[PATCH v7 00/10] ACPI: APEI: share GHES CPER helpers and add DT FFH provider

[PATCH v7 00/10] ACPI: APEI: share GHES CPER helpers and add DT FFH provider

[Ahmed Tiba]

This is v7 of the GHES refactor series. Compared to v6, it addresses
the Sashiko-reported issues including pre-existing ones and fixes
the ACPI-disabled cper-x86 build break.

The DT firmware-first CPER provider is intended for the upstream zena-css
platform. Validation so far has been on FVP.

Changes in v7:
- Address Sashiko-reported issues for this series, including pre-existing ones.
- Fix pre-existing CPER header overflow validation in cper.c.
- Fix AER recovery leak when no pci_dev is found.
- For DT provider: serialize pool init, return IRQ_NONE on empty status,
  add OF_RESERVED_MEM dependency, and harden status length checks.
- Include <asm/acpi.h> in cper-x86.c for ACPI-disabled builds.
- Link to v6: https://lore.kernel.org/r/20260617-topics-ahmtib01-ras_ffh_arm_internal_review-v6-0-91f725174aa0@arm.com

---
Ahmed Tiba (10):
      ACPI: APEI: GHES: share macros via a private header
      ACPI: APEI: GHES: move CPER read helpers
      ACPI: APEI: GHES: move GHESv2 ack and alloc helpers
      ACPI: APEI: GHES: move estatus cache helpers
      ACPI: APEI: GHES: move vendor record helpers
      ACPI: APEI: GHES: move CXL CPER helpers
      ACPI: APEI: introduce GHES helper
      ACPI: APEI: share GHES CPER helpers
      dt-bindings: firmware: add arm,ras-cper
      RAS: add firmware-first CPER provider

 Documentation/admin-guide/RAS/main.rst             |   15 +
 .../devicetree/bindings/firmware/arm,ras-cper.yaml |   52 +
 MAINTAINERS                                        |    6 +
 drivers/Makefile                                   |    1 +
 drivers/acpi/Kconfig                               |    4 +
 drivers/acpi/apei/Kconfig                          |    1 +
 drivers/acpi/apei/apei-internal.h                  |    3 +-
 drivers/acpi/apei/ghes.c                           | 1044 +-----------------
 drivers/acpi/apei/ghes_cper.c                      | 1122 ++++++++++++++++++++
 drivers/firmware/efi/cper-x86.c                    |    1 +
 drivers/firmware/efi/cper.c                        |    3 +-
 drivers/pci/pcie/aer.c                             |    9 +-
 drivers/ras/Kconfig                                |   12 +
 drivers/ras/Makefile                               |    1 +
 drivers/ras/cper-esource.c                         |  332 ++++++
 include/acpi/ghes.h                                |   10 +-
 include/acpi/ghes_cper.h                           |  141 +++
 include/cxl/event.h                                |    2 +-
 18 files changed, 1709 insertions(+), 1050 deletions(-)
---
base-commit: 0e35b9b6ec0ffcc5e23cbdec09f5c622ad532b53
change-id: 20260220-topics-ahmtib01-ras_ffh_arm_internal_review-bfddc7fc7cab

Best regards,
-- 
Ahmed Tiba <ahmed.tiba@arm.com>

[PATCH v7 01/10] ACPI: APEI: GHES: share macros via a private header

[Ahmed Tiba]

Carve the CPER helper macros out of ghes.c and place them in a private
header so they can be shared with upcoming helper files.

Move the vendor record entry declaration and the prototypes for the CPER
read and clear helpers along with ghes_new() and ghes_fini() into the
same header. This requires dropping their local static visibility in
ghes.c.

Also synchronize ghes_proc_irq_work during ghes_remove()
to avoid a use-after-free.

Reviewed-by: Jonathan Cameron <jic23@kernel.org>
Signed-off-by: Ahmed Tiba <ahmed.tiba@arm.com>
---
 drivers/acpi/apei/ghes.c |  95 +++++++++----------------------------------
 include/acpi/ghes_cper.h | 103 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 122 insertions(+), 76 deletions(-)

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 3236a3ce79d6..c73a316644e8 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -49,6 +49,7 @@
 
 #include <acpi/actbl1.h>
 #include <acpi/ghes.h>
+#include <acpi/ghes_cper.h>
 #include <acpi/apei.h>
 #include <asm/fixmap.h>
 #include <asm/tlbflush.h>
@@ -57,40 +58,6 @@
 
 #include "apei-internal.h"
 
-#define GHES_PFX	"GHES: "
-
-#define GHES_ESTATUS_MAX_SIZE		65536
-#define GHES_ESOURCE_PREALLOC_MAX_SIZE	65536
-
-#define GHES_ESTATUS_POOL_MIN_ALLOC_ORDER 3
-
-/* This is just an estimation for memory pool allocation */
-#define GHES_ESTATUS_CACHE_AVG_SIZE	512
-
-#define GHES_ESTATUS_CACHES_SIZE	4
-
-#define GHES_ESTATUS_IN_CACHE_MAX_NSEC	10000000000ULL
-/* Prevent too many caches are allocated because of RCU */
-#define GHES_ESTATUS_CACHE_ALLOCED_MAX	(GHES_ESTATUS_CACHES_SIZE * 3 / 2)
-
-#define GHES_ESTATUS_CACHE_LEN(estatus_len)			\
-	(sizeof(struct ghes_estatus_cache) + (estatus_len))
-#define GHES_ESTATUS_FROM_CACHE(estatus_cache)			\
-	((struct acpi_hest_generic_status *)				\
-	 ((struct ghes_estatus_cache *)(estatus_cache) + 1))
-
-#define GHES_ESTATUS_NODE_LEN(estatus_len)			\
-	(sizeof(struct ghes_estatus_node) + (estatus_len))
-#define GHES_ESTATUS_FROM_NODE(estatus_node)			\
-	((struct acpi_hest_generic_status *)				\
-	 ((struct ghes_estatus_node *)(estatus_node) + 1))
-
-#define GHES_VENDOR_ENTRY_LEN(gdata_len)                               \
-	(sizeof(struct ghes_vendor_record_entry) + (gdata_len))
-#define GHES_GDATA_FROM_VENDOR_ENTRY(vendor_entry)                     \
-	((struct acpi_hest_generic_data *)                              \
-	((struct ghes_vendor_record_entry *)(vendor_entry) + 1))
-
 /*
  *  NMI-like notifications vary by architecture, before the compiler can prune
  *  unused static functions it needs a value for these enums.
@@ -102,25 +69,6 @@
 
 static ATOMIC_NOTIFIER_HEAD(ghes_report_chain);
 
-static inline bool is_hest_type_generic_v2(struct ghes *ghes)
-{
-	return ghes->generic->header.type == ACPI_HEST_TYPE_GENERIC_ERROR_V2;
-}
-
-/*
- * A platform may describe one error source for the handling of synchronous
- * errors (e.g. MCE or SEA), or for handling asynchronous errors (e.g. SCI
- * or External Interrupt). On x86, the HEST notifications are always
- * asynchronous, so only SEA on ARM is delivered as a synchronous
- * notification.
- */
-static inline bool is_hest_sync_notify(struct ghes *ghes)
-{
-	u8 notify_type = ghes->generic->notify.type;
-
-	return notify_type == ACPI_HEST_NOTIFY_SEA;
-}
-
 /*
  * This driver isn't really modular, however for the time being,
  * continuing to use module_param is the easiest way to remain
@@ -165,12 +113,6 @@ static DEFINE_MUTEX(ghes_devs_mutex);
  */
 static DEFINE_SPINLOCK(ghes_notify_lock_irq);
 
-struct ghes_vendor_record_entry {
-	struct work_struct work;
-	int error_severity;
-	char vendor_record[];
-};
-
 static struct gen_pool *ghes_estatus_pool;
 
 static struct ghes_estatus_cache __rcu *ghes_estatus_caches[GHES_ESTATUS_CACHES_SIZE];
@@ -266,7 +208,7 @@ static void ghes_ack_error(struct acpi_hest_generic_v2 *gv2)
 	apei_write(val, &gv2->read_ack_register);
 }
 
-static struct ghes *ghes_new(struct acpi_hest_generic *generic)
+struct ghes *ghes_new(struct acpi_hest_generic *generic)
 {
 	struct ghes *ghes;
 	unsigned int error_block_length;
@@ -313,7 +255,7 @@ static struct ghes *ghes_new(struct acpi_hest_generic *generic)
 	return ERR_PTR(rc);
 }
 
-static void ghes_fini(struct ghes *ghes)
+void ghes_fini(struct ghes *ghes)
 {
 	kfree(ghes->estatus);
 	apei_unmap_generic_address(&ghes->generic->error_status_address);
@@ -363,8 +305,8 @@ static void ghes_copy_tofrom_phys(void *buffer, u64 paddr, u32 len,
 }
 
 /* Check the top-level record header has an appropriate size. */
-static int __ghes_check_estatus(struct ghes *ghes,
-				struct acpi_hest_generic_status *estatus)
+int __ghes_check_estatus(struct ghes *ghes,
+			 struct acpi_hest_generic_status *estatus)
 {
 	u32 len = cper_estatus_len(estatus);
 	u32 max_len = min(ghes->generic->error_block_length,
@@ -389,9 +331,9 @@ static int __ghes_check_estatus(struct ghes *ghes,
 }
 
 /* Read the CPER block, returning its address, and header in estatus. */
-static int __ghes_peek_estatus(struct ghes *ghes,
-			       struct acpi_hest_generic_status *estatus,
-			       u64 *buf_paddr, enum fixed_addresses fixmap_idx)
+int __ghes_peek_estatus(struct ghes *ghes,
+			struct acpi_hest_generic_status *estatus,
+			u64 *buf_paddr, enum fixed_addresses fixmap_idx)
 {
 	struct acpi_hest_generic *g = ghes->generic;
 	int rc;
@@ -400,7 +342,7 @@ static int __ghes_peek_estatus(struct ghes *ghes,
 	if (rc) {
 		*buf_paddr = 0;
 		pr_warn_ratelimited(FW_WARN GHES_PFX
-"Failed to read error status block address for hardware error source: %d.\n",
+				    "Failed to read error status block address for hardware error source: %d.\n",
 				   g->header.source_id);
 		return -EIO;
 	}
@@ -417,9 +359,9 @@ static int __ghes_peek_estatus(struct ghes *ghes,
 	return 0;
 }
 
-static int __ghes_read_estatus(struct acpi_hest_generic_status *estatus,
-			       u64 buf_paddr, enum fixed_addresses fixmap_idx,
-			       size_t buf_len)
+int __ghes_read_estatus(struct acpi_hest_generic_status *estatus,
+			u64 buf_paddr, enum fixed_addresses fixmap_idx,
+			size_t buf_len)
 {
 	ghes_copy_tofrom_phys(estatus, buf_paddr, buf_len, 1, fixmap_idx);
 	if (cper_estatus_check(estatus)) {
@@ -431,9 +373,9 @@ static int __ghes_read_estatus(struct acpi_hest_generic_status *estatus,
 	return 0;
 }
 
-static int ghes_read_estatus(struct ghes *ghes,
-			     struct acpi_hest_generic_status *estatus,
-			     u64 *buf_paddr, enum fixed_addresses fixmap_idx)
+int ghes_read_estatus(struct ghes *ghes,
+		      struct acpi_hest_generic_status *estatus,
+		      u64 *buf_paddr, enum fixed_addresses fixmap_idx)
 {
 	int rc;
 
@@ -449,9 +391,9 @@ static int ghes_read_estatus(struct ghes *ghes,
 				   cper_estatus_len(estatus));
 }
 
-static void ghes_clear_estatus(struct ghes *ghes,
-			       struct acpi_hest_generic_status *estatus,
-			       u64 buf_paddr, enum fixed_addresses fixmap_idx)
+void ghes_clear_estatus(struct ghes *ghes,
+			struct acpi_hest_generic_status *estatus,
+			u64 buf_paddr, enum fixed_addresses fixmap_idx)
 {
 	estatus->block_status = 0;
 
@@ -1852,6 +1794,7 @@ static void ghes_remove(struct platform_device *ghes_dev)
 		break;
 	}
 
+	irq_work_sync(&ghes_proc_irq_work);
 	ghes_fini(ghes);
 
 	mutex_lock(&ghes_devs_mutex);
diff --git a/include/acpi/ghes_cper.h b/include/acpi/ghes_cper.h
new file mode 100644
index 000000000000..4649e3140888
--- /dev/null
+++ b/include/acpi/ghes_cper.h
@@ -0,0 +1,103 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * GHES declarations used by both the ACPI APEI GHES driver
+ * and the firmware-first CPER provider.
+ *
+ * These declarations lets GHES and other firmware-first error sources use
+ * the same helper so the non-ACPI path follows the same
+ * behavior as GHES instead of carrying a separate copy.
+ *
+ * Derived from the ACPI APEI GHES driver.
+ *
+ * Copyright 2010,2011 Intel Corp.
+ *   Author: Huang Ying <ying.huang@intel.com>
+ */
+
+#ifndef ACPI_APEI_GHES_CPER_H
+#define ACPI_APEI_GHES_CPER_H
+
+#include <linux/workqueue.h>
+
+#include <acpi/ghes.h>
+#include <asm/fixmap.h>
+
+#define GHES_PFX	"GHES: "
+
+#define GHES_ESTATUS_MAX_SIZE		65536
+#define GHES_ESOURCE_PREALLOC_MAX_SIZE	65536
+
+#define GHES_ESTATUS_POOL_MIN_ALLOC_ORDER 3
+
+/* This is just an estimation for memory pool allocation */
+#define GHES_ESTATUS_CACHE_AVG_SIZE	512
+
+#define GHES_ESTATUS_CACHES_SIZE	4
+
+#define GHES_ESTATUS_IN_CACHE_MAX_NSEC	10000000000ULL
+/* Prevent too many caches are allocated because of RCU */
+#define GHES_ESTATUS_CACHE_ALLOCED_MAX	(GHES_ESTATUS_CACHES_SIZE * 3 / 2)
+
+#define GHES_ESTATUS_CACHE_LEN(estatus_len)			\
+	(sizeof(struct ghes_estatus_cache) + (estatus_len))
+#define GHES_ESTATUS_FROM_CACHE(estatus_cache)			\
+	((struct acpi_hest_generic_status *)				\
+	 ((struct ghes_estatus_cache *)(estatus_cache) + 1))
+
+#define GHES_ESTATUS_NODE_LEN(estatus_len)			\
+	(sizeof(struct ghes_estatus_node) + (estatus_len))
+#define GHES_ESTATUS_FROM_NODE(estatus_node)			\
+	((struct acpi_hest_generic_status *)				\
+	 ((struct ghes_estatus_node *)(estatus_node) + 1))
+
+#define GHES_VENDOR_ENTRY_LEN(gdata_len)                               \
+	(sizeof(struct ghes_vendor_record_entry) + (gdata_len))
+#define GHES_GDATA_FROM_VENDOR_ENTRY(vendor_entry)                     \
+	((struct acpi_hest_generic_data *)                              \
+	((struct ghes_vendor_record_entry *)(vendor_entry) + 1))
+
+static inline bool is_hest_type_generic_v2(struct ghes *ghes)
+{
+	return ghes->generic->header.type == ACPI_HEST_TYPE_GENERIC_ERROR_V2;
+}
+
+/*
+ * A platform may describe one error source for the handling of synchronous
+ * errors (e.g. MCE or SEA), or for handling asynchronous errors (e.g. SCI
+ * or External Interrupt). On x86, the HEST notifications are always
+ * asynchronous, so only SEA on ARM is delivered as a synchronous
+ * notification.
+ */
+static inline bool is_hest_sync_notify(struct ghes *ghes)
+{
+	u8 notify_type = ghes->generic->notify.type;
+
+	return notify_type == ACPI_HEST_NOTIFY_SEA;
+}
+
+struct ghes_vendor_record_entry {
+	struct work_struct work;
+	int error_severity;
+	char vendor_record[];
+};
+
+#ifdef CONFIG_ACPI_APEI
+struct ghes *ghes_new(struct acpi_hest_generic *generic);
+void ghes_fini(struct ghes *ghes);
+
+int ghes_read_estatus(struct ghes *ghes,
+		      struct acpi_hest_generic_status *estatus,
+		      u64 *buf_paddr, enum fixed_addresses fixmap_idx);
+void ghes_clear_estatus(struct ghes *ghes,
+			struct acpi_hest_generic_status *estatus,
+			u64 buf_paddr, enum fixed_addresses fixmap_idx);
+int __ghes_peek_estatus(struct ghes *ghes,
+			struct acpi_hest_generic_status *estatus,
+			u64 *buf_paddr, enum fixed_addresses fixmap_idx);
+int __ghes_check_estatus(struct ghes *ghes,
+			 struct acpi_hest_generic_status *estatus);
+int __ghes_read_estatus(struct acpi_hest_generic_status *estatus,
+			u64 buf_paddr, enum fixed_addresses fixmap_idx,
+			size_t buf_len);
+#endif
+
+#endif /* ACPI_APEI_GHES_CPER_H */

-- 
2.43.0

[PATCH v7 02/10] ACPI: APEI: GHES: move CPER read helpers

[Ahmed Tiba]

Relocate the CPER buffer mapping, peek, and clear helpers from ghes.c into
ghes_cper.c so they can be shared with other firmware-first providers.
This commit only shuffles code; behavior stays the same.

While here, fix ghes_ack_error() mask handling and add second-copy length
validation in __ghes_read_estatus().

