Merge branch 'apei-release' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux-acpi-2.6

* 'apei-release' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux-acpi-2.6:
  ACPI, APEI, EINJ Param support is disabled by default
  APEI GHES: 32-bit buildfix
  ACPI: APEI build fix
  ACPI, APEI, GHES: Add hardware memory error recovery support
  HWPoison: add memory_failure_queue()
  ACPI, APEI, GHES, Error records content based throttle
  ACPI, APEI, GHES, printk support for recoverable error via NMI
  lib, Make gen_pool memory allocator lockless
  lib, Add lock-less NULL terminated single list
  Add Kconfig option ARCH_HAVE_NMI_SAFE_CMPXCHG
  ACPI, APEI, Add WHEA _OSC support
  ACPI, APEI, Add APEI bit support in generic _OSC call
  ACPI, APEI, GHES, Support disable GHES at boot time
  ACPI, APEI, GHES, Prevent GHES to be built as module
  ACPI, APEI, Use apei_exec_run_optional in APEI EINJ and ERST
  ACPI, APEI, Add apei_exec_run_optional
  ACPI, APEI, GHES, Do not ratelimit fatal error printk before panic
  ACPI, APEI, ERST, Fix erst-dbg long record reading issue
  ACPI, APEI, ERST, Prevent erst_dbg from loading if ERST is disabled

9 files changed, 516 insertions, 68 deletions

diff --git a/drivers/acpi/apei/Kconfig b/drivers/acpi/apei/Kconfig
index f739a70b1c7..c34aa51af4e 100644
--- a/drivers/acpi/apei/Kconfig
+++ b/drivers/acpi/apei/Kconfig
@@ -10,9 +10,11 @@ config ACPI_APEI
 	  error injection.
 
 config ACPI_APEI_GHES
-	tristate "APEI Generic Hardware Error Source"
+	bool "APEI Generic Hardware Error Source"
 	depends on ACPI_APEI && X86
 	select ACPI_HED
+	select LLIST
+	select GENERIC_ALLOCATOR
 	help
 	  Generic Hardware Error Source provides a way to report
 	  platform hardware errors (such as that from chipset). It
@@ -30,6 +32,13 @@ config ACPI_APEI_PCIEAER
 	  PCIe AER errors may be reported via APEI firmware first mode.
 	  Turn on this option to enable the corresponding support.
 
+config ACPI_APEI_MEMORY_FAILURE
+	bool "APEI memory error recovering support"
+	depends on ACPI_APEI && MEMORY_FAILURE
+	help
+	  Memory errors may be reported via APEI firmware first mode.
+	  Turn on this option to enable the memory recovering support.
+
 config ACPI_APEI_EINJ
 	tristate "APEI Error INJection (EINJ)"
 	depends on ACPI_APEI && DEBUG_FS
diff --git a/drivers/acpi/apei/apei-base.c b/drivers/acpi/apei/apei-base.c
index 4a904a4bf05..8041248fce9 100644
--- a/drivers/acpi/apei/apei-base.c
+++ b/drivers/acpi/apei/apei-base.c
@@ -157,9 +157,10 @@ EXPORT_SYMBOL_GPL(apei_exec_noop);
  * Interpret the specified action. Go through whole action table,
  * execute all instructions belong to the action.
  */
-int apei_exec_run(struct apei_exec_context *ctx, u8 action)
+int __apei_exec_run(struct apei_exec_context *ctx, u8 action,
+		    bool optional)
 {
-	int rc;
+	int rc = -ENOENT;
 	u32 i, ip;
 	struct acpi_whea_header *entry;
 	apei_exec_ins_func_t run;
@@ -198,9 +199,9 @@ rewind:
 			goto rewind;
 	}
 
