Merge branch 'acpi-apei'

* acpi-apei: (29 commits)
  efi: cper: Fix possible out-of-bounds access
  ACPI: APEI: Fix possible out-of-bounds access to BERT region
  MAINTAINERS: Add James Morse to the list of APEI reviewers
  ACPI / APEI: Add support for the SDEI GHES Notification type
  firmware: arm_sdei: Add ACPI GHES registration helper
  ACPI / APEI: Use separate fixmap pages for arm64 NMI-like notifications
  ACPI / APEI: Only use queued estatus entry during in_nmi_queue_one_entry()
  ACPI / APEI: Split ghes_read_estatus() to allow a peek at the CPER length
  ACPI / APEI: Make GHES estatus header validation more user friendly
  ACPI / APEI: Pass ghes and estatus separately to avoid a later copy
  ACPI / APEI: Let the notification helper specify the fixmap slot
  ACPI / APEI: Move locking to the notification helper
  arm64: KVM/mm: Move SEA handling behind a single 'claim' interface
  KVM: arm/arm64: Add kvm_ras.h to collect kvm specific RAS plumbing
  ACPI / APEI: Switch NOTIFY_SEA to use the estatus queue
  ACPI / APEI: Move NOTIFY_SEA between the estatus-queue and NOTIFY_NMI
  ACPI / APEI: Don't allow ghes_ack_error() to mask earlier errors
  ACPI / APEI: Generalise the estatus queue's notify code
  ACPI / APEI: Don't update struct ghes' flags in read/clear estatus
  ACPI / APEI: Remove spurious GHES_TO_CLEAR check
  ...

drivers/acpi/apei/Kconfig

@@ -41,19 +41,9 @@ config ACPI_APEI_PCIEAER
 	  Turn on this option to enable the corresponding support.
 
 config ACPI_APEI_SEA
-	bool "APEI Synchronous External Abort logging/recovering support"
+	bool
 	depends on ARM64 && ACPI_APEI_GHES
 	default y
-	help
-	  This option should be enabled if the system supports
-	  firmware first handling of SEA (Synchronous External Abort).
-	  SEA happens with certain faults of data abort or instruction
-	  abort synchronous exceptions on ARMv8 systems. If a system
-	  supports firmware first handling of SEA, the platform analyzes
-	  and handles hardware error notifications from SEA, and it may then
-	  form a HW error record for the OS to parse and handle. This
-	  option allows the OS to look for such hardware error record, and
-	  take appropriate action.
 
 config ACPI_APEI_MEMORY_FAILURE
 	bool "APEI memory error recovering support"

drivers/acpi/apei/bert.c

@@ -42,15 +42,7 @@ static void __init bert_print_all(struct acpi_bert_region *region,
 	int remain = region_len;
 	u32 estatus_len;
 
-	if (!estatus->block_status)
-		return;
-
-	while (remain > sizeof(struct acpi_bert_region)) {
-		if (cper_estatus_check(estatus)) {
-			pr_err(FW_BUG "Invalid error record.\n");
-			return;
-		}
-
+	while (remain >= sizeof(struct acpi_bert_region)) {
 		estatus_len = cper_estatus_len(estatus);
 		if (remain < estatus_len) {
 			pr_err(FW_BUG "Truncated status block (length: %u).\n",
@@ -58,6 +50,15 @@ static void __init bert_print_all(struct acpi_bert_region *region,
 			return;
 		}
 
+		/* No more error records. */
+		if (!estatus->block_status)
+			return;
+
+		if (cper_estatus_check(estatus)) {
+			pr_err(FW_BUG "Invalid error record.\n");
+			return;
+		}
+
 		pr_info_once("Error records from previous boot:\n");
 
 		cper_estatus_print(KERN_INFO HW_ERR, estatus);
@@ -70,10 +71,6 @@ static void __init bert_print_all(struct acpi_bert_region *region,
 		estatus->block_status = 0;
 
 		estatus = (void *)estatus + estatus_len;
-		/* No more error records. */
-		if (!estatus->block_status)
-			return;
-
 		remain -= estatus_len;
 	}
 }

drivers/acpi/apei/einj.c

@@ -644,8 +644,8 @@ static int error_type_set(void *data, u64 val)
 	return 0;
 }
 
-DEFINE_SIMPLE_ATTRIBUTE(error_type_fops, error_type_get,
-			error_type_set, "0x%llx\n");
+DEFINE_DEBUGFS_ATTRIBUTE(error_type_fops, error_type_get, error_type_set,
+			 "0x%llx\n");
 
 static int error_inject_set(void *data, u64 val)
 {
@@ -656,8 +656,7 @@ static int error_inject_set(void *data, u64 val)
 		error_param3, error_param4);
 }
 
-DEFINE_SIMPLE_ATTRIBUTE(error_inject_fops, NULL,
-			error_inject_set, "%llu\n");
+DEFINE_DEBUGFS_ATTRIBUTE(error_inject_fops, NULL, error_inject_set, "%llu\n");
 
 static int einj_check_table(struct acpi_table_einj *einj_tab)
 {
@@ -709,10 +708,10 @@ static int __init einj_init(void)
 
 	debugfs_create_file("available_error_type", S_IRUSR, einj_debug_dir,
 			    NULL, &available_error_type_fops);
-	debugfs_create_file("error_type", S_IRUSR | S_IWUSR, einj_debug_dir,
-			    NULL, &error_type_fops);
-	debugfs_create_file("error_inject", S_IWUSR, einj_debug_dir,
-			    NULL, &error_inject_fops);
+	debugfs_create_file_unsafe("error_type", 0600, einj_debug_dir,
+				   NULL, &error_type_fops);
+	debugfs_create_file_unsafe("error_inject", 0200, einj_debug_dir,
+				   NULL, &error_inject_fops);
 
 	apei_resources_init(&einj_resources);
 	einj_exec_ctx_init(&ctx);

drivers/acpi/apei/erst.c

@@ -938,17 +938,17 @@ static struct pstore_info erst_info = {
 };
 
