Merge branch 'x86-ras-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull RAS updates from Ingo Molnar:
 "The main changes in this cycle are:

   - RAS tracing/events infrastructure, by Gong Chen.

   - Various generalizations of the APEI code to make it available to
     non-x86 architectures, by Tomasz Nowicki"

* 'x86-ras-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/ras: Fix build warnings in <linux/aer.h>
  acpi, apei, ghes: Factor out ioremap virtual memory for IRQ and NMI context.
  acpi, apei, ghes: Make NMI error notification to be GHES architecture extension.
  apei, mce: Factor out APEI architecture specific MCE calls.
  RAS, extlog: Adjust init flow
  trace, eMCA: Add a knob to adjust where to save event log
  trace, RAS: Add eMCA trace event interface
  RAS, debugfs: Add debugfs interface for RAS subsystem
  CPER: Adjust code flow of some functions
  x86, MCE: Robustify mcheck_init_device
  trace, AER: Move trace into unified interface
  trace, RAS: Add basic RAS trace event
  x86, MCE: Kill CPU_POST_DEAD

28 files changed, 653 insertions, 247 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 86216a55eb59..6b71f0417293 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -131,6 +131,8 @@ config X86
 	select GENERIC_CPU_AUTOPROBE
 	select HAVE_ARCH_AUDITSYSCALL
 	select ARCH_SUPPORTS_ATOMIC_RMW
+	select HAVE_ACPI_APEI if ACPI
+	select HAVE_ACPI_APEI_NMI if ACPI
 
 config INSTRUCTION_DECODER
 	def_bool y
diff --git a/arch/x86/kernel/acpi/Makefile b/arch/x86/kernel/acpi/Makefile
index 163b22581472..3242e591fa82 100644
--- a/arch/x86/kernel/acpi/Makefile
+++ b/arch/x86/kernel/acpi/Makefile
@@ -1,5 +1,6 @@
 obj-$(CONFIG_ACPI)		+= boot.o
 obj-$(CONFIG_ACPI_SLEEP)	+= sleep.o wakeup_$(BITS).o
+obj-$(CONFIG_ACPI_APEI)		+= apei.o
 
 ifneq ($(CONFIG_ACPI_PROCESSOR),)
 obj-y				+= cstate.o
diff --git a/arch/x86/kernel/acpi/apei.c b/arch/x86/kernel/acpi/apei.c
new file mode 100644
index 000000000000..c280df6b2aa2
--- /dev/null
+++ b/arch/x86/kernel/acpi/apei.c
@@ -0,0 +1,62 @@
+/*
+ * Arch-specific APEI-related functions.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <acpi/apei.h>
+
+#include <asm/mce.h>
+#include <asm/tlbflush.h>
+
+int arch_apei_enable_cmcff(struct acpi_hest_header *hest_hdr, void *data)
+{
+#ifdef CONFIG_X86_MCE
+	int i;
+	struct acpi_hest_ia_corrected *cmc;
+	struct acpi_hest_ia_error_bank *mc_bank;
+
+	if (hest_hdr->type != ACPI_HEST_TYPE_IA32_CORRECTED_CHECK)
+		return 0;
+
+	cmc = (struct acpi_hest_ia_corrected *)hest_hdr;
+	if (!cmc->enabled)
+		return 0;
+
+	/*
+	 * We expect HEST to provide a list of MC banks that report errors
+	 * in firmware first mode. Otherwise, return non-zero value to
+	 * indicate that we are done parsing HEST.
+	 */
+	if (!(cmc->flags & ACPI_HEST_FIRMWARE_FIRST) ||
+	    !cmc->num_hardware_banks)
+		return 1;
+
+	pr_info("HEST: Enabling Firmware First mode for corrected errors.\n");
+
+	mc_bank = (struct acpi_hest_ia_error_bank *)(cmc + 1);
+	for (i = 0; i < cmc->num_hardware_banks; i++, mc_bank++)
+		mce_disable_bank(mc_bank->bank_number);
+#endif
+	return 1;
+}
+
+void arch_apei_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
+{
+#ifdef CONFIG_X86_MCE
+	apei_mce_report_mem_error(sev, mem_err);
+#endif
+}
+
+void arch_apei_flush_tlb_one(unsigned long addr)
+{
+	__flush_tlb_one(addr);
+}
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 9a79c8dbd8e8..4fc57975acc1 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -2385,6 +2385,10 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 			threshold_cpu_callback(action, cpu);
 		mce_device_remove(cpu);
 		mce_intel_hcpu_update(cpu);
+
+		/* intentionally ignoring frozen here */
+		if (!(action & CPU_TASKS_FROZEN))
+			cmci_rediscover();
 		break;
 	case CPU_DOWN_PREPARE:
 		smp_call_function_single(cpu, mce_disable_cpu, &action, 1);
@@ -2396,11 +2400,6 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		break;
 	}
 