Reviewed-by: Jonathan Cameron <jic23@kernel.org>
Signed-off-by: Ahmed Tiba <ahmed.tiba@arm.com>
---
 drivers/acpi/apei/Makefile    |   2 +-
 drivers/acpi/apei/ghes.c      | 166 ---------------------------------
 drivers/acpi/apei/ghes_cper.c | 210 ++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 211 insertions(+), 167 deletions(-)

diff --git a/drivers/acpi/apei/Makefile b/drivers/acpi/apei/Makefile
index 66588d6be56f..f57f3b009d8e 100644
--- a/drivers/acpi/apei/Makefile
+++ b/drivers/acpi/apei/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_ACPI_APEI)		+= apei.o
-obj-$(CONFIG_ACPI_APEI_GHES)	+= ghes.o
+obj-$(CONFIG_ACPI_APEI_GHES)	+= ghes.o ghes_cper.o
 # clang versions prior to 18 may blow out the stack with KASAN
 ifeq ($(CONFIG_COMPILE_TEST)_$(CONFIG_CC_IS_CLANG)_$(call clang-min-version, 180000),y_y_)
 KASAN_SANITIZE_ghes.o := n
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index c73a316644e8..f74fd5de34cc 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -118,26 +118,6 @@ static struct gen_pool *ghes_estatus_pool;
 static struct ghes_estatus_cache __rcu *ghes_estatus_caches[GHES_ESTATUS_CACHES_SIZE];
 static atomic_t ghes_estatus_cache_alloced;
 
-static void __iomem *ghes_map(u64 pfn, enum fixed_addresses fixmap_idx)
-{
-	phys_addr_t paddr;
-	pgprot_t prot;
-
-	paddr = PFN_PHYS(pfn);
-	prot = arch_apei_get_mem_attribute(paddr);
-	__set_fixmap(fixmap_idx, paddr, prot);
-
-	return (void __iomem *) __fix_to_virt(fixmap_idx);
-}
-
-static void ghes_unmap(void __iomem *vaddr, enum fixed_addresses fixmap_idx)
-{
-	int _idx = virt_to_fix((unsigned long)vaddr);
-
-	WARN_ON_ONCE(fixmap_idx != _idx);
-	clear_fixmap(fixmap_idx);
-}
-
 int ghes_estatus_pool_init(unsigned int num_ghes)
 {
 	unsigned long addr, len;
@@ -193,21 +173,6 @@ static void unmap_gen_v2(struct ghes *ghes)
 	apei_unmap_generic_address(&ghes->generic_v2->read_ack_register);
 }
 
-static void ghes_ack_error(struct acpi_hest_generic_v2 *gv2)
-{
-	int rc;
-	u64 val = 0;
-
-	rc = apei_read(&val, &gv2->read_ack_register);
-	if (rc)
-		return;
-
-	val &= gv2->read_ack_preserve << gv2->read_ack_register.bit_offset;
-	val |= gv2->read_ack_write    << gv2->read_ack_register.bit_offset;
-
-	apei_write(val, &gv2->read_ack_register);
-}
-
 struct ghes *ghes_new(struct acpi_hest_generic *generic)
 {
 	struct ghes *ghes;
@@ -280,137 +245,6 @@ static inline int ghes_severity(int severity)
 	}
 }
 
-static void ghes_copy_tofrom_phys(void *buffer, u64 paddr, u32 len,
-				  int from_phys,
-				  enum fixed_addresses fixmap_idx)
-{
-	void __iomem *vaddr;
-	u64 offset;
-	u32 trunk;
-
-	while (len > 0) {
-		offset = paddr - (paddr & PAGE_MASK);
-		vaddr = ghes_map(PHYS_PFN(paddr), fixmap_idx);
-		trunk = PAGE_SIZE - offset;
-		trunk = min(trunk, len);
-		if (from_phys)
-			memcpy_fromio(buffer, vaddr + offset, trunk);
-		else
-			memcpy_toio(vaddr + offset, buffer, trunk);
-		len -= trunk;
-		paddr += trunk;
-		buffer += trunk;
-		ghes_unmap(vaddr, fixmap_idx);
-	}
-}
-
-/* Check the top-level record header has an appropriate size. */
-int __ghes_check_estatus(struct ghes *ghes,
-			 struct acpi_hest_generic_status *estatus)
-{
-	u32 len = cper_estatus_len(estatus);
-	u32 max_len = min(ghes->generic->error_block_length,
-			  ghes->estatus_length);
-
-	if (len < sizeof(*estatus)) {
-		pr_warn_ratelimited(FW_WARN GHES_PFX "Truncated error status block!\n");
-		return -EIO;
-	}
-
-	if (!len || len > max_len) {
-		pr_warn_ratelimited(FW_WARN GHES_PFX "Invalid error status block length!\n");
-		return -EIO;
-	}
-
-	if (cper_estatus_check_header(estatus)) {
-		pr_warn_ratelimited(FW_WARN GHES_PFX "Invalid CPER header!\n");
-		return -EIO;
-	}
-
-	return 0;
-}
-
-/* Read the CPER block, returning its address, and header in estatus. */
-int __ghes_peek_estatus(struct ghes *ghes,
-			struct acpi_hest_generic_status *estatus,
-			u64 *buf_paddr, enum fixed_addresses fixmap_idx)
-{
-	struct acpi_hest_generic *g = ghes->generic;
-	int rc;
-
-	rc = apei_read(buf_paddr, &g->error_status_address);
-	if (rc) {
-		*buf_paddr = 0;
-		pr_warn_ratelimited(FW_WARN GHES_PFX
-				    "Failed to read error status block address for hardware error source: %d.\n",
-				   g->header.source_id);
-		return -EIO;
-	}
-	if (!*buf_paddr)
-		return -ENOENT;
-
-	ghes_copy_tofrom_phys(estatus, *buf_paddr, sizeof(*estatus), 1,
-			      fixmap_idx);
-	if (!estatus->block_status) {
-		*buf_paddr = 0;
-		return -ENOENT;
-	}
-
-	return 0;
-}
-
-int __ghes_read_estatus(struct acpi_hest_generic_status *estatus,
-			u64 buf_paddr, enum fixed_addresses fixmap_idx,
-			size_t buf_len)
-{
-	ghes_copy_tofrom_phys(estatus, buf_paddr, buf_len, 1, fixmap_idx);
-	if (cper_estatus_check(estatus)) {
-		pr_warn_ratelimited(FW_WARN GHES_PFX
-				    "Failed to read error status block!\n");
-		return -EIO;
-	}
-
-	return 0;
-}
-
-int ghes_read_estatus(struct ghes *ghes,
-		      struct acpi_hest_generic_status *estatus,
-		      u64 *buf_paddr, enum fixed_addresses fixmap_idx)
-{
-	int rc;
-
-	rc = __ghes_peek_estatus(ghes, estatus, buf_paddr, fixmap_idx);
-	if (rc)
-		return rc;
-
-	rc = __ghes_check_estatus(ghes, estatus);
-	if (rc)
-		return rc;
-
-	return __ghes_read_estatus(estatus, *buf_paddr, fixmap_idx,
-				   cper_estatus_len(estatus));
-}
-
-void ghes_clear_estatus(struct ghes *ghes,
-			struct acpi_hest_generic_status *estatus,
-			u64 buf_paddr, enum fixed_addresses fixmap_idx)
-{
-	estatus->block_status = 0;
-
-	if (!buf_paddr)
-		return;
-
-	ghes_copy_tofrom_phys(estatus, buf_paddr,
-			      sizeof(estatus->block_status), 0,
-			      fixmap_idx);
-
-	/*
-	 * GHESv2 type HEST entries introduce support for error acknowledgment,
-	 * so only acknowledge the error if this support is present.
-	 */
-	if (is_hest_type_generic_v2(ghes))
-		ghes_ack_error(ghes->generic_v2);
-}
 
 /**
  * struct ghes_task_work - for synchronous RAS event
diff --git a/drivers/acpi/apei/ghes_cper.c b/drivers/acpi/apei/ghes_cper.c
new file mode 100644
index 000000000000..0c3f52b2d7f1
--- /dev/null
+++ b/drivers/acpi/apei/ghes_cper.c
@@ -0,0 +1,210 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Shared GHES helpers for firmware-first CPER error handling.
+ *
+ * This file holds the GHES helper code that is shared by the in-tree GHES
+ * driver and by other firmware-first error sources that reuse the same CPER
+ * handling flow.
+ *
+ * Derived from the ACPI APEI GHES driver.
+ *
+ * Copyright 2010,2011 Intel Corp.
+ *   Author: Huang Ying <ying.huang@intel.com>
+ */
+
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/ratelimit.h>
+#include <linux/slab.h>
+
+#include <acpi/apei.h>
+#include <acpi/acpi_io.h>
+#include <acpi/ghes_cper.h>
+
+#include <asm/fixmap.h>
+#include <asm/tlbflush.h>
+
+#include "apei-internal.h"
+
+static void __iomem *ghes_map(u64 pfn, enum fixed_addresses fixmap_idx)
+{
+	phys_addr_t paddr;
+	pgprot_t prot;
+
+	paddr = PFN_PHYS(pfn);
+	prot = arch_apei_get_mem_attribute(paddr);
+	__set_fixmap(fixmap_idx, paddr, prot);
+
+	return (void __iomem *) __fix_to_virt(fixmap_idx);
+}
+
+static void ghes_unmap(void __iomem *vaddr, enum fixed_addresses fixmap_idx)
+{
+	int _idx = virt_to_fix((unsigned long)vaddr);
+
+	WARN_ON_ONCE(fixmap_idx != _idx);
+	clear_fixmap(fixmap_idx);
+}
+
+static void ghes_ack_error(struct acpi_hest_generic_v2 *gv2)
+{
+	int rc;
+	u64 val = 0;
+
+	rc = apei_read(&val, &gv2->read_ack_register);
+	if (rc)
+		return;
+
+	val &= gv2->read_ack_preserve;
+	val |= gv2->read_ack_write;
+
+	apei_write(val, &gv2->read_ack_register);
+}
+
+static void ghes_copy_tofrom_phys(void *buffer, u64 paddr, u32 len,
+				  int from_phys,
+				  enum fixed_addresses fixmap_idx)
+{
+	void __iomem *vaddr;
+	u64 offset;
+	u32 trunk;
+
+	while (len > 0) {
+		offset = paddr - (paddr & PAGE_MASK);
+		vaddr = ghes_map(PHYS_PFN(paddr), fixmap_idx);
+		trunk = PAGE_SIZE - offset;
+		trunk = min(trunk, len);
+		if (from_phys)
+			memcpy_fromio(buffer, vaddr + offset, trunk);
+		else
+			memcpy_toio(vaddr + offset, buffer, trunk);
+		len -= trunk;
+		paddr += trunk;
+		buffer += trunk;
+		ghes_unmap(vaddr, fixmap_idx);
+	}
+}
+
+/* Check the top-level record header has an appropriate size. */
+int __ghes_check_estatus(struct ghes *ghes,
+			 struct acpi_hest_generic_status *estatus)
+{
+	u32 len = cper_estatus_len(estatus);
+	u32 max_len = min(ghes->generic->error_block_length,
+			  ghes->estatus_length);
+
+	if (len < sizeof(*estatus)) {
+		pr_warn_ratelimited(FW_WARN GHES_PFX "Truncated error status block!\n");
+		return -EIO;
+	}
+
+	if (len > max_len) {
+		pr_warn_ratelimited(FW_WARN GHES_PFX "Invalid error status block length!\n");
+		return -EIO;
+	}
+
+	if (cper_estatus_check_header(estatus)) {
+		pr_warn_ratelimited(FW_WARN GHES_PFX "Invalid CPER header!\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+/* Read the CPER block, returning its address, and header in estatus. */
+int __ghes_peek_estatus(struct ghes *ghes,
+			struct acpi_hest_generic_status *estatus,
+			u64 *buf_paddr, enum fixed_addresses fixmap_idx)
+{
+	struct acpi_hest_generic *g = ghes->generic;
+	int rc;
+
+	rc = apei_read(buf_paddr, &g->error_status_address);
+	if (rc) {
+		*buf_paddr = 0;
+		pr_warn_ratelimited(FW_WARN GHES_PFX
+				    "Failed to read error status block address for hardware error source: %d.\n",
+				    g->header.source_id);
+		return -EIO;
+	}
+	if (!*buf_paddr)
+		return -ENOENT;
+
+	ghes_copy_tofrom_phys(estatus, *buf_paddr, sizeof(*estatus), 1,
+			      fixmap_idx);
+	if (!estatus->block_status) {
+		*buf_paddr = 0;
+		return -ENOENT;
+	}
+
+	return 0;
+}
+
+int __ghes_read_estatus(struct acpi_hest_generic_status *estatus,
+			u64 buf_paddr, enum fixed_addresses fixmap_idx,
+			size_t buf_len)
+{
+	u32 len;
+
+	ghes_copy_tofrom_phys(estatus, buf_paddr, buf_len, 1, fixmap_idx);
+
+	len = cper_estatus_len(estatus);
+	if (len < sizeof(*estatus)) {
+		pr_warn_ratelimited(FW_WARN GHES_PFX "Truncated error status block!\n");
+		return -EIO;
+	}
+
+	if (len > buf_len) {
+		pr_warn_ratelimited(FW_WARN GHES_PFX "Invalid error status block length!\n");
+		return -EIO;
+	}
+
+	if (cper_estatus_check(estatus)) {
+		pr_warn_ratelimited(FW_WARN GHES_PFX
+				    "Failed to read error status block!\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+int ghes_read_estatus(struct ghes *ghes,
+		      struct acpi_hest_generic_status *estatus,
+		      u64 *buf_paddr, enum fixed_addresses fixmap_idx)
+{
+	int rc;
+
+	rc = __ghes_peek_estatus(ghes, estatus, buf_paddr, fixmap_idx);
+	if (rc)
+		return rc;
+
+	rc = __ghes_check_estatus(ghes, estatus);
+	if (rc)
+		return rc;
+
+	return __ghes_read_estatus(estatus, *buf_paddr, fixmap_idx,
+				   cper_estatus_len(estatus));
+}
+
+void ghes_clear_estatus(struct ghes *ghes,
+			struct acpi_hest_generic_status *estatus,
+			u64 buf_paddr, enum fixed_addresses fixmap_idx)
+{
+	estatus->block_status = 0;
+
+	if (!buf_paddr)
+		return;
+
+	ghes_copy_tofrom_phys(estatus, buf_paddr,
+			      sizeof(estatus->block_status), 0,
+			      fixmap_idx);
+
+	/*
+	 * GHESv2 type HEST entries introduce support for error acknowledgment,
+	 * so only acknowledge the error if this support is present.
+	 */
+	if (is_hest_type_generic_v2(ghes))
+		ghes_ack_error(ghes->generic_v2);
+}

-- 
2.43.0

[PATCH v7 03/10] ACPI: APEI: GHES: move GHESv2 ack and alloc helpers

[Ahmed Tiba]

Move the GHESv2 acknowledgment and error-source allocation helpers from
ghes.c into ghes_cper.c. This is a mechanical refactor that keeps the
logic unchanged while making the helpers reusable.

Reviewed-by: Jonathan Cameron <jic23@kernel.org>
Signed-off-by: Ahmed Tiba <ahmed.tiba@arm.com>
---
 drivers/acpi/apei/ghes.c      | 65 -------------------------------------------
 drivers/acpi/apei/ghes_cper.c | 65 +++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 65 insertions(+), 65 deletions(-)

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index f74fd5de34cc..bda535224422 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -163,71 +163,6 @@ void ghes_estatus_pool_region_free(unsigned long addr, u32 size)
 }
 EXPORT_SYMBOL_GPL(ghes_estatus_pool_region_free);
 
-static int map_gen_v2(struct ghes *ghes)
-{
-	return apei_map_generic_address(&ghes->generic_v2->read_ack_register);
-}
-
-static void unmap_gen_v2(struct ghes *ghes)
-{
-	apei_unmap_generic_address(&ghes->generic_v2->read_ack_register);
-}
-
-struct ghes *ghes_new(struct acpi_hest_generic *generic)
-{
-	struct ghes *ghes;
-	unsigned int error_block_length;
-	int rc;
-
-	ghes = kzalloc_obj(*ghes);
-	if (!ghes)
-		return ERR_PTR(-ENOMEM);
-
-	ghes->generic = generic;
-	if (is_hest_type_generic_v2(ghes)) {
-		rc = map_gen_v2(ghes);
-		if (rc)
-			goto err_free;
-	}
-
-	rc = apei_map_generic_address(&generic->error_status_address);
-	if (rc)
-		goto err_unmap_read_ack_addr;
-	error_block_length = generic->error_block_length;
-	if (error_block_length > GHES_ESTATUS_MAX_SIZE) {
-		pr_warn(FW_WARN GHES_PFX
-			"Error status block length is too long: %u for "
-			"generic hardware error source: %d.\n",
-			error_block_length, generic->header.source_id);
-		error_block_length = GHES_ESTATUS_MAX_SIZE;
-	}
-	ghes->estatus = kmalloc(error_block_length, GFP_KERNEL);
-	ghes->estatus_length = error_block_length;
-	if (!ghes->estatus) {
-		rc = -ENOMEM;
-		goto err_unmap_status_addr;
-	}
-
-	return ghes;
-
-err_unmap_status_addr:
-	apei_unmap_generic_address(&generic->error_status_address);
-err_unmap_read_ack_addr:
-	if (is_hest_type_generic_v2(ghes))
-		unmap_gen_v2(ghes);
-err_free:
-	kfree(ghes);
-	return ERR_PTR(rc);
-}
-
-void ghes_fini(struct ghes *ghes)
-{
-	kfree(ghes->estatus);
-	apei_unmap_generic_address(&ghes->generic->error_status_address);
-	if (is_hest_type_generic_v2(ghes))
-		unmap_gen_v2(ghes);
-}
-
 static inline int ghes_severity(int severity)
 {
 	switch (severity) {
diff --git a/drivers/acpi/apei/ghes_cper.c b/drivers/acpi/apei/ghes_cper.c
index 0c3f52b2d7f1..9c668725e08a 100644
--- a/drivers/acpi/apei/ghes_cper.c
+++ b/drivers/acpi/apei/ghes_cper.c
@@ -63,6 +63,71 @@ static void ghes_ack_error(struct acpi_hest_generic_v2 *gv2)
 	apei_write(val, &gv2->read_ack_register);
 }
 
+static int map_gen_v2(struct ghes *ghes)
+{
+	return apei_map_generic_address(&ghes->generic_v2->read_ack_register);
+}
+
+static void unmap_gen_v2(struct ghes *ghes)
+{
+	apei_unmap_generic_address(&ghes->generic_v2->read_ack_register);
+}
+
+struct ghes *ghes_new(struct acpi_hest_generic *generic)
+{
+	struct ghes *ghes;
+	unsigned int error_block_length;
+	int rc;
+
+	ghes = kzalloc_obj(*ghes);
+	if (!ghes)
+		return ERR_PTR(-ENOMEM);
+
+	ghes->generic = generic;
+	if (is_hest_type_generic_v2(ghes)) {
+		rc = map_gen_v2(ghes);
+		if (rc)
+			goto err_free;
+	}
+
+	rc = apei_map_generic_address(&generic->error_status_address);
+	if (rc)
+		goto err_unmap_read_ack_addr;
+	error_block_length = generic->error_block_length;
+	if (error_block_length > GHES_ESTATUS_MAX_SIZE) {
+		pr_warn(FW_WARN GHES_PFX
+			"Error status block length is too long: %u for "
+			"generic hardware error source: %d.\n",
+			error_block_length, generic->header.source_id);
+		error_block_length = GHES_ESTATUS_MAX_SIZE;
+	}
+	ghes->estatus = kmalloc(error_block_length, GFP_KERNEL);
+	ghes->estatus_length = error_block_length;
+	if (!ghes->estatus) {
+		rc = -ENOMEM;
+		goto err_unmap_status_addr;
+	}
+
+	return ghes;
+
+err_unmap_status_addr:
+	apei_unmap_generic_address(&generic->error_status_address);
+err_unmap_read_ack_addr:
+	if (is_hest_type_generic_v2(ghes))
+		unmap_gen_v2(ghes);
+err_free:
+	kfree(ghes);
+	return ERR_PTR(rc);
+}
+
+void ghes_fini(struct ghes *ghes)
+{
+	kfree(ghes->estatus);
+	apei_unmap_generic_address(&ghes->generic->error_status_address);
+	if (is_hest_type_generic_v2(ghes))
+		unmap_gen_v2(ghes);
+}
+
 static void ghes_copy_tofrom_phys(void *buffer, u64 paddr, u32 len,
 				  int from_phys,
 				  enum fixed_addresses fixmap_idx)

-- 
2.43.0

[PATCH v7 04/10] ACPI: APEI: GHES: move estatus cache helpers

[Ahmed Tiba]

Relocate the estatus cache allocation and lookup helpers from ghes.c into
ghes_cper.c. This code move keeps the logic intact while making the cache
implementation available to forthcoming users.

