONFIG_X86_USER_SHADOW_STACK
-#define DISABLE_USER_SHSTK	0
-#else
-#define DISABLE_USER_SHSTK	(1 << (X86_FEATURE_USER_SHSTK & 31))
-#endif
-
-#ifdef CONFIG_X86_KERNEL_IBT
-#define DISABLE_IBT	0
-#else
-#define DISABLE_IBT	(1 << (X86_FEATURE_IBT & 31))
-#endif
-
-#ifdef CONFIG_X86_FRED
-# define DISABLE_FRED	0
-#else
-# define DISABLE_FRED	(1 << (X86_FEATURE_FRED & 31))
-#endif
-
-#ifdef CONFIG_KVM_AMD_SEV
-#define DISABLE_SEV_SNP		0
-#else
-#define DISABLE_SEV_SNP		(1 << (X86_FEATURE_SEV_SNP & 31))
-#endif
-
-#ifdef CONFIG_BROADCAST_TLB_FLUSH
-#define DISABLE_INVLPGB		0
-#else
-#define DISABLE_INVLPGB		(1 << (X86_FEATURE_INVLPGB & 31))
-#endif
-
-/*
- * Make sure to add features to the correct mask
- */
-#define DISABLED_MASK0	(DISABLE_VME)
-#define DISABLED_MASK1	0
-#define DISABLED_MASK2	0
-#define DISABLED_MASK3	(DISABLE_CYRIX_ARR|DISABLE_CENTAUR_MCR|DISABLE_K6_MTRR)
-#define DISABLED_MASK4	(DISABLE_PCID)
-#define DISABLED_MASK5	0
-#define DISABLED_MASK6	0
-#define DISABLED_MASK7	(DISABLE_PTI)
-#define DISABLED_MASK8	(DISABLE_XENPV|DISABLE_TDX_GUEST)
-#define DISABLED_MASK9	(DISABLE_SGX)
-#define DISABLED_MASK10	0
-#define DISABLED_MASK11	(DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET| \
-			 DISABLE_CALL_DEPTH_TRACKING|DISABLE_USER_SHSTK)
-#define DISABLED_MASK12	(DISABLE_FRED|DISABLE_LAM)
-#define DISABLED_MASK13	(DISABLE_INVLPGB)
-#define DISABLED_MASK14	0
-#define DISABLED_MASK15	0
-#define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP| \
-			 DISABLE_ENQCMD)
-#define DISABLED_MASK17	0
-#define DISABLED_MASK18	(DISABLE_IBT)
-#define DISABLED_MASK19	(DISABLE_SEV_SNP)
-#define DISABLED_MASK20	0
-#define DISABLED_MASK21	0
-#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22)
-
-#endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
deleted file mode 100644
index 0068133cb622f..0000000000000
--- a/arch/x86/include/asm/required-features.h
+++ /dev/null
@@ -1,105 +0,0 @@
-#ifndef _ASM_X86_REQUIRED_FEATURES_H
-#define _ASM_X86_REQUIRED_FEATURES_H
-
-/* Define minimum CPUID feature set for kernel These bits are checked
-   really early to actually display a visible error message before the
-   kernel dies.  Make sure to assign features to the proper mask!
-
-   Some requirements that are not in CPUID yet are also in the
-   CONFIG_X86_MINIMUM_CPU_FAMILY which is checked too.
-
-   The real information is in arch/x86/Kconfig.cpu, this just converts
-   the CONFIGs into a bitmask */
-
-#ifndef CONFIG_MATH_EMULATION
-# define NEED_FPU	(1<<(X86_FEATURE_FPU & 31))
-#else
-# define NEED_FPU	0
-#endif
-
-#if defined(CONFIG_X86_PAE) || defined(CONFIG_X86_64)
-# define NEED_PAE	(1<<(X86_FEATURE_PAE & 31))
-#else
-# define NEED_PAE	0
-#endif
-
-#ifdef CONFIG_X86_CX8
-# define NEED_CX8	(1<<(X86_FEATURE_CX8 & 31))
-#else
-# define NEED_CX8	0
-#endif
-
-#if defined(CONFIG_X86_CMOV) || defined(CONFIG_X86_64)
-# define NEED_CMOV	(1<<(X86_FEATURE_CMOV & 31))
-#else
-# define NEED_CMOV	0
-#endif
-
-# define NEED_3DNOW	0
-
-#if defined(CONFIG_X86_P6_NOP) || defined(CONFIG_X86_64)
-# define NEED_NOPL	(1<<(X86_FEATURE_NOPL & 31))
-#else
-# define NEED_NOPL	0
-#endif
-
-#ifdef CONFIG_MATOM
-# define NEED_MOVBE	(1<<(X86_FEATURE_MOVBE & 31))
-#else
-# define NEED_MOVBE	0
-#endif
-
-#ifdef CONFIG_X86_64
-#ifdef CONFIG_PARAVIRT_XXL
-/* Paravirtualized systems may not have PSE or PGE available */
-#define NEED_PSE	0
-#define NEED_PGE	0
-#else
-#define NEED_PSE	(1<<(X86_FEATURE_PSE) & 31)
-#define NEED_PGE	(1<<(X86_FEATURE_PGE) & 31)
-#endif
-#define NEED_MSR	(1<<(X86_FEATURE_MSR & 31))
-#define NEED_FXSR	(1<<(X86_FEATURE_FXSR & 31))
-#define NEED_XMM	(1<<(X86_FEATURE_XMM & 31))
-#define NEED_XMM2	(1<<(X86_FEATURE_XMM2 & 31))
-#define NEED_LM		(1<<(X86_FEATURE_LM & 31))
-#else
-#define NEED_PSE	0
-#define NEED_MSR	0
-#define NEED_PGE	0
-#define NEED_FXSR	0
-#define NEED_XMM	0
-#define NEED_XMM2	0
-#define NEED_LM		0
-#endif
-
-#define REQUIRED_MASK0	(NEED_FPU|NEED_PSE|NEED_MSR|NEED_PAE|\
-			 NEED_CX8|NEED_PGE|NEED_FXSR|NEED_CMOV|\
-			 NEED_XMM|NEED_XMM2)
-#define SSE_MASK	(NEED_XMM|NEED_XMM2)
-
-#define REQUIRED_MASK1	(NEED_LM|NEED_3DNOW)
-
-#define REQUIRED_MASK2	0
-#define REQUIRED_MASK3	(NEED_NOPL)
-#define REQUIRED_MASK4	(NEED_MOVBE)
-#define REQUIRED_MASK5	0
-#define REQUIRED_MASK6	0
-#define REQUIRED_MASK7	0
-#define REQUIRED_MASK8	0
-#define REQUIRED_MASK9	0
-#define REQUIRED_MASK10	0
-#define REQUIRED_MASK11	0
-#define REQUIRED_MASK12	0
-#define REQUIRED_MASK13	0
-#define REQUIRED_MASK14	0
-#define REQUIRED_MASK15	0
-#define REQUIRED_MASK16	0
-#define REQUIRED_MASK17	0
-#define REQUIRED_MASK18	0
-#define REQUIRED_MASK19	0
-#define REQUIRED_MASK20	0
-#define REQUIRED_MASK21	0
-#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22)
-
-#endif /* _ASM_X86_REQUIRED_FEATURES_H */
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 17b6590748c00..c691481d59ce2 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -2,14 +2,6 @@
 #ifndef _ASM_X86_CPUFEATURES_H
 #define _ASM_X86_CPUFEATURES_H
 
-#ifndef _ASM_X86_REQUIRED_FEATURES_H
-#include <asm/required-features.h>
-#endif
-
-#ifndef _ASM_X86_DISABLED_FEATURES_H
-#include <asm/disabled-features.h>
-#endif
-
 /*
  * Defines x86 CPU feature bits
  */
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
deleted file mode 100644
index c492bdc97b059..0000000000000
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ /dev/null
@@ -1,161 +0,0 @@
-#ifndef _ASM_X86_DISABLED_FEATURES_H
-#define _ASM_X86_DISABLED_FEATURES_H
-
-/* These features, although they might be available in a CPU
- * will not be used because the compile options to support
- * them are not present.
- *
- * This code allows them to be checked and disabled at
- * compile time without an explicit #ifdef.  Use
- * cpu_feature_enabled().
- */
-
-#ifdef CONFIG_X86_UMIP
-# define DISABLE_UMIP	0
-#else
-# define DISABLE_UMIP	(1<<(X86_FEATURE_UMIP & 31))
-#endif
-
-#ifdef CONFIG_X86_64
-# define DISABLE_VME		(1<<(X86_FEATURE_VME & 31))
-# define DISABLE_K6_MTRR	(1<<(X86_FEATURE_K6_MTRR & 31))
-# define DISABLE_CYRIX_ARR	(1<<(X86_FEATURE_CYRIX_ARR & 31))
-# define DISABLE_CENTAUR_MCR	(1<<(X86_FEATURE_CENTAUR_MCR & 31))
-# define DISABLE_PCID		0
-#else
-# define DISABLE_VME		0
-# define DISABLE_K6_MTRR	0
-# define DISABLE_CYRIX_ARR	0
-# define DISABLE_CENTAUR_MCR	0
-# define DISABLE_PCID		(1<<(X86_FEATURE_PCID & 31))
-#endif /* CONFIG_X86_64 */
-
-#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
-# define DISABLE_PKU		0
-# define DISABLE_OSPKE		0
-#else
-# define DISABLE_PKU		(1<<(X86_FEATURE_PKU & 31))
-# define DISABLE_OSPKE		(1<<(X86_FEATURE_OSPKE & 31))
-#endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */
-
-#ifdef CONFIG_X86_5LEVEL
-# define DISABLE_LA57	0
-#else
-# define DISABLE_LA57	(1<<(X86_FEATURE_LA57 & 31))
-#endif
-
-#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
-# define DISABLE_PTI		0
-#else
-# define DISABLE_PTI		(1 << (X86_FEATURE_PTI & 31))
-#endif
-
-#ifdef CONFIG_MITIGATION_RETPOLINE
-# define DISABLE_RETPOLINE	0
-#else
-# define DISABLE_RETPOLINE	((1 << (X86_FEATURE_RETPOLINE & 31)) | \
-				 (1 << (X86_FEATURE_RETPOLINE_LFENCE & 31)))
-#endif
-
-#ifdef CONFIG_MITIGATION_RETHUNK
-# define DISABLE_RETHUNK	0
-#else
-# define DISABLE_RETHUNK	(1 << (X86_FEATURE_RETHUNK & 31))
-#endif
-
-#ifdef CONFIG_MITIGATION_UNRET_ENTRY
-# define DISABLE_UNRET		0
-#else
-# define DISABLE_UNRET		(1 << (X86_FEATURE_UNRET & 31))
-#endif
-
-#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING
-# define DISABLE_CALL_DEPTH_TRACKING	0
-#else
-# define DISABLE_CALL_DEPTH_TRACKING	(1 << (X86_FEATURE_CALL_DEPTH & 31))
-#endif
-
-#ifdef CONFIG_ADDRESS_MASKING
-# define DISABLE_LAM		0
-#else
-# define DISABLE_LAM		(1 << (X86_FEATURE_LAM & 31))
-#endif
-
-#ifdef CONFIG_INTEL_IOMMU_SVM
-# define DISABLE_ENQCMD		0
-#else
-# define DISABLE_ENQCMD		(1 << (X86_FEATURE_ENQCMD & 31))
-#endif
-
-#ifdef CONFIG_X86_SGX
-# define DISABLE_SGX	0
-#else
-# define DISABLE_SGX	(1 << (X86_FEATURE_SGX & 31))
-#endif
-
-#ifdef CONFIG_XEN_PV
-# define DISABLE_XENPV		0
-#else
-# define DISABLE_XENPV		(1 << (X86_FEATURE_XENPV & 31))
-#endif
-
-#ifdef CONFIG_INTEL_TDX_GUEST
-# define DISABLE_TDX_GUEST	0
-#else
-# define DISABLE_TDX_GUEST	(1 << (X86_FEATURE_TDX_GUEST & 31))
-#endif
-
-#ifdef CONFIG_X86_USER_SHADOW_STACK
-#define DISABLE_USER_SHSTK	0
-#else
-#define DISABLE_USER_SHSTK	(1 << (X86_FEATURE_USER_SHSTK & 31))
-#endif
-
-#ifdef CONFIG_X86_KERNEL_IBT
-#define DISABLE_IBT	0
-#else
-#define DISABLE_IBT	(1 << (X86_FEATURE_IBT & 31))
-#endif
-
-#ifdef CONFIG_X86_FRED
-# define DISABLE_FRED	0
-#else
-# define DISABLE_FRED	(1 << (X86_FEATURE_FRED & 31))
-#endif
-
-#ifdef CONFIG_KVM_AMD_SEV
-#define DISABLE_SEV_SNP		0
-#else
-#define DISABLE_SEV_SNP		(1 << (X86_FEATURE_SEV_SNP & 31))
-#endif
-
-/*
- * Make sure to add features to the correct mask
- */
-#define DISABLED_MASK0	(DISABLE_VME)
-#define DISABLED_MASK1	0
-#define DISABLED_MASK2	0
-#define DISABLED_MASK3	(DISABLE_CYRIX_ARR|DISABLE_CENTAUR_MCR|DISABLE_K6_MTRR)
-#define DISABLED_MASK4	(DISABLE_PCID)
-#define DISABLED_MASK5	0
-#define DISABLED_MASK6	0
-#define DISABLED_MASK7	(DISABLE_PTI)
-#define DISABLED_MASK8	(DISABLE_XENPV|DISABLE_TDX_GUEST)
-#define DISABLED_MASK9	(DISABLE_SGX)
-#define DISABLED_MASK10	0
-#define DISABLED_MASK11	(DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET| \
-			 DISABLE_CALL_DEPTH_TRACKING|DISABLE_USER_SHSTK)
-#define DISABLED_MASK12	(DISABLE_FRED|DISABLE_LAM)
-#define DISABLED_MASK13	0
-#define DISABLED_MASK14	0
-#define DISABLED_MASK15	0
-#define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP| \
-			 DISABLE_ENQCMD)
-#define DISABLED_MASK17	0
-#define DISABLED_MASK18	(DISABLE_IBT)
-#define DISABLED_MASK19	(DISABLE_SEV_SNP)
-#define DISABLED_MASK20	0
-#define DISABLED_MASK21	0
-#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22)
-
-#endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h
deleted file mode 100644
index 0068133cb622f..0000000000000
--- a/tools/arch/x86/include/asm/required-features.h
+++ /dev/null
@@ -1,105 +0,0 @@
-#ifndef _ASM_X86_REQUIRED_FEATURES_H
-#define _ASM_X86_REQUIRED_FEATURES_H
-
-/* Define minimum CPUID feature set for kernel These bits are checked
-   really early to actually display a visible error message before the
-   kernel dies.  Make sure to assign features to the proper mask!
-
-   Some requirements that are not in CPUID yet are also in the
-   CONFIG_X86_MINIMUM_CPU_FAMILY which is checked too.
-
-   The real information is in arch/x86/Kconfig.cpu, this just converts
-   the CONFIGs into a bitmask */
-
-#ifndef CONFIG_MATH_EMULATION
-# define NEED_FPU	(1<<(X86_FEATURE_FPU & 31))
-#else
-# define NEED_FPU	0
-#endif
-
-#if defined(CONFIG_X86_PAE) || defined(CONFIG_X86_64)
-# define NEED_PAE	(1<<(X86_FEATURE_PAE & 31))
-#else
-# define NEED_PAE	0
-#endif
-
-#ifdef CONFIG_X86_CX8
-# define NEED_CX8	(1<<(X86_FEATURE_CX8 & 31))
-#else
-# define NEED_CX8	0
-#endif
-
-#if defined(CONFIG_X86_CMOV) || defined(CONFIG_X86_64)
-# define NEED_CMOV	(1<<(X86_FEATURE_CMOV & 31))
-#else
-# define NEED_CMOV	0
-#endif
-
-# define NEED_3DNOW	0
-
-#if defined(CONFIG_X86_P6_NOP) || defined(CONFIG_X86_64)
-# define NEED_NOPL	(1<<(X86_FEATURE_NOPL & 31))
-#else
-# define NEED_NOPL	0
-#endif
-
-#ifdef CONFIG_MATOM
-# define NEED_MOVBE	(1<<(X86_FEATURE_MOVBE & 31))
-#else
-# define NEED_MOVBE	0
-#endif
-
-#ifdef CONFIG_X86_64
-#ifdef CONFIG_PARAVIRT_XXL
-/* Paravirtualized systems may not have PSE or PGE available */
-#define NEED_PSE	0
-#define NEED_PGE	0
-#else
-#define NEED_PSE	(1<<(X86_FEATURE_PSE) & 31)
-#define NEED_PGE	(1<<(X86_FEATURE_PGE) & 31)
-#endif
-#define NEED_MSR	(1<<(X86_FEATURE_MSR & 31))
-#define NEED_FXSR	(1<<(X86_FEATURE_FXSR & 31))
-#define NEED_XMM	(1<<(X86_FEATURE_XMM & 31))
-#define NEED_XMM2	(1<<(X86_FEATURE_XMM2 & 31))
-#define NEED_LM		(1<<(X86_FEATURE_LM & 31))
-#else
-#define NEED_PSE	0
-#define NEED_MSR	0
-#define NEED_PGE	0
-#define NEED_FXSR	0
-#define NEED_XMM	0
-#define NEED_XMM2	0
-#define NEED_LM		0
-#endif
-
-#define REQUIRED_MASK0	(NEED_FPU|NEED_PSE|NEED_MSR|NEED_PAE|\
-			 NEED_CX8|NEED_PGE|NEED_FXSR|NEED_CMOV|\
-			 NEED_XMM|NEED_XMM2)
-#define SSE_MASK	(NEED_XMM|NEED_XMM2)
-
-#define REQUIRED_MASK1	(NEED_LM|NEED_3DNOW)
-
-#define REQUIRED_MASK2	0
-#define REQUIRED_MASK3	(NEED_NOPL)
-#define REQUIRED_MASK4	(NEED_MOVBE)
-#define REQUIRED_MASK5	0
-#define REQUIRED_MASK6	0
-#define REQUIRED_MASK7	0
-#define REQUIRED_MASK8	0
-#define REQUIRED_MASK9	0
-#define REQUIRED_MASK10	0
-#define REQUIRED_MASK11	0
-#define REQUIRED_MASK12	0
-#define REQUIRED_MASK13	0
-#define REQUIRED_MASK14	0
-#define REQUIRED_MASK15	0
-#define REQUIRED_MASK16	0
-#define REQUIRED_MASK17	0
-#define REQUIRED_MASK18	0
-#define REQUIRED_MASK19	0
-#define REQUIRED_MASK20	0
-#define REQUIRED_MASK21	0
-#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22)
-
-#endif /* _ASM_X86_REQUIRED_FEATURES_H */
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index d3c6e10dce73f..a4499e5a6f9cb 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -26,8 +26,6 @@ FILES=(
   "include/linux/hash.h"
   "include/linux/list-sort.h"
   "include/uapi/linux/hw_breakpoint.h"
-  "arch/x86/include/asm/disabled-features.h"
-  "arch/x86/include/asm/required-features.h"
   "arch/x86/include/asm/cpufeatures.h"
   "arch/x86/include/asm/inat_types.h"
   "arch/x86/include/asm/emulate_prefix.h"

From 55d9f0b05e1ca53c0884545445b7e29466679a33 Mon Sep 17 00:00:00 2001
From: "Xin Li (Intel)" <xin@zytor.com>
Date: Fri, 28 Feb 2025 00:23:38 -0800
Subject: [PATCH 1135/1173] x86/cpufeatures: Use AWK to generate
 {REQUIRED|DISABLED}_MASK_BIT_SET in <asm/cpufeaturemasks.h>

Generate the {REQUIRED|DISABLED}_MASK_BIT_SET macros in the newly added AWK
script that generates <asm/cpufeaturemasks.h>.

Suggested-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Xin Li (Intel) <xin@zytor.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Brian Gerst <brgerst@gmail.com>
Reviewed-by: Nikolay Borisov <nik.borisov@suse.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250228082338.73859-6-xin@zytor.com
---
 arch/x86/include/asm/cpufeature.h  | 69 ------------------------------
 arch/x86/tools/cpufeaturemasks.awk |  9 +++-
 2 files changed, 8 insertions(+), 70 deletions(-)

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index d54db88fae93b..910601c59d319 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -51,75 +51,6 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 #define test_cpu_cap(c, bit)						\
 	 arch_test_bit(bit, (unsigned long *)((c)->x86_capability))
 
-/*
- * There are 32 bits/features in each mask word.  The high bits
- * (selected with (bit>>5) give us the word number and the low 5
- * bits give us the bit/feature number inside the word.
- * (1UL<<((bit)&31) gives us a mask for the feature_bit so we can
- * see if it is set in the mask word.
- */
-#define CHECK_BIT_IN_MASK_WORD(maskname, word, bit)	\
-	(((bit)>>5)==(word) && (1UL<<((bit)&31) & maskname##word ))
-
-/*
- * {REQUIRED,DISABLED}_MASK_CHECK below may seem duplicated with the
- * following BUILD_BUG_ON_ZERO() check but when NCAPINTS gets changed, all
- * header macros which use NCAPINTS need to be changed. The duplicated macro
- * use causes the compiler to issue errors for all headers so that all usage
- * sites can be corrected.
- */
-#define REQUIRED_MASK_BIT_SET(feature_bit)		\
-	 ( CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  0, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  1, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  2, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  3, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  4, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  5, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  6, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  7, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  8, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  9, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 10, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 11, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 12, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 13, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 14, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 15, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 16, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 17, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 19, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 20, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 21, feature_bit) ||	\
-	   REQUIRED_MASK_CHECK					  ||	\
-	   BUILD_BUG_ON_ZERO(NCAPINTS != 22))
-
-#define DISABLED_MASK_BIT_SET(feature_bit)				\
-	 ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  0, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  1, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  2, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  3, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  4, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  5, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  6, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  7, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  8, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  9, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 10, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 11, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 12, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 13, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 14, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 15, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 16, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 17, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 19, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 20, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 21, feature_bit) ||	\
-	   DISABLED_MASK_CHECK					  ||	\
-	   BUILD_BUG_ON_ZERO(NCAPINTS != 22))
-
 #define cpu_has(c, bit)							\
 	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 :	\
 	 test_cpu_cap(c, bit))
diff --git a/arch/x86/tools/cpufeaturemasks.awk b/arch/x86/tools/cpufeaturemasks.awk
index 59757ca3897a7..173d5bf2d999f 100755
--- a/arch/x86/tools/cpufeaturemasks.awk
+++ b/arch/x86/tools/cpufeaturemasks.awk
@@ -74,7 +74,14 @@ END {
 		for (i = 0; i < ncapints; i++)
 			printf "#define %s_MASK%d\t0x%08xU\n", s, i, masks[i];
 
-		printf "#define %s_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != %d)\n\n", s, ncapints;
+		printf "\n#define %s_MASK_BIT_SET(x)\t\t\t\\\n", s;
+		printf "\t((\t\t\t\t\t";
+		for (i = 0; i < ncapints; i++) {
+			if (masks[i])
+				printf "\t\\\n\t\t((x) >> 5) == %2d ? %s_MASK%d :", i, s, i;
+		}
+		printf " 0\t\\\n";
+		printf "\t) & (1U << ((x) & 31)))\n\n";
 	}
 
 	printf "#endif /* _ASM_X86_CPUFEATUREMASKS_H */\n";

From aa4a1d5b198314e9ef02844d0f9426efd5127f74 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 15 Jan 2025 09:53:50 +0100
Subject: [PATCH 1136/1173] irqdomain: Remove extern from function declarations

'extern' is not needed for function declarations. So remove it from
irqdomain.h. Note that the declarations are now unified as some had
'extern' and some did not.

Signed-off-by: Jiri Slaby (SUSE) <jirislaby@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250115085409.1629787-2-jirislaby@kernel.org
---
 include/linux/irqdomain.h | 140 +++++++++++++++++++-------------------
 1 file changed, 71 insertions(+), 69 deletions(-)

diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index e432b6a12a32f..5c0ec335d980f 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -350,13 +350,13 @@ struct irq_domain *irq_domain_create_legacy(struct fwnode_handle *fwnode,
 					    irq_hw_number_t first_hwirq,
 					    const struct irq_domain_ops *ops,
 					    void *host_data);
-extern struct irq_domain *irq_find_matching_fwspec(struct irq_fwspec *fwspec,
-						   enum irq_domain_bus_token bus_token);
-extern void irq_set_default_host(struct irq_domain *host);
-extern struct irq_domain *irq_get_default_host(void);
-extern int irq_domain_alloc_descs(int virq, unsigned int nr_irqs,
-				  irq_hw_number_t hwirq, int node,
-				  const struct irq_affinity_desc *affinity);
+struct irq_domain *irq_find_matching_fwspec(struct irq_fwspec *fwspec,
+					    enum irq_domain_bus_token bus_token);
+void irq_set_default_host(struct irq_domain *host);
+struct irq_domain *irq_get_default_host(void);
+int irq_domain_alloc_descs(int virq, unsigned int nr_irqs,
+			   irq_hw_number_t hwirq, int node,
+			   const struct irq_affinity_desc *affinity);
 
 static inline struct fwnode_handle *of_node_to_fwnode(struct device_node *node)
 {
@@ -370,8 +370,8 @@ static inline bool is_fwnode_irqchip(const struct fwnode_handle *fwnode)
 	return fwnode && fwnode->ops == &irqchip_fwnode_ops;
 }
 
-extern void irq_domain_update_bus_token(struct irq_domain *domain,
-					enum irq_domain_bus_token bus_token);
+void irq_domain_update_bus_token(struct irq_domain *domain,
+				 enum irq_domain_bus_token bus_token);
 
 static inline
 struct irq_domain *irq_find_matching_fwnode(struct fwnode_handle *fwnode,
@@ -454,7 +454,7 @@ static inline struct irq_domain *irq_domain_add_nomap(struct device_node *of_nod
 	return IS_ERR(d) ? NULL : d;
 }
 
-extern unsigned int irq_create_direct_mapping(struct irq_domain *host);
+unsigned int irq_create_direct_mapping(struct irq_domain *host);
 #endif
 
 static inline struct irq_domain *irq_domain_add_tree(struct device_node *of_node,
@@ -507,19 +507,19 @@ static inline struct irq_domain *irq_domain_create_tree(struct fwnode_handle *fw
 	return IS_ERR(d) ? NULL : d;
 }
 
-extern void irq_domain_remove(struct irq_domain *host);
+void irq_domain_remove(struct irq_domain *host);
 
-extern int irq_domain_associate(struct irq_domain *domain, unsigned int irq,
-					irq_hw_number_t hwirq);
-extern void irq_domain_associate_many(struct irq_domain *domain,
-				      unsigned int irq_base,
-				      irq_hw_number_t hwirq_base, int count);
+int irq_domain_associate(struct irq_domain *domain, unsigned int irq,
+			 irq_hw_number_t hwirq);
+void irq_domain_associate_many(struct irq_domain *domain,
+			       unsigned int irq_base,
+			       irq_hw_number_t hwirq_base, int count);
 
-extern unsigned int irq_create_mapping_affinity(struct irq_domain *host,
-				      irq_hw_number_t hwirq,
-				      const struct irq_affinity_desc *affinity);
-extern unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec);
-extern void irq_dispose_mapping(unsigned int virq);
+unsigned int irq_create_mapping_affinity(struct irq_domain *host,
+					 irq_hw_number_t hwirq,
+					 const struct irq_affinity_desc *affinity);
+unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec);
+void irq_dispose_mapping(unsigned int virq);
 
 static inline unsigned int irq_create_mapping(struct irq_domain *host,
 					      irq_hw_number_t hwirq)
@@ -527,9 +527,9 @@ static inline unsigned int irq_create_mapping(struct irq_domain *host,
 	return irq_create_mapping_affinity(host, hwirq, NULL);
 }
 
-extern struct irq_desc *__irq_resolve_mapping(struct irq_domain *domain,
-					      irq_hw_number_t hwirq,
-					      unsigned int *irq);
+struct irq_desc *__irq_resolve_mapping(struct irq_domain *domain,
+				       irq_hw_number_t hwirq,
+				       unsigned int *irq);
 
 static inline struct irq_desc *irq_resolve_mapping(struct irq_domain *domain,
 						   irq_hw_number_t hwirq)
@@ -587,19 +587,21 @@ int irq_reserve_ipi(struct irq_domain *domain, const struct cpumask *dest);
 int irq_destroy_ipi(unsigned int irq, const struct cpumask *dest);
 
 /* V2 interfaces to support hierarchy IRQ domains. */
-extern struct irq_data *irq_domain_get_irq_data(struct irq_domain *domain,
-						unsigned int virq);
-extern void irq_domain_set_info(struct irq_domain *domain, unsigned int virq,
-				irq_hw_number_t hwirq,
-				const struct irq_chip *chip,
-				void *chip_data, irq_flow_handler_t handler,
-				void *handler_data, const char *handler_name);
-extern void irq_domain_reset_irq_data(struct irq_data *irq_data);
+struct irq_data *irq_domain_get_irq_data(struct irq_domain *domain,
+					 unsigned int virq);
+void irq_domain_set_info(struct irq_domain *domain, unsigned int virq,
+			 irq_hw_number_t hwirq,
+			 const struct irq_chip *chip,
+			 void *chip_data, irq_flow_handler_t handler,
+			 void *handler_data, const char *handler_name);
+void irq_domain_reset_irq_data(struct irq_data *irq_data);
 #ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
-extern struct irq_domain *irq_domain_create_hierarchy(struct irq_domain *parent,
-			unsigned int flags, unsigned int size,
-			struct fwnode_handle *fwnode,
-			const struct irq_domain_ops *ops, void *host_data);
+struct irq_domain *irq_domain_create_hierarchy(struct irq_domain *parent,
+					       unsigned int flags,
+					       unsigned int size,
+					       struct fwnode_handle *fwnode,
+					       const struct irq_domain_ops *ops,
+					       void *host_data);
 
 static inline struct irq_domain *irq_domain_add_hierarchy(struct irq_domain *parent,
 					    unsigned int flags,
@@ -613,13 +615,13 @@ static inline struct irq_domain *irq_domain_add_hierarchy(struct irq_domain *par
 					   ops, host_data);
 }
 
-extern int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base,
-				   unsigned int nr_irqs, int node, void *arg,
-				   bool realloc,
-				   const struct irq_affinity_desc *affinity);
-extern void irq_domain_free_irqs(unsigned int virq, unsigned int nr_irqs);
-extern int irq_domain_activate_irq(struct irq_data *irq_data, bool early);
-extern void irq_domain_deactivate_irq(struct irq_data *irq_data);
+int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base,
+			    unsigned int nr_irqs, int node, void *arg,
+			    bool realloc,
+			    const struct irq_affinity_desc *affinity);
+void irq_domain_free_irqs(unsigned int virq, unsigned int nr_irqs);
+int irq_domain_activate_irq(struct irq_data *irq_data, bool early);
+void irq_domain_deactivate_irq(struct irq_data *irq_data);
 
 static inline int irq_domain_alloc_irqs(struct irq_domain *domain,
 			unsigned int nr_irqs, int node, void *arg)
@@ -628,32 +630,32 @@ static inline int irq_domain_alloc_irqs(struct irq_domain *domain,
 				       NULL);
 }
 
-extern int irq_domain_alloc_irqs_hierarchy(struct irq_domain *domain,
-					   unsigned int irq_base,
-					   unsigned int nr_irqs, void *arg);
-extern int irq_domain_set_hwirq_and_chip(struct irq_domain *domain,
-					 unsigned int virq,
-					 irq_hw_number_t hwirq,
-					 const struct irq_chip *chip,
-					 void *chip_data);
-extern void irq_domain_free_irqs_common(struct irq_domain *domain,
-					unsigned int virq,
-					unsigned int nr_irqs);
-extern void irq_domain_free_irqs_top(struct irq_domain *domain,
-				     unsigned int virq, unsigned int nr_irqs);
-
-extern int irq_domain_push_irq(struct irq_domain *domain, int virq, void *arg);
-extern int irq_domain_pop_irq(struct irq_domain *domain, int virq);
-
-extern int irq_domain_alloc_irqs_parent(struct irq_domain *domain,
-					unsigned int irq_base,
-					unsigned int nr_irqs, void *arg);
-
-extern void irq_domain_free_irqs_parent(struct irq_domain *domain,
-					unsigned int irq_base,
-					unsigned int nr_irqs);
-
-extern int irq_domain_disconnect_hierarchy(struct irq_domain *domain,
+int irq_domain_alloc_irqs_hierarchy(struct irq_domain *domain,
+				    unsigned int irq_base,
+				    unsigned int nr_irqs, void *arg);
+int irq_domain_set_hwirq_and_chip(struct irq_domain *domain,
+				  unsigned int virq,
+				  irq_hw_number_t hwirq,
+				  const struct irq_chip *chip,
+				  void *chip_data);
+void irq_domain_free_irqs_common(struct irq_domain *domain,
+				 unsigned int virq,
+				 unsigned int nr_irqs);
+void irq_domain_free_irqs_top(struct irq_domain *domain,
+			      unsigned int virq, unsigned int nr_irqs);
+
+int irq_domain_push_irq(struct irq_domain *domain, int virq, void *arg);
+int irq_domain_pop_irq(struct irq_domain *domain, int virq);
+
+int irq_domain_alloc_irqs_parent(struct irq_domain *domain,
+				 unsigned int irq_base,
+				 unsigned int nr_irqs, void *arg);
+
+void irq_domain_free_irqs_parent(struct irq_domain *domain,
+				 unsigned int irq_base,
+				 unsigned int nr_irqs);
+
+int irq_domain_disconnect_hierarchy(struct irq_domain *domain,
 					   unsigned int virq);
 
 static inline bool irq_domain_is_hierarchy(struct irq_domain *domain)

From 827bafd527dde5a6e81421e88fb2144adac1f36c Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sun, 9 Mar 2025 19:38:26 +0100
Subject: [PATCH 1137/1173] genirq: Make a few functions static

None of these functions are used outside of their source files.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/878qpe2gnx.ffs@tglx
---
 include/linux/irqdomain.h |  3 ---
 kernel/irq/chip.c         | 30 +++++++++++++++---------------
 kernel/irq/internals.h    |  9 ---------
 kernel/irq/irqdesc.c      |  2 +-
 kernel/irq/irqdomain.c    |  5 ++---
 kernel/irq/manage.c       |  7 ++++---
 6 files changed, 22 insertions(+), 34 deletions(-)

diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index 5c0ec335d980f..33ff41eef8f73 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -630,9 +630,6 @@ static inline int irq_domain_alloc_irqs(struct irq_domain *domain,
 				       NULL);
 }
 
-int irq_domain_alloc_irqs_hierarchy(struct irq_domain *domain,
-				    unsigned int irq_base,
-				    unsigned int nr_irqs, void *arg);
 int irq_domain_set_hwirq_and_chip(struct irq_domain *domain,
 				  unsigned int virq,
 				  irq_hw_number_t hwirq,
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index c901436ebd9f4..0ff987d3a7991 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -232,6 +232,21 @@ __irq_startup_managed(struct irq_desc *desc, const struct cpumask *aff,
 }
 #endif
 
+static void irq_enable(struct irq_desc *desc)
+{
+	if (!irqd_irq_disabled(&desc->irq_data)) {
+		unmask_irq(desc);
+	} else {
+		irq_state_clr_disabled(desc);
+		if (desc->irq_data.chip->irq_enable) {
+			desc->irq_data.chip->irq_enable(&desc->irq_data);
+			irq_state_clr_masked(desc);
+		} else {
+			unmask_irq(desc);
+		}
+	}
+}
+
 static int __irq_startup(struct irq_desc *desc)
 {
 	struct irq_data *d = irq_desc_get_irq_data(desc);
@@ -332,21 +347,6 @@ void irq_shutdown_and_deactivate(struct irq_desc *desc)
 	irq_domain_deactivate_irq(&desc->irq_data);
 }
 
-void irq_enable(struct irq_desc *desc)
-{
-	if (!irqd_irq_disabled(&desc->irq_data)) {
-		unmask_irq(desc);
-	} else {
-		irq_state_clr_disabled(desc);
-		if (desc->irq_data.chip->irq_enable) {
-			desc->irq_data.chip->irq_enable(&desc->irq_data);
-			irq_state_clr_masked(desc);
-		} else {
-			unmask_irq(desc);
-		}
-	}
-}
-
 static void __irq_disable(struct irq_desc *desc, bool mask)
 {
 	if (irqd_irq_disabled(&desc->irq_data)) {
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index a979523640d0a..556b7132f831c 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -90,7 +90,6 @@ extern int irq_startup(struct irq_desc *desc, bool resend, bool force);
 
 extern void irq_shutdown(struct irq_desc *desc);
 extern void irq_shutdown_and_deactivate(struct irq_desc *desc);
-extern void irq_enable(struct irq_desc *desc);
 extern void irq_disable(struct irq_desc *desc);
 extern void irq_percpu_enable(struct irq_desc *desc, unsigned int cpu);
 extern void irq_percpu_disable(struct irq_desc *desc, unsigned int cpu);
@@ -98,18 +97,12 @@ extern void mask_irq(struct irq_desc *desc);
 extern void unmask_irq(struct irq_desc *desc);
 extern void unmask_threaded_irq(struct irq_desc *desc);
 
-extern unsigned int kstat_irqs_desc(struct irq_desc *desc, const struct cpumask *cpumask);
-
 #ifdef CONFIG_SPARSE_IRQ
 static inline void irq_mark_irq(unsigned int irq) { }
 #else
 extern void irq_mark_irq(unsigned int irq);
 #endif
 
-extern int __irq_get_irqchip_state(struct irq_data *data,
-				   enum irqchip_irq_state which,
-				   bool *state);
-
 irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc);
 irqreturn_t handle_irq_event_percpu(struct irq_desc *desc);
 irqreturn_t handle_irq_event(struct irq_desc *desc);
@@ -139,8 +132,6 @@ static inline void unregister_handler_proc(unsigned int irq,
 
 extern bool irq_can_set_affinity_usr(unsigned int irq);
 
-extern void irq_set_thread_affinity(struct irq_desc *desc);
-
 extern int irq_do_set_affinity(struct irq_data *data,
 			       const struct cpumask *dest, bool force);
 
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 2878307397833..4258cd6bd3b4f 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -991,7 +991,7 @@ unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
 	return desc && desc->kstat_irqs ? per_cpu(desc->kstat_irqs->cnt, cpu) : 0;
 }
 
-unsigned int kstat_irqs_desc(struct irq_desc *desc, const struct cpumask *cpumask)
+static unsigned int kstat_irqs_desc(struct irq_desc *desc, const struct cpumask *cpumask)
 {
 	unsigned int sum = 0;
 	int cpu;
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index ec6d8e72d980f..2861f89880af5 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -1589,9 +1589,8 @@ static void irq_domain_free_irqs_hierarchy(struct irq_domain *domain,
 	}
 }
 
-int irq_domain_alloc_irqs_hierarchy(struct irq_domain *domain,
-				    unsigned int irq_base,
-				    unsigned int nr_irqs, void *arg)
+static int irq_domain_alloc_irqs_hierarchy(struct irq_domain *domain, unsigned int irq_base,
+					   unsigned int nr_irqs, void *arg)
 {
 	if (!domain->ops->alloc) {
 		pr_debug("domain->ops->alloc() is NULL\n");
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index f300bb6be3bd4..753eef8e041cb 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -35,6 +35,8 @@ static int __init setup_forced_irqthreads(char *arg)
 early_param("threadirqs", setup_forced_irqthreads);
 #endif
 
+static int __irq_get_irqchip_state(struct irq_data *d, enum irqchip_irq_state which, bool *state);
+
 static void __synchronize_hardirq(struct irq_desc *desc, bool sync_chip)
 {
 	struct irq_data *irqd = irq_desc_get_irq_data(desc);
@@ -187,7 +189,7 @@ bool irq_can_set_affinity_usr(unsigned int irq)
  *	set_cpus_allowed_ptr() here as we hold desc->lock and this
  *	code can be called from hard interrupt context.
  */
-void irq_set_thread_affinity(struct irq_desc *desc)
+static void irq_set_thread_affinity(struct irq_desc *desc)
 {
 	struct irqaction *action;
 
@@ -2789,8 +2791,7 @@ void teardown_percpu_nmi(unsigned int irq)
 	irq_put_desc_unlock(desc, flags);
 }
 
-int __irq_get_irqchip_state(struct irq_data *data, enum irqchip_irq_state which,
-			    bool *state)
+static int __irq_get_irqchip_state(struct irq_data *data, enum irqchip_irq_state which, bool *state)
 {
 	struct irq_chip *chip;
 	int err = -EINVAL;

From e28eecf2602bdce826833ccb9a6b7a6bacafd98b Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Mon, 10 Mar 2025 11:42:56 +0100
Subject: [PATCH 1138/1173] x86/headers: Replace __ASSEMBLY__ with
 __ASSEMBLER__ in UAPI headers

__ASSEMBLY__ is only defined by the Makefile of the kernel, so
this is not really useful for UAPI headers (unless the userspace
Makefile defines it, too). Let's switch to __ASSEMBLER__ which
gets set automatically by the compiler when compiling assembly
code.

Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Brian Gerst <brgerst@gmail.com>
Link: https://lore.kernel.org/r/20250310104256.123527-1-thuth@redhat.com
---
 arch/x86/include/uapi/asm/bootparam.h  | 4 ++--
 arch/x86/include/uapi/asm/e820.h       | 4 ++--
 arch/x86/include/uapi/asm/ldt.h        | 4 ++--
 arch/x86/include/uapi/asm/msr.h        | 4 ++--
 arch/x86/include/uapi/asm/ptrace-abi.h | 6 +++---
 arch/x86/include/uapi/asm/ptrace.h     | 4 ++--
 arch/x86/include/uapi/asm/setup_data.h | 4 ++--
 arch/x86/include/uapi/asm/signal.h     | 8 ++++----
 8 files changed, 19 insertions(+), 19 deletions(-)

diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index 9b82eebd7add5..dafbf581c515d 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -26,7 +26,7 @@
 #define XLF_5LEVEL_ENABLED		(1<<6)
 #define XLF_MEM_ENCRYPTION		(1<<7)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/types.h>
 #include <linux/screen_info.h>
@@ -210,6 +210,6 @@ enum x86_hardware_subarch {
 	X86_NR_SUBARCHS,
 };
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_X86_BOOTPARAM_H */
diff --git a/arch/x86/include/uapi/asm/e820.h b/arch/x86/include/uapi/asm/e820.h
index 2f491efe3a126..55bc668671560 100644
--- a/arch/x86/include/uapi/asm/e820.h
+++ b/arch/x86/include/uapi/asm/e820.h
@@ -54,7 +54,7 @@
  */
 #define E820_RESERVED_KERN        128
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/types.h>
 struct e820entry {
 	__u64 addr;	/* start of memory segment */
@@ -76,7 +76,7 @@ struct e820map {
 #define BIOS_ROM_BASE		0xffe00000
 #define BIOS_ROM_END		0xffffffff
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 
 #endif /* _UAPI_ASM_X86_E820_H */
diff --git a/arch/x86/include/uapi/asm/ldt.h b/arch/x86/include/uapi/asm/ldt.h
index d62ac5db093b4..a82c039d8e6a7 100644
--- a/arch/x86/include/uapi/asm/ldt.h
+++ b/arch/x86/include/uapi/asm/ldt.h
@@ -12,7 +12,7 @@
 /* The size of each LDT entry. */
 #define LDT_ENTRY_SIZE	8
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 /*
  * Note on 64bit base and limit is ignored and you cannot set DS/ES/CS
  * not to the default values if you still want to do syscalls. This
@@ -44,5 +44,5 @@ struct user_desc {
 #define MODIFY_LDT_CONTENTS_STACK	1
 #define MODIFY_LDT_CONTENTS_CODE	2
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 #endif /* _ASM_X86_LDT_H */
diff --git a/arch/x86/include/uapi/asm/msr.h b/arch/x86/include/uapi/asm/msr.h
index e7516b402a00f..4b8917ca28fe7 100644
--- a/arch/x86/include/uapi/asm/msr.h
+++ b/arch/x86/include/uapi/asm/msr.h
@@ -2,7 +2,7 @@
 #ifndef _UAPI_ASM_X86_MSR_H
 #define _UAPI_ASM_X86_MSR_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/types.h>
 #include <linux/ioctl.h>
@@ -10,5 +10,5 @@
 #define X86_IOC_RDMSR_REGS	_IOWR('c', 0xA0, __u32[8])
 #define X86_IOC_WRMSR_REGS	_IOWR('c', 0xA1, __u32[8])
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* _UAPI_ASM_X86_MSR_H */
diff --git a/arch/x86/include/uapi/asm/ptrace-abi.h b/arch/x86/include/uapi/asm/ptrace-abi.h
index 16074b9c93bb5..5823584dea132 100644
--- a/arch/x86/include/uapi/asm/ptrace-abi.h
+++ b/arch/x86/include/uapi/asm/ptrace-abi.h
@@ -25,7 +25,7 @@
 
 #else /* __i386__ */
 
-#if defined(__ASSEMBLY__) || defined(__FRAME_OFFSETS)
+#if defined(__ASSEMBLER__) || defined(__FRAME_OFFSETS)
 /*
  * C ABI says these regs are callee-preserved. They aren't saved on kernel entry
  * unless syscall needs a complete, fully filled "struct pt_regs".
@@ -57,7 +57,7 @@
 #define EFLAGS 144
 #define RSP 152
 #define SS 160
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 /* top of stack page */
 #define FRAME_SIZE 168
@@ -87,7 +87,7 @@
 
 #define PTRACE_SINGLEBLOCK	33	/* resume execution until next branch */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/types.h>
 #endif
 
diff --git a/arch/x86/include/uapi/asm/ptrace.h b/arch/x86/include/uapi/asm/ptrace.h
index 85165c0edafc8..e0b5b4f6226b1 100644
--- a/arch/x86/include/uapi/asm/ptrace.h
+++ b/arch/x86/include/uapi/asm/ptrace.h
@@ -7,7 +7,7 @@
 #include <asm/processor-flags.h>
 
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #ifdef __i386__
 /* this struct defines the way the registers are stored on the
@@ -81,6 +81,6 @@ struct pt_regs {
 
 
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* _UAPI_ASM_X86_PTRACE_H */
diff --git a/arch/x86/include/uapi/asm/setup_data.h b/arch/x86/include/uapi/asm/setup_data.h
index b111b0c185449..50c45ead4e7c9 100644
--- a/arch/x86/include/uapi/asm/setup_data.h
+++ b/arch/x86/include/uapi/asm/setup_data.h
@@ -18,7 +18,7 @@
 #define SETUP_INDIRECT			(1<<31)
 #define SETUP_TYPE_MAX			(SETUP_ENUM_MAX | SETUP_INDIRECT)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/types.h>
 
@@ -78,6 +78,6 @@ struct ima_setup_data {
 	__u64 size;
 } __attribute__((packed));
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _UAPI_ASM_X86_SETUP_DATA_H */
diff --git a/arch/x86/include/uapi/asm/signal.h b/arch/x86/include/uapi/asm/signal.h
index f777346450ec3..1067efabf18b5 100644
--- a/arch/x86/include/uapi/asm/signal.h
+++ b/arch/x86/include/uapi/asm/signal.h
@@ -2,7 +2,7 @@
 #ifndef _UAPI_ASM_X86_SIGNAL_H
 #define _UAPI_ASM_X86_SIGNAL_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/types.h>
 #include <linux/compiler.h>
 
@@ -16,7 +16,7 @@ struct siginfo;
 typedef unsigned long sigset_t;
 
 #endif /* __KERNEL__ */
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 
 #define SIGHUP		 1
@@ -68,7 +68,7 @@ typedef unsigned long sigset_t;
 
 #include <asm-generic/signal-defs.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 
 # ifndef __KERNEL__
@@ -106,6 +106,6 @@ typedef struct sigaltstack {
 	__kernel_size_t ss_size;
 } stack_t;
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _UAPI_ASM_X86_SIGNAL_H */

From 65be5c95d08eedda570a6c888a12384c77fe7614 Mon Sep 17 00:00:00 2001
From: Vladis Dronov <vdronov@redhat.com>
Date: Sun, 9 Mar 2025 18:22:16 +0100
Subject: [PATCH 1139/1173] x86/sgx: Warn explicitly if X86_FEATURE_SGX_LC is
 not enabled

The kernel requires X86_FEATURE_SGX_LC to be able to create SGX enclaves,
not just X86_FEATURE_SGX.

There is quite a number of hardware which has X86_FEATURE_SGX but not
X86_FEATURE_SGX_LC. A kernel running on such hardware does not create
the /dev/sgx_enclave file and does so silently.

Explicitly warn if X86_FEATURE_SGX_LC is not enabled to properly notify
users that the kernel disabled the SGX driver.

The X86_FEATURE_SGX_LC, a.k.a. SGX Launch Control, is a CPU feature
that enables LE (Launch Enclave) hash MSRs to be writable (with
additional opt-in required in the 'feature control' MSR) when running
enclaves, i.e. using a custom root key rather than the Intel proprietary
key for enclave signing.

I've hit this issue myself and have spent some time researching where
my /dev/sgx_enclave file went on SGX-enabled hardware.

Related links:

  https://github.com/intel/linux-sgx/issues/837
  https://patchwork.kernel.org/project/platform-driver-x86/patch/20180827185507.17087-3-jarkko.sakkinen@linux.intel.com/

[ mingo: Made the error message a bit more verbose, and added other cases
         where the kernel fails to create the /dev/sgx_enclave device node. ]

Signed-off-by: Vladis Dronov <vdronov@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Kai Huang <kai.huang@intel.com>
Cc: Jarkko Sakkinen <jarkko@kernel.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Sean Christopherson <sean.j.christopherson@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250309172215.21777-2-vdronov@redhat.com
---
 arch/x86/kernel/cpu/sgx/driver.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/cpu/sgx/driver.c b/arch/x86/kernel/cpu/sgx/driver.c
index 22b65a5f5ec6c..7f8d1e11dbee2 100644
--- a/arch/x86/kernel/cpu/sgx/driver.c
+++ b/arch/x86/kernel/cpu/sgx/driver.c
@@ -150,13 +150,15 @@ int __init sgx_drv_init(void)
 	u64 xfrm_mask;
 	int ret;
 
-	if (!cpu_feature_enabled(X86_FEATURE_SGX_LC))
+	if (!cpu_feature_enabled(X86_FEATURE_SGX_LC)) {
+		pr_info("SGX disabled: SGX launch control CPU feature is not available, /dev/sgx_enclave disabled.\n");
 		return -ENODEV;
+	}
 
 	cpuid_count(SGX_CPUID, 0, &eax, &ebx, &ecx, &edx);
 
 	if (!(eax & 1))  {
-		pr_err("SGX disabled: SGX1 instruction support not available.\n");
+		pr_info("SGX disabled: SGX1 instruction support not available, /dev/sgx_enclave disabled.\n");
 		return -ENODEV;
 	}
 
@@ -173,8 +175,10 @@ int __init sgx_drv_init(void)
 	}
 
 	ret = misc_register(&sgx_dev_enclave);
-	if (ret)
+	if (ret) {
+		pr_info("SGX disabled: Unable to register the /dev/sgx_enclave driver (%d).\n", ret);
 		return ret;
+	}
 
 	return 0;
 }

From f3fa0e40df175acd60b71036b9a1fd62310aec03 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Wed, 5 Feb 2025 11:24:38 +0800
Subject: [PATCH 1140/1173] sched/clock: Don't define sched_clock_irqtime as
 static key
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The sched_clock_irqtime was defined as a static key in:

  8722903cbb8f ("sched: Define sched_clock_irqtime as static key")

However, this change introduces a 'sleeping in atomic context' warning:

	arch/x86/kernel/tsc.c:1214 mark_tsc_unstable()
	warn: sleeping in atomic context

As analyzed by Dan, the affected code path is as follows:

vcpu_load() <- disables preempt
-> kvm_arch_vcpu_load()
   -> mark_tsc_unstable() <- sleeps

virt/kvm/kvm_main.c
   166  void vcpu_load(struct kvm_vcpu *vcpu)
   167  {
   168          int cpu = get_cpu();
                          ^^^^^^^^^^
This get_cpu() disables preemption.

   169
   170          __this_cpu_write(kvm_running_vcpu, vcpu);
   171          preempt_notifier_register(&vcpu->preempt_notifier);
   172          kvm_arch_vcpu_load(vcpu, cpu);
   173          put_cpu();
   174  }

arch/x86/kvm/x86.c
  4979          if (unlikely(vcpu->cpu != cpu) || kvm_check_tsc_unstable()) {
  4980                  s64 tsc_delta = !vcpu->arch.last_host_tsc ? 0 :
  4981                                  rdtsc() - vcpu->arch.last_host_tsc;
  4982                  if (tsc_delta < 0)
  4983                          mark_tsc_unstable("KVM discovered backwards TSC");

arch/x86/kernel/tsc.c
    1206 void mark_tsc_unstable(char *reason)
    1207 {
    1208         if (tsc_unstable)
    1209                 return;
    1210
    1211         tsc_unstable = 1;
    1212         if (using_native_sched_clock())
    1213                 clear_sched_clock_stable();
--> 1214         disable_sched_clock_irqtime();
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
kernel/jump_label.c
   245  void static_key_disable(struct static_key *key)
   246  {
   247          cpus_read_lock();
                ^^^^^^^^^^^^^^^^
This lock has a might_sleep() in it which triggers the static checker
warning.

