Merge tag 'cxl-for-6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/cxl/cxl

Pull Compute Express Link (CXL)  updates from Dave Jiang:

 - Add support for Global Persistent Flush (GPF)

 - Cleanup of DPA partition metadata handling:
     - Remove the CXL_DECODER_MIXED enum that's not needed anymore
     - Introduce helpers to access resource and perf meta data
     - Introduce 'struct cxl_dpa_partition' and 'struct cxl_range_info'
     - Make cxl_dpa_alloc() DPA partition number agnostic
     - Remove cxl_decoder_mode
     - Cleanup partition size and perf helpers

 - Remove unused CXL partition values

 - Add logging support for CXL CPER endpoint and port protocol errors:
     - Prefix protocol error struct and function names with cxl_
     - Move protocol error definitions and structures to a common location
     - Remove drivers/firmware/efi/cper_cxl.h to include/linux/cper.h
     - Add support in GHES to process CXL CPER protocol errors
     - Process CXL CPER protocol errors
     - Add trace logging for CXL PCIe port RAS errors

 - Remove redundant gp_port init

 - Add validation of cxl device serial number

 - CXL ABI documentation updates/fixups

 - A series that uses guard() to clean up open coded mutex lockings and
   remove gotos for error handling.

 - Some followup patches to support dirty shutdown accounting:
     - Add helper to retrieve DVSEC offset for dirty shutdown registers
     - Rename cxl_get_dirty_shutdown() to cxl_arm_dirty_shutdown()
     - Add support for dirty shutdown count via sysfs
     - cxl_test support for dirty shutdown

 - A series to support CXL mailbox Features commands.

   Mostly in preparation for CXL EDAC code to utilize the Features
   commands. It's also in preparation for CXL fwctl support to utilize
   the CXL Features. The commands include "Get Supported Features", "Get
   Feature", and "Set Feature".

 - A series to support extended linear cache support described by the
   ACPI HMAT table.

   The addition helps enumerate the cache and also provides additional
   RAS reporting support for configuration with extended linear cache.
   (and related fixes for the series).

 - An update to cxl_test to support a 3-way capable CFMWS

 - A documentation fix to remove unused "mixed mode"

* tag 'cxl-for-6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/cxl/cxl: (39 commits)
  cxl/region: Fix the first aliased address miscalculation
  cxl/region: Quiet some dev_warn()s in extended linear cache setup
  cxl/Documentation: Remove 'mixed' from sysfs mode doc
  cxl: Fix warning from emitting resource_size_t as long long int on 32bit systems
  cxl/test: Define a CFMWS capable of a 3 way HB interleave
  cxl/mem: Do not return error if CONFIG_CXL_MCE unset
  tools/testing/cxl: Set Shutdown State support
  cxl/pmem: Export dirty shutdown count via sysfs
  cxl/pmem: Rename cxl_dirty_shutdown_state()
  cxl/pci: Introduce cxl_gpf_get_dvsec()
  cxl/pci: Support Global Persistent Flush (GPF)
  cxl: Document missing sysfs files
  cxl: Plug typos in ABI doc
  cxl/pmem: debug invalid serial number data
  cxl/cdat: Remove redundant gp_port initialization
  cxl/memdev: Remove unused partition values
  cxl/region: Drop goto pattern of construct_region()
  cxl/region: Drop goto pattern in cxl_dax_region_alloc()
  cxl/core: Use guard() to drop goto pattern of cxl_dpa_alloc()
  cxl/core: Use guard() to drop the goto pattern of cxl_dpa_free()
  ...

Author: torvalds

Documentation/ABI/stable/sysfs-devices-node

@@ -177,6 +177,12 @@ Description:
 		The cache write policy: 0 for write-back, 1 for write-through,
 		other or unknown.
 
+What:		/sys/devices/system/node/nodeX/memory_side_cache/indexY/address_mode
+Date:		March 2025
+Contact:	Dave Jiang <[email protected]>
+Description:
+		The address mode: 0 for reserved, 1 for extended-linear.
+
 What:		/sys/devices/system/node/nodeX/x86/sgx_total_bytes
 Date:		November 2021
 Contact:	Jarkko Sakkinen <[email protected]>

Documentation/ABI/testing/sysfs-bus-cxl

@@ -1,5 +1,5 @@
 What:		/sys/bus/cxl/flush
-Date:		Januarry, 2022
+Date:		January, 2022
 KernelVersion:	v5.18
 Contact:	[email protected]
 Description:
@@ -18,6 +18,24 @@ Description:
 		specification.
 