Fix ghes_estatus_cache_add() by freeing new_cache and decrementing
ghes_estatus_cache_alloced. This avoids leaks and counter exhaustion
that can disable estatus deduplication.

Reviewed-by: Jonathan Cameron <jic23@kernel.org>
Signed-off-by: Ahmed Tiba <ahmed.tiba@arm.com>
---
 drivers/acpi/apei/ghes.c      | 138 +---------------------------------------
 drivers/acpi/apei/ghes_cper.c | 143 ++++++++++++++++++++++++++++++++++++++++++
 include/acpi/ghes_cper.h      |   5 ++
 3 files changed, 149 insertions(+), 137 deletions(-)

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index bda535224422..e9cb576eefcf 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -113,10 +113,7 @@ static DEFINE_MUTEX(ghes_devs_mutex);
  */
 static DEFINE_SPINLOCK(ghes_notify_lock_irq);
 
-static struct gen_pool *ghes_estatus_pool;
-
-static struct ghes_estatus_cache __rcu *ghes_estatus_caches[GHES_ESTATUS_CACHES_SIZE];
-static atomic_t ghes_estatus_cache_alloced;
+struct gen_pool *ghes_estatus_pool;
 
 int ghes_estatus_pool_init(unsigned int num_ghes)
 {
@@ -733,139 +730,6 @@ static int ghes_print_estatus(const char *pfx,
 	return 0;
 }
 
-/*
- * GHES error status reporting throttle, to report more kinds of
- * errors, instead of just most frequently occurred errors.
- */
-static int ghes_estatus_cached(struct acpi_hest_generic_status *estatus)
-{
-	u32 len;
-	int i, cached = 0;
-	unsigned long long now;
-	struct ghes_estatus_cache *cache;
-	struct acpi_hest_generic_status *cache_estatus;
-
-	len = cper_estatus_len(estatus);
-	rcu_read_lock();
-	for (i = 0; i < GHES_ESTATUS_CACHES_SIZE; i++) {
-		cache = rcu_dereference(ghes_estatus_caches[i]);
-		if (cache == NULL)
-			continue;
-		if (len != cache->estatus_len)
-			continue;
-		cache_estatus = GHES_ESTATUS_FROM_CACHE(cache);
-		if (memcmp(estatus, cache_estatus, len))
-			continue;
-		atomic_inc(&cache->count);
-		now = sched_clock();
-		if (now - cache->time_in < GHES_ESTATUS_IN_CACHE_MAX_NSEC)
-			cached = 1;
-		break;
-	}
-	rcu_read_unlock();
-	return cached;
-}
-
-static struct ghes_estatus_cache *ghes_estatus_cache_alloc(
-	struct acpi_hest_generic *generic,
-	struct acpi_hest_generic_status *estatus)
-{
-	int alloced;
-	u32 len, cache_len;
-	struct ghes_estatus_cache *cache;
-	struct acpi_hest_generic_status *cache_estatus;
-
-	alloced = atomic_add_return(1, &ghes_estatus_cache_alloced);
-	if (alloced > GHES_ESTATUS_CACHE_ALLOCED_MAX) {
-		atomic_dec(&ghes_estatus_cache_alloced);
-		return NULL;
-	}
-	len = cper_estatus_len(estatus);
-	cache_len = GHES_ESTATUS_CACHE_LEN(len);
-	cache = (void *)gen_pool_alloc(ghes_estatus_pool, cache_len);
-	if (!cache) {
-		atomic_dec(&ghes_estatus_cache_alloced);
-		return NULL;
-	}
-	cache_estatus = GHES_ESTATUS_FROM_CACHE(cache);
-	memcpy(cache_estatus, estatus, len);
-	cache->estatus_len = len;
-	atomic_set(&cache->count, 0);
-	cache->generic = generic;
-	cache->time_in = sched_clock();
-	return cache;
-}
-
-static void ghes_estatus_cache_rcu_free(struct rcu_head *head)
-{
-	struct ghes_estatus_cache *cache;
-	u32 len;
-
-	cache = container_of(head, struct ghes_estatus_cache, rcu);
-	len = cper_estatus_len(GHES_ESTATUS_FROM_CACHE(cache));
-	len = GHES_ESTATUS_CACHE_LEN(len);
-	gen_pool_free(ghes_estatus_pool, (unsigned long)cache, len);
-	atomic_dec(&ghes_estatus_cache_alloced);
-}
-
-static void
-ghes_estatus_cache_add(struct acpi_hest_generic *generic,
-		       struct acpi_hest_generic_status *estatus)
-{
-	unsigned long long now, duration, period, max_period = 0;
-	struct ghes_estatus_cache *cache, *new_cache;
-	struct ghes_estatus_cache __rcu *victim;
-	int i, slot = -1, count;
-
-	new_cache = ghes_estatus_cache_alloc(generic, estatus);
-	if (!new_cache)
-		return;
-
-	rcu_read_lock();
-	now = sched_clock();
-	for (i = 0; i < GHES_ESTATUS_CACHES_SIZE; i++) {
-		cache = rcu_dereference(ghes_estatus_caches[i]);
-		if (cache == NULL) {
-			slot = i;
-			break;
-		}
-		duration = now - cache->time_in;
-		if (duration >= GHES_ESTATUS_IN_CACHE_MAX_NSEC) {
-			slot = i;
-			break;
-		}
-		count = atomic_read(&cache->count);
-		period = duration;
-		do_div(period, (count + 1));
-		if (period > max_period) {
-			max_period = period;
-			slot = i;
-		}
-	}
-	rcu_read_unlock();
-
-	if (slot != -1) {
-		/*
-		 * Use release semantics to ensure that ghes_estatus_cached()
-		 * running on another CPU will see the updated cache fields if
-		 * it can see the new value of the pointer.
-		 */
-		victim = xchg_release(&ghes_estatus_caches[slot],
-				      RCU_INITIALIZER(new_cache));
-
-		/*
-		 * At this point, victim may point to a cached item different
-		 * from the one based on which we selected the slot. Instead of
-		 * going to the loop again to pick another slot, let's just
-		 * drop the other item anyway: this may cause a false cache
-		 * miss later on, but that won't cause any problems.
-		 */
-		if (victim)
-			call_rcu(&unrcu_pointer(victim)->rcu,
-				 ghes_estatus_cache_rcu_free);
-	}
-}
-
 static void __ghes_panic(struct ghes *ghes,
 			 struct acpi_hest_generic_status *estatus,
 			 u64 buf_paddr, enum fixed_addresses fixmap_idx)
diff --git a/drivers/acpi/apei/ghes_cper.c b/drivers/acpi/apei/ghes_cper.c
index 9c668725e08a..44b644584703 100644
--- a/drivers/acpi/apei/ghes_cper.c
+++ b/drivers/acpi/apei/ghes_cper.c
@@ -13,10 +13,14 @@
  */
 
 #include <linux/err.h>
+#include <linux/genalloc.h>
 #include <linux/io.h>
 #include <linux/kernel.h>
+#include <linux/math64.h>
 #include <linux/mm.h>
 #include <linux/ratelimit.h>
+#include <linux/rcupdate.h>
+#include <linux/sched/clock.h>
 #include <linux/slab.h>
 
 #include <acpi/apei.h>
@@ -28,6 +32,9 @@
 
 #include "apei-internal.h"
 
+static struct ghes_estatus_cache __rcu *ghes_estatus_caches[GHES_ESTATUS_CACHES_SIZE];
+static atomic_t ghes_estatus_cache_alloced;
+
 static void __iomem *ghes_map(u64 pfn, enum fixed_addresses fixmap_idx)
 {
 	phys_addr_t paddr;
@@ -273,3 +280,139 @@ void ghes_clear_estatus(struct ghes *ghes,
 	if (is_hest_type_generic_v2(ghes))
 		ghes_ack_error(ghes->generic_v2);
 }
+
+/*
+ * GHES error status reporting throttle, to report more kinds of
+ * errors, instead of just most frequently occurred errors.
+ */
+int ghes_estatus_cached(struct acpi_hest_generic_status *estatus)
+{
+	u32 len;
+	int i, cached = 0;
+	unsigned long long now;
+	struct ghes_estatus_cache *cache;
+	struct acpi_hest_generic_status *cache_estatus;
+
+	len = cper_estatus_len(estatus);
+	rcu_read_lock();
+	for (i = 0; i < GHES_ESTATUS_CACHES_SIZE; i++) {
+		cache = rcu_dereference(ghes_estatus_caches[i]);
+		if (cache == NULL)
+			continue;
+		if (len != cache->estatus_len)
+			continue;
+		cache_estatus = GHES_ESTATUS_FROM_CACHE(cache);
+		if (memcmp(estatus, cache_estatus, len))
+			continue;
+		atomic_inc(&cache->count);
+		now = sched_clock();
+		if (now - cache->time_in < GHES_ESTATUS_IN_CACHE_MAX_NSEC)
+			cached = 1;
+		break;
+	}
+	rcu_read_unlock();
+	return cached;
+}
+
+static struct ghes_estatus_cache *ghes_estatus_cache_alloc(
+	struct acpi_hest_generic *generic,
+	struct acpi_hest_generic_status *estatus)
+{
+	int alloced;
+	u32 len, cache_len;
+	struct ghes_estatus_cache *cache;
+	struct acpi_hest_generic_status *cache_estatus;
+
+	alloced = atomic_add_return(1, &ghes_estatus_cache_alloced);
+	if (alloced > GHES_ESTATUS_CACHE_ALLOCED_MAX) {
+		atomic_dec(&ghes_estatus_cache_alloced);
+		return NULL;
+	}
+	len = cper_estatus_len(estatus);
+	cache_len = GHES_ESTATUS_CACHE_LEN(len);
+	cache = (void *)gen_pool_alloc(ghes_estatus_pool, cache_len);
+	if (cache == NULL) {
+		atomic_dec(&ghes_estatus_cache_alloced);
+		return NULL;
+	}
+	cache_estatus = GHES_ESTATUS_FROM_CACHE(cache);
+	memcpy(cache_estatus, estatus, len);
+	cache->estatus_len = len;
+	atomic_set(&cache->count, 0);
+	cache->generic = generic;
+	cache->time_in = sched_clock();
+	return cache;
+}
+
+static void ghes_estatus_cache_rcu_free(struct rcu_head *head)
+{
+	struct ghes_estatus_cache *cache;
+	u32 len;
+
+	cache = container_of(head, struct ghes_estatus_cache, rcu);
+	len = cper_estatus_len(GHES_ESTATUS_FROM_CACHE(cache));
+	len = GHES_ESTATUS_CACHE_LEN(len);
+	gen_pool_free(ghes_estatus_pool, (unsigned long)cache, len);
+	atomic_dec(&ghes_estatus_cache_alloced);
+}
+
+void ghes_estatus_cache_add(struct acpi_hest_generic *generic,
+			    struct acpi_hest_generic_status *estatus)
+{
+	unsigned long long now, duration, period, max_period = 0;
+	struct ghes_estatus_cache *cache, *new_cache;
+	struct ghes_estatus_cache __rcu *victim;
+	int i, slot = -1, count;
+
+	new_cache = ghes_estatus_cache_alloc(generic, estatus);
+	if (!new_cache)
+		return;
+
+	rcu_read_lock();
+	now = sched_clock();
+	for (i = 0; i < GHES_ESTATUS_CACHES_SIZE; i++) {
+		cache = rcu_dereference(ghes_estatus_caches[i]);
+		if (cache == NULL) {
+			slot = i;
+			break;
+		}
+		duration = now - cache->time_in;
+		if (duration >= GHES_ESTATUS_IN_CACHE_MAX_NSEC) {
+			slot = i;
+			break;
+		}
+		count = atomic_read(&cache->count);
+		period = duration;
+		do_div(period, (count + 1));
+		if (period > max_period) {
+			max_period = period;
+			slot = i;
+		}
+	}
+	rcu_read_unlock();
+
+	if (slot != -1) {
+		/*
+		 * Use release semantics to ensure that ghes_estatus_cached()
+		 * running on another CPU will see the updated cache fields if
+		 * it can see the new value of the pointer.
+		 */
+		victim = xchg_release(&ghes_estatus_caches[slot],
+				      RCU_INITIALIZER(new_cache));
+
+		/*
+		 * At this point, victim may point to a cached item different
+		 * from the one based on which we selected the slot. Instead of
+		 * going to the loop again to pick another slot, let's just
+		 * drop the other item anyway: this may cause a false cache
+		 * miss later on, but that won't cause any problems.
+		 */
+		if (victim)
+			call_rcu(&unrcu_pointer(victim)->rcu,
+				 ghes_estatus_cache_rcu_free);
+	} else {
+		gen_pool_free(ghes_estatus_pool, (unsigned long)new_cache,
+			     GHES_ESTATUS_CACHE_LEN(new_cache->estatus_len));
+		atomic_dec(&ghes_estatus_cache_alloced);
+	}
+}
diff --git a/include/acpi/ghes_cper.h b/include/acpi/ghes_cper.h
index 4649e3140888..15305c8be9a7 100644
--- a/include/acpi/ghes_cper.h
+++ b/include/acpi/ghes_cper.h
@@ -55,6 +55,8 @@
 	((struct acpi_hest_generic_data *)                              \
 	((struct ghes_vendor_record_entry *)(vendor_entry) + 1))
 
+extern struct gen_pool *ghes_estatus_pool;
+
 static inline bool is_hest_type_generic_v2(struct ghes *ghes)
 {
 	return ghes->generic->header.type == ACPI_HEST_TYPE_GENERIC_ERROR_V2;
@@ -99,5 +101,8 @@ int __ghes_read_estatus(struct acpi_hest_generic_status *estatus,
 			u64 buf_paddr, enum fixed_addresses fixmap_idx,
 			size_t buf_len);
 #endif
+int ghes_estatus_cached(struct acpi_hest_generic_status *estatus);
+void ghes_estatus_cache_add(struct acpi_hest_generic *generic,
+			    struct acpi_hest_generic_status *estatus);
 
 #endif /* ACPI_APEI_GHES_CPER_H */

-- 
2.43.0

[PATCH v7 05/10] ACPI: APEI: GHES: move vendor record helpers

[Ahmed Tiba]

Shift the vendor record workqueue helpers into ghes_cper.c so both GHES
and future DT-based providers can use the same implementation. The change
is mechanical and keeps the notifier behavior identical.

Signed-off-by: Ahmed Tiba <ahmed.tiba@arm.com>
---
 drivers/acpi/apei/ghes.c      | 68 ------------------------------------------
 drivers/acpi/apei/ghes_cper.c | 69 +++++++++++++++++++++++++++++++++++++++++++
 include/acpi/ghes_cper.h      |  2 ++
 3 files changed, 71 insertions(+), 68 deletions(-)

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index e9cb576eefcf..07e4001ea8d7 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -383,74 +383,6 @@ static void ghes_handle_aer(struct acpi_hest_generic_data *gdata)
 #endif
 }
 
-static BLOCKING_NOTIFIER_HEAD(vendor_record_notify_list);
-
-int ghes_register_vendor_record_notifier(struct notifier_block *nb)
-{
-	return blocking_notifier_chain_register(&vendor_record_notify_list, nb);
-}
-EXPORT_SYMBOL_GPL(ghes_register_vendor_record_notifier);
-
-void ghes_unregister_vendor_record_notifier(struct notifier_block *nb)
-{
-	blocking_notifier_chain_unregister(&vendor_record_notify_list, nb);
-}
-EXPORT_SYMBOL_GPL(ghes_unregister_vendor_record_notifier);
-
-static void ghes_vendor_record_notifier_destroy(void *nb)
-{
-	ghes_unregister_vendor_record_notifier(nb);
-}
-
-int devm_ghes_register_vendor_record_notifier(struct device *dev,
-					      struct notifier_block *nb)
-{
-	int ret;
-
-	ret = ghes_register_vendor_record_notifier(nb);
-	if (ret)
-		return ret;
-
-	return devm_add_action_or_reset(dev, ghes_vendor_record_notifier_destroy, nb);
-}
-EXPORT_SYMBOL_GPL(devm_ghes_register_vendor_record_notifier);
-
-static void ghes_vendor_record_work_func(struct work_struct *work)
-{
-	struct ghes_vendor_record_entry *entry;
-	struct acpi_hest_generic_data *gdata;
-	u32 len;
-
-	entry = container_of(work, struct ghes_vendor_record_entry, work);
-	gdata = GHES_GDATA_FROM_VENDOR_ENTRY(entry);
-
-	blocking_notifier_call_chain(&vendor_record_notify_list,
-				     entry->error_severity, gdata);
-
-	len = GHES_VENDOR_ENTRY_LEN(acpi_hest_get_record_size(gdata));
-	gen_pool_free(ghes_estatus_pool, (unsigned long)entry, len);
-}
-
-static void ghes_defer_non_standard_event(struct acpi_hest_generic_data *gdata,
-					  int sev)
-{
-	struct acpi_hest_generic_data *copied_gdata;
-	struct ghes_vendor_record_entry *entry;
-	u32 len;
-
-	len = GHES_VENDOR_ENTRY_LEN(acpi_hest_get_record_size(gdata));
-	entry = (void *)gen_pool_alloc(ghes_estatus_pool, len);
-	if (!entry)
-		return;
-
-	copied_gdata = GHES_GDATA_FROM_VENDOR_ENTRY(entry);
-	memcpy(copied_gdata, gdata, acpi_hest_get_record_size(gdata));
-	entry->error_severity = sev;
-
-	INIT_WORK(&entry->work, ghes_vendor_record_work_func);
-	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,
diff --git a/drivers/acpi/apei/ghes_cper.c b/drivers/acpi/apei/ghes_cper.c
index 44b644584703..7e4a66b788b8 100644
--- a/drivers/acpi/apei/ghes_cper.c
+++ b/drivers/acpi/apei/ghes_cper.c
@@ -18,6 +18,7 @@
 #include <linux/kernel.h>
 #include <linux/math64.h>
 #include <linux/mm.h>
+#include <linux/notifier.h>
 #include <linux/ratelimit.h>
 #include <linux/rcupdate.h>
 #include <linux/sched/clock.h>
@@ -281,6 +282,74 @@ void ghes_clear_estatus(struct ghes *ghes,
 		ghes_ack_error(ghes->generic_v2);
 }
 