-	return 0;
+	return !optional && rc < 0 ? rc : 0;
 }
-EXPORT_SYMBOL_GPL(apei_exec_run);
+EXPORT_SYMBOL_GPL(__apei_exec_run);
 
 typedef int (*apei_exec_entry_func_t)(struct apei_exec_context *ctx,
 				      struct acpi_whea_header *entry,
@@ -603,3 +604,29 @@ struct dentry *apei_get_debugfs_dir(void)
 	return dapei;
 }
 EXPORT_SYMBOL_GPL(apei_get_debugfs_dir);
+
+int apei_osc_setup(void)
+{
+	static u8 whea_uuid_str[] = "ed855e0c-6c90-47bf-a62a-26de0fc5ad5c";
+	acpi_handle handle;
+	u32 capbuf[3];
+	struct acpi_osc_context context = {
+		.uuid_str	= whea_uuid_str,
+		.rev		= 1,
+		.cap.length	= sizeof(capbuf),
+		.cap.pointer	= capbuf,
+	};
+
+	capbuf[OSC_QUERY_TYPE] = OSC_QUERY_ENABLE;
+	capbuf[OSC_SUPPORT_TYPE] = 0;
+	capbuf[OSC_CONTROL_TYPE] = 0;
+
+	if (ACPI_FAILURE(acpi_get_handle(NULL, "\\_SB", &handle))
+	    || ACPI_FAILURE(acpi_run_osc(handle, &context)))
+		return -EIO;
+	else {
+		kfree(context.ret.pointer);
+		return 0;
+	}
+}
+EXPORT_SYMBOL_GPL(apei_osc_setup);
diff --git a/drivers/acpi/apei/apei-internal.h b/drivers/acpi/apei/apei-internal.h
index ef0581f2094..f57050e7a5e 100644
--- a/drivers/acpi/apei/apei-internal.h
+++ b/drivers/acpi/apei/apei-internal.h
@@ -50,7 +50,18 @@ static inline u64 apei_exec_ctx_get_output(struct apei_exec_context *ctx)
 	return ctx->value;
 }
 
-int apei_exec_run(struct apei_exec_context *ctx, u8 action);
+int __apei_exec_run(struct apei_exec_context *ctx, u8 action, bool optional);
+
+static inline int apei_exec_run(struct apei_exec_context *ctx, u8 action)
+{
+	return __apei_exec_run(ctx, action, 0);
+}
+
+/* It is optional whether the firmware provides the action */
+static inline int apei_exec_run_optional(struct apei_exec_context *ctx, u8 action)
+{
+	return __apei_exec_run(ctx, action, 1);
+}
 
 /* Common instruction implementation */
 
@@ -113,4 +124,6 @@ void apei_estatus_print(const char *pfx,
 			const struct acpi_hest_generic_status *estatus);
 int apei_estatus_check_header(const struct acpi_hest_generic_status *estatus);
 int apei_estatus_check(const struct acpi_hest_generic_status *estatus);
+
+int apei_osc_setup(void);
 #endif
diff --git a/drivers/acpi/apei/einj.c b/drivers/acpi/apei/einj.c
index f74b2ea11f2..589b96c3870 100644
--- a/drivers/acpi/apei/einj.c
+++ b/drivers/acpi/apei/einj.c
@@ -46,7 +46,8 @@
  * Some BIOSes allow parameters to the SET_ERROR_TYPE entries in the
  * EINJ table through an unpublished extension. Use with caution as
  * most will ignore the parameter and make their own choice of address
- * for error injection.
+ * for error injection.  This extension is used only if
+ * param_extension module parameter is specified.
  */
 struct einj_parameter {
 	u64 type;
@@ -65,6 +66,9 @@ struct einj_parameter {
 	((struct acpi_whea_header *)((char *)(tab) +			\
 				    sizeof(struct acpi_table_einj)))
 
+static bool param_extension;
+module_param(param_extension, bool, 0);
+
 static struct acpi_table_einj *einj_tab;
 
 static struct apei_resources einj_resources;
@@ -285,7 +289,7 @@ static int __einj_error_inject(u32 type, u64 param1, u64 param2)
 
 	einj_exec_ctx_init(&ctx);
 