 #define CPER_CREATOR_PSTORE						\
-	UUID_LE(0x75a574e3, 0x5052, 0x4b29, 0x8a, 0x8e, 0xbe, 0x2c,	\
-		0x64, 0x90, 0xb8, 0x9d)
+	GUID_INIT(0x75a574e3, 0x5052, 0x4b29, 0x8a, 0x8e, 0xbe, 0x2c,	\
+		  0x64, 0x90, 0xb8, 0x9d)
 #define CPER_SECTION_TYPE_DMESG						\
-	UUID_LE(0xc197e04e, 0xd545, 0x4a70, 0x9c, 0x17, 0xa5, 0x54,	\
-		0x94, 0x19, 0xeb, 0x12)
+	GUID_INIT(0xc197e04e, 0xd545, 0x4a70, 0x9c, 0x17, 0xa5, 0x54,	\
+		  0x94, 0x19, 0xeb, 0x12)
 #define CPER_SECTION_TYPE_DMESG_Z					\
-	UUID_LE(0x4f118707, 0x04dd, 0x4055, 0xb5, 0xdd, 0x95, 0x6d,	\
-		0x34, 0xdd, 0xfa, 0xc6)
+	GUID_INIT(0x4f118707, 0x04dd, 0x4055, 0xb5, 0xdd, 0x95, 0x6d,	\
+		  0x34, 0xdd, 0xfa, 0xc6)
 #define CPER_SECTION_TYPE_MCE						\
-	UUID_LE(0xfe08ffbe, 0x95e4, 0x4be7, 0xbc, 0x73, 0x40, 0x96,	\
-		0x04, 0x4a, 0x38, 0xfc)
+	GUID_INIT(0xfe08ffbe, 0x95e4, 0x4be7, 0xbc, 0x73, 0x40, 0x96,	\
+		  0x04, 0x4a, 0x38, 0xfc)
 
 struct cper_pstore_record {
 	struct cper_record_header hdr;
@@ -1012,7 +1012,7 @@ skip:
 		rc = -EIO;
 		goto out;
 	}
-	if (uuid_le_cmp(rcd->hdr.creator_id, CPER_CREATOR_PSTORE) != 0)
+	if (!guid_equal(&rcd->hdr.creator_id, &CPER_CREATOR_PSTORE))
 		goto skip;
 
 	record->buf = kmalloc(len, GFP_KERNEL);
@@ -1024,15 +1024,12 @@ skip:
 	record->id = record_id;
 	record->compressed = false;
 	record->ecc_notice_size = 0;
-	if (uuid_le_cmp(rcd->sec_hdr.section_type,
-			CPER_SECTION_TYPE_DMESG_Z) == 0) {
+	if (guid_equal(&rcd->sec_hdr.section_type, &CPER_SECTION_TYPE_DMESG_Z)) {
 		record->type = PSTORE_TYPE_DMESG;
 		record->compressed = true;
-	} else if (uuid_le_cmp(rcd->sec_hdr.section_type,
-			CPER_SECTION_TYPE_DMESG) == 0)
+	} else if (guid_equal(&rcd->sec_hdr.section_type, &CPER_SECTION_TYPE_DMESG))
 		record->type = PSTORE_TYPE_DMESG;
-	else if (uuid_le_cmp(rcd->sec_hdr.section_type,
-			     CPER_SECTION_TYPE_MCE) == 0)
+	else if (guid_equal(&rcd->sec_hdr.section_type, &CPER_SECTION_TYPE_MCE))
 		record->type = PSTORE_TYPE_MCE;
 	else
 		record->type = PSTORE_TYPE_MAX;

drivers/acpi/apei/ghes.c

@@ -25,6 +25,7 @@
  * GNU General Public License for more details.
  */
 
+#include <linux/arm_sdei.h>
 #include <linux/kernel.h>
 #include <linux/moduleparam.h>
 #include <linux/init.h>
@@ -33,7 +34,6 @@
 #include <linux/interrupt.h>
 #include <linux/timer.h>
 #include <linux/cper.h>
-#include <linux/kdebug.h>
 #include <linux/platform_device.h>
 #include <linux/mutex.h>
 #include <linux/ratelimit.h>
@@ -42,6 +42,7 @@
 #include <linux/llist.h>
 #include <linux/genalloc.h>
 #include <linux/pci.h>
+#include <linux/pfn.h>
 #include <linux/aer.h>
 #include <linux/nmi.h>
 #include <linux/sched/clock.h>
@@ -85,6 +86,15 @@
 	((struct acpi_hest_generic_status *)				\
 	 ((struct ghes_estatus_node *)(estatus_node) + 1))
 
+/*
+ *  NMI-like notifications vary by architecture, before the compiler can prune
+ *  unused static functions it needs a value for these enums.
+ */
+#ifndef CONFIG_ARM_SDE_INTERFACE
+#define FIX_APEI_GHES_SDEI_NORMAL	__end_of_fixed_addresses
+#define FIX_APEI_GHES_SDEI_CRITICAL	__end_of_fixed_addresses
+#endif
+
 static inline bool is_hest_type_generic_v2(struct ghes *ghes)
 {
 	return ghes->generic->header.type == ACPI_HEST_TYPE_GENERIC_ERROR_V2;
@@ -115,11 +125,10 @@ static DEFINE_MUTEX(ghes_list_mutex);
  * handler, but general ioremap can not be used in atomic context, so
  * the fixmap is used instead.
  *
- * These 2 spinlocks are used to prevent the fixmap entries from being used
+ * This spinlock is used to prevent the fixmap entry from being used
  * simultaneously.
  */
-static DEFINE_RAW_SPINLOCK(ghes_ioremap_lock_nmi);
-static DEFINE_SPINLOCK(ghes_ioremap_lock_irq);
+static DEFINE_SPINLOCK(ghes_notify_lock_irq);
 
 static struct gen_pool *ghes_estatus_pool;
 static unsigned long ghes_estatus_pool_size_request;
@@ -129,82 +138,49 @@ static atomic_t ghes_estatus_cache_alloced;
 
 static int ghes_panic_timeout __read_mostly = 30;
 