+static BLOCKING_NOTIFIER_HEAD(vendor_record_notify_list);
+
+int ghes_register_vendor_record_notifier(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_register(&vendor_record_notify_list, nb);
+}
+EXPORT_SYMBOL_GPL(ghes_register_vendor_record_notifier);
+
+void ghes_unregister_vendor_record_notifier(struct notifier_block *nb)
+{
+	blocking_notifier_chain_unregister(&vendor_record_notify_list, nb);
+}
+EXPORT_SYMBOL_GPL(ghes_unregister_vendor_record_notifier);
+
+static void ghes_vendor_record_notifier_destroy(void *nb)
+{
+	ghes_unregister_vendor_record_notifier(nb);
+}
+
+int devm_ghes_register_vendor_record_notifier(struct device *dev,
+					      struct notifier_block *nb)
+{
+	int ret;
+
+	ret = ghes_register_vendor_record_notifier(nb);
+	if (ret)
+		return ret;
+
+	return devm_add_action_or_reset(dev, ghes_vendor_record_notifier_destroy, nb);
+}
+EXPORT_SYMBOL_GPL(devm_ghes_register_vendor_record_notifier);
+
+static void ghes_vendor_record_work_func(struct work_struct *work)
+{
+	struct ghes_vendor_record_entry *entry;
+	struct acpi_hest_generic_data *gdata;
+	u32 len;
+
+	entry = container_of(work, struct ghes_vendor_record_entry, work);
+	gdata = GHES_GDATA_FROM_VENDOR_ENTRY(entry);
+
+	blocking_notifier_call_chain(&vendor_record_notify_list,
+				     entry->error_severity, gdata);
+
+	len = GHES_VENDOR_ENTRY_LEN(acpi_hest_get_record_size(gdata));
+	gen_pool_free(ghes_estatus_pool, (unsigned long)entry, len);
+}
+
+void ghes_defer_non_standard_event(struct acpi_hest_generic_data *gdata,
+				   int sev)
+{
+	struct acpi_hest_generic_data *copied_gdata;
+	struct ghes_vendor_record_entry *entry;
+	u32 len;
+
+	len = GHES_VENDOR_ENTRY_LEN(acpi_hest_get_record_size(gdata));
+	entry = (void *)gen_pool_alloc(ghes_estatus_pool, len);
+	if (!entry)
+		return;
+
+	copied_gdata = GHES_GDATA_FROM_VENDOR_ENTRY(entry);
+	memcpy(copied_gdata, gdata, acpi_hest_get_record_size(gdata));
+	entry->error_severity = sev;
+
+	INIT_WORK(&entry->work, ghes_vendor_record_work_func);
+	schedule_work(&entry->work);
+}
+
 /*
  * GHES error status reporting throttle, to report more kinds of
  * errors, instead of just most frequently occurred errors.
diff --git a/include/acpi/ghes_cper.h b/include/acpi/ghes_cper.h
index 15305c8be9a7..d9f9253d8de9 100644
--- a/include/acpi/ghes_cper.h
+++ b/include/acpi/ghes_cper.h
@@ -104,5 +104,7 @@ int __ghes_read_estatus(struct acpi_hest_generic_status *estatus,
 int ghes_estatus_cached(struct acpi_hest_generic_status *estatus);
 void ghes_estatus_cache_add(struct acpi_hest_generic *generic,
 			    struct acpi_hest_generic_status *estatus);
+void ghes_defer_non_standard_event(struct acpi_hest_generic_data *gdata,
+				   int sev);
 
 #endif /* ACPI_APEI_GHES_CPER_H */

-- 
2.43.0

[PATCH v7 06/10] ACPI: APEI: GHES: move CXL CPER helpers

[Ahmed Tiba]

Move the CXL CPER handling paths out of ghes.c and into ghes_cper.c so the
helpers can be reused. The code is moved as-is, with the public
prototypes updated so GHES keeps calling into the new translation unit.

While moving this code, also add CXL CPER section length checks and use
spinlock_irqsave() in CXL register/unregister paths for locking
consistency.

Reviewed-by: Jonathan Cameron <jic23@kernel.org>
Signed-off-by: Ahmed Tiba <ahmed.tiba@arm.com>
---
 drivers/acpi/apei/ghes.c      | 180 +++++++++++-------------------------------
 drivers/acpi/apei/ghes_cper.c | 135 +++++++++++++++++++++++++++++++
 include/acpi/ghes_cper.h      |  11 +++
 3 files changed, 194 insertions(+), 132 deletions(-)

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 07e4001ea8d7..2a83d326e692 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -383,138 +383,6 @@ static void ghes_handle_aer(struct acpi_hest_generic_data *gdata)
 #endif
 }
 
-/* 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;
-
-	if (cxl_cper_sec_prot_err_valid(prot_err))
-		return;
-
-	guard(spinlock_irqsave)(&cxl_cper_prot_err_work_lock);
-
-	if (!cxl_cper_prot_err_work)
-		return;
-
-	if (cxl_cper_setup_prot_err_work_data(&wd, prot_err, severity))
-		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);
-
-/* Synchronize schedule_work() with cxl_cper_work changes */
-static DEFINE_SPINLOCK(cxl_cper_work_lock);
-struct work_struct *cxl_cper_work;
-
-static void cxl_cper_post_event(enum cxl_event_type event_type,
-				struct cxl_cper_event_rec *rec)
-{
-	struct cxl_cper_work_data wd;
-
-	if (rec->hdr.length <= sizeof(rec->hdr) ||
-	    rec->hdr.length > sizeof(*rec)) {
-		pr_err(FW_WARN "CXL CPER Invalid section length (%u)\n",
-		       rec->hdr.length);
-		return;
-	}
-
-	if (!(rec->hdr.validation_bits & CPER_CXL_COMP_EVENT_LOG_VALID)) {
-		pr_err(FW_WARN "CXL CPER invalid event\n");
-		return;
-	}
-
-	guard(spinlock_irqsave)(&cxl_cper_work_lock);
-
-	if (!cxl_cper_work)
-		return;
-
-	wd.event_type = event_type;
-	memcpy(&wd.rec, rec, sizeof(wd.rec));
-
-	if (!kfifo_put(&cxl_cper_fifo, wd)) {
-		pr_err_ratelimited("CXL CPER kfifo overflow\n");
-		return;
-	}
-
-	schedule_work(cxl_cper_work);
-}
-
-int cxl_cper_register_work(struct work_struct *work)
-{
-	if (cxl_cper_work)
-		return -EINVAL;
-
-	guard(spinlock)(&cxl_cper_work_lock);
-	cxl_cper_work = work;
-	return 0;
-}
-EXPORT_SYMBOL_NS_GPL(cxl_cper_register_work, "CXL");
-
-int cxl_cper_unregister_work(struct work_struct *work)
-{
-	if (cxl_cper_work != work)
-		return -EINVAL;
-
-	guard(spinlock)(&cxl_cper_work_lock);
-	cxl_cper_work = NULL;
-	return 0;
-}
-EXPORT_SYMBOL_NS_GPL(cxl_cper_unregister_work, "CXL");
-
-int cxl_cper_kfifo_get(struct cxl_cper_work_data *wd)
-{
-	return kfifo_get(&cxl_cper_fifo, wd);
-}
-EXPORT_SYMBOL_NS_GPL(cxl_cper_kfifo_get, "CXL");
-
 static void ghes_log_hwerr(int sev, guid_t *sec_type)
 {
 	if (sev != CPER_SEV_RECOVERABLE)
@@ -549,6 +417,42 @@ static void ghes_log_hwerr(int sev, guid_t *sec_type)
 	hwerr_log_error_type(HWERR_RECOV_OTHERS);
 }
 
+static bool ghes_cxl_event_len_valid(struct acpi_hest_generic_data *gdata,
+				     struct cxl_cper_event_rec *rec)
+{
+	if (gdata->error_data_length < sizeof(*rec) ||
+	    rec->hdr.length <= sizeof(rec->hdr) ||
+	    rec->hdr.length > gdata->error_data_length ||
+	    rec->hdr.length > sizeof(*rec)) {
+		pr_err(FW_WARN "CXL CPER Invalid section length (%u)\n",
+		       rec->hdr.length);
+		return false;
+	}
+
+	return true;
+}
+
+static bool ghes_cxl_prot_err_len_valid(struct acpi_hest_generic_data *gdata,
+					struct cxl_cper_sec_prot_err *prot_err)
+{
+	if (gdata->error_data_length < sizeof(*prot_err) +
+	    sizeof(struct cxl_ras_capability_regs)) {
+		pr_err(FW_WARN "CXL CPER Invalid protocol error length (%u)\n",
+		       gdata->error_data_length);
+		return false;
+	}
+
+	if (prot_err->dvsec_len >
+	    gdata->error_data_length - sizeof(*prot_err) -
+	    sizeof(struct cxl_ras_capability_regs)) {
+		pr_err(FW_WARN "CXL CPER invalid DVSEC length (%u)\n",
+		       prot_err->dvsec_len);
+		return false;
+	}
+
+	return true;
+}
+
 static void ghes_do_proc(struct ghes *ghes,
 			 const struct acpi_hest_generic_status *estatus)
 {
@@ -585,18 +489,30 @@ static void ghes_do_proc(struct ghes *ghes,
 		} else if (guid_equal(sec_type, &CPER_SEC_CXL_PROT_ERR)) {
 			struct cxl_cper_sec_prot_err *prot_err = acpi_hest_get_payload(gdata);
 
+			if (!ghes_cxl_prot_err_len_valid(gdata, prot_err))
+				continue;
+
 			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);
 
+			if (!ghes_cxl_event_len_valid(gdata, rec))
+				continue;
+
 			cxl_cper_post_event(CXL_CPER_EVENT_GEN_MEDIA, rec);
 		} else if (guid_equal(sec_type, &CPER_SEC_CXL_DRAM_GUID)) {
 			struct cxl_cper_event_rec *rec = acpi_hest_get_payload(gdata);
 
+			if (!ghes_cxl_event_len_valid(gdata, rec))
+				continue;
+
 			cxl_cper_post_event(CXL_CPER_EVENT_DRAM, rec);
 		} else if (guid_equal(sec_type, &CPER_SEC_CXL_MEM_MODULE_GUID)) {
 			struct cxl_cper_event_rec *rec = acpi_hest_get_payload(gdata);
 
+			if (!ghes_cxl_event_len_valid(gdata, rec))
+				continue;
+
 			cxl_cper_post_event(CXL_CPER_EVENT_MEM_MODULE, rec);
 		} else {
 			void *err = acpi_hest_get_payload(gdata);
diff --git a/drivers/acpi/apei/ghes_cper.c b/drivers/acpi/apei/ghes_cper.c
index 7e4a66b788b8..b59e3ed3eab3 100644
--- a/drivers/acpi/apei/ghes_cper.c
+++ b/drivers/acpi/apei/ghes_cper.c
@@ -12,9 +12,12 @@
  *   Author: Huang Ying <ying.huang@intel.com>
  */
 
+#include <linux/aer.h>
+#include <linux/cleanup.h>
 #include <linux/err.h>
 #include <linux/genalloc.h>
 #include <linux/io.h>
+#include <linux/kfifo.h>
 #include <linux/kernel.h>
 #include <linux/math64.h>
 #include <linux/mm.h>
@@ -350,6 +353,138 @@ 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;
+
+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;
+
+	if (cxl_cper_sec_prot_err_valid(prot_err))
+		return;
+
+	guard(spinlock_irqsave)(&cxl_cper_prot_err_work_lock);
+
+	if (!cxl_cper_prot_err_work)
+		return;
+
+	if (cxl_cper_setup_prot_err_work_data(&wd, prot_err, severity))
+		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_irqsave)(&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_irqsave)(&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
+static DEFINE_KFIFO(cxl_cper_fifo, struct cxl_cper_work_data, CXL_CPER_FIFO_DEPTH);
+
+/* Synchronize schedule_work() with cxl_cper_work changes */
+static DEFINE_SPINLOCK(cxl_cper_work_lock);
+struct work_struct *cxl_cper_work;
+
+void cxl_cper_post_event(enum cxl_event_type event_type,
+			 struct cxl_cper_event_rec *rec)
+{
+	struct cxl_cper_work_data wd;
+
+	if (rec->hdr.length <= sizeof(rec->hdr) ||
+	    rec->hdr.length > sizeof(*rec)) {
+		pr_err(FW_WARN "CXL CPER Invalid section length (%u)\n",
+		       rec->hdr.length);
+		return;
+	}
+
+	if (!(rec->hdr.validation_bits & CPER_CXL_COMP_EVENT_LOG_VALID)) {
+		pr_err(FW_WARN "CXL CPER invalid event\n");
+		return;
+	}
+
+	guard(spinlock_irqsave)(&cxl_cper_work_lock);
+
+	if (!cxl_cper_work)
+		return;
+
+	wd.event_type = event_type;
+	memcpy(&wd.rec, rec, sizeof(wd.rec));
+
+	if (!kfifo_put(&cxl_cper_fifo, wd)) {
+		pr_err_ratelimited("CXL CPER kfifo overflow\n");
+		return;
+	}
+
+	schedule_work(cxl_cper_work);
+}
+
+int cxl_cper_register_work(struct work_struct *work)
+{
+	if (cxl_cper_work)
+		return -EINVAL;
+
+	guard(spinlock_irqsave)(&cxl_cper_work_lock);
+	cxl_cper_work = work;
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cper_register_work, "CXL");
+
+int cxl_cper_unregister_work(struct work_struct *work)
+{
+	if (cxl_cper_work != work)
+		return -EINVAL;
+
+	guard(spinlock_irqsave)(&cxl_cper_work_lock);
+	cxl_cper_work = NULL;
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cper_unregister_work, "CXL");
+
+int cxl_cper_kfifo_get(struct cxl_cper_work_data *wd)
+{
+	return kfifo_get(&cxl_cper_fifo, wd);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cper_kfifo_get, "CXL");
+
 /*
  * GHES error status reporting throttle, to report more kinds of
  * errors, instead of just most frequently occurred errors.
diff --git a/include/acpi/ghes_cper.h b/include/acpi/ghes_cper.h
index d9f9253d8de9..a853a5996cdf 100644
--- a/include/acpi/ghes_cper.h
+++ b/include/acpi/ghes_cper.h
@@ -20,6 +20,7 @@
 
 #include <acpi/ghes.h>
 #include <asm/fixmap.h>
+#include <cxl/event.h>
 
 #define GHES_PFX	"GHES: "
 
@@ -106,5 +107,15 @@ void ghes_estatus_cache_add(struct acpi_hest_generic *generic,
 			    struct acpi_hest_generic_status *estatus);
 void ghes_defer_non_standard_event(struct acpi_hest_generic_data *gdata,
 				   int sev);
+void cxl_cper_post_prot_err(struct cxl_cper_sec_prot_err *prot_err,
+			    int severity);
+int cxl_cper_register_prot_err_work(struct work_struct *work);
+int cxl_cper_unregister_prot_err_work(struct work_struct *work);
+int cxl_cper_prot_err_kfifo_get(struct cxl_cper_prot_err_work_data *wd);
+void cxl_cper_post_event(enum cxl_event_type event_type,
+			 struct cxl_cper_event_rec *rec);
+int cxl_cper_register_work(struct work_struct *work);
+int cxl_cper_unregister_work(struct work_struct *work);
+int cxl_cper_kfifo_get(struct cxl_cper_work_data *wd);
 
 #endif /* ACPI_APEI_GHES_CPER_H */

-- 
2.43.0

[PATCH v7 07/10] ACPI: APEI: introduce GHES helper

[Ahmed Tiba]

Add a dedicated GHES_CPER_HELPERS Kconfig entry so the shared helper code
can be built even when ACPI_APEI_GHES is disabled. Update the build glue
and headers to depend on the new symbol.

Include asm/acpi.h in cper-x86.c to provide arch_apei_report_x86_error()
declaration in ACPI-disabled builds.

Signed-off-by: Ahmed Tiba <ahmed.tiba@arm.com>
---
 drivers/Makefile                |  1 +
 drivers/acpi/Kconfig            |  4 ++++
 drivers/acpi/apei/Kconfig       |  1 +
 drivers/acpi/apei/Makefile      |  2 +-
 drivers/firmware/efi/cper-x86.c |  1 +
 include/acpi/ghes.h             | 10 ++++++----
 include/cxl/event.h             |  2 +-
 7 files changed, 15 insertions(+), 6 deletions(-)

diff --git a/drivers/Makefile b/drivers/Makefile
index 0841ea851847..27a664cb45ea 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -31,6 +31,7 @@ obj-y				+= idle/
 obj-y				+= char/ipmi/
 
 obj-$(CONFIG_ACPI)		+= acpi/
+obj-$(CONFIG_GHES_CPER_HELPERS)	+= acpi/apei/ghes_cper.o
 
 # PnP must come after ACPI since it will eventually need to check if acpi
 # was used and do nothing if so
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index f165d14cf61a..13ef0e99f840 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -6,6 +6,10 @@
 config ARCH_SUPPORTS_ACPI
 	bool
 
+config GHES_CPER_HELPERS
+	bool
+	select UEFI_CPER
+
 menuconfig ACPI
 	bool "ACPI (Advanced Configuration and Power Interface) Support"
 	depends on ARCH_SUPPORTS_ACPI
diff --git a/drivers/acpi/apei/Kconfig b/drivers/acpi/apei/Kconfig
index 428458c623f0..ddb62638eb02 100644
--- a/drivers/acpi/apei/Kconfig
+++ b/drivers/acpi/apei/Kconfig
@@ -21,6 +21,7 @@ config ACPI_APEI_GHES
 	bool "APEI Generic Hardware Error Source"
 	depends on ACPI_APEI
 	select ACPI_HED
+	select GHES_CPER_HELPERS
 	select IRQ_WORK
 	select GENERIC_ALLOCATOR
 	select ARM_SDE_INTERFACE if ARM64
diff --git a/drivers/acpi/apei/Makefile b/drivers/acpi/apei/Makefile
index f57f3b009d8e..66588d6be56f 100644
--- a/drivers/acpi/apei/Makefile
+++ b/drivers/acpi/apei/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_ACPI_APEI)		+= apei.o
-obj-$(CONFIG_ACPI_APEI_GHES)	+= ghes.o ghes_cper.o
+obj-$(CONFIG_ACPI_APEI_GHES)	+= ghes.o
 # clang versions prior to 18 may blow out the stack with KASAN
 ifeq ($(CONFIG_COMPILE_TEST)_$(CONFIG_CC_IS_CLANG)_$(call clang-min-version, 180000),y_y_)
 KASAN_SANITIZE_ghes.o := n
diff --git a/drivers/firmware/efi/cper-x86.c b/drivers/firmware/efi/cper-x86.c
index 3949d7b5e808..aa9388284e65 100644
--- a/drivers/firmware/efi/cper-x86.c
+++ b/drivers/firmware/efi/cper-x86.c
@@ -3,6 +3,7 @@
 
 #include <linux/cper.h>
 #include <linux/acpi.h>
+#include <asm/acpi.h>
 
 /*
  * We don't need a "CPER_IA" prefix since these are all locally defined.
diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h
index 8d7e5caef3f1..2ffab36b6154 100644
--- a/include/acpi/ghes.h
+++ b/include/acpi/ghes.h
@@ -83,15 +83,17 @@ int devm_ghes_register_vendor_record_notifier(struct device *dev,
 					      struct notifier_block *nb);
 
 struct list_head *ghes_get_devices(void);
-
-void ghes_estatus_pool_region_free(unsigned long addr, u32 size);
 #else
 static inline struct list_head *ghes_get_devices(void) { return NULL; }
-
-static inline void ghes_estatus_pool_region_free(unsigned long addr, u32 size) { return; }
 #endif
 
+#ifdef CONFIG_GHES_CPER_HELPERS
 int ghes_estatus_pool_init(unsigned int num_ghes);
+void ghes_estatus_pool_region_free(unsigned long addr, u32 size);
+#else
+static inline int ghes_estatus_pool_init(unsigned int num_ghes) { return -ENODEV; }
+static inline void ghes_estatus_pool_region_free(unsigned long addr, u32 size) { }
+#endif
 
 static inline int acpi_hest_get_version(struct acpi_hest_generic_data *gdata)
 {
diff --git a/include/cxl/event.h b/include/cxl/event.h
index ff97fea718d2..2ebd65b0d9d6 100644
--- a/include/cxl/event.h
+++ b/include/cxl/event.h
@@ -285,7 +285,7 @@ struct cxl_cper_prot_err_work_data {
 	int severity;
 };
 
-#ifdef CONFIG_ACPI_APEI_GHES
+#ifdef CONFIG_GHES_CPER_HELPERS
 int cxl_cper_register_work(struct work_struct *work);
 int cxl_cper_unregister_work(struct work_struct *work);
 int cxl_cper_kfifo_get(struct cxl_cper_work_data *wd);

-- 
2.43.0

[PATCH v7 08/10] ACPI: APEI: share GHES CPER helpers

[Ahmed Tiba]

Wire GHES up to the helper routines in ghes_cper.c and remove the local
copies from ghes.c. This keeps the control flow identical while letting
the helpers be shared with other firmware-first providers.