   248          static_key_disable_cpuslocked(key);
   249          cpus_read_unlock();
   250  }

Let revert this change for now as {disable,enable}_sched_clock_irqtime
are used in many places, as pointed out by Sean, including the following:

The code path in clocksource_watchdog():

  clocksource_watchdog()
  |
  -> spin_lock(&watchdog_lock);
     |
     -> __clocksource_unstable()
        |
        -> clocksource.mark_unstable() == tsc_cs_mark_unstable()
           |
           -> disable_sched_clock_irqtime()

And the code path in sched_clock_register():

	/* Cannot register a sched_clock with interrupts on */
	local_irq_save(flags);

	...

	/* Enable IRQ time accounting if we have a fast enough sched_clock() */
	if (irqtime > 0 || (irqtime == -1 && rate >= 1000000))
		enable_sched_clock_irqtime();

	local_irq_restore(flags);

[ lkp@intel.com: reported a build error in the prev version ]
[ mingo: cherry-picked it over into sched/urgent ]

Closes: https://lore.kernel.org/kvm/37a79ba3-9ce0-479c-a5b0-2bd75d573ed3@stanley.mountain/
Fixes: 8722903cbb8f ("sched: Define sched_clock_irqtime as static key")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Debugged-by: Dan Carpenter <dan.carpenter@linaro.org>
Debugged-by: Sean Christopherson <seanjc@google.com>
Debugged-by: Michal Koutný <mkoutny@suse.com>
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20250205032438.14668-1-laoar.shao@gmail.com
---
 kernel/sched/cputime.c | 8 ++++----
 kernel/sched/sched.h   | 4 ++--
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 5d9143dd08791..6dab4854c6c08 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -9,8 +9,6 @@
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
 
-DEFINE_STATIC_KEY_FALSE(sched_clock_irqtime);
-
 /*
  * There are no locks covering percpu hardirq/softirq time.
  * They are only modified in vtime_account, on corresponding CPU
@@ -24,14 +22,16 @@ DEFINE_STATIC_KEY_FALSE(sched_clock_irqtime);
  */
 DEFINE_PER_CPU(struct irqtime, cpu_irqtime);
 
+int sched_clock_irqtime;
+
 void enable_sched_clock_irqtime(void)
 {
-	static_branch_enable(&sched_clock_irqtime);
+	sched_clock_irqtime = 1;
 }
 
 void disable_sched_clock_irqtime(void)
 {
-	static_branch_disable(&sched_clock_irqtime);
+	sched_clock_irqtime = 0;
 }
 
 static void irqtime_account_delta(struct irqtime *irqtime, u64 delta,
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c8512a9fb0229..023b844159c94 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -3259,11 +3259,11 @@ struct irqtime {
 };
 
 DECLARE_PER_CPU(struct irqtime, cpu_irqtime);
-DECLARE_STATIC_KEY_FALSE(sched_clock_irqtime);
+extern int sched_clock_irqtime;
 
 static inline int irqtime_enabled(void)
 {
-	return static_branch_likely(&sched_clock_irqtime);
+	return sched_clock_irqtime;
 }
 
 /*

From e3e89178a9f4a80092578af3ff3c8478f9187d59 Mon Sep 17 00:00:00 2001
From: Florent Revest <revest@chromium.org>
Date: Mon, 10 Mar 2025 15:42:43 +0100
Subject: [PATCH 1141/1173] x86/microcode/AMD: Fix out-of-bounds on systems
 with CPU-less NUMA nodes

Currently, load_microcode_amd() iterates over all NUMA nodes, retrieves their
CPU masks and unconditionally accesses per-CPU data for the first CPU of each
mask.

According to Documentation/admin-guide/mm/numaperf.rst:

  "Some memory may share the same node as a CPU, and others are provided as
  memory only nodes."

Therefore, some node CPU masks may be empty and wouldn't have a "first CPU".

On a machine with far memory (and therefore CPU-less NUMA nodes):
- cpumask_of_node(nid) is 0
- cpumask_first(0) is CONFIG_NR_CPUS
- cpu_data(CONFIG_NR_CPUS) accesses the cpu_info per-CPU array at an
  index that is 1 out of bounds

This does not have any security implications since flashing microcode is
a privileged operation but I believe this has reliability implications by
potentially corrupting memory while flashing a microcode update.

When booting with CONFIG_UBSAN_BOUNDS=y on an AMD machine that flashes
a microcode update. I get the following splat:

  UBSAN: array-index-out-of-bounds in arch/x86/kernel/cpu/microcode/amd.c:X:Y
  index 512 is out of range for type 'unsigned long[512]'
  [...]
  Call Trace:
   dump_stack
   __ubsan_handle_out_of_bounds
   load_microcode_amd
   request_microcode_amd
   reload_store
   kernfs_fop_write_iter
   vfs_write
   ksys_write
   do_syscall_64
   entry_SYSCALL_64_after_hwframe

Change the loop to go over only NUMA nodes which have CPUs before determining
whether the first CPU on the respective node needs microcode update.

  [ bp: Massage commit message, fix typo. ]

Fixes: 7ff6edf4fef3 ("x86/microcode/AMD: Fix mixed steppings support")
Signed-off-by: Florent Revest <revest@chromium.org>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250310144243.861978-1-revest@chromium.org
---
 arch/x86/kernel/cpu/microcode/amd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index c69b1bc454834..138689b8e1d83 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -1074,7 +1074,7 @@ static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t siz
 	if (ret != UCODE_OK)
 		return ret;
 
-	for_each_node(nid) {
+	for_each_node_with_cpus(nid) {
 		cpu = cpumask_first(cpumask_of_node(nid));
 		c = &cpu_data(cpu);
 

From 366fef794bd2b7c2e9df933f6828dd9739bfba84 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Mon, 10 Mar 2025 14:21:58 +0200
Subject: [PATCH 1142/1173] <linux/cleanup.h>: Allow the passing of both iomem
 and non-iomem pointers to no_free_ptr()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Calling no_free_ptr() for an __iomem pointer results in Sparse
complaining about the types:

  warning: incorrect type in argument 1 (different address spaces)
     expected void const volatile *val
     got void [noderef] __iomem *__val

[ The example is from drivers/platform/x86/intel/pmc/core_ssram.c:283 ]

The problem is caused by the signature of __must_check_fn() added in:

  85be6d842447 ("cleanup: Make no_free_ptr() __must_check")

... to enforce that the return value is always used.

Use __force to allow both iomem and non-iomem pointers to be given for
no_free_ptr().

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250310122158.20966-1-ilpo.jarvinen@linux.intel.com
Closes: https://lore.kernel.org/oe-kbuild-all/202403050547.qnZtuNlN-lkp@intel.com/
---
 include/linux/cleanup.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h
index ec00e3f7af2b3..ee2614adb7858 100644
--- a/include/linux/cleanup.h
+++ b/include/linux/cleanup.h
@@ -212,7 +212,7 @@ const volatile void * __must_check_fn(const volatile void *val)
 { return val; }
 
 #define no_free_ptr(p) \
-	((typeof(p)) __must_check_fn(__get_and_null(p, NULL)))
+	((typeof(p)) __must_check_fn((__force const volatile void *)__get_and_null(p, NULL)))
 
 #define return_ptr(p)	return no_free_ptr(p)
 

From ec73859d76db768da97ee799a91eb9c7d28974fe Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 10 Mar 2025 14:10:59 +0100
Subject: [PATCH 1143/1173] x86/coco: Replace 'static const cc_mask' with the
 newly introduced cc_get_mask() function

When extra warnings are enabled, the cc_mask definition in <asm/coco.h>
causes a build failure with GCC:

  arch/x86/include/asm/coco.h:28:18: error: 'cc_mask' defined but not used [-Werror=unused-const-variable=]
     28 | static const u64 cc_mask = 0;

Add a cc_get_mask() function mirroring cc_set_mask() for the one
user of the variable outside of the CoCo implementation.

Fixes: a0a8d15a798b ("x86/tdx: Preserve shared bit on mprotect()")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250310131114.2635497-1-arnd@kernel.org

--
v2: use an inline helper instead of a __maybe_unused annotaiton.
---
 arch/x86/include/asm/coco.h          | 10 +++++++++-
 arch/x86/include/asm/pgtable_types.h |  2 +-
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/coco.h b/arch/x86/include/asm/coco.h
index aa6c8f8ca9588..e7225452963f0 100644
--- a/arch/x86/include/asm/coco.h
+++ b/arch/x86/include/asm/coco.h
@@ -15,6 +15,11 @@ enum cc_vendor {
 extern enum cc_vendor cc_vendor;
 extern u64 cc_mask;
 
+static inline u64 cc_get_mask(void)
+{
+	return cc_mask;
+}
+
 static inline void cc_set_mask(u64 mask)
 {
 	RIP_REL_REF(cc_mask) = mask;
@@ -25,7 +30,10 @@ u64 cc_mkdec(u64 val);
 void cc_random_init(void);
 #else
 #define cc_vendor (CC_VENDOR_NONE)
-static const u64 cc_mask = 0;
+static inline u64 cc_get_mask(void)
+{
+	return 0;
+}
 
 static inline u64 cc_mkenc(u64 val)
 {
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 4b804531b03c3..9c4d9fafe0105 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -177,7 +177,7 @@ enum page_cache_mode {
 };
 #endif
 
-#define _PAGE_CC		(_AT(pteval_t, cc_mask))
+#define _PAGE_CC		(_AT(pteval_t, cc_get_mask()))
 #define _PAGE_ENC		(_AT(pteval_t, sme_me_mask))
 
 #define _PAGE_CACHE_MASK	(_PAGE_PWT | _PAGE_PCD | _PAGE_PAT)

From 376daf20eda4898a49a4746f225153efb4c094e7 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Wed, 16 Oct 2024 14:14:56 +0300
Subject: [PATCH 1144/1173] x86/acpi: Replace manual page table initialization
 with kernel_ident_mapping_init()

The init_transition_pgtable() functions maps the page with
asm_acpi_mp_play_dead() into an identity mapping.

Replace open-coded manual page table initialization with
kernel_ident_mapping_init() to avoid code duplication.

Use x86_mapping_info::offset to get the page mapped at the
correct location.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Kai Huang <kai.huang@intel.com>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20241016111458.846228-3-kirill.shutemov@linux.intel.com
---
 arch/x86/kernel/acpi/madt_wakeup.c | 73 ++++++------------------------
 1 file changed, 15 insertions(+), 58 deletions(-)

diff --git a/arch/x86/kernel/acpi/madt_wakeup.c b/arch/x86/kernel/acpi/madt_wakeup.c
index d5ef6215583bc..f36f28405dcc6 100644
--- a/arch/x86/kernel/acpi/madt_wakeup.c
+++ b/arch/x86/kernel/acpi/madt_wakeup.c
@@ -70,58 +70,6 @@ static void __init free_pgt_page(void *pgt, void *dummy)
 	return memblock_free(pgt, PAGE_SIZE);
 }
 
-/*
- * Make sure asm_acpi_mp_play_dead() is present in the identity mapping at
- * the same place as in the kernel page tables. asm_acpi_mp_play_dead() switches
- * to the identity mapping and the function has be present at the same spot in
- * the virtual address space before and after switching page tables.
- */
-static int __init init_transition_pgtable(pgd_t *pgd)
-{
-	pgprot_t prot = PAGE_KERNEL_EXEC_NOENC;
-	unsigned long vaddr, paddr;
-	p4d_t *p4d;
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte;
-
-	vaddr = (unsigned long)asm_acpi_mp_play_dead;
-	pgd += pgd_index(vaddr);
-	if (!pgd_present(*pgd)) {
-		p4d = (p4d_t *)alloc_pgt_page(NULL);
-		if (!p4d)
-			return -ENOMEM;
-		set_pgd(pgd, __pgd(__pa(p4d) | _KERNPG_TABLE));
-	}
-	p4d = p4d_offset(pgd, vaddr);
-	if (!p4d_present(*p4d)) {
-		pud = (pud_t *)alloc_pgt_page(NULL);
-		if (!pud)
-			return -ENOMEM;
-		set_p4d(p4d, __p4d(__pa(pud) | _KERNPG_TABLE));
-	}
-	pud = pud_offset(p4d, vaddr);
-	if (!pud_present(*pud)) {
-		pmd = (pmd_t *)alloc_pgt_page(NULL);
-		if (!pmd)
-			return -ENOMEM;
-		set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
-	}
-	pmd = pmd_offset(pud, vaddr);
-	if (!pmd_present(*pmd)) {
-		pte = (pte_t *)alloc_pgt_page(NULL);
-		if (!pte)
-			return -ENOMEM;
-		set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE));
-	}
-	pte = pte_offset_kernel(pmd, vaddr);
-
-	paddr = __pa(vaddr);
-	set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, prot));
-
-	return 0;
-}
-
 static int __init acpi_mp_setup_reset(u64 reset_vector)
 {
 	struct x86_mapping_info info = {
@@ -130,6 +78,7 @@ static int __init acpi_mp_setup_reset(u64 reset_vector)
 		.page_flag      = __PAGE_KERNEL_LARGE_EXEC,
 		.kernpg_flag    = _KERNPG_TABLE_NOENC,
 	};
+	unsigned long mstart, mend;
 	pgd_t *pgd;
 
 	pgd = alloc_pgt_page(NULL);
@@ -137,8 +86,6 @@ static int __init acpi_mp_setup_reset(u64 reset_vector)
 		return -ENOMEM;
 
 	for (int i = 0; i < nr_pfn_mapped; i++) {
-		unsigned long mstart, mend;
-
 		mstart = pfn_mapped[i].start << PAGE_SHIFT;
 		mend   = pfn_mapped[i].end << PAGE_SHIFT;
 		if (kernel_ident_mapping_init(&info, pgd, mstart, mend)) {
@@ -147,14 +94,24 @@ static int __init acpi_mp_setup_reset(u64 reset_vector)
 		}
 	}
 
-	if (kernel_ident_mapping_init(&info, pgd,
-				      PAGE_ALIGN_DOWN(reset_vector),
-				      PAGE_ALIGN(reset_vector + 1))) {
+	mstart = PAGE_ALIGN_DOWN(reset_vector);
+	mend = mstart + PAGE_SIZE;
+	if (kernel_ident_mapping_init(&info, pgd, mstart, mend)) {
 		kernel_ident_mapping_free(&info, pgd);
 		return -ENOMEM;
 	}
 
-	if (init_transition_pgtable(pgd)) {
+	/*
+	 * Make sure asm_acpi_mp_play_dead() is present in the identity mapping
+	 * at the same place as in the kernel page tables.
+	 * asm_acpi_mp_play_dead() switches to the identity mapping and the
+	 * function must be present at the same spot in the virtual address space
+	 * before and after switching page tables.
+	 */
+	info.offset = __START_KERNEL_map - phys_base;
+	mstart = PAGE_ALIGN_DOWN(__pa(asm_acpi_mp_play_dead));
+	mend = mstart + PAGE_SIZE;
+	if (kernel_ident_mapping_init(&info, pgd, mstart, mend)) {
 		kernel_ident_mapping_free(&info, pgd);
 		return -ENOMEM;
 	}

From 4f10ec03fe1ed12479134be33ddf006382744651 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Wed, 16 Oct 2024 14:14:55 +0300
Subject: [PATCH 1145/1173] x86/mm/ident_map: Fix theoretical virtual address
 overflow to zero

The current calculation of the 'next' virtual address in the
page table initialization functions in arch/x86/mm/ident_map.c
doesn't protect against wrapping to zero.

This is a theoretical issue that cannot happen currently,
the problematic case is possible only if the user sets a
high enough x86_mapping_info::offset value - which no
current code in the upstream kernel does.

( The wrapping to zero only occurs if the top PGD entry is accessed.
  There are no such users upstream. Only hibernate_64.c uses
  x86_mapping_info::offset, and it operates on the direct mapping
  range, which is not the top PGD entry. )

Should such an overflow happen, it can result in page table
corruption and a hang.

To future-proof this code, replace the manual 'next' calculation
with p?d_addr_end() which handles wrapping correctly.

[ Backporter's note: there's no need to backport this patch. ]

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Kai Huang <kai.huang@intel.com>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20241016111458.846228-2-kirill.shutemov@linux.intel.com
---
 arch/x86/mm/ident_map.c | 14 +++-----------
 1 file changed, 3 insertions(+), 11 deletions(-)

diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index 5ab7bd2f1983c..bd5d101c5c379 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -101,9 +101,7 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
 		pmd_t *pmd;
 		bool use_gbpage;
 
-		next = (addr & PUD_MASK) + PUD_SIZE;
-		if (next > end)
-			next = end;
+		next = pud_addr_end(addr, end);
 
 		/* if this is already a gbpage, this portion is already mapped */
 		if (pud_leaf(*pud))
@@ -154,10 +152,7 @@ static int ident_p4d_init(struct x86_mapping_info *info, p4d_t *p4d_page,
 		p4d_t *p4d = p4d_page + p4d_index(addr);
 		pud_t *pud;
 
-		next = (addr & P4D_MASK) + P4D_SIZE;
-		if (next > end)
-			next = end;
-
+		next = p4d_addr_end(addr, end);
 		if (p4d_present(*p4d)) {
 			pud = pud_offset(p4d, 0);
 			result = ident_pud_init(info, pud, addr, next);
@@ -199,10 +194,7 @@ int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
 		pgd_t *pgd = pgd_page + pgd_index(addr);
 		p4d_t *p4d;
 
-		next = (addr & PGDIR_MASK) + PGDIR_SIZE;
-		if (next > end)
-			next = end;
-
+		next = pgd_addr_end(addr, end);
 		if (pgd_present(*pgd)) {
 			p4d = p4d_offset(pgd, 0);
 			result = ident_p4d_init(info, p4d, addr, next);

From fd3f5d385a52531589c8a7a26d9e108aa1d3f52e Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Mon, 10 Mar 2025 20:23:35 +0100
Subject: [PATCH 1146/1173] perf/core: Remove optional 'size' arguments from
 strscpy() calls

The 'size' parameter is optional and strscpy() automatically determines
the length of the destination buffer using sizeof() if the argument is
omitted. This makes the explicit sizeof() calls unnecessary.

Furthermore, KSYM_NAME_LEN is equal to sizeof(name) and can also be
removed. Remove them to shorten and simplify the code.

Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250310192336.442994-1-thorsten.blum@linux.dev
---
 kernel/events/core.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index f159dbab45300..e7d0b055f96c7 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8665,7 +8665,7 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event)
 	unsigned int size;
 
 	memset(comm, 0, sizeof(comm));
-	strscpy(comm, comm_event->task->comm, sizeof(comm));
+	strscpy(comm, comm_event->task->comm);
 	size = ALIGN(strlen(comm)+1, sizeof(u64));
 
 	comm_event->comm = comm;
@@ -9109,7 +9109,7 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
 	}
 
 cpy_name:
-	strscpy(tmp, name, sizeof(tmp));
+	strscpy(tmp, name);
 	name = tmp;
 got_name:
 	/*
@@ -9533,7 +9533,7 @@ void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister,
 	    ksym_type == PERF_RECORD_KSYMBOL_TYPE_UNKNOWN)
 		goto err;
 
-	strscpy(name, sym, KSYM_NAME_LEN);
+	strscpy(name, sym);
 	name_len = strlen(name) + 1;
 	while (!IS_ALIGNED(name_len, sizeof(u64)))
 		name[name_len++] = '\0';

From c080f2b8a2e44077aed15f1b4f0fbc0f4a912a66 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Thu, 6 Mar 2025 15:07:20 +0100
Subject: [PATCH 1147/1173] x86/vdso: Always reject undefined references during
 linking
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Instead of using a custom script to detect and fail on undefined
references, use --no-undefined for all VDSO linker invocations.

Drop the now unused checkundef.sh script.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250306-vdso-checkundef-v2-1-a26cc315fd73@linutronix.de
---
 arch/x86/entry/vdso/Makefile      |  7 +++----
 arch/x86/entry/vdso/checkundef.sh | 10 ----------
 2 files changed, 3 insertions(+), 14 deletions(-)
 delete mode 100755 arch/x86/entry/vdso/checkundef.sh

diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index 1c0072336e661..a6430c5636b8d 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -32,7 +32,7 @@ targets += $(foreach x, 64 x32 32, vdso-image-$(x).c vdso$(x).so vdso$(x).so.dbg
 
 CPPFLAGS_vdso.lds += -P -C
 
-VDSO_LDFLAGS_vdso.lds = -m elf_x86_64 -soname linux-vdso.so.1 --no-undefined \
+VDSO_LDFLAGS_vdso.lds = -m elf_x86_64 -soname linux-vdso.so.1 \
 			-z max-page-size=4096
 
 $(obj)/vdso64.so.dbg: $(obj)/vdso.lds $(vobjs) FORCE
@@ -151,10 +151,9 @@ $(obj)/vdso32.so.dbg: $(obj)/vdso32/vdso32.lds $(vobjs32) FORCE
 quiet_cmd_vdso = VDSO    $@
       cmd_vdso = $(LD) -o $@ \
 		       $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \
-		       -T $(filter %.lds,$^) $(filter %.o,$^) && \
-		 sh $(src)/checkundef.sh '$(NM)' '$@'
+		       -T $(filter %.lds,$^) $(filter %.o,$^)
 
-VDSO_LDFLAGS = -shared --hash-style=both --build-id=sha1 \
+VDSO_LDFLAGS = -shared --hash-style=both --build-id=sha1 --no-undefined \
 	$(call ld-option, --eh-frame-hdr) -Bsymbolic -z noexecstack
 
 quiet_cmd_vdso_and_check = VDSO    $@
diff --git a/arch/x86/entry/vdso/checkundef.sh b/arch/x86/entry/vdso/checkundef.sh
deleted file mode 100755
index 7ee90a9b549da..0000000000000
--- a/arch/x86/entry/vdso/checkundef.sh
+++ /dev/null
@@ -1,10 +0,0 @@
-#!/bin/sh
-nm="$1"
-file="$2"
-$nm "$file" | grep '^ *U' > /dev/null 2>&1
-if [ $? -eq 1 ]; then
-    exit 0
-else
-    echo "$file: undefined symbols found" >&2
-    exit 1
-fi

From 652262975db421767ada3f05b926854bbb357759 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Thu, 6 Mar 2025 15:07:21 +0100
Subject: [PATCH 1148/1173] sparc/vdso: Always reject undefined references
 during linking
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Instead of using a custom script to detect and fail on undefined
references, use --no-undefined for all VDSO linker invocations.

Drop the now unused checkundef.sh script.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: David S. Miller <davem@davemloft.net>
Cc: Andreas Larsson <andreas@gaisler.com>
Link: https://lore.kernel.org/r/20250306-vdso-checkundef-v2-2-a26cc315fd73@linutronix.de
---
 arch/sparc/vdso/Makefile      |  7 +++----
 arch/sparc/vdso/checkundef.sh | 10 ----------
 2 files changed, 3 insertions(+), 14 deletions(-)
 delete mode 100644 arch/sparc/vdso/checkundef.sh

diff --git a/arch/sparc/vdso/Makefile b/arch/sparc/vdso/Makefile
index 50ec2978cda53..fdc4a8f5a49c5 100644
--- a/arch/sparc/vdso/Makefile
+++ b/arch/sparc/vdso/Makefile
@@ -22,7 +22,7 @@ targets += $(foreach x, 32 64, vdso-image-$(x).c vdso$(x).so vdso$(x).so.dbg)
 
 CPPFLAGS_vdso.lds += -P -C
 
-VDSO_LDFLAGS_vdso.lds = -m elf64_sparc -soname linux-vdso.so.1 --no-undefined \
+VDSO_LDFLAGS_vdso.lds = -m elf64_sparc -soname linux-vdso.so.1 \
 			-z max-page-size=8192
 
 $(obj)/vdso64.so.dbg: $(obj)/vdso.lds $(vobjs) FORCE
@@ -101,7 +101,6 @@ $(obj)/vdso32.so.dbg: FORCE \
 quiet_cmd_vdso = VDSO    $@
       cmd_vdso = $(LD) -nostdlib -o $@ \
 		       $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \
-		       -T $(filter %.lds,$^) $(filter %.o,$^) && \
-		sh $(src)/checkundef.sh '$(OBJDUMP)' '$@'
+		       -T $(filter %.lds,$^) $(filter %.o,$^)
 
-VDSO_LDFLAGS = -shared --hash-style=both --build-id=sha1 -Bsymbolic
+VDSO_LDFLAGS = -shared --hash-style=both --build-id=sha1 -Bsymbolic --no-undefined
diff --git a/arch/sparc/vdso/checkundef.sh b/arch/sparc/vdso/checkundef.sh
deleted file mode 100644
index 2d85876ffc325..0000000000000
--- a/arch/sparc/vdso/checkundef.sh
+++ /dev/null
@@ -1,10 +0,0 @@
-#!/bin/sh
-objdump="$1"
-file="$2"
-$objdump -t "$file" | grep '*UUND*' | grep -v '#scratch' > /dev/null 2>&1
-if [ $? -eq 1 ]; then
-    exit 0
-else
-    echo "$file: undefined symbols found" >&2
-    exit 1
-fi

From 474f6ed560684855148c51181721dca600e04e66 Mon Sep 17 00:00:00 2001
From: Kernel Patches Daemon <kernel-patches-bot@fb.com>
Date: Tue, 11 Mar 2025 04:33:45 -0700
Subject: [PATCH 1149/1173] adding ci files

---
 .../veristat_baseline_compare/action.yml      |  49 +
 .github/scripts/compare-veristat-results.sh   |  18 +
 .github/scripts/download-gcc-bpf.sh           |  30 +
 .github/scripts/matrix.py                     | 194 ++++
 .../scripts/tests/test_veristat_compare.py    |  75 ++
 .github/scripts/tmpfsify-workspace.sh         |  21 +
 .github/scripts/veristat_compare.py           | 263 +++++
 .github/workflows/gcc-bpf.yml                 | 100 ++
 .github/workflows/kernel-build-test.yml       | 147 +++
 .github/workflows/kernel-build.yml            | 191 ++++
 .github/workflows/kernel-test.yml             |  88 ++
 .github/workflows/lint.yml                    |  65 ++
 .github/workflows/test.yml                    |  62 ++
 .github/workflows/veristat-kernel.yml         |  65 ++
 .github/workflows/veristat-meta.yml           |  87 ++
 README                                        |  18 -
 ci/diffs/.keep                                |   0
 ...-unnecessary-audit-log-for-CPU-secur.patch |  33 +
 ...e-SPECULATION_MITIGATIONS-to-arch-Kc.patch |  69 ++
 ...lftest-failures-due-to-llvm18-change.patch |  94 ++
 ...er-bug-due-to-incorrect-branch-offse.patch |  67 ++
 ...-bpf-Fix-a-btf_dump-selftest-failure.patch |  40 +
 ...sockopt_lock_sock-in-ip_sock_set_tos.patch |  99 ++
 ...lter-out-_GNU_SOURCE-when-compiling-.patch |  51 +
 ...x-bpf_cookie-and-find_vma-in-nested-.patch |  50 +
 ...x-pyperf180-compilation-failure-with.patch |  78 ++
 ...sable-detection-of-llvm-when-buildin.patch |  41 +
 ...x-inet_csk_accept-prototype-in-test_.patch |  32 +
 ...f-work-around-latest-Clang-smartness.patch |  31 +
 ...kxceiver-ksft_print_msg-fix-format-t.patch |  89 ++
 ...s-compilation-to-non-host-endianness.patch | 142 +++
 ...Fix-symbol-counting-logic-by-looking.patch |  65 ++
 ...s-compilation-to-non-host-endianness.patch | 117 +++
 ci/diffs/0099-s390x_nolockdep.diff            |  48 +
 ci/diffs/0099-selftest-cross-compile.diff     |  13 +
 ...ancing-slot-in-iter_folioq_get_pages.patch |  46 +
 ...lftests-bpf-Fix-uprobe-consumer-test.patch |  58 ++
 ...ext-fix-build-after-renames-in-sched.patch | 231 +++++
 ...-samples-bpf-fix-samples-compilation.patch |  61 ++
 ...to-remove-ftrace_test_recursion_tryl.patch |  46 +
 ...g-Define-ftrace_get_symaddr-for-s390.patch |  28 +
 ...dd-fno-strict-aliasing-to-BPF_CFLAGS.patch |  75 ++
 ...d-std-gnu11-to-BPF_CFLAGS-and-CFLAGS.patch |  63 ++
 ...g-NETFS_RREQ_ALL_QUEUED-to-be-after-.patch | 100 ++
 ...nvalid-irq-restore-in-scx_ops_bypass.patch |  56 ++
 ...99-scx-Fix-maximal-BPF-selftest-prog.patch |  56 ++
 ci/vmtest/configs/DENYLIST                    |  15 +
 ci/vmtest/configs/DENYLIST.aarch64            |   4 +
 ci/vmtest/configs/DENYLIST.rc                 |   3 +
 ci/vmtest/configs/DENYLIST.s390x              |  11 +
 ci/vmtest/configs/DENYLIST.test_progs-bpf_gcc | 904 ++++++++++++++++++
 ci/vmtest/configs/DENYLIST.x86_64             |   1 +
 ci/vmtest/configs/run-vmtest.env              |  42 +
 ci/vmtest/configs/run_veristat.kernel.cfg     |   4 +
 ci/vmtest/configs/run_veristat.meta.cfg       |   4 +
 ci/vmtest/configs/veristat_meta.cfg           |  10 +
 56 files changed, 4432 insertions(+), 18 deletions(-)
 create mode 100644 .github/actions/veristat_baseline_compare/action.yml
 create mode 100755 .github/scripts/compare-veristat-results.sh
 create mode 100755 .github/scripts/download-gcc-bpf.sh
 create mode 100644 .github/scripts/matrix.py
 create mode 100644 .github/scripts/tests/test_veristat_compare.py
 create mode 100755 .github/scripts/tmpfsify-workspace.sh
 create mode 100644 .github/scripts/veristat_compare.py
 create mode 100644 .github/workflows/gcc-bpf.yml
 create mode 100644 .github/workflows/kernel-build-test.yml
 create mode 100644 .github/workflows/kernel-build.yml
 create mode 100644 .github/workflows/kernel-test.yml
 create mode 100644 .github/workflows/lint.yml
 create mode 100644 .github/workflows/test.yml
 create mode 100644 .github/workflows/veristat-kernel.yml
 create mode 100644 .github/workflows/veristat-meta.yml
 create mode 100644 ci/diffs/.keep
 create mode 100644 ci/diffs/0001-Revert-bpf-Avoid-unnecessary-audit-log-for-CPU-secur.patch
 create mode 100644 ci/diffs/0001-arch-Kconfig-Move-SPECULATION_MITIGATIONS-to-arch-Kc.patch
 create mode 100644 ci/diffs/0001-bpf-Fix-a-few-selftest-failures-due-to-llvm18-change.patch
 create mode 100644 ci/diffs/0001-bpf-Fix-a-verifier-bug-due-to-incorrect-branch-offse.patch
 create mode 100644 ci/diffs/0001-bpf-next-selftests-bpf-Fix-a-btf_dump-selftest-failure.patch
 create mode 100644 ci/diffs/0001-net-bpf-Use-sockopt_lock_sock-in-ip_sock_set_tos.patch
 create mode 100644 ci/diffs/0001-selftests-bpf-Filter-out-_GNU_SOURCE-when-compiling-.patch
 create mode 100644 ci/diffs/0001-selftests-bpf-Fix-bpf_cookie-and-find_vma-in-nested-.patch
 create mode 100644 ci/diffs/0001-selftests-bpf-Fix-pyperf180-compilation-failure-with.patch
 create mode 100644 ci/diffs/0001-selftests-bpf-disable-detection-of-llvm-when-buildin.patch
 create mode 100644 ci/diffs/0001-selftests-bpf-fix-inet_csk_accept-prototype-in-test_.patch
 create mode 100644 ci/diffs/0001-selftests-bpf-work-around-latest-Clang-smartness.patch
 create mode 100644 ci/diffs/0001-selftests-bpf-xskxceiver-ksft_print_msg-fix-format-t.patch
 create mode 100644 ci/diffs/0001-tools-resolve_btfids-fix-cross-compilation-to-non-host-endianness.patch
 create mode 100644 ci/diffs/0001-tracing-kprobes-Fix-symbol-counting-logic-by-looking.patch
 create mode 100644 ci/diffs/0002-tools-resolve_btfids-fix-cross-compilation-to-non-host-endianness.patch
 create mode 100644 ci/diffs/0099-s390x_nolockdep.diff
 create mode 100644 ci/diffs/0099-selftest-cross-compile.diff
 create mode 100644 ci/diffs/0199-iov_iter-fix-advancing-slot-in-iter_folioq_get_pages.patch
 create mode 100644 ci/diffs/0299-selftests-bpf-Fix-uprobe-consumer-test.patch
 create mode 100644 ci/diffs/0399-selftests-sched_ext-fix-build-after-renames-in-sched.patch
 create mode 100644 ci/diffs/0499-samples-bpf-fix-samples-compilation.patch
 create mode 100644 ci/diffs/2000-s390-fgraph-Fix-to-remove-ftrace_test_recursion_tryl.patch
 create mode 100644 ci/diffs/2001-s390-tracing-Define-ftrace_get_symaddr-for-s390.patch
 create mode 100644 ci/diffs/2001-selftests-bpf-add-fno-strict-aliasing-to-BPF_CFLAGS.patch
 create mode 100644 ci/diffs/2002-selftests-bpf-add-std-gnu11-to-BPF_CFLAGS-and-CFLAGS.patch
 create mode 100644 ci/diffs/8888-netfs-Fix-setting-NETFS_RREQ_ALL_QUEUED-to-be-after-.patch
 create mode 100644 ci/diffs/9998-sched_ext-Fix-invalid-irq-restore-in-scx_ops_bypass.patch
 create mode 100644 ci/diffs/9999-scx-Fix-maximal-BPF-selftest-prog.patch
 create mode 100644 ci/vmtest/configs/DENYLIST
 create mode 100644 ci/vmtest/configs/DENYLIST.aarch64
 create mode 100644 ci/vmtest/configs/DENYLIST.rc
 create mode 100644 ci/vmtest/configs/DENYLIST.s390x
 create mode 100644 ci/vmtest/configs/DENYLIST.test_progs-bpf_gcc
 create mode 100644 ci/vmtest/configs/DENYLIST.x86_64
 create mode 100644 ci/vmtest/configs/run-vmtest.env
 create mode 100644 ci/vmtest/configs/run_veristat.kernel.cfg
 create mode 100644 ci/vmtest/configs/run_veristat.meta.cfg
 create mode 100644 ci/vmtest/configs/veristat_meta.cfg