-	if (action == CPU_POST_DEAD) {
-		/* intentionally ignoring frozen here */
-		cmci_rediscover();
-	}
-
 	return NOTIFY_OK;
 }
 
diff --git a/drivers/Kconfig b/drivers/Kconfig
index 0e87a34b6472..4e6e66c3c8d6 100644
--- a/drivers/Kconfig
+++ b/drivers/Kconfig
@@ -176,4 +176,6 @@ source "drivers/powercap/Kconfig"
 
 source "drivers/mcb/Kconfig"
 
+source "drivers/ras/Kconfig"
+
 endmenu
diff --git a/drivers/Makefile b/drivers/Makefile
index f98b50d8251d..65c32b1cea3d 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -158,3 +158,4 @@ obj-$(CONFIG_NTB)		+= ntb/
 obj-$(CONFIG_FMC)		+= fmc/
 obj-$(CONFIG_POWERCAP)		+= powercap/
 obj-$(CONFIG_MCB)		+= mcb/
+obj-$(CONFIG_RAS)		+= ras/
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index a34a22841002..206942b8d105 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -370,6 +370,7 @@ config ACPI_EXTLOG
 	tristate "Extended Error Log support"
 	depends on X86_MCE && X86_LOCAL_APIC
 	select UEFI_CPER
+	select RAS
 	default n
 	help
 	  Certain usages such as Predictive Failure Analysis (PFA) require
@@ -384,6 +385,7 @@ config ACPI_EXTLOG
 
 	  Enhanced MCA Logging allows firmware to provide additional error
 	  information to system software, synchronous with MCE or CMCI. This
-	  driver adds support for that functionality.
+	  driver adds support for that functionality with corresponding
+	  tracepoint which carries that information to userspace.
 
 endif	# ACPI
diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c
index 185334114d71..0ad6f389d922 100644
--- a/drivers/acpi/acpi_extlog.c
+++ b/drivers/acpi/acpi_extlog.c
@@ -12,10 +12,12 @@
 #include <linux/cper.h>
 #include <linux/ratelimit.h>
 #include <linux/edac.h>
+#include <linux/ras.h>
 #include <asm/cpu.h>
 #include <asm/mce.h>
 
 #include "apei/apei-internal.h"
+#include <ras/ras_event.h>
 
 #define EXT_ELOG_ENTRY_MASK	GENMASK_ULL(51, 0) /* elog entry address mask */
 
@@ -137,8 +139,12 @@ static int extlog_print(struct notifier_block *nb, unsigned long val,
 	struct mce *mce = (struct mce *)data;
 	int	bank = mce->bank;
 	int	cpu = mce->extcpu;
-	struct acpi_generic_status *estatus;
-	int rc;
+	struct acpi_generic_status *estatus, *tmp;
+	struct acpi_generic_data *gdata;
+	const uuid_le *fru_id = &NULL_UUID_LE;
+	char *fru_text = "";
+	uuid_le *sec_type;
+	static u32 err_seq;
 
 	estatus = extlog_elog_entry_check(cpu, bank);
 	if (estatus == NULL)
@@ -148,8 +154,29 @@ static int extlog_print(struct notifier_block *nb, unsigned long val,
 	/* clear record status to enable BIOS to update it again */
 	estatus->block_status = 0;
 