-static void __iomem *ghes_ioremap_pfn_nmi(u64 pfn)
+static void __iomem *ghes_map(u64 pfn, enum fixed_addresses fixmap_idx)
 {
 	phys_addr_t paddr;
 	pgprot_t prot;
 
-	paddr = pfn << PAGE_SHIFT;
+	paddr = PFN_PHYS(pfn);
 	prot = arch_apei_get_mem_attribute(paddr);
-	__set_fixmap(FIX_APEI_GHES_NMI, paddr, prot);
+	__set_fixmap(fixmap_idx, paddr, prot);
 
-	return (void __iomem *) fix_to_virt(FIX_APEI_GHES_NMI);
+	return (void __iomem *) __fix_to_virt(fixmap_idx);
 }
 
-static void __iomem *ghes_ioremap_pfn_irq(u64 pfn)
+static void ghes_unmap(void __iomem *vaddr, enum fixed_addresses fixmap_idx)
 {
-	phys_addr_t paddr;
-	pgprot_t prot;
+	int _idx = virt_to_fix((unsigned long)vaddr);
 
-	paddr = pfn << PAGE_SHIFT;
-	prot = arch_apei_get_mem_attribute(paddr);
-	__set_fixmap(FIX_APEI_GHES_IRQ, paddr, prot);
-
-	return (void __iomem *) fix_to_virt(FIX_APEI_GHES_IRQ);
+	WARN_ON_ONCE(fixmap_idx != _idx);
+	clear_fixmap(fixmap_idx);
 }
 
-static void ghes_iounmap_nmi(void)
+int ghes_estatus_pool_init(int num_ghes)
 {
-	clear_fixmap(FIX_APEI_GHES_NMI);
-}
+	unsigned long addr, len;
 
-static void ghes_iounmap_irq(void)
-{
-	clear_fixmap(FIX_APEI_GHES_IRQ);
-}
-
-static int ghes_estatus_pool_init(void)
-{
 	ghes_estatus_pool = gen_pool_create(GHES_ESTATUS_POOL_MIN_ALLOC_ORDER, -1);
 	if (!ghes_estatus_pool)
 		return -ENOMEM;
-	return 0;
-}
 
-static void ghes_estatus_pool_free_chunk_page(struct gen_pool *pool,
-					      struct gen_pool_chunk *chunk,
-					      void *data)
-{
-	free_page(chunk->start_addr);
-}
+	len = GHES_ESTATUS_CACHE_AVG_SIZE * GHES_ESTATUS_CACHE_ALLOCED_MAX;
+	len += (num_ghes * GHES_ESOURCE_PREALLOC_MAX_SIZE);
 
-static void ghes_estatus_pool_exit(void)
-{
-	gen_pool_for_each_chunk(ghes_estatus_pool,
-				ghes_estatus_pool_free_chunk_page, NULL);
-	gen_pool_destroy(ghes_estatus_pool);
-}
+	ghes_estatus_pool_size_request = PAGE_ALIGN(len);
+	addr = (unsigned long)vmalloc(PAGE_ALIGN(len));
+	if (!addr)
+		return -ENOMEM;
 
-static int ghes_estatus_pool_expand(unsigned long len)
-{
-	unsigned long i, pages, size, addr;
-	int ret;
+	/*
+	 * New allocation must be visible in all pgd before it can be found by
+	 * an NMI allocating from the pool.
+	 */
+	vmalloc_sync_all();
 
-	ghes_estatus_pool_size_request += PAGE_ALIGN(len);
-	size = gen_pool_size(ghes_estatus_pool);
-	if (size >= ghes_estatus_pool_size_request)
-		return 0;
-	pages = (ghes_estatus_pool_size_request - size) / PAGE_SIZE;
-	for (i = 0; i < pages; i++) {
-		addr = __get_free_page(GFP_KERNEL);
-		if (!addr)
-			return -ENOMEM;
-		ret = gen_pool_add(ghes_estatus_pool, addr, PAGE_SIZE, -1);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
+	return gen_pool_add(ghes_estatus_pool, addr, PAGE_ALIGN(len), -1);
 }
 
 static int map_gen_v2(struct ghes *ghes)
@@ -217,6 +193,21 @@ 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);
+}
+
 static struct ghes *ghes_new(struct acpi_hest_generic *generic)
 {
 	struct ghes *ghes;
@@ -289,23 +280,16 @@ static inline int ghes_severity(int severity)
 }
 
 static void ghes_copy_tofrom_phys(void *buffer, u64 paddr, u32 len,
-				  int from_phys)
+				  int from_phys,
+				  enum fixed_addresses fixmap_idx)
 {
 	void __iomem *vaddr;
-	unsigned long flags = 0;
-	int in_nmi = in_nmi();
 	u64 offset;
 	u32 trunk;
 
 	while (len > 0) {
 		offset = paddr - (paddr & PAGE_MASK);
-		if (in_nmi) {
-			raw_spin_lock(&ghes_ioremap_lock_nmi);
-			vaddr = ghes_ioremap_pfn_nmi(paddr >> PAGE_SHIFT);
-		} else {
-			spin_lock_irqsave(&ghes_ioremap_lock_irq, flags);
-			vaddr = ghes_ioremap_pfn_irq(paddr >> PAGE_SHIFT);
-		}
+		vaddr = ghes_map(PHYS_PFN(paddr), fixmap_idx);
 		trunk = PAGE_SIZE - offset;
 		trunk = min(trunk, len);
 		if (from_phys)
@@ -315,72 +299,114 @@ static void ghes_copy_tofrom_phys(void *buffer, u64 paddr, u32 len,
 		len -= trunk;
 		paddr += trunk;
 		buffer += trunk;
-		if (in_nmi) {
-			ghes_iounmap_nmi();
-			raw_spin_unlock(&ghes_ioremap_lock_nmi);
-		} else {
-			ghes_iounmap_irq();
-			spin_unlock_irqrestore(&ghes_ioremap_lock_irq, flags);
-		}
+		ghes_unmap(vaddr, fixmap_idx);
 	}
 }
 