diff --git a/.github/actions/veristat_baseline_compare/action.yml b/.github/actions/veristat_baseline_compare/action.yml
new file mode 100644
index 0000000000000..9e25a2b0bf1ca
--- /dev/null
+++ b/.github/actions/veristat_baseline_compare/action.yml
@@ -0,0 +1,49 @@
+name: 'run-veristat'
+description: 'Run veristat benchmark'
+inputs:
+  veristat_output:
+    description: 'Veristat output filepath'
+    required: true
+  baseline_name:
+    description: 'Veristat baseline cache name'
+    required: true
+runs:
+  using: "composite"
+  steps:
+    - uses: actions/upload-artifact@v4
+      with:
+        name: ${{ inputs.baseline_name }}
+        if-no-files-found: error
+        path: ${{ github.workspace }}/${{ inputs.veristat_output }}
+
+    # For pull request:
+    # - get baseline log from cache
+    # - compare it to current run
+    - if: ${{ github.event_name == 'pull_request' }}
+      uses: actions/cache/restore@v4
+      with:
+        key: ${{ inputs.baseline_name }}
+        restore-keys: |
+          ${{ inputs.baseline_name }}-
+        path: '${{ github.workspace }}/${{ inputs.baseline_name }}'
+
+    - if: ${{ github.event_name == 'pull_request' }}
+      name: Show veristat comparison
+      shell: bash
+      run: ./.github/scripts/compare-veristat-results.sh
+      env:
+        BASELINE_PATH: ${{ github.workspace }}/${{ inputs.baseline_name }}
+        VERISTAT_OUTPUT: ${{ inputs.veristat_output }}
+
+    # For push: just put baseline log to cache
+    - if: ${{ github.event_name == 'push' }}
+      shell: bash
+      run: |
+        mv "${{ github.workspace }}/${{ inputs.veristat_output }}" \
+           "${{ github.workspace }}/${{ inputs.baseline_name }}"
+
+    - if: ${{ github.event_name == 'push' }}
+      uses: actions/cache/save@v4
+      with:
+        key: ${{ inputs.baseline_name }}-${{ github.run_id }}
+        path: '${{ github.workspace }}/${{ inputs.baseline_name }}'
diff --git a/.github/scripts/compare-veristat-results.sh b/.github/scripts/compare-veristat-results.sh
new file mode 100755
index 0000000000000..f95c3c192d80d
--- /dev/null
+++ b/.github/scripts/compare-veristat-results.sh
@@ -0,0 +1,18 @@
+#!/bin/bash
+
+if [[ ! -f "${BASELINE_PATH}" ]]; then
+    echo "# No ${BASELINE_PATH} available" >> "${GITHUB_STEP_SUMMARY}"
+
+    echo "No ${BASELINE_PATH} available"
+    echo "Printing veristat results"
+    cat "${VERISTAT_OUTPUT}"
+
+    exit
+fi
+
+selftests/bpf/veristat \
+    --output-format csv \
+    --emit file,prog,verdict,states \
+    --compare "${BASELINE_PATH}" "${VERISTAT_OUTPUT}" > compare.csv
+
+python3 ./.github/scripts/veristat_compare.py compare.csv
diff --git a/.github/scripts/download-gcc-bpf.sh b/.github/scripts/download-gcc-bpf.sh
new file mode 100755
index 0000000000000..894584a01b2ec
--- /dev/null
+++ b/.github/scripts/download-gcc-bpf.sh
@@ -0,0 +1,30 @@
+#!/bin/bash
+
+set -euo pipefail
+
+GCC_BPF_RELEASE_GH_REPO=$1
+INSTALL_DIR=$(realpath $2)
+
+cd /tmp
+
+tag=$(gh release list -L 1 -R ${GCC_BPF_RELEASE_GH_REPO} --json tagName -q .[].tagName)
+if [[ -z "$tag" ]]; then
+    echo "Could not find latest GCC BPF release at ${GCC_BPF_RELEASE_GH_REPO}"
+    exit 1
+fi
+
+url="https://github.com/${GCC_BPF_RELEASE_GH_REPO}/releases/download/${tag}/${tag}.tar.zst"
+echo "Downloading $url"
+wget -q "$url"
+
+tarball=${tag}.tar.zst
+dir=$(tar tf $tarball | head -1 || true)
+
+echo "Extracting $tarball ..."
+tar -I zstd -xf $tarball && rm -f $tarball
+
+rm -rf $INSTALL_DIR
+mv -v $dir $INSTALL_DIR
+
+cd -
+
diff --git a/.github/scripts/matrix.py b/.github/scripts/matrix.py
new file mode 100644
index 0000000000000..9f4f5bbe23a15
--- /dev/null
+++ b/.github/scripts/matrix.py
@@ -0,0 +1,194 @@
+#!/usr/bin/env python3
+
+import os
+import dataclasses
+import json
+
+from enum import Enum
+from typing import Any, Dict, List, Final, Set, Union
+
+MANAGED_OWNER: Final[str] = "kernel-patches"
+MANAGED_REPOS: Final[Set[str]] = {
+    f"{MANAGED_OWNER}/bpf",
+    f"{MANAGED_OWNER}/vmtest",
+}
+
+DEFAULT_SELF_HOSTED_RUNNER_TAGS: Final[List[str]] = ["self-hosted", "docker-noble-main"]
+DEFAULT_RUNNER: Final[str] = "ubuntu-24.04"
+DEFAULT_LLVM_VERSION: Final[int] = 17
+
+
+class Arch(str, Enum):
+    """
+    CPU architecture supported by CI.
+    """
+
+    AARCH64 = "aarch64"
+    S390X = "s390x"
+    X86_64 = "x86_64"
+
+
+class Compiler(str, Enum):
+    GCC = "gcc"
+    LLVM = "llvm"
+
+
+@dataclasses.dataclass
+class Toolchain:
+    compiler: Compiler
+    # This is relevant ONLY for LLVM and should not be required for GCC
+    version: int
+
+    @property
+    def short_name(self) -> str:
+        return str(self.compiler.value)
+
+    @property
+    def full_name(self) -> str:
+        if self.compiler == Compiler.GCC:
+            return self.short_name
+
+        return f"{self.short_name}-{self.version}"
+
+    def to_dict(self) -> Dict[str, Union[str, int]]:
+        return {
+            "name": self.short_name,
+            "fullname": self.full_name,
+            "version": self.version,
+        }
+
+
+@dataclasses.dataclass
+class BuildConfig:
+    arch: Arch
+    toolchain: Toolchain
+    kernel: str = "LATEST"
+    run_veristat: bool = False
+    parallel_tests: bool = False
+    build_release: bool = False
+
+    @property
+    def runs_on(self) -> List[str]:
+        if is_managed_repo():
+            return DEFAULT_SELF_HOSTED_RUNNER_TAGS + [self.arch.value]
+        else:
+            return [DEFAULT_RUNNER]
+
+    @property
+    def build_runs_on(self) -> List[str]:
+        if is_managed_repo():
+            return ["codebuild"]
+        else:
+            return [DEFAULT_RUNNER]
+
+    @property
+    def tests(self) -> Dict[str, Any]:
+        tests_list = [
+            "test_progs",
+            "test_progs_parallel",
+            "test_progs_no_alu32",
+            "test_progs_no_alu32_parallel",
+            "test_verifier",
+        ]
+
+        if self.arch.value != "s390x":
+            tests_list.append("test_maps")
+
+        if self.toolchain.version >= 18:
+            tests_list.append("test_progs_cpuv4")
+
+        # if self.arch in [Arch.X86_64, Arch.AARCH64]:
+        #     tests_list.append("sched_ext")
+
+        # Don't run GCC BPF runner, because too many tests are failing
+        # See: https://lore.kernel.org/bpf/87bjw6qpje.fsf@oracle.com/
+        # if self.arch == Arch.X86_64:
+        #    tests_list.append("test_progs-bpf_gcc")
+
+        if not self.parallel_tests:
+            tests_list = [test for test in tests_list if not test.endswith("parallel")]
+
+        return {"include": [generate_test_config(test) for test in tests_list]}
+
+    def to_dict(self) -> Dict[str, Any]:
+        return {
+            "arch": self.arch.value,
+            "toolchain": self.toolchain.to_dict(),
+            "kernel": self.kernel,
+            "run_veristat": self.run_veristat,
+            "parallel_tests": self.parallel_tests,
+            "build_release": self.build_release,
+            "runs_on": self.runs_on,
+            "tests": self.tests,
+            "build_runs_on": self.build_runs_on,
+        }
+
+
+def is_managed_repo() -> bool:
+    return (
+        os.environ["GITHUB_REPOSITORY_OWNER"] == MANAGED_OWNER
+        and os.environ["GITHUB_REPOSITORY"] in MANAGED_REPOS
+    )
+
+
+def set_output(name, value):
+    """Write an output variable to the GitHub output file."""
+    with open(os.getenv("GITHUB_OUTPUT"), "a", encoding="utf-8") as file:
+        file.write(f"{name}={value}\n")
+
+
+def generate_test_config(test: str) -> Dict[str, Union[str, int]]:
+    """Create the configuration for the provided test."""
+    is_parallel = test.endswith("_parallel")
+    config = {
+        "test": test,
+        "continue_on_error": is_parallel,
+        # While in experimental mode, parallel jobs may get stuck
+        # anywhere, including in user space where the kernel won't detect
+        # a problem and panic. We add a second layer of (smaller) timeouts
+        # here such that if we get stuck in a parallel run, we hit this
+        # timeout and fail without affecting the overall job success (as
+        # would be the case if we hit the job-wide timeout). For
+        # non-experimental jobs, 360 is the default which will be
+        # superseded by the overall workflow timeout (but we need to
+        # specify something).
+        "timeout_minutes": 30 if is_parallel else 360,
+    }
+    return config
+
+
+if __name__ == "__main__":
+    matrix = [
+        BuildConfig(
+            arch=Arch.X86_64,
+            toolchain=Toolchain(compiler=Compiler.GCC, version=DEFAULT_LLVM_VERSION),
+            run_veristat=True,
+            parallel_tests=True,
+        ),
+        BuildConfig(
+            arch=Arch.X86_64,
+            toolchain=Toolchain(compiler=Compiler.LLVM, version=DEFAULT_LLVM_VERSION),
+            build_release=True,
+        ),
+        BuildConfig(
+            arch=Arch.X86_64,
+            toolchain=Toolchain(compiler=Compiler.LLVM, version=18),
+            build_release=True,
+        ),
+        BuildConfig(
+            arch=Arch.AARCH64,
+            toolchain=Toolchain(compiler=Compiler.GCC, version=DEFAULT_LLVM_VERSION),
+        ),
+        BuildConfig(
+            arch=Arch.S390X,
+            toolchain=Toolchain(compiler=Compiler.GCC, version=DEFAULT_LLVM_VERSION),
+        ),
+    ]
+
+    # Outside of managed repositories only run on x86_64
+    if not is_managed_repo():
+        matrix = [config for config in matrix if config.arch == Arch.X86_64]
+
+    json_matrix = json.dumps({"include": [config.to_dict() for config in matrix]})
+    print(json.dumps(json.loads(json_matrix), indent=4))
+    set_output("build_matrix", json_matrix)
diff --git a/.github/scripts/tests/test_veristat_compare.py b/.github/scripts/tests/test_veristat_compare.py
new file mode 100644
index 0000000000000..b65b69295235d
--- /dev/null
+++ b/.github/scripts/tests/test_veristat_compare.py
@@ -0,0 +1,75 @@
+#!/usr/bin/env python3
+
+import unittest
+from typing import Iterable, List
+
+from ..veristat_compare import parse_table, VeristatFields
+
+
+def gen_csv_table(records: Iterable[str]) -> List[str]:
+    return [
+        ",".join(VeristatFields.headers()),
+        *records,
+    ]
+
+
+class TestVeristatCompare(unittest.TestCase):
+    def test_parse_table_ignore_new_prog(self):
+        table = gen_csv_table(
+            [
+                "prog_file.bpf.o,prog_name,N/A,success,N/A,N/A,1,N/A",
+            ]
+        )
+        veristat_info = parse_table(table)
+        self.assertEqual(veristat_info.table, [])
+        self.assertFalse(veristat_info.changes)
+        self.assertFalse(veristat_info.new_failures)
+
+    def test_parse_table_ignore_removed_prog(self):
+        table = gen_csv_table(
+            [
+                "prog_file.bpf.o,prog_name,success,N/A,N/A,1,N/A,N/A",
+            ]
+        )
+        veristat_info = parse_table(table)
+        self.assertEqual(veristat_info.table, [])
+        self.assertFalse(veristat_info.changes)
+        self.assertFalse(veristat_info.new_failures)
+
+    def test_parse_table_new_failure(self):
+        table = gen_csv_table(
+            [
+                "prog_file.bpf.o,prog_name,success,failure,MISMATCH,1,1,+0 (+0.00%)",
+            ]
+        )
+        veristat_info = parse_table(table)
+        self.assertEqual(
+            veristat_info.table,
+            [["prog_file.bpf.o", "prog_name", "success -> failure (!!)", "+0.00 %"]],
+        )
+        self.assertTrue(veristat_info.changes)
+        self.assertTrue(veristat_info.new_failures)
+
+    def test_parse_table_new_changes(self):
+        table = gen_csv_table(
+            [
+                "prog_file.bpf.o,prog_name,failure,success,MISMATCH,0,0,+0 (+0.00%)",
+                "prog_file.bpf.o,prog_name_increase,failure,failure,MATCH,1,2,+1 (+100.00%)",
+                "prog_file.bpf.o,prog_name_decrease,success,success,MATCH,1,1,-1 (-100.00%)",
+            ]
+        )
+        veristat_info = parse_table(table)
+        self.assertEqual(
+            veristat_info.table,
+            [
+                ["prog_file.bpf.o", "prog_name", "failure -> success", "+0.00 %"],
+                ["prog_file.bpf.o", "prog_name_increase", "failure", "+100.00 %"],
+                ["prog_file.bpf.o", "prog_name_decrease", "success", "-100.00 %"],
+            ],
+        )
+        self.assertTrue(veristat_info.changes)
+        self.assertFalse(veristat_info.new_failures)
+
+
+if __name__ == "__main__":
+    unittest.main()
diff --git a/.github/scripts/tmpfsify-workspace.sh b/.github/scripts/tmpfsify-workspace.sh
new file mode 100755
index 0000000000000..6fd62b4ad2a49
--- /dev/null
+++ b/.github/scripts/tmpfsify-workspace.sh
@@ -0,0 +1,21 @@
+#!/bin/bash
+
+set -x -euo pipefail
+
+TMPFS_SIZE=20 # GB
+MEM_TOTAL=$(awk '/MemTotal/ {print int($2/1024)}' /proc/meminfo)
+
+# sanity check: total mem is at least double TMPFS_SIZE
+if [ $MEM_TOTAL -lt $(($TMPFS_SIZE*1024*2)) ]; then
+    echo "tmpfsify-workspace.sh: will not allocate tmpfs, total memory is too low (${MEM_TOTAL}MB)"
+    exit 0
+fi
+
+dir="$(basename "$GITHUB_WORKSPACE")"
+cd "$(dirname "$GITHUB_WORKSPACE")"
+mv "${dir}" "${dir}.backup"
+mkdir "${dir}"
+sudo mount -t tmpfs -o size=${TMPFS_SIZE}G tmpfs "${dir}"
+rsync -a "${dir}.backup/" "${dir}"
+cd -
+
diff --git a/.github/scripts/veristat_compare.py b/.github/scripts/veristat_compare.py
new file mode 100644
index 0000000000000..07271b8cbd3aa
--- /dev/null
+++ b/.github/scripts/veristat_compare.py
@@ -0,0 +1,263 @@
+#!/usr/bin/env python3
+
+# This script reads a CSV file produced by the following invocation:
+#
+#   veristat --emit file,prog,verdict,states \
+#            --output-format csv \
+#            --compare ...
+#
+# And produces a markdown summary for the file.
+# The summary is printed to standard output and appended to a file
+# pointed to by GITHUB_STEP_SUMMARY variable.
+#
+# Script exits with return code 1 if there are new failures in the
+# veristat results.
+#
+# For testing purposes invoke as follows:
+#
+#  GITHUB_STEP_SUMMARY=/dev/null python3 veristat-compare.py test.csv
+#
+# File format (columns):
+#  0. file_name
+#  1. prog_name
+#  2. verdict_base
+#  3. verdict_comp
+#  4. verdict_diff
+#  5. total_states_base
+#  6. total_states_comp
+#  7. total_states_diff
+#
+# Records sample:
+#  file-a,a,success,failure,MISMATCH,12,12,+0 (+0.00%)
+#  file-b,b,success,success,MATCH,67,67,+0 (+0.00%)
+#
+# For better readability suffixes '_OLD' and '_NEW'
+# are used instead of '_base' and '_comp' for variable
+# names etc.
+
+import io
+import os
+import sys
+import re
+import csv
+import logging
+import argparse
+import enum
+from dataclasses import dataclass
+from typing import Dict, Iterable, List, Final
+
+
+TRESHOLD_PCT: Final[int] = 0
+
+SUMMARY_HEADERS = ["File", "Program", "Verdict", "States Diff (%)"]
+
+# expected format: +0 (+0.00%) / -0 (-0.00%)
+TOTAL_STATES_DIFF_REGEX = (
+    r"(?P<absolute_diff>[+-]\d+) \((?P<percentage_diff>[+-]\d+\.\d+)\%\)"
+)
+
+
+TEXT_SUMMARY_TEMPLATE: Final[str] = (
+    """
+# {title}
+
+{table}
+""".strip()
+)
+
+HTML_SUMMARY_TEMPLATE: Final[str] = (
+    """
+# {title}
+
+<details>
+<summary>Click to expand</summary>
+
+{table}
+</details>
+""".strip()
+)
+
+GITHUB_MARKUP_REPLACEMENTS: Final[Dict[str, str]] = {
+    "->": "&rarr;",
+    "(!!)": ":bangbang:",
+}
+
+NEW_FAILURE_SUFFIX: Final[str] = "(!!)"
+
+
+class VeristatFields(str, enum.Enum):
+    FILE_NAME = "file_name"
+    PROG_NAME = "prog_name"
+    VERDICT_OLD = "verdict_base"
+    VERDICT_NEW = "verdict_comp"
+    VERDICT_DIFF = "verdict_diff"
+    TOTAL_STATES_OLD = "total_states_base"
+    TOTAL_STATES_NEW = "total_states_comp"
+    TOTAL_STATES_DIFF = "total_states_diff"
+
+    @classmethod
+    def headers(cls) -> List[str]:
+        return [
+            cls.FILE_NAME,
+            cls.PROG_NAME,
+            cls.VERDICT_OLD,
+            cls.VERDICT_NEW,
+            cls.VERDICT_DIFF,
+            cls.TOTAL_STATES_OLD,
+            cls.TOTAL_STATES_NEW,
+            cls.TOTAL_STATES_DIFF,
+        ]
+
+
+@dataclass
+class VeristatInfo:
+    table: list
+    changes: bool
+    new_failures: bool
+
+    def get_results_title(self) -> str:
+        if self.new_failures:
+            return "There are new veristat failures"
+
+        if self.changes:
+            return "There are changes in verification performance"
+
+        return "No changes in verification performance"
+
+    def get_results_summary(self, markup: bool = False) -> str:
+        title = self.get_results_title()
+        if not self.table:
+            return f"# {title}\n"
+
+        template = TEXT_SUMMARY_TEMPLATE
+        table = format_table(headers=SUMMARY_HEADERS, rows=self.table)
+
+        if markup:
+            template = HTML_SUMMARY_TEMPLATE
+            table = github_markup_decorate(table)
+
+        return template.format(title=title, table=table)
+
+
+def get_state_diff(value: str) -> float:
+    if value == "N/A":
+        return 0.0
+
+    matches = re.match(TOTAL_STATES_DIFF_REGEX, value)
+    if not matches:
+        raise ValueError(f"Failed to parse total states diff field value '{value}'")
+
+    if percentage_diff := matches.group("percentage_diff"):
+        return float(percentage_diff)
+
+    raise ValueError(f"Invalid {VeristatFields.TOTAL_STATES_DIFF} field value: {value}")
+
+
+def parse_table(csv_file: Iterable[str]) -> VeristatInfo:
+    reader = csv.DictReader(csv_file)
+    assert reader.fieldnames == VeristatFields.headers()
+
+    new_failures = False
+    changes = False
+    table = []
+
+    for record in reader:
+        add = False
+
+        verdict_old, verdict_new = (
+            record[VeristatFields.VERDICT_OLD],
+            record[VeristatFields.VERDICT_NEW],
+        )
+
+        # Ignore results from completely new and removed programs
+        if "N/A" in [verdict_new, verdict_old]:
+            continue
+
+        if record[VeristatFields.VERDICT_DIFF] == "MISMATCH":
+            changes = True
+            add = True
+            verdict = f"{verdict_old} -> {verdict_new}"
+            if verdict_new == "failure":
+                new_failures = True
+                verdict += f" {NEW_FAILURE_SUFFIX}"
+        else:
+            verdict = record[VeristatFields.VERDICT_NEW]
+
+        diff = get_state_diff(record[VeristatFields.TOTAL_STATES_DIFF])
+        if abs(diff) > TRESHOLD_PCT:
+            changes = True
+            add = True
+
+        if not add:
+            continue
+
+        table.append(
+            [
+                record[VeristatFields.FILE_NAME],
+                record[VeristatFields.PROG_NAME],
+                verdict,
+                f"{diff:+.2f} %",
+            ]
+        )
+
+    return VeristatInfo(table=table, changes=changes, new_failures=new_failures)
+
+
+def github_markup_decorate(input_str: str) -> str:
+    for text, markup in GITHUB_MARKUP_REPLACEMENTS.items():
+        input_str = input_str.replace(text, markup)
+    return input_str
+
+
+def format_table(headers: List[str], rows: List[List[str]]) -> str:
+    column_width = [
+        max(len(row[column_idx]) for row in [headers] + rows)
+        for column_idx in range(len(headers))
+    ]
+
+    # Row template string in the following format:
+    # "{0:8}|{1:10}|{2:15}|{3:7}|{4:10}"
+    row_template = "|".join(
+        f"{{{idx}:{width}}}" for idx, width in enumerate(column_width)
+    )
+    row_template_nl = f"|{row_template}|\n"
+
+    with io.StringIO() as out:
+        out.write(row_template_nl.format(*headers))
+
+        separator_row = ["-" * width for width in column_width]
+        out.write(row_template_nl.format(*separator_row))
+
+        for row in rows:
+            row_str = row_template_nl.format(*row)
+            out.write(row_str)
+
+        return out.getvalue()
+
+
+def main(compare_csv_filename: os.PathLike, output_filename: os.PathLike) -> None:
+    with open(compare_csv_filename, newline="", encoding="utf-8") as csv_file:
+        veristat_results = parse_table(csv_file)
+
+    sys.stdout.write(veristat_results.get_results_summary())
+
+    with open(output_filename, encoding="utf-8", mode="a") as file:
+        file.write(veristat_results.get_results_summary(markup=True))
+
+    if veristat_results.new_failures:
+        return 1
+
+    return 0
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(
+        description="Print veristat comparison output as markdown step summary"
+    )
+    parser.add_argument("filename")
+    args = parser.parse_args()
+    summary_filename = os.getenv("GITHUB_STEP_SUMMARY")
+    if not summary_filename:
+        logging.error("GITHUB_STEP_SUMMARY environment variable is not set")
+        sys.exit(1)
+    sys.exit(main(args.filename, summary_filename))
diff --git a/.github/workflows/gcc-bpf.yml b/.github/workflows/gcc-bpf.yml
new file mode 100644
index 0000000000000..8356a0af836f1
--- /dev/null
+++ b/.github/workflows/gcc-bpf.yml
@@ -0,0 +1,100 @@
+name: Testing GCC BPF compiler
+
+on:
+  workflow_call:
+    inputs:
+      runs_on:
+        required: true
+        type: string
+      arch:
+        required: true
+        type: string
+      llvm-version:
+        required: true
+        type: string
+      toolchain:
+        required: true
+        type: string
+      toolchain_full:
+        required: true
+        type: string
+      download_sources:
+        required: true
+        type: boolean
+
+jobs:
+  test:
+    name: GCC BPF
+    runs-on: >-
+      ${{
+          contains(fromJSON(inputs.runs_on), 'codebuild')
+          && format('codebuild-bpf-ci-{0}-{1}', github.run_id, github.run_attempt)
+          || fromJSON(inputs.runs_on)
+      }}
+    env:
+      ARCH: ${{ inputs.arch }}
+      BPF_NEXT_BASE_BRANCH: 'master'
+      GCC_BPF_INSTALL_DIR: ${{ github.workspace }}/gcc-bpf
+      GCC_BPF_RELEASE_REPO: 'theihor/gcc-bpf'
+      KBUILD_OUTPUT: ${{ github.workspace }}/src/kbuild-output
+      REPO_ROOT: ${{ github.workspace }}/src
+
+    steps:
+
+      - uses: actions/checkout@v4
+        with:
+          sparse-checkout: |
+            .github
+            ci
+
+      - if: ${{ inputs.download_sources }}
+        name: Download bpf-next tree
+        uses: libbpf/ci/get-linux-source@v3
+        with:
+          dest: ${{ env.REPO_ROOT }}
+          rev: ${{ env.BPF_NEXT_BASE_BRANCH }}
+
+      - if: ${{ ! inputs.download_sources }}
+        name: Checkout ${{ github.repository }} to ./src
+        uses: actions/checkout@v4
+        with:
+          path: 'src'
+
+      - uses:  libbpf/ci/patch-kernel@v3
+        with:
+          patches-root: '${{ github.workspace }}/ci/diffs'
+          repo-root: ${{ env.REPO_ROOT }}
+
+      - uses: actions/download-artifact@v4
+        with:
+          name: vmlinux-${{ inputs.arch }}-${{ inputs.toolchain_full }}
+          path: ${{ env.REPO_ROOT }}
+
+      - name: Untar artifacts
+        working-directory: ${{ env.REPO_ROOT }}
+        run: zstd -d -T0 vmlinux-${{ inputs.arch }}-${{ inputs.toolchain_full }}.tar.zst --stdout | tar -xf -
+
+      - name: Setup build environment
+        uses: libbpf/ci/setup-build-env@v3
+        with:
+          arch: ${{ inputs.arch }}
+          llvm-version: ${{ inputs.llvm-version }}
+
+      - name: Download GCC BPF compiler
+        shell: bash
+        env:
+          GH_TOKEN: ${{ github.token }}
+        run: .github/scripts/download-gcc-bpf.sh ${{ env.GCC_BPF_RELEASE_REPO }} ${{ env.GCC_BPF_INSTALL_DIR }}
+
+      - name: Build selftests/bpf/test_progs-bpf_gcc
+        uses: libbpf/ci/build-selftests@v3
+        env:
+          BPF_GCC: ${{ env.GCC_BPF_INSTALL_DIR }}
+          MAX_MAKE_JOBS: 32
+          SELFTESTS_BPF_TARGETS: 'test_progs-bpf_gcc'
+        with:
+          arch: ${{ inputs.arch }}
+          kernel-root: ${{ env.REPO_ROOT }}
+          llvm-version: ${{ inputs.llvm-version }}
+          toolchain: ${{ inputs.toolchain }}
+
diff --git a/.github/workflows/kernel-build-test.yml b/.github/workflows/kernel-build-test.yml
new file mode 100644
index 0000000000000..541ef910b1d28
--- /dev/null
+++ b/.github/workflows/kernel-build-test.yml
@@ -0,0 +1,147 @@
+name: Reusable Build/Test/Veristat workflow
+
+on:
+  workflow_call:
+    inputs:
+      arch:
+        required: true
+        type: string
+        description: The architecture to build against, e.g x86_64, aarch64, s390x...
+      toolchain_full:
+        required: true
+        type: string
+        description: The toolchain and for llvm, its version, e.g gcc, llvm-15
+      toolchain:
+        required: true
+        type: string
+        description: The toolchain, e.g gcc, llvm
+      runs_on:
+        required: true
+        type: string
+        description: The runners to run the test on. This is a json string representing an array of labels.
+      build_runs_on:
+        required: true
+        type: string
+        description: The runners to run the builds on. This is a json string representing an array of labels.
+      llvm-version:
+        required: true
+        type: string
+        description: The version of LLVM used to build selftest.... for llvm toolchain, this should match the one from toolchain_full, for gcc it is an arbritrary version we decide to build selftests against.
+      kernel:
+        required: true
+        type: string
+        description: The kernel to run the test against. For KPD this is always LATEST, which runs against a newly built kernel.
+      tests:
+        required: true
+        type: string
+        description: A serialized json array with the tests to be running, it must follow the json-matrix format, https://www.jitsejan.com/use-github-actions-with-json-file-as-matrix
+      run_veristat:
+        required: true
+        type: boolean
+        description: Whether or not to run the veristat job.
+      run_tests:
+        required: true
+        type: boolean
+        description: Whether or not to run the test job.
+      download_sources:
+        required: true
+        type: boolean
+        description: Whether to download the linux sources into the working directory.
+        default: false
+      build_release:
+        required: true
+        type: boolean
+        description: Build selftests with -O2 optimization in addition to non-optimized build.
+        default: false
+    secrets:
+      AWS_ROLE_ARN:
+        required: true
+
+jobs:
+
+  # Build kernel and selftest
+  build:
+    uses: ./.github/workflows/kernel-build.yml
+    with:
+      arch: ${{ inputs.arch }}
+      toolchain_full: ${{ inputs.toolchain_full }}
+      toolchain: ${{ inputs.toolchain }}
+      runs_on: ${{ inputs.build_runs_on }}
+      llvm-version: ${{ inputs.llvm-version }}
+      kernel: ${{ inputs.kernel }}
+      download_sources: ${{ inputs.download_sources }}
+
+  build-release:
+    if: ${{ inputs.build_release }}
+    uses: ./.github/workflows/kernel-build.yml
+    with:
+      arch: ${{ inputs.arch }}
+      toolchain_full: ${{ inputs.toolchain_full }}
+      toolchain: ${{ inputs.toolchain }}
+      runs_on: ${{ inputs.build_runs_on }}
+      llvm-version: ${{ inputs.llvm-version }}
+      kernel: ${{ inputs.kernel }}
+      download_sources: ${{ inputs.download_sources }}
+      release: true
+
+  test:
+    if: ${{ inputs.run_tests }}
+    uses: ./.github/workflows/kernel-test.yml
+    # Setting name to test here to avoid lengthy autogenerated names due to matrix
+    # e.g build-and-test x86_64-gcc / test (test_progs_parallel, true, 30) / test_progs_parallel on x86_64 with gcc
+    name: "test"
+    needs: [build]
+    strategy:
+      fail-fast: false
+      matrix: ${{ fromJSON(inputs.tests) }}
+    with:
+      arch: ${{ inputs.arch }}
+      toolchain_full: ${{ inputs.toolchain_full }}
+      runs_on: ${{ inputs.runs_on }}
+      kernel: ${{ inputs.kernel }}
+      test: ${{ matrix.test }}
+      continue_on_error: ${{ toJSON(matrix.continue_on_error) }}
+      timeout_minutes: ${{ matrix.timeout_minutes }}
+
+  veristat-kernel:
+    if: ${{ inputs.run_veristat }}
+    uses: ./.github/workflows/veristat-kernel.yml
+    needs: [build]
+    permissions:
+      id-token: write
+      contents: read
+    with:
+      arch: ${{ inputs.arch }}
+      toolchain: ${{ inputs.toolchain }}
+      runs_on: ${{ inputs.runs_on }}
+
+  veristat-meta:
+    # Check for vars.AWS_REGION is necessary to skip this job in case of a PR from a fork.
+    if: ${{ inputs.run_veristat && github.repository_owner == 'kernel-patches' && vars.AWS_REGION }}
+    uses: ./.github/workflows/veristat-meta.yml
+    needs: [build]
+    permissions:
+      id-token: write
+      contents: read
+    with:
+      arch: ${{ inputs.arch }}
+      toolchain: ${{ inputs.toolchain }}
+      aws_region: ${{ vars.AWS_REGION }}
+      runs_on: ${{ inputs.runs_on }}
+    secrets:
+      AWS_ROLE_ARN: ${{ secrets.AWS_ROLE_ARN }}
+
+  gcc-bpf:
+    name: 'GCC BPF'
+    if: ${{ inputs.arch == 'x86_64' }}
+    uses: ./.github/workflows/gcc-bpf.yml
+    needs: [build]
+    with:
+      # GCC BPF does not need /dev/kvm, so use the "build" runners
+      runs_on: ${{ inputs.build_runs_on }}
+      arch: ${{ inputs.arch }}
+      llvm-version: ${{ inputs.llvm-version }}
+      toolchain: ${{ inputs.toolchain }}
+      toolchain_full: ${{ inputs.toolchain_full }}
+      download_sources: ${{ inputs.download_sources }}
+
diff --git a/.github/workflows/kernel-build.yml b/.github/workflows/kernel-build.yml
new file mode 100644
index 0000000000000..513d96411921e
--- /dev/null
+++ b/.github/workflows/kernel-build.yml
@@ -0,0 +1,191 @@
+
+name: Reusable build workflow
+
+on:
+  workflow_call:
+    inputs:
+      arch:
+        required: true
+        type: string
+        description: The architecture to build against, e.g x86_64, aarch64, s390x...
+      toolchain_full:
+        required: true
+        type: string
+        description: The toolchain and for llvm, its version, e.g gcc, llvm-15
+      toolchain:
+        required: true
+        type: string
+        description: The toolchain, e.g gcc, llvm
+      runs_on:
+        required: true
+        type: string
+        description: The runners to run the test on. This is a json string representing an array of labels.
+      llvm-version:
+        required: true
+        type: string
+        description: The version of LLVM used to build selftest.... for llvm toolchain, this should match the one from toolchain_full, for gcc it is an arbritrary version we decide to build selftests against.
+      kernel:
+        required: true
+        type: string
+        description: The kernel to run the test against. For KPD this is always LATEST, which runs against a newly built kernel.
+      download_sources:
+        required: true
+        type: boolean
+        description: Whether to download the linux sources into the working directory.
+        default: false
+      release:
+        required: false
+        type: boolean
+        description: Build selftest with -O2 optimization
+        default: false
+
+jobs:
+  build:
+    name: build for ${{ inputs.arch }} with ${{ inputs.toolchain_full }}${{ inputs.release && '-O2' || '' }}
+    # To run on CodeBuild, runs-on value must correspond to the AWS
+    # CodeBuild project associated with the kernel-patches webhook
+    # However matrix.py passes just a 'codebuild' string
+    runs-on: >-
+      ${{
+          contains(fromJSON(inputs.runs_on), 'codebuild')
+          && format('codebuild-bpf-ci-{0}-{1}', github.run_id, github.run_attempt)
+          || fromJSON(inputs.runs_on)
+      }}
+    env:
+        ARTIFACTS_ARCHIVE: "vmlinux-${{ inputs.arch }}-${{ inputs.toolchain_full }}.tar.zst"
+        BPF_NEXT_BASE_BRANCH: 'master'
+        BPF_NEXT_FETCH_DEPTH: 64 # A bit of history is needed to facilitate incremental builds
+        CROSS_COMPILE: ${{ inputs.arch != 'x86_64' && 'true' || '' }}
+        # BUILD_SCHED_EXT_SELFTESTS: ${{ inputs.arch == 'x86_64' || inputs.arch == 'aarch64' && 'true' || '' }}
+        KBUILD_OUTPUT: ${{ github.workspace }}/kbuild-output
+        KERNEL: ${{ inputs.kernel }}
+        KERNEL_ROOT: ${{ github.workspace }}
+        REPO_PATH: ""
+        REPO_ROOT: ${{ github.workspace }}
+        RUNNER_TYPE: ${{ github.repository_owner == 'kernel-patches' && 'codebuild' || 'default' }}
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: ${{ inputs.download_sources && 1 || env.BPF_NEXT_FETCH_DEPTH }}
+
+      - if: ${{ env.RUNNER_TYPE == 'codebuild' }}
+        shell: bash
+        run: .github/scripts/tmpfsify-workspace.sh
+
+      - if: ${{ inputs.download_sources }}
+        name: Download bpf-next tree
+        env:
+          FETCH_DEPTH: ${{ env.BPF_NEXT_FETCH_DEPTH }}
+        uses: libbpf/ci/get-linux-source@v3
+        with:
+          dest: '.kernel'
+          rev: ${{ env.BPF_NEXT_BASE_BRANCH }}
+      - uses: libbpf/ci/prepare-incremental-build@v3
+        with:
+          repo-root: ${{ inputs.download_sources && '.kernel' || env.REPO_ROOT }}
+          base-branch: >-
+            ${{    inputs.download_sources && env.BPF_NEXT_BASE_BRANCH
+                || github.event_name == 'pull_request' && github.base_ref
+                || github.ref_name
+             }}
+          arch: ${{ inputs.arch }}
+          toolchain_full: ${{ inputs.toolchain_full }}
+          kbuild-output: ${{ env.KBUILD_OUTPUT }}
+      - if: ${{ inputs.download_sources }}
+        name: Move linux source in place
+        shell: bash
+        run: |
+          cd .kernel
+          rm -rf .git
+          mv -t .. $(ls -A)
+          cd ..
+          rmdir .kernel
+      - uses:  libbpf/ci/patch-kernel@v3
+        with:
+          patches-root: '${{ github.workspace }}/ci/diffs'
+          repo-root: ${{ env.REPO_ROOT }}
+
+      - name: Setup build environment
+        uses: libbpf/ci/setup-build-env@v3
+        with:
+          arch: ${{ inputs.arch }}
+          llvm-version: ${{ inputs.llvm-version }}
+          pahole: master
+
+        # We have to setup qemu+binfmt in order to enable cross-compation of selftests.
+        # During selftests build, freshly built bpftool is executed.
+        # On self-hosted bare-metal hosts binfmt is pre-configured.
+      - if: ${{ env.RUNNER_TYPE == 'codebuild' && env.CROSS_COMPILE }}
+        name: Set up docker
+        uses: docker/setup-docker-action@v4
+      - if: ${{ env.RUNNER_TYPE == 'codebuild' && env.CROSS_COMPILE }}
+        name: Setup binfmt and qemu
+        uses: docker/setup-qemu-action@v3
+        with:
+          image: tonistiigi/binfmt:qemu-v9.2.0
+
+      - name: Build kernel image
+        uses: libbpf/ci/build-linux@v3
+        with:
+          arch: ${{ inputs.arch }}
+          toolchain: ${{ inputs.toolchain }}
+          kbuild-output: ${{ env.KBUILD_OUTPUT }}
+          max-make-jobs: 32
+          llvm-version: ${{ inputs.llvm-version }}
+
+      - name: Build selftests/bpf
+        uses: libbpf/ci/build-selftests@v3
+        env:
+          MAX_MAKE_JOBS: 32
+          RELEASE: ${{ inputs.release && '1' || '' }}
+        with:
+          arch: ${{ inputs.arch }}
+          kernel-root: ${{ env.KERNEL_ROOT }}
+          llvm-version: ${{ inputs.llvm-version }}
+          toolchain: ${{ inputs.toolchain }}
+
+      - if: ${{ env.BUILD_SCHED_EXT_SELFTESTS }}
+        name: Build selftests/sched_ext
+        uses: libbpf/ci/build-scx-selftests@v3
+        with:
+          kbuild-output: ${{ env.KBUILD_OUTPUT }}
+          repo-root: ${{ env.REPO_ROOT }}
+          arch: ${{ inputs.arch }}
+          toolchain: ${{ inputs.toolchain }}
+          llvm-version: ${{ inputs.llvm-version }}
+          max-make-jobs: 32
+
+      - if: ${{ github.event_name != 'push' }}
+        name: Build samples
+        uses: libbpf/ci/build-samples@v3
+        with:
+          arch: ${{ inputs.arch }}
+          toolchain: ${{ inputs.toolchain }}
+          kbuild-output: ${{ env.KBUILD_OUTPUT }}
+          max-make-jobs: 32
+          llvm-version: ${{ inputs.llvm-version }}
+      - name: Tar artifacts
+        id: tar-artifacts
+        uses: libbpf/ci/tar-artifacts@v3
+        env:
+          ARCHIVE_BPF_SELFTESTS: 'true'
+          ARCHIVE_MAKE_HELPERS: 'true'
+          ARCHIVE_SCHED_EXT_SELFTESTS: ${{ env.BUILD_SCHED_EXT_SELFTESTS }}
+        with:
+          arch: ${{ inputs.arch }}
+          archive: ${{ env.ARTIFACTS_ARCHIVE }}
+          kbuild-output: ${{ env.KBUILD_OUTPUT }}
+          repo-root: ${{ env.REPO_ROOT }}
+      - if: ${{ github.event_name != 'push' }}
+        name: Remove KBUILD_OUTPUT content
+        shell: bash
+        run: |
+          # Remove $KBUILD_OUTPUT to prevent cache creation for pull requests.
+          # Only on pushed changes are build artifacts actually cached, because
+          # of github.com/actions/cache's cache isolation logic.
+          rm -rf "${KBUILD_OUTPUT}"
+      - uses: actions/upload-artifact@v4
+        with:
+          name: vmlinux-${{ inputs.arch }}-${{ inputs.toolchain_full }}${{ inputs.release && '-release' || '' }}
+          if-no-files-found: error
+          path: ${{ env.ARTIFACTS_ARCHIVE }}
diff --git a/.github/workflows/kernel-test.yml b/.github/workflows/kernel-test.yml
new file mode 100644
index 0000000000000..6eda80362b9b0
--- /dev/null
+++ b/.github/workflows/kernel-test.yml
@@ -0,0 +1,88 @@
+name: Reusable test workflow
+
+on:
+  workflow_call:
+    inputs:
+      arch:
+        required: true
+        type: string
+        description: The architecture to build against, e.g x86_64, aarch64, s390x...
+      toolchain_full:
+        required: true
+        type: string
+        description: The toolchain and for llvm, its version, e.g gcc, llvm-15
+      runs_on:
+        required: true
+        type: string
+        description: The runners to run the test on. This is a json string representing an array of labels.
+      kernel:
+        required: true
+        type: string
+        description: The kernel to run the test against. For KPD this is always LATEST, which runs against a newly built kernel.
+      test:
+        required: true
+        type: string
+        description: The test to run in the vm, e.g test_progs, test_maps, test_progs_no_alu32...
+      continue_on_error:
+        required: true
+        type: string
+        description: Whether to continue on error. This is typically set to true for parallel tests which are currently known to fail, but we don't want to fail the whole CI because of that.
+      timeout_minutes:
+        required: true
+        type: number
+        description: In case a test runs for too long, after how many seconds shall we timeout and error.
+
+jobs:
+  test:
+    name: ${{ inputs.test }} on ${{ inputs.arch }} with ${{ inputs.toolchain_full }}
+    runs-on: ${{ fromJSON(inputs.runs_on) }}
+    timeout-minutes: 100
+    env:
+      ARCH: ${{ inputs.arch }}
+      KERNEL: ${{ inputs.kernel }}
+      REPO_ROOT: ${{ github.workspace }}
+      REPO_PATH: ""
+      # https://github.com/actions/runner/issues/1483#issuecomment-1031671517
+      # booleans are weird in GH.
+      CONTINUE_ON_ERROR: ${{ inputs.continue_on_error }}
+      DEPLOYMENT: ${{ github.repository == 'kernel-patches/bpf' && 'prod' || 'rc' }}
+      ALLOWLIST_FILE: /tmp/allowlist
+      DENYLIST_FILE: /tmp/denylist
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          sparse-checkout: |
+            .github
+            ci
+
+      - uses: actions/download-artifact@v4
+        with:
+          name: vmlinux-${{ inputs.arch }}-${{ inputs.toolchain_full }}
+          path: .
+
+      - name: Untar artifacts
+        # zstd is installed by default in the runner images.
+        run: zstd -d -T0  vmlinux-${{ inputs.arch }}-${{ inputs.toolchain_full }}.tar.zst --stdout | tar -xf -
+
+      - name: Run selftests
+        uses: libbpf/ci/run-vmtest@v3
+        # https://github.com/actions/runner/issues/1483#issuecomment-1031671517
+        # booleans are weird in GH.
+        continue-on-error: ${{ fromJSON(env.CONTINUE_ON_ERROR) }}
+        timeout-minutes: ${{ inputs.timeout_minutes }}
+        env:
+          ARCH: ${{ inputs.arch }}
+          DEPLOYMENT: ${{ env.DEPLOYMENT }}
+          KERNEL_TEST: ${{ inputs.test }}
+          SELFTESTS_BPF: ${{ github.workspace }}/selftests/bpf
+          VMTEST_CONFIGS: ${{ github.workspace }}/ci/vmtest/configs
+          TEST_PROGS_WATCHDOG_TIMEOUT: 600
+        with:
+          arch: ${{ inputs.arch }}
+          vmlinuz: '${{ github.workspace }}/vmlinuz'
+          kernel-root: ${{ env.REPO_ROOT }}
+          max-cpu: 8
+          kernel-test: ${{ inputs.test }}
+          # Here we must use kbuild-output local to the repo, because
+          # it was extracted from the artifacts.
+          kbuild-output: ${{ env.REPO_ROOT }}/kbuild-output
diff --git a/.github/workflows/lint.yml b/.github/workflows/lint.yml
new file mode 100644
index 0000000000000..1c910fd297309
--- /dev/null
+++ b/.github/workflows/lint.yml
@@ -0,0 +1,65 @@
+name: "lint"
+
+on:
+  pull_request:
+  push:
+    branches:
+      - master
+
+jobs:
+  shellcheck:
+    # This workflow gets injected into other Linux repositories, but we don't
+    # want it to run there.
+    if: ${{ github.repository == 'kernel-patches/vmtest' }}
+    name: ShellCheck
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+      - name: Run ShellCheck
+        uses: ludeeus/action-shellcheck@master
+        env:
+          SHELLCHECK_OPTS: --severity=warning --exclude=SC1091
+
+  # Ensure some consistency in the formatting.
+  lint:
+    if: ${{ github.repository == 'kernel-patches/vmtest' }}
+    name: Lint
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+      - name: Run black
+        uses: psf/black@stable
+        with:
+          src: ./.github/scripts
+
+  validate_matrix:
+    if: ${{ github.repository == 'kernel-patches/vmtest' }}
+    name: Validate matrix.py
+    runs-on: ubuntu-latest
+    env:
+      GITHUB_REPOSITORY_OWNER: ${{ matrix.owner }}
+      GITHUB_REPOSITORY: ${{ matrix.repository }}
+      GITHUB_OUTPUT: /dev/stdout
+    strategy:
+      matrix:
+        owner: ['kernel-patches', 'foo']
+        repository: ['bpf', 'vmtest', 'bar']
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+      - name: run script
+        run: |
+          python3 .github/scripts/matrix.py
+
+  unittests:
+    if: ${{ github.repository == 'kernel-patches/vmtest' }}
+    name: Unittests
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+      - name: Run unittests
+        run: python3 -m unittest scripts/tests/*.py
+        working-directory: .github
diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml
new file mode 100644
index 0000000000000..fdf9d9f58253f
--- /dev/null
+++ b/.github/workflows/test.yml
@@ -0,0 +1,62 @@
+name: bpf-ci
+
+on:
+  pull_request:
+  push:
+    branches:
+      - bpf_base
+      - bpf-next_base
+
+concurrency:
+  group: ci-test-${{ github.ref_name }}
+  cancel-in-progress: true
+
+jobs:
+  set-matrix:
+    # FIXME: set-matrix is lightweight, run it on any self-hosted machines for kernel-patches org
+    # so we do not wait for GH hosted runners when there potentially all are busy because of bpf-rc
+    # repo for instance.
+    # This could be somehow fixed long term by making this action/workflow re-usable and letting the called
+    # specify what to run on.
+    runs-on: ${{ github.repository_owner == 'kernel-patches' && 'x86_64' || 'ubuntu-latest' }}
+    outputs:
+      build-matrix: ${{ steps.set-matrix-impl.outputs.build_matrix }}
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          sparse-checkout: |
+            .github
+            ci
+      - id: set-matrix-impl
+        run: |
+          python3 .github/scripts/matrix.py
+
+  build-and-test:
+    # Setting name to arch-compiler here to avoid lengthy autogenerated names due to matrix
+    # e.g build-and-test x86_64-gcc / test (test_progs_parallel, true, 30) / test_progs_parallel on x86_64 with gcc
+    name: "${{ matrix.arch }}-${{ matrix.toolchain.fullname }}"
+    uses: ./.github/workflows/kernel-build-test.yml
+    needs: [set-matrix]
+    permissions:
+      id-token: write
+      contents: read
+    strategy:
+      fail-fast: false
+      matrix: ${{ fromJSON(needs.set-matrix.outputs.build-matrix) }}
+    with:
+      arch: ${{ matrix.arch }}
+      toolchain_full: ${{ matrix.toolchain.fullname }}
+      toolchain: ${{ matrix.toolchain.name }}
+      runs_on: ${{ toJSON(matrix.runs_on) }}
+      build_runs_on: ${{ toJSON(matrix.build_runs_on) }}
+      llvm-version: ${{ matrix.toolchain.version }}
+      kernel: ${{ matrix.kernel }}
+      tests: ${{ toJSON(matrix.tests) }}
+      run_veristat: ${{ matrix.run_veristat }}
+      # We only run tests on pull requests.
+      run_tests: ${{ github.event_name != 'push' }}
+      # Download sources
+      download_sources: ${{ github.repository == 'kernel-patches/vmtest' }}
+      build_release: ${{ matrix.build_release }}
+    secrets:
+      AWS_ROLE_ARN: ${{ secrets.AWS_ROLE_ARN }}
diff --git a/.github/workflows/veristat-kernel.yml b/.github/workflows/veristat-kernel.yml
new file mode 100644
index 0000000000000..0557daebf5bab
--- /dev/null
+++ b/.github/workflows/veristat-kernel.yml
@@ -0,0 +1,65 @@
+name: veristat_kernel
+
+on:
+  workflow_call:
+    inputs:
+      arch:
+        required: true
+        type: string
+        description: The architecture to build against, e.g x86_64, aarch64, s390x...
+      toolchain:
+        required: true
+        type: string
+        description: The toolchain, e.g gcc, llvm
+      runs_on:
+        required: true
+        type: string
+        description: The runners to run the test on. This is a json string representing an array of labels.
+
+jobs:
+  veristat:
+    name: ${{ inputs.arch }}-${{ inputs.toolchain }} veristat_kernel
+    runs-on: ${{ fromJSON(inputs.runs_on) }}
+    timeout-minutes: 100
+    permissions:
+        id-token: write
+        contents: read
+    env:
+      KERNEL: LATEST
+      REPO_ROOT: ${{ github.workspace }}
+      REPO_PATH: ""
+      KBUILD_OUTPUT: kbuild-output/
+      ARCH_AND_TOOL: ${{ inputs.arch }}-${{ inputs.toolchain }}
+
+    steps:
+
+      - uses: actions/checkout@v4
+        with:
+          sparse-checkout: |
+            .github
+            ci
+
+      - uses: actions/download-artifact@v4
+        with:
+          name: vmlinux-${{ env.ARCH_AND_TOOL }}
+          path: .
+
+      - name: Untar artifacts