-	rc = print_extlog_rcd(NULL, (struct acpi_generic_status *)elog_buf, cpu);
+	tmp = (struct acpi_generic_status *)elog_buf;
+
+	if (!ras_userspace_consumers()) {
+		print_extlog_rcd(NULL, tmp, cpu);
+		goto out;
+	}
+
+	/* log event via trace */
+	err_seq++;
+	gdata = (struct acpi_generic_data *)(tmp + 1);
+	if (gdata->validation_bits & CPER_SEC_VALID_FRU_ID)
+		fru_id = (uuid_le *)gdata->fru_id;
+	if (gdata->validation_bits & CPER_SEC_VALID_FRU_TEXT)
+		fru_text = gdata->fru_text;
+	sec_type = (uuid_le *)gdata->section_type;
+	if (!uuid_le_cmp(*sec_type, CPER_SEC_PLATFORM_MEM)) {
+		struct cper_sec_mem_err *mem = (void *)(gdata + 1);
+		if (gdata->error_data_length >= sizeof(*mem))
+			trace_extlog_mem_event(mem, err_seq, fru_id, fru_text,
+					       (u8)gdata->error_severity);
+	}
 
+out:
 	return NOTIFY_STOP;
 }
 
@@ -196,19 +223,16 @@ static int __init extlog_init(void)
 	u64 cap;
 	int rc;
 
+	rdmsrl(MSR_IA32_MCG_CAP, cap);
+
+	if (!(cap & MCG_ELOG_P) || !extlog_get_l1addr())
+		return -ENODEV;
+
 	if (get_edac_report_status() == EDAC_REPORTING_FORCE) {
 		pr_warn("Not loading eMCA, error reporting force-enabled through EDAC.\n");
 		return -EPERM;
 	}
 
-	rc = -ENODEV;
-	rdmsrl(MSR_IA32_MCG_CAP, cap);
-	if (!(cap & MCG_ELOG_P))
-		return rc;
-
-	if (!extlog_get_l1addr())
-		return rc;
-
 	rc = -EINVAL;
 	/* get L1 header to fetch necessary information */
 	l1_hdr_size = sizeof(struct extlog_l1_head);
diff --git a/drivers/acpi/apei/Kconfig b/drivers/acpi/apei/Kconfig
index c4dac7150960..b0140c8fc733 100644
--- a/drivers/acpi/apei/Kconfig
+++ b/drivers/acpi/apei/Kconfig
@@ -1,9 +1,15 @@
+config HAVE_ACPI_APEI
+	bool
+
+config HAVE_ACPI_APEI_NMI
+	bool
+
 config ACPI_APEI
 	bool "ACPI Platform Error Interface (APEI)"
 	select MISC_FILESYSTEMS
 	select PSTORE
 	select UEFI_CPER
-	depends on X86
+	depends on HAVE_ACPI_APEI
 	help
 	  APEI allows to report errors (for example from the chipset)
 	  to the operating system. This improves NMI handling
diff --git a/drivers/acpi/apei/apei-base.c b/drivers/acpi/apei/apei-base.c
index 8678dfe5366b..2cd7bdd6c8b3 100644
--- a/drivers/acpi/apei/apei-base.c
+++ b/drivers/acpi/apei/apei-base.c
@@ -745,6 +745,19 @@ struct dentry *apei_get_debugfs_dir(void)
 }
 EXPORT_SYMBOL_GPL(apei_get_debugfs_dir);
 