 
+What:		/sys/bus/cxl/devices/memX/payload_max
+Date:		December, 2020
+KernelVersion:	v5.12
+Contact:	[email protected]
+Description:
+		(RO) Maximum size (in bytes) of the mailbox command payload
+		registers. Linux caps this at 1MB if the device reports a
+		larger size.
+
+
+What:		/sys/bus/cxl/devices/memX/label_storage_size
+Date:		May, 2021
+KernelVersion:	v5.13
+Contact:	[email protected]
+Description:
+		(RO) Size (in bytes) of the Label Storage Area (LSA).
+
+
 What:		/sys/bus/cxl/devices/memX/ram/size
 Date:		December, 2020
 KernelVersion:	v5.12
@@ -33,7 +51,7 @@ Date:		May, 2023
 KernelVersion:	v6.8
 Contact:	[email protected]
 Description:
-		(RO) For CXL host platforms that support "QoS Telemmetry"
+		(RO) For CXL host platforms that support "QoS Telemetry"
 		this attribute conveys a comma delimited list of platform
 		specific cookies that identifies a QoS performance class
 		for the volatile partition of the CXL mem device. These
@@ -60,7 +78,7 @@ Date:		May, 2023
 KernelVersion:	v6.8
 Contact:	[email protected]
 Description:
-		(RO) For CXL host platforms that support "QoS Telemmetry"
+		(RO) For CXL host platforms that support "QoS Telemetry"
 		this attribute conveys a comma delimited list of platform
 		specific cookies that identifies a QoS performance class
 		for the persistent partition of the CXL mem device. These
@@ -321,14 +339,13 @@ KernelVersion:	v6.0
 Contact:	[email protected]
 Description:
 		(RW) When a CXL decoder is of devtype "cxl_decoder_endpoint" it
-		translates from a host physical address range, to a device local
-		address range. Device-local address ranges are further split
-		into a 'ram' (volatile memory) range and 'pmem' (persistent
-		memory) range. The 'mode' attribute emits one of 'ram', 'pmem',
-		'mixed', or 'none'. The 'mixed' indication is for error cases
-		when a decoder straddles the volatile/persistent partition
-		boundary, and 'none' indicates the decoder is not actively
-		decoding, or no DPA allocation policy has been set.
+		translates from a host physical address range, to a device
+		local address range. Device-local address ranges are further
+		split into a 'ram' (volatile memory) range and 'pmem'
+		(persistent memory) range. The 'mode' attribute emits one of
+		'ram', 'pmem', or 'none'. The 'none' indicates the decoder is
+		not actively decoding, or no DPA allocation policy has been
+		set.
 
 		'mode' can be written, when the decoder is in the 'disabled'
 		state, with either 'ram' or 'pmem' to set the boundaries for the
@@ -423,7 +440,7 @@ Date:		May, 2023
 KernelVersion:	v6.5
 Contact:	[email protected]
 Description:
-		(RO) For CXL host platforms that support "QoS Telemmetry" this
+		(RO) For CXL host platforms that support "QoS Telemetry" this
 		root-decoder-only attribute conveys a platform specific cookie
 		that identifies a QoS performance class for the CXL Window.
 		This class-id can be compared against a similar "qos_class"
@@ -586,3 +603,15 @@ Description:
 		See Documentation/ABI/stable/sysfs-devices-node. access0 provides
 		the number to the closest initiator and access1 provides the
 		number to the closest CPU.
+
+
+What:		/sys/bus/cxl/devices/nvdimm-bridge0/ndbusX/nmemY/cxl/dirty_shutdown
+Date:		Feb, 2025
+KernelVersion:	v6.15
+Contact:	[email protected]
+Description:
+		(RO) The device dirty shutdown count value, which is the number
+		of times the device could have incurred in potential data loss.
+		The count is persistent across power loss and wraps back to 0
+		upon overflow. If this file is not present, the device does not
+		have the necessary support for dirty tracking.

Documentation/driver-api/cxl/maturity-map.rst

@@ -130,7 +130,7 @@ Mailbox commands
 * [0] Switch CCI
 * [3] Timestamp
 * [1] PMEM labels
-* [0] PMEM GPF / Dirty Shutdown
+* [3] PMEM GPF / Dirty Shutdown
 * [0] Scan Media
 
 PMU

arch/x86/mm/pat/set_memory.c

@@ -2274,6 +2274,7 @@ int set_mce_nospec(unsigned long pfn)
 		pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn);
 	return rc;
 }
+EXPORT_SYMBOL_GPL(set_mce_nospec);
 
 /* Restore full speculative operation to the pfn. */
 int clear_mce_nospec(unsigned long pfn)

drivers/acpi/apei/ghes.c

@@ -674,6 +674,105 @@ static void ghes_defer_non_standard_event(struct acpi_hest_generic_data *gdata,
 	schedule_work(&entry->work);
 }
 