-static int ghes_read_estatus(struct ghes *ghes, int silent)
+/* Check the top-level record header has an appropriate size. */
+static int __ghes_check_estatus(struct ghes *ghes,
+				struct acpi_hest_generic_status *estatus)
+{
+	u32 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 > ghes->generic->error_block_length) {
+		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. */
+static 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;
-	u64 buf_paddr;
-	u32 len;
 	int rc;
 
-	rc = apei_read(&buf_paddr, &g->error_status_address);
+	rc = apei_read(buf_paddr, &g->error_status_address);
 	if (rc) {
-		if (!silent && printk_ratelimit())
-			pr_warning(FW_WARN GHES_PFX
+		*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)
+	if (!*buf_paddr)
 		return -ENOENT;
 
-	ghes_copy_tofrom_phys(ghes->estatus, buf_paddr,
-			      sizeof(*ghes->estatus), 1);
-	if (!ghes->estatus->block_status)
+	ghes_copy_tofrom_phys(estatus, *buf_paddr, sizeof(*estatus), 1,
+			      fixmap_idx);
+	if (!estatus->block_status) {
+		*buf_paddr = 0;
 		return -ENOENT;
+	}
 
-	ghes->buffer_paddr = buf_paddr;
-	ghes->flags |= GHES_TO_CLEAR;
-
-	rc = -EIO;
-	len = cper_estatus_len(ghes->estatus);
-	if (len < sizeof(*ghes->estatus))
-		goto err_read_block;
-	if (len > ghes->generic->error_block_length)
-		goto err_read_block;
-	if (cper_estatus_check_header(ghes->estatus))
-		goto err_read_block;
-	ghes_copy_tofrom_phys(ghes->estatus + 1,
-			      buf_paddr + sizeof(*ghes->estatus),
-			      len - sizeof(*ghes->estatus), 1);
-	if (cper_estatus_check(ghes->estatus))
-		goto err_read_block;
-	rc = 0;
-
-err_read_block:
-	if (rc && !silent && printk_ratelimit())
-		pr_warning(FW_WARN GHES_PFX
-			   "Failed to read error status block!\n");
-	return rc;
+	return __ghes_check_estatus(ghes, estatus);
 }
 
-static void ghes_clear_estatus(struct ghes *ghes)
+static int __ghes_read_estatus(struct acpi_hest_generic_status *estatus,
+			       u64 buf_paddr, enum fixed_addresses fixmap_idx,
+			       size_t buf_len)
 {
-	ghes->estatus->block_status = 0;
-	if (!(ghes->flags & GHES_TO_CLEAR))
+	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;
+}
+
+static 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));
+}
+
+static 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(ghes->estatus, ghes->buffer_paddr,
-			      sizeof(ghes->estatus->block_status), 0);
-	ghes->flags &= ~GHES_TO_CLEAR;
+
+	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);
 }
 
 static void ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, int sev)
@@ -672,26 +698,13 @@ static void ghes_estatus_cache_add(
 	rcu_read_unlock();
 }
 
-static int ghes_ack_error(struct acpi_hest_generic_v2 *gv2)
+static void __ghes_panic(struct ghes *ghes,
+			 struct acpi_hest_generic_status *estatus,
+			 u64 buf_paddr, enum fixed_addresses fixmap_idx)
 {
-	int rc;
-	u64 val = 0;
+	__ghes_print_estatus(KERN_EMERG, ghes->generic, estatus);
 
-	rc = apei_read(&val, &gv2->read_ack_register);
-	if (rc)
-		return rc;
-
-	val &= gv2->read_ack_preserve << gv2->read_ack_register.bit_offset;
-	val |= gv2->read_ack_write    << gv2->read_ack_register.bit_offset;
-
-	return apei_write(val, &gv2->read_ack_register);
-}
-
-static void __ghes_panic(struct ghes *ghes)
-{
-	__ghes_print_estatus(KERN_EMERG, ghes->generic, ghes->estatus);
-
-	ghes_clear_estatus(ghes);
+	ghes_clear_estatus(ghes, estatus, buf_paddr, fixmap_idx);
 
 	/* reboot to log the error! */
 	if (!panic_timeout)
@@ -701,34 +714,25 @@ static void __ghes_panic(struct ghes *ghes)
 
 static int ghes_proc(struct ghes *ghes)
 {
+	struct acpi_hest_generic_status *estatus = ghes->estatus;
+	u64 buf_paddr;
 	int rc;
 
-	rc = ghes_read_estatus(ghes, 0);
+	rc = ghes_read_estatus(ghes, estatus, &buf_paddr, FIX_APEI_GHES_IRQ);
 	if (rc)
 		goto out;
 
-	if (ghes_severity(ghes->estatus->error_severity) >= GHES_SEV_PANIC) {
-		__ghes_panic(ghes);
-	}
+	if (ghes_severity(estatus->error_severity) >= GHES_SEV_PANIC)
+		__ghes_panic(ghes, estatus, buf_paddr, FIX_APEI_GHES_IRQ);
 