The weak arch_apei_report_mem_error() fallback is only there to keep the
shared helper buildable when GHES_CPER_HELPERS is enabled without
ACPI_APEI, while preserving the current GHES behaviour when ACPI_APEI
is enabled.

Serialize ghes_estatus_pool_init() and allow later users to extend the
shared pool instead of racing a second initialization or silently
reusing a pool sized only for the first user.

Fix queued tracking and AER overflow cleanup.

Signed-off-by: Ahmed Tiba <ahmed.tiba@arm.com>
---
 drivers/acpi/apei/ghes.c      | 464 +--------------------------------------
 drivers/acpi/apei/ghes_cper.c | 500 ++++++++++++++++++++++++++++++++++++++++++
 drivers/pci/pcie/aer.c        |   9 +-
 include/acpi/ghes_cper.h      |  20 ++
 4 files changed, 529 insertions(+), 464 deletions(-)

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 2a83d326e692..c643c1703819 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -67,8 +67,6 @@
 #define FIX_APEI_GHES_SDEI_CRITICAL	__end_of_fixed_addresses
 #endif
 
-static ATOMIC_NOTIFIER_HEAD(ghes_report_chain);
-
 /*
  * This driver isn't really modular, however for the time being,
  * continuing to use module_param is the easiest way to remain
@@ -113,469 +111,11 @@ static DEFINE_MUTEX(ghes_devs_mutex);
  */
 static DEFINE_SPINLOCK(ghes_notify_lock_irq);
 
-struct gen_pool *ghes_estatus_pool;
-
-int ghes_estatus_pool_init(unsigned int num_ghes)
-{
-	unsigned long addr, len;
-	int rc;
-
-	ghes_estatus_pool = gen_pool_create(GHES_ESTATUS_POOL_MIN_ALLOC_ORDER, -1);
-	if (!ghes_estatus_pool)
-		return -ENOMEM;
-
-	len = GHES_ESTATUS_CACHE_AVG_SIZE * GHES_ESTATUS_CACHE_ALLOCED_MAX;
-	len += (num_ghes * GHES_ESOURCE_PREALLOC_MAX_SIZE);
-
-	addr = (unsigned long)vmalloc(PAGE_ALIGN(len));
-	if (!addr)
-		goto err_pool_alloc;
-
-	rc = gen_pool_add(ghes_estatus_pool, addr, PAGE_ALIGN(len), -1);
-	if (rc)
-		goto err_pool_add;
-
-	return 0;
-
-err_pool_add:
-	vfree((void *)addr);
-
-err_pool_alloc:
-	gen_pool_destroy(ghes_estatus_pool);
-
-	return -ENOMEM;
-}
-
-/**
- * ghes_estatus_pool_region_free - free previously allocated memory
- *				   from the ghes_estatus_pool.
- * @addr: address of memory to free.
- * @size: size of memory to free.
- *
- * Returns none.
- */
-void ghes_estatus_pool_region_free(unsigned long addr, u32 size)
-{
-	gen_pool_free(ghes_estatus_pool, addr, size);
-}
-EXPORT_SYMBOL_GPL(ghes_estatus_pool_region_free);
-
-static inline int ghes_severity(int severity)
-{
-	switch (severity) {
-	case CPER_SEV_INFORMATIONAL:
-		return GHES_SEV_NO;
-	case CPER_SEV_CORRECTED:
-		return GHES_SEV_CORRECTED;
-	case CPER_SEV_RECOVERABLE:
-		return GHES_SEV_RECOVERABLE;
-	case CPER_SEV_FATAL:
-		return GHES_SEV_PANIC;
-	default:
-		/* Unknown, go panic */
-		return GHES_SEV_PANIC;
-	}
-}
-
-
-/**
- * struct ghes_task_work - for synchronous RAS event
- *
- * @twork:                callback_head for task work
- * @pfn:                  page frame number of corrupted page
- * @flags:                work control flags
- *
- * Structure to pass task work to be handled before
- * returning to user-space via task_work_add().
- */
-struct ghes_task_work {
-	struct callback_head twork;
-	u64 pfn;
-	int flags;
-};
-
-static void memory_failure_cb(struct callback_head *twork)
-{
-	struct ghes_task_work *twcb = container_of(twork, struct ghes_task_work, twork);
-	int ret;
-
-	ret = memory_failure(twcb->pfn, twcb->flags);
-	gen_pool_free(ghes_estatus_pool, (unsigned long)twcb, sizeof(*twcb));
-
-	if (!ret || ret == -EHWPOISON || ret == -EOPNOTSUPP)
-		return;
-
-	pr_err("%#llx: Sending SIGBUS to %s:%d due to hardware memory corruption\n",
-			twcb->pfn, current->comm, task_pid_nr(current));
-	force_sig(SIGBUS);
-}
-
-static bool ghes_do_memory_failure(u64 physical_addr, int flags)
-{
-	struct ghes_task_work *twcb;
-	unsigned long pfn;
-
-	if (!IS_ENABLED(CONFIG_ACPI_APEI_MEMORY_FAILURE))
-		return false;
-
-	pfn = PHYS_PFN(physical_addr);
-
-	if (flags == MF_ACTION_REQUIRED && current->mm) {
-		twcb = (void *)gen_pool_alloc(ghes_estatus_pool, sizeof(*twcb));
-		if (!twcb)
-			return false;
-
-		twcb->pfn = pfn;
-		twcb->flags = flags;
-		init_task_work(&twcb->twork, memory_failure_cb);
-		task_work_add(current, &twcb->twork, TWA_RESUME);
-		return true;
-	}
-
-	memory_failure_queue(pfn, flags);
-	return true;
-}
-
-static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
-				       int sev, bool sync)
-{
-	int flags = -1;
-	int sec_sev = ghes_severity(gdata->error_severity);
-	struct cper_sec_mem_err *mem_err = acpi_hest_get_payload(gdata);
-
-	if (!(mem_err->validation_bits & CPER_MEM_VALID_PA))
-		return false;
-
-	/* iff following two events can be handled properly by now */
-	if (sec_sev == GHES_SEV_CORRECTED &&
-	    (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED))
-		flags = MF_SOFT_OFFLINE;
-	if (sev == GHES_SEV_RECOVERABLE && sec_sev == GHES_SEV_RECOVERABLE)
-		flags = sync ? MF_ACTION_REQUIRED : 0;
-
-	if (flags != -1)
-		return ghes_do_memory_failure(mem_err->physical_addr, flags);
-
-	return false;
-}
-
-static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata,
-				     int sev, bool sync)
-{
-	struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata);
-	int flags = sync ? MF_ACTION_REQUIRED : 0;
-	int length = gdata->error_data_length;
-	char error_type[120];
-	bool queued = false;
-	int sec_sev, i;
-	char *p;
-
-	sec_sev = ghes_severity(gdata->error_severity);
-	if (length >= sizeof(*err)) {
-		log_arm_hw_error(err, sec_sev);
-	} else {
-		pr_warn(FW_BUG "arm error length: %d\n", length);
-		pr_warn(FW_BUG "length is too small\n");
-		pr_warn(FW_BUG "firmware-generated error record is incorrect\n");
-		return false;
-	}
-
-	if (sev != GHES_SEV_RECOVERABLE || sec_sev != GHES_SEV_RECOVERABLE)
-		return false;
-
-	p = (char *)(err + 1);
-	length -= sizeof(err);
-
-	for (i = 0; i < err->err_info_num; i++) {
-		struct cper_arm_err_info *err_info;
-		bool is_cache, has_pa;
-
-		/* Ensure we have enough data for the error info header */
-		if (length < sizeof(*err_info))
-			break;
-
-		err_info = (struct cper_arm_err_info *)p;
-
-		/* Validate the claimed length before using it */
-		length -= err_info->length;
-		if (length < 0)
-			break;
-
-		is_cache = err_info->type & CPER_ARM_CACHE_ERROR;
-		has_pa = (err_info->validation_bits & CPER_ARM_INFO_VALID_PHYSICAL_ADDR);
-
-		/*
-		 * The field (err_info->error_info & BIT(26)) is fixed to set to
-		 * 1 in some old firmware of HiSilicon Kunpeng920. We assume that
-		 * firmware won't mix corrected errors in an uncorrected section,
-		 * and don't filter out 'corrected' error here.
-		 */
-		if (is_cache && has_pa) {
-			queued = ghes_do_memory_failure(err_info->physical_fault_addr, flags);
-			p += err_info->length;
-			continue;
-		}
-
-		cper_bits_to_str(error_type, sizeof(error_type),
-				 FIELD_GET(CPER_ARM_ERR_TYPE_MASK, err_info->type),
-				 cper_proc_error_type_strs,
-				 ARRAY_SIZE(cper_proc_error_type_strs));
-
-		pr_warn_ratelimited(FW_WARN GHES_PFX
-				    "Unhandled processor error type 0x%02x: %s%s\n",
-				    err_info->type, error_type,
-				    (err_info->type & ~CPER_ARM_ERR_TYPE_MASK) ? " with reserved bit(s)" : "");
-		p += err_info->length;
-	}
-
-	return queued;
-}
-
-/*
- * PCIe AER errors need to be sent to the AER driver for reporting and
- * recovery. The GHES severities map to the following AER severities and
- * require the following handling:
- *
- * GHES_SEV_CORRECTABLE -> AER_CORRECTABLE
- *     These need to be reported by the AER driver but no recovery is
- *     necessary.
- * GHES_SEV_RECOVERABLE -> AER_NONFATAL
- * GHES_SEV_RECOVERABLE && CPER_SEC_RESET -> AER_FATAL
- *     These both need to be reported and recovered from by the AER driver.
- * GHES_SEV_PANIC does not make it to this handling since the kernel must
- *     panic.
- */
-static void ghes_handle_aer(struct acpi_hest_generic_data *gdata)
-{
-#ifdef CONFIG_ACPI_APEI_PCIEAER
-	struct cper_sec_pcie *pcie_err = acpi_hest_get_payload(gdata);
-
-	if (pcie_err->validation_bits & CPER_PCIE_VALID_DEVICE_ID &&
-	    pcie_err->validation_bits & CPER_PCIE_VALID_AER_INFO) {
-		unsigned int devfn;
-		int aer_severity;
-		u8 *aer_info;
-
-		devfn = PCI_DEVFN(pcie_err->device_id.device,
-				  pcie_err->device_id.function);
-		aer_severity = cper_severity_to_aer(gdata->error_severity);
-
-		/*
-		 * If firmware reset the component to contain
-		 * the error, we must reinitialize it before
-		 * use, so treat it as a fatal AER error.
-		 */
-		if (gdata->flags & CPER_SEC_RESET)
-			aer_severity = AER_FATAL;
-
-		aer_info = (void *)gen_pool_alloc(ghes_estatus_pool,
-						  sizeof(struct aer_capability_regs));
-		if (!aer_info)
-			return;
-		memcpy(aer_info, pcie_err->aer_info, sizeof(struct aer_capability_regs));
-
-		aer_recover_queue(pcie_err->device_id.segment,
-				  pcie_err->device_id.bus,
-				  devfn, aer_severity,
-				  (struct aer_capability_regs *)
-				  aer_info);
-	}
-#endif
-}
-
-static void ghes_log_hwerr(int sev, guid_t *sec_type)
-{
-	if (sev != CPER_SEV_RECOVERABLE)
-		return;
-
-	if (guid_equal(sec_type, &CPER_SEC_PROC_ARM) ||
-	    guid_equal(sec_type, &CPER_SEC_PROC_GENERIC) ||
-	    guid_equal(sec_type, &CPER_SEC_PROC_IA)) {
-		hwerr_log_error_type(HWERR_RECOV_CPU);
-		return;
-	}
-
-	if (guid_equal(sec_type, &CPER_SEC_CXL_PROT_ERR) ||
-	    guid_equal(sec_type, &CPER_SEC_CXL_GEN_MEDIA_GUID) ||
-	    guid_equal(sec_type, &CPER_SEC_CXL_DRAM_GUID) ||
-	    guid_equal(sec_type, &CPER_SEC_CXL_MEM_MODULE_GUID)) {
-		hwerr_log_error_type(HWERR_RECOV_CXL);
-		return;
-	}
-
-	if (guid_equal(sec_type, &CPER_SEC_PCIE) ||
-	    guid_equal(sec_type, &CPER_SEC_PCI_X_BUS)) {
-		hwerr_log_error_type(HWERR_RECOV_PCI);
-		return;
-	}
-
-	if (guid_equal(sec_type, &CPER_SEC_PLATFORM_MEM)) {
-		hwerr_log_error_type(HWERR_RECOV_MEMORY);
-		return;
-	}
-
-	hwerr_log_error_type(HWERR_RECOV_OTHERS);
-}
-
-static bool ghes_cxl_event_len_valid(struct acpi_hest_generic_data *gdata,
-				     struct cxl_cper_event_rec *rec)
-{
-	if (gdata->error_data_length < sizeof(*rec) ||
-	    rec->hdr.length <= sizeof(rec->hdr) ||
-	    rec->hdr.length > gdata->error_data_length ||
-	    rec->hdr.length > sizeof(*rec)) {
-		pr_err(FW_WARN "CXL CPER Invalid section length (%u)\n",
-		       rec->hdr.length);
-		return false;
-	}
-
-	return true;
-}
-
-static bool ghes_cxl_prot_err_len_valid(struct acpi_hest_generic_data *gdata,
-					struct cxl_cper_sec_prot_err *prot_err)
-{
-	if (gdata->error_data_length < sizeof(*prot_err) +
-	    sizeof(struct cxl_ras_capability_regs)) {
-		pr_err(FW_WARN "CXL CPER Invalid protocol error length (%u)\n",
-		       gdata->error_data_length);
-		return false;
-	}
-
-	if (prot_err->dvsec_len >
-	    gdata->error_data_length - sizeof(*prot_err) -
-	    sizeof(struct cxl_ras_capability_regs)) {
-		pr_err(FW_WARN "CXL CPER invalid DVSEC length (%u)\n",
-		       prot_err->dvsec_len);
-		return false;
-	}
-
-	return true;
-}
-
 static void ghes_do_proc(struct ghes *ghes,
 			 const struct acpi_hest_generic_status *estatus)
 {
-	int sev, sec_sev;
-	struct acpi_hest_generic_data *gdata;
-	guid_t *sec_type;
-	const guid_t *fru_id = &guid_null;
-	char *fru_text = "";
-	bool queued = false;
-	bool sync = is_hest_sync_notify(ghes);
-
-	sev = ghes_severity(estatus->error_severity);
-	apei_estatus_for_each_section(estatus, gdata) {
-		sec_type = (guid_t *)gdata->section_type;
-		sec_sev = ghes_severity(gdata->error_severity);
-		if (gdata->validation_bits & CPER_SEC_VALID_FRU_ID)
-			fru_id = (guid_t *)gdata->fru_id;
-
-		if (gdata->validation_bits & CPER_SEC_VALID_FRU_TEXT)
-			fru_text = gdata->fru_text;
-
-		ghes_log_hwerr(sev, sec_type);
-		if (guid_equal(sec_type, &CPER_SEC_PLATFORM_MEM)) {
-			struct cper_sec_mem_err *mem_err = acpi_hest_get_payload(gdata);
-
-			atomic_notifier_call_chain(&ghes_report_chain, sev, mem_err);
-
-			arch_apei_report_mem_error(sev, mem_err);
-			queued = ghes_handle_memory_failure(gdata, sev, sync);
-		} else if (guid_equal(sec_type, &CPER_SEC_PCIE)) {
-			ghes_handle_aer(gdata);
-		} 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);
-
-			if (!ghes_cxl_prot_err_len_valid(gdata, prot_err))
-				continue;
-
-			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);
-
-			if (!ghes_cxl_event_len_valid(gdata, rec))
-				continue;
-
-			cxl_cper_post_event(CXL_CPER_EVENT_GEN_MEDIA, rec);
-		} else if (guid_equal(sec_type, &CPER_SEC_CXL_DRAM_GUID)) {
-			struct cxl_cper_event_rec *rec = acpi_hest_get_payload(gdata);
-
-			if (!ghes_cxl_event_len_valid(gdata, rec))
-				continue;
-
-			cxl_cper_post_event(CXL_CPER_EVENT_DRAM, rec);
-		} else if (guid_equal(sec_type, &CPER_SEC_CXL_MEM_MODULE_GUID)) {
-			struct cxl_cper_event_rec *rec = acpi_hest_get_payload(gdata);
-
-			if (!ghes_cxl_event_len_valid(gdata, rec))
-				continue;
-
-			cxl_cper_post_event(CXL_CPER_EVENT_MEM_MODULE, rec);
-		} else {
-			void *err = acpi_hest_get_payload(gdata);
-
-			ghes_defer_non_standard_event(gdata, sev);
-			log_non_standard_event(sec_type, fru_id, fru_text,
-					       sec_sev, err,
-					       gdata->error_data_length);
-		}
-	}
-
-	/*
-	 * If no memory failure work is queued for abnormal synchronous
-	 * errors, do a force kill.
-	 */
-	if (sync && !queued) {
-		dev_err(ghes->dev,
-			HW_ERR GHES_PFX "%s:%d: synchronous unrecoverable error (SIGBUS)\n",
-			current->comm, task_pid_nr(current));
-		force_sig(SIGBUS);
-	}
-}
-
-static void __ghes_print_estatus(const char *pfx,
-				 const struct acpi_hest_generic *generic,
-				 const struct acpi_hest_generic_status *estatus)
-{
-	static atomic_t seqno;
-	unsigned int curr_seqno;
-	char pfx_seq[64];
-
-	if (pfx == NULL) {
-		if (ghes_severity(estatus->error_severity) <=
-		    GHES_SEV_CORRECTED)
-			pfx = KERN_WARNING;
-		else
-			pfx = KERN_ERR;
-	}
-	curr_seqno = atomic_inc_return(&seqno);
-	snprintf(pfx_seq, sizeof(pfx_seq), "%s{%u}" HW_ERR, pfx, curr_seqno);
-	printk("%s""Hardware error from APEI Generic Hardware Error Source: %d\n",
-	       pfx_seq, generic->header.source_id);
-	cper_estatus_print(pfx_seq, estatus);
-}
-
-static int ghes_print_estatus(const char *pfx,
-			      const struct acpi_hest_generic *generic,
-			      const struct acpi_hest_generic_status *estatus)
-{
-	/* Not more than 2 messages every 5 seconds */
-	static DEFINE_RATELIMIT_STATE(ratelimit_corrected, 5*HZ, 2);
-	static DEFINE_RATELIMIT_STATE(ratelimit_uncorrected, 5*HZ, 2);
-	struct ratelimit_state *ratelimit;
-
-	if (ghes_severity(estatus->error_severity) <= GHES_SEV_CORRECTED)
-		ratelimit = &ratelimit_corrected;
-	else
-		ratelimit = &ratelimit_uncorrected;
-	if (__ratelimit(ratelimit)) {
-		__ghes_print_estatus(pfx, generic, estatus);
-		return 1;
-	}
-	return 0;
+	ghes_cper_handle_status(ghes->dev, ghes->generic,
+				estatus, is_hest_sync_notify(ghes));
 }
 
 static void __ghes_panic(struct ghes *ghes,
diff --git a/drivers/acpi/apei/ghes_cper.c b/drivers/acpi/apei/ghes_cper.c
index b59e3ed3eab3..ec8881ada97e 100644
--- a/drivers/acpi/apei/ghes_cper.c
+++ b/drivers/acpi/apei/ghes_cper.c
@@ -13,7 +13,9 @@
  */
 