+        run: zstd -d -T0  vmlinux-${{ env.ARCH_AND_TOOL }}.tar.zst --stdout | tar -xf -
+
+      - name: Run veristat
+        uses: libbpf/ci/run-vmtest@v3
+        with:
+          arch: x86_64
+          vmlinuz: '${{ github.workspace }}/vmlinuz'
+          kernel-root: '.'
+          max-cpu: 8
+          kernel-test: 'run_veristat_kernel'
+          output-dir: '${{ github.workspace }}'
+
+      - name: Compare and save veristat.kernel.csv
+        uses: ./.github/actions/veristat_baseline_compare
+        with:
+          veristat_output: veristat-kernel
+          baseline_name: ${{ env.ARCH_AND_TOOL}}-baseline-veristat-kernel
+
diff --git a/.github/workflows/veristat-meta.yml b/.github/workflows/veristat-meta.yml
new file mode 100644
index 0000000000000..00700a8205e62
--- /dev/null
+++ b/.github/workflows/veristat-meta.yml
@@ -0,0 +1,87 @@
+name: veristat_meta
+
+on:
+  workflow_call:
+    inputs:
+      arch:
+        required: true
+        type: string
+        description: The architecture to build against, e.g x86_64, aarch64, s390x...
+      toolchain:
+        required: true
+        type: string
+        description: The toolchain, e.g gcc, llvm
+      runs_on:
+        required: true
+        type: string
+        description: The runners to run the test on. This is a json string representing an array of labels.
+      aws_region:
+        required: true
+        type: string
+        description: The AWS region where we pull bpf objects to run against veristat.
+    secrets:
+        AWS_ROLE_ARN:
+            required: true
+            description: The AWS role used by GH to pull BPF objects from AWS.
+
+jobs:
+  veristat:
+    name: ${{ inputs.arch }}-${{ inputs.toolchain }} veristat_meta
+    runs-on: ${{ fromJSON(inputs.runs_on) }}
+    timeout-minutes: 100
+    permissions:
+        id-token: write
+        contents: read
+    env:
+      KERNEL: LATEST
+      REPO_ROOT: ${{ github.workspace }}
+      REPO_PATH: ""
+      KBUILD_OUTPUT: kbuild-output/
+      ARCH_AND_TOOL: ${{ inputs.arch }}-${{ inputs.toolchain }}
+
+    steps:
+
+      - uses: actions/checkout@v4
+        with:
+          sparse-checkout: |
+            .github
+            ci
+
+      - uses: actions/download-artifact@v4
+        with:
+          name: vmlinux-${{ env.ARCH_AND_TOOL }}
+          path: .
+
+      - name: Untar artifacts
+        run: zstd -d -T0  vmlinux-${{ env.ARCH_AND_TOOL }}.tar.zst --stdout | tar -xf -
+
+      - name: Configure AWS Credentials
+        uses: aws-actions/configure-aws-credentials@v3
+        with:
+          aws-region: ${{ inputs.aws_region }}
+          role-to-assume: ${{ secrets.AWS_ROLE_ARN }}
+          role-session-name: github-action-bpf-ci
+
+      - name: Download BPF objects
+        run: |
+          mkdir ./bpf_objects
+          aws s3 sync s3://veristat-bpf-binaries ./bpf_objects
+        env:
+          AWS_ROLE_ARN: ${{ secrets.AWS_ROLE_ARN }}
+
+      - name: Run veristat
+        uses: libbpf/ci/run-vmtest@v3
+        with:
+          arch: x86_64
+          vmlinuz: '${{ github.workspace }}/vmlinuz'
+          kernel-root: '.'
+          max-cpu: 8
+          kernel-test: 'run_veristat_meta'
+          output-dir: '${{ github.workspace }}'
+
+      - name: Compare and save veristat.meta.csv
+        uses: ./.github/actions/veristat_baseline_compare
+        with:
+          veristat_output: veristat-meta
+          baseline_name: ${{ env.ARCH_AND_TOOL}}-baseline-veristat-meta
+
diff --git a/README b/README
index fd903645e6de0..e69de29bb2d1d 100644
--- a/README
+++ b/README
@@ -1,18 +0,0 @@
-Linux kernel
-============
-
-There are several guides for kernel developers and users. These guides can
-be rendered in a number of formats, like HTML and PDF. Please read
-Documentation/admin-guide/README.rst first.
-
-In order to build the documentation, use ``make htmldocs`` or
-``make pdfdocs``.  The formatted documentation can also be read online at:
-
-    https://www.kernel.org/doc/html/latest/
-
-There are various text files in the Documentation/ subdirectory,
-several of them using the reStructuredText markup notation.
-
-Please read the Documentation/process/changes.rst file, as it contains the
-requirements for building and running the kernel, and information about
-the problems which may result by upgrading your kernel.
diff --git a/ci/diffs/.keep b/ci/diffs/.keep
new file mode 100644
index 0000000000000..e69de29bb2d1d
diff --git a/ci/diffs/0001-Revert-bpf-Avoid-unnecessary-audit-log-for-CPU-secur.patch b/ci/diffs/0001-Revert-bpf-Avoid-unnecessary-audit-log-for-CPU-secur.patch
new file mode 100644
index 0000000000000..3b6139225e7bf
--- /dev/null
+++ b/ci/diffs/0001-Revert-bpf-Avoid-unnecessary-audit-log-for-CPU-secur.patch
@@ -0,0 +1,33 @@
+From 5440a12ac8fb2a8e051c597fcf5d85b427fe612a Mon Sep 17 00:00:00 2001
+From: Andrii Nakryiko <andrii@kernel.org>
+Date: Fri, 13 Oct 2023 12:44:34 -0700
+Subject: [PATCH] Revert "bpf: Avoid unnecessary audit log for CPU security
+ mitigations"
+
+This reverts commit 236334aeec0f93217cf9235f2004e61a0a1a5985.
+---
+ include/linux/bpf.h | 4 ++--
+ 1 file changed, 2 insertions(+), 2 deletions(-)
+
+diff --git a/include/linux/bpf.h b/include/linux/bpf.h
+index f0891ba24cb1..61bde4520f5c 100644
+--- a/include/linux/bpf.h
++++ b/include/linux/bpf.h
+@@ -2164,12 +2164,12 @@ static inline bool bpf_allow_uninit_stack(void)
+ 
+ static inline bool bpf_bypass_spec_v1(void)
+ {
+-	return cpu_mitigations_off() || perfmon_capable();
++	return perfmon_capable() || cpu_mitigations_off();
+ }
+ 
+ static inline bool bpf_bypass_spec_v4(void)
+ {
+-	return cpu_mitigations_off() || perfmon_capable();
++	return perfmon_capable() || cpu_mitigations_off();
+ }
+ 
+ int bpf_map_new_fd(struct bpf_map *map, int flags);
+-- 
+2.34.1
+
diff --git a/ci/diffs/0001-arch-Kconfig-Move-SPECULATION_MITIGATIONS-to-arch-Kc.patch b/ci/diffs/0001-arch-Kconfig-Move-SPECULATION_MITIGATIONS-to-arch-Kc.patch
new file mode 100644
index 0000000000000..63bdd28adedd2
--- /dev/null
+++ b/ci/diffs/0001-arch-Kconfig-Move-SPECULATION_MITIGATIONS-to-arch-Kc.patch
@@ -0,0 +1,69 @@
+From c71766e8ff7a7f950522d25896fba758585500df Mon Sep 17 00:00:00 2001
+From: Song Liu <song@kernel.org>
+Date: Mon, 22 Apr 2024 21:14:40 -0700
+Subject: [PATCH] arch/Kconfig: Move SPECULATION_MITIGATIONS to arch/Kconfig
+
+SPECULATION_MITIGATIONS is currently defined only for x86. As a result,
+IS_ENABLED(CONFIG_SPECULATION_MITIGATIONS) is always false for other
+archs. f337a6a21e2f effectively set "mitigations=off" by default on
+non-x86 archs, which is not desired behavior. Jakub observed this
+change when running bpf selftests on s390 and arm64.
+
+Fix this by moving SPECULATION_MITIGATIONS to arch/Kconfig so that it is
+available in all archs and thus can be used safely in kernel/cpu.c
+
+Fixes: f337a6a21e2f ("x86/cpu: Actually turn off mitigations by default for SPECULATION_MITIGATIONS=n")
+Cc: stable@vger.kernel.org
+Cc: Sean Christopherson <seanjc@google.com>
+Cc: Ingo Molnar <mingo@kernel.org>
+Cc: Daniel Sneddon <daniel.sneddon@linux.intel.com>
+Cc: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Song Liu <song@kernel.org>
+---
+ arch/Kconfig     | 10 ++++++++++
+ arch/x86/Kconfig | 10 ----------
+ 2 files changed, 10 insertions(+), 10 deletions(-)
+
+diff --git a/arch/Kconfig b/arch/Kconfig
+index 9f066785bb71..8f4af75005f8 100644
+--- a/arch/Kconfig
++++ b/arch/Kconfig
+@@ -1609,4 +1609,14 @@ config CC_HAS_SANE_FUNCTION_ALIGNMENT
+ 	# strict alignment always, even with -falign-functions.
+ 	def_bool CC_HAS_MIN_FUNCTION_ALIGNMENT || CC_IS_CLANG
+ 
++menuconfig SPECULATION_MITIGATIONS
++	bool "Mitigations for speculative execution vulnerabilities"
++	default y
++	help
++	  Say Y here to enable options which enable mitigations for
++	  speculative execution hardware vulnerabilities.
++
++	  If you say N, all mitigations will be disabled. You really
++	  should know what you are doing to say so.
++
+ endmenu
+diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
+index 39886bab943a..50c890fce5e0 100644
+--- a/arch/x86/Kconfig
++++ b/arch/x86/Kconfig
+@@ -2486,16 +2486,6 @@ config PREFIX_SYMBOLS
+ 	def_bool y
+ 	depends on CALL_PADDING && !CFI_CLANG
+ 
+-menuconfig SPECULATION_MITIGATIONS
+-	bool "Mitigations for speculative execution vulnerabilities"
+-	default y
+-	help
+-	  Say Y here to enable options which enable mitigations for
+-	  speculative execution hardware vulnerabilities.
+-
+-	  If you say N, all mitigations will be disabled. You really
+-	  should know what you are doing to say so.
+-
+ if SPECULATION_MITIGATIONS
+ 
+ config MITIGATION_PAGE_TABLE_ISOLATION
+-- 
+2.43.0
+
diff --git a/ci/diffs/0001-bpf-Fix-a-few-selftest-failures-due-to-llvm18-change.patch b/ci/diffs/0001-bpf-Fix-a-few-selftest-failures-due-to-llvm18-change.patch
new file mode 100644
index 0000000000000..a13d767197413
--- /dev/null
+++ b/ci/diffs/0001-bpf-Fix-a-few-selftest-failures-due-to-llvm18-change.patch
@@ -0,0 +1,94 @@
+From fb9a697860acd8f54f2ba6647923794378eb33da Mon Sep 17 00:00:00 2001
+From: Yonghong Song <yonghong.song@linux.dev>
+Date: Sun, 26 Nov 2023 21:03:42 -0800
+Subject: [PATCH] bpf: Fix a few selftest failures due to llvm18 change
+
+With latest upstream llvm18, the following test cases failed:
+
+  $ ./test_progs -j
+  #13/2    bpf_cookie/multi_kprobe_link_api:FAIL
+  #13/3    bpf_cookie/multi_kprobe_attach_api:FAIL
+  #13      bpf_cookie:FAIL
+  #77      fentry_fexit:FAIL
+  #78/1    fentry_test/fentry:FAIL
+  #78      fentry_test:FAIL
+  #82/1    fexit_test/fexit:FAIL
+  #82      fexit_test:FAIL
+  #112/1   kprobe_multi_test/skel_api:FAIL
+  #112/2   kprobe_multi_test/link_api_addrs:FAIL
+  [...]
+  #112     kprobe_multi_test:FAIL
+  #356/17  test_global_funcs/global_func17:FAIL
+  #356     test_global_funcs:FAIL
+
+Further analysis shows llvm upstream patch [1] is responsible for the above
+failures. For example, for function bpf_fentry_test7() in net/bpf/test_run.c,
+without [1], the asm code is:
+
+  0000000000000400 <bpf_fentry_test7>:
+     400: f3 0f 1e fa                   endbr64
+     404: e8 00 00 00 00                callq   0x409 <bpf_fentry_test7+0x9>
+     409: 48 89 f8                      movq    %rdi, %rax
+     40c: c3                            retq
+     40d: 0f 1f 00                      nopl    (%rax)
+
+... and with [1], the asm code is:
+
+  0000000000005d20 <bpf_fentry_test7.specialized.1>:
+    5d20: e8 00 00 00 00                callq   0x5d25 <bpf_fentry_test7.specialized.1+0x5>
+    5d25: c3                            retq
+
+... and <bpf_fentry_test7.specialized.1> is called instead of <bpf_fentry_test7>
+and this caused test failures for #13/#77 etc. except #356.
+
+For test case #356/17, with [1] (progs/test_global_func17.c)), the main prog
+looks like:
+
+  0000000000000000 <global_func17>:
+       0:       b4 00 00 00 2a 00 00 00 w0 = 0x2a
+       1:       95 00 00 00 00 00 00 00 exit
+
+... which passed verification while the test itself expects a verification
+failure.
+
+Let us add 'barrier_var' style asm code in both places to prevent function
+specialization which caused selftests failure.
+
+  [1] https://github.com/llvm/llvm-project/pull/72903
+
+Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
+Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
+Link: https://lore.kernel.org/bpf/20231127050342.1945270-1-yonghong.song@linux.dev
+---
+ net/bpf/test_run.c                                     | 2 +-
+ tools/testing/selftests/bpf/progs/test_global_func17.c | 1 +
+ 2 files changed, 2 insertions(+), 1 deletion(-)
+
+diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
+index c9fdcc5cdce1..711cf5d59816 100644
+--- a/net/bpf/test_run.c
++++ b/net/bpf/test_run.c
+@@ -542,7 +542,7 @@ struct bpf_fentry_test_t {
+ 
+ int noinline bpf_fentry_test7(struct bpf_fentry_test_t *arg)
+ {
+-	asm volatile ("");
++	asm volatile ("": "+r"(arg));
+ 	return (long)arg;
+ }
+ 
+diff --git a/tools/testing/selftests/bpf/progs/test_global_func17.c b/tools/testing/selftests/bpf/progs/test_global_func17.c
+index a32e11c7d933..5de44b09e8ec 100644
+--- a/tools/testing/selftests/bpf/progs/test_global_func17.c
++++ b/tools/testing/selftests/bpf/progs/test_global_func17.c
+@@ -5,6 +5,7 @@
+ 
+ __noinline int foo(int *p)
+ {
++	barrier_var(p);
+ 	return p ? (*p = 42) : 0;
+ }
+ 
+-- 
+2.34.1
+
diff --git a/ci/diffs/0001-bpf-Fix-a-verifier-bug-due-to-incorrect-branch-offse.patch b/ci/diffs/0001-bpf-Fix-a-verifier-bug-due-to-incorrect-branch-offse.patch
new file mode 100644
index 0000000000000..5832a42664706
--- /dev/null
+++ b/ci/diffs/0001-bpf-Fix-a-verifier-bug-due-to-incorrect-branch-offse.patch
@@ -0,0 +1,67 @@
+From dfce9cb3140592b886838e06f3e0c25fea2a9cae Mon Sep 17 00:00:00 2001
+From: Yonghong Song <yonghong.song@linux.dev>
+Date: Thu, 30 Nov 2023 18:46:40 -0800
+Subject: [PATCH 1/1] bpf: Fix a verifier bug due to incorrect branch offset
+ comparison with cpu=v4
+
+Bpf cpu=v4 support is introduced in [1] and Commit 4cd58e9af8b9
+("bpf: Support new 32bit offset jmp instruction") added support for new
+32bit offset jmp instruction. Unfortunately, in function
+bpf_adj_delta_to_off(), for new branch insn with 32bit offset, the offset
+(plus/minor a small delta) compares to 16-bit offset bound
+[S16_MIN, S16_MAX], which caused the following verification failure:
+  $ ./test_progs-cpuv4 -t verif_scale_pyperf180
+  ...
+  insn 10 cannot be patched due to 16-bit range
+  ...
+  libbpf: failed to load object 'pyperf180.bpf.o'
+  scale_test:FAIL:expect_success unexpected error: -12 (errno 12)
+  #405     verif_scale_pyperf180:FAIL
+
+Note that due to recent llvm18 development, the patch [2] (already applied
+in bpf-next) needs to be applied to bpf tree for testing purpose.
+
+The fix is rather simple. For 32bit offset branch insn, the adjusted
+offset compares to [S32_MIN, S32_MAX] and then verification succeeded.
+
+  [1] https://lore.kernel.org/all/20230728011143.3710005-1-yonghong.song@linux.dev
+  [2] https://lore.kernel.org/bpf/20231110193644.3130906-1-yonghong.song@linux.dev
+
+Fixes: 4cd58e9af8b9 ("bpf: Support new 32bit offset jmp instruction")
+Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
+Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
+Link: https://lore.kernel.org/bpf/20231201024640.3417057-1-yonghong.song@linux.dev
+---
+ kernel/bpf/core.c | 12 ++++++++----
+ 1 file changed, 8 insertions(+), 4 deletions(-)
+
+diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
+index cd3afe57ece3..fe254ae035fe 100644
+--- a/kernel/bpf/core.c
++++ b/kernel/bpf/core.c
+@@ -371,14 +371,18 @@ static int bpf_adj_delta_to_imm(struct bpf_insn *insn, u32 pos, s32 end_old,
+ static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, s32 end_old,
+ 				s32 end_new, s32 curr, const bool probe_pass)
+ {
+-	const s32 off_min = S16_MIN, off_max = S16_MAX;
++	s64 off_min, off_max, off;
+ 	s32 delta = end_new - end_old;
+-	s32 off;
+ 
+-	if (insn->code == (BPF_JMP32 | BPF_JA))
++	if (insn->code == (BPF_JMP32 | BPF_JA)) {
+ 		off = insn->imm;
+-	else
++		off_min = S32_MIN;
++		off_max = S32_MAX;
++	} else {
+ 		off = insn->off;
++		off_min = S16_MIN;
++		off_max = S16_MAX;
++	}
+ 
+ 	if (curr < pos && curr + off + 1 >= end_old)
+ 		off += delta;
+-- 
+2.34.1
+
diff --git a/ci/diffs/0001-bpf-next-selftests-bpf-Fix-a-btf_dump-selftest-failure.patch b/ci/diffs/0001-bpf-next-selftests-bpf-Fix-a-btf_dump-selftest-failure.patch
new file mode 100644
index 0000000000000..ea6b2386d0345
--- /dev/null
+++ b/ci/diffs/0001-bpf-next-selftests-bpf-Fix-a-btf_dump-selftest-failure.patch
@@ -0,0 +1,40 @@
+From patchwork Fri Aug  2 18:54:34 2024
+From: Yonghong Song <yonghong.song@linux.dev>
+Subject: [PATCH bpf-next] selftests/bpf: Fix a btf_dump selftest failure
+
+Jakub reported bpf selftest "btf_dump" failure after forwarding to
+v6.11-rc1 with netdev.
+  Error: #33 btf_dump
+  Error: #33/15 btf_dump/btf_dump: var_data
+    btf_dump_data:FAIL:find type id unexpected find type id: actual -2 < expected 0
+
+The reason for the failure is due to
+  commit 94ede2a3e913 ("profiling: remove stale percpu flip buffer variables")
+where percpu static variable "cpu_profile_flip" is removed.
+
+Let us replace "cpu_profile_flip" with a variable in bpf subsystem
+so whenever that variable gets deleted or renamed, we can detect the
+failure immediately. In this case, I picked a static percpu variable
+"bpf_cgrp_storage_busy" which is defined in kernel/bpf/bpf_cgrp_storage.c.
+
+Reported-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
+---
+ tools/testing/selftests/bpf/prog_tests/btf_dump.c | 4 ++--
+ 1 file changed, 2 insertions(+), 2 deletions(-)
+
+diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
+index 09a8e6f9b379..b293b8501fd6 100644
+--- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c
++++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
+@@ -805,8 +805,8 @@ static void test_btf_dump_var_data(struct btf *btf, struct btf_dump *d,
+ 	TEST_BTF_DUMP_VAR(btf, d, NULL, str, "cpu_number", int, BTF_F_COMPACT,
+ 			  "int cpu_number = (int)100", 100);
+ #endif
+-	TEST_BTF_DUMP_VAR(btf, d, NULL, str, "cpu_profile_flip", int, BTF_F_COMPACT,
+-			  "static int cpu_profile_flip = (int)2", 2);
++	TEST_BTF_DUMP_VAR(btf, d, NULL, str, "bpf_cgrp_storage_busy", int, BTF_F_COMPACT,
++			  "static int bpf_cgrp_storage_busy = (int)2", 2);
+ }
+ 
+ static void test_btf_datasec(struct btf *btf, struct btf_dump *d, char *str,
diff --git a/ci/diffs/0001-net-bpf-Use-sockopt_lock_sock-in-ip_sock_set_tos.patch b/ci/diffs/0001-net-bpf-Use-sockopt_lock_sock-in-ip_sock_set_tos.patch
new file mode 100644
index 0000000000000..bd12bd9b3fba5
--- /dev/null
+++ b/ci/diffs/0001-net-bpf-Use-sockopt_lock_sock-in-ip_sock_set_tos.patch
@@ -0,0 +1,99 @@
+From c8268f8e9fa33c32e1f2f86fc7b703408a396c70 Mon Sep 17 00:00:00 2001
+From: Yonghong Song <yonghong.song@linux.dev>
+Date: Fri, 27 Oct 2023 11:24:24 -0700
+Subject: [PATCH] net: bpf: Use sockopt_lock_sock() in ip_sock_set_tos()
+
+With latest sync from net-next tree, bpf-next has a bpf selftest failure:
+  [root@arch-fb-vm1 bpf]# ./test_progs -t setget_sockopt
+  ...
+  [   76.194349] ============================================
+  [   76.194682] WARNING: possible recursive locking detected
+  [   76.195039] 6.6.0-rc7-g37884503df08-dirty #67 Tainted: G        W  OE
+  [   76.195518] --------------------------------------------
+  [   76.195852] new_name/154 is trying to acquire lock:
+  [   76.196159] ffff8c3e06ad8d30 (sk_lock-AF_INET){+.+.}-{0:0}, at: ip_sock_set_tos+0x19/0x30
+  [   76.196669]
+  [   76.196669] but task is already holding lock:
+  [   76.197028] ffff8c3e06ad8d30 (sk_lock-AF_INET){+.+.}-{0:0}, at: inet_listen+0x21/0x70
+  [   76.197517]
+  [   76.197517] other info that might help us debug this:
+  [   76.197919]  Possible unsafe locking scenario:
+  [   76.197919]
+  [   76.198287]        CPU0
+  [   76.198444]        ----
+  [   76.198600]   lock(sk_lock-AF_INET);
+  [   76.198831]   lock(sk_lock-AF_INET);
+  [   76.199062]
+  [   76.199062]  *** DEADLOCK ***
+  [   76.199062]
+  [   76.199420]  May be due to missing lock nesting notation
+  [   76.199420]
+  [   76.199879] 2 locks held by new_name/154:
+  [   76.200131]  #0: ffff8c3e06ad8d30 (sk_lock-AF_INET){+.+.}-{0:0}, at: inet_listen+0x21/0x70
+  [   76.200644]  #1: ffffffff90f96a40 (rcu_read_lock){....}-{1:2}, at: __cgroup_bpf_run_filter_sock_ops+0x55/0x290
+  [   76.201268]
+  [   76.201268] stack backtrace:
+  [   76.201538] CPU: 4 PID: 154 Comm: new_name Tainted: G        W  OE      6.6.0-rc7-g37884503df08-dirty #67
+  [   76.202134] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014
+  [   76.202699] Call Trace:
+  [   76.202858]  <TASK>
+  [   76.203002]  dump_stack_lvl+0x4b/0x80
+  [   76.203239]  __lock_acquire+0x740/0x1ec0
+  [   76.203503]  lock_acquire+0xc1/0x2a0
+  [   76.203766]  ? ip_sock_set_tos+0x19/0x30
+  [   76.204050]  ? sk_stream_write_space+0x12a/0x230
+  [   76.204389]  ? lock_release+0xbe/0x260
+  [   76.204661]  lock_sock_nested+0x32/0x80
+  [   76.204942]  ? ip_sock_set_tos+0x19/0x30
+  [   76.205208]  ip_sock_set_tos+0x19/0x30
+  [   76.205452]  do_ip_setsockopt+0x4b3/0x1580
+  [   76.205719]  __bpf_setsockopt+0x62/0xa0
+  [   76.205963]  bpf_sock_ops_setsockopt+0x11/0x20
+  [   76.206247]  bpf_prog_630217292049c96e_bpf_test_sockopt_int+0xbc/0x123
+  [   76.206660]  bpf_prog_493685a3bae00bbd_bpf_test_ip_sockopt+0x49/0x4b
+  [   76.207055]  bpf_prog_b0bcd27f269aeea0_skops_sockopt+0x44c/0xec7
+  [   76.207437]  __cgroup_bpf_run_filter_sock_ops+0xda/0x290
+  [   76.207829]  __inet_listen_sk+0x108/0x1b0
+  [   76.208122]  inet_listen+0x48/0x70
+  [   76.208373]  __sys_listen+0x74/0xb0
+  [   76.208630]  __x64_sys_listen+0x16/0x20
+  [   76.208911]  do_syscall_64+0x3f/0x90
+  [   76.209174]  entry_SYSCALL_64_after_hwframe+0x6e/0xd8
+  ...
+
+Both ip_sock_set_tos() and inet_listen() calls lock_sock(sk) which
+caused a dead lock.
+
+To fix the issue, use sockopt_lock_sock() in ip_sock_set_tos()
+instead. sockopt_lock_sock() will avoid lock_sock() if it is in bpf
+context.
+
+Fixes: 878d951c6712 ("inet: lock the socket in ip_sock_set_tos()")
+Suggested-by: Martin KaFai Lau <martin.lau@kernel.org>
+Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
+Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
+Reviewed-by: Eric Dumazet <edumazet@google.com>
+Link: https://lore.kernel.org/bpf/20231027182424.1444845-1-yonghong.song@linux.dev
+---
+ net/ipv4/ip_sockglue.c | 4 ++--
+ 1 file changed, 2 insertions(+), 2 deletions(-)
+
+diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
+index 9c68b6b74d9f..2efc53526a38 100644
+--- a/net/ipv4/ip_sockglue.c
++++ b/net/ipv4/ip_sockglue.c
+@@ -602,9 +602,9 @@ void __ip_sock_set_tos(struct sock *sk, int val)
+ 
+ void ip_sock_set_tos(struct sock *sk, int val)
+ {
+-	lock_sock(sk);
++	sockopt_lock_sock(sk);
+ 	__ip_sock_set_tos(sk, val);
+-	release_sock(sk);
++	sockopt_release_sock(sk);
+ }
+ EXPORT_SYMBOL(ip_sock_set_tos);
+ 
+-- 
+2.34.1
+
diff --git a/ci/diffs/0001-selftests-bpf-Filter-out-_GNU_SOURCE-when-compiling-.patch b/ci/diffs/0001-selftests-bpf-Filter-out-_GNU_SOURCE-when-compiling-.patch
new file mode 100644
index 0000000000000..da5bcdc455967
--- /dev/null
+++ b/ci/diffs/0001-selftests-bpf-Filter-out-_GNU_SOURCE-when-compiling-.patch
@@ -0,0 +1,51 @@
+From 41c24102af7b6236277a214428b203d51a3462df Mon Sep 17 00:00:00 2001
+From: Stanislav Fomichev <sdf@fomichev.me>
+Date: Thu, 25 Jul 2024 14:40:29 -0700
+Subject: [PATCH 1/1] selftests/bpf: Filter out _GNU_SOURCE when compiling
+ test_cpp
+
+Jakub reports build failures when merging linux/master with net tree:
+
+CXX      test_cpp
+In file included from <built-in>:454:
+<command line>:2:9: error: '_GNU_SOURCE' macro redefined [-Werror,-Wmacro-redefined]
+    2 | #define _GNU_SOURCE
+      |         ^
+<built-in>:445:9: note: previous definition is here
+  445 | #define _GNU_SOURCE 1
+
+The culprit is commit cc937dad85ae ("selftests: centralize -D_GNU_SOURCE= to
+CFLAGS in lib.mk") which unconditionally added -D_GNU_SOUCE to CLFAGS.
+Apparently clang++ also unconditionally adds it for the C++ targets [0]
+which causes a conflict. Add small change in the selftests makefile
+to filter it out for test_cpp.
+
+Not sure which tree it should go via, targeting bpf for now, but net
+might be better?
+
+0: https://stackoverflow.com/questions/11670581/why-is-gnu-source-defined-by-default-and-how-to-turn-it-off
+
+Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
+Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
+Acked-by: Jiri Olsa <jolsa@kernel.org>
+Link: https://lore.kernel.org/bpf/20240725214029.1760809-1-sdf@fomichev.me
+---
+ tools/testing/selftests/bpf/Makefile | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
+index dd49c1d23a60..81d4757ecd4c 100644
+--- a/tools/testing/selftests/bpf/Makefile
++++ b/tools/testing/selftests/bpf/Makefile
+@@ -713,7 +713,7 @@ $(OUTPUT)/xdp_features: xdp_features.c $(OUTPUT)/network_helpers.o $(OUTPUT)/xdp
+ # Make sure we are able to include and link libbpf against c++.
+ $(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ)
+ 	$(call msg,CXX,,$@)
+-	$(Q)$(CXX) $(CFLAGS) $(filter %.a %.o %.cpp,$^) $(LDLIBS) -o $@
++	$(Q)$(CXX) $(subst -D_GNU_SOURCE=,,$(CFLAGS)) $(filter %.a %.o %.cpp,$^) $(LDLIBS) -o $@
+ 
+ # Benchmark runner
+ $(OUTPUT)/bench_%.o: benchs/bench_%.c bench.h $(BPFOBJ)
+-- 
+2.43.0
+
diff --git a/ci/diffs/0001-selftests-bpf-Fix-bpf_cookie-and-find_vma-in-nested-.patch b/ci/diffs/0001-selftests-bpf-Fix-bpf_cookie-and-find_vma-in-nested-.patch
new file mode 100644
index 0000000000000..4ebfe20b24707
--- /dev/null
+++ b/ci/diffs/0001-selftests-bpf-Fix-bpf_cookie-and-find_vma-in-nested-.patch
@@ -0,0 +1,50 @@
+From f3d2080e8cf23125f79e345061149ae40f66816f Mon Sep 17 00:00:00 2001
+From: Song Liu <song@kernel.org>
+Date: Mon, 3 Jun 2024 23:43:17 -0700
+Subject: [PATCH bpf-next] selftests/bpf: Fix bpf_cookie and find_vma in nested
+ VM
+
+bpf_cookie and find_vma are flaky in nested VMs, which is used by some CI
+systems. It turns out these failures are caused by unreliable perf event
+in nested VM. Fix these by:
+
+  1. Use PERF_COUNT_SW_CPU_CLOCK in find_vma;
+  2. Increase sample_freq in bpf_cookie.
+
+Signed-off-by: Song Liu <song@kernel.org>
+---
+ tools/testing/selftests/bpf/prog_tests/bpf_cookie.c | 2 +-
+ tools/testing/selftests/bpf/prog_tests/find_vma.c   | 4 ++--
+ 2 files changed, 3 insertions(+), 3 deletions(-)
+
+diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
+index 4407ea428e77..070c52c312e5 100644
+--- a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
++++ b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
+@@ -451,7 +451,7 @@ static void pe_subtest(struct test_bpf_cookie *skel)
+ 	attr.type = PERF_TYPE_SOFTWARE;
+ 	attr.config = PERF_COUNT_SW_CPU_CLOCK;
+ 	attr.freq = 1;
+-	attr.sample_freq = 1000;
++	attr.sample_freq = 10000;
+ 	pfd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC);
+ 	if (!ASSERT_GE(pfd, 0, "perf_fd"))
+ 		goto cleanup;
+diff --git a/tools/testing/selftests/bpf/prog_tests/find_vma.c b/tools/testing/selftests/bpf/prog_tests/find_vma.c
+index 5165b38f0e59..f7619e0ade10 100644
+--- a/tools/testing/selftests/bpf/prog_tests/find_vma.c
++++ b/tools/testing/selftests/bpf/prog_tests/find_vma.c
+@@ -29,8 +29,8 @@ static int open_pe(void)
+ 
+ 	/* create perf event */
+ 	attr.size = sizeof(attr);
+-	attr.type = PERF_TYPE_HARDWARE;
+-	attr.config = PERF_COUNT_HW_CPU_CYCLES;
++	attr.type = PERF_TYPE_SOFTWARE;
++	attr.config = PERF_COUNT_SW_CPU_CLOCK;
+ 	attr.freq = 1;
+ 	attr.sample_freq = 1000;
+ 	pfd = syscall(__NR_perf_event_open, &attr, 0, -1, -1, PERF_FLAG_FD_CLOEXEC);
+-- 
+2.43.0
+
diff --git a/ci/diffs/0001-selftests-bpf-Fix-pyperf180-compilation-failure-with.patch b/ci/diffs/0001-selftests-bpf-Fix-pyperf180-compilation-failure-with.patch
new file mode 100644
index 0000000000000..d55d2e7af8651
--- /dev/null
+++ b/ci/diffs/0001-selftests-bpf-Fix-pyperf180-compilation-failure-with.patch
@@ -0,0 +1,78 @@
+From 100888fb6d8a185866b1520031ee7e3182b173de Mon Sep 17 00:00:00 2001
+From: Yonghong Song <yonghong.song@linux.dev>
+Date: Fri, 10 Nov 2023 11:36:44 -0800
+Subject: [PATCH] selftests/bpf: Fix pyperf180 compilation failure with clang18
+
+With latest clang18 (main branch of llvm-project repo), when building bpf selftests,
+    [~/work/bpf-next (master)]$ make -C tools/testing/selftests/bpf LLVM=1 -j
+
+The following compilation error happens:
+    fatal error: error in backend: Branch target out of insn range
+    ...
+    Stack dump:
+    0.      Program arguments: clang -g -Wall -Werror -D__TARGET_ARCH_x86 -mlittle-endian
+      -I/home/yhs/work/bpf-next/tools/testing/selftests/bpf/tools/include
+      -I/home/yhs/work/bpf-next/tools/testing/selftests/bpf -I/home/yhs/work/bpf-next/tools/include/uapi
+      -I/home/yhs/work/bpf-next/tools/testing/selftests/usr/include -idirafter
+      /home/yhs/work/llvm-project/llvm/build.18/install/lib/clang/18/include -idirafter /usr/local/include
+      -idirafter /usr/include -Wno-compare-distinct-pointer-types -DENABLE_ATOMICS_TESTS -O2 --target=bpf
+      -c progs/pyperf180.c -mcpu=v3 -o /home/yhs/work/bpf-next/tools/testing/selftests/bpf/pyperf180.bpf.o
+    1.      <eof> parser at end of file
+    2.      Code generation
+    ...
+
+The compilation failure only happens to cpu=v2 and cpu=v3. cpu=v4 is okay
+since cpu=v4 supports 32-bit branch target offset.
+
+The above failure is due to upstream llvm patch [1] where some inlining behavior
+are changed in clang18.
+
+To workaround the issue, previously all 180 loop iterations are fully unrolled.
+The bpf macro __BPF_CPU_VERSION__ (implemented in clang18 recently) is used to avoid
+unrolling changes if cpu=v4. If __BPF_CPU_VERSION__ is not available and the
+compiler is clang18, the unrollng amount is unconditionally reduced.
+
+  [1] https://github.com/llvm/llvm-project/commit/1a2e77cf9e11dbf56b5720c607313a566eebb16e
+
+Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
+Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
+Tested-by: Alan Maguire <alan.maguire@oracle.com>
+Link: https://lore.kernel.org/bpf/20231110193644.3130906-1-yonghong.song@linux.dev
+---
+ tools/testing/selftests/bpf/progs/pyperf180.c | 22 +++++++++++++++++++
+ 1 file changed, 22 insertions(+)
+
+diff --git a/tools/testing/selftests/bpf/progs/pyperf180.c b/tools/testing/selftests/bpf/progs/pyperf180.c
+index c39f559d3100..42c4a8b62e36 100644
+--- a/tools/testing/selftests/bpf/progs/pyperf180.c
++++ b/tools/testing/selftests/bpf/progs/pyperf180.c
+@@ -1,4 +1,26 @@
+ // SPDX-License-Identifier: GPL-2.0
+ // Copyright (c) 2019 Facebook
+ #define STACK_MAX_LEN 180
++
++/* llvm upstream commit at clang18
++ *   https://github.com/llvm/llvm-project/commit/1a2e77cf9e11dbf56b5720c607313a566eebb16e
++ * changed inlining behavior and caused compilation failure as some branch
++ * target distance exceeded 16bit representation which is the maximum for
++ * cpu v1/v2/v3. Macro __BPF_CPU_VERSION__ is later implemented in clang18
++ * to specify which cpu version is used for compilation. So a smaller
++ * unroll_count can be set if __BPF_CPU_VERSION__ is less than 4, which
++ * reduced some branch target distances and resolved the compilation failure.
++ *
++ * To capture the case where a developer/ci uses clang18 but the corresponding
++ * repo checkpoint does not have __BPF_CPU_VERSION__, a smaller unroll_count
++ * will be set as well to prevent potential compilation failures.
++ */
++#ifdef __BPF_CPU_VERSION__
++#if __BPF_CPU_VERSION__ < 4
++#define UNROLL_COUNT 90
++#endif
++#elif __clang_major__ == 18
++#define UNROLL_COUNT 90
++#endif
++
+ #include "pyperf.h"
+-- 
+2.34.1
+
diff --git a/ci/diffs/0001-selftests-bpf-disable-detection-of-llvm-when-buildin.patch b/ci/diffs/0001-selftests-bpf-disable-detection-of-llvm-when-buildin.patch
new file mode 100644
index 0000000000000..6497a6cc38c90
--- /dev/null
+++ b/ci/diffs/0001-selftests-bpf-disable-detection-of-llvm-when-buildin.patch
@@ -0,0 +1,41 @@
+From 42839864a62ee244ec280b09149b1cb439f681db Mon Sep 17 00:00:00 2001
+From: Manu Bretelle <chantr4@gmail.com>
+Date: Fri, 27 Oct 2023 18:25:39 -0700
+Subject: [PATCH bpf-next] selftests/bpf: disable detection of llvm when
+ building bpftool
+
+The VMs in which we run the selftests do not have llvm installed.
+We build selftests/bpftool in a host that have llvm.
+bpftool currently will use llvm first and fallback to libbfd but there
+is no way to disable detection from the command line.
+
+Removing it from the feature detection should force us to use libbfd.
+
+Signed-off-by: Manu Bretelle <chantr4@gmail.com>
+---
+ tools/bpf/bpftool/Makefile | 2 --
+ 1 file changed, 2 deletions(-)
+
+diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
+index e9154ace80ff..01314458e25e 100644
+--- a/tools/bpf/bpftool/Makefile
++++ b/tools/bpf/bpftool/Makefile
+@@ -95,7 +95,6 @@ RM ?= rm -f
+ FEATURE_USER = .bpftool
+ 
+ FEATURE_TESTS := clang-bpf-co-re
+-FEATURE_TESTS += llvm
+ FEATURE_TESTS += libcap
+ FEATURE_TESTS += libbfd
+ FEATURE_TESTS += libbfd-liberty
+@@ -104,7 +103,6 @@ FEATURE_TESTS += disassembler-four-args
+ FEATURE_TESTS += disassembler-init-styled
+ 
+ FEATURE_DISPLAY := clang-bpf-co-re
+-FEATURE_DISPLAY += llvm
+ FEATURE_DISPLAY += libcap
+ FEATURE_DISPLAY += libbfd
+ FEATURE_DISPLAY += libbfd-liberty
+-- 
+2.39.3
+
diff --git a/ci/diffs/0001-selftests-bpf-fix-inet_csk_accept-prototype-in-test_.patch b/ci/diffs/0001-selftests-bpf-fix-inet_csk_accept-prototype-in-test_.patch
new file mode 100644
index 0000000000000..3fa007c51db68
--- /dev/null
+++ b/ci/diffs/0001-selftests-bpf-fix-inet_csk_accept-prototype-in-test_.patch
@@ -0,0 +1,32 @@
+From 0daad0a615e687e1247230f3d0c31ae60ba32314 Mon Sep 17 00:00:00 2001
+From: Andrii Nakryiko <andrii@kernel.org>
+Date: Tue, 28 May 2024 15:29:38 -0700
+Subject: [PATCH bpf-next] selftests/bpf: fix inet_csk_accept prototype in
+ test_sk_storage_tracing.c
+
+Recent kernel change ([0]) changed inet_csk_accept() prototype. Adapt
+progs/test_sk_storage_tracing.c to take that into account.
+
+  [0] 92ef0fd55ac8 ("net: change proto and proto_ops accept type")
+
+Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
+---
+ tools/testing/selftests/bpf/progs/test_sk_storage_tracing.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/tools/testing/selftests/bpf/progs/test_sk_storage_tracing.c b/tools/testing/selftests/bpf/progs/test_sk_storage_tracing.c
+index 02e718f06e0f..40531e56776e 100644
+--- a/tools/testing/selftests/bpf/progs/test_sk_storage_tracing.c
++++ b/tools/testing/selftests/bpf/progs/test_sk_storage_tracing.c
+@@ -84,7 +84,7 @@ int BPF_PROG(trace_tcp_connect, struct sock *sk)
+ }
+ 
+ SEC("fexit/inet_csk_accept")
+-int BPF_PROG(inet_csk_accept, struct sock *sk, int flags, int *err, bool kern,
++int BPF_PROG(inet_csk_accept, struct sock *sk, struct proto_accept_arg *arg,
+ 	     struct sock *accepted_sk)
+ {
+ 	set_task_info(accepted_sk);
+-- 
+2.43.0
+
diff --git a/ci/diffs/0001-selftests-bpf-work-around-latest-Clang-smartness.patch b/ci/diffs/0001-selftests-bpf-work-around-latest-Clang-smartness.patch
new file mode 100644
index 0000000000000..ec1e29a8ab974
--- /dev/null
+++ b/ci/diffs/0001-selftests-bpf-work-around-latest-Clang-smartness.patch
@@ -0,0 +1,31 @@
+From d31a7125891994681503770cff46a119692fb2b9 Mon Sep 17 00:00:00 2001
+From: Andrii Nakryiko <andrii@kernel.org>
+Date: Mon, 11 Dec 2023 17:09:38 -0800
+Subject: [PATCH 1/1] selftests/bpf: work around latest Clang smartness
+
+Work around the issue while we deal with it in the Clang itself.
+See [0].
+
+  [0] https://github.com/llvm/llvm-project/pull/73662#issuecomment-1849281758
+
+Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
+---
+ tools/testing/selftests/bpf/progs/iters.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c
+index 3aca3dc145b5..929ba6fa2105 100644
+--- a/tools/testing/selftests/bpf/progs/iters.c
++++ b/tools/testing/selftests/bpf/progs/iters.c
+@@ -1420,7 +1420,7 @@ SEC("raw_tp")
+ __success
+ int iter_arr_with_actual_elem_count(const void *ctx)
+ {
+-	int i, n = loop_data.n, sum = 0;
++	unsigned i, n = loop_data.n, sum = 0;
+ 
+ 	if (n > ARRAY_SIZE(loop_data.data))
+ 		return 0;
+-- 
+2.34.1
+
diff --git a/ci/diffs/0001-selftests-bpf-xskxceiver-ksft_print_msg-fix-format-t.patch b/ci/diffs/0001-selftests-bpf-xskxceiver-ksft_print_msg-fix-format-t.patch
new file mode 100644
index 0000000000000..e631fac0cc698
--- /dev/null
+++ b/ci/diffs/0001-selftests-bpf-xskxceiver-ksft_print_msg-fix-format-t.patch
@@ -0,0 +1,89 @@
+From fe69a1b1b6ed9ffc2c578c63f526026a8ab74f0c Mon Sep 17 00:00:00 2001
+From: Anders Roxell <anders.roxell@linaro.org>
+Date: Thu, 9 Nov 2023 18:43:28 +0100
+Subject: [PATCH] selftests: bpf: xskxceiver: ksft_print_msg: fix format type
+ error
+
+Crossbuilding selftests/bpf for architecture arm64, format specifies
+type error show up like.
+
+xskxceiver.c:912:34: error: format specifies type 'int' but the argument
+has type '__u64' (aka 'unsigned long long') [-Werror,-Wformat]
+ ksft_print_msg("[%s] expected meta_count [%d], got meta_count [%d]\n",
+                                                                ~~
+                                                                %llu
+                __func__, pkt->pkt_nb, meta->count);
+                                       ^~~~~~~~~~~
+xskxceiver.c:929:55: error: format specifies type 'unsigned long long' but
+ the argument has type 'u64' (aka 'unsigned long') [-Werror,-Wformat]
+ ksft_print_msg("Frag invalid addr: %llx len: %u\n", addr, len);
+                                    ~~~~             ^~~~
+
+Fixing the issues by casting to (unsigned long long) and changing the
+specifiers to be %llu from %d and %u, since with u64s it might be %llx
+or %lx, depending on architecture.
+
+Signed-off-by: Anders Roxell <anders.roxell@linaro.org>
+Link: https://lore.kernel.org/r/20231109174328.1774571-1-anders.roxell@linaro.org
+Signed-off-by: Alexei Starovoitov <ast@kernel.org>
+---
+ tools/testing/selftests/bpf/xskxceiver.c | 19 ++++++++++++-------
+ 1 file changed, 12 insertions(+), 7 deletions(-)
+
+diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
+index 591ca9637b23..b604c570309a 100644
+--- a/tools/testing/selftests/bpf/xskxceiver.c
++++ b/tools/testing/selftests/bpf/xskxceiver.c
+@@ -908,8 +908,9 @@ static bool is_metadata_correct(struct pkt *pkt, void *buffer, u64 addr)
+ 	struct xdp_info *meta = data - sizeof(struct xdp_info);
+ 
+ 	if (meta->count != pkt->pkt_nb) {
+-		ksft_print_msg("[%s] expected meta_count [%d], got meta_count [%d]\n",
+-			       __func__, pkt->pkt_nb, meta->count);
++		ksft_print_msg("[%s] expected meta_count [%d], got meta_count [%llu]\n",
++			       __func__, pkt->pkt_nb,
++			       (unsigned long long)meta->count);
+ 		return false;
+ 	}
+ 
+@@ -926,11 +927,13 @@ static bool is_frag_valid(struct xsk_umem_info *umem, u64 addr, u32 len, u32 exp
+ 
+ 	if (addr >= umem->num_frames * umem->frame_size ||
+ 	    addr + len > umem->num_frames * umem->frame_size) {
+-		ksft_print_msg("Frag invalid addr: %llx len: %u\n", addr, len);
++		ksft_print_msg("Frag invalid addr: %llx len: %u\n",
++			       (unsigned long long)addr, len);
+ 		return false;
+ 	}
+ 	if (!umem->unaligned_mode && addr % umem->frame_size + len > umem->frame_size) {
+-		ksft_print_msg("Frag crosses frame boundary addr: %llx len: %u\n", addr, len);
++		ksft_print_msg("Frag crosses frame boundary addr: %llx len: %u\n",
++			       (unsigned long long)addr, len);
+ 		return false;
+ 	}
+ 
+@@ -1029,7 +1032,8 @@ static int complete_pkts(struct xsk_socket_info *xsk, int batch_size)
+ 			u64 addr = *xsk_ring_cons__comp_addr(&xsk->umem->cq, idx + rcvd - 1);
+ 
+ 			ksft_print_msg("[%s] Too many packets completed\n", __func__);
+-			ksft_print_msg("Last completion address: %llx\n", addr);
++			ksft_print_msg("Last completion address: %llx\n",
++				       (unsigned long long)addr);
+ 			return TEST_FAILURE;
+ 		}
+ 
+@@ -1513,8 +1517,9 @@ static int validate_tx_invalid_descs(struct ifobject *ifobject)
+ 	}
+ 
+ 	if (stats.tx_invalid_descs != ifobject->xsk->pkt_stream->nb_pkts / 2) {
+-		ksft_print_msg("[%s] tx_invalid_descs incorrect. Got [%u] expected [%u]\n",
+-			       __func__, stats.tx_invalid_descs,
++		ksft_print_msg("[%s] tx_invalid_descs incorrect. Got [%llu] expected [%u]\n",
++			       __func__,
++			       (unsigned long long)stats.tx_invalid_descs,
+ 			       ifobject->xsk->pkt_stream->nb_pkts);
+ 		return TEST_FAILURE;
+ 	}
+-- 
+2.34.1
+
diff --git a/ci/diffs/0001-tools-resolve_btfids-fix-cross-compilation-to-non-host-endianness.patch b/ci/diffs/0001-tools-resolve_btfids-fix-cross-compilation-to-non-host-endianness.patch
new file mode 100644
index 0000000000000..19d269de7e8ca
--- /dev/null
+++ b/ci/diffs/0001-tools-resolve_btfids-fix-cross-compilation-to-non-host-endianness.patch
@@ -0,0 +1,142 @@
+From 3772e6cdb51f21a11df2acf6aa431cc8b9137bfb Mon Sep 17 00:00:00 2001
+From: Viktor Malik <vmalik@redhat.com>
+Date: Tue, 6 Feb 2024 13:46:09 +0100
+Subject: [PATCH 1/2] tools/resolve_btfids: Refactor set sorting with types
+ from btf_ids.h
+
+Instead of using magic offsets to access BTF ID set data, leverage types
+from btf_ids.h (btf_id_set and btf_id_set8) which define the actual
+layout of the data. Thanks to this change, set sorting should also
+continue working if the layout changes.
+
+This requires to sync the definition of 'struct btf_id_set8' from
+include/linux/btf_ids.h to tools/include/linux/btf_ids.h. We don't sync
+the rest of the file at the moment, b/c that would require to also sync
+multiple dependent headers and we don't need any other defs from
+btf_ids.h.
+
+Signed-off-by: Viktor Malik <vmalik@redhat.com>
+Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
+Acked-by: Daniel Xu <dxu@dxuuu.xyz>
+Link: https://lore.kernel.org/bpf/ff7f062ddf6a00815fda3087957c4ce667f50532.1707223196.git.vmalik@redhat.com
+---
+ tools/bpf/resolve_btfids/main.c | 35 ++++++++++++++++++++-------------
+ tools/include/linux/btf_ids.h   |  9 +++++++++
+ 2 files changed, 30 insertions(+), 14 deletions(-)
+
+diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c
+index 27a23196d58e..32634f00abba 100644
+--- a/tools/bpf/resolve_btfids/main.c
++++ b/tools/bpf/resolve_btfids/main.c
+@@ -70,6 +70,7 @@
+ #include <sys/stat.h>
+ #include <fcntl.h>
+ #include <errno.h>
++#include <linux/btf_ids.h>
+ #include <linux/rbtree.h>
+ #include <linux/zalloc.h>
+ #include <linux/err.h>
+@@ -78,7 +79,7 @@
+ #include <subcmd/parse-options.h>
+ 
+ #define BTF_IDS_SECTION	".BTF_ids"
+-#define BTF_ID		"__BTF_ID__"
++#define BTF_ID_PREFIX	"__BTF_ID__"
+ 
+ #define BTF_STRUCT	"struct"
+ #define BTF_UNION	"union"
+@@ -161,7 +162,7 @@ static int eprintf(int level, int var, const char *fmt, ...)
+ 
+ static bool is_btf_id(const char *name)
+ {
+-	return name && !strncmp(name, BTF_ID, sizeof(BTF_ID) - 1);
++	return name && !strncmp(name, BTF_ID_PREFIX, sizeof(BTF_ID_PREFIX) - 1);
+ }
+ 
+ static struct btf_id *btf_id__find(struct rb_root *root, const char *name)
+@@ -441,7 +442,7 @@ static int symbols_collect(struct object *obj)
+ 		 * __BTF_ID__TYPE__vfs_truncate__0
+ 		 * prefix =  ^
+ 		 */
+-		prefix = name + sizeof(BTF_ID) - 1;
++		prefix = name + sizeof(BTF_ID_PREFIX) - 1;
+ 
+ 		/* struct */
+ 		if (!strncmp(prefix, BTF_STRUCT, sizeof(BTF_STRUCT) - 1)) {
+@@ -649,19 +650,18 @@ static int cmp_id(const void *pa, const void *pb)
+ static int sets_patch(struct object *obj)
+ {
+ 	Elf_Data *data = obj->efile.idlist;
+-	int *ptr = data->d_buf;
+ 	struct rb_node *next;
+ 
+ 	next = rb_first(&obj->sets);
+ 	while (next) {
+-		unsigned long addr, idx;
++		struct btf_id_set8 *set8;
++		struct btf_id_set *set;
++		unsigned long addr, off;
+ 		struct btf_id *id;
+-		int *base;
+-		int cnt;
+ 
+ 		id   = rb_entry(next, struct btf_id, rb_node);
+ 		addr = id->addr[0];
+-		idx  = addr - obj->efile.idlist_addr;
++		off = addr - obj->efile.idlist_addr;
+ 
+ 		/* sets are unique */
+ 		if (id->addr_cnt != 1) {
+@@ -670,14 +670,21 @@ static int sets_patch(struct object *obj)
+ 			return -1;
+ 		}
+ 
+-		idx = idx / sizeof(int);
+-		base = &ptr[idx] + (id->is_set8 ? 2 : 1);
+-		cnt = ptr[idx];
++		if (id->is_set) {
++			set = data->d_buf + off;
++			qsort(set->ids, set->cnt, sizeof(set->ids[0]), cmp_id);
++		} else {
++			set8 = data->d_buf + off;
++			/*
++			 * Make sure id is at the beginning of the pairs
++			 * struct, otherwise the below qsort would not work.
++			 */
++			BUILD_BUG_ON(set8->pairs != &set8->pairs[0].id);
++			qsort(set8->pairs, set8->cnt, sizeof(set8->pairs[0]), cmp_id);
++		}
+ 
+ 		pr_debug("sorting  addr %5lu: cnt %6d [%s]\n",
+-			 (idx + 1) * sizeof(int), cnt, id->name);
+-
+-		qsort(base, cnt, id->is_set8 ? sizeof(uint64_t) : sizeof(int), cmp_id);
++			 off, id->is_set ? set->cnt : set8->cnt, id->name);
+ 
+ 		next = rb_next(next);
+ 	}
+diff --git a/tools/include/linux/btf_ids.h b/tools/include/linux/btf_ids.h
+index 2f882d5cb30f..72535f00572f 100644
+--- a/tools/include/linux/btf_ids.h
++++ b/tools/include/linux/btf_ids.h
+@@ -8,6 +8,15 @@ struct btf_id_set {
+ 	u32 ids[];
+ };
+ 
++struct btf_id_set8 {
++	u32 cnt;
++	u32 flags;
++	struct {
++		u32 id;
++		u32 flags;
++	} pairs[];
++};
++
+ #ifdef CONFIG_DEBUG_INFO_BTF
+ 
+ #include <linux/compiler.h> /* for __PASTE */
+-- 
+2.39.3
+
+
+
diff --git a/ci/diffs/0001-tracing-kprobes-Fix-symbol-counting-logic-by-looking.patch b/ci/diffs/0001-tracing-kprobes-Fix-symbol-counting-logic-by-looking.patch
new file mode 100644
index 0000000000000..24ebc231056cb
--- /dev/null
+++ b/ci/diffs/0001-tracing-kprobes-Fix-symbol-counting-logic-by-looking.patch
@@ -0,0 +1,65 @@
+From 08969a676d234a178ff9f8c67936a2ad98a741eb Mon Sep 17 00:00:00 2001
+From: Andrii Nakryiko <andrii@kernel.org>
+Date: Fri, 27 Oct 2023 16:22:24 -0700
+Subject: [PATCH] tracing/kprobes: Fix symbol counting logic by looking at
+ modules as well
+
+Recent changes to count number of matching symbols when creating
+a kprobe event failed to take into account kernel modules. As such, it
+breaks kprobes on kernel module symbols, by assuming there is no match.
+
+Fix this my calling module_kallsyms_on_each_symbol() in addition to
+kallsyms_on_each_match_symbol() to perform a proper counting.
+
+Cc: Francis Laniel <flaniel@linux.microsoft.com>
+Cc: stable@vger.kernel.org
+Cc: Masami Hiramatsu <mhiramat@kernel.org>
+Cc: Steven Rostedt <rostedt@goodmis.org>
+Fixes: b022f0c7e404 ("tracing/kprobes: Return EADDRNOTAVAIL when func matches several symbols")
+Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
+---
+ kernel/trace/trace_kprobe.c | 24 ++++++++++++++++++++----
+ 1 file changed, 20 insertions(+), 4 deletions(-)
+
+diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
+index effcaede4759..1efb27f35963 100644
+--- a/kernel/trace/trace_kprobe.c
++++ b/kernel/trace/trace_kprobe.c
+@@ -714,14 +714,30 @@ static int count_symbols(void *data, unsigned long unused)
+ 	return 0;
+ }
+ 
++struct sym_count_ctx {
++	unsigned int count;
++	const char *name;
++};
++
++static int count_mod_symbols(void *data, const char *name, unsigned long unused)
++{
++	struct sym_count_ctx *ctx = data;
++
++	if (strcmp(name, ctx->name) == 0)
++		ctx->count++;
++
++	return 0;
++}
++
+ static unsigned int number_of_same_symbols(char *func_name)
+ {
+-	unsigned int count;
++	struct sym_count_ctx ctx = { .count = 0, .name = func_name };
++
++	kallsyms_on_each_match_symbol(count_symbols, func_name, &ctx.count);
+ 
+-	count = 0;