+int __weak arch_apei_enable_cmcff(struct acpi_hest_header *hest_hdr,
+				  void *data)
+{
+	return 1;
+}
+EXPORT_SYMBOL_GPL(arch_apei_enable_cmcff);
+
+void __weak arch_apei_report_mem_error(int sev,
+				       struct cper_sec_mem_err *mem_err)
+{
+}
+EXPORT_SYMBOL_GPL(arch_apei_report_mem_error);
+
 int apei_osc_setup(void)
 {
 	static u8 whea_uuid_str[] = "ed855e0c-6c90-47bf-a62a-26de0fc5ad5c";
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index dab7cb7349df..e05d84e7b06d 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -47,11 +47,11 @@
 #include <linux/genalloc.h>
 #include <linux/pci.h>
 #include <linux/aer.h>
+#include <linux/nmi.h>
 
 #include <acpi/ghes.h>
-#include <asm/mce.h>
+#include <acpi/apei.h>
 #include <asm/tlbflush.h>
-#include <asm/nmi.h>
 
 #include "apei-internal.h"
 
@@ -86,8 +86,6 @@
 bool ghes_disable;
 module_param_named(disable, ghes_disable, bool, 0);
 
-static int ghes_panic_timeout	__read_mostly = 30;
-
 /*
  * All error sources notified with SCI shares one notifier function,
  * so they need to be linked and checked one by one.  This is applied
@@ -97,16 +95,9 @@ static int ghes_panic_timeout	__read_mostly = 30;
  * list changing, not for traversing.
  */
 static LIST_HEAD(ghes_sci);
-static LIST_HEAD(ghes_nmi);
 static DEFINE_MUTEX(ghes_list_mutex);
 
 /*
- * NMI may be triggered on any CPU, so ghes_nmi_lock is used for
- * mutual exclusion.
- */
-static DEFINE_RAW_SPINLOCK(ghes_nmi_lock);
-
-/*
  * Because the memory area used to transfer hardware error information
  * from BIOS to Linux can be determined only in NMI, IRQ or timer
  * handler, but general ioremap can not be used in atomic context, so
@@ -114,12 +105,16 @@ static DEFINE_RAW_SPINLOCK(ghes_nmi_lock);
  */
 
 /*
- * Two virtual pages are used, one for NMI context, the other for
- * IRQ/PROCESS context
+ * Two virtual pages are used, one for IRQ/PROCESS context, the other for
+ * NMI context (optionally).
  */
-#define GHES_IOREMAP_PAGES		2
-#define GHES_IOREMAP_NMI_PAGE(base)	(base)
-#define GHES_IOREMAP_IRQ_PAGE(base)	((base) + PAGE_SIZE)
+#ifdef CONFIG_HAVE_ACPI_APEI_NMI
+#define GHES_IOREMAP_PAGES           2
+#else
+#define GHES_IOREMAP_PAGES           1
+#endif
+#define GHES_IOREMAP_IRQ_PAGE(base)	(base)
+#define GHES_IOREMAP_NMI_PAGE(base)	((base) + PAGE_SIZE)
 
 /* virtual memory area for atomic ioremap */
 static struct vm_struct *ghes_ioremap_area;
@@ -130,18 +125,8 @@ 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;
@@ -192,7 +177,7 @@ static void ghes_iounmap_nmi(void __iomem *vaddr_ptr)
 
 	BUG_ON(vaddr != (unsigned long)GHES_IOREMAP_NMI_PAGE(base));
 	unmap_kernel_range_noflush(vaddr, PAGE_SIZE);
-	__flush_tlb_one(vaddr);
+	arch_apei_flush_tlb_one(vaddr);
 }
 
 static void ghes_iounmap_irq(void __iomem *vaddr_ptr)
@@ -202,7 +187,7 @@ static void ghes_iounmap_irq(void __iomem *vaddr_ptr)
 