 #include <linux/aer.h>
+#include <linux/bitfield.h>
 #include <linux/cleanup.h>
+#include <linux/device.h>
 #include <linux/err.h>
 #include <linux/genalloc.h>
 #include <linux/io.h>
@@ -21,11 +23,20 @@
 #include <linux/kernel.h>
 #include <linux/math64.h>
 #include <linux/mm.h>
+#include <linux/mutex.h>
+#include <linux/string.h>
+#include <linux/uuid.h>
+#include <linux/sched/signal.h>
+#include <linux/task_work.h>
 #include <linux/notifier.h>
+#include <linux/ras.h>
+#include <ras/ras_event.h>
 #include <linux/ratelimit.h>
 #include <linux/rcupdate.h>
 #include <linux/sched/clock.h>
 #include <linux/slab.h>
+#include <linux/vmcore_info.h>
+#include <linux/vmalloc.h>
 
 #include <acpi/apei.h>
 #include <acpi/acpi_io.h>
@@ -36,9 +47,497 @@
 
 #include "apei-internal.h"
 
+ATOMIC_NOTIFIER_HEAD(ghes_report_chain);
+
+#ifndef CONFIG_ACPI_APEI
+void __weak arch_apei_report_mem_error(int sev, struct cper_sec_mem_err *mem_err) { }
+#endif
+
 static struct ghes_estatus_cache __rcu *ghes_estatus_caches[GHES_ESTATUS_CACHES_SIZE];
 static atomic_t ghes_estatus_cache_alloced;
 
+struct gen_pool *ghes_estatus_pool;
+static DEFINE_MUTEX(ghes_estatus_pool_lock);
+
+int ghes_estatus_pool_init(unsigned int num_ghes)
+{
+	unsigned long addr, len;
+	int rc;
+
+	len = GHES_ESTATUS_CACHE_AVG_SIZE * GHES_ESTATUS_CACHE_ALLOCED_MAX;
+	len += (num_ghes * GHES_ESOURCE_PREALLOC_MAX_SIZE);
+	len = PAGE_ALIGN(len);
+
+	mutex_lock(&ghes_estatus_pool_lock);
+
+	if (!ghes_estatus_pool) {
+		ghes_estatus_pool = gen_pool_create(GHES_ESTATUS_POOL_MIN_ALLOC_ORDER, -1);
+		if (!ghes_estatus_pool) {
+			rc = -ENOMEM;
+			goto out_unlock;
+		}
+	}
+
+	addr = (unsigned long)vmalloc(len);
+	if (!addr) {
+		rc = -ENOMEM;
+		goto err_pool_alloc;
+	}
+
+	rc = gen_pool_add(ghes_estatus_pool, addr, len, -1);
+	if (rc)
+		goto err_pool_add;
+
+	mutex_unlock(&ghes_estatus_pool_lock);
+	return 0;
+
+err_pool_add:
+	vfree((void *)addr);
+
+err_pool_alloc:
+	if (!gen_pool_avail(ghes_estatus_pool) && !gen_pool_size(ghes_estatus_pool)) {
+		gen_pool_destroy(ghes_estatus_pool);
+		ghes_estatus_pool = NULL;
+	}
+out_unlock:
+	mutex_unlock(&ghes_estatus_pool_lock);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(ghes_estatus_pool_init);
+
+/**
+ * ghes_estatus_pool_region_free - free previously allocated memory
+ *				   from the ghes_estatus_pool.
+ * @addr: address of memory to free.
+ * @size: size of memory to free.
+ *
+ * Returns none.
+ */
+void ghes_estatus_pool_region_free(unsigned long addr, u32 size)
+{
+	gen_pool_free(ghes_estatus_pool, addr, size);
+}
+EXPORT_SYMBOL_GPL(ghes_estatus_pool_region_free);
+
+int ghes_severity(int severity)
+{
+	switch (severity) {
+	case CPER_SEV_INFORMATIONAL:
+		return GHES_SEV_NO;
+	case CPER_SEV_CORRECTED:
+		return GHES_SEV_CORRECTED;
+	case CPER_SEV_RECOVERABLE:
+		return GHES_SEV_RECOVERABLE;
+	case CPER_SEV_FATAL:
+		return GHES_SEV_PANIC;
+	default:
+		/* Unknown, go panic */
+		return GHES_SEV_PANIC;
+	}
+}
+
+/**
+ * struct ghes_task_work - for synchronous RAS event
+ *
+ * @twork:                callback_head for task work
+ * @pfn:                  page frame number of corrupted page
+ * @flags:                work control flags
+ *
+ * Structure to pass task work to be handled before
+ * returning to user-space via task_work_add().
+ */
+struct ghes_task_work {
+	struct callback_head twork;
+	u64 pfn;
+	int flags;
+};
+
+static void memory_failure_cb(struct callback_head *twork)
+{
+	struct ghes_task_work *twcb = container_of(twork, struct ghes_task_work, twork);
+	int ret;
+
+	ret = memory_failure(twcb->pfn, twcb->flags);
+	gen_pool_free(ghes_estatus_pool, (unsigned long)twcb, sizeof(*twcb));
+
+	if (!ret || ret == -EHWPOISON || ret == -EOPNOTSUPP)
+		return;
+
+	pr_err("%#llx: Sending SIGBUS to %s:%d due to hardware memory corruption\n",
+			twcb->pfn, current->comm, task_pid_nr(current));
+	force_sig(SIGBUS);
+}
+
+static bool ghes_do_memory_failure(u64 physical_addr, int flags)
+{
+	struct ghes_task_work *twcb;
+	unsigned long pfn;
+
+	if (!IS_ENABLED(CONFIG_ACPI_APEI_MEMORY_FAILURE))
+		return false;
+
+	pfn = PHYS_PFN(physical_addr);
+
+	if (flags == MF_ACTION_REQUIRED && current->mm) {
+		twcb = (void *)gen_pool_alloc(ghes_estatus_pool, sizeof(*twcb));
+		if (!twcb)
+			return false;
+
+		twcb->pfn = pfn;
+		twcb->flags = flags;
+		init_task_work(&twcb->twork, memory_failure_cb);
+		task_work_add(current, &twcb->twork, TWA_RESUME);
+		return true;
+	}
+
+	memory_failure_queue(pfn, flags);
+	return true;
+}
+
+bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
+				int sev, bool sync)
+{
+	int flags = -1;
+	int sec_sev = ghes_severity(gdata->error_severity);
+	struct cper_sec_mem_err *mem_err = acpi_hest_get_payload(gdata);
+
+	if (!(mem_err->validation_bits & CPER_MEM_VALID_PA))
+		return false;
+
+	/* iff following two events can be handled properly by now */
+	if (sec_sev == GHES_SEV_CORRECTED &&
+	    (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED))
+		flags = MF_SOFT_OFFLINE;
+	if (sev == GHES_SEV_RECOVERABLE && sec_sev == GHES_SEV_RECOVERABLE)
+		flags = sync ? MF_ACTION_REQUIRED : 0;
+
+	if (flags != -1)
+		return ghes_do_memory_failure(mem_err->physical_addr, flags);
+
+	return false;
+}
+
+bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata,
+			      int sev, bool sync)
+{
+	struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata);
+	int flags = sync ? MF_ACTION_REQUIRED : 0;
+	int length = gdata->error_data_length;
+	char error_type[120];
+	bool queued = false;
+	int sec_sev, i;
+	char *p;
+
+	sec_sev = ghes_severity(gdata->error_severity);
+	if (length >= sizeof(*err)) {
+		log_arm_hw_error(err, sec_sev);
+	} else {
+		pr_warn(FW_BUG "arm error length: %d\n", length);
+		pr_warn(FW_BUG "length is too small\n");
+		pr_warn(FW_BUG "firmware-generated error record is incorrect\n");
+		return false;
+	}
+
+	if (sev != GHES_SEV_RECOVERABLE || sec_sev != GHES_SEV_RECOVERABLE)
+		return false;
+
+	p = (char *)(err + 1);
+	length -= sizeof(*err);
+
+	for (i = 0; i < err->err_info_num; i++) {
+		struct cper_arm_err_info *err_info;
+		bool is_cache, has_pa;
+
+		/* Ensure we have enough data for the error info header */
+		if (length < sizeof(*err_info))
+			break;
+
+		err_info = (struct cper_arm_err_info *)p;
+
+		/* Validate the claimed length before using it */
+		length -= err_info->length;
+		if (length < 0)
+			break;
+
+		is_cache = err_info->type & CPER_ARM_CACHE_ERROR;
+		has_pa = (err_info->validation_bits & CPER_ARM_INFO_VALID_PHYSICAL_ADDR);
+
+		/*
+		 * The field (err_info->error_info & BIT(26)) is fixed to set to
+		 * 1 in some old firmware of HiSilicon Kunpeng920. We assume that
+		 * firmware won't mix corrected errors in an uncorrected section,
+		 * and don't filter out 'corrected' error here.
+		 */
+		if (is_cache && has_pa) {
+			queued |= ghes_do_memory_failure(err_info->physical_fault_addr, flags);
+			p += err_info->length;
+			continue;
+		}
+
+		cper_bits_to_str(error_type, sizeof(error_type),
+				 FIELD_GET(CPER_ARM_ERR_TYPE_MASK, err_info->type),
+				 cper_proc_error_type_strs,
+				 ARRAY_SIZE(cper_proc_error_type_strs));
+
+		pr_warn_ratelimited(FW_WARN GHES_PFX
+				    "Unhandled processor error type 0x%02x: %s%s\n",
+				    err_info->type, error_type,
+				    (err_info->type & ~CPER_ARM_ERR_TYPE_MASK) ? " with reserved bit(s)" : "");
+		p += err_info->length;
+	}
+
+	return queued;
+}
+
+/*
+ * PCIe AER errors need to be sent to the AER driver for reporting and
+ * recovery. The GHES severities map to the following AER severities and
+ * require the following handling:
+ *
+ * GHES_SEV_CORRECTABLE -> AER_CORRECTABLE
+ *     These need to be reported by the AER driver but no recovery is
+ *     necessary.
+ * GHES_SEV_RECOVERABLE -> AER_NONFATAL
+ * GHES_SEV_RECOVERABLE && CPER_SEC_RESET -> AER_FATAL
+ *     These both need to be reported and recovered from by the AER driver.
+ * GHES_SEV_PANIC does not make it to this handling since the kernel must
+ *     panic.
+ */
+void ghes_handle_aer(struct acpi_hest_generic_data *gdata)
+{
+#ifdef CONFIG_ACPI_APEI_PCIEAER
+	struct cper_sec_pcie *pcie_err = acpi_hest_get_payload(gdata);
+
+	if (pcie_err->validation_bits & CPER_PCIE_VALID_DEVICE_ID &&
+	    pcie_err->validation_bits & CPER_PCIE_VALID_AER_INFO) {
+		unsigned int devfn;
+		int aer_severity;
+		u8 *aer_info;
+
+		devfn = PCI_DEVFN(pcie_err->device_id.device,
+				  pcie_err->device_id.function);
+		aer_severity = cper_severity_to_aer(gdata->error_severity);
+
+		/*
+		 * If firmware reset the component to contain
+		 * the error, we must reinitialize it before
+		 * use, so treat it as a fatal AER error.
+		 */
+		if (gdata->flags & CPER_SEC_RESET)
+			aer_severity = AER_FATAL;
+
+		aer_info = (void *)gen_pool_alloc(ghes_estatus_pool,
+						  sizeof(struct aer_capability_regs));
+		if (!aer_info)
+			return;
+		memcpy(aer_info, pcie_err->aer_info, sizeof(struct aer_capability_regs));
+
+		aer_recover_queue(pcie_err->device_id.segment,
+				  pcie_err->device_id.bus,
+				  devfn, aer_severity,
+				  (struct aer_capability_regs *)
+				  aer_info);
+	}
+#endif
+}
+
+void ghes_log_hwerr(int sev, guid_t *sec_type)
+{
+	if (sev != CPER_SEV_RECOVERABLE)
+		return;
+
+	if (guid_equal(sec_type, &CPER_SEC_PROC_ARM) ||
+	    guid_equal(sec_type, &CPER_SEC_PROC_GENERIC) ||
+	    guid_equal(sec_type, &CPER_SEC_PROC_IA)) {
+		hwerr_log_error_type(HWERR_RECOV_CPU);
+		return;
+	}
+
+	if (guid_equal(sec_type, &CPER_SEC_CXL_PROT_ERR) ||
+	    guid_equal(sec_type, &CPER_SEC_CXL_GEN_MEDIA_GUID) ||
+	    guid_equal(sec_type, &CPER_SEC_CXL_DRAM_GUID) ||
+	    guid_equal(sec_type, &CPER_SEC_CXL_MEM_MODULE_GUID)) {
+		hwerr_log_error_type(HWERR_RECOV_CXL);
+		return;
+	}
+
+	if (guid_equal(sec_type, &CPER_SEC_PCIE) ||
+	    guid_equal(sec_type, &CPER_SEC_PCI_X_BUS)) {
+		hwerr_log_error_type(HWERR_RECOV_PCI);
+		return;
+	}
+
+	if (guid_equal(sec_type, &CPER_SEC_PLATFORM_MEM)) {
+		hwerr_log_error_type(HWERR_RECOV_MEMORY);
+		return;
+	}
+
+	hwerr_log_error_type(HWERR_RECOV_OTHERS);
+}
+
+static bool ghes_cxl_event_len_valid(struct acpi_hest_generic_data *gdata,
+				     struct cxl_cper_event_rec *rec)
+{
+	if (gdata->error_data_length < sizeof(*rec) ||
+	    rec->hdr.length <= sizeof(rec->hdr) ||
+	    rec->hdr.length > gdata->error_data_length ||
+	    rec->hdr.length > sizeof(*rec)) {
+		pr_err(FW_WARN "CXL CPER Invalid section length (%u)\n",
+		       rec->hdr.length);
+		return false;
+	}
+
+	return true;
+}
+
+static bool ghes_cxl_prot_err_len_valid(struct acpi_hest_generic_data *gdata,
+					struct cxl_cper_sec_prot_err *prot_err)
+{
+	if (gdata->error_data_length < sizeof(*prot_err) +
+	    sizeof(struct cxl_ras_capability_regs)) {
+		pr_err(FW_WARN "CXL CPER Invalid protocol error length (%u)\n",
+		       gdata->error_data_length);
+		return false;
+	}
+
+	if (prot_err->dvsec_len >
+	    gdata->error_data_length - sizeof(*prot_err) -
+	    sizeof(struct cxl_ras_capability_regs)) {
+		pr_err(FW_WARN "CXL CPER invalid DVSEC length (%u)\n",
+		       prot_err->dvsec_len);
+		return false;
+	}
+
+	return true;
+}
+
+void ghes_cper_handle_status(struct device *dev,
+			     const struct acpi_hest_generic *generic,
+			     const struct acpi_hest_generic_status *estatus,
+			     bool sync)
+{
+	int sev, sec_sev;
+	struct acpi_hest_generic_data *gdata;
+	guid_t *sec_type;
+	const guid_t *fru_id = &guid_null;
+	char *fru_text = "";
+	bool queued = false;
+
+	sev = ghes_severity(estatus->error_severity);
+	apei_estatus_for_each_section(estatus, gdata) {
+		sec_type = (guid_t *)gdata->section_type;
+		sec_sev = ghes_severity(gdata->error_severity);
+		if (gdata->validation_bits & CPER_SEC_VALID_FRU_ID)
+			fru_id = (guid_t *)gdata->fru_id;
+
+		if (gdata->validation_bits & CPER_SEC_VALID_FRU_TEXT)
+			fru_text = gdata->fru_text;
+
+		ghes_log_hwerr(sev, sec_type);
+		if (guid_equal(sec_type, &CPER_SEC_PLATFORM_MEM)) {
+			struct cper_sec_mem_err *mem_err = acpi_hest_get_payload(gdata);
+
+			atomic_notifier_call_chain(&ghes_report_chain, sev, mem_err);
+
+			arch_apei_report_mem_error(sev, mem_err);
+			queued |= ghes_handle_memory_failure(gdata, sev, sync);
+		} else if (guid_equal(sec_type, &CPER_SEC_PCIE)) {
+			ghes_handle_aer(gdata);
+		} 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);
+
+			if (!ghes_cxl_prot_err_len_valid(gdata, prot_err))
+				continue;
+
+			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);
+
+			if (!ghes_cxl_event_len_valid(gdata, rec))
+				continue;
+
+			cxl_cper_post_event(CXL_CPER_EVENT_GEN_MEDIA, rec);
+		} else if (guid_equal(sec_type, &CPER_SEC_CXL_DRAM_GUID)) {
+			struct cxl_cper_event_rec *rec = acpi_hest_get_payload(gdata);
+
+			if (!ghes_cxl_event_len_valid(gdata, rec))
+				continue;
+
+			cxl_cper_post_event(CXL_CPER_EVENT_DRAM, rec);
+		} else if (guid_equal(sec_type, &CPER_SEC_CXL_MEM_MODULE_GUID)) {
+			struct cxl_cper_event_rec *rec = acpi_hest_get_payload(gdata);
+
+			if (!ghes_cxl_event_len_valid(gdata, rec))
+				continue;
+
+			cxl_cper_post_event(CXL_CPER_EVENT_MEM_MODULE, rec);
+		} else {
+			void *err = acpi_hest_get_payload(gdata);
+
+			ghes_defer_non_standard_event(gdata, sev);
+			log_non_standard_event(sec_type, fru_id, fru_text,
+					       sec_sev, err,
+					       gdata->error_data_length);
+		}
+	}
+
+	/*
+	 * If no memory failure work is queued for abnormal synchronous
+	 * errors, do a force kill.
+	 */
+	if (sync && !queued) {
+		dev_err(dev,
+			HW_ERR GHES_PFX "%s:%d: synchronous unrecoverable error (SIGBUS)\n",
+			current->comm, task_pid_nr(current));
+		force_sig(SIGBUS);
+	}
+}
+
+void __ghes_print_estatus(const char *pfx,
+			  const struct acpi_hest_generic *generic,
+			  const struct acpi_hest_generic_status *estatus)
+{
+	static atomic_t seqno;
+	unsigned int curr_seqno;
+	char pfx_seq[64];
+
+	if (pfx == NULL) {
+		if (ghes_severity(estatus->error_severity) <=
+		    GHES_SEV_CORRECTED)
+			pfx = KERN_WARNING;
+		else
+			pfx = KERN_ERR;
+	}
+	curr_seqno = atomic_inc_return(&seqno);
+	snprintf(pfx_seq, sizeof(pfx_seq), "%s{%u}" HW_ERR, pfx, curr_seqno);
+	printk("%s""Hardware error from APEI Generic Hardware Error Source: %d\n",
+	       pfx_seq, generic->header.source_id);
+	cper_estatus_print(pfx_seq, estatus);
+}
+
+int ghes_print_estatus(const char *pfx,
+		       const struct acpi_hest_generic *generic,
+		       const struct acpi_hest_generic_status *estatus)
+{
+	/* Not more than 2 messages every 5 seconds */
+	static DEFINE_RATELIMIT_STATE(ratelimit_corrected, 5*HZ, 2);
+	static DEFINE_RATELIMIT_STATE(ratelimit_uncorrected, 5*HZ, 2);
+	struct ratelimit_state *ratelimit;
+
+	if (ghes_severity(estatus->error_severity) <= GHES_SEV_CORRECTED)
+		ratelimit = &ratelimit_corrected;
+	else
+		ratelimit = &ratelimit_uncorrected;
+	if (__ratelimit(ratelimit)) {
+		__ghes_print_estatus(pfx, generic, estatus);
+		return 1;
+	}
+	return 0;
+}
+
+#ifdef CONFIG_ACPI_APEI
 static void __iomem *ghes_map(u64 pfn, enum fixed_addresses fixmap_idx)
 {
 	phys_addr_t paddr;
@@ -284,6 +783,7 @@ void ghes_clear_estatus(struct ghes *ghes,
 	if (is_hest_type_generic_v2(ghes))
 		ghes_ack_error(ghes->generic_v2);
 }
+#endif /* CONFIG_ACPI_APEI */
 
 static BLOCKING_NOTIFIER_HEAD(vendor_record_notify_list);
 