+-	kallsyms_on_each_match_symbol(count_symbols, func_name, &count);
++	module_kallsyms_on_each_symbol(NULL, count_mod_symbols, &ctx);
+ 
+-	return count;
++	return ctx.count;
+ }
+ 
+ static int __trace_kprobe_create(int argc, const char *argv[])
+-- 
+2.34.1
+
diff --git a/ci/diffs/0002-tools-resolve_btfids-fix-cross-compilation-to-non-host-endianness.patch b/ci/diffs/0002-tools-resolve_btfids-fix-cross-compilation-to-non-host-endianness.patch
new file mode 100644
index 0000000000000..c4d67693bd132
--- /dev/null
+++ b/ci/diffs/0002-tools-resolve_btfids-fix-cross-compilation-to-non-host-endianness.patch
@@ -0,0 +1,117 @@
+From c3dcadfdf2bf8f01471066700c098b5185240df6 Mon Sep 17 00:00:00 2001
+From: Viktor Malik <vmalik@redhat.com>
+Date: Tue, 6 Feb 2024 13:46:10 +0100
+Subject: [PATCH 2/2] tools/resolve_btfids: Fix cross-compilation to non-host
+ endianness
+
+The .BTF_ids section is pre-filled with zeroed BTF ID entries during the
+build and afterwards patched by resolve_btfids with correct values.
+Since resolve_btfids always writes in host-native endianness, it relies
+on libelf to do the translation when the target ELF is cross-compiled to
+a different endianness (this was introduced in commit 61e8aeda9398
+("bpf: Fix libelf endian handling in resolv_btfids")).
+
+Unfortunately, the translation will corrupt the flags fields of SET8
+entries because these were written during vmlinux compilation and are in
+the correct endianness already. This will lead to numerous selftests
+failures such as:
+
+    $ sudo ./test_verifier 502 502
+    #502/p sleepable fentry accept FAIL
+    Failed to load prog 'Invalid argument'!
+    bpf_fentry_test1 is not sleepable
+    verification time 34 usec
+    stack depth 0
+    processed 0 insns (limit 1000000) max_states_per_insn 0 total_states 0 peak_states 0 mark_read 0
+    Summary: 0 PASSED, 0 SKIPPED, 1 FAILED
+
+Since it's not possible to instruct libelf to translate just certain
+values, let's manually bswap the flags (both global and entry flags) in
+resolve_btfids when needed, so that libelf then translates everything
+correctly.
+
+Fixes: ef2c6f370a63 ("tools/resolve_btfids: Add support for 8-byte BTF sets")
+Signed-off-by: Viktor Malik <vmalik@redhat.com>
+Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
+Link: https://lore.kernel.org/bpf/7b6bff690919555574ce0f13d2a5996cacf7bf69.1707223196.git.vmalik@redhat.com
+---
+ tools/bpf/resolve_btfids/main.c | 35 +++++++++++++++++++++++++++++++++
+ 1 file changed, 35 insertions(+)
+
+diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c
+index 32634f00abba..d9520cb826b3 100644
+--- a/tools/bpf/resolve_btfids/main.c
++++ b/tools/bpf/resolve_btfids/main.c
+@@ -90,6 +90,14 @@
+ 
+ #define ADDR_CNT	100
+ 
++#if __BYTE_ORDER == __LITTLE_ENDIAN
++# define ELFDATANATIVE	ELFDATA2LSB
++#elif __BYTE_ORDER == __BIG_ENDIAN
++# define ELFDATANATIVE	ELFDATA2MSB
++#else
++# error "Unknown machine endianness!"
++#endif
++
+ struct btf_id {
+ 	struct rb_node	 rb_node;
+ 	char		*name;
+@@ -117,6 +125,7 @@ struct object {
+ 		int		 idlist_shndx;
+ 		size_t		 strtabidx;
+ 		unsigned long	 idlist_addr;
++		int		 encoding;
+ 	} efile;
+ 
+ 	struct rb_root	sets;
+@@ -320,6 +329,7 @@ static int elf_collect(struct object *obj)
+ {
+ 	Elf_Scn *scn = NULL;
+ 	size_t shdrstrndx;
++	GElf_Ehdr ehdr;
+ 	int idx = 0;
+ 	Elf *elf;
+ 	int fd;
+@@ -351,6 +361,13 @@ static int elf_collect(struct object *obj)
+ 		return -1;
+ 	}
+ 
++	if (gelf_getehdr(obj->efile.elf, &ehdr) == NULL) {
++		pr_err("FAILED cannot get ELF header: %s\n",
++			elf_errmsg(-1));
++		return -1;
++	}
++	obj->efile.encoding = ehdr.e_ident[EI_DATA];
++
+ 	/*
+ 	 * Scan all the elf sections and look for save data
+ 	 * from .BTF_ids section and symbols.
+@@ -681,6 +698,24 @@ static int sets_patch(struct object *obj)
+ 			 */
+ 			BUILD_BUG_ON(set8->pairs != &set8->pairs[0].id);
+ 			qsort(set8->pairs, set8->cnt, sizeof(set8->pairs[0]), cmp_id);
++
++			/*
++			 * When ELF endianness does not match endianness of the
++			 * host, libelf will do the translation when updating
++			 * the ELF. This, however, corrupts SET8 flags which are
++			 * already in the target endianness. So, let's bswap
++			 * them to the host endianness and libelf will then
++			 * correctly translate everything.
++			 */
++			if (obj->efile.encoding != ELFDATANATIVE) {
++				int i;
++
++				set8->flags = bswap_32(set8->flags);
++				for (i = 0; i < set8->cnt; i++) {
++					set8->pairs[i].flags =
++						bswap_32(set8->pairs[i].flags);
++				}
++			}
+ 		}
+ 
+ 		pr_debug("sorting  addr %5lu: cnt %6d [%s]\n",
+-- 
+2.39.3
+
diff --git a/ci/diffs/0099-s390x_nolockdep.diff b/ci/diffs/0099-s390x_nolockdep.diff
new file mode 100644
index 0000000000000..44c2d1a520656
--- /dev/null
+++ b/ci/diffs/0099-s390x_nolockdep.diff
@@ -0,0 +1,48 @@
+From 470d0c7874ac638ea62cddc3a20ec047fa4ab539 Mon Sep 17 00:00:00 2001
+From: Manu Bretelle <chantr4@gmail.com>
+Date: Wed, 14 Feb 2024 17:25:35 -0800
+Subject: [PATCH] bpf/selftests: disable lockdep on s390x
+
+Tests are slow to run on s390x, this should make them faster.
+
+Signed-off-by: Manu Bretelle <chantr4@gmail.com>
+---
+ tools/testing/selftests/bpf/config.s390x | 8 ++++----
+ 1 file changed, 4 insertions(+), 4 deletions(-)
+
+diff --git a/tools/testing/selftests/bpf/config.s390x b/tools/testing/selftests/bpf/config.s390x
+index 706931a8c2c69..67bfd62b0b582 100644
+--- a/tools/testing/selftests/bpf/config.s390x
++++ b/tools/testing/selftests/bpf/config.s390x
+@@ -23,11 +23,11 @@ CONFIG_CPUSETS=y
+ CONFIG_CRASH_DUMP=y
+ CONFIG_CRYPTO_USER_API_RNG=y
+ CONFIG_CRYPTO_USER_API_SKCIPHER=y
+-CONFIG_DEBUG_ATOMIC_SLEEP=y
++CONFIG_DEBUG_ATOMIC_SLEEP=n
+ CONFIG_DEBUG_INFO_BTF=y
+ CONFIG_DEBUG_INFO_DWARF4=y
+ CONFIG_DEBUG_LIST=y
+-CONFIG_DEBUG_LOCKDEP=y
++CONFIG_DEBUG_LOCKDEP=n
+ CONFIG_DEBUG_NOTIFIERS=y
+ CONFIG_DEBUG_PAGEALLOC=y
+ CONFIG_DEBUG_SECTION_MISMATCH=y
+@@ -71,7 +71,7 @@ CONFIG_KRETPROBES=y
+ CONFIG_KSM=y
+ CONFIG_LATENCYTOP=y
+ CONFIG_LIVEPATCH=y
+-CONFIG_LOCK_STAT=y
++CONFIG_LOCK_STAT=n
+ CONFIG_MACVLAN=y
+ CONFIG_MACVTAP=y
+ CONFIG_MAGIC_SYSRQ=y
+@@ -101,7 +101,7 @@ CONFIG_PCI=y
+ CONFIG_POSIX_MQUEUE=y
+ CONFIG_PROC_KCORE=y
+ CONFIG_PROFILING=y
+-CONFIG_PROVE_LOCKING=y
++CONFIG_PROVE_LOCKING=n
+ CONFIG_PTDUMP_DEBUGFS=y
+ CONFIG_RC_DEVICES=y
+ CONFIG_RC_LOOPBACK=y
diff --git a/ci/diffs/0099-selftest-cross-compile.diff b/ci/diffs/0099-selftest-cross-compile.diff
new file mode 100644
index 0000000000000..e8732596bdb3f
--- /dev/null
+++ b/ci/diffs/0099-selftest-cross-compile.diff
@@ -0,0 +1,13 @@
+diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
+index a38a3001527c..af68528cc944 100644
+--- a/tools/testing/selftests/bpf/Makefile
++++ b/tools/testing/selftests/bpf/Makefile
+@@ -304,7 +304,7 @@ $(OUTPUT)/test_maps: $(TESTING_HELPERS)
+ $(OUTPUT)/test_verifier: $(TESTING_HELPERS) $(CAP_HELPERS) $(UNPRIV_HELPERS)
+ $(OUTPUT)/xsk.o: $(BPFOBJ)
+ 
+-BPFTOOL ?= $(DEFAULT_BPFTOOL)
++BPFTOOL ?= $(TRUNNER_BPFTOOL)
+ $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile)    \
+ 		    $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/bpftool
+ 	$(Q)$(MAKE) $(submake_extras)  -C $(BPFTOOLDIR)			       \
diff --git a/ci/diffs/0199-iov_iter-fix-advancing-slot-in-iter_folioq_get_pages.patch b/ci/diffs/0199-iov_iter-fix-advancing-slot-in-iter_folioq_get_pages.patch
new file mode 100644
index 0000000000000..b81d22a35322c
--- /dev/null
+++ b/ci/diffs/0199-iov_iter-fix-advancing-slot-in-iter_folioq_get_pages.patch
@@ -0,0 +1,46 @@
+From 0d24852bd71ec85ca0016b6d6fc997e6a3381552 Mon Sep 17 00:00:00 2001
+From: Omar Sandoval <osandov@fb.com>
+Date: Mon, 30 Sep 2024 11:55:00 -0700
+Subject: [PATCH] iov_iter: fix advancing slot in iter_folioq_get_pages()
+
+iter_folioq_get_pages() decides to advance to the next folioq slot when
+it has reached the end of the current folio. However, it is checking
+offset, which is the beginning of the current part, instead of
+iov_offset, which is adjusted to the end of the current part, so it
+doesn't advance the slot when it's supposed to. As a result, on the next
+iteration, we'll use the same folio with an out-of-bounds offset and
+return an unrelated page.
+
+This manifested as various crashes and other failures in 9pfs in drgn's
+VM testing setup and BPF CI.
+
+Fixes: db0aa2e9566f ("mm: Define struct folio_queue and ITER_FOLIOQ to handle a sequence of folios")
+Link: https://lore.kernel.org/linux-fsdevel/20240923183432.1876750-1-chantr4@gmail.com/
+Tested-by: Manu Bretelle <chantr4@gmail.com>
+Signed-off-by: Omar Sandoval <osandov@fb.com>
+Link: https://lore.kernel.org/r/cbaf141ba6c0e2e209717d02746584072844841a.1727722269.git.osandov@fb.com
+Tested-by: Eduard Zingerman <eddyz87@gmail.com>
+Tested-by: Leon Romanovsky <leon@kernel.org>
+Tested-by: Joey Gouly <joey.gouly@arm.com>
+Acked-by: David Howells <dhowells@redhat.com>
+Signed-off-by: Christian Brauner <brauner@kernel.org>
+---
+ lib/iov_iter.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/lib/iov_iter.c b/lib/iov_iter.c
+index 97003155b..1abb32c0d 100644
+--- a/lib/iov_iter.c
++++ b/lib/iov_iter.c
+@@ -1033,7 +1033,7 @@ static ssize_t iter_folioq_get_pages(struct iov_iter *iter,
+ 		if (maxpages == 0 || extracted >= maxsize)
+ 			break;
+ 
+-		if (offset >= fsize) {
++		if (iov_offset >= fsize) {
+ 			iov_offset = 0;
+ 			slot++;
+ 			if (slot == folioq_nr_slots(folioq) && folioq->next) {
+-- 
+2.34.1
+
diff --git a/ci/diffs/0299-selftests-bpf-Fix-uprobe-consumer-test.patch b/ci/diffs/0299-selftests-bpf-Fix-uprobe-consumer-test.patch
new file mode 100644
index 0000000000000..11aa3626f5a81
--- /dev/null
+++ b/ci/diffs/0299-selftests-bpf-Fix-uprobe-consumer-test.patch
@@ -0,0 +1,58 @@
+From affb32e4f056883f285f8535b766293b85752fb4 Mon Sep 17 00:00:00 2001
+From: Jiri Olsa <jolsa@kernel.org>
+Date: Tue, 24 Sep 2024 13:07:30 +0200
+Subject: [PATCH] selftests/bpf: Fix uprobe consumer test
+
+With newly merged code the uprobe behaviour is slightly different
+and affects uprobe consumer test.
+
+We no longer need to check if the uprobe object is still preserved
+after removing last uretprobe, because it stays as long as there's
+pending/installed uretprobe instance.
+
+This allows to run uretprobe consumers registered 'after' uprobe was
+hit even if previous uretprobe got unregistered before being hit.
+
+The uprobe object will be now removed after the last uprobe ref is
+released and in such case it's held by ri->uprobe (return instance)
+which is released after the uretprobe is hit.
+
+Reported-by: Ihor Solodrai <ihor.solodrai@pm.me>
+Signed-off-by: Jiri Olsa <jolsa@kernel.org>
+Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
+Tested-by: Ihor Solodrai <ihor.solodrai@pm.me>
+Closes: https://lore.kernel.org/bpf/w6U8Z9fdhjnkSp2UaFaV1fGqJXvfLEtDKEUyGDkwmoruDJ_AgF_c0FFhrkeKW18OqiP-05s9yDKiT6X-Ns-avN_ABf0dcUkXqbSJN1TQSXo=@pm.me/
+---
+ .../testing/selftests/bpf/prog_tests/uprobe_multi_test.c | 9 +--------
+ 1 file changed, 1 insertion(+), 8 deletions(-)
+
+diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
+index 844f6fc8487b..c1ac813ff9ba 100644
+--- a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
++++ b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
+@@ -869,21 +869,14 @@ static void consumer_test(struct uprobe_multi_consumers *skel,
+ 			fmt = "prog 0/1: uprobe";
+ 		} else {
+ 			/*
+-			 * uprobe return is tricky ;-)
+-			 *
+ 			 * to trigger uretprobe consumer, the uretprobe needs to be installed,
+ 			 * which means one of the 'return' uprobes was alive when probe was hit:
+ 			 *
+ 			 *   idxs: 2/3 uprobe return in 'installed' mask
+-			 *
+-			 * in addition if 'after' state removes everything that was installed in
+-			 * 'before' state, then uprobe kernel object goes away and return uprobe
+-			 * is not installed and we won't hit it even if it's in 'after' state.
+ 			 */
+ 			unsigned long had_uretprobes  = before & 0b1100; /* is uretprobe installed */
+-			unsigned long probe_preserved = before & after;  /* did uprobe go away */
+ 
+-			if (had_uretprobes && probe_preserved && test_bit(idx, after))
++			if (had_uretprobes && test_bit(idx, after))
+ 				val++;
+ 			fmt = "idx 2/3: uretprobe";
+ 		}
+-- 
+2.34.1
+
diff --git a/ci/diffs/0399-selftests-sched_ext-fix-build-after-renames-in-sched.patch b/ci/diffs/0399-selftests-sched_ext-fix-build-after-renames-in-sched.patch
new file mode 100644
index 0000000000000..ba37429396236
--- /dev/null
+++ b/ci/diffs/0399-selftests-sched_ext-fix-build-after-renames-in-sched.patch
@@ -0,0 +1,231 @@
+From 5565144e82b97c5d2082ab19866836dfe5b2e592 Mon Sep 17 00:00:00 2001
+From: Ihor Solodrai <ihor.solodrai@pm.me>
+Date: Thu, 21 Nov 2024 13:20:46 -0800
+Subject: [PATCH] selftests/sched_ext: fix build after renames in sched_ext API
+
+The selftests are falining to build on current tip of bpf-next and
+sched_ext [1]. This has broken BPF CI [2] after merge from upstream.
+
+Use appropriate function names in the selftests according to the
+recent changes in the sched_ext API [3].
+
+[1]
+https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/commit/?id=fc39fb56917bb3cb53e99560ca3612a84456ada2
+[2] https://github.com/kernel-patches/bpf/actions/runs/11959327258/job/33340923745
+[3] https://lore.kernel.org/all/20241109194853.580310-1-tj@kernel.org/
+
+Signed-off-by: Ihor Solodrai <ihor.solodrai@pm.me>
+---
+ .../testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c | 2 +-
+ .../selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c        | 4 ++--
+ tools/testing/selftests/sched_ext/dsp_local_on.bpf.c      | 2 +-
+ .../selftests/sched_ext/enq_select_cpu_fails.bpf.c        | 2 +-
+ tools/testing/selftests/sched_ext/exit.bpf.c              | 4 ++--
+ tools/testing/selftests/sched_ext/maximal.bpf.c           | 4 ++--
+ tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c    | 2 +-
+ .../selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c   | 2 +-
+ .../testing/selftests/sched_ext/select_cpu_dispatch.bpf.c | 2 +-
+ .../selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c | 2 +-
+ .../selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c | 4 ++--
+ tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c  | 8 ++++----
+ 12 files changed, 19 insertions(+), 19 deletions(-)
+
+diff --git a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c
+index 37d9bf6fb745..6f4c3f5a1c5d 100644
+--- a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c
++++ b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c
+@@ -20,7 +20,7 @@ s32 BPF_STRUCT_OPS(ddsp_bogus_dsq_fail_select_cpu, struct task_struct *p,
+ 		 * If we dispatch to a bogus DSQ that will fall back to the
+ 		 * builtin global DSQ, we fail gracefully.
+ 		 */
+-		scx_bpf_dispatch_vtime(p, 0xcafef00d, SCX_SLICE_DFL,
++		scx_bpf_dsq_insert_vtime(p, 0xcafef00d, SCX_SLICE_DFL,
+ 				       p->scx.dsq_vtime, 0);
+ 		return cpu;
+ 	}
+diff --git a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c
+index dffc97d9cdf1..e4a55027778f 100644
+--- a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c
++++ b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c
+@@ -17,8 +17,8 @@ s32 BPF_STRUCT_OPS(ddsp_vtimelocal_fail_select_cpu, struct task_struct *p,
+ 
+ 	if (cpu >= 0) {
+ 		/* Shouldn't be allowed to vtime dispatch to a builtin DSQ. */
+-		scx_bpf_dispatch_vtime(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL,
+-				       p->scx.dsq_vtime, 0);
++		scx_bpf_dsq_insert_vtime(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL,
++					 p->scx.dsq_vtime, 0);
+ 		return cpu;
+ 	}
+ 
+diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c
+index 6a7db1502c29..6325bf76f47e 100644
+--- a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c
++++ b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c
+@@ -45,7 +45,7 @@ void BPF_STRUCT_OPS(dsp_local_on_dispatch, s32 cpu, struct task_struct *prev)
+ 
+ 	target = bpf_get_prandom_u32() % nr_cpus;
+ 
+-	scx_bpf_dispatch(p, SCX_DSQ_LOCAL_ON | target, SCX_SLICE_DFL, 0);
++	scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL_ON | target, SCX_SLICE_DFL, 0);
+ 	bpf_task_release(p);
+ }
+ 
+diff --git a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c
+index 1efb50d61040..a7cf868d5e31 100644
+--- a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c
++++ b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c
+@@ -31,7 +31,7 @@ void BPF_STRUCT_OPS(enq_select_cpu_fails_enqueue, struct task_struct *p,
+ 	/* Can only call from ops.select_cpu() */
+ 	scx_bpf_select_cpu_dfl(p, 0, 0, &found);
+ 
+-	scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
++	scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
+ }
+ 
+ SEC(".struct_ops.link")
+diff --git a/tools/testing/selftests/sched_ext/exit.bpf.c b/tools/testing/selftests/sched_ext/exit.bpf.c
+index d75d4faf07f6..4bc36182d3ff 100644
+--- a/tools/testing/selftests/sched_ext/exit.bpf.c
++++ b/tools/testing/selftests/sched_ext/exit.bpf.c
+@@ -33,7 +33,7 @@ void BPF_STRUCT_OPS(exit_enqueue, struct task_struct *p, u64 enq_flags)
+ 	if (exit_point == EXIT_ENQUEUE)
+ 		EXIT_CLEANLY();
+ 
+-	scx_bpf_dispatch(p, DSQ_ID, SCX_SLICE_DFL, enq_flags);
++	scx_bpf_dsq_insert(p, DSQ_ID, SCX_SLICE_DFL, enq_flags);
+ }
+ 
+ void BPF_STRUCT_OPS(exit_dispatch, s32 cpu, struct task_struct *p)
+@@ -41,7 +41,7 @@ void BPF_STRUCT_OPS(exit_dispatch, s32 cpu, struct task_struct *p)
+ 	if (exit_point == EXIT_DISPATCH)
+ 		EXIT_CLEANLY();
+ 
+-	scx_bpf_consume(DSQ_ID);
++	scx_bpf_dsq_move_to_local(DSQ_ID);
+ }
+ 
+ void BPF_STRUCT_OPS(exit_enable, struct task_struct *p)
+diff --git a/tools/testing/selftests/sched_ext/maximal.bpf.c b/tools/testing/selftests/sched_ext/maximal.bpf.c
+index 4d4cd8d966db..4c005fa71810 100644
+--- a/tools/testing/selftests/sched_ext/maximal.bpf.c
++++ b/tools/testing/selftests/sched_ext/maximal.bpf.c
+@@ -20,7 +20,7 @@ s32 BPF_STRUCT_OPS(maximal_select_cpu, struct task_struct *p, s32 prev_cpu,
+ 
+ void BPF_STRUCT_OPS(maximal_enqueue, struct task_struct *p, u64 enq_flags)
+ {
+-	scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
++	scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
+ }
+ 
+ void BPF_STRUCT_OPS(maximal_dequeue, struct task_struct *p, u64 deq_flags)
+@@ -28,7 +28,7 @@ void BPF_STRUCT_OPS(maximal_dequeue, struct task_struct *p, u64 deq_flags)
+ 
+ void BPF_STRUCT_OPS(maximal_dispatch, s32 cpu, struct task_struct *prev)
+ {
+-	scx_bpf_consume(SCX_DSQ_GLOBAL);
++	scx_bpf_dsq_move_to_local(SCX_DSQ_GLOBAL);
+ }
+ 
+ void BPF_STRUCT_OPS(maximal_runnable, struct task_struct *p, u64 enq_flags)
+diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c
+index f171ac470970..13d0f5be788d 100644
+--- a/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c
++++ b/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c
+@@ -30,7 +30,7 @@ void BPF_STRUCT_OPS(select_cpu_dfl_enqueue, struct task_struct *p,
+ 	}
+ 	scx_bpf_put_idle_cpumask(idle_mask);
+ 
+-	scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
++	scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
+ }
+ 
+ SEC(".struct_ops.link")
+diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c
+index 9efdbb7da928..815f1d5d61ac 100644
+--- a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c
++++ b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c
+@@ -67,7 +67,7 @@ void BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_enqueue, struct task_struct *p,
+ 		saw_local = true;
+ 	}
+ 
+-	scx_bpf_dispatch(p, dsq_id, SCX_SLICE_DFL, enq_flags);
++	scx_bpf_dsq_insert(p, dsq_id, SCX_SLICE_DFL, enq_flags);
+ }
+ 
+ s32 BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_init_task,
+diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c
+index 59bfc4f36167..4bb99699e920 100644
+--- a/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c
++++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c
+@@ -29,7 +29,7 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_select_cpu, struct task_struct *p,
+ 	cpu = prev_cpu;
+ 
+ dispatch:
+-	scx_bpf_dispatch(p, dsq_id, SCX_SLICE_DFL, 0);
++	scx_bpf_dsq_insert(p, dsq_id, SCX_SLICE_DFL, 0);
+ 	return cpu;
+ }
+ 
+diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c
+index 3bbd5fcdfb18..2a75de11b2cf 100644
+--- a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c
++++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c
+@@ -18,7 +18,7 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_bad_dsq_select_cpu, struct task_struct *p
+ 		   s32 prev_cpu, u64 wake_flags)
+ {
+ 	/* Dispatching to a random DSQ should fail. */
+-	scx_bpf_dispatch(p, 0xcafef00d, SCX_SLICE_DFL, 0);
++	scx_bpf_dsq_insert(p, 0xcafef00d, SCX_SLICE_DFL, 0);
+ 
+ 	return prev_cpu;
+ }
+diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c
+index 0fda57fe0ecf..99d075695c97 100644
+--- a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c
++++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c
+@@ -18,8 +18,8 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_dbl_dsp_select_cpu, struct task_struct *p
+ 		   s32 prev_cpu, u64 wake_flags)
+ {
+ 	/* Dispatching twice in a row is disallowed. */
+-	scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0);
+-	scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0);
++	scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0);
++	scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0);
+ 
+ 	return prev_cpu;
+ }
+diff --git a/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c
+index e6c67bcf5e6e..bfcb96cd4954 100644
+--- a/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c
++++ b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c
+@@ -2,8 +2,8 @@
+ /*
+  * A scheduler that validates that enqueue flags are properly stored and
+  * applied at dispatch time when a task is directly dispatched from
+- * ops.select_cpu(). We validate this by using scx_bpf_dispatch_vtime(), and
+- * making the test a very basic vtime scheduler.
++ * ops.select_cpu(). We validate this by using scx_bpf_dsq_insert_vtime(),
++ * and making the test a very basic vtime scheduler.
+  *
+  * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+  * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+@@ -47,13 +47,13 @@ s32 BPF_STRUCT_OPS(select_cpu_vtime_select_cpu, struct task_struct *p,
+ 	cpu = prev_cpu;
+ 	scx_bpf_test_and_clear_cpu_idle(cpu);
+ ddsp:
+-	scx_bpf_dispatch_vtime(p, VTIME_DSQ, SCX_SLICE_DFL, task_vtime(p), 0);
++	scx_bpf_dsq_insert_vtime(p, VTIME_DSQ, SCX_SLICE_DFL, task_vtime(p), 0);
+ 	return cpu;
+ }
+ 
+ void BPF_STRUCT_OPS(select_cpu_vtime_dispatch, s32 cpu, struct task_struct *p)
+ {
+-	if (scx_bpf_consume(VTIME_DSQ))
++	if (scx_bpf_dsq_move_to_local(VTIME_DSQ))
+ 		consumed = true;
+ }
+ 
+-- 
+2.47.0
+
diff --git a/ci/diffs/0499-samples-bpf-fix-samples-compilation.patch b/ci/diffs/0499-samples-bpf-fix-samples-compilation.patch
new file mode 100644
index 0000000000000..1f95c3c237cb9
--- /dev/null
+++ b/ci/diffs/0499-samples-bpf-fix-samples-compilation.patch
@@ -0,0 +1,61 @@
+From 80a5958a52b86e39c1a1bf5f4702011c0cf6ab4f Mon Sep 17 00:00:00 2001
+From: Eduard Zingerman <eddyz87@gmail.com>
+Date: Mon, 2 Dec 2024 12:14:46 -0800
+Subject: [PATCH] samples/bpf: fix samples compilation
+
+Commit [0] breaks samples build.
+
+TODO: moar details here
+
+[0] 13b25489b6f8 ("kbuild: change working directory to external module directory with M=")
+
+Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
+Signed-off-by: Ihor Solodrai <ihor.solodrai@pm.me>
+---
+ samples/bpf/Makefile | 13 +++++++------
+ 1 file changed, 7 insertions(+), 6 deletions(-)
+
+diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
+index bcf103a4c14f..ee10dbf1b471 100644
+--- a/samples/bpf/Makefile
++++ b/samples/bpf/Makefile
+@@ -146,13 +146,14 @@ ifeq ($(ARCH), x86)
+ BPF_EXTRA_CFLAGS += -fcf-protection
+ endif
+ 
+-TPROGS_CFLAGS += -Wall -O2
+-TPROGS_CFLAGS += -Wmissing-prototypes
+-TPROGS_CFLAGS += -Wstrict-prototypes
+-TPROGS_CFLAGS += $(call try-run,\
++COMMON_CFLAGS += -Wall -O2
++COMMON_CFLAGS += -Wmissing-prototypes
++COMMON_CFLAGS += -Wstrict-prototypes
++COMMON_CFLAGS += $(call try-run,\
+ 	printf "int main() { return 0; }" |\
+ 	$(CC) -Werror -fsanitize=bounds -x c - -o "$$TMP",-fsanitize=bounds,)
+ 
++TPROGS_CFLAGS += $(COMMON_CFLAGS)
+ TPROGS_CFLAGS += -I$(objtree)/usr/include
+ TPROGS_CFLAGS += -I$(srctree)/tools/testing/selftests/bpf/
+ TPROGS_CFLAGS += -I$(LIBBPF_INCLUDE)
+@@ -229,7 +230,7 @@ clean:
+ 
+ $(LIBBPF): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OUTPUT)
+ # Fix up variables inherited from Kbuild that tools/ build system won't like
+-	$(MAKE) -C $(LIBBPF_SRC) RM='rm -rf' EXTRA_CFLAGS="$(TPROGS_CFLAGS)" \
++	$(MAKE) -C $(LIBBPF_SRC) RM='rm -rf' EXTRA_CFLAGS="$(COMMON_CFLAGS)" \
+ 		LDFLAGS="$(TPROGS_LDFLAGS)" srctree=$(BPF_SAMPLES_PATH)/../../ \
+ 		O= OUTPUT=$(LIBBPF_OUTPUT)/ DESTDIR=$(LIBBPF_DESTDIR) prefix= \
+ 		$@ install_headers
+@@ -305,7 +306,7 @@ $(obj)/$(TRACE_HELPERS): TPROGS_CFLAGS := $(TPROGS_CFLAGS) -D__must_check=
+ -include $(BPF_SAMPLES_PATH)/Makefile.target
+ 
+ VMLINUX_BTF_PATHS ?= $(abspath $(if $(O),$(O)/vmlinux))				\
+-		     $(abspath $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux))	\
++		     $(abspath $(if $(objtree),$(objtree)/vmlinux))		\
+ 		     $(abspath ./vmlinux)
+ VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS))))
+ 
+-- 
+2.47.0
+
diff --git a/ci/diffs/2000-s390-fgraph-Fix-to-remove-ftrace_test_recursion_tryl.patch b/ci/diffs/2000-s390-fgraph-Fix-to-remove-ftrace_test_recursion_tryl.patch
new file mode 100644
index 0000000000000..7e38b1a151a10
--- /dev/null
+++ b/ci/diffs/2000-s390-fgraph-Fix-to-remove-ftrace_test_recursion_tryl.patch
@@ -0,0 +1,46 @@
+From faf291ff4beaef8dedebd166f11f815cdee257dc Mon Sep 17 00:00:00 2001
+From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
+Date: Wed, 29 Jan 2025 00:29:37 +0900
+Subject: [PATCH 2000/2001] s390: fgraph: Fix to remove
+ ftrace_test_recursion_trylock()
+
+Fix to remove ftrace_test_recursion_trylock() from ftrace_graph_func()
+because commit d576aec24df9 ("fgraph: Get ftrace recursion lock in
+function_graph_enter") has been moved it to function_graph_enter_regs()
+already.
+
+Reported-by: Jiri Olsa <olsajiri@gmail.com>
+Closes: https://lore.kernel.org/all/Z5O0shrdgeExZ2kF@krava/
+Fixes: d576aec24df9 ("fgraph: Get ftrace recursion lock in function_graph_enter")
+Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
+Tested-by: Jiri Olsa <jolsa@kernel.org>
+---
+ arch/s390/kernel/ftrace.c | 5 -----
+ 1 file changed, 5 deletions(-)
+
+diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
+index c0b2c97efefb..63ba6306632e 100644
+--- a/arch/s390/kernel/ftrace.c
++++ b/arch/s390/kernel/ftrace.c
+@@ -266,18 +266,13 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
+ 		       struct ftrace_ops *op, struct ftrace_regs *fregs)
+ {
+ 	unsigned long *parent = &arch_ftrace_regs(fregs)->regs.gprs[14];
+-	int bit;
+ 
+ 	if (unlikely(ftrace_graph_is_dead()))
+ 		return;
+ 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
+ 		return;
+-	bit = ftrace_test_recursion_trylock(ip, *parent);
+-	if (bit < 0)
+-		return;
+ 	if (!function_graph_enter_regs(*parent, ip, 0, parent, fregs))
+ 		*parent = (unsigned long)&return_to_handler;
+-	ftrace_test_recursion_unlock(bit);
+ }
+ 
+ #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+-- 
+2.48.1
+
diff --git a/ci/diffs/2001-s390-tracing-Define-ftrace_get_symaddr-for-s390.patch b/ci/diffs/2001-s390-tracing-Define-ftrace_get_symaddr-for-s390.patch
new file mode 100644
index 0000000000000..66483206f448f
--- /dev/null
+++ b/ci/diffs/2001-s390-tracing-Define-ftrace_get_symaddr-for-s390.patch
@@ -0,0 +1,28 @@
+From 04fce0d606f59a62105729094013c4784492ec7b Mon Sep 17 00:00:00 2001
+From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
+Date: Wed, 29 Jan 2025 00:29:48 +0900
+Subject: [PATCH 2001/2001] s390: tracing: Define ftrace_get_symaddr() for s390
+
+Add ftrace_get_symaddr() for s390, which returns the symbol address
+from ftrace's 'ip' parameter.
+
+Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
+---
+ arch/s390/include/asm/ftrace.h | 1 +
+ 1 file changed, 1 insertion(+)
+
+diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h
+index a3b73a4f626e..185331e91f83 100644
+--- a/arch/s390/include/asm/ftrace.h
++++ b/arch/s390/include/asm/ftrace.h
+@@ -51,6 +51,7 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
+ {
+ 	return addr;
+ }
++#define ftrace_get_symaddr(fentry_ip) ((unsigned long)(fentry_ip))
+ 
+ #include <linux/ftrace_regs.h>
+ 
+-- 
+2.48.1
+
diff --git a/ci/diffs/2001-selftests-bpf-add-fno-strict-aliasing-to-BPF_CFLAGS.patch b/ci/diffs/2001-selftests-bpf-add-fno-strict-aliasing-to-BPF_CFLAGS.patch
new file mode 100644
index 0000000000000..9b24de70e2846
--- /dev/null
+++ b/ci/diffs/2001-selftests-bpf-add-fno-strict-aliasing-to-BPF_CFLAGS.patch
@@ -0,0 +1,75 @@
+From f44275e7155dc310d36516fc25be503da099781c Mon Sep 17 00:00:00 2001
+From: Ihor Solodrai <ihor.solodrai@pm.me>
+Date: Mon, 6 Jan 2025 20:17:31 +0000
+Subject: [PATCH] selftests/bpf: add -fno-strict-aliasing to BPF_CFLAGS
+
+Following the discussion at [1], set -fno-strict-aliasing flag for all
+BPF object build rules. Remove now unnecessary <test>-CFLAGS variables.
+
+[1] https://lore.kernel.org/bpf/20250106185447.951609-1-ihor.solodrai@pm.me/
+
+CC: Jose E. Marchesi <jose.marchesi@oracle.com>
+Signed-off-by: Ihor Solodrai <ihor.solodrai@pm.me>
+Acked-by: Eduard Zingerman <eddyz87@gmail.com>
+Link: https://lore.kernel.org/r/20250106201728.1219791-1-ihor.solodrai@pm.me
+Signed-off-by: Alexei Starovoitov <ast@kernel.org>
+---
+ tools/testing/selftests/bpf/Makefile | 28 +---------------------------
+ 1 file changed, 1 insertion(+), 27 deletions(-)
+
+diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
+index eb4d21651aa7..d5be2f94deef 100644
+--- a/tools/testing/selftests/bpf/Makefile
++++ b/tools/testing/selftests/bpf/Makefile
+@@ -54,21 +54,6 @@ PCAP_LIBS	:= $(shell $(PKG_CONFIG) --libs libpcap 2>/dev/null)
+ LDLIBS += $(PCAP_LIBS)
+ CFLAGS += $(PCAP_CFLAGS)
+ 
+-# The following tests perform type punning and they may break strict
+-# aliasing rules, which are exploited by both GCC and clang by default
+-# while optimizing.  This can lead to broken programs.
+-progs/bind4_prog.c-CFLAGS := -fno-strict-aliasing
+-progs/bind6_prog.c-CFLAGS := -fno-strict-aliasing
+-progs/dynptr_fail.c-CFLAGS := -fno-strict-aliasing
+-progs/linked_list_fail.c-CFLAGS := -fno-strict-aliasing
+-progs/map_kptr_fail.c-CFLAGS := -fno-strict-aliasing
+-progs/syscall.c-CFLAGS := -fno-strict-aliasing
+-progs/test_pkt_md_access.c-CFLAGS := -fno-strict-aliasing
+-progs/test_sk_lookup.c-CFLAGS := -fno-strict-aliasing
+-progs/timer_crash.c-CFLAGS := -fno-strict-aliasing
+-progs/test_global_func9.c-CFLAGS := -fno-strict-aliasing
+-progs/verifier_nocsr.c-CFLAGS := -fno-strict-aliasing
+-
+ # Some utility functions use LLVM libraries
+ jit_disasm_helpers.c-CFLAGS = $(LLVM_CFLAGS)
+ 
+@@ -103,18 +88,6 @@ progs/btf_dump_test_case_packing.c-bpf_gcc-CFLAGS := -Wno-error
+ progs/btf_dump_test_case_padding.c-bpf_gcc-CFLAGS := -Wno-error
+ progs/btf_dump_test_case_syntax.c-bpf_gcc-CFLAGS := -Wno-error
+ 
+-# The following tests do type-punning, via the __imm_insn macro, from
+-# `struct bpf_insn' to long and then uses the value.  This triggers an
+-# "is used uninitialized" warning in GCC due to strict-aliasing
+-# rules.
+-progs/verifier_ref_tracking.c-bpf_gcc-CFLAGS := -fno-strict-aliasing
+-progs/verifier_unpriv.c-bpf_gcc-CFLAGS := -fno-strict-aliasing
+-progs/verifier_cgroup_storage.c-bpf_gcc-CFLAGS := -fno-strict-aliasing
+-progs/verifier_ld_ind.c-bpf_gcc-CFLAGS := -fno-strict-aliasing
+-progs/verifier_map_ret_val.c-bpf_gcc-CFLAGS := -fno-strict-aliasing
+-progs/verifier_spill_fill.c-bpf_gcc-CFLAGS := -fno-strict-aliasing
+-progs/verifier_subprog_precision.c-bpf_gcc-CFLAGS := -fno-strict-aliasing
+-progs/verifier_uninit.c-bpf_gcc-CFLAGS := -fno-strict-aliasing
+ endif
+ 
+ ifneq ($(CLANG_CPUV4),)
+@@ -474,6 +447,7 @@ CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH))
+ BPF_CFLAGS = -g -Wall -Werror -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN)	\
+ 	     -I$(INCLUDE_DIR) -I$(CURDIR) -I$(APIDIR)			\
+ 	     -I$(abspath $(OUTPUT)/../usr/include)			\
++	     -fno-strict-aliasing 					\
+ 	     -Wno-compare-distinct-pointer-types
+ # TODO: enable me -Wsign-compare
+ 
+-- 
+2.47.1
+
diff --git a/ci/diffs/2002-selftests-bpf-add-std-gnu11-to-BPF_CFLAGS-and-CFLAGS.patch b/ci/diffs/2002-selftests-bpf-add-std-gnu11-to-BPF_CFLAGS-and-CFLAGS.patch
new file mode 100644
index 0000000000000..127b2641dc223
--- /dev/null
+++ b/ci/diffs/2002-selftests-bpf-add-std-gnu11-to-BPF_CFLAGS-and-CFLAGS.patch
@@ -0,0 +1,63 @@
+From bab18c7db44d3aa6c84450095451580922359c7a Mon Sep 17 00:00:00 2001
+From: Ihor Solodrai <ihor.solodrai@pm.me>
+Date: Tue, 7 Jan 2025 23:58:18 +0000
+Subject: [PATCH] selftests/bpf: add -std=gnu11 to BPF_CFLAGS and CFLAGS
+
+Latest versions of GCC BPF use C23 standard by default. This causes
+compilation errors in vmlinux.h due to bool types declarations.
+
+Add -std=gnu11 to BPF_CFLAGS and CFLAGS. This aligns with the version
+of the standard used when building the kernel currently [1].
+
+For more details see the discussions at [2] and [3].
+
+[1] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/Makefile#n465
+[2] https://lore.kernel.org/bpf/EYcXjcKDCJY7Yb0GGtAAb7nLKPEvrgWdvWpuNzXm2qi6rYMZDixKv5KwfVVMBq17V55xyC-A1wIjrqG3aw-Imqudo9q9X7D7nLU2gWgbN0w=@pm.me/
+[3] https://lore.kernel.org/bpf/20250106202715.1232864-1-ihor.solodrai@pm.me/
+
+CC: Jose E. Marchesi <jose.marchesi@oracle.com>
+Signed-off-by: Ihor Solodrai <ihor.solodrai@pm.me>
+Link: https://lore.kernel.org/r/20250107235813.2964472-1-ihor.solodrai@pm.me
+Signed-off-by: Alexei Starovoitov <ast@kernel.org>
+---
+ tools/testing/selftests/bpf/Makefile | 8 ++++++--
+ 1 file changed, 6 insertions(+), 2 deletions(-)
+
+diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
+index d5be2f94deef..ea9cee5de0f8 100644
+--- a/tools/testing/selftests/bpf/Makefile
++++ b/tools/testing/selftests/bpf/Makefile
+@@ -41,7 +41,7 @@ srctree := $(patsubst %/,%,$(dir $(srctree)))
+ srctree := $(patsubst %/,%,$(dir $(srctree)))
+ endif
+ 
+-CFLAGS += -g $(OPT_FLAGS) -rdynamic					\
++CFLAGS += -g $(OPT_FLAGS) -rdynamic -std=gnu11				\
+ 	  -Wall -Werror -fno-omit-frame-pointer				\
+ 	  $(GENFLAGS) $(SAN_CFLAGS) $(LIBELF_CFLAGS)			\
+ 	  -I$(CURDIR) -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR)		\
+@@ -447,6 +447,7 @@ CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH))
+ BPF_CFLAGS = -g -Wall -Werror -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN)	\
+ 	     -I$(INCLUDE_DIR) -I$(CURDIR) -I$(APIDIR)			\
+ 	     -I$(abspath $(OUTPUT)/../usr/include)			\
++	     -std=gnu11		 					\
+ 	     -fno-strict-aliasing 					\
+ 	     -Wno-compare-distinct-pointer-types
+ # TODO: enable me -Wsign-compare
+@@ -787,9 +788,12 @@ $(OUTPUT)/xdp_features: xdp_features.c $(OUTPUT)/network_helpers.o $(OUTPUT)/xdp
+ 	$(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@
+ 
+ # Make sure we are able to include and link libbpf against c++.
++CXXFLAGS += $(CFLAGS)
++CXXFLAGS := $(subst -D_GNU_SOURCE=,,$(CXXFLAGS))
++CXXFLAGS := $(subst -std=gnu11,-std=gnu++11,$(CXXFLAGS))
+ $(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ)
+ 	$(call msg,CXX,,$@)
+-	$(Q)$(CXX) $(subst -D_GNU_SOURCE=,,$(CFLAGS)) $(filter %.a %.o %.cpp,$^) $(LDLIBS) -o $@
++	$(Q)$(CXX) $(CXXFLAGS) $(filter %.a %.o %.cpp,$^) $(LDLIBS) -o $@
+ 
+ # Benchmark runner
+ $(OUTPUT)/bench_%.o: benchs/bench_%.c bench.h $(BPFOBJ)
+-- 
+2.47.1
+
diff --git a/ci/diffs/8888-netfs-Fix-setting-NETFS_RREQ_ALL_QUEUED-to-be-after-.patch b/ci/diffs/8888-netfs-Fix-setting-NETFS_RREQ_ALL_QUEUED-to-be-after-.patch
new file mode 100644
index 0000000000000..31bc3fb4717ec
--- /dev/null
+++ b/ci/diffs/8888-netfs-Fix-setting-NETFS_RREQ_ALL_QUEUED-to-be-after-.patch
@@ -0,0 +1,100 @@
+From a99b3ef16d4473f8f9b7547f89791d037112a7e6 Mon Sep 17 00:00:00 2001
+From: David Howells <dhowells@redhat.com>
+Date: Wed, 12 Feb 2025 22:24:01 +0000
+Subject: [PATCH] netfs: Fix setting NETFS_RREQ_ALL_QUEUED to be after all
+ subreqs queued
+
+Due to the code that queues a subreq on the active subrequest list getting
+moved to netfs_issue_read(), the NETFS_RREQ_ALL_QUEUED flag may now get set
+before the list-add actually happens.  This is not a problem if the
+collection worker happens after the list-add, but it's a race - and, for
+9P, where the read from the server is synchronous and done in the
+submitting thread, this is a lot more likely.
+
+The result is that, if the timing is wrong, a ref gets leaked because the
+collector thinks that all the subreqs have completed (because it can't see
+the last one yet) and clears NETFS_RREQ_IN_PROGRESS - at which point, the
+collection worker no longer goes into the collector.
+
+This can be provoked with AFS by injecting an msleep() right before the
+final subreq is queued.
+
+Fix this by splitting the queuing part out of netfs_issue_read() into a new
+function, netfs_queue_read(), and calling it separately.  The setting of
+NETFS_RREQ_ALL_QUEUED is then done by netfs_queue_read() whilst it is
+holding the spinlock (that's probably unnecessary, but shouldn't hurt).
+
+It might be better to set a flag on the final subreq, but this could be a
+problem if an error occurs and we can't queue it.
+
+Fixes: e2d46f2ec332 ("netfs: Change the read result collector to only use one work item")
+Reported-by: Ihor Solodrai <ihor.solodrai@pm.me>
+Closes: https://lore.kernel.org/r/a7x33d4dnMdGTtRivptq6S1i8btK70SNBP2XyX_xwDAhLvgQoPox6FVBOkifq4eBinfFfbZlIkMZBe3QarlWTxoEtHZwJCZbNKtaqrR7PvI=@pm.me/
+Signed-off-by: David Howells <dhowells@redhat.com>
+Tested-by: Ihor Solodrai <ihor.solodrai@linux.dev>
+cc: Eric Van Hensbergen <ericvh@kernel.org>
+cc: Latchesar Ionkov <lucho@ionkov.net>
+cc: Dominique Martinet <asmadeus@codewreck.org>
+cc: Christian Schoenebeck <linux_oss@crudebyte.com>
+cc: Marc Dionne <marc.dionne@auristor.com>
+cc: Steve French <stfrench@microsoft.com>
+cc: Paulo Alcantara <pc@manguebit.com>
+cc: Jeff Layton <jlayton@kernel.org>
+cc: v9fs@lists.linux.dev
+cc: linux-cifs@vger.kernel.org
+cc: netfs@lists.linux.dev
+cc: linux-fsdevel@vger.kernel.org
+---
+ fs/netfs/buffered_read.c | 19 +++++++++++++------
+ 1 file changed, 13 insertions(+), 6 deletions(-)
+
+diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
+index f761d44b3436..0d1b6d35ff3b 100644
+--- a/fs/netfs/buffered_read.c
++++ b/fs/netfs/buffered_read.c
+@@ -155,8 +155,9 @@ static void netfs_read_cache_to_pagecache(struct netfs_io_request *rreq,
+ 			netfs_cache_read_terminated, subreq);
+ }
+ 
+-static void netfs_issue_read(struct netfs_io_request *rreq,
+-			     struct netfs_io_subrequest *subreq)
++static void netfs_queue_read(struct netfs_io_request *rreq,
++			     struct netfs_io_subrequest *subreq,
++			     bool last_subreq)
+ {
+ 	struct netfs_io_stream *stream = &rreq->io_streams[0];
+ 
+@@ -177,8 +178,17 @@ static void netfs_issue_read(struct netfs_io_request *rreq,
+ 		}
+ 	}
+ 
++	if (last_subreq) {
++		smp_wmb(); /* Write lists before ALL_QUEUED. */
++		set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags);
++	}
++
+ 	spin_unlock(&rreq->lock);
++}
+ 
++static void netfs_issue_read(struct netfs_io_request *rreq,
++			     struct netfs_io_subrequest *subreq)
++{
+ 	switch (subreq->source) {
+ 	case NETFS_DOWNLOAD_FROM_SERVER:
+ 		rreq->netfs_ops->issue_read(subreq);
+@@ -293,11 +303,8 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq)
+ 		}
+ 		size -= slice;
+ 		start += slice;
+-		if (size <= 0) {
+-			smp_wmb(); /* Write lists before ALL_QUEUED. */
+-			set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags);
+-		}
+ 
++		netfs_queue_read(rreq, subreq, size <= 0);
+ 		netfs_issue_read(rreq, subreq);
+ 		cond_resched();
+ 	} while (size > 0);
+-- 
+2.48.1
+
diff --git a/ci/diffs/9998-sched_ext-Fix-invalid-irq-restore-in-scx_ops_bypass.patch b/ci/diffs/9998-sched_ext-Fix-invalid-irq-restore-in-scx_ops_bypass.patch
new file mode 100644
index 0000000000000..0f65cb47ce2e6
--- /dev/null
+++ b/ci/diffs/9998-sched_ext-Fix-invalid-irq-restore-in-scx_ops_bypass.patch
@@ -0,0 +1,56 @@
+From 10e1d78546b3dd4ea9d773c0b0257064a99211e9 Mon Sep 17 00:00:00 2001
+From: Tejun Heo <tj@kernel.org>
+Date: Wed, 11 Dec 2024 11:01:51 -1000
+Subject: [PATCH] sched_ext: Fix invalid irq restore in scx_ops_bypass()
+
+While adding outer irqsave/restore locking, 0e7ffff1b811 ("scx: Fix raciness
+in scx_ops_bypass()") forgot to convert an inner rq_unlock_irqrestore() to
+rq_unlock() which could re-enable IRQ prematurely leading to the following
+warning:
+
+  raw_local_irq_restore() called with IRQs enabled
+  WARNING: CPU: 1 PID: 96 at kernel/locking/irqflag-debug.c:10 warn_bogus_irq_restore+0x30/0x40
+  ...
+  Sched_ext: create_dsq (enabling)
+  pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
+  pc : warn_bogus_irq_restore+0x30/0x40
+  lr : warn_bogus_irq_restore+0x30/0x40
+  ...
+  Call trace:
+   warn_bogus_irq_restore+0x30/0x40 (P)
+   warn_bogus_irq_restore+0x30/0x40 (L)
+   scx_ops_bypass+0x224/0x3b8
+   scx_ops_enable.isra.0+0x2c8/0xaa8
+   bpf_scx_reg+0x18/0x30
+  ...
+  irq event stamp: 33739
+  hardirqs last  enabled at (33739): [<ffff8000800b699c>] scx_ops_bypass+0x174/0x3b8
+  hardirqs last disabled at (33738): [<ffff800080d48ad4>] _raw_spin_lock_irqsave+0xb4/0xd8
+
+Drop the stray _irqrestore().
+
+Signed-off-by: Tejun Heo <tj@kernel.org>
+Reported-by: Ihor Solodrai <ihor.solodrai@pm.me>
+Link: http://lkml.kernel.org/r/qC39k3UsonrBYD_SmuxHnZIQLsuuccoCrkiqb_BT7DvH945A1_LZwE4g-5Pu9FcCtqZt4lY1HhIPi0homRuNWxkgo1rgP3bkxa0donw8kV4=@pm.me
+Fixes: 0e7ffff1b811 ("scx: Fix raciness in scx_ops_bypass()")
+Cc: stable@vger.kernel.org # v6.12
+---
+ kernel/sched/ext.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
+index 7fff1d045477..98519e6d0dcd 100644
+--- a/kernel/sched/ext.c
++++ b/kernel/sched/ext.c
+@@ -4763,7 +4763,7 @@ static void scx_ops_bypass(bool bypass)
+ 		 * sees scx_rq_bypassing() before moving tasks to SCX.
+ 		 */
+ 		if (!scx_enabled()) {
+-			rq_unlock_irqrestore(rq, &rf);
++			rq_unlock(rq, &rf);
+ 			continue;
+ 		}
+ 
+-- 
+2.47.1
+
diff --git a/ci/diffs/9999-scx-Fix-maximal-BPF-selftest-prog.patch b/ci/diffs/9999-scx-Fix-maximal-BPF-selftest-prog.patch
new file mode 100644
index 0000000000000..9b5e6d50778e1
--- /dev/null
+++ b/ci/diffs/9999-scx-Fix-maximal-BPF-selftest-prog.patch
@@ -0,0 +1,56 @@
+From 70414cacbe536a197d56f58a42f9563e5a01b8ec Mon Sep 17 00:00:00 2001
+From: David Vernet <void@manifault.com>
+Date: Mon, 9 Dec 2024 09:29:24 -0600
+Subject: [PATCH] scx: Fix maximal BPF selftest prog
+
+maximal.bpf.c is still dispatching to and consuming from SCX_DSQ_GLOBAL.
+Let's have it use its own DSQ to avoid any runtime errors.
+
+Signed-off-by: David Vernet <void@manifault.com>
+---
+ tools/testing/selftests/sched_ext/maximal.bpf.c | 8 +++++---
+ 1 file changed, 5 insertions(+), 3 deletions(-)
+
+diff --git a/tools/testing/selftests/sched_ext/maximal.bpf.c b/tools/testing/selftests/sched_ext/maximal.bpf.c
+index 4c005fa71810..430f5e13bf55 100644
+--- a/tools/testing/selftests/sched_ext/maximal.bpf.c
++++ b/tools/testing/selftests/sched_ext/maximal.bpf.c
+@@ -12,6 +12,8 @@
+ 
+ char _license[] SEC("license") = "GPL";
+ 
++#define DSQ_ID 0
++
+ s32 BPF_STRUCT_OPS(maximal_select_cpu, struct task_struct *p, s32 prev_cpu,
+ 		   u64 wake_flags)
+ {
+@@ -20,7 +22,7 @@ s32 BPF_STRUCT_OPS(maximal_select_cpu, struct task_struct *p, s32 prev_cpu,
+ 
+ void BPF_STRUCT_OPS(maximal_enqueue, struct task_struct *p, u64 enq_flags)
+ {
+-	scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
++	scx_bpf_dsq_insert(p, DSQ_ID, SCX_SLICE_DFL, enq_flags);
+ }
+ 
+ void BPF_STRUCT_OPS(maximal_dequeue, struct task_struct *p, u64 deq_flags)
+@@ -28,7 +30,7 @@ void BPF_STRUCT_OPS(maximal_dequeue, struct task_struct *p, u64 deq_flags)
+ 
+ void BPF_STRUCT_OPS(maximal_dispatch, s32 cpu, struct task_struct *prev)
+ {
+-	scx_bpf_dsq_move_to_local(SCX_DSQ_GLOBAL);
++	scx_bpf_dsq_move_to_local(DSQ_ID);
+ }
+ 
+ void BPF_STRUCT_OPS(maximal_runnable, struct task_struct *p, u64 enq_flags)
+@@ -123,7 +125,7 @@ void BPF_STRUCT_OPS(maximal_cgroup_set_weight, struct cgroup *cgrp, u32 weight)
+ 
+ s32 BPF_STRUCT_OPS_SLEEPABLE(maximal_init)
+ {
+-	return 0;
++	return scx_bpf_create_dsq(DSQ_ID, -1);
+ }
+ 
+ void BPF_STRUCT_OPS(maximal_exit, struct scx_exit_info *info)
+-- 
+2.47.1
+
diff --git a/ci/vmtest/configs/DENYLIST b/ci/vmtest/configs/DENYLIST
new file mode 100644
index 0000000000000..2f9bf5c0aa016
--- /dev/null
+++ b/ci/vmtest/configs/DENYLIST
@@ -0,0 +1,15 @@
+# TEMPORARY
+btf_dump/btf_dump: syntax
+kprobe_multi_bench_attach
+core_reloc/enum64val
+core_reloc/size___diff_sz
+core_reloc/type_based___diff_sz
+test_ima	# All of CI is broken on it following 6.3-rc1 merge
+
+lwt_reroute      # crashes kernel after netnext merge from 2ab1efad60ad "net/sched: cls_api: complement tcf_tfilter_dump_policy"
+tc_links_ingress # started failing after net-next merge from 2ab1efad60ad "net/sched: cls_api: complement tcf_tfilter_dump_policy"
+xdp_bonding/xdp_bonding_features     # started failing after net merge from 359e54a93ab4 "l2tp: pass correct message length to ip6_append_data"
+tc_redirect/tc_redirect_dtime # uapi breakage after net-next commit 885c36e59f46 ("net: Re-use and set mono_delivery_time bit for userspace tstamp packets")
+migrate_reuseport/IPv4 TCP_NEW_SYN_RECV reqsk_timer_handler # flaky, under investigation
+migrate_reuseport/IPv6 TCP_NEW_SYN_RECV reqsk_timer_handler # flaky, under investigation
+connect_force_port # unreliably fails
diff --git a/ci/vmtest/configs/DENYLIST.aarch64 b/ci/vmtest/configs/DENYLIST.aarch64
new file mode 100644
index 0000000000000..487b19ede4b61
--- /dev/null
+++ b/ci/vmtest/configs/DENYLIST.aarch64
@@ -0,0 +1,4 @@
+cgrp_local_storage                  # libbpf: prog 'update_cookie_tracing': failed to attach: ERROR: strerror_r(-524)=22
+core_reloc_btfgen                   # run_core_reloc_tests:FAIL:run_btfgen unexpected error: 32512 (errno 22)
+usdt/multispec                      # usdt_300_bad_attach unexpected pointer: 0x558c63d8f0
+xdp_bonding                         # whole test suite is very unstable on aarch64
diff --git a/ci/vmtest/configs/DENYLIST.rc b/ci/vmtest/configs/DENYLIST.rc
new file mode 100644
index 0000000000000..8aa33e6b71443
--- /dev/null
+++ b/ci/vmtest/configs/DENYLIST.rc
@@ -0,0 +1,3 @@
+send_signal/send_signal_nmi            # PMU events configure correctly but don't trigger NMI's for some reason (AMD nested virt)
+send_signal/send_signal_nmi_thread     # Same as above