-	rc = apei_exec_run(&ctx, ACPI_EINJ_BEGIN_OPERATION);
+	rc = apei_exec_run_optional(&ctx, ACPI_EINJ_BEGIN_OPERATION);
 	if (rc)
 		return rc;
 	apei_exec_ctx_set_input(&ctx, type);
@@ -323,7 +327,7 @@ static int __einj_error_inject(u32 type, u64 param1, u64 param2)
 	rc = __einj_error_trigger(trigger_paddr);
 	if (rc)
 		return rc;
-	rc = apei_exec_run(&ctx, ACPI_EINJ_END_OPERATION);
+	rc = apei_exec_run_optional(&ctx, ACPI_EINJ_END_OPERATION);
 
 	return rc;
 }
@@ -489,14 +493,6 @@ static int __init einj_init(void)
 				     einj_debug_dir, NULL, &error_type_fops);
 	if (!fentry)
 		goto err_cleanup;
-	fentry = debugfs_create_x64("param1", S_IRUSR | S_IWUSR,
-				    einj_debug_dir, &error_param1);
-	if (!fentry)
-		goto err_cleanup;
-	fentry = debugfs_create_x64("param2", S_IRUSR | S_IWUSR,
-				    einj_debug_dir, &error_param2);
-	if (!fentry)
-		goto err_cleanup;
 	fentry = debugfs_create_file("error_inject", S_IWUSR,
 				     einj_debug_dir, NULL, &error_inject_fops);
 	if (!fentry)
@@ -513,12 +509,23 @@ static int __init einj_init(void)
 	rc = apei_exec_pre_map_gars(&ctx);
 	if (rc)
 		goto err_release;
-	param_paddr = einj_get_parameter_address();
-	if (param_paddr) {
-		einj_param = ioremap(param_paddr, sizeof(*einj_param));
-		rc = -ENOMEM;
-		if (!einj_param)
-			goto err_unmap;
+	if (param_extension) {
+		param_paddr = einj_get_parameter_address();
+		if (param_paddr) {
+			einj_param = ioremap(param_paddr, sizeof(*einj_param));
+			rc = -ENOMEM;
+			if (!einj_param)
+				goto err_unmap;
+			fentry = debugfs_create_x64("param1", S_IRUSR | S_IWUSR,
+						    einj_debug_dir, &error_param1);
+			if (!fentry)
+				goto err_unmap;
+			fentry = debugfs_create_x64("param2", S_IRUSR | S_IWUSR,
+						    einj_debug_dir, &error_param2);
+			if (!fentry)
+				goto err_unmap;
+		} else
+			pr_warn(EINJ_PFX "Parameter extension is not supported.\n");
 	}
 
 	pr_info(EINJ_PFX "Error INJection is initialized.\n");
@@ -526,6 +533,8 @@ static int __init einj_init(void)
 	return 0;
 
 err_unmap:
+	if (einj_param)
+		iounmap(einj_param);
 	apei_exec_post_unmap_gars(&ctx);
 err_release:
 	apei_resources_release(&einj_resources);
diff --git a/drivers/acpi/apei/erst-dbg.c b/drivers/acpi/apei/erst-dbg.c
index a4cfb64c86a..903549df809 100644
--- a/drivers/acpi/apei/erst-dbg.c
+++ b/drivers/acpi/apei/erst-dbg.c
@@ -33,7 +33,7 @@
 
 #define ERST_DBG_PFX			"ERST DBG: "
 
-#define ERST_DBG_RECORD_LEN_MAX		4096
+#define ERST_DBG_RECORD_LEN_MAX		0x4000
 
 static void *erst_dbg_buf;
 static unsigned int erst_dbg_buf_len;
@@ -213,6 +213,10 @@ static struct miscdevice erst_dbg_dev = {
 
 static __init int erst_dbg_init(void)
 {
+	if (erst_disable) {
+		pr_info(ERST_DBG_PFX "ERST support is disabled.\n");
+		return -ENODEV;
+	}
 	return misc_register(&erst_dbg_dev);
 }
 
diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c
index 6053f4780df..2ca59dc69f7 100644
--- a/drivers/acpi/apei/erst.c
+++ b/drivers/acpi/apei/erst.c
@@ -642,7 +642,7 @@ static int __erst_write_to_storage(u64 offset)
 	int rc;
 
 	erst_exec_ctx_init(&ctx);
-	rc = apei_exec_run(&ctx, ACPI_ERST_BEGIN_WRITE);
+	rc = apei_exec_run_optional(&ctx, ACPI_ERST_BEGIN_WRITE);
 	if (rc)
 		return rc;
 	apei_exec_ctx_set_input(&ctx, offset);
@@ -666,7 +666,7 @@ static int __erst_write_to_storage(u64 offset)
 	if (rc)
 		return rc;
 	val = apei_exec_ctx_get_output(&ctx);
-	rc = apei_exec_run(&ctx, ACPI_ERST_END);
+	rc = apei_exec_run_optional(&ctx, ACPI_ERST_END);
 	if (rc)
 		return rc;
 