 	BUG_ON(vaddr != (unsigned long)GHES_IOREMAP_IRQ_PAGE(base));
 	unmap_kernel_range_noflush(vaddr, PAGE_SIZE);
-	__flush_tlb_one(vaddr);
+	arch_apei_flush_tlb_one(vaddr);
 }
 
 static int ghes_estatus_pool_init(void)
@@ -249,11 +234,6 @@ static int ghes_estatus_pool_expand(unsigned long len)
 	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;
@@ -455,9 +435,7 @@ static void ghes_do_proc(struct ghes *ghes,
 			mem_err = (struct cper_sec_mem_err *)(gdata+1);
 			ghes_edac_report_mem_error(ghes, sev, mem_err);
 
-#ifdef CONFIG_X86_MCE
-			apei_mce_report_mem_error(sev, mem_err);
-#endif
+			arch_apei_report_mem_error(sev, mem_err);
 			ghes_handle_memory_failure(gdata, sev);
 		}
 #ifdef CONFIG_ACPI_APEI_PCIEAER
@@ -734,6 +712,32 @@ static int ghes_notify_sci(struct notifier_block *this,
 	return ret;
 }
 
+static struct notifier_block ghes_notifier_sci = {
+	.notifier_call = ghes_notify_sci,
+};
+
+#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.
+ */
+static struct llist_head ghes_estatus_llist;
+static struct irq_work ghes_proc_irq_work;
+
+/*
+ * NMI may be triggered on any CPU, so ghes_nmi_lock is used for
+ * mutual exclusion.
+ */
+static DEFINE_RAW_SPINLOCK(ghes_nmi_lock);
+
+static LIST_HEAD(ghes_nmi);
+
+static int ghes_panic_timeout	__read_mostly = 30;
+
 static struct llist_node *llist_nodes_reverse(struct llist_node *llnode)
 {
 	struct llist_node *next, *tail = NULL;
@@ -877,10 +881,6 @@ out:
 	return ret;
 }
 
-static struct notifier_block ghes_notifier_sci = {
-	.notifier_call = ghes_notify_sci,
-};
-
 static unsigned long ghes_esource_prealloc_size(
 	const struct acpi_hest_generic *generic)
 {
@@ -896,11 +896,71 @@ static unsigned long ghes_esource_prealloc_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");
+	list_add_rcu(&ghes->list, &ghes_nmi);
+	mutex_unlock(&ghes_list_mutex);
+}
+
+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))
+		unregister_nmi_handler(NMI_LOCAL, "ghes");
+	mutex_unlock(&ghes_list_mutex);
+	/*
+	 * To synchronize with NMI handler, ghes can only be
+	 * freed after NMI handler finishes.
+	 */
+	synchronize_rcu();
+	len = ghes_esource_prealloc_size(ghes->generic);
+	ghes_estatus_pool_shrink(len);
+}
+
+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)
+{
+	pr_err(GHES_PFX "ID: %d, trying to add NMI notification which is not supported!\n",
+	       ghes->generic->header.source_id);
+	BUG();
+}
+
+static inline void ghes_nmi_remove(struct ghes *ghes)
+{
+	pr_err(GHES_PFX "ID: %d, trying to remove NMI notification which is not supported!\n",
+	       ghes->generic->header.source_id);
+	BUG();
+}
+
+static inline void ghes_nmi_init_cxt(void)
+{
+}
+#endif /* CONFIG_HAVE_ACPI_APEI_NMI */
+
 static int 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;
@@ -911,7 +971,13 @@ static int ghes_probe(struct platform_device *ghes_dev)
 	case ACPI_HEST_NOTIFY_POLLED:
 	case ACPI_HEST_NOTIFY_EXTERNAL:
 	case ACPI_HEST_NOTIFY_SCI:
+		break;
 	case ACPI_HEST_NOTIFY_NMI:
+		if (!IS_ENABLED(CONFIG_HAVE_ACPI_APEI_NMI)) {
+			pr_warn(GHES_PFX "Generic hardware error source: %d notified via NMI interrupt 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",
@@ -972,14 +1038,7 @@ static int 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_nmi_handler(NMI_LOCAL, ghes_notify_nmi, 0,
-						"ghes");
-		list_add_rcu(&ghes->list, &ghes_nmi);
-		mutex_unlock(&ghes_list_mutex);
+		ghes_nmi_add(ghes);
 		break;
 	default:
 		BUG();
@@ -1001,7 +1060,6 @@ static int 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;
@@ -1022,18 +1080,7 @@ static int ghes_remove(struct platform_device *ghes_dev)
 		mutex_unlock(&ghes_list_mutex);
 		break;
 	case ACPI_HEST_NOTIFY_NMI:
-		mutex_lock(&ghes_list_mutex);
-		list_del_rcu(&ghes->list);
-		if (list_empty(&ghes_nmi))
-			unregister_nmi_handler(NMI_LOCAL, "ghes");
-		mutex_unlock(&ghes_list_mutex);
-		/*
-		 * To synchronize with NMI handler, ghes can only be
-		 * freed after NMI handler finishes.
-		 */
-		synchronize_rcu();
-		len = ghes_esource_prealloc_size(generic);
-		ghes_estatus_pool_shrink(len);
+		ghes_nmi_remove(ghes);
 		break;
 	default:
 		BUG();
@@ -1077,7 +1124,7 @@ static int __init ghes_init(void)
 		return -EINVAL;
 	}
 