+token/obj_priv_implicit_token_envvar   # Unknown root cause, but reliably fails
diff --git a/ci/vmtest/configs/DENYLIST.s390x b/ci/vmtest/configs/DENYLIST.s390x
new file mode 100644
index 0000000000000..9b90b615aea55
--- /dev/null
+++ b/ci/vmtest/configs/DENYLIST.s390x
@@ -0,0 +1,11 @@
+deny_namespace                           # not yet in bpf denylist
+tc_redirect/tc_redirect_dtime            # very flaky
+lru_bug                                  # not yet in bpf-next denylist
+# Disabled temporarily for a crash.
+# https://lore.kernel.org/bpf/c9923c1d-971d-4022-8dc8-1364e929d34c@gmail.com/
+dummy_st_ops/dummy_init_ptr_arg
+fexit_bpf2bpf
+tailcalls
+trace_ext
+xdp_bpf2bpf
+xdp_metadata
diff --git a/ci/vmtest/configs/DENYLIST.test_progs-bpf_gcc b/ci/vmtest/configs/DENYLIST.test_progs-bpf_gcc
new file mode 100644
index 0000000000000..a3c745d1f5b52
--- /dev/null
+++ b/ci/vmtest/configs/DENYLIST.test_progs-bpf_gcc
@@ -0,0 +1,904 @@
+arena_htab
+async_stack_depth
+bad_struct_ops/invalid_prog_reuse
+bpf_cookie
+bpf_iter/bpf_hash_map
+bpf_iter/ksym
+bpf_iter/tcp4
+bpf_iter/tcp6
+bpf_iter/udp4
+bpf_iter/udp6
+bpf_iter/unix
+bpf_iter_setsockopt
+bpf_iter_setsockopt_unix
+bpf_mod_race
+bpf_nf/tc-bpf-ct
+bpf_nf/xdp-ct
+bpf_tcp_ca/cubic
+btf_dump/btf_dump: bitfields
+btf_dump/btf_dump: packing
+btf_dump/btf_dump: padding
+btf_dump/btf_dump: syntax
+btf_map_in_map
+cb_refs
+cgroup_get_current_cgroup_id
+cgroup_iter/cgroup_iter__self_only_css_task
+cgroup_tcp_skb
+cgrp_kfunc
+cls_redirect/cls_redirect_dynptr
+connect_force_port
+core_autosize
+core_read_macros
+core_reloc/type_id
+core_reloc/type_id___missing_targets
+core_reloc_btfgen/type_id
+core_reloc_btfgen/type_id___missing_targets
+cpumask/test_acquire_wrong_cpumask
+cpumask/test_alloc_double_release
+cpumask/test_alloc_free_cpumask
+cpumask/test_alloc_no_release
+cpumask/test_and_or_xor
+cpumask/test_copy_any_anyand
+cpumask/test_cpumask_null
+cpumask/test_cpumask_weight
+cpumask/test_first_firstzero_cpu
+cpumask/test_firstand_nocpu
+cpumask/test_global_mask_array_l2_rcu
+cpumask/test_global_mask_array_one_rcu
+cpumask/test_global_mask_array_rcu
+cpumask/test_global_mask_nested_deep_array_rcu
+cpumask/test_global_mask_nested_deep_rcu
+cpumask/test_global_mask_nested_rcu
+cpumask/test_global_mask_no_null_check
+cpumask/test_global_mask_out_of_rcu
+cpumask/test_global_mask_rcu
+cpumask/test_global_mask_rcu_no_null_check
+cpumask/test_insert_leave
+cpumask/test_insert_remove_no_release
+cpumask/test_insert_remove_release
+cpumask/test_intersects_subset
+cpumask/test_invalid_nested_array
+cpumask/test_mutate_cpumask
+cpumask/test_set_clear_cpu
+cpumask/test_setall_clear_cpu
+cpumask/test_test_and_set_clear
+crypto_basic/crypto_acquire
+crypto_sanity
+deny_namespace
+dummy_st_ops/test_unsupported_field_sleepable
+dynptr/add_dynptr_to_map1
+dynptr/add_dynptr_to_map2
+dynptr/clone_invalid1
+dynptr/clone_invalid2
+dynptr/clone_invalidate1
+dynptr/clone_invalidate2
+dynptr/clone_invalidate3
+dynptr/clone_invalidate4
+dynptr/clone_invalidate5
+dynptr/clone_invalidate6
+dynptr/clone_skb_packet_data
+dynptr/clone_xdp_packet_data
+dynptr/data_slice_missing_null_check1
+dynptr/data_slice_missing_null_check2
+dynptr/data_slice_out_of_bounds_map_value
+dynptr/data_slice_out_of_bounds_ringbuf
+dynptr/data_slice_out_of_bounds_skb
+dynptr/data_slice_use_after_release1
+dynptr/data_slice_use_after_release2
+dynptr/dynptr_adjust_invalid
+dynptr/dynptr_from_mem_invalid_api
+dynptr/dynptr_invalidate_slice_failure
+dynptr/dynptr_invalidate_slice_or_null
+dynptr/dynptr_invalidate_slice_reinit
+dynptr/dynptr_is_null_invalid
+dynptr/dynptr_is_rdonly_invalid
+dynptr/dynptr_overwrite_ref
+dynptr/dynptr_partial_slot_invalidate
+dynptr/dynptr_pruning_overwrite
+dynptr/dynptr_pruning_type_confusion
+dynptr/dynptr_read_into_slot
+dynptr/dynptr_size_invalid
+dynptr/dynptr_slice_var_len1
+dynptr/dynptr_slice_var_len2
+dynptr/dynptr_var_off_overwrite
+dynptr/global
+dynptr/invalid_data_slices
+dynptr/invalid_helper1
+dynptr/invalid_helper2
+dynptr/invalid_offset
+dynptr/invalid_read1
+dynptr/invalid_read2
+dynptr/invalid_read3
+dynptr/invalid_read4
+dynptr/invalid_slice_rdwr_rdonly
+dynptr/invalid_write1
+dynptr/invalid_write2
+dynptr/invalid_write3
+dynptr/invalid_write4
+dynptr/release_twice
+dynptr/release_twice_callback
+dynptr/ringbuf_invalid_api
+dynptr/ringbuf_missing_release1
+dynptr/ringbuf_missing_release2
+dynptr/ringbuf_missing_release_callback
+dynptr/ringbuf_release_uninit_dynptr
+dynptr/skb_invalid_ctx
+dynptr/skb_invalid_ctx_fentry
+dynptr/skb_invalid_ctx_fexit
+dynptr/skb_invalid_data_slice1
+dynptr/skb_invalid_data_slice2
+dynptr/skb_invalid_data_slice3
+dynptr/skb_invalid_data_slice4
+dynptr/skb_invalid_slice_write
+dynptr/test_dynptr_reg_type
+dynptr/test_dynptr_skb_no_buff
+dynptr/test_dynptr_skb_small_buff
+dynptr/test_dynptr_skb_tp_btf
+dynptr/test_read_write
+dynptr/uninit_write_into_slot
+dynptr/use_after_invalid
+dynptr/xdp_invalid_ctx
+dynptr/xdp_invalid_data_slice1
+dynptr/xdp_invalid_data_slice2
+exceptions/check_assert_eq_int_max
+exceptions/check_assert_eq_int_min
+exceptions/check_assert_eq_llong_max
+exceptions/check_assert_eq_llong_min
+exceptions/check_assert_eq_zero
+exceptions/check_assert_ge_neg
+exceptions/check_assert_ge_pos
+exceptions/check_assert_ge_zero
+exceptions/check_assert_generic
+exceptions/check_assert_gt_neg
+exceptions/check_assert_gt_pos
+exceptions/check_assert_gt_zero
+exceptions/check_assert_le_neg
+exceptions/check_assert_le_pos
+exceptions/check_assert_le_zero
+exceptions/check_assert_lt_neg
+exceptions/check_assert_lt_pos
+exceptions/check_assert_lt_zero
+exceptions/check_assert_range_s64
+exceptions/check_assert_range_u64
+exceptions/check_assert_single_range_s64
+exceptions/check_assert_single_range_u64
+exceptions/check_assert_with_return
+exceptions/exception_ext
+exceptions/exception_ext_mod_cb_runtime
+exceptions/non-throwing extension -> non-throwing subprog
+exceptions/non-throwing extension -> throwing global subprog
+exceptions/non-throwing fentry -> exception_cb
+exceptions/non-throwing fexit -> exception_cb
+exceptions/non-throwing fmod_ret -> non-throwing global subprog
+exceptions/reject_async_callback_throw
+exceptions/reject_exception_throw_cb
+exceptions/reject_exception_throw_cb_diff
+exceptions/reject_set_exception_cb_bad_ret2
+exceptions/reject_subprog_with_lock
+exceptions/reject_subprog_with_rcu_read_lock
+exceptions/reject_with_cb
+exceptions/reject_with_cb_reference
+exceptions/reject_with_lock
+exceptions/reject_with_rbtree_add_throw
+exceptions/reject_with_rcu_read_lock
+exceptions/reject_with_reference
+exceptions/reject_with_subprog_reference
+exceptions/throwing extension (with custom cb) -> exception_cb
+exceptions/throwing extension -> global func in exception_cb
+exceptions/throwing extension -> non-throwing global subprog
+exceptions/throwing extension -> throwing global subprog
+exceptions/throwing fentry -> exception_cb
+exceptions/throwing fexit -> exception_cb
+failures_wq
+fexit_bpf2bpf/fmod_ret_freplace
+fexit_bpf2bpf/func_replace
+fexit_bpf2bpf/func_replace_global_func
+fexit_bpf2bpf/func_replace_multi
+fexit_bpf2bpf/func_sockmap_update
+fexit_bpf2bpf/target_yes_callees
+global_func_dead_code
+global_map_resize
+inner_array_lookup
+irq/irq_flag_overwrite
+irq/irq_flag_overwrite_partial
+irq/irq_global_subprog
+irq/irq_ooo_refs_array
+irq/irq_restore_4_subprog
+irq/irq_restore_bad_arg
+irq/irq_restore_invalid
+irq/irq_restore_iter
+irq/irq_restore_missing_1_subprog
+irq/irq_restore_missing_2
+irq/irq_restore_missing_2_subprog
+irq/irq_restore_missing_3
+irq/irq_restore_missing_3_minus_2
+irq/irq_restore_missing_3_minus_2_subprog
+irq/irq_restore_missing_3_subprog
+irq/irq_restore_ooo
+irq/irq_restore_ooo_3
+irq/irq_restore_ooo_3_subprog
+irq/irq_save_bad_arg
+irq/irq_save_invalid
+irq/irq_save_iter
+irq/irq_sleepable_helper
+irq/irq_sleepable_kfunc
+iters/compromise_iter_w_direct_write_and_skip_destroy_fail
+iters/compromise_iter_w_direct_write_fail
+iters/compromise_iter_w_helper_write_fail
+iters/create_and_forget_to_destroy_fail
+iters/css_task
+iters/delayed_precision_mark
+iters/delayed_read_mark
+iters/destroy_without_creating_fail
+iters/double_create_fail
+iters/double_destroy_fail
+iters/iter_css_lock_and_unlock
+iters/iter_css_task_for_each
+iters/iter_css_without_lock
+iters/iter_destroy_bad_arg
+iters/iter_err_too_permissive1
+iters/iter_err_too_permissive2
+iters/iter_err_too_permissive3
+iters/iter_err_unsafe_asm_loop
+iters/iter_err_unsafe_c_loop
+iters/iter_nested_iters
+iters/iter_new_bad_arg
+iters/iter_next_bad_arg
+iters/iter_next_ptr_mem_not_trusted
+iters/iter_next_rcu_not_trusted
+iters/iter_next_rcu_or_null
+iters/iter_next_trusted_or_null
+iters/iter_obfuscate_counter
+iters/iter_subprog_iters
+iters/iter_tasks_lock_and_unlock
+iters/iter_tasks_without_lock
+iters/leak_iter_from_subprog_fail
+iters/loop_state_deps1
+iters/loop_state_deps2
+iters/missing_null_check_fail
+iters/next_after_destroy_fail
+iters/next_without_new_fail
+iters/read_from_iter_slot_fail
+iters/stacksafe_should_not_conflate_stack_spill_and_iter
+iters/testmod_seq_getter_after_bad
+iters/testmod_seq_getter_before_bad
+iters/wrong_sized_read_fail
+jeq_infer_not_null
+jit_probe_mem
+kfree_skb
+kfunc_call/kfunc_call_ctx
+kfunc_call/kfunc_call_test1
+kfunc_call/kfunc_call_test2
+kfunc_call/kfunc_call_test4
+kfunc_call/kfunc_call_test_get_mem
+kfunc_call/kfunc_call_test_ref_btf_id
+kfunc_call/kfunc_call_test_static_unused_arg
+kfunc_call/kfunc_syscall_test
+kfunc_call/kfunc_syscall_test_null
+kfunc_dynptr_param/not_ptr_to_stack
+kfunc_dynptr_param/not_valid_dynptr
+kfunc_param_nullable/kfunc_dynptr_nullable_test3
+kprobe_multi_test/kprobe_session_return_2
+kptr_xchg_inline
+l4lb_all/l4lb_noinline
+l4lb_all/l4lb_noinline_dynptr
+linked_list
+local_kptr_stash/drop_rb_node_off
+local_kptr_stash/local_kptr_stash_local_with_root
+local_kptr_stash/local_kptr_stash_plain
+local_kptr_stash/local_kptr_stash_simple
+local_kptr_stash/local_kptr_stash_unstash
+local_kptr_stash/refcount_acquire_without_unstash
+local_kptr_stash/stash_rb_nodes
+log_buf/obj_load_log_buf
+log_fixup/bad_core_relo_subprog
+log_fixup/bad_core_relo_trunc_full
+lru_bug
+map_btf
+map_in_map/acc_map_in_array
+map_in_map/acc_map_in_htab
+map_in_map/sleepable_acc_map_in_array
+map_in_map/sleepable_acc_map_in_htab
+map_kptr/correct_btf_id_check_size
+map_kptr/inherit_untrusted_on_walk
+map_kptr/kptr_xchg_possibly_null
+map_kptr/kptr_xchg_ref_state
+map_kptr/mark_ref_as_untrusted_or_null
+map_kptr/marked_as_untrusted_or_null
+map_kptr/non_const_var_off
+map_kptr/non_const_var_off_kptr_xchg
+map_kptr/reject_bad_type_xchg
+map_kptr/reject_kptr_xchg_on_unref
+map_kptr/reject_member_of_ref_xchg
+map_kptr/reject_untrusted_xchg
+map_kptr/success-map
+map_ptr
+nested_trust/test_invalid_nested_user_cpus
+nested_trust/test_invalid_skb_field
+percpu_alloc/array
+percpu_alloc/array_sleepable
+percpu_alloc/cgrp_local_storage
+percpu_alloc/test_array_map_1
+percpu_alloc/test_array_map_2
+percpu_alloc/test_array_map_3
+percpu_alloc/test_array_map_4
+percpu_alloc/test_array_map_5
+percpu_alloc/test_array_map_6
+percpu_alloc/test_array_map_7
+percpu_alloc/test_array_map_8
+perf_branches/perf_branches_no_hw
+pkt_access
+preempt_lock/preempt_global_subprog_test
+preempt_lock/preempt_lock_missing_1
+preempt_lock/preempt_lock_missing_1_subprog
+preempt_lock/preempt_lock_missing_2
+preempt_lock/preempt_lock_missing_2_minus_1_subprog
+preempt_lock/preempt_lock_missing_2_subprog
+preempt_lock/preempt_lock_missing_3
+preempt_lock/preempt_lock_missing_3_minus_2
+preempt_lock/preempt_sleepable_helper
+preempt_lock/preempt_sleepable_kfunc
+preempted_bpf_ma_op
+prog_run_opts
+prog_tests_framework
+raw_tp_null
+rbtree_fail
+rbtree_success
+recursion
+refcounted_kptr
+refcounted_kptr_fail
+refcounted_kptr_wrong_owner
+reference_tracking/sk_lookup_success
+ringbuf_multi
+setget_sockopt
+sk_lookup
+skc_to_unix_sock
+sock_addr/recvmsg4: attach prog with wrong attach type
+sock_addr/recvmsg4: recvfrom (dgram)
+sock_addr/recvmsg6: attach prog with wrong attach type
+sock_addr/recvmsg6: recvfrom (dgram)
+sock_addr/sendmsg4: attach prog with wrong attach type
+sock_addr/sendmsg4: kernel_sendmsg (dgram)
+sock_addr/sendmsg4: kernel_sendmsg deny (dgram)
+sock_addr/sendmsg4: sendmsg (dgram)
+sock_addr/sendmsg4: sendmsg deny (dgram)
+sock_addr/sendmsg4: sock_sendmsg (dgram)
+sock_addr/sendmsg4: sock_sendmsg deny (dgram)
+sock_addr/sendmsg6: attach prog with wrong attach type
+sock_addr/sendmsg6: kernel_sendmsg (dgram)
+sock_addr/sendmsg6: kernel_sendmsg [::] (BSD'ism) (dgram)
+sock_addr/sendmsg6: kernel_sendmsg deny (dgram)
+sock_addr/sendmsg6: sendmsg (dgram)
+sock_addr/sendmsg6: sendmsg IPv4-mapped IPv6 (dgram)
+sock_addr/sendmsg6: sendmsg [::] (BSD'ism) (dgram)
+sock_addr/sendmsg6: sendmsg deny (dgram)
+sock_addr/sendmsg6: sendmsg dst IP = [::] (BSD'ism) (dgram)
+sock_addr/sendmsg6: sock_sendmsg (dgram)
+sock_addr/sendmsg6: sock_sendmsg [::] (BSD'ism) (dgram)
+sock_addr/sendmsg6: sock_sendmsg deny (dgram)
+sock_destroy/trace_tcp_destroy_sock
+sock_fields
+sockmap_listen/sockhash IPv4 TCP test_reuseport_mixed_groups
+sockmap_listen/sockhash IPv4 TCP test_reuseport_select_connected
+sockmap_listen/sockhash IPv4 UDP test_reuseport_mixed_groups
+sockmap_listen/sockhash IPv4 UDP test_reuseport_select_connected
+sockmap_listen/sockhash IPv6 TCP test_reuseport_mixed_groups
+sockmap_listen/sockhash IPv6 TCP test_reuseport_select_connected
+sockmap_listen/sockhash IPv6 UDP test_reuseport_mixed_groups
+sockmap_listen/sockhash IPv6 UDP test_reuseport_select_connected
+sockmap_listen/sockmap IPv4 TCP test_reuseport_mixed_groups
+sockmap_listen/sockmap IPv4 TCP test_reuseport_select_connected
+sockmap_listen/sockmap IPv4 UDP test_reuseport_mixed_groups
+sockmap_listen/sockmap IPv4 UDP test_reuseport_select_connected
+sockmap_listen/sockmap IPv6 TCP test_reuseport_mixed_groups
+sockmap_listen/sockmap IPv6 TCP test_reuseport_select_connected
+sockmap_listen/sockmap IPv6 UDP test_reuseport_mixed_groups
+sockmap_listen/sockmap IPv6 UDP test_reuseport_select_connected
+spin_lock
+struct_ops_module/unsupported_ops
+syscall
+tailcalls/classifier_0
+tailcalls/classifier_1
+tailcalls/reject_tail_call_preempt_lock
+tailcalls/reject_tail_call_rcu_lock
+tailcalls/reject_tail_call_ref
+tailcalls/reject_tail_call_spin_lock
+tailcalls/tailcall_6
+tailcalls/tailcall_bpf2bpf_2
+tailcalls/tailcall_bpf2bpf_3
+tailcalls/tailcall_bpf2bpf_fentry
+tailcalls/tailcall_bpf2bpf_fentry_entry
+tailcalls/tailcall_bpf2bpf_fentry_fexit
+tailcalls/tailcall_bpf2bpf_fexit
+tailcalls/tailcall_bpf2bpf_hierarchy_2
+tailcalls/tailcall_bpf2bpf_hierarchy_3
+task_kfunc
+task_local_storage/uptr_across_pages
+task_local_storage/uptr_basic
+task_local_storage/uptr_kptr_xchg
+task_local_storage/uptr_map_failure_e2big
+task_local_storage/uptr_map_failure_kstruct
+task_local_storage/uptr_map_failure_size0
+task_local_storage/uptr_no_null_check
+task_local_storage/uptr_obj_new
+task_local_storage/uptr_update_failure
+tc_bpf/tc_bpf_non_root
+tc_redirect/tc_redirect_dtime
+tcp_custom_syncookie
+tcp_hdr_options
+test_bpf_ma
+test_global_funcs/arg_tag_ctx_kprobe
+test_global_funcs/arg_tag_ctx_perf
+test_global_funcs/arg_tag_ctx_raw_tp
+test_global_funcs/global_func1
+test_global_funcs/global_func10
+test_global_funcs/global_func11
+test_global_funcs/global_func12
+test_global_funcs/global_func13
+test_global_funcs/global_func14
+test_global_funcs/global_func15
+test_global_funcs/global_func15_tricky_pruning
+test_global_funcs/global_func17
+test_global_funcs/global_func3
+test_global_funcs/global_func5
+test_global_funcs/global_func6
+test_global_funcs/global_func7
+test_lsm/lsm_basic
+test_profiler
+test_strncmp/strncmp_bad_not_null_term_target
+timer
+timer_mim
+token
+tp_btf_nullable/handle_tp_btf_nullable_bare1
+tunnel
+uprobe_multi_test/uprobe_sesison_return_2
+user_ringbuf/user_ringbuf_callback_bad_access1
+user_ringbuf/user_ringbuf_callback_bad_access2
+user_ringbuf/user_ringbuf_callback_const_ptr_to_dynptr_reg_off
+user_ringbuf/user_ringbuf_callback_discard_dynptr
+user_ringbuf/user_ringbuf_callback_invalid_return
+user_ringbuf/user_ringbuf_callback_null_context_read
+user_ringbuf/user_ringbuf_callback_null_context_write
+user_ringbuf/user_ringbuf_callback_reinit_dynptr_mem
+user_ringbuf/user_ringbuf_callback_reinit_dynptr_ringbuf
+user_ringbuf/user_ringbuf_callback_submit_dynptr
+user_ringbuf/user_ringbuf_callback_write_forbidden
+verif_scale_pyperf100
+verif_scale_pyperf180
+verif_scale_pyperf600
+verif_scale_pyperf600_nounroll
+verif_scale_seg6_loop
+verif_scale_strobemeta
+verif_scale_strobemeta_nounroll1
+verif_scale_strobemeta_nounroll2
+verif_scale_strobemeta_subprogs
+verif_scale_sysctl_loop1
+verif_scale_sysctl_loop2
+verif_scale_xdp_loop
+verifier_and/invalid_and_of_negative_number
+verifier_and/invalid_range_check
+verifier_arena/iter_maps2
+verifier_arena/iter_maps3
+verifier_array_access/a_read_only_array_1_2
+verifier_array_access/a_read_only_array_2_2
+verifier_array_access/a_write_only_array_1_2
+verifier_array_access/a_write_only_array_2_2
+verifier_array_access/an_array_with_a_constant_2
+verifier_array_access/an_array_with_a_register_2
+verifier_array_access/an_array_with_a_variable_2
+verifier_array_access/array_with_no_floor_check
+verifier_array_access/with_a_invalid_max_check_1
+verifier_array_access/with_a_invalid_max_check_2
+verifier_basic_stack/invalid_fp_arithmetic
+verifier_basic_stack/misaligned_read_from_stack
+verifier_basic_stack/stack_out_of_bounds
+verifier_bitfield_write
+verifier_bits_iter/destroy_uninit
+verifier_bits_iter/next_uninit
+verifier_bits_iter/no_destroy
+verifier_bounds/bounds_map_value_variant_1
+verifier_bounds/bounds_map_value_variant_2
+verifier_bounds/of_boundary_crossing_range_1
+verifier_bounds/of_boundary_crossing_range_2
+verifier_bounds/on_sign_extended_mov_test1
+verifier_bounds/on_sign_extended_mov_test2
+verifier_bounds/reg32_any_reg32_xor_3
+verifier_bounds/reg_any_reg_xor_3
+verifier_bounds/shift_of_maybe_negative_number
+verifier_bounds/shift_with_64_bit_input
+verifier_bounds/shift_with_oversized_count_operand
+verifier_bounds/size_signed_32bit_overflow_test1
+verifier_bounds/size_signed_32bit_overflow_test2
+verifier_bounds/size_signed_32bit_overflow_test3
+verifier_bounds/size_signed_32bit_overflow_test4
+verifier_bounds/var_off_insn_off_test1
+verifier_bounds/var_off_insn_off_test2
+verifier_bounds_deduction/deducing_bounds_from_const_1
+verifier_bounds_deduction/deducing_bounds_from_const_10
+verifier_bounds_deduction/deducing_bounds_from_const_3
+verifier_bounds_deduction/deducing_bounds_from_const_5
+verifier_bounds_deduction/deducing_bounds_from_const_6
+verifier_bounds_deduction/deducing_bounds_from_const_7
+verifier_bounds_deduction/deducing_bounds_from_const_8
+verifier_bounds_deduction/deducing_bounds_from_const_9
+verifier_bounds_mix_sign_unsign/checks_mixing_signed_and_unsigned
+verifier_bounds_mix_sign_unsign/signed_and_unsigned_positive_bounds
+verifier_bounds_mix_sign_unsign/signed_and_unsigned_variant_10
+verifier_bounds_mix_sign_unsign/signed_and_unsigned_variant_11
+verifier_bounds_mix_sign_unsign/signed_and_unsigned_variant_12
+verifier_bounds_mix_sign_unsign/signed_and_unsigned_variant_13
+verifier_bounds_mix_sign_unsign/signed_and_unsigned_variant_14
+verifier_bounds_mix_sign_unsign/signed_and_unsigned_variant_15
+verifier_bounds_mix_sign_unsign/signed_and_unsigned_variant_2
+verifier_bounds_mix_sign_unsign/signed_and_unsigned_variant_3
+verifier_bounds_mix_sign_unsign/signed_and_unsigned_variant_5
+verifier_bounds_mix_sign_unsign/signed_and_unsigned_variant_6
+verifier_bounds_mix_sign_unsign/signed_and_unsigned_variant_8
+verifier_btf_ctx_access/ctx_access_u32_pointer_reject_16
+verifier_btf_ctx_access/ctx_access_u32_pointer_reject_32
+verifier_btf_ctx_access/ctx_access_u32_pointer_reject_8
+verifier_cfg/conditional_loop
+verifier_cfg/loop2_back_edge
+verifier_cfg/loop_back_edge
+verifier_cfg/out_of_range_jump
+verifier_cfg/out_of_range_jump2
+verifier_cfg/uncond_loop_after_cond_jmp
+verifier_cfg/uncond_loop_in_subprog_after_cond_jmp
+verifier_cfg/unreachable
+verifier_cfg/unreachable2
+verifier_cgroup_inv_retcode/with_invalid_return_code_test1
+verifier_cgroup_inv_retcode/with_invalid_return_code_test3
+verifier_cgroup_inv_retcode/with_invalid_return_code_test5
+verifier_cgroup_inv_retcode/with_invalid_return_code_test6
+verifier_cgroup_inv_retcode/with_invalid_return_code_test7
+verifier_cgroup_skb/data_meta_for_cgroup_skb
+verifier_cgroup_skb/flow_keys_for_cgroup_skb
+verifier_cgroup_skb/napi_id_for_cgroup_skb
+verifier_cgroup_skb/tc_classid_for_cgroup_skb
+verifier_cgroup_storage/cpu_cgroup_storage_access_1
+verifier_cgroup_storage/cpu_cgroup_storage_access_2
+verifier_cgroup_storage/cpu_cgroup_storage_access_3
+verifier_cgroup_storage/cpu_cgroup_storage_access_4
+verifier_cgroup_storage/cpu_cgroup_storage_access_5
+verifier_cgroup_storage/cpu_cgroup_storage_access_6
+verifier_cgroup_storage/invalid_cgroup_storage_access_1
+verifier_cgroup_storage/invalid_cgroup_storage_access_2
+verifier_cgroup_storage/invalid_cgroup_storage_access_3
+verifier_cgroup_storage/invalid_cgroup_storage_access_4
+verifier_cgroup_storage/invalid_cgroup_storage_access_5
+verifier_cgroup_storage/invalid_cgroup_storage_access_6
+verifier_const/bprm
+verifier_const/tcx1
+verifier_const/tcx4
+verifier_const/tcx7
+verifier_const_or/not_bypass_stack_boundary_checks_1
+verifier_const_or/not_bypass_stack_boundary_checks_2
+verifier_ctx/context_stores_via_bpf_atomic
+verifier_ctx/ctx_pointer_to_helper_1
+verifier_ctx/ctx_pointer_to_helper_2
+verifier_ctx/ctx_pointer_to_helper_3
+verifier_ctx/make_ptr_to_ctx_unusable
+verifier_ctx/null_check_4_ctx_const
+verifier_ctx/null_check_8_null_bind
+verifier_ctx/or_null_check_3_1
+verifier_ctx_sk_msg/of_size_in_sk_msg
+verifier_ctx_sk_msg/past_end_of_sk_msg
+verifier_ctx_sk_msg/read_offset_in_sk_msg
+verifier_d_path/d_path_reject
+verifier_direct_packet_access/access_test15_spill_with_xadd
+verifier_direct_packet_access/direct_packet_access_test3
+verifier_direct_packet_access/id_in_regsafe_bad_access
+verifier_direct_packet_access/packet_access_test10_write_invalid
+verifier_direct_packet_access/pkt_end_reg_bad_access
+verifier_direct_packet_access/pkt_end_reg_both_accesses
+verifier_direct_packet_access/test16_arith_on_data_end
+verifier_direct_packet_access/test23_x_pkt_ptr_4
+verifier_direct_packet_access/test26_marking_on_bad_access
+verifier_direct_packet_access/test28_marking_on_bad_access
+verifier_direct_stack_access_wraparound
+verifier_global_ptr_args
+verifier_global_subprogs
+verifier_helper_access_var_len/bitwise_and_jmp_wrong_max
+verifier_helper_access_var_len/jmp_signed_no_min_check
+verifier_helper_access_var_len/map_adjusted_jmp_wrong_max
+verifier_helper_access_var_len/memory_map_jmp_wrong_max
+verifier_helper_access_var_len/memory_stack_jmp_bounds_offset
+verifier_helper_access_var_len/memory_stack_jmp_wrong_max
+verifier_helper_access_var_len/ptr_to_mem_or_null_2
+verifier_helper_access_var_len/ptr_to_mem_or_null_8
+verifier_helper_access_var_len/ptr_to_mem_or_null_9
+verifier_helper_access_var_len/stack_jmp_no_max_check
+verifier_helper_packet_access/cls_helper_fail_range_1
+verifier_helper_packet_access/cls_helper_fail_range_2
+verifier_helper_packet_access/cls_helper_fail_range_3
+verifier_helper_packet_access/packet_ptr_with_bad_range_1
+verifier_helper_packet_access/packet_ptr_with_bad_range_2
+verifier_helper_packet_access/packet_test2_unchecked_packet_ptr
+verifier_helper_packet_access/ptr_with_too_short_range_1
+verifier_helper_packet_access/ptr_with_too_short_range_2
+verifier_helper_packet_access/test11_cls_unsuitable_helper_1
+verifier_helper_packet_access/test12_cls_unsuitable_helper_2
+verifier_helper_packet_access/test15_cls_helper_fail_sub
+verifier_helper_packet_access/test20_pkt_end_as_input
+verifier_helper_packet_access/test7_cls_unchecked_packet_ptr
+verifier_helper_packet_access/to_packet_test21_wrong_reg
+verifier_helper_restricted
+verifier_helper_value_access/access_to_map_empty_range
+verifier_helper_value_access/access_to_map_negative_range
+verifier_helper_value_access/access_to_map_possibly_empty_range
+verifier_helper_value_access/access_to_map_wrong_size
+verifier_helper_value_access/bounds_check_using_bad_access_1
+verifier_helper_value_access/bounds_check_using_bad_access_2
+verifier_helper_value_access/check_using_s_bad_access_1
+verifier_helper_value_access/check_using_s_bad_access_2
+verifier_helper_value_access/const_imm_negative_range_adjustment_1
+verifier_helper_value_access/const_imm_negative_range_adjustment_2
+verifier_helper_value_access/const_reg_negative_range_adjustment_1
+verifier_helper_value_access/const_reg_negative_range_adjustment_2
+verifier_helper_value_access/imm_out_of_bound_1
+verifier_helper_value_access/imm_out_of_bound_2
+verifier_helper_value_access/imm_out_of_bound_range
+verifier_helper_value_access/map_out_of_bound_range
+verifier_helper_value_access/map_via_variable_empty_range
+verifier_helper_value_access/reg_out_of_bound_1
+verifier_helper_value_access/reg_out_of_bound_2
+verifier_helper_value_access/reg_out_of_bound_range
+verifier_helper_value_access/via_const_imm_empty_range
+verifier_helper_value_access/via_const_reg_empty_range
+verifier_helper_value_access/via_variable_no_max_check_1
+verifier_helper_value_access/via_variable_no_max_check_2
+verifier_helper_value_access/via_variable_wrong_max_check_1
+verifier_helper_value_access/via_variable_wrong_max_check_2
+verifier_int_ptr/arg_ptr_to_long_misaligned
+verifier_int_ptr/to_long_size_sizeof_long
+verifier_iterating_callbacks/bpf_loop_iter_limit_overflow
+verifier_iterating_callbacks/check_add_const_3regs
+verifier_iterating_callbacks/check_add_const_3regs_2if
+verifier_iterating_callbacks/check_add_const_regsafe_off
+verifier_iterating_callbacks/iter_limit_bug
+verifier_iterating_callbacks/jgt_imm64_and_may_goto
+verifier_iterating_callbacks/loop_detection
+verifier_iterating_callbacks/may_goto_self
+verifier_iterating_callbacks/unsafe_find_vma
+verifier_iterating_callbacks/unsafe_for_each_map_elem
+verifier_iterating_callbacks/unsafe_on_2nd_iter
+verifier_iterating_callbacks/unsafe_on_zero_iter
+verifier_iterating_callbacks/unsafe_ringbuf_drain
+verifier_jeq_infer_not_null/unchanged_for_jeq_false_branch
+verifier_jeq_infer_not_null/unchanged_for_jne_true_branch
+verifier_kfunc_prog_types/cgrp_kfunc_raw_tp
+verifier_kfunc_prog_types/cpumask_kfunc_raw_tp
+verifier_kfunc_prog_types/task_kfunc_raw_tp
+verifier_ld_ind/ind_check_calling_conv_r1
+verifier_ld_ind/ind_check_calling_conv_r2
+verifier_ld_ind/ind_check_calling_conv_r3
+verifier_ld_ind/ind_check_calling_conv_r4
+verifier_ld_ind/ind_check_calling_conv_r5
+verifier_leak_ptr/leak_pointer_into_ctx_1
+verifier_leak_ptr/leak_pointer_into_ctx_2
+verifier_linked_scalars
+verifier_loops1/bounded_recursion
+verifier_loops1/infinite_loop_in_two_jumps
+verifier_loops1/infinite_loop_three_jump_trick
+verifier_loops1/loop_after_a_conditional_jump
+verifier_lsm/bool_retval_test3
+verifier_lsm/bool_retval_test4
+verifier_lsm/disabled_hook_test1
+verifier_lsm/disabled_hook_test2
+verifier_lsm/disabled_hook_test3
+verifier_lsm/errno_zero_retval_test4
+verifier_lsm/errno_zero_retval_test5
+verifier_lsm/errno_zero_retval_test6
+verifier_lwt/not_permitted_for_lwt_prog
+verifier_lwt/packet_write_for_lwt_in
+verifier_lwt/packet_write_for_lwt_out
+verifier_lwt/tc_classid_for_lwt_in
+verifier_lwt/tc_classid_for_lwt_out
+verifier_lwt/tc_classid_for_lwt_xmit
+verifier_map_in_map/invalid_inner_map_pointer
+verifier_map_in_map/on_the_inner_map_pointer
+verifier_map_ptr/bpf_map_ptr_write_rejected
+verifier_map_ptr/read_non_existent_field_rejected
+verifier_map_ptr/read_with_negative_offset_rejected
+verifier_map_ptr_mixing
+verifier_map_ret_val
+verifier_meta_access/meta_access_test10
+verifier_meta_access/meta_access_test2
+verifier_meta_access/meta_access_test3
+verifier_meta_access/meta_access_test4
+verifier_meta_access/meta_access_test5
+verifier_meta_access/meta_access_test6
+verifier_meta_access/meta_access_test9
+verifier_netfilter_ctx/with_invalid_ctx_access_test1
+verifier_netfilter_ctx/with_invalid_ctx_access_test2
+verifier_netfilter_ctx/with_invalid_ctx_access_test3
+verifier_netfilter_ctx/with_invalid_ctx_access_test4
+verifier_netfilter_ctx/with_invalid_ctx_access_test5
+verifier_netfilter_retcode/with_invalid_return_code_test1
+verifier_netfilter_retcode/with_invalid_return_code_test4
+verifier_or_jmp32_k
+verifier_prevent_map_lookup
+verifier_raw_stack/bytes_spilled_regs_corruption_2
+verifier_raw_stack/load_bytes_invalid_access_1
+verifier_raw_stack/load_bytes_invalid_access_2
+verifier_raw_stack/load_bytes_invalid_access_3
+verifier_raw_stack/load_bytes_invalid_access_4
+verifier_raw_stack/load_bytes_invalid_access_5
+verifier_raw_stack/load_bytes_invalid_access_6
+verifier_raw_stack/load_bytes_negative_len_2
+verifier_raw_stack/load_bytes_spilled_regs_corruption
+verifier_raw_stack/skb_load_bytes_negative_len
+verifier_raw_stack/skb_load_bytes_zero_len
+verifier_raw_tp_writable
+verifier_ref_tracking
+verifier_reg_equal/subreg_equality_2
+verifier_regalloc/regalloc_and_spill_negative
+verifier_regalloc/regalloc_negative
+verifier_regalloc/regalloc_src_reg_negative
+verifier_ringbuf/ringbuf_invalid_reservation_offset_1
+verifier_ringbuf/ringbuf_invalid_reservation_offset_2
+verifier_runtime_jit
+verifier_scalar_ids/check_ids_in_regsafe
+verifier_scalar_ids/check_ids_in_regsafe_2
+verifier_scalar_ids/linked_regs_broken_link_2
+verifier_search_pruning/for_u32_spills_u64_fill
+verifier_search_pruning/liveness_pruning_and_write_screening
+verifier_search_pruning/short_loop1
+verifier_search_pruning/should_be_verified_nop_operation
+verifier_search_pruning/tracking_for_u32_spill_fill
+verifier_search_pruning/varlen_map_value_access_pruning
+verifier_sock/bpf_sk_fullsock_skb_sk
+verifier_sock/bpf_sk_release_skb_sk
+verifier_sock/bpf_tcp_sock_skb_sk
+verifier_sock/dst_port_byte_load_invalid
+verifier_sock/dst_port_half_load_invalid_1
+verifier_sock/dst_port_half_load_invalid_2
+verifier_sock/invalidate_pkt_pointers_by_tail_call
+verifier_sock/invalidate_pkt_pointers_from_global_func
+verifier_sock/map_lookup_elem_smap_key
+verifier_sock/map_lookup_elem_sockhash_key
+verifier_sock/map_lookup_elem_sockmap_key
+verifier_sock/no_null_check_on_ret_1
+verifier_sock/no_null_check_on_ret_2
+verifier_sock/of_bpf_skc_to_helpers
+verifier_sock/post_bind4_read_mark
+verifier_sock/post_bind4_read_src_ip6
+verifier_sock/post_bind6_read_src_ip4
+verifier_sock/sk_1_1_value_1
+verifier_sock/sk_no_skb_sk_check_1
+verifier_sock/sk_no_skb_sk_check_2
+verifier_sock/sk_sk_type_fullsock_field_1
+verifier_sock/skb_sk_beyond_last_field_1
+verifier_sock/skb_sk_beyond_last_field_2
+verifier_sock/skb_sk_no_null_check
+verifier_sock/sock_create_read_src_port
+verifier_sock_addr/bind4_bad_return_code
+verifier_sock_addr/bind6_bad_return_code
+verifier_sock_addr/connect4_bad_return_code
+verifier_sock_addr/connect6_bad_return_code
+verifier_sock_addr/connect_unix_bad_return_code
+verifier_sock_addr/getpeername4_bad_return_code
+verifier_sock_addr/getpeername6_bad_return_code
+verifier_sock_addr/getpeername_unix_bad_return_code
+verifier_sock_addr/getsockname4_bad_return_code
+verifier_sock_addr/getsockname6_bad_return_code
+verifier_sock_addr/getsockname_unix_unix_bad_return_code
+verifier_sock_addr/recvmsg4_bad_return_code
+verifier_sock_addr/recvmsg6_bad_return_code
+verifier_sock_addr/recvmsg_unix_bad_return_code
+verifier_sock_addr/sendmsg4_bad_return_code
+verifier_sock_addr/sendmsg6_bad_return_code
+verifier_sock_addr/sendmsg_unix_bad_return_code
+verifier_sockmap_mutate/test_flow_dissector_update
+verifier_sockmap_mutate/test_raw_tp_delete
+verifier_sockmap_mutate/test_raw_tp_update
+verifier_sockmap_mutate/test_sockops_update
+verifier_spill_fill/_6_offset_to_skb_data
+verifier_spill_fill/addr_offset_to_skb_data
+verifier_spill_fill/check_corrupted_spill_fill
+verifier_spill_fill/fill_32bit_after_spill_64bit_clear_id
+verifier_spill_fill/spill_16bit_of_32bit_fail
+verifier_spill_fill/spill_32bit_of_64bit_fail
+verifier_spill_fill/u64_offset_to_skb_data
+verifier_spill_fill/with_invalid_reg_offset_0
+verifier_spin_lock/call_within_a_locked_region
+verifier_spin_lock/lock_test2_direct_ld_st
+verifier_spin_lock/lock_test3_direct_ld_st
+verifier_spin_lock/lock_test4_direct_ld_st
+verifier_spin_lock/lock_test7_unlock_without_lock
+verifier_spin_lock/reg_id_for_map_value
+verifier_spin_lock/spin_lock_test6_missing_unlock
+verifier_spin_lock/spin_lock_test8_double_lock
+verifier_spin_lock/spin_lock_test9_different_lock
+verifier_spin_lock/test11_ld_abs_under_lock
+verifier_stack_ptr/load_bad_alignment_on_off
+verifier_stack_ptr/load_bad_alignment_on_reg
+verifier_stack_ptr/load_out_of_bounds_high
+verifier_stack_ptr/load_out_of_bounds_low
+verifier_stack_ptr/to_stack_check_high_4
+verifier_stack_ptr/to_stack_check_high_5
+verifier_stack_ptr/to_stack_check_high_6
+verifier_stack_ptr/to_stack_check_high_7
+verifier_stack_ptr/to_stack_check_low_3
+verifier_stack_ptr/to_stack_check_low_4
+verifier_stack_ptr/to_stack_check_low_5
+verifier_stack_ptr/to_stack_check_low_6
+verifier_stack_ptr/to_stack_check_low_7
+verifier_subprog_precision/callback_precise_return_fail
+verifier_tailcall_jit
+verifier_uninit
+verifier_unpriv
+verifier_unpriv_perf
+verifier_value/store_of_cleared_call_register
+verifier_value_illegal_alu
+verifier_value_or_null/map_access_from_else_condition
+verifier_value_or_null/map_value_or_null_1
+verifier_value_or_null/map_value_or_null_2
+verifier_value_or_null/map_value_or_null_3
+verifier_value_or_null/multiple_map_lookup_elem_calls
+verifier_value_or_null/null_check_ids_in_regsafe
+verifier_value_ptr_arith/access_known_scalar_value_ptr_2
+verifier_value_ptr_arith/access_unknown_scalar_value_ptr
+verifier_value_ptr_arith/access_value_ptr_known_scalar
+verifier_value_ptr_arith/access_value_ptr_unknown_scalar
+verifier_value_ptr_arith/access_value_ptr_value_ptr_1
+verifier_value_ptr_arith/access_value_ptr_value_ptr_2
+verifier_value_ptr_arith/lower_oob_arith_test_1
+verifier_value_ptr_arith/to_leak_tainted_dst_reg
+verifier_value_ptr_arith/unknown_scalar_value_ptr_4
+verifier_value_ptr_arith/value_ptr_known_scalar_2_1
+verifier_value_ptr_arith/value_ptr_known_scalar_3
+verifier_var_off/access_max_out_of_bound
+verifier_var_off/access_min_out_of_bound
+verifier_var_off/stack_write_clobbers_spilled_regs
+verifier_var_off/variable_offset_ctx_access
+verifier_var_off/variable_offset_stack_access_unbounded
+verifier_var_off/zero_sized_access_max_out_of_bound
+verifier_vfs_reject
+verifier_xadd/xadd_w_check_unaligned_map
+verifier_xadd/xadd_w_check_unaligned_pkt
+verifier_xadd/xadd_w_check_unaligned_stack
+verifier_xdp_direct_packet_access/corner_case_1_bad_access_1
+verifier_xdp_direct_packet_access/corner_case_1_bad_access_10
+verifier_xdp_direct_packet_access/corner_case_1_bad_access_11
+verifier_xdp_direct_packet_access/corner_case_1_bad_access_12
+verifier_xdp_direct_packet_access/corner_case_1_bad_access_13
+verifier_xdp_direct_packet_access/corner_case_1_bad_access_14
+verifier_xdp_direct_packet_access/corner_case_1_bad_access_15
+verifier_xdp_direct_packet_access/corner_case_1_bad_access_16
+verifier_xdp_direct_packet_access/corner_case_1_bad_access_2
+verifier_xdp_direct_packet_access/corner_case_1_bad_access_3
+verifier_xdp_direct_packet_access/corner_case_1_bad_access_4
+verifier_xdp_direct_packet_access/corner_case_1_bad_access_5
+verifier_xdp_direct_packet_access/corner_case_1_bad_access_6
+verifier_xdp_direct_packet_access/corner_case_1_bad_access_7
+verifier_xdp_direct_packet_access/corner_case_1_bad_access_8
+verifier_xdp_direct_packet_access/corner_case_1_bad_access_9
+verifier_xdp_direct_packet_access/end_mangling_bad_access_1
+verifier_xdp_direct_packet_access/end_mangling_bad_access_2
+verifier_xdp_direct_packet_access/pkt_data_bad_access_1_1
+verifier_xdp_direct_packet_access/pkt_data_bad_access_1_2
+verifier_xdp_direct_packet_access/pkt_data_bad_access_1_3
+verifier_xdp_direct_packet_access/pkt_data_bad_access_1_4
+verifier_xdp_direct_packet_access/pkt_data_bad_access_2_1
+verifier_xdp_direct_packet_access/pkt_data_bad_access_2_2
+verifier_xdp_direct_packet_access/pkt_data_bad_access_2_3
+verifier_xdp_direct_packet_access/pkt_data_bad_access_2_4
+verifier_xdp_direct_packet_access/pkt_data_bad_access_2_5
+verifier_xdp_direct_packet_access/pkt_data_bad_access_2_6
+verifier_xdp_direct_packet_access/pkt_data_bad_access_2_7
+verifier_xdp_direct_packet_access/pkt_data_bad_access_2_8
+verifier_xdp_direct_packet_access/pkt_end_bad_access_1_1
+verifier_xdp_direct_packet_access/pkt_end_bad_access_1_2
+verifier_xdp_direct_packet_access/pkt_end_bad_access_2_1
+verifier_xdp_direct_packet_access/pkt_end_bad_access_2_2
+verifier_xdp_direct_packet_access/pkt_end_bad_access_2_3
+verifier_xdp_direct_packet_access/pkt_end_bad_access_2_4
+verifier_xdp_direct_packet_access/pkt_meta_bad_access_1_1
+verifier_xdp_direct_packet_access/pkt_meta_bad_access_1_2
+verifier_xdp_direct_packet_access/pkt_meta_bad_access_2_1
+verifier_xdp_direct_packet_access/pkt_meta_bad_access_2_2
+verifier_xdp_direct_packet_access/pkt_meta_bad_access_2_3
+verifier_xdp_direct_packet_access/pkt_meta_bad_access_2_4
+verify_pkcs7_sig
+xdp_synproxy
diff --git a/ci/vmtest/configs/DENYLIST.x86_64 b/ci/vmtest/configs/DENYLIST.x86_64
new file mode 100644
index 0000000000000..6fc3413daab9f
--- /dev/null
+++ b/ci/vmtest/configs/DENYLIST.x86_64
@@ -0,0 +1 @@
+netcnt              # with kvm enabled, fail with packets unexpected packets: actual 10001 != expected 10000
diff --git a/ci/vmtest/configs/run-vmtest.env b/ci/vmtest/configs/run-vmtest.env
new file mode 100644
index 0000000000000..c60f1db6673c7
--- /dev/null
+++ b/ci/vmtest/configs/run-vmtest.env
@@ -0,0 +1,42 @@
+#!/bin/bash
+
+# This file is sourced by libbpf/ci/run-vmtest Github Action scripts.
+#
+# The primary reason it exists is that assembling ALLOWLIST and
+# DENYLIST for a particular test run is not a trivial operation.
+#
+# Users of libbpf/ci/run-vmtest action need to be able to specify a
+# list of allow/denylist **files**, that later has to be correctly
+# merged into a single allow/denylist passed to a test runner.
+#
+# Obviously it's perferrable for the scripts merging many lists into
+# one to be reusable, and not copy-pasted between repositories which
+# use libbpf/ci actions. And specifying the lists should be trivial.
+# This file is a solution to that.
+
+# $SELFTESTS_BPF and $VMTEST_CONFIGS are set in the workflow, before
+# libbpf/ci/run-vmtest action is called
+# See .github/workflows/kernel-test.yml
+
+ALLOWLIST_FILES=(
+    "${SELFTESTS_BPF}/ALLOWLIST"
+    "${SELFTESTS_BPF}/ALLOWLIST.${ARCH}"
+    "${VMTEST_CONFIGS}/ALLOWLIST"
+    "${VMTEST_CONFIGS}/ALLOWLIST.${ARCH}"
+    "${VMTEST_CONFIGS}/ALLOWLIST.${DEPLOYMENT}"
+    "${VMTEST_CONFIGS}/ALLOWLIST.${KERNEL_TEST}"
+)
+
+DENYLIST_FILES=(
+    "${SELFTESTS_BPF}/DENYLIST"
+    "${SELFTESTS_BPF}/DENYLIST.${ARCH}"
+    "${VMTEST_CONFIGS}/DENYLIST"
+    "${VMTEST_CONFIGS}/DENYLIST.${ARCH}"
+    "${VMTEST_CONFIGS}/DENYLIST.${DEPLOYMENT}"
+    "${VMTEST_CONFIGS}/DENYLIST.${KERNEL_TEST}"
+)
+
+# Export pipe-separated strings, because bash doesn't support array export
+export SELFTESTS_BPF_ALLOWLIST_FILES=$(IFS="|"; echo "${ALLOWLIST_FILES[*]}")
+export SELFTESTS_BPF_DENYLIST_FILES=$(IFS="|"; echo "${DENYLIST_FILES[*]}")
+
diff --git a/ci/vmtest/configs/run_veristat.kernel.cfg b/ci/vmtest/configs/run_veristat.kernel.cfg
new file mode 100644
index 0000000000000..807efc251073f
--- /dev/null
+++ b/ci/vmtest/configs/run_veristat.kernel.cfg
@@ -0,0 +1,4 @@
+VERISTAT_OBJECTS_DIR="${SELFTESTS_BPF}"
+VERISTAT_OBJECTS_GLOB="*.bpf.o"
+VERISTAT_CFG_FILE="${SELFTESTS_BPF}/veristat.cfg"
+VERISTAT_OUTPUT="veristat-kernel"
diff --git a/ci/vmtest/configs/run_veristat.meta.cfg b/ci/vmtest/configs/run_veristat.meta.cfg
new file mode 100644
index 0000000000000..14f08d241d206
--- /dev/null
+++ b/ci/vmtest/configs/run_veristat.meta.cfg
@@ -0,0 +1,4 @@
+VERISTAT_OBJECTS_DIR="${WORKING_DIR}/bpf_objects"
+VERISTAT_OBJECTS_GLOB="*.o"
+VERISTAT_OUTPUT="veristat-meta"
+VERISTAT_CFG_FILE="${VERISTAT_CONFIGS}/veristat_meta.cfg"
diff --git a/ci/vmtest/configs/veristat_meta.cfg b/ci/vmtest/configs/veristat_meta.cfg
new file mode 100644
index 0000000000000..a8c25d71cb9e2
--- /dev/null
+++ b/ci/vmtest/configs/veristat_meta.cfg
@@ -0,0 +1,10 @@
+# List of exceptions we know about that are not going to work with veristat.
+
+# needs 'migrate_misplaced_page' which went away in
+# commit 73eab3ca481e ("mm: migrate: convert migrate_misplaced_page() to migrate_misplaced_folio()")
+!numamove_bpf-numamove_bpf.o
+
+# use non-libbpf loader
+!takeover_bpf_lib-takeover.bpf.o
+!tcp_tuner_bpf_lib-tcptuner.bpf.o
+

From a46de9e55cf6744ccfb7f3692bcc6433ebf5d5df Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Fri, 25 Oct 2024 14:20:53 +0200
Subject: [PATCH 1150/1173] uprobes: Rename arch_uretprobe_trampoline function

We are about to add uprobe trampoline, so cleaning up the namespace.

Acked-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 arch/x86/kernel/uprobes.c | 2 +-
 include/linux/uprobes.h   | 2 +-
 kernel/events/uprobes.c   | 4 ++--
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 9194695662b26..39521f1c4185e 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -338,7 +338,7 @@ extern u8 uretprobe_trampoline_entry[];
 extern u8 uretprobe_trampoline_end[];
 extern u8 uretprobe_syscall_check[];
 
-void *arch_uprobe_trampoline(unsigned long *psize)
+void *arch_uretprobe_trampoline(unsigned long *psize)
 {
 	static uprobe_opcode_t insn = UPROBE_SWBP_INSN;
 	struct pt_regs *regs = task_pt_regs(current);
diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index 2e46b69ff0a6f..37cd745640b8e 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -224,7 +224,7 @@ extern bool arch_uprobe_ignore(struct arch_uprobe *aup, struct pt_regs *regs);
 extern void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
 					 void *src, unsigned long len);
 extern void uprobe_handle_trampoline(struct pt_regs *regs);
-extern void *arch_uprobe_trampoline(unsigned long *psize);
+extern void *arch_uretprobe_trampoline(unsigned long *psize);
 extern unsigned long uprobe_get_trampoline_vaddr(void);
 #else /* !CONFIG_UPROBES */
 struct uprobes_state {
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 70c84b9d7be3b..e160445e7d07d 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1708,7 +1708,7 @@ static int xol_add_vma(struct mm_struct *mm, struct xol_area *area)
 	return ret;
 }
 
-void * __weak arch_uprobe_trampoline(unsigned long *psize)
+void * __weak arch_uretprobe_trampoline(unsigned long *psize)
 {
 	static uprobe_opcode_t insn = UPROBE_SWBP_INSN;
 
@@ -1740,7 +1740,7 @@ static struct xol_area *__create_xol_area(unsigned long vaddr)
 	init_waitqueue_head(&area->wq);
 	/* Reserve the 1st slot for get_trampoline_vaddr() */
 	set_bit(0, area->bitmap);
-	insns = arch_uprobe_trampoline(&insns_size);
+	insns = arch_uretprobe_trampoline(&insns_size);
 	arch_uprobe_copy_ixol(area->page, 0, insns, insns_size);
 
 	if (!xol_add_vma(mm, area))

From a5c7dbec15bb4bb9f01bb855939f315f94985cd5 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 23 Oct 2024 23:16:23 +0200
Subject: [PATCH 1151/1173] uprobes: Make copy_from_page global

Making copy_from_page global and adding uprobe prefix.
Adding the uprobe prefix to copy_to_page as well for symmetry.

Acked-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 include/linux/uprobes.h |  1 +
 kernel/events/uprobes.c | 16 ++++++++--------
 2 files changed, 9 insertions(+), 8 deletions(-)

diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index 37cd745640b8e..38803e8c8c3d9 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -226,6 +226,7 @@ extern void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
 extern void uprobe_handle_trampoline(struct pt_regs *regs);
 extern void *arch_uretprobe_trampoline(unsigned long *psize);
 extern unsigned long uprobe_get_trampoline_vaddr(void);
+extern void uprobe_copy_from_page(struct page *page, unsigned long vaddr, void *dst, int len);
 #else /* !CONFIG_UPROBES */
 struct uprobes_state {
 };
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index e160445e7d07d..5c9fc31c50f19 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -250,14 +250,14 @@ bool __weak is_trap_insn(uprobe_opcode_t *insn)
 	return is_swbp_insn(insn);
 }
 
-static void copy_from_page(struct page *page, unsigned long vaddr, void *dst, int len)
+void uprobe_copy_from_page(struct page *page, unsigned long vaddr, void *dst, int len)
 {
 	void *kaddr = kmap_atomic(page);
 	memcpy(dst, kaddr + (vaddr & ~PAGE_MASK), len);
 	kunmap_atomic(kaddr);
 }
 
-static void copy_to_page(struct page *page, unsigned long vaddr, const void *src, int len)
+static void uprobe_copy_to_page(struct page *page, unsigned long vaddr, const void *src, int len)
 {
 	void *kaddr = kmap_atomic(page);
 	memcpy(kaddr + (vaddr & ~PAGE_MASK), src, len);
@@ -278,7 +278,7 @@ static int verify_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t
 	 * is a trap variant; uprobes always wins over any other (gdb)
 	 * breakpoint.
 	 */
-	copy_from_page(page, vaddr, &old_opcode, UPROBE_SWBP_INSN_SIZE);
+	uprobe_copy_from_page(page, vaddr, &old_opcode, UPROBE_SWBP_INSN_SIZE);
 	is_swbp = is_swbp_insn(&old_opcode);
 
 	if (is_swbp_insn(new_opcode)) {
@@ -530,7 +530,7 @@ int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
 
 	__SetPageUptodate(new_page);
 	copy_highpage(new_page, old_page);
-	copy_to_page(new_page, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE);
+	uprobe_copy_to_page(new_page, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE);
 
 	if (!is_register) {
 		struct page *orig_page;
@@ -1036,7 +1036,7 @@ static int __copy_insn(struct address_space *mapping, struct file *filp,
 	if (IS_ERR(page))
 		return PTR_ERR(page);
 
-	copy_from_page(page, offset, insn, nbytes);
+	uprobe_copy_from_page(page, offset, insn, nbytes);
 	put_page(page);
 
 	return 0;
@@ -1380,7 +1380,7 @@ struct uprobe *uprobe_register(struct inode *inode,
 		return ERR_PTR(-EINVAL);
 
 	/*
-	 * This ensures that copy_from_page(), copy_to_page() and
+	 * This ensures that uprobe_copy_from_page(), uprobe_copy_to_page() and
 	 * __update_ref_ctr() can't cross page boundary.
 	 */
 	if (!IS_ALIGNED(offset, UPROBE_SWBP_INSN_SIZE))