@@ -681,7 +681,7 @@ static int __erst_read_from_storage(u64 record_id, u64 offset)
 	int rc;
 
 	erst_exec_ctx_init(&ctx);
-	rc = apei_exec_run(&ctx, ACPI_ERST_BEGIN_READ);
+	rc = apei_exec_run_optional(&ctx, ACPI_ERST_BEGIN_READ);
 	if (rc)
 		return rc;
 	apei_exec_ctx_set_input(&ctx, offset);
@@ -709,7 +709,7 @@ static int __erst_read_from_storage(u64 record_id, u64 offset)
 	if (rc)
 		return rc;
 	val = apei_exec_ctx_get_output(&ctx);
-	rc = apei_exec_run(&ctx, ACPI_ERST_END);
+	rc = apei_exec_run_optional(&ctx, ACPI_ERST_END);
 	if (rc)
 		return rc;
 
@@ -724,7 +724,7 @@ static int __erst_clear_from_storage(u64 record_id)
 	int rc;
 
 	erst_exec_ctx_init(&ctx);
-	rc = apei_exec_run(&ctx, ACPI_ERST_BEGIN_CLEAR);
+	rc = apei_exec_run_optional(&ctx, ACPI_ERST_BEGIN_CLEAR);
 	if (rc)
 		return rc;
 	apei_exec_ctx_set_input(&ctx, record_id);
@@ -748,7 +748,7 @@ static int __erst_clear_from_storage(u64 record_id)
 	if (rc)
 		return rc;
 	val = apei_exec_ctx_get_output(&ctx);
-	rc = apei_exec_run(&ctx, ACPI_ERST_END);
+	rc = apei_exec_run_optional(&ctx, ACPI_ERST_END);
 	if (rc)
 		return rc;
 
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index f703b288115..0784f99a466 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -12,7 +12,7 @@
  * For more information about Generic Hardware Error Source, please
  * refer to ACPI Specification version 4.0, section 17.3.2.6
  *
- * Copyright 2010 Intel Corp.
+ * Copyright 2010,2011 Intel Corp.
  *   Author: Huang Ying <ying.huang@intel.com>
  *
  * This program is free software; you can redistribute it and/or
@@ -42,6 +42,9 @@
 #include <linux/mutex.h>
 #include <linux/ratelimit.h>
 #include <linux/vmalloc.h>
+#include <linux/irq_work.h>
+#include <linux/llist.h>
+#include <linux/genalloc.h>
 #include <acpi/apei.h>
 #include <acpi/atomicio.h>
 #include <acpi/hed.h>
@@ -53,6 +56,30 @@
 #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))
 
 /*
  * One struct ghes is created for each generic hardware error source.
@@ -77,6 +104,22 @@ struct ghes {
 	};
 };
 
+struct ghes_estatus_node {
+	struct llist_node llnode;
+	struct acpi_hest_generic *generic;
+};
+
+struct ghes_estatus_cache {
+	u32 estatus_len;
+	atomic_t count;
+	struct acpi_hest_generic *generic;
+	unsigned long long time_in;
+	struct rcu_head rcu;
+};
+
+int ghes_disable;
+module_param_named(disable, ghes_disable, bool, 0);
+
 static int ghes_panic_timeout	__read_mostly = 30;
 
 /*
@@ -121,6 +164,22 @@ static struct vm_struct *ghes_ioremap_area;
 static DEFINE_RAW_SPINLOCK(ghes_ioremap_lock_nmi);
 static DEFINE_SPINLOCK(ghes_ioremap_lock_irq);
 