-	init_irq_work(&ghes_proc_irq_work, ghes_proc_in_irq);
+	ghes_nmi_init_cxt();
 
 	rc = ghes_ioremap_init();
 	if (rc)
diff --git a/drivers/acpi/apei/hest.c b/drivers/acpi/apei/hest.c
index f5e37f32c71f..06e9b411a0a2 100644
--- a/drivers/acpi/apei/hest.c
+++ b/drivers/acpi/apei/hest.c
@@ -36,7 +36,6 @@
 #include <linux/io.h>
 #include <linux/platform_device.h>
 #include <acpi/apei.h>
-#include <asm/mce.h>
 
 #include "apei-internal.h"
 
@@ -128,33 +127,7 @@ EXPORT_SYMBOL_GPL(apei_hest_parse);
  */
 static int __init hest_parse_cmc(struct acpi_hest_header *hest_hdr, void *data)
 {
-#ifdef CONFIG_X86_MCE
-	int i;
-	struct acpi_hest_ia_corrected *cmc;
-	struct acpi_hest_ia_error_bank *mc_bank;
-
-	if (hest_hdr->type != ACPI_HEST_TYPE_IA32_CORRECTED_CHECK)
-		return 0;
-
-	cmc = (struct acpi_hest_ia_corrected *)hest_hdr;
-	if (!cmc->enabled)
-		return 0;
-
-	/*
-	 * We expect HEST to provide a list of MC banks that report errors
-	 * in firmware first mode. Otherwise, return non-zero value to
-	 * indicate that we are done parsing HEST.
-	 */
-	if (!(cmc->flags & ACPI_HEST_FIRMWARE_FIRST) || !cmc->num_hardware_banks)
-		return 1;
-
-	pr_info(HEST_PFX "Enabling Firmware First mode for corrected errors.\n");
-
-	mc_bank = (struct acpi_hest_ia_error_bank *)(cmc + 1);
-	for (i = 0; i < cmc->num_hardware_banks; i++, mc_bank++)
-		mce_disable_bank(mc_bank->bank_number);
-#endif
-	return 1;
+	return arch_apei_enable_cmcff(hest_hdr, data);
 }
 
 struct ghes_arr {
diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
index e339c6b91425..f8665f9c3e03 100644
--- a/drivers/edac/Kconfig
+++ b/drivers/edac/Kconfig
@@ -72,6 +72,7 @@ config EDAC_MCE_INJ
 
 config EDAC_MM_EDAC
 	tristate "Main Memory EDAC (Error Detection And Correction) reporting"
+	select RAS
 	help
 	  Some systems are able to detect and correct errors in main
 	  memory.  EDAC can report statistics on memory error
diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index 2c694b5297cc..9f134823fa75 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -33,9 +33,6 @@
 #include <asm/edac.h>
 #include "edac_core.h"
 #include "edac_module.h"
-
-#define CREATE_TRACE_POINTS
-#define TRACE_INCLUDE_PATH ../../include/ras
 #include <ras/ras_event.h>
 
