M7350v1_en_gpl

kernel/drivers/acpi/apei/Kconfig

@@ -0,0 +1,57 @@
+config ACPI_APEI
+	bool "ACPI Platform Error Interface (APEI)"
+	select MISC_FILESYSTEMS
+	select PSTORE
+	depends on X86
+	help
+	  APEI allows to report errors (for example from the chipset)
+	  to the operating system. This improves NMI handling
+	  especially. In addition it supports error serialization and
+	  error injection.
+
+config ACPI_APEI_GHES
+	bool "APEI Generic Hardware Error Source"
+	depends on ACPI_APEI && X86
+	select ACPI_HED
+	select IRQ_WORK
+	select GENERIC_ALLOCATOR
+	help
+	  Generic Hardware Error Source provides a way to report
+	  platform hardware errors (such as that from chipset). It
+	  works in so called "Firmware First" mode, that is, hardware
+	  errors are reported to firmware firstly, then reported to
+	  Linux by firmware. This way, some non-standard hardware
+	  error registers or non-standard hardware link can be checked
+	  by firmware to produce more valuable hardware error
+	  information for Linux.
+
+config ACPI_APEI_PCIEAER
+	bool "APEI PCIe AER logging/recovering support"
+	depends on ACPI_APEI && PCIEAER
+	help
+	  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
+	help
+	  EINJ provides a hardware error injection mechanism, it is
+	  mainly used for debugging and testing the other parts of
+	  APEI and some other RAS features.
+
+config ACPI_APEI_ERST_DEBUG
+	tristate "APEI Error Record Serialization Table (ERST) Debug Support"
+	depends on ACPI_APEI
+	help
+	  ERST is a way provided by APEI to save and retrieve hardware
+	  error information to and from a persistent store. Enable this
+	  if you want to debugging and testing the ERST kernel support
+	  and firmware implementation.

kernel/drivers/acpi/apei/Makefile

@@ -0,0 +1,6 @@
+obj-$(CONFIG_ACPI_APEI)		+= apei.o
+obj-$(CONFIG_ACPI_APEI_GHES)	+= ghes.o
+obj-$(CONFIG_ACPI_APEI_EINJ)	+= einj.o
+obj-$(CONFIG_ACPI_APEI_ERST_DEBUG) += erst-dbg.o
+
+apei-y := apei-base.o hest.o cper.o erst.o