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index c4fd9c0b2a54..1448f4f725d4 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -1228,6 +1228,8 @@ static void aer_recover_work_func(struct work_struct *work)
 					   entry.domain, entry.bus,
 					   PCI_SLOT(entry.devfn),
 					   PCI_FUNC(entry.devfn));
+			ghes_estatus_pool_region_free((unsigned long)entry.regs,
+					      sizeof(struct aer_capability_regs));
 			continue;
 		}
 		pci_print_aer(pdev, entry.severity, entry.regs);
@@ -1274,9 +1276,12 @@ void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn,
 	if (kfifo_in_spinlocked(&aer_recover_ring, &entry, 1,
 				 &aer_recover_ring_lock))
 		schedule_work(&aer_recover_work);
-	else
-		pr_err("buffer overflow in recovery for %04x:%02x:%02x.%x\n",
+	else {
+		ghes_estatus_pool_region_free((unsigned long)aer_regs,
+					      sizeof(*aer_regs));
+		pr_err_ratelimited("buffer overflow in recovery for %04x:%02x:%02x.%x\n",
 		       domain, bus, PCI_SLOT(devfn), PCI_FUNC(devfn));
+	}
 }
 EXPORT_SYMBOL_GPL(aer_recover_queue);
 #endif
diff --git a/include/acpi/ghes_cper.h b/include/acpi/ghes_cper.h
index a853a5996cdf..e09a33d343d7 100644
--- a/include/acpi/ghes_cper.h
+++ b/include/acpi/ghes_cper.h
@@ -16,6 +16,8 @@
 #ifndef ACPI_APEI_GHES_CPER_H
 #define ACPI_APEI_GHES_CPER_H
 
+#include <linux/device.h>
+#include <linux/notifier.h>
 #include <linux/workqueue.h>
 
 #include <acpi/ghes.h>
@@ -57,6 +59,7 @@
 	((struct ghes_vendor_record_entry *)(vendor_entry) + 1))
 
 extern struct gen_pool *ghes_estatus_pool;
+extern struct atomic_notifier_head ghes_report_chain;
 
 static inline bool is_hest_type_generic_v2(struct ghes *ghes)
 {
@@ -107,6 +110,23 @@ void ghes_estatus_cache_add(struct acpi_hest_generic *generic,
 			    struct acpi_hest_generic_status *estatus);
 void ghes_defer_non_standard_event(struct acpi_hest_generic_data *gdata,
 				   int sev);
+int ghes_severity(int severity);
+bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
+				int sev, bool sync);
+bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata,
+			      int sev, bool sync);
+void ghes_handle_aer(struct acpi_hest_generic_data *gdata);
+void ghes_log_hwerr(int sev, guid_t *sec_type);
+void __ghes_print_estatus(const char *pfx,
+			  const struct acpi_hest_generic *generic,
+			  const struct acpi_hest_generic_status *estatus);
+int ghes_print_estatus(const char *pfx,
+		       const struct acpi_hest_generic *generic,
+		       const struct acpi_hest_generic_status *estatus);
+void ghes_cper_handle_status(struct device *dev,
+			     const struct acpi_hest_generic *generic,
+			     const struct acpi_hest_generic_status *estatus,
+			     bool sync);
 void cxl_cper_post_prot_err(struct cxl_cper_sec_prot_err *prot_err,
 			    int severity);
 int cxl_cper_register_prot_err_work(struct work_struct *work);

-- 
2.43.0

[PATCH v7 09/10] dt-bindings: firmware: add arm,ras-cper

[Ahmed Tiba]

Describe the DeviceTree node that exposes the Arm firmware-first CPER
provider and hook the file into MAINTAINERS so the binding has an
owner.

The initial user is the upstream zena-css platform, validated so far
on FVP.

Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: Ahmed Tiba <ahmed.tiba@arm.com>
---
 .../devicetree/bindings/firmware/arm,ras-cper.yaml | 52 ++++++++++++++++++++++
 MAINTAINERS                                        |  5 +++
 2 files changed, 57 insertions(+)

diff --git a/Documentation/devicetree/bindings/firmware/arm,ras-cper.yaml b/Documentation/devicetree/bindings/firmware/arm,ras-cper.yaml
new file mode 100644
index 000000000000..23d54008230d
--- /dev/null
+++ b/Documentation/devicetree/bindings/firmware/arm,ras-cper.yaml
@@ -0,0 +1,52 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/firmware/arm,ras-cper.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Arm RAS CPER provider
+
+maintainers:
+  - Ahmed Tiba <ahmed.tiba@arm.com>
+
+description:
+  Arm Reliability, Availability and Serviceability (RAS) firmware can expose
+  a firmware-first CPER error source directly via DeviceTree. Firmware
+  provides the CPER Generic Error Status block and notifies the OS through
+  an interrupt.
+
+properties:
+  compatible:
+    const: arm,ras-cper
+
+  memory-region:
+    items:
+      - description:
+          CPER Generic Error Status block exposed by firmware.
+      - description:
+          Firmware-owned ack buffer. Firmware watches bit 0 and expects the
+          OS to set it once the current status block has been consumed
+          before the CPER buffer is overwritten.
+
+  interrupts:
+    maxItems: 1
+    description:
+      Interrupt used to signal that a new status record is ready.
+
+required:
+  - compatible
+  - memory-region
+  - interrupts
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    error-handler {
+      compatible = "arm,ras-cper";
+      memory-region = <&ras_cper_buffer>, <&ras_cper_ack>;
+      interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>;
+    };
+...
diff --git a/MAINTAINERS b/MAINTAINERS
index f37a81950e25..951342f11e6e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -22521,6 +22521,11 @@ M:	Alexandre Bounine <alex.bou9@gmail.com>
 S:	Maintained
 F:	drivers/rapidio/
 
+RAS ERROR STATUS
+M:	Ahmed Tiba <ahmed.tiba@arm.com>
+S:	Maintained
+F:	Documentation/devicetree/bindings/firmware/arm,ras-cper.yaml
+
 RAS INFRASTRUCTURE
 M:	Tony Luck <tony.luck@intel.com>
 M:	Borislav Petkov <bp@alien8.de>

-- 
2.43.0

[PATCH v7 10/10] RAS: add firmware-first CPER provider

[Ahmed Tiba]

Add a firmware-first CPER provider that reuses the shared
GHES helpers, wire it into the RAS Kconfig/Makefile and
document it in the admin guide.

Update MAINTAINERS now that the driver exists.

Signed-off-by: Ahmed Tiba <ahmed.tiba@arm.com>
---
 Documentation/admin-guide/RAS/main.rst |  15 ++
 MAINTAINERS                            |   1 +
 drivers/acpi/apei/apei-internal.h      |   3 +-
 drivers/firmware/efi/cper.c            |   3 +-
 drivers/ras/Kconfig                    |  12 ++
 drivers/ras/Makefile                   |   1 +
 drivers/ras/cper-esource.c             | 332 +++++++++++++++++++++++++++++++++
 7 files changed, 364 insertions(+), 3 deletions(-)

diff --git a/Documentation/admin-guide/RAS/main.rst b/Documentation/admin-guide/RAS/main.rst
index 5a45db32c49b..d4e3c8c1b92f 100644
--- a/Documentation/admin-guide/RAS/main.rst
+++ b/Documentation/admin-guide/RAS/main.rst
@@ -205,6 +205,21 @@ Architecture (MCA)\ [#f3]_.
 .. [#f3] For more details about the Machine Check Architecture (MCA),
   please read Documentation/arch/x86/x86_64/machinecheck.rst at the Kernel tree.
 
+Firmware-first CPER providers
+-----------------------------
+
+Some systems expose Common Platform Error Record (CPER) data through
+platform firmware, with the error source described in DeviceTree.
+Enable ``CONFIG_RAS_CPER_ESOURCE`` to support those providers. The
+current in-tree binding is
+``Documentation/devicetree/bindings/firmware/arm,ras-cper.yaml``.
+
+The DeviceTree node describes the firmware-owned status buffer and ack
+buffer used to exchange CPER data with the OS. The driver reuses the
+shared GHES CPER handling helpers, so parsing, logging, notifier
+delivery, and memory failure handling follow the same paths as ACPI
+GHES whether the error source is described by ACPI or DeviceTree.
+
 EDAC - Error Detection And Correction
 *************************************
 
diff --git a/MAINTAINERS b/MAINTAINERS
index 951342f11e6e..3fa901cb884a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -22525,6 +22525,7 @@ RAS ERROR STATUS
 M:	Ahmed Tiba <ahmed.tiba@arm.com>
 S:	Maintained
 F:	Documentation/devicetree/bindings/firmware/arm,ras-cper.yaml
+F:	drivers/ras/cper-esource.c
 
 RAS INFRASTRUCTURE
 M:	Tony Luck <tony.luck@intel.com>
diff --git a/drivers/acpi/apei/apei-internal.h b/drivers/acpi/apei/apei-internal.h
index 77c10a7a7a9f..15d11f10d067 100644
--- a/drivers/acpi/apei/apei-internal.h
+++ b/drivers/acpi/apei/apei-internal.h
@@ -123,8 +123,7 @@ struct dentry *apei_get_debugfs_dir(void);
 static inline u32 cper_estatus_len(struct acpi_hest_generic_status *estatus)
 {
 	if (estatus->raw_data_length)
-		return estatus->raw_data_offset + \
-			estatus->raw_data_length;
+		return estatus->raw_data_offset + estatus->raw_data_length;
 	else
 		return sizeof(*estatus) + estatus->data_length;
 }
diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index 06b4fdb59917..a78e7d17a1b9 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -742,7 +742,8 @@ int cper_estatus_check_header(const struct acpi_hest_generic_status *estatus)
 	    estatus->data_length < sizeof(struct acpi_hest_generic_data))
 		return -EINVAL;
 	if (estatus->raw_data_length &&
-	    estatus->raw_data_offset < sizeof(*estatus) + estatus->data_length)
+	    (estatus->raw_data_offset < sizeof(*estatus) ||
+	     estatus->raw_data_offset - sizeof(*estatus) < estatus->data_length))
 		return -EINVAL;
 
 	return 0;
diff --git a/drivers/ras/Kconfig b/drivers/ras/Kconfig
index fc4f4bb94a4c..0592a98792f9 100644
--- a/drivers/ras/Kconfig
+++ b/drivers/ras/Kconfig
@@ -34,6 +34,18 @@ if RAS
 source "arch/x86/ras/Kconfig"
 source "drivers/ras/amd/atl/Kconfig"
 
+config RAS_CPER_ESOURCE
+	bool "Firmware-first CPER error source block provider"
+	select GHES_CPER_HELPERS
+	depends on OF_RESERVED_MEM
+	help
+	  Enable support for firmware-first Common Platform Error Record
+	  (CPER) error source block providers. The current in-tree user is
+	  described by the arm,ras-cper DeviceTree binding. The driver
+	  reuses the existing GHES CPER helpers so the error processing
+	  matches the ACPI code paths, but it can be built even when ACPI is
+	  disabled.
+
 config RAS_FMPM
 	tristate "FRU Memory Poison Manager"
 	default m
diff --git a/drivers/ras/Makefile b/drivers/ras/Makefile
index 11f95d59d397..0de069557f31 100644
--- a/drivers/ras/Makefile
+++ b/drivers/ras/Makefile
@@ -2,6 +2,7 @@
 obj-$(CONFIG_RAS)	+= ras.o
 obj-$(CONFIG_DEBUG_FS)	+= debugfs.o
 obj-$(CONFIG_RAS_CEC)	+= cec.o
+obj-$(CONFIG_RAS_CPER_ESOURCE)	+= cper-esource.o
 