+/*
+ * 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.
+ */
+static struct gen_pool *ghes_estatus_pool;
+static unsigned long ghes_estatus_pool_size_request;
+static struct llist_head ghes_estatus_llist;
+static struct irq_work ghes_proc_irq_work;
+
+struct ghes_estatus_cache *ghes_estatus_caches[GHES_ESTATUS_CACHES_SIZE];
+static atomic_t ghes_estatus_cache_alloced;
+
 static int ghes_ioremap_init(void)
 {
 	ghes_ioremap_area = __get_vm_area(PAGE_SIZE * GHES_IOREMAP_PAGES,
@@ -180,6 +239,55 @@ static void ghes_iounmap_irq(void __iomem *vaddr_ptr)
 	__flush_tlb_one(vaddr);
 }
 
+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);
+}
+
+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);
+}
+
+static int ghes_estatus_pool_expand(unsigned long len)
+{
+	unsigned long i, pages, size, addr;
+	int ret;
+
+	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;
+}
+
+static void ghes_estatus_pool_shrink(unsigned long len)
+{
+	ghes_estatus_pool_size_request -= PAGE_ALIGN(len);
+}
+
 static struct ghes *ghes_new(struct acpi_hest_generic *generic)
 {
 	struct ghes *ghes;
@@ -341,43 +449,196 @@ static void ghes_clear_estatus(struct ghes *ghes)
 	ghes->flags &= ~GHES_TO_CLEAR;
 }
 
-static void ghes_do_proc(struct ghes *ghes)
+static void ghes_do_proc(const struct acpi_hest_generic_status *estatus)
 {
-	int sev, processed = 0;
+	int sev, sec_sev;
 	struct acpi_hest_generic_data *gdata;
 
-	sev = ghes_severity(ghes->estatus->error_severity);
-	apei_estatus_for_each_section(ghes->estatus, gdata) {
-#ifdef CONFIG_X86_MCE
+	sev = ghes_severity(estatus->error_severity);
+	apei_estatus_for_each_section(estatus, gdata) {
+		sec_sev = ghes_severity(gdata->error_severity);
 		if (!uuid_le_cmp(*(uuid_le *)gdata->section_type,
 				 CPER_SEC_PLATFORM_MEM)) {
-			apei_mce_report_mem_error(
-				sev == GHES_SEV_CORRECTED,
-				(struct cper_sec_mem_err *)(gdata+1));
-			processed = 1;
-		}
+			struct cper_sec_mem_err *mem_err;
+			mem_err = (struct cper_sec_mem_err *)(gdata+1);
+#ifdef CONFIG_X86_MCE
+			apei_mce_report_mem_error(sev == GHES_SEV_CORRECTED,
+						  mem_err);
 #endif
+#ifdef CONFIG_ACPI_APEI_MEMORY_FAILURE
+			if (sev == GHES_SEV_RECOVERABLE &&
+			    sec_sev == GHES_SEV_RECOVERABLE &&
+			    mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS) {
+				unsigned long pfn;
+				pfn = mem_err->physical_addr >> PAGE_SHIFT;
+				memory_failure_queue(pfn, 0, 0);
+			}
+#endif
+		}
 	}
 }
 