-	if (!ghes_estatus_cached(ghes->estatus)) {
-		if (ghes_print_estatus(NULL, ghes->generic, ghes->estatus))
-			ghes_estatus_cache_add(ghes->generic, ghes->estatus);
+	if (!ghes_estatus_cached(estatus)) {
+		if (ghes_print_estatus(NULL, ghes->generic, estatus))
+			ghes_estatus_cache_add(ghes->generic, estatus);
 	}
-	ghes_do_proc(ghes, ghes->estatus);
+	ghes_do_proc(ghes, estatus);
 
 out:
-	ghes_clear_estatus(ghes);
-
-	if (rc == -ENOENT)
-		return rc;
-
-	/*
-	 * 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))
-		return ghes_ack_error(ghes->generic_v2);
+	ghes_clear_estatus(ghes, estatus, buf_paddr, FIX_APEI_GHES_IRQ);
 
 	return rc;
 }
@@ -751,8 +755,11 @@ static void ghes_add_timer(struct ghes *ghes)
 static void ghes_poll_func(struct timer_list *t)
 {
 	struct ghes *ghes = from_timer(ghes, t, timer);
+	unsigned long flags;
 
+	spin_lock_irqsave(&ghes_notify_lock_irq, flags);
 	ghes_proc(ghes);
+	spin_unlock_irqrestore(&ghes_notify_lock_irq, flags);
 	if (!(ghes->flags & GHES_EXITING))
 		ghes_add_timer(ghes);
 }
@@ -760,9 +767,12 @@ static void ghes_poll_func(struct timer_list *t)
 static irqreturn_t ghes_irq_func(int irq, void *data)
 {
 	struct ghes *ghes = data;
+	unsigned long flags;
 	int rc;
 
+	spin_lock_irqsave(&ghes_notify_lock_irq, flags);
 	rc = ghes_proc(ghes);
+	spin_unlock_irqrestore(&ghes_notify_lock_irq, flags);
 	if (rc)
 		return IRQ_NONE;
 
@@ -773,14 +783,17 @@ static int ghes_notify_hed(struct notifier_block *this, unsigned long event,
 			   void *data)
 {
 	struct ghes *ghes;
+	unsigned long flags;
 	int ret = NOTIFY_DONE;
 
+	spin_lock_irqsave(&ghes_notify_lock_irq, flags);
 	rcu_read_lock();
 	list_for_each_entry_rcu(ghes, &ghes_hed, list) {
 		if (!ghes_proc(ghes))
 			ret = NOTIFY_OK;
 	}
 	rcu_read_unlock();
+	spin_unlock_irqrestore(&ghes_notify_lock_irq, flags);
 
 	return ret;
 }
@@ -789,66 +802,20 @@ static struct notifier_block ghes_notifier_hed = {
 	.notifier_call = ghes_notify_hed,
 };
 
-#ifdef CONFIG_ACPI_APEI_SEA
-static LIST_HEAD(ghes_sea);
-
 /*
- * Return 0 only if one of the SEA error sources successfully reported an error
- * record sent from the firmware.
- */
-int ghes_notify_sea(void)
-{
-	struct ghes *ghes;
-	int ret = -ENOENT;
-
-	rcu_read_lock();
-	list_for_each_entry_rcu(ghes, &ghes_sea, list) {
-		if (!ghes_proc(ghes))
-			ret = 0;
-	}
-	rcu_read_unlock();
-	return ret;
-}
-
-static void ghes_sea_add(struct ghes *ghes)
-{
-	mutex_lock(&ghes_list_mutex);
-	list_add_rcu(&ghes->list, &ghes_sea);
-	mutex_unlock(&ghes_list_mutex);
-}
-
-static void ghes_sea_remove(struct ghes *ghes)
-{
-	mutex_lock(&ghes_list_mutex);
-	list_del_rcu(&ghes->list);
-	mutex_unlock(&ghes_list_mutex);
-	synchronize_rcu();
-}
-#else /* CONFIG_ACPI_APEI_SEA */
-static inline void ghes_sea_add(struct ghes *ghes) { }
-static inline void ghes_sea_remove(struct ghes *ghes) { }
-#endif /* CONFIG_ACPI_APEI_SEA */
-
-#ifdef CONFIG_HAVE_ACPI_APEI_NMI
-/*
- * printk is not safe in NMI context.  So in NMI handler, we allocate
- * required memory from lock-less memory allocator
- * (ghes_estatus_pool), save estatus into it, put them into lock-less
- * list (ghes_estatus_llist), then delay printk into IRQ context via
- * irq_work (ghes_proc_irq_work).  ghes_estatus_size_request record
- * required pool size by all NMI error source.
+ * Handlers for CPER records may not be NMI safe. For example,
+ * memory_failure_queue() takes spinlocks and calls schedule_work_on().
+ * In any NMI-like handler, memory from ghes_estatus_pool is used to save
+ * estatus, and added to the ghes_estatus_llist. irq_work_queue() causes
+ * ghes_proc_in_irq() to run in IRQ context where each estatus in
+ * ghes_estatus_llist is processed.
+ *
+ * Memory from the ghes_estatus_pool is also used with the ghes_estatus_cache
+ * to suppress frequent messages.
  */
 static struct llist_head ghes_estatus_llist;
 static struct irq_work ghes_proc_irq_work;
 
-/*
- * NMI may be triggered on any CPU, so ghes_in_nmi is used for
- * having only one concurrent reader.
- */
-static atomic_t ghes_in_nmi = ATOMIC_INIT(0);
-
-static LIST_HEAD(ghes_nmi);
-
 static void ghes_proc_in_irq(struct irq_work *irq_work)
 {
 	struct llist_node *llnode, *next;
@@ -905,96 +872,154 @@ static void ghes_print_queued_estatus(void)
 	}
 }
 