 /* lock to memory controller's control array */
diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index 1491dd4f08f9..437e6fd47311 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -34,6 +34,9 @@
 #include <linux/aer.h>
 
 #define INDENT_SP	" "
+
+static char rcd_decode_str[CPER_REC_LEN];
+
 /*
  * CPER record ID need to be unique even after reboot, because record
  * ID is used as index for ERST storage, while CPER records from
@@ -50,18 +53,19 @@ u64 cper_next_record_id(void)
 }
 EXPORT_SYMBOL_GPL(cper_next_record_id);
 
-static const char *cper_severity_strs[] = {
+static const char * const severity_strs[] = {
 	"recoverable",
 	"fatal",
 	"corrected",
 	"info",
 };
 
-static const char *cper_severity_str(unsigned int severity)
+const char *cper_severity_str(unsigned int severity)
 {
-	return severity < ARRAY_SIZE(cper_severity_strs) ?
-		cper_severity_strs[severity] : "unknown";
+	return severity < ARRAY_SIZE(severity_strs) ?
+		severity_strs[severity] : "unknown";
 }
+EXPORT_SYMBOL_GPL(cper_severity_str);
 
 /*
  * cper_print_bits - print strings for set bits
@@ -100,32 +104,32 @@ void cper_print_bits(const char *pfx, unsigned int bits,
 		printk("%s\n", buf);
 }
 
-static const char * const cper_proc_type_strs[] = {
+static const char * const proc_type_strs[] = {
 	"IA32/X64",
 	"IA64",
 };
 
-static const char * const cper_proc_isa_strs[] = {
+static const char * const proc_isa_strs[] = {
 	"IA32",
 	"IA64",
 	"X64",
 };
 
-static const char * const cper_proc_error_type_strs[] = {
+static const char * const proc_error_type_strs[] = {
 	"cache error",
 	"TLB error",
 	"bus error",
 	"micro-architectural error",
 };
 
-static const char * const cper_proc_op_strs[] = {
+static const char * const proc_op_strs[] = {
 	"unknown or generic",
 	"data read",
 	"data write",
 	"instruction execution",
 };
 
-static const char * const cper_proc_flag_strs[] = {
+static const char * const proc_flag_strs[] = {
 	"restartable",
 	"precise IP",
 	"overflow",
@@ -137,26 +141,26 @@ static void cper_print_proc_generic(const char *pfx,
 {
 	if (proc->validation_bits & CPER_PROC_VALID_TYPE)
 		printk("%s""processor_type: %d, %s\n", pfx, proc->proc_type,
-		       proc->proc_type < ARRAY_SIZE(cper_proc_type_strs) ?
-		       cper_proc_type_strs[proc->proc_type] : "unknown");
+		       proc->proc_type < ARRAY_SIZE(proc_type_strs) ?
+		       proc_type_strs[proc->proc_type] : "unknown");
 	if (proc->validation_bits & CPER_PROC_VALID_ISA)
 		printk("%s""processor_isa: %d, %s\n", pfx, proc->proc_isa,
-		       proc->proc_isa < ARRAY_SIZE(cper_proc_isa_strs) ?
-		       cper_proc_isa_strs[proc->proc_isa] : "unknown");
+		       proc->proc_isa < ARRAY_SIZE(proc_isa_strs) ?
+		       proc_isa_strs[proc->proc_isa] : "unknown");
 	if (proc->validation_bits & CPER_PROC_VALID_ERROR_TYPE) {
 		printk("%s""error_type: 0x%02x\n", pfx, proc->proc_error_type);
 		cper_print_bits(pfx, proc->proc_error_type,
-				cper_proc_error_type_strs,
-				ARRAY_SIZE(cper_proc_error_type_strs));
+				proc_error_type_strs,
+				ARRAY_SIZE(proc_error_type_strs));
 	}
 	if (proc->validation_bits & CPER_PROC_VALID_OPERATION)
 		printk("%s""operation: %d, %s\n", pfx, proc->operation,
-		       proc->operation < ARRAY_SIZE(cper_proc_op_strs) ?
-		       cper_proc_op_strs[proc->operation] : "unknown");
+		       proc->operation < ARRAY_SIZE(proc_op_strs) ?
+		       proc_op_strs[proc->operation] : "unknown");
 	if (proc->validation_bits & CPER_PROC_VALID_FLAGS) {
 		printk("%s""flags: 0x%02x\n", pfx, proc->flags);
-		cper_print_bits(pfx, proc->flags, cper_proc_flag_strs,
-				ARRAY_SIZE(cper_proc_flag_strs));
+		cper_print_bits(pfx, proc->flags, proc_flag_strs,
+				ARRAY_SIZE(proc_flag_strs));
 	}
 	if (proc->validation_bits & CPER_PROC_VALID_LEVEL)
 		printk("%s""level: %d\n", pfx, proc->level);
@@ -177,7 +181,7 @@ static void cper_print_proc_generic(const char *pfx,
 		printk("%s""IP: 0x%016llx\n", pfx, proc->ip);
 }
 