-static void ghes_print_estatus(const char *pfx, struct ghes *ghes)
+static void __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, 5*HZ, 2);
-
 	if (pfx == NULL) {
-		if (ghes_severity(ghes->estatus->error_severity) <=
+		if (ghes_severity(estatus->error_severity) <=
 		    GHES_SEV_CORRECTED)
 			pfx = KERN_WARNING HW_ERR;
 		else
 			pfx = KERN_ERR HW_ERR;
 	}
-	if (__ratelimit(&ratelimit)) {
-		printk(
-	"%s""Hardware error from APEI Generic Hardware Error Source: %d\n",
-	pfx, ghes->generic->header.source_id);
-		apei_estatus_print(pfx, ghes->estatus);
+	printk("%s""Hardware error from APEI Generic Hardware Error Source: %d\n",
+	       pfx, generic->header.source_id);
+	apei_estatus_print(pfx, 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 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 = apei_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 = apei_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_free(struct ghes_estatus_cache *cache)
+{
+	u32 len;
+
+	len = apei_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_rcu_free(struct rcu_head *head)
+{
+	struct ghes_estatus_cache *cache;
+
+	cache = container_of(head, struct ghes_estatus_cache, rcu);
+	ghes_estatus_cache_free(cache);
+}
+
+static void ghes_estatus_cache_add(
+	struct acpi_hest_generic *generic,
+	struct acpi_hest_generic_status *estatus)
+{
+	int i, slot = -1, count;
+	unsigned long long now, duration, period, max_period = 0;
+	struct ghes_estatus_cache *cache, *slot_cache = NULL, *new_cache;
+
+	new_cache = ghes_estatus_cache_alloc(generic, estatus);
+	if (new_cache == NULL)
+		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;
+			slot_cache = NULL;
+			break;
+		}
+		duration = now - cache->time_in;
+		if (duration >= GHES_ESTATUS_IN_CACHE_MAX_NSEC) {
+			slot = i;
+			slot_cache = cache;
+			break;
+		}
+		count = atomic_read(&cache->count);
+		period = duration;
+		do_div(period, (count + 1));
+		if (period > max_period) {
+			max_period = period;
+			slot = i;
+			slot_cache = cache;
+		}
+	}
+	/* new_cache must be put into array after its contents are written */
+	smp_wmb();
+	if (slot != -1 && cmpxchg(ghes_estatus_caches + slot,
+				  slot_cache, new_cache) == slot_cache) {
+		if (slot_cache)
+			call_rcu(&slot_cache->rcu, ghes_estatus_cache_rcu_free);
+	} else
+		ghes_estatus_cache_free(new_cache);
+	rcu_read_unlock();
 }
 
 static int ghes_proc(struct ghes *ghes)
@@ -387,9 +648,11 @@ static int ghes_proc(struct ghes *ghes)
 	rc = ghes_read_estatus(ghes, 0);
 	if (rc)
 		goto out;
-	ghes_print_estatus(NULL, ghes);
-	ghes_do_proc(ghes);
-
+	if (!ghes_estatus_cached(ghes->estatus)) {
+		if (ghes_print_estatus(NULL, ghes->generic, ghes->estatus))
+			ghes_estatus_cache_add(ghes->generic, ghes->estatus);
+	}
+	ghes_do_proc(ghes->estatus);
 out:
 	ghes_clear_estatus(ghes);
 	return 0;
@@ -447,6 +710,45 @@ static int ghes_notify_sci(struct notifier_block *this,
 	return ret;
 }
 
+static void ghes_proc_in_irq(struct irq_work *irq_work)
+{
+	struct llist_node *llnode, *next, *tail = NULL;
+	struct ghes_estatus_node *estatus_node;
+	struct acpi_hest_generic *generic;
+	struct acpi_hest_generic_status *estatus;
+	u32 len, node_len;
+
+	/*
+	 * Because the time order of estatus in list is reversed,
+	 * revert it back to proper order.
+	 */
+	llnode = llist_del_all(&ghes_estatus_llist);
+	while (llnode) {
+		next = llnode->next;
+		llnode->next = tail;
+		tail = llnode;
+		llnode = next;
+	}
+	llnode = tail;
+	while (llnode) {
+		next = llnode->next;
+		estatus_node = llist_entry(llnode, struct ghes_estatus_node,
+					   llnode);
+		estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
+		len = apei_estatus_len(estatus);
+		node_len = GHES_ESTATUS_NODE_LEN(len);
+		ghes_do_proc(estatus);
+		if (!ghes_estatus_cached(estatus)) {
+			generic = estatus_node->generic;
+			if (ghes_print_estatus(NULL, generic, estatus))
+				ghes_estatus_cache_add(generic, estatus);
+		}
+		gen_pool_free(ghes_estatus_pool, (unsigned long)estatus_node,
+			      node_len);
+		llnode = next;
+	}
+}
+
 static int ghes_notify_nmi(struct notifier_block *this,
 				  unsigned long cmd, void *data)
 {
@@ -476,7 +778,8 @@ static int ghes_notify_nmi(struct notifier_block *this,
 