-/* Save estatus for further processing in IRQ context */
-static void __process_error(struct ghes *ghes)
+static int ghes_in_nmi_queue_one_entry(struct ghes *ghes,
+				       enum fixed_addresses fixmap_idx)
 {
-#ifdef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
-	u32 len, node_len;
+	struct acpi_hest_generic_status *estatus, tmp_header;
 	struct ghes_estatus_node *estatus_node;
-	struct acpi_hest_generic_status *estatus;
+	u32 len, node_len;
+	u64 buf_paddr;
+	int sev, rc;
 
-	if (ghes_estatus_cached(ghes->estatus))
-		return;
+	if (!IS_ENABLED(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG))
+		return -EOPNOTSUPP;
 
-	len = cper_estatus_len(ghes->estatus);
+	rc = __ghes_peek_estatus(ghes, &tmp_header, &buf_paddr, fixmap_idx);
+	if (rc) {
+		ghes_clear_estatus(ghes, &tmp_header, buf_paddr, fixmap_idx);
+		return rc;
+	}
+
+	rc = __ghes_check_estatus(ghes, &tmp_header);
+	if (rc) {
+		ghes_clear_estatus(ghes, &tmp_header, buf_paddr, fixmap_idx);
+		return rc;
+	}
+
+	len = cper_estatus_len(&tmp_header);
 	node_len = GHES_ESTATUS_NODE_LEN(len);
-
 	estatus_node = (void *)gen_pool_alloc(ghes_estatus_pool, node_len);
 	if (!estatus_node)
-		return;
+		return -ENOMEM;
 
 	estatus_node->ghes = ghes;
 	estatus_node->generic = ghes->generic;
 	estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
-	memcpy(estatus, ghes->estatus, len);
+
+	if (__ghes_read_estatus(estatus, buf_paddr, fixmap_idx, len)) {
+		ghes_clear_estatus(ghes, estatus, buf_paddr, fixmap_idx);
+		rc = -ENOENT;
+		goto no_work;
+	}
+
+	sev = ghes_severity(estatus->error_severity);
+	if (sev >= GHES_SEV_PANIC) {
+		ghes_print_queued_estatus();
+		__ghes_panic(ghes, estatus, buf_paddr, fixmap_idx);
+	}
+
+	ghes_clear_estatus(ghes, &tmp_header, buf_paddr, fixmap_idx);
+
+	/* This error has been reported before, don't process it again. */
+	if (ghes_estatus_cached(estatus))
+		goto no_work;
+
 	llist_add(&estatus_node->llnode, &ghes_estatus_llist);
-#endif
+
+	return rc;
+
+no_work:
+	gen_pool_free(ghes_estatus_pool, (unsigned long)estatus_node,
+		      node_len);
+
+	return rc;
 }
 
+static int ghes_in_nmi_spool_from_list(struct list_head *rcu_list,
+				       enum fixed_addresses fixmap_idx)
+{
+	int ret = -ENOENT;
+	struct ghes *ghes;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(ghes, rcu_list, list) {
+		if (!ghes_in_nmi_queue_one_entry(ghes, fixmap_idx))
+			ret = 0;
+	}
+	rcu_read_unlock();
+
+	if (IS_ENABLED(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG) && !ret)
+		irq_work_queue(&ghes_proc_irq_work);
+
+	return ret;
+}
+
+#ifdef CONFIG_ACPI_APEI_SEA
+static LIST_HEAD(ghes_sea);
+
+/*
+ * Return 0 only if one of the SEA error sources successfully reported an error
+ * record sent from the firmware.
+ */
+int ghes_notify_sea(void)
+{
+	static DEFINE_RAW_SPINLOCK(ghes_notify_lock_sea);
+	int rv;
+
+	raw_spin_lock(&ghes_notify_lock_sea);
+	rv = ghes_in_nmi_spool_from_list(&ghes_sea, FIX_APEI_GHES_SEA);
+	raw_spin_unlock(&ghes_notify_lock_sea);
+
+	return rv;
+}
+
+static void ghes_sea_add(struct ghes *ghes)
+{
+	mutex_lock(&ghes_list_mutex);
+	list_add_rcu(&ghes->list, &ghes_sea);
+	mutex_unlock(&ghes_list_mutex);
+}
+
+static void ghes_sea_remove(struct ghes *ghes)
+{
+	mutex_lock(&ghes_list_mutex);
+	list_del_rcu(&ghes->list);
+	mutex_unlock(&ghes_list_mutex);
+	synchronize_rcu();
+}
+#else /* CONFIG_ACPI_APEI_SEA */
+static inline void ghes_sea_add(struct ghes *ghes) { }
+static inline void ghes_sea_remove(struct ghes *ghes) { }
+#endif /* CONFIG_ACPI_APEI_SEA */
+
+#ifdef CONFIG_HAVE_ACPI_APEI_NMI
+/*
+ * NMI may be triggered on any CPU, so ghes_in_nmi is used for
+ * having only one concurrent reader.
+ */
+static atomic_t ghes_in_nmi = ATOMIC_INIT(0);
+
+static LIST_HEAD(ghes_nmi);
+
 static int ghes_notify_nmi(unsigned int cmd, struct pt_regs *regs)
 {
-	struct ghes *ghes;
-	int sev, ret = NMI_DONE;
+	static DEFINE_RAW_SPINLOCK(ghes_notify_lock_nmi);
+	int ret = NMI_DONE;
 
 	if (!atomic_add_unless(&ghes_in_nmi, 1, 1))
 		return ret;
 
-	list_for_each_entry_rcu(ghes, &ghes_nmi, list) {
-		if (ghes_read_estatus(ghes, 1)) {
-			ghes_clear_estatus(ghes);
-			continue;
-		} else {
-			ret = NMI_HANDLED;
-		}
+	raw_spin_lock(&ghes_notify_lock_nmi);
+	if (!ghes_in_nmi_spool_from_list(&ghes_nmi, FIX_APEI_GHES_NMI))
+		ret = NMI_HANDLED;
+	raw_spin_unlock(&ghes_notify_lock_nmi);
 