 obj-$(CONFIG_RAS_FMPM)	+= amd/fmpm.o
 obj-y			+= amd/atl/
diff --git a/drivers/ras/cper-esource.c b/drivers/ras/cper-esource.c
new file mode 100644
index 000000000000..3f60c9849d9a
--- /dev/null
+++ b/drivers/ras/cper-esource.c
@@ -0,0 +1,332 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Firmware-first CPER error source provider.
+ *
+ * This driver shares the GHES CPER helpers so we keep the reporting and
+ * notifier behaviour identical to ACPI GHES.
+ *
+ * Copyright (C) 2026 ARM Ltd.
+ * Author: Ahmed Tiba <ahmed.tiba@arm.com>
+ */
+
+#include <linux/bitops.h>
+#include <linux/cper.h>
+#include <linux/idr.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/of_reserved_mem.h>
+#include <linux/panic.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#include <acpi/ghes.h>
+#include <acpi/ghes_cper.h>
+
+static DEFINE_IDA(cper_esource_source_ids);
+static DEFINE_MUTEX(cper_esource_pool_lock);
+static bool cper_esource_pool_ready;
+
+struct cper_esource_ack {
+	void *addr;
+	u64 preserve;
+	u64 set;
+	u8 width;
+	bool present;
+};
+
+struct cper_esource {
+	struct device *dev;
+	void *status;
+	size_t status_len;
+
+	struct cper_esource_ack ack;
+
+	struct acpi_hest_generic generic;
+	struct acpi_hest_generic_status *estatus;
+
+	int irq;
+};
+
+static void *cper_esource_map_region(struct device *dev, unsigned int index,
+				     size_t *size)
+{
+	struct resource res;
+	void *addr;
+
+	if (of_reserved_mem_region_to_resource(dev->of_node, index, &res))
+		return ERR_PTR(dev_err_probe(dev, -EINVAL,
+					     "unable to resolve memory-region %u\n",
+					     index));
+
+	*size = resource_size(&res);
+	if (!*size)
+		return ERR_PTR(dev_err_probe(dev, -EINVAL,
+					     "memory-region %u has zero length\n",
+					     index));
+
+	addr = devm_memremap(dev, res.start, *size, MEMREMAP_WB);
+	if (!addr)
+		return ERR_PTR(dev_err_probe(dev, -ENOMEM,
+					     "failed to map memory-region %u\n",
+					     index));
+
+	return addr;
+}
+
+static void cper_esource_release_source_id(void *data)
+{
+	struct cper_esource *ctx = data;
+
+	ida_free(&cper_esource_source_ids, ctx->generic.header.source_id);
+}
+
+static int cper_esource_init_pool(void)
+{
+	int rc = 0;
+
+	mutex_lock(&cper_esource_pool_lock);
+	if (!cper_esource_pool_ready) {
+		rc = ghes_estatus_pool_init(1);
+		if (!rc)
+			cper_esource_pool_ready = true;
+	}
+	mutex_unlock(&cper_esource_pool_lock);
+
+	return rc;
+}
+
+static size_t cper_esource_estatus_len(struct acpi_hest_generic_status *estatus)
+{
+	if (estatus->raw_data_length)
+		return (size_t)estatus->raw_data_offset +
+		       (size_t)estatus->raw_data_length;
+	else
+		return sizeof(*estatus) + (size_t)estatus->data_length;
+}
+
+static int cper_esource_validate_status(struct cper_esource *ctx)
+{
+	size_t estatus_len;
+
+	if (!ctx->estatus->block_status)
+		return -ENOENT;
+
+	if (ctx->estatus->data_length >
+	    ctx->status_len - sizeof(*ctx->estatus))
+		return -EINVAL;
+
+	if (cper_estatus_check_header(ctx->estatus))
+		return -EINVAL;
+
+	if (ctx->estatus->raw_data_length &&
+	    (ctx->estatus->raw_data_offset > ctx->status_len ||
+	     ctx->estatus->raw_data_length >
+	     ctx->status_len - ctx->estatus->raw_data_offset))
+		return -EINVAL;
+
+	estatus_len = cper_esource_estatus_len(ctx->estatus);
+	if (estatus_len < sizeof(*ctx->estatus) || estatus_len > ctx->status_len)
+		return -EINVAL;
+
+	if (cper_estatus_check(ctx->estatus))
+		return -EINVAL;
+
+	return 0;
+}
+
+static void cper_esource_ack(struct cper_esource *ctx)
+{
+	if (!ctx->ack.present)
+		return;
+
+	if (ctx->ack.width == 64) {
+		u64 *addr = ctx->ack.addr;
+		u64 val = READ_ONCE(*addr);
+
+		/* Publish status-buffer updates before raising the ack bit. */
+		wmb();
+		val &= ctx->ack.preserve;
+		val |= ctx->ack.set;
+		WRITE_ONCE(*addr, val);
+	} else {
+		u32 *addr = ctx->ack.addr;
+		u32 val = READ_ONCE(*addr);
+
+		/* Publish status-buffer updates before raising the ack bit. */
+		wmb();
+		val &= (u32)ctx->ack.preserve;
+		val |= (u32)ctx->ack.set;
+		WRITE_ONCE(*addr, val);
+	}
+}
+
+static void cper_esource_clear_status(struct cper_esource *ctx)
+{
+	ctx->estatus->block_status = 0;
+	WRITE_ONCE(((struct acpi_hest_generic_status *)ctx->status)->block_status, 0);
+}
+
+static void cper_esource_fatal(struct cper_esource *ctx)
+{
+	__ghes_print_estatus(KERN_EMERG, &ctx->generic, ctx->estatus);
+	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_STILL_OK);
+	panic("GHES: fatal firmware-first CPER record from %s\n",
+	      dev_name(ctx->dev));
+}
+
+static irqreturn_t cper_esource_process(struct cper_esource *ctx)
+{
+	int rc;
+	int sev;
+
+	memcpy(ctx->estatus, ctx->status, ctx->status_len);
+
+	rc = cper_esource_validate_status(ctx);
+	if (rc == -ENOENT)
+		return IRQ_NONE;
+	if (rc) {
+		dev_warn_ratelimited(ctx->dev, FW_WARN GHES_PFX
+				     "Invalid error status block\n");
+		cper_esource_clear_status(ctx);
+		cper_esource_ack(ctx);
+		return IRQ_HANDLED;
+	}
+
+	sev = ghes_severity(ctx->estatus->error_severity);
+	if (sev >= GHES_SEV_PANIC)
+		cper_esource_fatal(ctx);
+
+	ghes_print_estatus(NULL, &ctx->generic, ctx->estatus);
+
+	ghes_cper_handle_status(ctx->dev, &ctx->generic, ctx->estatus, false);
+	cper_esource_clear_status(ctx);
+	cper_esource_ack(ctx);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t cper_esource_irq(int irq, void *data)
+{
+	struct cper_esource *ctx = data;
+
+	return cper_esource_process(ctx);
+}
+
+static int cper_esource_init_ack(struct cper_esource *ctx)
+{
+	struct device *dev = ctx->dev;
+	size_t size;
+
+	ctx->ack.addr = cper_esource_map_region(dev, 1, &size);
+	if (IS_ERR(ctx->ack.addr))
+		return PTR_ERR(ctx->ack.addr);
+
+	switch (size) {
+	case 4:
+		ctx->ack.width = 32;
+		ctx->ack.preserve = ~0U;
+		break;
+	case 8:
+		ctx->ack.width = 64;
+		ctx->ack.preserve = ~0ULL;
+		break;
+	default:
+		return dev_err_probe(dev, -EINVAL,
+				     "unsupported ack resource size %zu\n", size);
+	}
+
+	ctx->ack.set = BIT_ULL(0);
+	ctx->ack.present = true;
+	return 0;
+}
+
+static int cper_esource_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct cper_esource *ctx;
+	size_t size;
+	int source_id;
+	int rc;
+
+	ctx = devm_kzalloc(dev, sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->dev = dev;
+
+	ctx->status = cper_esource_map_region(dev, 0, &size);
+	if (IS_ERR(ctx->status))
+		return PTR_ERR(ctx->status);
+
+	ctx->status_len = size;
+	if (ctx->status_len < sizeof(*ctx->estatus))
+		return dev_err_probe(dev, -EINVAL,
+				     "status region is smaller than a CPER header\n");
+
+	rc = cper_esource_init_ack(ctx);
+	if (rc)
+		return rc;
+
+	rc = cper_esource_init_pool();
+	if (rc)
+		return rc;
+
+	ctx->estatus = devm_kzalloc(dev, ctx->status_len, GFP_KERNEL);
+	if (!ctx->estatus)
+		return -ENOMEM;
+
+	/* Keep source_id 0 unused so a zeroed header is never treated as valid. */
+	source_id = ida_alloc_min(&cper_esource_source_ids, 1, GFP_KERNEL);
+	if (source_id < 0)
+		return source_id;
+	if (source_id > U16_MAX) {
+		ida_free(&cper_esource_source_ids, source_id);
+		return -ENOSPC;
+	}
+
+	ctx->generic.header.type = ACPI_HEST_TYPE_GENERIC_ERROR;
+	ctx->generic.header.source_id = source_id;
+
+	rc = devm_add_action_or_reset(dev, cper_esource_release_source_id,
+				      ctx);
+	if (rc)
+		return rc;
+
+	ctx->generic.notify.type = ACPI_HEST_NOTIFY_EXTERNAL;
+	ctx->generic.error_block_length = ctx->status_len;
+
+	ctx->irq = platform_get_irq(pdev, 0);
+	if (ctx->irq < 0)
+		return ctx->irq;
+
+	rc = devm_request_threaded_irq(dev, ctx->irq, NULL, cper_esource_irq,
+				       IRQF_ONESHOT,
+				       dev_name(dev), ctx);
+	if (rc)
+		return dev_err_probe(dev, rc, "failed to request interrupt\n");
+
+	return 0;
+}
+
+static const struct of_device_id cper_esource_of_match[] = {
+	{ .compatible = "arm,ras-cper" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, cper_esource_of_match);
+
+static struct platform_driver cper_esource_driver = {
+	.driver = {
+		.name = "cper-esource",
+		.of_match_table = cper_esource_of_match,
+	},
+	.probe = cper_esource_probe,
+};
+
+module_platform_driver(cper_esource_driver);
+
+MODULE_AUTHOR("Ahmed Tiba <ahmed.tiba@arm.com>");
+MODULE_DESCRIPTION("Firmware-first CPER provider");
+MODULE_LICENSE("GPL");

-- 
2.43.0

Re: [PATCH v7 10/10] RAS: add firmware-first CPER provider

[Uwe Kleine-König]

[-- Attachment #1: Type: text/plain, Size: 244 bytes --]

Hello Ahmed,

On Wed, Jul 08, 2026 at 02:59:09PM +0100, Ahmed Tiba wrote:
> +#include <linux/mod_devicetable.h>

Please don't add new users for this header file. Only use those
<linux/device-id/*.h> that you actually need (if any).

Thanks
Uwe

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]

Re: [PATCH v7 06/10] ACPI: APEI: GHES: move CXL CPER helpers

[Alison Schofield]

On Wed, Jul 08, 2026 at 02:59:05PM +0100, Ahmed Tiba wrote:
> Move the CXL CPER handling paths out of ghes.c and into ghes_cper.c so the
> helpers can be reused. The code is moved as-is, with the public
> prototypes updated so GHES keeps calling into the new translation unit.
> 
> While moving this code, also add CXL CPER section length checks and use
> spinlock_irqsave() in CXL register/unregister paths for locking
> consistency.

NAK on moving and changing in the same patch, and esp in a patch
whose subject only says MOVE.


> 
> Reviewed-by: Jonathan Cameron <jic23@kernel.org>
> Signed-off-by: Ahmed Tiba <ahmed.tiba@arm.com>
> ---
>  drivers/acpi/apei/ghes.c      | 180 +++++++++++-------------------------------
>  drivers/acpi/apei/ghes_cper.c | 135 +++++++++++++++++++++++++++++++
>  include/acpi/ghes_cper.h      |  11 +++
>  3 files changed, 194 insertions(+), 132 deletions(-)
> 
> diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
> index 07e4001ea8d7..2a83d326e692 100644
> --- a/drivers/acpi/apei/ghes.c
> +++ b/drivers/acpi/apei/ghes.c
> @@ -383,138 +383,6 @@ static void ghes_handle_aer(struct acpi_hest_generic_data *gdata)
>  #endif
>  }
>  
> -/* 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;
> -
> -	if (cxl_cper_sec_prot_err_valid(prot_err))
> -		return;
> -
> -	guard(spinlock_irqsave)(&cxl_cper_prot_err_work_lock);
> -
> -	if (!cxl_cper_prot_err_work)
> -		return;
> -
> -	if (cxl_cper_setup_prot_err_work_data(&wd, prot_err, severity))
> -		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);
> -
> -/* Synchronize schedule_work() with cxl_cper_work changes */
> -static DEFINE_SPINLOCK(cxl_cper_work_lock);
> -struct work_struct *cxl_cper_work;
> -
> -static void cxl_cper_post_event(enum cxl_event_type event_type,
> -				struct cxl_cper_event_rec *rec)
> -{
> -	struct cxl_cper_work_data wd;
> -
> -	if (rec->hdr.length <= sizeof(rec->hdr) ||
> -	    rec->hdr.length > sizeof(*rec)) {
> -		pr_err(FW_WARN "CXL CPER Invalid section length (%u)\n",
> -		       rec->hdr.length);
> -		return;
> -	}
> -
> -	if (!(rec->hdr.validation_bits & CPER_CXL_COMP_EVENT_LOG_VALID)) {
> -		pr_err(FW_WARN "CXL CPER invalid event\n");
> -		return;
> -	}
> -
> -	guard(spinlock_irqsave)(&cxl_cper_work_lock);
> -
> -	if (!cxl_cper_work)
> -		return;
> -
> -	wd.event_type = event_type;
> -	memcpy(&wd.rec, rec, sizeof(wd.rec));
> -
> -	if (!kfifo_put(&cxl_cper_fifo, wd)) {
> -		pr_err_ratelimited("CXL CPER kfifo overflow\n");
> -		return;
> -	}
> -
> -	schedule_work(cxl_cper_work);
> -}
> -
> -int cxl_cper_register_work(struct work_struct *work)
> -{
> -	if (cxl_cper_work)
> -		return -EINVAL;
> -
> -	guard(spinlock)(&cxl_cper_work_lock);
> -	cxl_cper_work = work;
> -	return 0;
> -}
> -EXPORT_SYMBOL_NS_GPL(cxl_cper_register_work, "CXL");
> -
> -int cxl_cper_unregister_work(struct work_struct *work)
> -{
> -	if (cxl_cper_work != work)
> -		return -EINVAL;
> -
> -	guard(spinlock)(&cxl_cper_work_lock);
> -	cxl_cper_work = NULL;
> -	return 0;
> -}
> -EXPORT_SYMBOL_NS_GPL(cxl_cper_unregister_work, "CXL");
> -
> -int cxl_cper_kfifo_get(struct cxl_cper_work_data *wd)
> -{
> -	return kfifo_get(&cxl_cper_fifo, wd);
> -}
> -EXPORT_SYMBOL_NS_GPL(cxl_cper_kfifo_get, "CXL");
> -
>  static void ghes_log_hwerr(int sev, guid_t *sec_type)
>  {
>  	if (sev != CPER_SEV_RECOVERABLE)
> @@ -549,6 +417,42 @@ static void ghes_log_hwerr(int sev, guid_t *sec_type)
>  	hwerr_log_error_type(HWERR_RECOV_OTHERS);
>  }
>  
> +static bool ghes_cxl_event_len_valid(struct acpi_hest_generic_data *gdata,
> +				     struct cxl_cper_event_rec *rec)
> +{
> +	if (gdata->error_data_length < sizeof(*rec) ||
> +	    rec->hdr.length <= sizeof(rec->hdr) ||
> +	    rec->hdr.length > gdata->error_data_length ||
> +	    rec->hdr.length > sizeof(*rec)) {
> +		pr_err(FW_WARN "CXL CPER Invalid section length (%u)\n",
> +		       rec->hdr.length);
> +		return false;
> +	}
> +
> +	return true;
> +}
> +
> +static bool ghes_cxl_prot_err_len_valid(struct acpi_hest_generic_data *gdata,
> +					struct cxl_cper_sec_prot_err *prot_err)
> +{
> +	if (gdata->error_data_length < sizeof(*prot_err) +
> +	    sizeof(struct cxl_ras_capability_regs)) {
> +		pr_err(FW_WARN "CXL CPER Invalid protocol error length (%u)\n",
> +		       gdata->error_data_length);
> +		return false;
> +	}
> +
> +	if (prot_err->dvsec_len >
> +	    gdata->error_data_length - sizeof(*prot_err) -
> +	    sizeof(struct cxl_ras_capability_regs)) {
> +		pr_err(FW_WARN "CXL CPER invalid DVSEC length (%u)\n",
> +		       prot_err->dvsec_len);
> +		return false;
> +	}
> +
> +	return true;
> +}
> +
>  static void ghes_do_proc(struct ghes *ghes,
>  			 const struct acpi_hest_generic_status *estatus)
>  {
> @@ -585,18 +489,30 @@ static void ghes_do_proc(struct ghes *ghes,
>  		} else if (guid_equal(sec_type, &CPER_SEC_CXL_PROT_ERR)) {
>  			struct cxl_cper_sec_prot_err *prot_err = acpi_hest_get_payload(gdata);
>  
> +			if (!ghes_cxl_prot_err_len_valid(gdata, prot_err))
> +				continue;
> +
>  			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);
>  
> +			if (!ghes_cxl_event_len_valid(gdata, rec))
> +				continue;
> +
>  			cxl_cper_post_event(CXL_CPER_EVENT_GEN_MEDIA, rec);
>  		} else if (guid_equal(sec_type, &CPER_SEC_CXL_DRAM_GUID)) {
>  			struct cxl_cper_event_rec *rec = acpi_hest_get_payload(gdata);
>  
> +			if (!ghes_cxl_event_len_valid(gdata, rec))
> +				continue;
> +
>  			cxl_cper_post_event(CXL_CPER_EVENT_DRAM, rec);
>  		} else if (guid_equal(sec_type, &CPER_SEC_CXL_MEM_MODULE_GUID)) {
>  			struct cxl_cper_event_rec *rec = acpi_hest_get_payload(gdata);
>  
> +			if (!ghes_cxl_event_len_valid(gdata, rec))
> +				continue;
> +
>  			cxl_cper_post_event(CXL_CPER_EVENT_MEM_MODULE, rec);
>  		} else {
>  			void *err = acpi_hest_get_payload(gdata);
> diff --git a/drivers/acpi/apei/ghes_cper.c b/drivers/acpi/apei/ghes_cper.c
> index 7e4a66b788b8..b59e3ed3eab3 100644
> --- a/drivers/acpi/apei/ghes_cper.c
> +++ b/drivers/acpi/apei/ghes_cper.c
> @@ -12,9 +12,12 @@
>   *   Author: Huang Ying <ying.huang@intel.com>
>   */
>  
> +#include <linux/aer.h>
> +#include <linux/cleanup.h>
>  #include <linux/err.h>
>  #include <linux/genalloc.h>
>  #include <linux/io.h>
> +#include <linux/kfifo.h>
>  #include <linux/kernel.h>
>  #include <linux/math64.h>
>  #include <linux/mm.h>
> @@ -350,6 +353,138 @@ 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;
> +
> +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;
> +
> +	if (cxl_cper_sec_prot_err_valid(prot_err))
> +		return;
> +
> +	guard(spinlock_irqsave)(&cxl_cper_prot_err_work_lock);
> +
> +	if (!cxl_cper_prot_err_work)
> +		return;
> +
> +	if (cxl_cper_setup_prot_err_work_data(&wd, prot_err, severity))
> +		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_irqsave)(&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_irqsave)(&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
> +static DEFINE_KFIFO(cxl_cper_fifo, struct cxl_cper_work_data, CXL_CPER_FIFO_DEPTH);
> +
> +/* Synchronize schedule_work() with cxl_cper_work changes */
> +static DEFINE_SPINLOCK(cxl_cper_work_lock);
> +struct work_struct *cxl_cper_work;
> +
> +void cxl_cper_post_event(enum cxl_event_type event_type,
> +			 struct cxl_cper_event_rec *rec)
> +{
> +	struct cxl_cper_work_data wd;
> +
> +	if (rec->hdr.length <= sizeof(rec->hdr) ||
> +	    rec->hdr.length > sizeof(*rec)) {
> +		pr_err(FW_WARN "CXL CPER Invalid section length (%u)\n",
> +		       rec->hdr.length);
> +		return;
> +	}
> +
> +	if (!(rec->hdr.validation_bits & CPER_CXL_COMP_EVENT_LOG_VALID)) {
> +		pr_err(FW_WARN "CXL CPER invalid event\n");
> +		return;
> +	}
> +
> +	guard(spinlock_irqsave)(&cxl_cper_work_lock);
> +
> +	if (!cxl_cper_work)
> +		return;
> +
> +	wd.event_type = event_type;
> +	memcpy(&wd.rec, rec, sizeof(wd.rec));
> +
> +	if (!kfifo_put(&cxl_cper_fifo, wd)) {
> +		pr_err_ratelimited("CXL CPER kfifo overflow\n");
> +		return;
> +	}
> +
> +	schedule_work(cxl_cper_work);
> +}
> +
> +int cxl_cper_register_work(struct work_struct *work)
> +{
> +	if (cxl_cper_work)
> +		return -EINVAL;
> +
> +	guard(spinlock_irqsave)(&cxl_cper_work_lock);
> +	cxl_cper_work = work;
> +	return 0;
> +}
> +EXPORT_SYMBOL_NS_GPL(cxl_cper_register_work, "CXL");
> +
> +int cxl_cper_unregister_work(struct work_struct *work)
> +{
> +	if (cxl_cper_work != work)
> +		return -EINVAL;
> +
> +	guard(spinlock_irqsave)(&cxl_cper_work_lock);
> +	cxl_cper_work = NULL;
> +	return 0;
> +}
> +EXPORT_SYMBOL_NS_GPL(cxl_cper_unregister_work, "CXL");
> +
> +int cxl_cper_kfifo_get(struct cxl_cper_work_data *wd)
> +{
> +	return kfifo_get(&cxl_cper_fifo, wd);
> +}
> +EXPORT_SYMBOL_NS_GPL(cxl_cper_kfifo_get, "CXL");
> +
>  /*
>   * GHES error status reporting throttle, to report more kinds of
>   * errors, instead of just most frequently occurred errors.
> diff --git a/include/acpi/ghes_cper.h b/include/acpi/ghes_cper.h
> index d9f9253d8de9..a853a5996cdf 100644
> --- a/include/acpi/ghes_cper.h
> +++ b/include/acpi/ghes_cper.h
> @@ -20,6 +20,7 @@
>  
>  #include <acpi/ghes.h>
>  #include <asm/fixmap.h>
> +#include <cxl/event.h>
>  
>  #define GHES_PFX	"GHES: "
>  
> @@ -106,5 +107,15 @@ void ghes_estatus_cache_add(struct acpi_hest_generic *generic,
>  			    struct acpi_hest_generic_status *estatus);
>  void ghes_defer_non_standard_event(struct acpi_hest_generic_data *gdata,
>  				   int sev);
> +void cxl_cper_post_prot_err(struct cxl_cper_sec_prot_err *prot_err,
> +			    int severity);
> +int cxl_cper_register_prot_err_work(struct work_struct *work);
> +int cxl_cper_unregister_prot_err_work(struct work_struct *work);
> +int cxl_cper_prot_err_kfifo_get(struct cxl_cper_prot_err_work_data *wd);
> +void cxl_cper_post_event(enum cxl_event_type event_type,
> +			 struct cxl_cper_event_rec *rec);
> +int cxl_cper_register_work(struct work_struct *work);
> +int cxl_cper_unregister_work(struct work_struct *work);
> +int cxl_cper_kfifo_get(struct cxl_cper_work_data *wd);
>  
>  #endif /* ACPI_APEI_GHES_CPER_H */
> 
> -- 
> 2.43.0
>