 	if (sev_global >= GHES_SEV_PANIC) {
 		oops_begin();
-		ghes_print_estatus(KERN_EMERG HW_ERR, ghes_global);
+		__ghes_print_estatus(KERN_EMERG HW_ERR, ghes_global->generic,
+				     ghes_global->estatus);
 		/* reboot to log the error! */
 		if (panic_timeout == 0)
 			panic_timeout = ghes_panic_timeout;
@@ -484,12 +787,34 @@ static int ghes_notify_nmi(struct notifier_block *this,
 	}
 
 	list_for_each_entry_rcu(ghes, &ghes_nmi, list) {
+#ifdef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
+		u32 len, node_len;
+		struct ghes_estatus_node *estatus_node;
+		struct acpi_hest_generic_status *estatus;
+#endif
 		if (!(ghes->flags & GHES_TO_CLEAR))
 			continue;
-		/* Do not print estatus because printk is not NMI safe */
-		ghes_do_proc(ghes);
+#ifdef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
+		if (ghes_estatus_cached(ghes->estatus))
+			goto next;
+		/* Save estatus for further processing in IRQ context */
+		len = apei_estatus_len(ghes->estatus);
+		node_len = GHES_ESTATUS_NODE_LEN(len);
+		estatus_node = (void *)gen_pool_alloc(ghes_estatus_pool,
+						      node_len);
+		if (estatus_node) {
+			estatus_node->generic = ghes->generic;
+			estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
+			memcpy(estatus, ghes->estatus, len);
+			llist_add(&estatus_node->llnode, &ghes_estatus_llist);
+		}
+next:
+#endif
 		ghes_clear_estatus(ghes);
 	}
+#ifdef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
+	irq_work_queue(&ghes_proc_irq_work);
+#endif
 
 out:
 	raw_spin_unlock(&ghes_nmi_lock);
@@ -504,10 +829,26 @@ static struct notifier_block ghes_notifier_nmi = {
 	.notifier_call = ghes_notify_nmi,
 };
 
+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 int __devinit ghes_probe(struct platform_device *ghes_dev)
 {
 	struct acpi_hest_generic *generic;
 	struct ghes *ghes = NULL;
+	unsigned long len;
 	int rc = -EINVAL;
 
 	generic = *(struct acpi_hest_generic **)ghes_dev->dev.platform_data;
@@ -573,6 +914,8 @@ static int __devinit ghes_probe(struct platform_device *ghes_dev)
 		mutex_unlock(&ghes_list_mutex);
 		break;
 	case ACPI_HEST_NOTIFY_NMI:
+		len = ghes_esource_prealloc_size(generic);
+		ghes_estatus_pool_expand(len);
 		mutex_lock(&ghes_list_mutex);
 		if (list_empty(&ghes_nmi))
 			register_die_notifier(&ghes_notifier_nmi);
@@ -597,6 +940,7 @@ static int __devexit ghes_remove(struct platform_device *ghes_dev)
 {
 	struct ghes *ghes;
 	struct acpi_hest_generic *generic;
+	unsigned long len;
 
 	ghes = platform_get_drvdata(ghes_dev);
 	generic = ghes->generic;
@@ -627,6 +971,8 @@ static int __devexit ghes_remove(struct platform_device *ghes_dev)
 		 * freed after NMI handler finishes.
 		 */
 		synchronize_rcu();
+		len = ghes_esource_prealloc_size(generic);
+		ghes_estatus_pool_shrink(len);
 		break;
 	default:
 		BUG();
@@ -662,15 +1008,43 @@ static int __init ghes_init(void)
 		return -EINVAL;
 	}
 
+	if (ghes_disable) {
+		pr_info(GHES_PFX "GHES is not enabled!\n");
+		return -EINVAL;
+	}
+
+	init_irq_work(&ghes_proc_irq_work, ghes_proc_in_irq);
+
 	rc = ghes_ioremap_init();
 	if (rc)
 		goto err;
 
-	rc = platform_driver_register(&ghes_platform_driver);
+	rc = ghes_estatus_pool_init();
 	if (rc)
 		goto err_ioremap_exit;
 