-		sev = ghes_severity(ghes->estatus->error_severity);
-		if (sev >= GHES_SEV_PANIC) {
-			oops_begin();
-			ghes_print_queued_estatus();
-			__ghes_panic(ghes);
-		}
-
-		if (!(ghes->flags & GHES_TO_CLEAR))
-			continue;
-
-		__process_error(ghes);
-		ghes_clear_estatus(ghes);
-	}
-
-#ifdef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
-	if (ret == NMI_HANDLED)
-		irq_work_queue(&ghes_proc_irq_work);
-#endif
 	atomic_dec(&ghes_in_nmi);
 	return ret;
 }
 
-static unsigned long ghes_esource_prealloc_size(
-	const struct acpi_hest_generic *generic)
-{
-	unsigned long block_length, prealloc_records, prealloc_size;
-
-	block_length = min_t(unsigned long, generic->error_block_length,
-			     GHES_ESTATUS_MAX_SIZE);
-	prealloc_records = max_t(unsigned long,
-				 generic->records_to_preallocate, 1);
-	prealloc_size = min_t(unsigned long, block_length * prealloc_records,
-			      GHES_ESOURCE_PREALLOC_MAX_SIZE);
-
-	return prealloc_size;
-}
-
-static void ghes_estatus_pool_shrink(unsigned long len)
-{
-	ghes_estatus_pool_size_request -= PAGE_ALIGN(len);
-}
-
 static void ghes_nmi_add(struct ghes *ghes)
 {
-	unsigned long len;
-
-	len = ghes_esource_prealloc_size(ghes->generic);
-	ghes_estatus_pool_expand(len);
 	mutex_lock(&ghes_list_mutex);
 	if (list_empty(&ghes_nmi))
 		register_nmi_handler(NMI_LOCAL, ghes_notify_nmi, 0, "ghes");
@@ -1004,8 +1029,6 @@ static void ghes_nmi_add(struct ghes *ghes)
 
 static void ghes_nmi_remove(struct ghes *ghes)
 {
-	unsigned long len;
-
 	mutex_lock(&ghes_list_mutex);
 	list_del_rcu(&ghes->list);
 	if (list_empty(&ghes_nmi))
@@ -1016,24 +1039,79 @@ static void ghes_nmi_remove(struct ghes *ghes)
 	 * freed after NMI handler finishes.
 	 */
 	synchronize_rcu();
-	len = ghes_esource_prealloc_size(ghes->generic);
-	ghes_estatus_pool_shrink(len);
 }
+#else /* CONFIG_HAVE_ACPI_APEI_NMI */
+static inline void ghes_nmi_add(struct ghes *ghes) { }
+static inline void ghes_nmi_remove(struct ghes *ghes) { }
+#endif /* CONFIG_HAVE_ACPI_APEI_NMI */
 
 static void ghes_nmi_init_cxt(void)
 {
 	init_irq_work(&ghes_proc_irq_work, ghes_proc_in_irq);
 }
-#else /* CONFIG_HAVE_ACPI_APEI_NMI */
-static inline void ghes_nmi_add(struct ghes *ghes) { }
-static inline void ghes_nmi_remove(struct ghes *ghes) { }
-static inline void ghes_nmi_init_cxt(void) { }
-#endif /* CONFIG_HAVE_ACPI_APEI_NMI */
+
+static int __ghes_sdei_callback(struct ghes *ghes,
+				enum fixed_addresses fixmap_idx)
+{
+	if (!ghes_in_nmi_queue_one_entry(ghes, fixmap_idx)) {
+		irq_work_queue(&ghes_proc_irq_work);
+
+		return 0;
+	}
+
+	return -ENOENT;
+}
+
+static int ghes_sdei_normal_callback(u32 event_num, struct pt_regs *regs,
+				      void *arg)
+{
+	static DEFINE_RAW_SPINLOCK(ghes_notify_lock_sdei_normal);
+	struct ghes *ghes = arg;
+	int err;
+
+	raw_spin_lock(&ghes_notify_lock_sdei_normal);
+	err = __ghes_sdei_callback(ghes, FIX_APEI_GHES_SDEI_NORMAL);
+	raw_spin_unlock(&ghes_notify_lock_sdei_normal);
+
+	return err;
+}
+
+static int ghes_sdei_critical_callback(u32 event_num, struct pt_regs *regs,
+				       void *arg)
+{
+	static DEFINE_RAW_SPINLOCK(ghes_notify_lock_sdei_critical);
+	struct ghes *ghes = arg;
+	int err;
+
+	raw_spin_lock(&ghes_notify_lock_sdei_critical);
+	err = __ghes_sdei_callback(ghes, FIX_APEI_GHES_SDEI_CRITICAL);
+	raw_spin_unlock(&ghes_notify_lock_sdei_critical);
+
+	return err;
+}
+
+static int apei_sdei_register_ghes(struct ghes *ghes)
+{
+	if (!IS_ENABLED(CONFIG_ARM_SDE_INTERFACE))
+		return -EOPNOTSUPP;
+
+	return sdei_register_ghes(ghes, ghes_sdei_normal_callback,
+				 ghes_sdei_critical_callback);
+}
+
+static int apei_sdei_unregister_ghes(struct ghes *ghes)
+{
+	if (!IS_ENABLED(CONFIG_ARM_SDE_INTERFACE))
+		return -EOPNOTSUPP;
+
+	return sdei_unregister_ghes(ghes);
+}
 
 static int ghes_probe(struct platform_device *ghes_dev)
 {
 	struct acpi_hest_generic *generic;
 	struct ghes *ghes = NULL;
+	unsigned long flags;
 
 	int rc = -EINVAL;
 