+/* Room for 8 entries */
+#define CXL_CPER_PROT_ERR_FIFO_DEPTH 8
+static DEFINE_KFIFO(cxl_cper_prot_err_fifo, struct cxl_cper_prot_err_work_data,
+		    CXL_CPER_PROT_ERR_FIFO_DEPTH);
+
+/* Synchronize schedule_work() with cxl_cper_prot_err_work changes */
+static DEFINE_SPINLOCK(cxl_cper_prot_err_work_lock);
+struct work_struct *cxl_cper_prot_err_work;
+
+static void cxl_cper_post_prot_err(struct cxl_cper_sec_prot_err *prot_err,
+				   int severity)
+{
+#ifdef CONFIG_ACPI_APEI_PCIEAER
+	struct cxl_cper_prot_err_work_data wd;
+	u8 *dvsec_start, *cap_start;
+
+	if (!(prot_err->valid_bits & PROT_ERR_VALID_AGENT_ADDRESS)) {
+		pr_err_ratelimited("CXL CPER invalid agent type\n");
+		return;
+	}
+
+	if (!(prot_err->valid_bits & PROT_ERR_VALID_ERROR_LOG)) {
+		pr_err_ratelimited("CXL CPER invalid protocol error log\n");
+		return;
+	}
+
+	if (prot_err->err_len != sizeof(struct cxl_ras_capability_regs)) {
+		pr_err_ratelimited("CXL CPER invalid RAS Cap size (%u)\n",
+				   prot_err->err_len);
+		return;
+	}
+
+	if (!(prot_err->valid_bits & PROT_ERR_VALID_SERIAL_NUMBER))
+		pr_warn(FW_WARN "CXL CPER no device serial number\n");
+
+	guard(spinlock_irqsave)(&cxl_cper_prot_err_work_lock);
+
+	if (!cxl_cper_prot_err_work)
+		return;
+
+	switch (prot_err->agent_type) {
+	case RCD:
+	case DEVICE:
+	case LD:
+	case FMLD:
+	case RP:
+	case DSP:
+	case USP:
+		memcpy(&wd.prot_err, prot_err, sizeof(wd.prot_err));
+
+		dvsec_start = (u8 *)(prot_err + 1);
+		cap_start = dvsec_start + prot_err->dvsec_len;
+
+		memcpy(&wd.ras_cap, cap_start, sizeof(wd.ras_cap));
+		wd.severity = cper_severity_to_aer(severity);
+		break;
+	default:
+		pr_err_ratelimited("CXL CPER invalid agent type: %d\n",
+				   prot_err->agent_type);
+		return;
+	}
+
+	if (!kfifo_put(&cxl_cper_prot_err_fifo, wd)) {
+		pr_err_ratelimited("CXL CPER kfifo overflow\n");
+		return;
+	}
+
+	schedule_work(cxl_cper_prot_err_work);
+#endif
+}
+
+int cxl_cper_register_prot_err_work(struct work_struct *work)
+{
+	if (cxl_cper_prot_err_work)
+		return -EINVAL;
+
+	guard(spinlock)(&cxl_cper_prot_err_work_lock);
+	cxl_cper_prot_err_work = work;
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cper_register_prot_err_work, "CXL");
+
+int cxl_cper_unregister_prot_err_work(struct work_struct *work)
+{
+	if (cxl_cper_prot_err_work != work)
+		return -EINVAL;
+
+	guard(spinlock)(&cxl_cper_prot_err_work_lock);
+	cxl_cper_prot_err_work = NULL;
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cper_unregister_prot_err_work, "CXL");
+
+int cxl_cper_prot_err_kfifo_get(struct cxl_cper_prot_err_work_data *wd)
+{
+	return kfifo_get(&cxl_cper_prot_err_fifo, wd);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cper_prot_err_kfifo_get, "CXL");
+
 /* Room for 8 entries for each of the 4 event log queues */
 #define CXL_CPER_FIFO_DEPTH 32
 DEFINE_KFIFO(cxl_cper_fifo, struct cxl_cper_work_data, CXL_CPER_FIFO_DEPTH);
@@ -777,6 +876,10 @@ static bool ghes_do_proc(struct ghes *ghes,
 		}
 		else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) {
 			queued = ghes_handle_arm_hw_error(gdata, sev, sync);
+		} else if (guid_equal(sec_type, &CPER_SEC_CXL_PROT_ERR)) {
+			struct cxl_cper_sec_prot_err *prot_err = acpi_hest_get_payload(gdata);
+
+			cxl_cper_post_prot_err(prot_err, gdata->error_severity);
 		} else if (guid_equal(sec_type, &CPER_SEC_CXL_GEN_MEDIA_GUID)) {
 			struct cxl_cper_event_rec *rec = acpi_hest_get_payload(gdata);
 

drivers/acpi/numa/hmat.c

@@ -108,6 +108,45 @@ static struct memory_target *find_mem_target(unsigned int mem_pxm)
 	return NULL;
 }
 