+	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;
+
+	rc = apei_osc_setup();
+	if (rc == 0 && osc_sb_apei_support_acked)
+		pr_info(GHES_PFX "APEI firmware first mode is enabled by APEI bit and WHEA _OSC.\n");
+	else if (rc == 0 && !osc_sb_apei_support_acked)
+		pr_info(GHES_PFX "APEI firmware first mode is enabled by WHEA _OSC.\n");
+	else if (rc && osc_sb_apei_support_acked)
+		pr_info(GHES_PFX "APEI firmware first mode is enabled by APEI bit.\n");
+	else
+		pr_info(GHES_PFX "Failed to enable APEI firmware first mode.\n");
+
 	return 0;
+err_pool_exit:
+	ghes_estatus_pool_exit();
 err_ioremap_exit:
 	ghes_ioremap_exit();
 err:
@@ -680,6 +1054,7 @@ err:
 static void __exit ghes_exit(void)
 {
 	platform_driver_unregister(&ghes_platform_driver);
+	ghes_estatus_pool_exit();
 	ghes_ioremap_exit();
 }
 
diff --git a/drivers/acpi/apei/hest.c b/drivers/acpi/apei/hest.c
index 181bc2f7bb7..05fee06f4d6 100644
--- a/drivers/acpi/apei/hest.c
+++ b/drivers/acpi/apei/hest.c
@@ -231,16 +231,17 @@ void __init acpi_hest_init(void)
 		goto err;
 	}
 
-	rc = apei_hest_parse(hest_parse_ghes_count, &ghes_count);
-	if (rc)
-		goto err;
-
-	rc = hest_ghes_dev_register(ghes_count);
-	if (!rc) {
-		pr_info(HEST_PFX "Table parsing has been initialized.\n");
-		return;
+	if (!ghes_disable) {
+		rc = apei_hest_parse(hest_parse_ghes_count, &ghes_count);
+		if (rc)
+			goto err;
+		rc = hest_ghes_dev_register(ghes_count);
+		if (rc)
+			goto err;
 	}
 
+	pr_info(HEST_PFX "Table parsing has been initialized.\n");
+	return;
 err:
 	hest_disable = 1;
 }
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index d1e06c182cd..437ddbf0c49 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -39,6 +39,7 @@
 #include <linux/pci.h>
 #include <acpi/acpi_bus.h>
 #include <acpi/acpi_drivers.h>
+#include <acpi/apei.h>
 #include <linux/dmi.h>
 #include <linux/suspend.h>
 
@@ -519,6 +520,7 @@ out_kfree:
 }
 EXPORT_SYMBOL(acpi_run_osc);
 
+bool osc_sb_apei_support_acked;
 static u8 sb_uuid_str[] = "0811B06E-4A27-44F9-8D60-3CBBC22E7B48";
 static void acpi_bus_osc_support(void)
 {
@@ -541,11 +543,19 @@ static void acpi_bus_osc_support(void)
 #if defined(CONFIG_ACPI_PROCESSOR) || defined(CONFIG_ACPI_PROCESSOR_MODULE)
 	capbuf[OSC_SUPPORT_TYPE] |= OSC_SB_PPC_OST_SUPPORT;
 #endif
+
+	if (!ghes_disable)
+		capbuf[OSC_SUPPORT_TYPE] |= OSC_SB_APEI_SUPPORT;
 	if (ACPI_FAILURE(acpi_get_handle(NULL, "\\_SB", &handle)))
 		return;
-	if (ACPI_SUCCESS(acpi_run_osc(handle, &context)))
+	if (ACPI_SUCCESS(acpi_run_osc(handle, &context))) {
+		u32 *capbuf_ret = context.ret.pointer;
+		if (context.ret.length > OSC_SUPPORT_TYPE)
+			osc_sb_apei_support_acked =
+				capbuf_ret[OSC_SUPPORT_TYPE] & OSC_SB_APEI_SUPPORT;
 		kfree(context.ret.pointer);
-	/* do we need to check the returned cap? Sounds no */
+	}
+	/* do we need to check other returned cap? Sounds no */
 }
 
 /* --------------------------------------------------------------------------