@@ -1064,6 +1142,13 @@ static int ghes_probe(struct platform_device *ghes_dev)
 			goto err;
 		}
 		break;
+	case ACPI_HEST_NOTIFY_SOFTWARE_DELEGATED:
+		if (!IS_ENABLED(CONFIG_ARM_SDE_INTERFACE)) {
+			pr_warn(GHES_PFX "Generic hardware error source: %d notified via SDE Interface is not supported!\n",
+				generic->header.source_id);
+			goto err;
+		}
+		break;
 	case ACPI_HEST_NOTIFY_LOCAL:
 		pr_warning(GHES_PFX "Generic hardware error source: %d notified via local interrupt is not supported!\n",
 			   generic->header.source_id);
@@ -1127,6 +1212,11 @@ static int ghes_probe(struct platform_device *ghes_dev)
 	case ACPI_HEST_NOTIFY_NMI:
 		ghes_nmi_add(ghes);
 		break;
+	case ACPI_HEST_NOTIFY_SOFTWARE_DELEGATED:
+		rc = apei_sdei_register_ghes(ghes);
+		if (rc)
+			goto err;
+		break;
 	default:
 		BUG();
 	}
@@ -1136,7 +1226,9 @@ static int ghes_probe(struct platform_device *ghes_dev)
 	ghes_edac_register(ghes, &ghes_dev->dev);
 
 	/* Handle any pending errors right away */
+	spin_lock_irqsave(&ghes_notify_lock_irq, flags);
 	ghes_proc(ghes);
+	spin_unlock_irqrestore(&ghes_notify_lock_irq, flags);
 
 	return 0;
 
@@ -1150,6 +1242,7 @@ err:
 
 static int ghes_remove(struct platform_device *ghes_dev)
 {
+	int rc;
 	struct ghes *ghes;
 	struct acpi_hest_generic *generic;
 
@@ -1182,6 +1275,11 @@ static int ghes_remove(struct platform_device *ghes_dev)
 	case ACPI_HEST_NOTIFY_NMI:
 		ghes_nmi_remove(ghes);
 		break;
+	case ACPI_HEST_NOTIFY_SOFTWARE_DELEGATED:
+		rc = apei_sdei_unregister_ghes(ghes);
+		if (rc)
+			return rc;
+		break;
 	default:
 		BUG();
 		break;
@@ -1230,18 +1328,9 @@ static int __init ghes_init(void)
 
 	ghes_nmi_init_cxt();
 
-	rc = ghes_estatus_pool_init();
-	if (rc)
-		goto err;
-
-	rc = ghes_estatus_pool_expand(GHES_ESTATUS_CACHE_AVG_SIZE *
-				      GHES_ESTATUS_CACHE_ALLOCED_MAX);
-	if (rc)
-		goto err_pool_exit;
-
 	rc = platform_driver_register(&ghes_platform_driver);
 	if (rc)
-		goto err_pool_exit;
+		goto err;
 
 	rc = apei_osc_setup();
 	if (rc == 0 && osc_sb_apei_support_acked)
@@ -1254,8 +1343,6 @@ static int __init ghes_init(void)
 		pr_info(GHES_PFX "Failed to enable APEI firmware first mode.\n");
 
 	return 0;
-err_pool_exit:
-	ghes_estatus_pool_exit();
 err:
 	return rc;
 }

drivers/acpi/apei/hest.c

@@ -32,6 +32,7 @@
 #include <linux/io.h>
 #include <linux/platform_device.h>
 #include <acpi/apei.h>
+#include <acpi/ghes.h>
 
 #include "apei-internal.h"
 
@@ -53,6 +54,7 @@ static const int hest_esrc_len_tab[ACPI_HEST_TYPE_RESERVED] = {
 	[ACPI_HEST_TYPE_AER_BRIDGE] = sizeof(struct acpi_hest_aer_bridge),
 	[ACPI_HEST_TYPE_GENERIC_ERROR] = sizeof(struct acpi_hest_generic),
 	[ACPI_HEST_TYPE_GENERIC_ERROR_V2] = sizeof(struct acpi_hest_generic_v2),
+	[ACPI_HEST_TYPE_IA32_DEFERRED_CHECK] = -1,
 };
 
 static int hest_esrc_len(struct acpi_hest_header *hest_hdr)
@@ -75,6 +77,11 @@ static int hest_esrc_len(struct acpi_hest_header *hest_hdr)
 		mc = (struct acpi_hest_ia_machine_check *)hest_hdr;
 		len = sizeof(*mc) + mc->num_hardware_banks *
 			sizeof(struct acpi_hest_ia_error_bank);
+	} else if (hest_type == ACPI_HEST_TYPE_IA32_DEFERRED_CHECK) {
+		struct acpi_hest_ia_deferred_check *mc;
+		mc = (struct acpi_hest_ia_deferred_check *)hest_hdr;
+		len = sizeof(*mc) + mc->num_hardware_banks *
+			sizeof(struct acpi_hest_ia_error_bank);
 	}
 	BUG_ON(len == -1);
 
@@ -203,6 +210,11 @@ static int __init hest_ghes_dev_register(unsigned int ghes_count)
 	rc = apei_hest_parse(hest_parse_ghes, &ghes_arr);
 	if (rc)
 		goto err;
+
+	rc = ghes_estatus_pool_init(ghes_count);
+	if (rc)
+		goto err;
+
 out:
 	kfree(ghes_arr.ghes_devs);
 	return rc;
@@ -251,7 +263,9 @@ void __init acpi_hest_init(void)
 		rc = apei_hest_parse(hest_parse_ghes_count, &ghes_count);
 		if (rc)
 			goto err;
-		rc = hest_ghes_dev_register(ghes_count);
+
+		if (ghes_count)
+			rc = hest_ghes_dev_register(ghes_count);
 		if (rc)
 			goto err;
 	}