-static const char *cper_mem_err_type_strs[] = {
+static const char * const mem_err_type_strs[] = {
 	"unknown",
 	"no error",
 	"single-bit ECC",
@@ -196,58 +200,136 @@ static const char *cper_mem_err_type_strs[] = {
 	"physical memory map-out event",
 };
 
-static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem)
+const char *cper_mem_err_type_str(unsigned int etype)
 {
-	if (mem->validation_bits & CPER_MEM_VALID_ERROR_STATUS)
-		printk("%s""error_status: 0x%016llx\n", pfx, mem->error_status);
-	if (mem->validation_bits & CPER_MEM_VALID_PA)
-		printk("%s""physical_address: 0x%016llx\n",
-		       pfx, mem->physical_addr);
-	if (mem->validation_bits & CPER_MEM_VALID_PA_MASK)
-		printk("%s""physical_address_mask: 0x%016llx\n",
-		       pfx, mem->physical_addr_mask);
+	return etype < ARRAY_SIZE(mem_err_type_strs) ?
+		mem_err_type_strs[etype] : "unknown";
+}
+EXPORT_SYMBOL_GPL(cper_mem_err_type_str);
+
+static int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg)
+{
+	u32 len, n;
+
+	if (!msg)
+		return 0;
+
+	n = 0;
+	len = CPER_REC_LEN - 1;
 	if (mem->validation_bits & CPER_MEM_VALID_NODE)
-		pr_debug("node: %d\n", mem->node);
+		n += scnprintf(msg + n, len - n, "node: %d ", mem->node);
 	if (mem->validation_bits & CPER_MEM_VALID_CARD)
-		pr_debug("card: %d\n", mem->card);
+		n += scnprintf(msg + n, len - n, "card: %d ", mem->card);
 	if (mem->validation_bits & CPER_MEM_VALID_MODULE)
-		pr_debug("module: %d\n", mem->module);
+		n += scnprintf(msg + n, len - n, "module: %d ", mem->module);
 	if (mem->validation_bits & CPER_MEM_VALID_RANK_NUMBER)
-		pr_debug("rank: %d\n", mem->rank);
+		n += scnprintf(msg + n, len - n, "rank: %d ", mem->rank);
 	if (mem->validation_bits & CPER_MEM_VALID_BANK)
-		pr_debug("bank: %d\n", mem->bank);
+		n += scnprintf(msg + n, len - n, "bank: %d ", mem->bank);
 	if (mem->validation_bits & CPER_MEM_VALID_DEVICE)
-		pr_debug("device: %d\n", mem->device);
+		n += scnprin