+/**
+ * hmat_get_extended_linear_cache_size - Retrieve the extended linear cache size
+ * @backing_res: resource from the backing media
+ * @nid: node id for the memory region
+ * @cache_size: (Output) size of extended linear cache.
+ *
+ * Return: 0 on success. Errno on failure.
+ *
+ */
+int hmat_get_extended_linear_cache_size(struct resource *backing_res, int nid,
+					resource_size_t *cache_size)
+{
+	unsigned int pxm = node_to_pxm(nid);
+	struct memory_target *target;
+	struct target_cache *tcache;
+	struct resource *res;
+
+	target = find_mem_target(pxm);
+	if (!target)
+		return -ENOENT;
+
+	list_for_each_entry(tcache, &target->caches, node) {
+		if (tcache->cache_attrs.address_mode !=
+				NODE_CACHE_ADDR_MODE_EXTENDED_LINEAR)
+			continue;
+
+		res = &target->memregions;
+		if (!resource_contains(res, backing_res))
+			continue;
+
+		*cache_size = tcache->cache_attrs.size;
+		return 0;
+	}
+
+	*cache_size = 0;
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(hmat_get_extended_linear_cache_size, "CXL");
+
 static struct memory_target *acpi_find_genport_target(u32 uid)
 {
 	struct memory_target *target;
@@ -506,6 +545,11 @@ static __init int hmat_parse_cache(union acpi_subtable_headers *header,
 	switch ((attrs & ACPI_HMAT_CACHE_ASSOCIATIVITY) >> 8) {
 	case ACPI_HMAT_CA_DIRECT_MAPPED:
 		tcache->cache_attrs.indexing = NODE_CACHE_DIRECT_MAP;
+		/* Extended Linear mode is only valid if cache is direct mapped */
+		if (cache->address_mode == ACPI_HMAT_CACHE_MODE_EXTENDED_LINEAR) {
+			tcache->cache_attrs.address_mode =
+				NODE_CACHE_ADDR_MODE_EXTENDED_LINEAR;
+		}
 		break;
 	case ACPI_HMAT_CA_COMPLEX_CACHE_INDEXING:
 		tcache->cache_attrs.indexing = NODE_CACHE_INDEXED;

drivers/base/node.c

@@ -244,12 +244,14 @@ CACHE_ATTR(size, "%llu")
 CACHE_ATTR(line_size, "%u")
 CACHE_ATTR(indexing, "%u")
 CACHE_ATTR(write_policy, "%u")
+CACHE_ATTR(address_mode, "%#x")
 
 static struct attribute *cache_attrs[] = {
 	&dev_attr_indexing.attr,
 	&dev_attr_size.attr,
 	&dev_attr_line_size.attr,
 	&dev_attr_write_policy.attr,
+	&dev_attr_address_mode.attr,
 	NULL,
 };
 ATTRIBUTE_GROUPS(cache);

drivers/cxl/Kconfig

@@ -158,4 +158,8 @@ config CXL_REGION_INVALIDATION_TEST
 	  If unsure, or if this kernel is meant for production environments,
 	  say N.
 
+config CXL_MCE
+	def_bool y
+	depends on X86_MCE && MEMORY_FAILURE
+
 endif

drivers/cxl/core/Makefile

@@ -14,6 +14,9 @@ cxl_core-y += pci.o
 cxl_core-y += hdm.o
 cxl_core-y += pmu.o
 cxl_core-y += cdat.o
+cxl_core-y += ras.o
+cxl_core-y += acpi.o
 cxl_core-$(CONFIG_TRACING) += trace.o
 cxl_core-$(CONFIG_CXL_REGION) += region.o
+cxl_core-$(CONFIG_CXL_MCE) += mce.o
 cxl_core-$(CONFIG_CXL_FEATURES) += features.o

drivers/cxl/core/acpi.c

@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2024 Intel Corporation. All rights reserved. */
+#include <linux/acpi.h>
+#include "cxl.h"
+#include "core.h"
+
+int cxl_acpi_get_extended_linear_cache_size(struct resource *backing_res,
+					    int nid, resource_size_t *size)
+{
+	return hmat_get_extended_linear_cache_size(backing_res, nid, size);
+}