@@ -1869,7 +1869,7 @@ void __weak arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
 				  void *src, unsigned long len)
 {
 	/* Initialize the slot */
-	copy_to_page(page, vaddr, src, len);
+	uprobe_copy_to_page(page, vaddr, src, len);
 
 	/*
 	 * We probably need flush_icache_user_page() but it needs vma.
@@ -2364,7 +2364,7 @@ static int is_trap_at_addr(struct mm_struct *mm, unsigned long vaddr)
 	if (result < 0)
 		return result;
 
-	copy_from_page(page, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE);
+	uprobe_copy_from_page(page, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE);
 	put_page(page);
  out:
 	/* This needs to return true for any variant of the trap insn */

From 8c838ba7b2b95572509e1a430913ce023e3fa030 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Sat, 4 Jan 2025 17:42:18 +0100
Subject: [PATCH 1152/1173] uprobes: Move ref_ctr_offset update out of
 uprobe_write_opcode

The uprobe_write_opcode function currently updates also refctr offset
if there's one defined for uprobe.

This is not handy for following changes which needs to make several
updates (writes) to install or remove uprobe, but update refctr offset
just once.

Adding set_swbp_refctr/set_orig_refctr which makes sure refctr offset
is updated.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 kernel/events/uprobes.c | 50 ++++++++++++++++++++++++++---------------
 1 file changed, 32 insertions(+), 18 deletions(-)

diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 5c9fc31c50f19..77b85b19f4c28 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -473,15 +473,13 @@ static int update_ref_ctr(struct uprobe *uprobe, struct mm_struct *mm,
 int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
 			unsigned long vaddr, uprobe_opcode_t opcode)
 {
-	struct uprobe *uprobe;
 	struct page *old_page, *new_page;
 	struct vm_area_struct *vma;
-	int ret, is_register, ref_ctr_updated = 0;
+	int ret, is_register;
 	bool orig_page_huge = false;
 	unsigned int gup_flags = FOLL_FORCE;
 
 	is_register = is_swbp_insn(&opcode);
-	uprobe = container_of(auprobe, struct uprobe, arch);
 
 retry:
 	if (is_register)
@@ -506,15 +504,6 @@ int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
 		goto put_old;
 	}
 
-	/* We are going to replace instruction, update ref_ctr. */
-	if (!ref_ctr_updated && uprobe->ref_ctr_offset) {
-		ret = update_ref_ctr(uprobe, mm, is_register ? 1 : -1);
-		if (ret)
-			goto put_old;
-
-		ref_ctr_updated = 1;
-	}
-
 	ret = 0;
 	if (!is_register && !PageAnon(old_page))
 		goto put_old;
@@ -565,10 +554,6 @@ int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
 	if (unlikely(ret == -EAGAIN))
 		goto retry;
 
-	/* Revert back reference counter if instruction update failed. */
-	if (ret && is_register && ref_ctr_updated)
-		update_ref_ctr(uprobe, mm, -1);
-
 	/* try collapse pmd for compound page */
 	if (!ret && orig_page_huge)
 		collapse_pte_mapped_thp(mm, vaddr, false);
@@ -590,6 +575,25 @@ int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned
 	return uprobe_write_opcode(auprobe, mm, vaddr, UPROBE_SWBP_INSN);
 }
 
+static int set_swbp_refctr(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vaddr)
+{
+	int err;
+
+	/* We are going to replace instruction, update ref_ctr. */
+	if (uprobe->ref_ctr_offset) {
+		err = update_ref_ctr(uprobe, mm, 1);
+		if (err)
+			return err;
+	}
+
+	err = set_swbp(&uprobe->arch, mm, vaddr);
+
+	/* Revert back reference counter if instruction update failed. */
+	if (err && uprobe->ref_ctr_offset)
+		update_ref_ctr(uprobe, mm, -1);
+	return err;
+}
+
 /**
  * set_orig_insn - Restore the original instruction.
  * @mm: the probed process address space.
@@ -606,6 +610,16 @@ set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long v
 			*(uprobe_opcode_t *)&auprobe->insn);
 }
 
+static int set_orig_refctr(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vaddr)
+{
+	int err = set_orig_insn(&uprobe->arch, mm, vaddr);
+
+	/* Revert back reference counter even if instruction update failed. */
+	if (uprobe->ref_ctr_offset)
+		update_ref_ctr(uprobe, mm, -1);
+	return err;
+}
+
 /* uprobe should have guaranteed positive refcount */
 static struct uprobe *get_uprobe(struct uprobe *uprobe)
 {
@@ -1142,7 +1156,7 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
 	if (first_uprobe)
 		set_bit(MMF_HAS_UPROBES, &mm->flags);
 
-	ret = set_swbp(&uprobe->arch, mm, vaddr);
+	ret = set_swbp_refctr(uprobe, mm, vaddr);
 	if (!ret)
 		clear_bit(MMF_RECALC_UPROBES, &mm->flags);
 	else if (first_uprobe)
@@ -1155,7 +1169,7 @@ static int
 remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vaddr)
 {
 	set_bit(MMF_RECALC_UPROBES, &mm->flags);
-	return set_orig_insn(&uprobe->arch, mm, vaddr);
+	return set_orig_refctr(uprobe, mm, vaddr);
 }
 
 struct map_info {

From c20c9a4c86ff481c2fc11d9e08558fceb569b2e2 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Mon, 17 Feb 2025 18:49:43 +0100
Subject: [PATCH 1153/1173] uprobes: Add uprobe_write function

Adding uprobe_write function that does what uprobe_write_opcode did
so far, but allows to pass verify callback function that checks the
memory location before writing the opcode.

It will be used in following changes to simplify the checking logic.

The uprobe_write_opcode now calls uprobe_write with verify_opcode as
the verify callback.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 include/linux/uprobes.h |  4 ++++
 kernel/events/uprobes.c | 13 ++++++++++---
 2 files changed, 14 insertions(+), 3 deletions(-)

diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index 38803e8c8c3d9..1dbaebc30ff9b 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -187,6 +187,8 @@ struct uprobes_state {
 	struct xol_area		*xol_area;
 };
 
+typedef int (*uprobe_write_verify_t)(struct page *page, unsigned long vaddr, uprobe_opcode_t *opcode);
+
 extern void __init uprobes_init(void);
 extern int set_swbp(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr);
 extern int set_orig_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr);
@@ -195,6 +197,8 @@ extern bool is_trap_insn(uprobe_opcode_t *insn);
 extern unsigned long uprobe_get_swbp_addr(struct pt_regs *regs);
 extern unsigned long uprobe_get_trap_addr(struct pt_regs *regs);
 extern int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t);
+extern int uprobe_write(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr,
+			uprobe_opcode_t *opcode, uprobe_write_verify_t verify);
 extern struct uprobe *uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc);
 extern int uprobe_apply(struct uprobe *uprobe, struct uprobe_consumer *uc, bool);
 extern void uprobe_unregister_nosync(struct uprobe *uprobe, struct uprobe_consumer *uc);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 77b85b19f4c28..546e8755cf6da 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -472,6 +472,13 @@ static int update_ref_ctr(struct uprobe *uprobe, struct mm_struct *mm,
  */
 int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
 			unsigned long vaddr, uprobe_opcode_t opcode)
+{
+	return uprobe_write(auprobe, mm, vaddr, &opcode, verify_opcode);
+}
+
+int uprobe_write(struct arch_uprobe *auprobe, struct mm_struct *mm,
+		 unsigned long vaddr, uprobe_opcode_t *opcode,
+		 uprobe_write_verify_t verify)
 {
 	struct page *old_page, *new_page;
 	struct vm_area_struct *vma;
@@ -479,7 +486,7 @@ int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
 	bool orig_page_huge = false;
 	unsigned int gup_flags = FOLL_FORCE;
 
-	is_register = is_swbp_insn(&opcode);
+	is_register = is_swbp_insn(opcode);
 
 retry:
 	if (is_register)
@@ -489,7 +496,7 @@ int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
 	if (IS_ERR(old_page))
 		return PTR_ERR(old_page);
 
-	ret = verify_opcode(old_page, vaddr, &opcode);
+	ret = verify(old_page, vaddr, opcode);
 	if (ret <= 0)
 		goto put_old;
 
@@ -519,7 +526,7 @@ int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
 
 	__SetPageUptodate(new_page);
 	copy_highpage(new_page, old_page);
-	uprobe_copy_to_page(new_page, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE);
+	uprobe_copy_to_page(new_page, vaddr, opcode, UPROBE_SWBP_INSN_SIZE);
 
 	if (!is_register) {
 		struct page *orig_page;

From 1132d4a7b62dbca6f5cdc9892afd8cd356102b8b Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Fri, 3 May 2024 00:45:39 +0200
Subject: [PATCH 1154/1173] uprobes: Add nbytes argument to uprobe_write_opcode

Adding nbytes argument to uprobe_write_opcode as preparation
for writing whole instructions in following changes.

Acked-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 include/linux/uprobes.h |  4 ++--
 kernel/events/uprobes.c | 14 +++++++-------
 2 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index 1dbaebc30ff9b..c69a057753943 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -187,7 +187,7 @@ struct uprobes_state {
 	struct xol_area		*xol_area;
 };
 
-typedef int (*uprobe_write_verify_t)(struct page *page, unsigned long vaddr, uprobe_opcode_t *opcode);
+typedef int (*uprobe_write_verify_t)(struct page *page, unsigned long vaddr, uprobe_opcode_t *opcode, int nbytes);
 
 extern void __init uprobes_init(void);
 extern int set_swbp(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr);
@@ -198,7 +198,7 @@ extern unsigned long uprobe_get_swbp_addr(struct pt_regs *regs);
 extern unsigned long uprobe_get_trap_addr(struct pt_regs *regs);
 extern int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t);
 extern int uprobe_write(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr,
-			uprobe_opcode_t *opcode, uprobe_write_verify_t verify);
+			uprobe_opcode_t *insn, int nbytes, uprobe_write_verify_t verify);
 extern struct uprobe *uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc);
 extern int uprobe_apply(struct uprobe *uprobe, struct uprobe_consumer *uc, bool);
 extern void uprobe_unregister_nosync(struct uprobe *uprobe, struct uprobe_consumer *uc);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 546e8755cf6da..7ff1f07c8f79e 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -264,7 +264,7 @@ static void uprobe_copy_to_page(struct page *page, unsigned long vaddr, const vo
 	kunmap_atomic(kaddr);
 }
 
-static int verify_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t *new_opcode)
+static int verify_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t *new_opcode, int nbytes)
 {
 	uprobe_opcode_t old_opcode;
 	bool is_swbp;
@@ -473,12 +473,12 @@ static int update_ref_ctr(struct uprobe *uprobe, struct mm_struct *mm,
 int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
 			unsigned long vaddr, uprobe_opcode_t opcode)
 {
-	return uprobe_write(auprobe, mm, vaddr, &opcode, verify_opcode);
+	return uprobe_write(auprobe, mm, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE, verify_opcode);
 }
 
 int uprobe_write(struct arch_uprobe *auprobe, struct mm_struct *mm,
-		 unsigned long vaddr, uprobe_opcode_t *opcode,
-		 uprobe_write_verify_t verify)
+		 unsigned long vaddr, uprobe_opcode_t *insn,
+		 int nbytes, uprobe_write_verify_t verify)
 {
 	struct page *old_page, *new_page;
 	struct vm_area_struct *vma;
@@ -486,7 +486,7 @@ int uprobe_write(struct arch_uprobe *auprobe, struct mm_struct *mm,
 	bool orig_page_huge = false;
 	unsigned int gup_flags = FOLL_FORCE;
 
-	is_register = is_swbp_insn(opcode);
+	is_register = is_swbp_insn(insn);
 
 retry:
 	if (is_register)
@@ -496,7 +496,7 @@ int uprobe_write(struct arch_uprobe *auprobe, struct mm_struct *mm,
 	if (IS_ERR(old_page))
 		return PTR_ERR(old_page);
 
-	ret = verify(old_page, vaddr, opcode);
+	ret = verify(old_page, vaddr, insn, nbytes);
 	if (ret <= 0)
 		goto put_old;
 
@@ -526,7 +526,7 @@ int uprobe_write(struct arch_uprobe *auprobe, struct mm_struct *mm,
 
 	__SetPageUptodate(new_page);
 	copy_highpage(new_page, old_page);
-	uprobe_copy_to_page(new_page, vaddr, opcode, UPROBE_SWBP_INSN_SIZE);
+	uprobe_copy_to_page(new_page, vaddr, insn, nbytes);
 
 	if (!is_register) {
 		struct page *orig_page;

From 24aedc06b4e252c932621f63501e200393dbeed8 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Sat, 4 Jan 2025 21:57:00 +0100
Subject: [PATCH 1155/1173] uprobes: Add orig argument to uprobe_write and
 uprobe_write_opcode

The uprobe_write has special path to restore the original page when
we write original instruction back.

This happens when uprobe_write detects that we want to write anything
else but breakpoint instruction.

In following changes we want to use uprobe_write function for multiple
updates, so adding new function argument to denote that this is the
original instruction update. This way uprobe_write can make appropriate
checks and restore the original page when possible.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 arch/arm/probes/uprobes/core.c |  2 +-
 include/linux/uprobes.h        |  5 +++--
 kernel/events/uprobes.c        | 22 ++++++++++------------
 3 files changed, 14 insertions(+), 15 deletions(-)

diff --git a/arch/arm/probes/uprobes/core.c b/arch/arm/probes/uprobes/core.c
index f5f790c6e5f89..54a90b5652858 100644
--- a/arch/arm/probes/uprobes/core.c
+++ b/arch/arm/probes/uprobes/core.c
@@ -30,7 +30,7 @@ int set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm,
 	     unsigned long vaddr)
 {
 	return uprobe_write_opcode(auprobe, mm, vaddr,
-		   __opcode_to_mem_arm(auprobe->bpinsn));
+		   __opcode_to_mem_arm(auprobe->bpinsn), false);
 }
 
 bool arch_uprobe_ignore(struct arch_uprobe *auprobe, struct pt_regs *regs)
diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index c69a057753943..1b6a4e2b54648 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -196,9 +196,10 @@ extern bool is_swbp_insn(uprobe_opcode_t *insn);
 extern bool is_trap_insn(uprobe_opcode_t *insn);
 extern unsigned long uprobe_get_swbp_addr(struct pt_regs *regs);
 extern unsigned long uprobe_get_trap_addr(struct pt_regs *regs);
-extern int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t);
+extern int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr,
+			       uprobe_opcode_t, bool);
 extern int uprobe_write(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr,
-			uprobe_opcode_t *insn, int nbytes, uprobe_write_verify_t verify);
+			uprobe_opcode_t *insn, int nbytes, uprobe_write_verify_t verify, bool orig);
 extern struct uprobe *uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc);
 extern int uprobe_apply(struct uprobe *uprobe, struct uprobe_consumer *uc, bool);
 extern void uprobe_unregister_nosync(struct uprobe *uprobe, struct uprobe_consumer *uc);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 7ff1f07c8f79e..92fed5e50ec15 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -471,25 +471,23 @@ static int update_ref_ctr(struct uprobe *uprobe, struct mm_struct *mm,
  * Return 0 (success) or a negative errno.
  */
 int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
-			unsigned long vaddr, uprobe_opcode_t opcode)
+			unsigned long vaddr, uprobe_opcode_t opcode, bool orig)
 {
-	return uprobe_write(auprobe, mm, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE, verify_opcode);
+	return uprobe_write(auprobe, mm, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE, verify_opcode, orig);
 }
 
 int uprobe_write(struct arch_uprobe *auprobe, struct mm_struct *mm,
 		 unsigned long vaddr, uprobe_opcode_t *insn,
-		 int nbytes, uprobe_write_verify_t verify)
+		 int nbytes, uprobe_write_verify_t verify, bool orig)
 {
 	struct page *old_page, *new_page;
 	struct vm_area_struct *vma;
-	int ret, is_register;
+	int ret;
 	bool orig_page_huge = false;
 	unsigned int gup_flags = FOLL_FORCE;
 
-	is_register = is_swbp_insn(insn);
-
 retry:
-	if (is_register)
+	if (!orig)
 		gup_flags |= FOLL_SPLIT_PMD;
 	/* Read the page with vaddr into memory */
 	old_page = get_user_page_vma_remote(mm, vaddr, gup_flags, &vma);
@@ -505,14 +503,14 @@ int uprobe_write(struct arch_uprobe *auprobe, struct mm_struct *mm,
 		goto put_old;
 	}
 
-	if (WARN(!is_register && PageCompound(old_page),
+	if (WARN(orig && PageCompound(old_page),
 		 "uprobe unregister should never work on compound page\n")) {
 		ret = -EINVAL;
 		goto put_old;
 	}
 
 	ret = 0;
-	if (!is_register && !PageAnon(old_page))
+	if (orig && !PageAnon(old_page))
 		goto put_old;
 
 	ret = anon_vma_prepare(vma);
@@ -528,7 +526,7 @@ int uprobe_write(struct arch_uprobe *auprobe, struct mm_struct *mm,
 	copy_highpage(new_page, old_page);
 	uprobe_copy_to_page(new_page, vaddr, insn, nbytes);
 
-	if (!is_register) {
+	if (orig) {
 		struct page *orig_page;
 		pgoff_t index;
 
@@ -579,7 +577,7 @@ int uprobe_write(struct arch_uprobe *auprobe, struct mm_struct *mm,
  */
 int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
 {
-	return uprobe_write_opcode(auprobe, mm, vaddr, UPROBE_SWBP_INSN);
+	return uprobe_write_opcode(auprobe, mm, vaddr, UPROBE_SWBP_INSN, false);
 }
 
 static int set_swbp_refctr(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vaddr)
@@ -614,7 +612,7 @@ int __weak
 set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
 {
 	return uprobe_write_opcode(auprobe, mm, vaddr,
-			*(uprobe_opcode_t *)&auprobe->insn);
+			*(uprobe_opcode_t *)&auprobe->insn, true);
 }
 
 static int set_orig_refctr(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vaddr)

From a6837d9e9ddb9cf9062ebda8565261adb615880e Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 12 Mar 2025 15:35:01 +0100
Subject: [PATCH 1156/1173] uprobes: Do breakpoint removal under
 mmap_write_lock

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 kernel/events/uprobes.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 92fed5e50ec15..bd4bc62f80d7c 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1465,7 +1465,7 @@ static int unapply_uprobe(struct uprobe *uprobe, struct mm_struct *mm)
 	struct vm_area_struct *vma;
 	int err = 0;
 
-	mmap_read_lock(mm);
+	mmap_write_lock(mm);
 	for_each_vma(vmi, vma) {
 		unsigned long vaddr;
 		loff_t offset;
@@ -1482,7 +1482,7 @@ static int unapply_uprobe(struct uprobe *uprobe, struct mm_struct *mm)
 		vaddr = offset_to_vaddr(vma, uprobe->offset);
 		err |= remove_breakpoint(uprobe, mm, vaddr);
 	}
-	mmap_read_unlock(mm);
+	mmap_write_unlock(mm);
 
 	return err;
 }

From 4d15721c904eb86346c2955b92bd20efbb8770a9 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Mon, 8 Apr 2024 13:59:22 +0200
Subject: [PATCH 1157/1173] uprobes/x86: Add uprobe syscall to speed up uprobe

Adding new uprobe syscall that calls uprobe handlers for given
'breakpoint' address.

The idea is that the 'breakpoint' address calls the user space
trampoline which executes the uprobe syscall.

The syscall handler reads the return address of the initial call
to retrieve the original 'breakpoint' address. With this address
we find the related uprobe object and call its consumers.

Adding the arch_uprobe_trampoline_mapping function that provides
uprobe trampoline mapping. This mapping is backed with one global
page initialized at __init time and shared by the all the mapping
instances.

We do not allow to execute uprobe syscall if the caller is not
from uprobe trampoline mapping.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 arch/x86/entry/syscalls/syscall_64.tbl |   1 +
 arch/x86/kernel/uprobes.c              | 134 +++++++++++++++++++++++++
 include/linux/syscalls.h               |   2 +
 include/linux/uprobes.h                |   1 +
 kernel/events/uprobes.c                |  22 ++++
 kernel/sys_ni.c                        |   1 +
 6 files changed, 161 insertions(+)

diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 5eb708bff1c79..88e388c7675b7 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -345,6 +345,7 @@
 333	common	io_pgetevents		sys_io_pgetevents
 334	common	rseq			sys_rseq
 335	common	uretprobe		sys_uretprobe
+336	common	uprobe			sys_uprobe
 # don't use numbers 387 through 423, add new calls after the last
 # 'common' entry
 424	common	pidfd_send_signal	sys_pidfd_send_signal
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 39521f1c4185e..b11dcd47edaa2 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -429,6 +429,140 @@ SYSCALL_DEFINE0(uretprobe)
 	return -1;
 }
 
+static int tramp_mremap(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma)
+{
+	return -EPERM;
+}
+
+static struct page *tramp_mapping_pages[2] __ro_after_init;
+
+static struct vm_special_mapping tramp_mapping = {
+	.name   = "[uprobes-trampoline]",
+	.mremap = tramp_mremap,
+	.pages  = tramp_mapping_pages,
+};
+
+static bool __in_uprobe_trampoline(unsigned long ip)
+{
+	struct vm_area_struct *vma = vma_lookup(current->mm, ip);
+
+	return vma && vma_is_special_mapping(vma, &tramp_mapping);
+}
+
+static bool in_uprobe_trampoline(unsigned long ip)
+{
+	struct mm_struct *mm = current->mm;
+	bool found, retry = true;
+	unsigned int seq;
+
+	rcu_read_lock();
+	if (mmap_lock_speculate_try_begin(mm, &seq)) {
+		found = __in_uprobe_trampoline(ip);
+		retry = mmap_lock_speculate_retry(mm, seq);
+	}
+	rcu_read_unlock();
+
+	if (retry) {
+		mmap_read_lock(mm);
+		found = __in_uprobe_trampoline(ip);
+		mmap_read_unlock(mm);
+	}
+	return found;
+}
+
+SYSCALL_DEFINE0(uprobe)
+{
+	struct pt_regs *regs = task_pt_regs(current);
+	unsigned long ip, sp, ax_r11_cx_ip[4];
+	int err;
+
+	/* Allow execution only from uprobe trampolines. */
+	if (!in_uprobe_trampoline(regs->ip))
+		goto sigill;
+
+	err = copy_from_user(ax_r11_cx_ip, (void __user *)regs->sp, sizeof(ax_r11_cx_ip));
+	if (err)
+		goto sigill;
+
+	ip = regs->ip;
+
+	/*
+	 * expose the "right" values of ax/r11/cx/ip/sp to uprobe_consumer/s, plus:
+	 * - adjust ip to the probe address, call saved next instruction address
+	 * - adjust sp to the probe's stack frame (check trampoline code)
+	 */
+	regs->ax  = ax_r11_cx_ip[0];
+	regs->r11 = ax_r11_cx_ip[1];
+	regs->cx  = ax_r11_cx_ip[2];
+	regs->ip  = ax_r11_cx_ip[3] - 5;
+	regs->sp += sizeof(ax_r11_cx_ip);
+	regs->orig_ax = -1;
+
+	sp = regs->sp;
+
+	handle_syscall_uprobe(regs, regs->ip);
+
+	/*
+	 * Some of the uprobe consumers has changed sp, we can do nothing,
+	 * just return via iret.
+	 */
+	if (regs->sp != sp)
+		return regs->ax;
+
+	regs->sp -= sizeof(ax_r11_cx_ip);
+
+	/* for the case uprobe_consumer has changed ax/r11/cx */
+	ax_r11_cx_ip[0] = regs->ax;
+	ax_r11_cx_ip[1] = regs->r11;
+	ax_r11_cx_ip[2] = regs->cx;
+
+	/* keep return address unless we are instructed otherwise */
+	if (ax_r11_cx_ip[3] - 5 != regs->ip)
+		ax_r11_cx_ip[3] = regs->ip;
+
+	regs->ip = ip;
+
+	err = copy_to_user((void __user *)regs->sp, ax_r11_cx_ip, sizeof(ax_r11_cx_ip));
+	if (err)
+		goto sigill;
+
+	/* ensure sysret, see do_syscall_64() */
+	regs->r11 = regs->flags;
+	regs->cx  = regs->ip;
+	return 0;
+
+sigill:
+	force_sig(SIGILL);
+	return -1;
+}
+
+asm (
+	".pushsection .rodata\n"
+	".balign " __stringify(PAGE_SIZE) "\n"
+	"uprobe_trampoline_entry:\n"
+	"push %rcx\n"
+	"push %r11\n"
+	"push %rax\n"
+	"movq $" __stringify(__NR_uprobe) ", %rax\n"
+	"syscall\n"
+	"pop %rax\n"
+	"pop %r11\n"
+	"pop %rcx\n"
+	"ret\n"
+	".balign " __stringify(PAGE_SIZE) "\n"
+	".popsection\n"
+);
+
+extern u8 uprobe_trampoline_entry[];
+
+static int __init arch_uprobes_init(void)
+{
+	tramp_mapping_pages[0] = virt_to_page(uprobe_trampoline_entry);
+	return 0;
+}
+
+late_initcall(arch_uprobes_init);
+
 /*
  * If arch_uprobe->insn doesn't use rip-relative addressing, return
  * immediately.  Otherwise, rewrite the instruction so that it accesses
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index c6333204d4513..002f4e1debe59 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -994,6 +994,8 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int on);
 
 asmlinkage long sys_uretprobe(void);
 
+asmlinkage long sys_uprobe(void);
+
 /* pciconfig: alpha, arm, arm64, ia64, sparc */
 asmlinkage long sys_pciconfig_read(unsigned long bus, unsigned long dfn,
 				unsigned long off, unsigned long len,
diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index 1b6a4e2b54648..4a2b950beefd5 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -232,6 +232,7 @@ extern void uprobe_handle_trampoline(struct pt_regs *regs);
 extern void *arch_uretprobe_trampoline(unsigned long *psize);
 extern unsigned long uprobe_get_trampoline_vaddr(void);
 extern void uprobe_copy_from_page(struct page *page, unsigned long vaddr, void *dst, int len);
+extern void handle_syscall_uprobe(struct pt_regs *regs, unsigned long bp_vaddr);
 #else /* !CONFIG_UPROBES */
 struct uprobes_state {
 };
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index bd4bc62f80d7c..4de04075576c2 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -2742,6 +2742,28 @@ static void handle_swbp(struct pt_regs *regs)
 	rcu_read_unlock_trace();
 }
 
+void handle_syscall_uprobe(struct pt_regs *regs, unsigned long bp_vaddr)
+{
+	struct uprobe *uprobe;
+	int is_swbp;
+
+	rcu_read_lock_trace();
+	uprobe = find_active_uprobe_rcu(bp_vaddr, &is_swbp);
+	if (!uprobe)
+		goto unlock;
+
+	if (!get_utask())
+		goto unlock;
+
+	if (arch_uprobe_ignore(&uprobe->arch, regs))
+		goto unlock;
+
+	handler_chain(uprobe, regs);
+
+ unlock:
+	rcu_read_unlock_trace();
+}
+
 /*
  * Perform required fix-ups and disable singlestep.
  * Allow pending signals to take effect.
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index c00a86931f8c6..bf5d05c635ffd 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -392,3 +392,4 @@ COND_SYSCALL(setuid16);
 COND_SYSCALL(rseq);
 
 COND_SYSCALL(uretprobe);
+COND_SYSCALL(uprobe);

From 6ea96bedaca26f672ef9c146947b5af4efd0d7b3 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 19 Feb 2025 10:09:18 +0100
Subject: [PATCH 1158/1173] uprobes/x86: Add mapping for optimized uprobe
 trampolines

Adding support to add special mapping for for user space trampoline
with following functions:

  uprobe_trampoline_get - find or add related uprobe_trampoline
  uprobe_trampoline_put - remove ref or destroy uprobe_trampoline

The user space trampoline is exported as architecture specific user space
special mapping, which is provided by arch_uprobe_trampoline_mapping
function.

The uprobe trampoline needs to be callable/reachable from the probe address,
so while searching for available address we use uprobe_is_callable function
to decide if the uprobe trampoline is callable from the probe address.

All uprobe_trampoline objects are stored in uprobes_state object and are
cleaned up when the process mm_struct goes down. Adding new arch hooks
for that, because this change is x86_64 specific.

Locking is provided by callers in following changes.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 arch/x86/kernel/uprobes.c | 123 ++++++++++++++++++++++++++++++++++++++
 include/linux/uprobes.h   |   6 ++
 kernel/events/uprobes.c   |  10 ++++
 kernel/fork.c             |   1 +
 4 files changed, 140 insertions(+)

diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index b11dcd47edaa2..5ee2cce4c63e2 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -742,6 +742,129 @@ static void riprel_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 		*sr = utask->autask.saved_scratch_register;
 	}
 }
+
+struct uprobe_trampoline {
+	struct hlist_node	node;
+	unsigned long		vaddr;
+	atomic64_t		ref;
+};
+
+static bool is_reachable_by_call(unsigned long vtramp, unsigned long vaddr)
+{
+	long delta = (long)(vaddr + 5 - vtramp);
+
+	return delta >= INT_MIN && delta <= INT_MAX;
+}
+
+static unsigned long find_nearest_page(unsigned long vaddr)
+{
+	struct vm_area_struct *vma, *prev = NULL;
+	unsigned long prev_vm_end = PAGE_SIZE;
+	VMA_ITERATOR(vmi, current->mm, 0);
+
+	vma = vma_next(&vmi);
+	while (vma) {
+		if (prev)
+			prev_vm_end = prev->vm_end;
+		if (vma->vm_start - prev_vm_end  >= PAGE_SIZE) {
+			if (is_reachable_by_call(prev_vm_end, vaddr))
+				return prev_vm_end;
+			if (is_reachable_by_call(vma->vm_start - PAGE_SIZE, vaddr))
+				return vma->vm_start - PAGE_SIZE;
+		}
+		prev = vma;
+		vma = vma_next(&vmi);
+	}
+
+	return 0;
+}
+
+static struct uprobe_trampoline *create_uprobe_trampoline(unsigned long vaddr)
+{
+	struct pt_regs *regs = task_pt_regs(current);
+	const struct vm_special_mapping *mapping;
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	struct uprobe_trampoline *tramp;
+
+	mapping = user_64bit_mode(regs) ? &tramp_mapping : NULL;
+	if (!mapping)
+		return NULL;
+
+	vaddr = find_nearest_page(vaddr);
+	if (!vaddr)
+		return NULL;
+
+	tramp = kzalloc(sizeof(*tramp), GFP_KERNEL);
+	if (unlikely(!tramp))
+		return NULL;
+
+	atomic64_set(&tramp->ref, 1);
+	tramp->vaddr = vaddr;
+
+	vma = _install_special_mapping(mm, tramp->vaddr, PAGE_SIZE,
+				VM_READ|VM_EXEC|VM_MAYEXEC|VM_MAYREAD|VM_DONTCOPY|VM_IO,
+				mapping);
+	if (IS_ERR(vma))
+		goto free_area;
+	return tramp;
+
+ free_area:
+	kfree(tramp);
+	return NULL;
+}
+
+__maybe_unused
+static struct uprobe_trampoline *uprobe_trampoline_get(unsigned long vaddr)
+{
+	struct uprobes_state *state = &current->mm->uprobes_state;
+	struct uprobe_trampoline *tramp = NULL;
+
+	hlist_for_each_entry(tramp, &state->head_tramps, node) {
+		if (is_reachable_by_call(tramp->vaddr, vaddr)) {
+			atomic64_inc(&tramp->ref);
+			return tramp;
+		}
+	}
+
+	tramp = create_uprobe_trampoline(vaddr);
+	if (!tramp)
+		return NULL;
+
+	hlist_add_head(&tramp->node, &state->head_tramps);
+	return tramp;
+}
+
+static void destroy_uprobe_trampoline(struct uprobe_trampoline *tramp)
+{
+	hlist_del(&tramp->node);
+	kfree(tramp);
+}
+
+__maybe_unused
+static void uprobe_trampoline_put(struct uprobe_trampoline *tramp)
+{
+	if (tramp == NULL)
+		return;
+
+	if (atomic64_dec_and_test(&tramp->ref))
+		destroy_uprobe_trampoline(tramp);
+}
+
+void arch_uprobe_init_state(struct mm_struct *mm)
+{
+	INIT_HLIST_HEAD(&mm->uprobes_state.head_tramps);
+}
+
+void arch_uprobe_clear_state(struct mm_struct *mm)
+{
+	struct uprobes_state *state = &mm->uprobes_state;
+	struct uprobe_trampoline *tramp;
+	struct hlist_node *n;
+
+	hlist_for_each_entry_safe(tramp, n, &state->head_tramps, node)
+		destroy_uprobe_trampoline(tramp);
+}
 #else /* 32-bit: */
 /*
  * No RIP-relative addressing on 32-bit
diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index 4a2b950beefd5..7bde688711502 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -17,6 +17,7 @@
 #include <linux/wait.h>
 #include <linux/timer.h>
 #include <linux/seqlock.h>
+#include <linux/mutex.h>
 
 struct uprobe;
 struct vm_area_struct;
@@ -185,6 +186,9 @@ struct xol_area;
 
 struct uprobes_state {
 	struct xol_area		*xol_area;
+#ifdef CONFIG_X86_64
+	struct hlist_head	head_tramps;
+#endif
 };
 
 typedef int (*uprobe_write_verify_t)(struct page *page, unsigned long vaddr, uprobe_opcode_t *opcode, int nbytes);
@@ -233,6 +237,8 @@ extern void *arch_uretprobe_trampoline(unsigned long *psize);
 extern unsigned long uprobe_get_trampoline_vaddr(void);
 extern void uprobe_copy_from_page(struct page *page, unsigned long vaddr, void *dst, int len);
 extern void handle_syscall_uprobe(struct pt_regs *regs, unsigned long bp_vaddr);
+extern void arch_uprobe_clear_state(struct mm_struct *mm);
+extern void arch_uprobe_init_state(struct mm_struct *mm);
 #else /* !CONFIG_UPROBES */
 struct uprobes_state {
 };
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 4de04075576c2..9370df47ec71f 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1793,6 +1793,14 @@ static struct xol_area *get_xol_area(void)
 	return area;
 }
 
+void __weak arch_uprobe_clear_state(struct mm_struct *mm)
+{
+}
+
+void __weak arch_uprobe_init_state(struct mm_struct *mm)
+{
+}
+
 /*
  * uprobe_clear_state - Free the area allocated for slots.
  */
@@ -1804,6 +1812,8 @@ void uprobe_clear_state(struct mm_struct *mm)
 	delayed_uprobe_remove(NULL, mm);
 	mutex_unlock(&delayed_uprobe_lock);
 
+	arch_uprobe_clear_state(mm);
+
 	if (!area)
 		return;
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 8695c345ca494..2720e42508a9e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1264,6 +1264,7 @@ static void mm_init_uprobes_state(struct mm_struct *mm)
 {
 #ifdef CONFIG_UPROBES
 	mm->uprobes_state.xol_area = NULL;
+	arch_uprobe_init_state(mm);
 #endif
 }
 

From d299d6728a2b49268d7333e3ffdac6afd541319a Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Tue, 26 Nov 2024 14:03:04 +0100
Subject: [PATCH 1159/1173] uprobes/x86: Add support to emulate nop5
 instruction

Adding support to emulate nop5 as the original uprobe instruction.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 arch/x86/kernel/uprobes.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 5ee2cce4c63e2..1661e0ab2a3d5 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -308,6 +308,11 @@ static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool
 	return -ENOTSUPP;
 }
 
+static int is_nop5_insn(uprobe_opcode_t *insn)
+{
+	return !memcmp(insn, x86_nops[5], 5);
+}
+
 #ifdef CONFIG_X86_64
 
 asm (
@@ -865,6 +870,11 @@ void arch_uprobe_clear_state(struct mm_struct *mm)
 	hlist_for_each_entry_safe(tramp, n, &state->head_tramps, node)
 		destroy_uprobe_trampoline(tramp);
 }
+
+static bool emulate_nop5_insn(struct arch_uprobe *auprobe)
+{
+	return is_nop5_insn((uprobe_opcode_t *) &auprobe->insn);
+}
 #else /* 32-bit: */
 /*
  * No RIP-relative addressing on 32-bit
@@ -878,6 +888,10 @@ static void riprel_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 static void riprel_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 {
 }
+static bool emulate_nop5_insn(struct arch_uprobe *auprobe)
+{
+	return false;
+}
 #endif /* CONFIG_X86_64 */
 
 struct uprobe_xol_ops {
@@ -1109,6 +1123,8 @@ static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn)
 		break;
 
 	case 0x0f:
+		if (emulate_nop5_insn(auprobe))
+			goto setup;
 		if (insn->opcode.nbytes != 2)
 			return -ENOSYS;
 		/*

From f1de9b166d49b8ac9deb45ff0f509d9d44bbfe4f Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 23 Oct 2024 23:21:21 +0200
Subject: [PATCH 1160/1173] uprobes/x86: Add support to optimize uprobes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Putting together all the previously added pieces to support optimized
uprobes on top of 5-byte nop instruction.

The current uprobe execution goes through following:
  - installs breakpoint instruction over original instruction
  - exception handler hit and calls related uprobe consumers
  - and either simulates original instruction or does out of line single step
    execution of it
  - returns to user space

The optimized uprobe path

  - checks the original instruction is 5-byte nop (plus other checks)
  - adds (or uses existing) user space trampoline and overwrites original
    instruction (5-byte nop) with call to user space trampoline
  - the user space trampoline executes uprobe syscall that calls related uprobe
    consumers
  - trampoline returns back to next instruction

This approach won't speed up all uprobes as it's limited to using nop5 as
original instruction, but we could use nop5 as USDT probe instruction (which
uses single byte nop ATM) and speed up the USDT probes.

This patch overloads related arch functions in uprobe_write_opcode and
set_orig_insn so they can install call instruction if needed.

The arch_uprobe_optimize triggers the uprobe optimization and is called after
first uprobe hit. I originally had it called on uprobe installation but then
it clashed with elf loader, because the user space trampoline was added in a
place where loader might need to put elf segments, so I decided to do it after
first uprobe hit when loading is done.

We do not unmap and release uprobe trampoline when it's no longer needed,
because there's no easy way to make sure none of the threads is still
inside the trampoline. But we do not waste memory, because there's just
single page for all the uprobe trampoline mappings.

We do waste frmae on page mapping for every 4GB by keeping the uprobe
trampoline page mapped, but that seems ok.

Attaching the speed up from benchs/run_bench_uprobes.sh script:

current:
        usermode-count :  818.836 ± 2.842M/s
        syscall-count  :    8.917 ± 0.003M/s
        uprobe-nop     :    3.056 ± 0.013M/s
        uprobe-push    :    2.903 ± 0.002M/s
        uprobe-ret     :    1.533 ± 0.001M/s
-->     uprobe-nop5    :    1.492 ± 0.000M/s
        uretprobe-nop  :    1.783 ± 0.000M/s
        uretprobe-push :    1.672 ± 0.001M/s
        uretprobe-ret  :    1.067 ± 0.002M/s
-->     uretprobe-nop5 :    1.052 ± 0.000M/s

after the change:

        usermode-count :  818.386 ± 1.886M/s
        syscall-count  :    8.923 ± 0.003M/s
        uprobe-nop     :    3.086 ± 0.005M/s
        uprobe-push    :    2.751 ± 0.001M/s
        uprobe-ret     :    1.481 ± 0.000M/s
-->     uprobe-nop5    :    4.016 ± 0.002M/s
        uretprobe-nop  :    1.712 ± 0.008M/s
        uretprobe-push :    1.616 ± 0.001M/s
        uretprobe-ret  :    1.052 ± 0.000M/s
-->     uretprobe-nop5 :    2.015 ± 0.000M/s

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 arch/x86/include/asm/uprobes.h |   7 +
 arch/x86/kernel/uprobes.c      | 269 ++++++++++++++++++++++++++++++++-
 include/linux/uprobes.h        |   6 +-
 kernel/events/uprobes.c        |  16 +-
 4 files changed, 290 insertions(+), 8 deletions(-)

diff --git a/arch/x86/include/asm/uprobes.h b/arch/x86/include/asm/uprobes.h
index 678fb546f0a75..1ee2e5115955c 100644
--- a/arch/x86/include/asm/uprobes.h
+++ b/arch/x86/include/asm/uprobes.h
@@ -20,6 +20,11 @@ typedef u8 uprobe_opcode_t;
 #define UPROBE_SWBP_INSN		0xcc
 #define UPROBE_SWBP_INSN_SIZE		   1
 
+enum {
+	ARCH_UPROBE_FLAG_CAN_OPTIMIZE   = 0,
+	ARCH_UPROBE_FLAG_OPTIMIZE_FAIL  = 1,
+};
+
 struct uprobe_xol_ops;
 
 struct arch_uprobe {
@@ -45,6 +50,8 @@ struct arch_uprobe {
 			u8	ilen;
 		}			push;
 	};
+
+	unsigned long flags;
 };
 
 struct arch_uprobe_task {
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 1661e0ab2a3d5..ff09211dada8d 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -18,6 +18,7 @@
 #include <asm/processor.h>
 #include <asm/insn.h>
 #include <asm/mmu_context.h>
+#include <asm/nops.h>
 
 /* Post-execution fixups. */
 
@@ -819,7 +820,6 @@ static struct uprobe_trampoline *create_uprobe_trampoline(unsigned long vaddr)
 	return NULL;
 }
 
-__maybe_unused
 static struct uprobe_trampoline *uprobe_trampoline_get(unsigned long vaddr)
 {
 	struct uprobes_state *state = &current->mm->uprobes_state;
@@ -846,7 +846,6 @@ static void destroy_uprobe_trampoline(struct uprobe_trampoline *tramp)
 	kfree(tramp);
 }
 
-__maybe_unused
 static void uprobe_trampoline_put(struct uprobe_trampoline *tramp)
 {
 	if (tramp == NULL)
@@ -856,6 +855,212 @@ static void uprobe_trampoline_put(struct uprobe_trampoline *tramp)
 		destroy_uprobe_trampoline(tramp);
 }
 
+enum {
+	OPT_PART,
+	OPT_INSN,
+	UNOPT_INT3,
+	UNOPT_PART,
+};
+
+struct write_opcode_ctx {
+	unsigned long base;
+	int update;
+};
+
+static int is_call_insn(uprobe_opcode_t *insn)
+{
+	return *insn == CALL_INSN_OPCODE;
+}
+
+static int verify_insn(struct page *page, unsigned long vaddr, uprobe_opcode_t *new_opcode,
+		       int nbytes, void *data)
+{
+	struct write_opcode_ctx *ctx = data;
+	uprobe_opcode_t old_opcode[5];
+
+	uprobe_copy_from_page(page, ctx->base, (uprobe_opcode_t *) &old_opcode, 5);
+
+	switch (ctx->update) {
+	case OPT_PART:
+	case OPT_INSN:
+		if (is_swbp_insn(&old_opcode[0]))
+			return 1;
+		break;
+	case UNOPT_INT3:
+		if (is_call_insn(&old_opcode[0]))
+			return 1;
+		break;
+	case UNOPT_PART:
+		if (is_swbp_insn(&old_opcode[0]))
+			return 1;
+		break;
+	}
+
+	return -1;
+}
+
+static int write_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr,
+		      uprobe_opcode_t *insn, int nbytes, void *ctx)
+{
+	return uprobe_write(auprobe, mm, vaddr, insn, nbytes, verify_insn, false, ctx);
+}
+
+static void relative_call(void *dest, long from, long to)
+{
+	struct __packed __arch_relative_insn {
+		u8 op;
+		s32 raddr;
+	} *insn;
+
+	insn = (struct __arch_relative_insn *)dest;
+	insn->raddr = (s32)(to - (from + 5));
+	insn->op = CALL_INSN_OPCODE;
+}
+
+static int swbp_optimize(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr,
+			 unsigned long tramp)
+{
+	struct write_opcode_ctx ctx = {
+		.base = vaddr,
+	};
+	char call[5];
+	int err;
+
+	relative_call(call, vaddr, tramp);
+
+	/*
+	 * We are in state where breakpoint (int3) is installed on top of first
+	 * byte of the nop5 instruction. We will do following steps to overwrite
+	 * this to call instruction:
+	 *
+	 * - sync cores
+	 * - write last 4 bytes of the call instruction
+	 * - sync cores
+	 * - update the call instruction opcode
+	 */
+
+	text_poke_sync();
+
+	ctx.update = OPT_PART;
+	err = write_insn(auprobe, mm, vaddr + 1, call + 1, 4, &ctx);
+	if (err)
+		return err;
+
+	text_poke_sync();
+
+	ctx.update = OPT_INSN;
+	return write_insn(auprobe, mm, vaddr, call, 1, &ctx);
+}
+
+static int swbp_unoptimize(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
+{
+	uprobe_opcode_t int3 = UPROBE_SWBP_INSN;
+	struct write_opcode_ctx ctx = {
+		.base = vaddr,
+	};
+	int err;
+
+	/*
+	 * We need to overwrite call instruction into nop5 instruction with
+	 * breakpoint (int3) installed on top of its first byte. We will:
+	 *
+	 * - overwrite call opcode with breakpoint (int3)
+	 * - sync cores
+	 * - write last 4 bytes of the nop5 instruction
+	 * - sync cores
+	 */
+
+	ctx.update = UNOPT_INT3;
+	err = write_insn(auprobe, mm, vaddr, &int3, 1, &ctx);
+	if (err)
+		return err;
+
+	text_poke_sync();
+
+	ctx.update = UNOPT_PART;
+	err = write_insn(auprobe, mm, vaddr + 1, (uprobe_opcode_t *) auprobe->insn + 1, 4, &ctx);
+
+	text_poke_sync();
+	return err;
+}
+
+static int copy_from_vaddr(struct mm_struct *mm, unsigned long vaddr, void *dst, int len)
+{
+	unsigned int gup_flags = FOLL_FORCE|FOLL_SPLIT_PMD;
+	struct vm_area_struct *vma;
+	struct page *page;
+
+	page = get_user_page_vma_remote(mm, vaddr, gup_flags, &vma);
+	if (IS_ERR(page))
+		return PTR_ERR(page);
+	uprobe_copy_from_page(page, vaddr, dst, len);
+	put_page(page);
+	return 0;
+}
+
+static bool __is_optimized(uprobe_opcode_t *insn, unsigned long vaddr)
+{
+	struct __packed __arch_relative_insn {
+		u8 op;
+		s32 raddr;
+	} *call = (struct __arch_relative_insn *) insn;
+
+	if (!is_call_insn(insn))
+		return false;
+	return __in_uprobe_trampoline(vaddr + 5 + call->raddr);
+}
+
+static int is_optimized(struct mm_struct *mm, unsigned long vaddr, bool *optimized)
+{
+	uprobe_opcode_t insn[5];
+	int err;
+
+	err = copy_from_vaddr(mm, vaddr, &insn, 5);
+	if (err)
+		return err;
+	*optimized = __is_optimized((uprobe_opcode_t *)&insn, vaddr);
+	return 0;
+}
+
+static bool should_optimize(struct arch_uprobe *auprobe)
+{
+	return !test_bit(ARCH_UPROBE_FLAG_OPTIMIZE_FAIL, &auprobe->flags) &&
+		test_bit(ARCH_UPROBE_FLAG_CAN_OPTIMIZE, &auprobe->flags);
+}
+
+int set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
+{
+	if (should_optimize(auprobe)) {
+		bool optimized = false;
+		int err;
+
+		err = is_optimized(mm, vaddr, &optimized);
+		if (err || optimized)
+			return err;
+	}
+	return uprobe_write_opcode(auprobe, mm, vaddr, UPROBE_SWBP_INSN, false);
+}
+
+int set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
+{
+	/*
+	 * We might be in race where we have optimized uprobe, but the uprobe
+	 * was flagged as failed from another task, so we try to unoptimize
+	 * the uprobe regardless the failed flag.
+	 */
+	if (test_bit(ARCH_UPROBE_FLAG_CAN_OPTIMIZE, &auprobe->flags)) {
+		bool optimized = false;
+		int err;
+
+		err = is_optimized(mm, vaddr, &optimized);
+		if (err)
+			return err;
+		if (optimized)
+			WARN_ON_ONCE(swbp_unoptimize(auprobe, mm, vaddr));
+	}
+	return uprobe_write_opcode(auprobe, mm, vaddr, *(uprobe_opcode_t *)&auprobe->insn, true);
+}
+
 void arch_uprobe_init_state(struct mm_struct *mm)
 {
 	INIT_HLIST_HEAD(&mm->uprobes_state.head_tramps);
@@ -875,6 +1080,59 @@ static bool emulate_nop5_insn(struct arch_uprobe *auprobe)
 {
 	return is_nop5_insn((uprobe_opcode_t *) &auprobe->insn);
 }
+
+static int __arch_uprobe_optimize(struct mm_struct *mm, struct arch_uprobe *auprobe,
+				  unsigned long vaddr)
+{
+	struct uprobe_trampoline *tramp;
+	int err = 0;
+
+	tramp = uprobe_trampoline_get(vaddr);
+	if (!tramp)
+		return -1;
+	err = swbp_optimize(auprobe, mm, vaddr, tramp->vaddr);
+	if (WARN_ON_ONCE(err))
+		uprobe_trampoline_put(tramp);
+	return err;
+}
+
+void arch_uprobe_optimize(struct arch_uprobe *auprobe, unsigned long vaddr)
+{
+	struct mm_struct *mm = current->mm;
+	uprobe_opcode_t insn[5];
+
+	if (!should_optimize(auprobe))
+		return;
+
+	mmap_write_lock(mm);
+
+	/*
+	 * Check if some other thread already optimized the uprobe for us,
+	 * if it's the case just go away silently.
+	 */
+	if (copy_from_vaddr(mm, vaddr, &insn, 5))
+		goto unlock;
+	if (!is_swbp_insn((uprobe_opcode_t*) &insn))
+		goto unlock;
+
+	/*
+	 * If we fail to optimize the uprobe we set the fail bit so the
+	 * above should_optimize will fail from now on.
+	 */
+	if (__arch_uprobe_optimize(mm, auprobe, vaddr))
+		set_bit(ARCH_UPROBE_FLAG_OPTIMIZE_FAIL, &auprobe->flags);
+
+unlock:
+	mmap_write_unlock(mm);
+}
+
+static bool can_optimize(struct arch_uprobe *auprobe, unsigned long vaddr)
+{
+	if (!is_nop5_insn((uprobe_opcode_t *) &auprobe->insn))
+		return false;
+	/* We can't do cross page atomic writes yet. */
+	return PAGE_SIZE - (vaddr & ~PAGE_MASK) >= 5;
+}
 #else /* 32-bit: */
 /*
  * No RIP-relative addressing on 32-bit
@@ -892,6 +1150,10 @@ static bool emulate_nop5_insn(struct arch_uprobe *auprobe)
 {
 	return false;
 }
+static bool can_optimize(struct arch_uprobe *auprobe, unsigned long vaddr)
+{
+	return false;
+}
 #endif /* CONFIG_X86_64 */
 
 struct uprobe_xol_ops {
@@ -1255,6 +1517,9 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm,
 	if (ret)
 		return ret;
 
+	if (can_optimize(auprobe, addr))
+		set_bit(ARCH_UPROBE_FLAG_CAN_OPTIMIZE, &auprobe->flags);
+
 	ret = branch_setup_xol_ops(auprobe, &insn);
 	if (ret != -ENOSYS)
 		return ret;
diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index 7bde688711502..58868407fed06 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -191,7 +191,8 @@ struct uprobes_state {
 #endif
 };
 
-typedef int (*uprobe_write_verify_t)(struct page *page, unsigned long vaddr, uprobe_opcode_t *opcode, int nbytes);
+typedef int (*uprobe_write_verify_t)(struct page *page, unsigned long vaddr, uprobe_opcode_t *opcode,
+				     int nbytes, void *data);
 
 extern void __init uprobes_init(void);
 extern int set_swbp(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr);
@@ -203,7 +204,7 @@ extern unsigned long uprobe_get_trap_addr(struct pt_regs *regs);
 extern int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr,
 			       uprobe_opcode_t, bool);
 extern int uprobe_write(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr,
-			uprobe_opcode_t *insn, int nbytes, uprobe_write_verify_t verify, bool orig);
+			uprobe_opcode_t *insn, int nbytes, uprobe_write_verify_t verify, bool orig, void *data);
 extern struct uprobe *uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc);
 extern int uprobe_apply(struct uprobe *uprobe, struct uprobe_consumer *uc, bool);
 extern void uprobe_unregister_nosync(struct uprobe *uprobe, struct uprobe_consumer *uc);
@@ -239,6 +240,7 @@ extern void uprobe_copy_from_page(struct page *page, unsigned long vaddr, void *
 extern void handle_syscall_uprobe(struct pt_regs *regs, unsigned long bp_vaddr);
 extern void arch_uprobe_clear_state(struct mm_struct *mm);
 extern void arch_uprobe_init_state(struct mm_struct *mm);
+extern void arch_uprobe_optimize(struct arch_uprobe *auprobe, unsigned long vaddr);
 #else /* !CONFIG_UPROBES */
 struct uprobes_state {
 };
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 9370df47ec71f..a6108bd0b8d78 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -264,7 +264,8 @@ static void uprobe_copy_to_page(struct page *page, unsigned long vaddr, const vo
 	kunmap_atomic(kaddr);
 }
 
-static int verify_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t *new_opcode, int nbytes)
+static int verify_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t *new_opcode,
+			 int nbytes, void *data)
 {
 	uprobe_opcode_t old_opcode;
 	bool is_swbp;
@@ -473,12 +474,12 @@ static int update_ref_ctr(struct uprobe *uprobe, struct mm_struct *mm,
 int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
 			unsigned long vaddr, uprobe_opcode_t opcode, bool orig)
 {
-	return uprobe_write(auprobe, mm, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE, verify_opcode, orig);
+	return uprobe_write(auprobe, mm, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE, verify_opcode, orig, NULL);
 }
 
 int uprobe_write(struct arch_uprobe *auprobe, struct mm_struct *mm,
 		 unsigned long vaddr, uprobe_opcode_t *insn,
-		 int nbytes, uprobe_write_verify_t verify, bool orig)
+		 int nbytes, uprobe_write_verify_t verify, bool orig, void *data)
 {
 	struct page *old_page, *new_page;
 	struct vm_area_struct *vma;
@@ -494,7 +495,7 @@ int uprobe_write(struct arch_uprobe *auprobe, struct mm_struct *mm,
 	if (IS_ERR(old_page))
 		return PTR_ERR(old_page);
 
-	ret = verify(old_page, vaddr, insn, nbytes);
+	ret = verify(old_page, vaddr, insn, nbytes, data);
 	if (ret <= 0)
 		goto put_old;
 
@@ -2677,6 +2678,10 @@ bool __weak arch_uretprobe_is_alive(struct return_instance *ret, enum rp_check c
 	return true;
 }
 
+void __weak arch_uprobe_optimize(struct arch_uprobe *auprobe, unsigned long vaddr)
+{
+}
+
 /*
  * Run handler and ask thread to singlestep.
  * Ensure all non-fatal signals cannot interrupt thread while it singlesteps.
@@ -2741,6 +2746,9 @@ static void handle_swbp(struct pt_regs *regs)
 
 	handler_chain(uprobe, regs);
 
+	/* Try to optimize after first hit. */
+	arch_uprobe_optimize(&uprobe->arch, bp_vaddr);
+
 	if (arch_uprobe_skip_sstep(&uprobe->arch, regs))
 		goto out;
 

From f68bd235a1ab6a60c769d97e47d7e8e0dd99b1c7 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Sun, 15 Dec 2024 14:29:48 +0100
Subject: [PATCH 1161/1173] selftests/bpf: Reorg the uprobe_syscall test
 function

Adding __test_uprobe_syscall with non x86_64 stub to execute all the tests,
so we don't need to keep adding non x86_64 stub functions for new tests.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 .../selftests/bpf/prog_tests/uprobe_syscall.c | 34 +++++++------------
 1 file changed, 12 insertions(+), 22 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
index c397336fe1ed1..2b00f16406c8f 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
@@ -350,29 +350,8 @@ static void test_uretprobe_shadow_stack(void)
 
 	ARCH_PRCTL(ARCH_SHSTK_DISABLE, ARCH_SHSTK_SHSTK);
 }
-#else
-static void test_uretprobe_regs_equal(void)
-{
-	test__skip();
-}
-
-static void test_uretprobe_regs_change(void)
-{
-	test__skip();
-}
-
-static void test_uretprobe_syscall_call(void)
-{
-	test__skip();
-}
 
-static void test_uretprobe_shadow_stack(void)
-{
-	test__skip();
-}
-#endif
-
-void test_uprobe_syscall(void)
+static void __test_uprobe_syscall(void)
 {
 	if (test__start_subtest("uretprobe_regs_equal"))
 		test_uretprobe_regs_equal();
@@ -383,3 +362,14 @@ void test_uprobe_syscall(void)
 	if (test__start_subtest("uretprobe_shadow_stack"))
 		test_uretprobe_shadow_stack();
 }
+#else
+static void __test_uprobe_syscall(void)
+{
+	test__skip();
+}
+#endif
+
+void test_uprobe_syscall(void)
+{
+	__test_uprobe_syscall();
+}

From cff4de372f575513d2549045451a100b75e69113 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 13 Mar 2025 09:54:52 +0100
Subject: [PATCH 1162/1173] selftests/bpf: Rename uprobe_syscall_executed prog
 to test_uretprobe_multi

Renaming uprobe_syscall_executed prog to test_uretprobe_multi
to fit properly in the following changes that add more programs.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c   | 8 ++++----
 .../testing/selftests/bpf/progs/uprobe_syscall_executed.c | 4 ++--
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
index 2b00f16406c8f..3c74a079e6d97 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
@@ -277,10 +277,10 @@ static void test_uretprobe_syscall_call(void)
 		_exit(0);
 	}
 
-	skel->links.test = bpf_program__attach_uprobe_multi(skel->progs.test, pid,
-							    "/proc/self/exe",
-							    "uretprobe_syscall_call", &opts);
-	if (!ASSERT_OK_PTR(skel->links.test, "bpf_program__attach_uprobe_multi"))
+	skel->links.test_uretprobe_multi = bpf_program__attach_uprobe_multi(skel->progs.test_uretprobe_multi,
+							pid, "/proc/self/exe",
+							"uretprobe_syscall_call", &opts);
+	if (!ASSERT_OK_PTR(skel->links.test_uretprobe_multi, "bpf_program__attach_uprobe_multi"))
 		goto cleanup;
 
 	/* kick the child */
diff --git a/tools/testing/selftests/bpf/progs/uprobe_syscall_executed.c b/tools/testing/selftests/bpf/progs/uprobe_syscall_executed.c
index 0d7f1a7db2e2e..2e1b689ed4fb2 100644
--- a/tools/testing/selftests/bpf/progs/uprobe_syscall_executed.c
+++ b/tools/testing/selftests/bpf/progs/uprobe_syscall_executed.c
@@ -10,8 +10,8 @@ char _license[] SEC("license") = "GPL";
 int executed = 0;
 
 SEC("uretprobe.multi")
-int test(struct pt_regs *regs)
+int test_uretprobe_multi(struct pt_regs *ctx)
 {
-	executed = 1;
+	executed++;
 	return 0;
 }

From ff11a6d3344ab1e5efd52b5a58eaa7b2f378adad Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 17 Apr 2024 14:48:47 +0200
Subject: [PATCH 1163/1173] selftests/bpf: Use 5-byte nop for x86 usdt probes

Using 5-byte nop for x86 usdt probes so we can switch
to optimized uprobe them.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/testing/selftests/bpf/sdt.h | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/sdt.h b/tools/testing/selftests/bpf/sdt.h
index 1fcfa5160231d..1d62c06f5ddcb 100644
--- a/tools/testing/selftests/bpf/sdt.h
+++ b/tools/testing/selftests/bpf/sdt.h
@@ -236,6 +236,13 @@ __extension__ extern unsigned long long __sdt_unsp;
 #define _SDT_NOP	nop
 #endif
 
+/* Use 5 byte nop for x86_64 to allow optimizing uprobes. */
+#if defined(__x86_64__)
+# define _SDT_DEF_NOP _SDT_ASM_5(990:	.byte 0x0f, 0x1f, 0x44, 0x00, 0x00)
+#else
+# define _SDT_DEF_NOP _SDT_ASM_1(990:	_SDT_NOP)
+#endif
+
 #define _SDT_NOTE_NAME	"stapsdt"
 #define _SDT_NOTE_TYPE	3
 
@@ -288,7 +295,7 @@ __extension__ extern unsigned long long __sdt_unsp;
 
 #define _SDT_ASM_BODY(provider, name, pack_args, args, ...)		      \
   _SDT_DEF_MACROS							      \
-  _SDT_ASM_1(990:	_SDT_NOP)					      \
+  _SDT_DEF_NOP								      \
   _SDT_ASM_3(		.pushsection .note.stapsdt,_SDT_ASM_AUTOGROUP,"note") \
   _SDT_ASM_1(		.balign 4)					      \
   _SDT_ASM_3(		.4byte 992f-991f, 994f-993f, _SDT_NOTE_TYPE)	      \

From f6df2bbea592f8dd229d9672aa37fd017ba0a267 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Sun, 15 Dec 2024 15:15:02 +0100
Subject: [PATCH 1164/1173] selftests/bpf: Add uprobe/usdt syscall tests

Adding tests for optimized uprobe/usdt probes.

Checking that we get expected trampoline and attached bpf programs
get executed properly.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 .../selftests/bpf/prog_tests/uprobe_syscall.c | 234 ++++++++++++++++++
 .../bpf/progs/uprobe_syscall_executed.c       |  30 +++
 2 files changed, 264 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
index 3c74a079e6d97..6c756f658fba4 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
@@ -14,6 +14,34 @@
 #include <asm/prctl.h>
 #include "uprobe_syscall.skel.h"
 #include "uprobe_syscall_executed.skel.h"
+#include "sdt.h"
+
+static unsigned char nop5[5] = { 0x0f, 0x1f, 0x44, 0x00, 0x00 };
+
+/*
+ * Compiler (gcc) can ignore __naked attribute and place endbr64 at the
+ * begining of the function, so let's just scan few more bytes to make
+ * sure we have nop5 addres/offset.
+ */
+static void *find_nop5(void *fn)
+{
+	int i;
+
+	for (i = 0; i < 10; i++) {
+		if (!memcmp(nop5, fn + i, 5))
+			return fn + i;
+	}
+	return NULL;
+}
+
+static unsigned long get_nop5_offset(void *fn, void **paddr)
+{
+	void *addr = find_nop5(fn);
+
+	if (paddr)
+		*paddr = addr;
+	return addr ? get_uprobe_offset(addr) : -1;
+}
 
 __naked unsigned long uretprobe_regs_trigger(void)
 {
@@ -351,6 +379,206 @@ static void test_uretprobe_shadow_stack(void)
 	ARCH_PRCTL(ARCH_SHSTK_DISABLE, ARCH_SHSTK_SHSTK);
 }
 
+#define TRAMP "[uprobes-trampoline]"
+
+__naked noinline void uprobe_test(void)
+{
+	asm volatile ("					\n"
+		".byte 0x0f, 0x1f, 0x44, 0x00, 0x00	\n"
+		"ret					\n"
+	);
+}
+
+noinline void usdt_test(void)
+{
+	STAP_PROBE(optimized_uprobe, usdt);
+}
+
+static int find_uprobes_trampoline(void **start, void **end)
+{
+	char line[128];
+	int ret = -1;
+	FILE *maps;
+
+	maps = fopen("/proc/self/maps", "r");
+	if (!maps) {
+		fprintf(stderr, "cannot open maps\n");
+		return -1;
+	}
+
+	while (fgets(line, sizeof(line), maps)) {
+		int m = -1;
+
+		/* We care only about private r-x mappings. */
+		if (sscanf(line, "%p-%p r-xp %*x %*x:%*x %*u %n", start, end, &m) != 2)
+			continue;
+		if (m < 0)
+			continue;
+		if (!strncmp(&line[m], TRAMP, sizeof(TRAMP)-1)) {
+			ret = 0;
+			break;
+		}
+	}
+
+	fclose(maps);
+	return ret;
+}
+
+static void check_attach(struct uprobe_syscall_executed *skel, void (*trigger)(void), void *addr)
+{
+	void *tramp_start, *tramp_end;
+	struct __arch_relative_insn {
+		u8 op;
+		s32 raddr;
+	} __packed *call;
+
+	s32 delta;
+
+	/* Uprobe gets optimized after first trigger, so let's press twice. */
+	trigger();
+	trigger();
+
+	if (!ASSERT_OK(find_uprobes_trampoline(&tramp_start, &tramp_end), "uprobes_trampoline"))
+		return;
+
+	/* Make sure bpf program got executed.. */
+	ASSERT_EQ(skel->bss->executed, 2, "executed");
+
+	/* .. and check the trampoline is as expected. */
+	call = (struct __arch_relative_insn *) addr;
+	delta = (unsigned long) tramp_start - ((unsigned long) addr + 5);
+
+	ASSERT_EQ(call->op, 0xe8, "call");
+	ASSERT_EQ(call->raddr, delta, "delta");
+	ASSERT_EQ(tramp_end - tramp_start, 4096, "size");
+}
+
+static void check_detach(struct uprobe_syscall_executed *skel, void (*trigger)(void), void *addr)
+{
+	void *tramp_start, *tramp_end;
+
+	/* [uprobes_trampoline] stays after detach */
+	ASSERT_OK(find_uprobes_trampoline(&tramp_start, &tramp_end), "uprobes_trampoline");
+	ASSERT_OK(memcmp(addr, nop5, 5), "nop5");
+}
+
+static void check(struct uprobe_syscall_executed *skel, struct bpf_link *link,
+		  void (*trigger)(void), void *addr)
+{
+	check_attach(skel, trigger, addr);
+	bpf_link__destroy(link);
+	check_detach(skel, trigger, addr);
+}
+
+static void test_uprobe_legacy(void)
+{
+	LIBBPF_OPTS(bpf_uprobe_opts, opts,
+		.retprobe = true,
+	);
+	struct uprobe_syscall_executed *skel;
+	struct bpf_link *link;
+	unsigned long offset;
+	void *addr;
+
+	offset = get_nop5_offset(&uprobe_test, &addr);
+	if (!ASSERT_GE(offset, 0, "get_nop5_offset"))
+		return;
+
+	/* uprobe */
+	skel = uprobe_syscall_executed__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_syscall_executed__open_and_load"))
+		return;
+
+	link = bpf_program__attach_uprobe_opts(skel->progs.test_uprobe,
+				0, "/proc/self/exe", offset, NULL);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_opts"))
+		goto cleanup;
+
+	check(skel, link, uprobe_test, addr);
+
+	/* uretprobe */
+	skel->bss->executed = 0;
+
+	link = bpf_program__attach_uprobe_opts(skel->progs.test_uretprobe,
+				0, "/proc/self/exe", offset, &opts);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_opts"))
+		goto cleanup;
+
+	check(skel, link, uprobe_test, addr);
+
+cleanup:
+	uprobe_syscall_executed__destroy(skel);
+}
+
+static void test_uprobe_multi(void)
+{
+	LIBBPF_OPTS(bpf_uprobe_multi_opts, opts);
+	struct uprobe_syscall_executed *skel;
+	struct bpf_link *link;
+	unsigned long offset;
+	void *addr;
+
+	/* uprobe */
+	offset = get_nop5_offset(&uprobe_test, &addr);
+	if (!ASSERT_GE(offset, 0, "get_nop5_offset"))
+		return;
+
+	opts.offsets = &offset;
+	opts.cnt = 1;
+
+	skel = uprobe_syscall_executed__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_syscall_executed__open_and_load"))
+		return;
+
+	/* uprobe.multi */
+	link = bpf_program__attach_uprobe_multi(skel->progs.test_uprobe_multi,
+				0, "/proc/self/exe", NULL, &opts);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
+		goto cleanup;
+
+	check(skel, link, uprobe_test, addr);
+
+	/* uretprobe.multi */
+	skel->bss->executed = 0;
+	opts.retprobe = true;
+	link = bpf_program__attach_uprobe_multi(skel->progs.test_uretprobe_multi,
+				0, "/proc/self/exe", NULL, &opts);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
+		goto cleanup;
+
+	check(skel, link, uprobe_test, addr);
+
+cleanup:
+	uprobe_syscall_executed__destroy(skel);
+}
+
+static void test_uprobe_usdt(void)
+{
+	struct uprobe_syscall_executed *skel;
+	struct bpf_link *link;
+	void *addr;
+
+	errno = 0;
+	addr = find_nop5(usdt_test);
+	if (!ASSERT_OK_PTR(addr, "find_nop5"))
+		return;
+
+	skel = uprobe_syscall_executed__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_syscall_executed__open_and_load"))
+		return;
+
+	link = bpf_program__attach_usdt(skel->progs.test_usdt,
+				-1 /* all PIDs */, "/proc/self/exe",
+				"optimized_uprobe", "usdt", NULL);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_usdt"))
+		goto cleanup;
+
+	check(skel, link, usdt_test, addr);
+
+cleanup:
+	uprobe_syscall_executed__destroy(skel);
+}
+
 static void __test_uprobe_syscall(void)
 {
 	if (test__start_subtest("uretprobe_regs_equal"))
@@ -361,6 +589,12 @@ static void __test_uprobe_syscall(void)
 		test_uretprobe_syscall_call();
 	if (test__start_subtest("uretprobe_shadow_stack"))
 		test_uretprobe_shadow_stack();
+	if (test__start_subtest("uprobe_legacy"))
+		test_uprobe_legacy();
+	if (test__start_subtest("uprobe_multi"))
+		test_uprobe_multi();
+	if (test__start_subtest("uprobe_usdt"))
+		test_uprobe_usdt();
 }
 #else
 static void __test_uprobe_syscall(void)
diff --git a/tools/testing/selftests/bpf/progs/uprobe_syscall_executed.c b/tools/testing/selftests/bpf/progs/uprobe_syscall_executed.c
index 2e1b689ed4fb2..802fd562ce4c0 100644
--- a/tools/testing/selftests/bpf/progs/uprobe_syscall_executed.c
+++ b/tools/testing/selftests/bpf/progs/uprobe_syscall_executed.c
@@ -1,6 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "vmlinux.h"
 #include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/usdt.bpf.h>
 #include <string.h>
 
 struct pt_regs regs;
@@ -9,9 +11,37 @@ char _license[] SEC("license") = "GPL";
 
 int executed = 0;
 
+SEC("uprobe")
+int BPF_UPROBE(test_uprobe)
+{
+	executed++;
+	return 0;
+}
+
+SEC("uretprobe")
+int BPF_URETPROBE(test_uretprobe)
+{
+	executed++;
+	return 0;
+}
+
+SEC("uprobe.multi")
+int test_uprobe_multi(struct pt_regs *ctx)
+{
+	executed++;
+	return 0;
+}
+
 SEC("uretprobe.multi")
 int test_uretprobe_multi(struct pt_regs *ctx)
 {
 	executed++;
 	return 0;
 }
+
+SEC("usdt")
+int test_usdt(struct pt_regs *ctx)
+{
+	executed++;
+	return 0;
+}

From 36d3b644461f3449f6878031dc3205a16c7a0603 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 11 Dec 2024 00:00:14 +0100
Subject: [PATCH 1165/1173] selftests/bpf: Add hit/attach/detach race optimized
 uprobe test

Adding test that makes sure parallel execution of the uprobe and
attach/detach of optimized uprobe on it works properly.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 .../selftests/bpf/prog_tests/uprobe_syscall.c | 74 +++++++++++++++++++
 1 file changed, 74 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
index 6c756f658fba4..fb2d36e73096e 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
@@ -579,6 +579,78 @@ static void test_uprobe_usdt(void)
 	uprobe_syscall_executed__destroy(skel);
 }
 
+static volatile bool race_stop;
+
+static void *worker_trigger(void *arg)
+{
+	unsigned long rounds = 0;
+
+	while (!race_stop) {
+		uprobe_test();
+		rounds++;
+	}
+
+	printf("tid %d trigger rounds: %lu\n", gettid(), rounds);
+	return NULL;
+}
+
+static void *worker_attach(void *arg)
+{
+	struct uprobe_syscall_executed *skel;
+	unsigned long rounds = 0, offset;
+
+	offset = get_nop5_offset(&uprobe_test, NULL);
+	if (!ASSERT_GE(offset, 0, "get_nop5_offset"))
+		return NULL;
+
+	skel = uprobe_syscall_executed__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_syscall_executed__open_and_load"))
+		return NULL;
+
+	while (!race_stop) {
+		skel->links.test_uprobe = bpf_program__attach_uprobe_opts(skel->progs.test_uprobe,
+					0, "/proc/self/exe", offset, NULL);
+		if (!ASSERT_OK_PTR(skel->links.test_uprobe, "bpf_program__attach_uprobe_opts"))
+			break;
+
+		bpf_link__destroy(skel->links.test_uprobe);
+		skel->links.test_uprobe = NULL;
+		rounds++;
+	}
+
+	printf("tid %d attach rounds: %lu hits: %d\n", gettid(), rounds, skel->bss->executed);
+	uprobe_syscall_executed__destroy(skel);
+	return NULL;
+}
+
+static void test_uprobe_race(void)
+{
+	int err, i, nr_threads;
+	pthread_t *threads;
+
+	nr_threads = libbpf_num_possible_cpus();
+	if (!ASSERT_GE(nr_threads, 0, "libbpf_num_possible_cpus"))
+		return;
+
+	threads = malloc(sizeof(*threads) * nr_threads);
+	if (!ASSERT_OK_PTR(threads, "malloc"))
+		return;
+
+	for (i = 0; i < nr_threads; i++) {
+		err = pthread_create(&threads[i], NULL, i % 2 ? worker_trigger : worker_attach,
+				     NULL);
+		if (!ASSERT_OK(err, "pthread_create"))
+			goto cleanup;
+	}
+
+	sleep(4);
+
+cleanup:
+	race_stop = true;
+	for (nr_threads = i, i = 0; i < nr_threads; i++)
+		pthread_join(threads[i], NULL);
+}
+
 static void __test_uprobe_syscall(void)
 {
 	if (test__start_subtest("uretprobe_regs_equal"))
@@ -595,6 +667,8 @@ static void __test_uprobe_syscall(void)
 		test_uprobe_multi();
 	if (test__start_subtest("uprobe_usdt"))
 		test_uprobe_usdt();
+	if (test__start_subtest("uprobe_race"))
+		test_uprobe_race();
 }
 #else
 static void __test_uprobe_syscall(void)

From 223a6ac1e919cc5ece58ebda77898e75ee03797b Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 11 Dec 2024 00:01:24 +0100
Subject: [PATCH 1166/1173] selftests/bpf: Add uprobe syscall sigill signal
 test

Make sure that calling uprobe syscall from outside uprobe trampoline
results in sigill signal.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 .../selftests/bpf/prog_tests/uprobe_syscall.c | 36 +++++++++++++++++++
 1 file changed, 36 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
index fb2d36e73096e..bcd36cd1e7188 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
@@ -651,6 +651,40 @@ static void test_uprobe_race(void)
 		pthread_join(threads[i], NULL);
 }
 
+#ifndef __NR_uprobe
+#define __NR_uprobe 336
+#endif
+
+static void test_uprobe_sigill(void)
+{
+	int status, err, pid;
+
+	pid = fork();
+	if (!ASSERT_GE(pid, 0, "fork"))
+		return;
+	/* child */
+	if (pid == 0) {
+		asm volatile (
+			"pushq %rax\n"
+			"pushq %rcx\n"
+			"pushq %r11\n"
+			"movq $" __stringify(__NR_uprobe) ", %rax\n"
+			"syscall\n"
+			"popq %r11\n"
+			"popq %rcx\n"
+			"retq\n"
+		);
+		exit(0);
+	}
+
+	err = waitpid(pid, &status, 0);
+	ASSERT_EQ(err, pid, "waitpid");
+
+	/* verify the child got killed with SIGILL */
+	ASSERT_EQ(WIFSIGNALED(status), 1, "WIFSIGNALED");
+	ASSERT_EQ(WTERMSIG(status), SIGILL, "WTERMSIG");
+}
+
 static void __test_uprobe_syscall(void)
 {
 	if (test__start_subtest("uretprobe_regs_equal"))
@@ -669,6 +703,8 @@ static void __test_uprobe_syscall(void)
 		test_uprobe_usdt();
 	if (test__start_subtest("uprobe_race"))
 		test_uprobe_race();
+	if (test__start_subtest("uprobe_sigill"))
+		test_uprobe_sigill();
 }
 #else
 static void __test_uprobe_syscall(void)

From 1fe214a29fe2e6d6f05502f7a626de89ba7a9372 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Sun, 2 Mar 2025 22:12:46 +0100
Subject: [PATCH 1167/1173] selftests/bpf: Add optimized usdt variant for basic
 usdt test

Adding optimized usdt variant for basic usdt test to check that
usdt arguments are properly passed in optimized code path.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/usdt.c | 38 ++++++++++++-------
 1 file changed, 25 insertions(+), 13 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/usdt.c b/tools/testing/selftests/bpf/prog_tests/usdt.c
index 495d66414b57e..3a5b5230bfa07 100644
--- a/tools/testing/selftests/bpf/prog_tests/usdt.c
+++ b/tools/testing/selftests/bpf/prog_tests/usdt.c
@@ -40,12 +40,19 @@ static void __always_inline trigger_func(int x) {
 	}
 }
 
-static void subtest_basic_usdt(void)
+static void subtest_basic_usdt(bool optimized)
 {
 	LIBBPF_OPTS(bpf_usdt_opts, opts);
 	struct test_usdt *skel;
 	struct test_usdt__bss *bss;
-	int err, i;
+	int err, i, called;
+
+#define TRIGGER(x) ({			\
+	trigger_func(x);		\
+	if (optimized)			\
+		trigger_func(x);	\
+	optimized ? 2 : 1;		\
+	})
 
 	skel = test_usdt__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "skel_open"))
@@ -66,11 +73,11 @@ static void subtest_basic_usdt(void)
 	if (!ASSERT_OK_PTR(skel->links.usdt0, "usdt0_link"))
 		goto cleanup;
 
-	trigger_func(1);
+	called = TRIGGER(1);
 
-	ASSERT_EQ(bss->usdt0_called, 1, "usdt0_called");
-	ASSERT_EQ(bss->usdt3_called, 1, "usdt3_called");
-	ASSERT_EQ(bss->usdt12_called, 1, "usdt12_called");
+	ASSERT_EQ(bss->usdt0_called, called, "usdt0_called");
+	ASSERT_EQ(bss->usdt3_called, called, "usdt3_called");
+	ASSERT_EQ(bss->usdt12_called, called, "usdt12_called");
 
 	ASSERT_EQ(bss->usdt0_cookie, 0xcafedeadbeeffeed, "usdt0_cookie");
 	ASSERT_EQ(bss->usdt0_arg_cnt, 0, "usdt0_arg_cnt");
@@ -119,11 +126,11 @@ static void subtest_basic_usdt(void)
 	 * bpf_program__attach_usdt() handles this properly and attaches to
 	 * all possible places of USDT invocation.
 	 */
-	trigger_func(2);
+	called += TRIGGER(2);
 
-	ASSERT_EQ(bss->usdt0_called, 2, "usdt0_called");
-	ASSERT_EQ(bss->usdt3_called, 2, "usdt3_called");
-	ASSERT_EQ(bss->usdt12_called, 2, "usdt12_called");
+	ASSERT_EQ(bss->usdt0_called, called, "usdt0_called");
+	ASSERT_EQ(bss->usdt3_called, called, "usdt3_called");
+	ASSERT_EQ(bss->usdt12_called, called, "usdt12_called");
 
 	/* only check values that depend on trigger_func()'s input value */
 	ASSERT_EQ(bss->usdt3_args[0], 2, "usdt3_arg1");
@@ -142,9 +149,9 @@ static void subtest_basic_usdt(void)
 	if (!ASSERT_OK_PTR(skel->links.usdt3, "usdt3_reattach"))
 		goto cleanup;
 
-	trigger_func(3);
+	called += TRIGGER(3);
 
-	ASSERT_EQ(bss->usdt3_called, 3, "usdt3_called");
+	ASSERT_EQ(bss->usdt3_called, called, "usdt3_called");
 	/* this time usdt3 has custom cookie */
 	ASSERT_EQ(bss->usdt3_cookie, 0xBADC00C51E, "usdt3_cookie");
 	ASSERT_EQ(bss->usdt3_arg_cnt, 3, "usdt3_arg_cnt");
@@ -158,6 +165,7 @@ static void subtest_basic_usdt(void)
 
 cleanup:
 	test_usdt__destroy(skel);
+#undef TRIGGER
 }
 
 unsigned short test_usdt_100_semaphore SEC(".probes");
@@ -419,7 +427,11 @@ static void subtest_urandom_usdt(bool auto_attach)
 void test_usdt(void)
 {
 	if (test__start_subtest("basic"))
-		subtest_basic_usdt();
+		subtest_basic_usdt(false);
+#ifdef __x86_64__
+	if (test__start_subtest("basic_optimized"))
+		subtest_basic_usdt(true);
+#endif
 	if (test__start_subtest("multispec"))
 		subtest_multispec_usdt();
 	if (test__start_subtest("urand_auto_attach"))

From 65d8fc5a4e244b1e3e756f9931b1cf9d5000ed7f Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Mon, 10 Mar 2025 14:04:47 +0100
Subject: [PATCH 1168/1173] selftests/bpf: Add uprobe_regs_equal test

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 .../selftests/bpf/prog_tests/uprobe_syscall.c | 49 +++++++++++++------
 .../selftests/bpf/progs/uprobe_syscall.c      |  4 +-
 2 files changed, 36 insertions(+), 17 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
index bcd36cd1e7188..5ecaf0980aaa9 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
@@ -43,15 +43,16 @@ static unsigned long get_nop5_offset(void *fn, void **paddr)
 	return addr ? get_uprobe_offset(addr) : -1;
 }
 
-__naked unsigned long uretprobe_regs_trigger(void)
+__naked unsigned long uprobe_regs_trigger(void)
 {
 	asm volatile (
-		"movq $0xdeadbeef, %rax\n"
+		".byte 0x0f, 0x1f, 0x44, 0x00, 0x00	\n"
+		"movq $0xdeadbeef, %rax			\n"
 		"ret\n"
 	);
 }
 
-__naked void uretprobe_regs(struct pt_regs *before, struct pt_regs *after)
+__naked void uprobe_regs(struct pt_regs *before, struct pt_regs *after)
 {
 	asm volatile (
 		"movq %r15,   0(%rdi)\n"
@@ -80,7 +81,7 @@ __naked void uretprobe_regs(struct pt_regs *before, struct pt_regs *after)
 
 		/* save 2nd argument */
 		"pushq %rsi\n"
-		"call uretprobe_regs_trigger\n"
+		"call uprobe_regs_trigger\n"
 
 		/* save  return value and load 2nd argument pointer to rax */
 		"pushq %rax\n"
@@ -120,25 +121,37 @@ __naked void uretprobe_regs(struct pt_regs *before, struct pt_regs *after)
 );
 }
 
-static void test_uretprobe_regs_equal(void)
+static void test_uprobe_regs_equal(bool retprobe)
 {
+	LIBBPF_OPTS(bpf_uprobe_opts, opts,
+		.retprobe = retprobe,
+	);
 	struct uprobe_syscall *skel = NULL;
 	struct pt_regs before = {}, after = {};
 	unsigned long *pb = (unsigned long *) &before;
 	unsigned long *pa = (unsigned long *) &after;
 	unsigned long *pp;
+	unsigned long offset;
 	unsigned int i, cnt;
-	int err;
+
+	offset = get_nop5_offset(&uprobe_regs_trigger, NULL);
+	if (!ASSERT_GE(offset, 0, "get_nop5_offset"))
+		return;
 
 	skel = uprobe_syscall__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "uprobe_syscall__open_and_load"))
 		goto cleanup;
 
-	err = uprobe_syscall__attach(skel);
-	if (!ASSERT_OK(err, "uprobe_syscall__attach"))
+	skel->links.probe = bpf_program__attach_uprobe_opts(skel->progs.probe,
+				0, "/proc/self/exe", offset, &opts);
+	if (!ASSERT_OK_PTR(skel->links.probe, "bpf_program__attach_uprobe_opts"))
 		goto cleanup;
 
-	uretprobe_regs(&before, &after);
+	/* make sure uprobe gets optimized */
+	if (!retprobe)
+		uprobe_regs_trigger();
+
+	uprobe_regs(&before, &after);
 
 	pp = (unsigned long *) &skel->bss->regs;
 	cnt = sizeof(before)/sizeof(*pb);
@@ -147,7 +160,7 @@ static void test_uretprobe_regs_equal(void)
 		unsigned int offset = i * sizeof(unsigned long);
 
 		/*
-		 * Check register before and after uretprobe_regs_trigger call
+		 * Check register before and after uprobe_regs_trigger call
 		 * that triggers the uretprobe.
 		 */
 		switch (offset) {
@@ -161,7 +174,7 @@ static void test_uretprobe_regs_equal(void)
 
 		/*
 		 * Check register seen from bpf program and register after
-		 * uretprobe_regs_trigger call
+		 * uprobe_regs_trigger call
 		 */
 		switch (offset) {
 		/*
@@ -174,6 +187,10 @@ static void test_uretprobe_regs_equal(void)
 		case offsetof(struct pt_regs, rsp):
 		case offsetof(struct pt_regs, ss):
 			break;
+		case offsetof(struct pt_regs, rax):
+			/* uprobe does not see return value */
+			if (!retprobe)
+				break;
 		default:
 			if (!ASSERT_EQ(pp[i], pa[i], "register prog-after value check"))
 				fprintf(stdout, "failed register offset %u\n", offset);
@@ -211,13 +228,13 @@ static void test_uretprobe_regs_change(void)
 	unsigned long cnt = sizeof(before)/sizeof(*pb);
 	unsigned int i, err, offset;
 
-	offset = get_uprobe_offset(uretprobe_regs_trigger);
+	offset = get_uprobe_offset(uprobe_regs_trigger);
 
 	err = write_bpf_testmod_uprobe(offset);
 	if (!ASSERT_OK(err, "register_uprobe"))
 		return;
 
-	uretprobe_regs(&before, &after);
+	uprobe_regs(&before, &after);
 
 	err = write_bpf_testmod_uprobe(0);
 	if (!ASSERT_OK(err, "unregister_uprobe"))
@@ -372,7 +389,7 @@ static void test_uretprobe_shadow_stack(void)
 	}
 
 	/* Run all of the uretprobe tests. */
-	test_uretprobe_regs_equal();
+	test_uprobe_regs_equal(false);
 	test_uretprobe_regs_change();
 	test_uretprobe_syscall_call();
 
@@ -688,7 +705,7 @@ static void test_uprobe_sigill(void)
 static void __test_uprobe_syscall(void)
 {
 	if (test__start_subtest("uretprobe_regs_equal"))
-		test_uretprobe_regs_equal();
+		test_uprobe_regs_equal(true);
 	if (test__start_subtest("uretprobe_regs_change"))
 		test_uretprobe_regs_change();
 	if (test__start_subtest("uretprobe_syscall_call"))
@@ -705,6 +722,8 @@ static void __test_uprobe_syscall(void)
 		test_uprobe_race();
 	if (test__start_subtest("uprobe_sigill"))
 		test_uprobe_sigill();
+	if (test__start_subtest("uprobe_regs_equal"))
+		test_uprobe_regs_equal(false);
 }
 #else
 static void __test_uprobe_syscall(void)
diff --git a/tools/testing/selftests/bpf/progs/uprobe_syscall.c b/tools/testing/selftests/bpf/progs/uprobe_syscall.c
index 8a4fa6c7ef590..e08c31669e5a7 100644
--- a/tools/testing/selftests/bpf/progs/uprobe_syscall.c
+++ b/tools/testing/selftests/bpf/progs/uprobe_syscall.c
@@ -7,8 +7,8 @@ struct pt_regs regs;
 
 char _license[] SEC("license") = "GPL";
 
-SEC("uretprobe//proc/self/exe:uretprobe_regs_trigger")
-int uretprobe(struct pt_regs *ctx)
+SEC("uprobe")
+int probe(struct pt_regs *ctx)
 {
 	__builtin_memcpy(&regs, ctx, sizeof(regs));
 	return 0;

From d360c61cfcb51772934261285fd28e83ef35d2f4 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Tue, 26 Nov 2024 10:46:17 +0100
Subject: [PATCH 1169/1173] selftests/bpf: Add 5-byte nop uprobe trigger bench

Add 5-byte nop uprobe trigger bench (x86_64 specific) to measure
uprobes/uretprobes on top of nop5 instruction.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/testing/selftests/bpf/bench.c           | 12 ++++++
 .../selftests/bpf/benchs/bench_trigger.c      | 42 +++++++++++++++++++
 .../selftests/bpf/benchs/run_bench_uprobes.sh |  2 +-
 3 files changed, 55 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c
index 1bd403a5ef7b3..0fd8c9b0d38f6 100644
--- a/tools/testing/selftests/bpf/bench.c
+++ b/tools/testing/selftests/bpf/bench.c
@@ -526,6 +526,12 @@ extern const struct bench bench_trig_uprobe_multi_push;
 extern const struct bench bench_trig_uretprobe_multi_push;
 extern const struct bench bench_trig_uprobe_multi_ret;
 extern const struct bench bench_trig_uretprobe_multi_ret;
+#ifdef __x86_64__
+extern const struct bench bench_trig_uprobe_nop5;
+extern const struct bench bench_trig_uretprobe_nop5;
+extern const struct bench bench_trig_uprobe_multi_nop5;
+extern const struct bench bench_trig_uretprobe_multi_nop5;
+#endif
 
 extern const struct bench bench_rb_libbpf;
 extern const struct bench bench_rb_custom;
@@ -586,6 +592,12 @@ static const struct bench *benchs[] = {
 	&bench_trig_uretprobe_multi_push,
 	&bench_trig_uprobe_multi_ret,
 	&bench_trig_uretprobe_multi_ret,
+#ifdef __x86_64__
+	&bench_trig_uprobe_nop5,
+	&bench_trig_uretprobe_nop5,
+	&bench_trig_uprobe_multi_nop5,
+	&bench_trig_uretprobe_multi_nop5,
+#endif
 	/* ringbuf/perfbuf benchmarks */
 	&bench_rb_libbpf,
 	&bench_rb_custom,
diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c
index 32e9f194d4497..82327657846e5 100644
--- a/tools/testing/selftests/bpf/benchs/bench_trigger.c
+++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c
@@ -333,6 +333,20 @@ static void *uprobe_producer_ret(void *input)
 	return NULL;
 }
 
+#ifdef __x86_64__
+__nocf_check __weak void uprobe_target_nop5(void)
+{
+	asm volatile (".byte 0x0f, 0x1f, 0x44, 0x00, 0x00");
+}
+
+static void *uprobe_producer_nop5(void *input)
+{
+	while (true)
+		uprobe_target_nop5();
+	return NULL;
+}
+#endif
+
 static void usetup(bool use_retprobe, bool use_multi, void *target_addr)
 {
 	size_t uprobe_offset;
@@ -448,6 +462,28 @@ static void uretprobe_multi_ret_setup(void)
 	usetup(true, true /* use_multi */, &uprobe_target_ret);
 }
 
+#ifdef __x86_64__
+static void uprobe_nop5_setup(void)
+{
+	usetup(false, false /* !use_multi */, &uprobe_target_nop5);
+}
+
+static void uretprobe_nop5_setup(void)
+{
+	usetup(true, false /* !use_multi */, &uprobe_target_nop5);
+}
+
+static void uprobe_multi_nop5_setup(void)
+{
+	usetup(false, true /* use_multi */, &uprobe_target_nop5);
+}
+
+static void uretprobe_multi_nop5_setup(void)
+{
+	usetup(true, true /* use_multi */, &uprobe_target_nop5);
+}
+#endif
+
 const struct bench bench_trig_syscall_count = {
 	.name = "trig-syscall-count",
 	.validate = trigger_validate,
@@ -506,3 +542,9 @@ BENCH_TRIG_USERMODE(uprobe_multi_ret, ret, "uprobe-multi-ret");
 BENCH_TRIG_USERMODE(uretprobe_multi_nop, nop, "uretprobe-multi-nop");
 BENCH_TRIG_USERMODE(uretprobe_multi_push, push, "uretprobe-multi-push");
 BENCH_TRIG_USERMODE(uretprobe_multi_ret, ret, "uretprobe-multi-ret");
+#ifdef __x86_64__
+BENCH_TRIG_USERMODE(uprobe_nop5, nop5, "uprobe-nop5");
+BENCH_TRIG_USERMODE(uretprobe_nop5, nop5, "uretprobe-nop5");
+BENCH_TRIG_USERMODE(uprobe_multi_nop5, nop5, "uprobe-multi-nop5");
+BENCH_TRIG_USERMODE(uretprobe_multi_nop5, nop5, "uretprobe-multi-nop5");
+#endif
diff --git a/tools/testing/selftests/bpf/benchs/run_bench_uprobes.sh b/tools/testing/selftests/bpf/benchs/run_bench_uprobes.sh
index af169f831f2f2..03f55405484b2 100755
--- a/tools/testing/selftests/bpf/benchs/run_bench_uprobes.sh
+++ b/tools/testing/selftests/bpf/benchs/run_bench_uprobes.sh
@@ -2,7 +2,7 @@
 
 set -eufo pipefail
 
-for i in usermode-count syscall-count {uprobe,uretprobe}-{nop,push,ret}
+for i in usermode-count syscall-count {uprobe,uretprobe}-{nop,push,ret,nop5}
 do
 	summary=$(sudo ./bench -w2 -d5 -a trig-$i | tail -n1 | cut -d'(' -f1 | cut -d' ' -f3-)
 	printf "%-15s: %s\n" $i "$summary"

From cb5df3661a9f17ee410bf4cee816cf290ea39af2 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Tue, 11 Mar 2025 09:05:24 +0100
Subject: [PATCH 1170/1173] selftests/bpf: Change test_uretprobe_regs_change
 for uprobe and uretprobe

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 .../selftests/bpf/prog_tests/uprobe_syscall.c     | 15 ++++++++++-----
 .../selftests/bpf/test_kmods/bpf_testmod.c        | 11 +++++++++--
 2 files changed, 19 insertions(+), 7 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
index 5ecaf0980aaa9..01c1aa74237bf 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
@@ -220,7 +220,7 @@ static int write_bpf_testmod_uprobe(unsigned long offset)
 	return ret != n ? (int) ret : 0;
 }
 
-static void test_uretprobe_regs_change(void)
+static void test_uprobe_regs_change(void)
 {
 	struct pt_regs before = {}, after = {};
 	unsigned long *pb = (unsigned long *) &before;
@@ -228,12 +228,17 @@ static void test_uretprobe_regs_change(void)
 	unsigned long cnt = sizeof(before)/sizeof(*pb);
 	unsigned int i, err, offset;
 
-	offset = get_uprobe_offset(uprobe_regs_trigger);
+	offset = get_nop5_offset(&uprobe_regs_trigger, NULL);
+	if (!ASSERT_GE(offset, 0, "get_nop5_offset"))
+		return;
 
 	err = write_bpf_testmod_uprobe(offset);
 	if (!ASSERT_OK(err, "register_uprobe"))
 		return;
 
+	/* make sure uprobe gets optimized */
+	uprobe_regs_trigger();
+
 	uprobe_regs(&before, &after);
 
 	err = write_bpf_testmod_uprobe(0);
@@ -390,8 +395,8 @@ static void test_uretprobe_shadow_stack(void)
 
 	/* Run all of the uretprobe tests. */
 	test_uprobe_regs_equal(false);
-	test_uretprobe_regs_change();
 	test_uretprobe_syscall_call();
+	test_uprobe_regs_change();
 
 	ARCH_PRCTL(ARCH_SHSTK_DISABLE, ARCH_SHSTK_SHSTK);
 }
@@ -706,8 +711,6 @@ static void __test_uprobe_syscall(void)
 {
 	if (test__start_subtest("uretprobe_regs_equal"))
 		test_uprobe_regs_equal(true);
-	if (test__start_subtest("uretprobe_regs_change"))
-		test_uretprobe_regs_change();
 	if (test__start_subtest("uretprobe_syscall_call"))
 		test_uretprobe_syscall_call();
 	if (test__start_subtest("uretprobe_shadow_stack"))
@@ -724,6 +727,8 @@ static void __test_uprobe_syscall(void)
 		test_uprobe_sigill();
 	if (test__start_subtest("uprobe_regs_equal"))
 		test_uprobe_regs_equal(false);
+	if (test__start_subtest("uprobe_regs_change"))
+		test_uprobe_regs_change();
 }
 #else
 static void __test_uprobe_syscall(void)
diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c
index 3220f1d28697e..08494fcf6a58c 100644
--- a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c
@@ -496,15 +496,21 @@ static struct bin_attribute bin_attr_bpf_testmod_file __ro_after_init = {
  */
 #ifdef __x86_64__
 
+static int
+uprobe_handler(struct uprobe_consumer *self, struct pt_regs *regs, __u64 *data)
+{
+	regs->cx = 0x87654321feebdaed;
+	return 0;
+}
+
 static int
 uprobe_ret_handler(struct uprobe_consumer *self, unsigned long func,
 		   struct pt_regs *regs, __u64 *data)
 
 {
 	regs->ax  = 0x12345678deadbeef;
-	regs->cx  = 0x87654321feebdaed;
 	regs->r11 = (u64) -1;
-	return true;
+	return 0;
 }
 
 struct testmod_uprobe {
@@ -516,6 +522,7 @@ struct testmod_uprobe {
 static DEFINE_MUTEX(testmod_uprobe_mutex);
 
 static struct testmod_uprobe uprobe = {
+	.consumer.handler = uprobe_handler,
 	.consumer.ret_handler = uprobe_ret_handler,
 };
 

From 36e694b15ec401196bcc7286dc3d4a43160f13df Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Sat, 8 Mar 2025 11:00:29 +0100
Subject: [PATCH 1171/1173] seccomp: passthrough uprobe systemcall without
 filtering

Pass uprobe systemcall through seccomp without depending on configuration.

Note: uprobe is currently only x86_64 and isn't expected to ever be
supported in i386.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 kernel/seccomp.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 7bbb408431ebc..9b26fc1fbbe85 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -750,13 +750,21 @@ static bool seccomp_is_const_allow(struct sock_fprog_kern *fprog,
 		return false;
 
 	/* Our single exception to filtering. */
-#ifdef __NR_uretprobe
+#if defined __NR_uretprobe || defined __NR_uprobe
 #ifdef SECCOMP_ARCH_COMPAT
 	if (sd->arch == SECCOMP_ARCH_NATIVE)
 #endif
+	{
+#ifdef __NR_uretprobe
 		if (sd->nr == __NR_uretprobe)
 			return true;
 #endif
+#ifdef __NR_uprobe
+		if (sd->nr == __NR_uprobe)
+			return true;
+#endif
+	}
+#endif
 
 	for (pc = 0; pc < fprog->len; pc++) {
 		struct sock_filter *insn = &fprog->filter[pc];
@@ -1034,6 +1042,9 @@ static const int mode1_syscalls[] = {
 	__NR_seccomp_read, __NR_seccomp_write, __NR_seccomp_exit, __NR_seccomp_sigreturn,
 #ifdef __NR_uretprobe
 	__NR_uretprobe,
+#endif
+#ifdef __NR_uprobe
+	__NR_uprobe,
 #endif
 	-1, /* negative terminated */
 };

From 0c5d0cad23db8dda6ce92b83142e0ddf90f4347e Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Mon, 24 Feb 2025 11:09:32 +0100
Subject: [PATCH 1172/1173] selftests/seccomp: validate uprobe syscall passes
 through seccomp

  UPROBE.not_attached.uprobe_default_allow
  UPROBE.not_attached.uprobe_default_block
  UPROBE.not_attached.uprobe_block_syscall
  UPROBE.not_attached.uprobe_default_block_with_syscall
  UPROBE.uprobe_attached.uprobe_default_allow
  UPROBE.uprobe_attached.uprobe_default_block
  UPROBE.uprobe_attached.uprobe_block_syscall
  UPROBE.uprobe_attached.uprobe_default_block_with_syscall
  UPROBE.uretprobe_attached.uprobe_default_allow
  UPROBE.uretprobe_attached.uprobe_default_block
  UPROBE.uretprobe_attached.uprobe_block_syscall
  UPROBE.uretprobe_attached.uprobe_default_block_with_syscall

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/testing/selftests/seccomp/seccomp_bpf.c | 88 ++++++++++++++-----
 1 file changed, 67 insertions(+), 21 deletions(-)

diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index 14ba51b52095a..ad4afac59cc54 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -4893,7 +4893,25 @@ TEST(tsync_vs_dead_thread_leader)
 	EXPECT_EQ(0, status);
 }
 
-noinline int probed(void)
+#ifdef __x86_64__
+__attribute__((naked)) noinline int probed_uprobe(void)
+{
+	/*
+	 * Optimized uprobe is possible only on top of nop5 instruction.
+	 */
+	asm volatile ("                                 \n"
+		".byte 0x0f, 0x1f, 0x44, 0x00, 0x00     \n"
+		"ret                                    \n"
+	);
+}
+#else
+noinline int probed_uprobe(void)
+{
+	return 1;
+}
+#endif
+
+noinline int probed_uretprobe(void)
 {
 	return 1;
 }
@@ -4946,35 +4964,46 @@ static ssize_t get_uprobe_offset(const void *addr)
 	return found ? (uintptr_t)addr - start + base : -1;
 }
 
-FIXTURE(URETPROBE) {
+FIXTURE(UPROBE) {
 	int fd;
 };
 
-FIXTURE_VARIANT(URETPROBE) {
+FIXTURE_VARIANT(UPROBE) {
 	/*
-	 * All of the URETPROBE behaviors can be tested with either
-	 * uretprobe attached or not
+	 * All of the U(RET)PROBE behaviors can be tested with either
+	 * u(ret)probe attached or not
 	 */
 	bool attach;
+	/*
+	 * Test both uprobe and uretprobe.
+	 */
+	bool uretprobe;
 };
 
-FIXTURE_VARIANT_ADD(URETPROBE, attached) {
+FIXTURE_VARIANT_ADD(UPROBE, not_attached) {
+	.attach = false,
+	.uretprobe = false,
+};
+
+FIXTURE_VARIANT_ADD(UPROBE, uprobe_attached) {
 	.attach = true,
+	.uretprobe = false,
 };
 
-FIXTURE_VARIANT_ADD(URETPROBE, not_attached) {
-	.attach = false,
+FIXTURE_VARIANT_ADD(UPROBE, uretprobe_attached) {
+	.attach = true,
+	.uretprobe = true,
 };
 
-FIXTURE_SETUP(URETPROBE)
+FIXTURE_SETUP(UPROBE)
 {
 	const size_t attr_sz = sizeof(struct perf_event_attr);
 	struct perf_event_attr attr;
 	ssize_t offset;
 	int type, bit;
 
-#ifndef __NR_uretprobe
-	SKIP(return, "__NR_uretprobe syscall not defined");
+#if !defined(__NR_uprobe) || !defined(__NR_uretprobe)
+	SKIP(return, "__NR_uprobe ot __NR_uretprobe syscalls not defined");
 #endif
 
 	if (!variant->attach)
@@ -4984,12 +5013,17 @@ FIXTURE_SETUP(URETPROBE)
 
 	type = determine_uprobe_perf_type();
 	ASSERT_GE(type, 0);
-	bit = determine_uprobe_retprobe_bit();
-	ASSERT_GE(bit, 0);
-	offset = get_uprobe_offset(probed);
+
+	if (variant->uretprobe) {
+		bit = determine_uprobe_retprobe_bit();
+		ASSERT_GE(bit, 0);
+	}
+
+	offset = get_uprobe_offset(variant->uretprobe ? probed_uretprobe : probed_uprobe);
 	ASSERT_GE(offset, 0);
 
-	attr.config |= 1 << bit;
+	if (variant->uretprobe)
+		attr.config |= 1 << bit;
 	attr.size = attr_sz;
 	attr.type = type;
 	attr.config1 = ptr_to_u64("/proc/self/exe");
@@ -5000,7 +5034,7 @@ FIXTURE_SETUP(URETPROBE)
 			   PERF_FLAG_FD_CLOEXEC);
 }
 
-FIXTURE_TEARDOWN(URETPROBE)
+FIXTURE_TEARDOWN(UPROBE)
 {
 	/* we could call close(self->fd), but we'd need extra filter for
 	 * that and since we are calling _exit right away..
@@ -5014,11 +5048,17 @@ static int run_probed_with_filter(struct sock_fprog *prog)
 		return -1;
 	}
 
-	probed();
+	/*
+	 * Uprobe is optimized after first hit, so let's hit twice.
+	 */
+	probed_uprobe();
+	probed_uprobe();
+
+	probed_uretprobe();
 	return 0;
 }
 
-TEST_F(URETPROBE, uretprobe_default_allow)
+TEST_F(UPROBE, uprobe_default_allow)
 {
 	struct sock_filter filter[] = {
 		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
@@ -5031,7 +5071,7 @@ TEST_F(URETPROBE, uretprobe_default_allow)
 	ASSERT_EQ(0, run_probed_with_filter(&prog));
 }
 
-TEST_F(URETPROBE, uretprobe_default_block)
+TEST_F(UPROBE, uprobe_default_block)
 {
 	struct sock_filter filter[] = {
 		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
@@ -5048,11 +5088,14 @@ TEST_F(URETPROBE, uretprobe_default_block)
 	ASSERT_EQ(0, run_probed_with_filter(&prog));
 }
 
-TEST_F(URETPROBE, uretprobe_block_uretprobe_syscall)
+TEST_F(UPROBE, uprobe_block_syscall)
 {
 	struct sock_filter filter[] = {
 		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
 			offsetof(struct seccomp_data, nr)),
+#ifdef __NR_uprobe
+		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_uprobe, 1, 2),
+#endif
 #ifdef __NR_uretprobe
 		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_uretprobe, 0, 1),
 #endif
@@ -5067,11 +5110,14 @@ TEST_F(URETPROBE, uretprobe_block_uretprobe_syscall)
 	ASSERT_EQ(0, run_probed_with_filter(&prog));
 }
 
-TEST_F(URETPROBE, uretprobe_default_block_with_uretprobe_syscall)
+TEST_F(UPROBE, uprobe_default_block_with_syscall)
 {
 	struct sock_filter filter[] = {
 		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
 			offsetof(struct seccomp_data, nr)),
+#ifdef __NR_uprobe
+		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_uprobe, 3, 0),
+#endif
 #ifdef __NR_uretprobe
 		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_uretprobe, 2, 0),
 #endif

From 3573018bd1331047e2cc0902d4e923f1711e99af Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Fri, 14 Mar 2025 13:14:28 +0100
Subject: [PATCH 1173/1173] fix

---
 .../selftests/bpf/prog_tests/uprobe_syscall.c  | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
index 01c1aa74237bf..9c7e31bb20dcb 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
@@ -4,6 +4,8 @@
 
 #ifdef __x86_64__
 
+#pragma GCC diagnostic ignored "-Wattributes"
+
 #include <unistd.h>
 #include <asm/ptrace.h>
 #include <linux/compiler.h>
@@ -36,14 +38,10 @@ static void *find_nop5(void *fn)
 
 static unsigned long get_nop5_offset(void *fn, void **paddr)
 {
-	void *addr = find_nop5(fn);
-
-	if (paddr)
-		*paddr = addr;
-	return addr ? get_uprobe_offset(addr) : -1;
+	return get_uprobe_offset(fn);
 }
 
-__naked unsigned long uprobe_regs_trigger(void)
+__nocf_check __weak __naked long uprobe_regs_trigger(void)
 {
 	asm volatile (
 		".byte 0x0f, 0x1f, 0x44, 0x00, 0x00	\n"
@@ -52,7 +50,7 @@ __naked unsigned long uprobe_regs_trigger(void)
 	);
 }
 
-__naked void uprobe_regs(struct pt_regs *before, struct pt_regs *after)
+__nocf_check __weak __naked void uprobe_regs(struct pt_regs *before, struct pt_regs *after)
 {
 	asm volatile (
 		"movq %r15,   0(%rdi)\n"
@@ -269,7 +267,7 @@ static void test_uprobe_regs_change(void)
 #define __NR_uretprobe 335
 #endif
 
-__naked unsigned long uretprobe_syscall_call_1(void)
+__nocf_check __weak __naked unsigned long uretprobe_syscall_call_1(void)
 {
 	/*
 	 * Pretend we are uretprobe trampoline to trigger the return
@@ -287,7 +285,7 @@ __naked unsigned long uretprobe_syscall_call_1(void)
 	);
 }
 
-__naked unsigned long uretprobe_syscall_call(void)
+__nocf_check __weak __naked unsigned long uretprobe_syscall_call(void)
 {
 	asm volatile (
 		"call uretprobe_syscall_call_1\n"
@@ -403,7 +401,7 @@ static void test_uretprobe_shadow_stack(void)
 
 #define TRAMP "[uprobes-trampoline]"
 
-__naked noinline void uprobe_test(void)
+__nocf_check __weak __naked void uprobe_test(void)
 {
 	asm volatile ("					\n"
 		".byte 0x0f, 0x1f, 0x44, 0x00, 0x00	\n"