kernel/drivers/acpi/apei/apei-base.c

@@ -0,0 +1,752 @@
+/*
+ * apei-base.c - ACPI Platform Error Interface (APEI) supporting
+ * infrastructure
+ *
+ * APEI allows to report errors (for example from the chipset) to the
+ * the operating system. This improves NMI handling especially. In
+ * addition it supports error serialization and error injection.
+ *
+ * For more information about APEI, please refer to ACPI Specification
+ * version 4.0, chapter 17.
+ *
+ * This file has Common functions used by more than one APEI table,
+ * including framework of interpreter for ERST and EINJ; resource
+ * management for APEI registers.
+ *
+ * Copyright (C) 2009, Intel Corp.
+ *	Author: Huang Ying <ying.huang@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/acpi.h>
+#include <linux/acpi_io.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+#include <linux/kref.h>
+#include <linux/rculist.h>
+#include <linux/interrupt.h>
+#include <linux/debugfs.h>
+
+#include "apei-internal.h"
+
+#define APEI_PFX "APEI: "
+
+/*
+ * APEI ERST (Error Record Serialization Table) and EINJ (Error
+ * INJection) interpreter framework.
+ */
+
+#define APEI_EXEC_PRESERVE_REGISTER	0x1
+
+void apei_exec_ctx_init(struct apei_exec_context *ctx,
+			struct apei_exec_ins_type *ins_table,
+			u32 instructions,
+			struct acpi_whea_header *action_table,
+			u32 entries)
+{
+	ctx->ins_table = ins_table;
+	ctx->instructions = instructions;
+	ctx->action_table = action_table;
+	ctx->entries = entries;
+}
+EXPORT_SYMBOL_GPL(apei_exec_ctx_init);
+
+int __apei_exec_read_register(struct acpi_whea_header *entry, u64 *val)
+{
+	int rc;
+
+	rc = apei_read(val, &entry->register_region);
+	if (rc)
+		return rc;
+	*val >>= entry->register_region.bit_offset;
+	*val &= entry->mask;
+
+	return 0;
+}
+
+int apei_exec_read_register(struct apei_exec_context *ctx,
+			    struct acpi_whea_header *entry)
+{
+	int rc;
+	u64 val = 0;
+
+	rc = __apei_exec_read_register(entry, &val);
+	if (rc)
+		return rc;
+	ctx->value = val;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(apei_exec_read_register);
+
+int apei_exec_read_register_value(struct apei_exec_context *ctx,
+				  struct acpi_whea_header *entry)
+{
+	int rc;
+
+	rc = apei_exec_read_register(ctx, entry);
+	if (rc)
+		return rc;
+	ctx->value = (ctx->value == entry->value);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(apei_exec_read_register_value);
+
+int __apei_exec_write_register(struct acpi_whea_header *entry, u64 val)
+{
+	int rc;
+
+	val &= entry->mask;
+	val <<= entry->register_region.bit_offset;
+	if (entry->flags & APEI_EXEC_PRESERVE_REGISTER) {
+		u64 valr = 0;
+		rc = apei_read(&valr, &entry->register_region);
+		if (rc)
+			return rc;
+		valr &= ~(entry->mask << entry->register_region.bit_offset);
+		val |= valr;
+	}
+	rc = apei_write(val, &entry->register_region);
+
+	return rc;
+}
+
+int apei_exec_write_register(struct apei_exec_context *ctx,
+			     struct acpi_whea_header *entry)
+{
+	return __apei_exec_write_register(entry, ctx->value);
+}
+EXPORT_SYMBOL_GPL(apei_exec_write_register);
+
+int apei_exec_write_register_value(struct apei_exec_context *ctx,
+				   struct acpi_whea_header *entry)
+{
+	int rc;
+
+	ctx->value = entry->value;
+	rc = apei_exec_write_register(ctx, entry);
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(apei_exec_write_register_value);
+
+int apei_exec_noop(struct apei_exec_context *ctx,
+		   struct acpi_whea_header *entry)
+{
+	return 0;
+}
+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,
+		    bool optional)
+{
+	int rc = -ENOENT;
+	u32 i, ip;
+	struct acpi_whea_header *entry;
+	apei_exec_ins_func_t run;
+
+	ctx->ip = 0;
+
+	/*
+	 * "ip" is the instruction pointer of current instruction,
+	 * "ctx->ip" specifies the next instruction to executed,
+	 * instruction "run" function may change the "ctx->ip" to
+	 * implement "goto" semantics.
+	 */
+rewind:
+	ip = 0;
+	for (i = 0; i < ctx->entries; i++) {
+		entry = &ctx->action_table[i];
+		if (entry->action != action)
+			continue;
+		if (ip == ctx->ip) {
+			if (entry->instruction >= ctx->instructions ||
+			    !ctx->ins_table[entry->instruction].run) {
+				pr_warning(FW_WARN APEI_PFX
+			"Invalid action table, unknown instruction type: %d\n",
+					   entry->instruction);
+				return -EINVAL;
+			}
+			run = ctx->ins_table[entry->instruction].run;
+			rc = run(ctx, entry);
+			if (rc < 0)
+				return rc;
+			else if (rc != APEI_EXEC_SET_IP)
+				ctx->ip++;
+		}
+		ip++;
+		if (ctx->ip < ip)
+			goto rewind;
+	}
+
+	return !optional && rc < 0 ? rc : 0;
+}
+EXPORT_SYMBOL_GPL(__apei_exec_run);
+
+typedef int (*apei_exec_entry_func_t)(struct apei_exec_context *ctx,
+				      struct acpi_whea_header *entry,
+				      void *data);
+
+static int apei_exec_for_each_entry(struct apei_exec_context *ctx,
+				    apei_exec_entry_func_t func,
+				    void *data,
+				    int *end)
+{
+	u8 ins;
+	int i, rc;
+	struct acpi_whea_header *entry;
+	struct apei_exec_ins_type *ins_table = ctx->ins_table;
+
+	for (i = 0; i < ctx->entries; i++) {
+		entry = ctx->action_table + i;
+		ins = entry->instruction;
+		if (end)
+			*end = i;
+		if (ins >= ctx->instructions || !ins_table[ins].run) {
+			pr_warning(FW_WARN APEI_PFX
+			"Invalid action table, unknown instruction type: %d\n",
+				   ins);
+			return -EINVAL;
+		}
+		rc = func(ctx, entry, data);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
+static int pre_map_gar_callback(struct apei_exec_context *ctx,
+				struct acpi_whea_header *entry,
+				void *data)
+{
+	u8 ins = entry->instruction;
+
+	if (ctx->ins_table[ins].flags & APEI_EXEC_INS_ACCESS_REGISTER)
+		return acpi_os_map_generic_address(&entry->register_region);
+
+	return 0;
+}
+
+/*
+ * Pre-map all GARs in action table to make it possible to access them
+ * in NMI handler.
+ */
+int apei_exec_pre_map_gars(struct apei_exec_context *ctx)
+{
+	int rc, end;
+
+	rc = apei_exec_for_each_entry(ctx, pre_map_gar_callback,
+				      NULL, &end);
+	if (rc) {
+		struct apei_exec_context ctx_unmap;
+		memcpy(&ctx_unmap, ctx, sizeof(*ctx));
+		ctx_unmap.entries = end;
+		apei_exec_post_unmap_gars(&ctx_unmap);
+	}
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(apei_exec_pre_map_gars);
+
+static int post_unmap_gar_callback(struct apei_exec_context *ctx,
+				   struct acpi_whea_header *entry,
+				   void *data)
+{
+	u8 ins = entry->instruction;
+
+	if (ctx->ins_table[ins].flags & APEI_EXEC_INS_ACCESS_REGISTER)
+		acpi_os_unmap_generic_address(&entry->register_region);
+
+	return 0;
+}
+
+/* Post-unmap all GAR in action table. */
+int apei_exec_post_unmap_gars(struct apei_exec_context *ctx)
+{
+	return apei_exec_for_each_entry(ctx, post_unmap_gar_callback,
+					NULL, NULL);
+}
+EXPORT_SYMBOL_GPL(apei_exec_post_unmap_gars);
+
+/*
+ * Resource management for GARs in APEI
+ */
+struct apei_res {
+	struct list_head list;
+	unsigned long start;
+	unsigned long end;
+};
+
+/* Collect all resources requested, to avoid conflict */
+struct apei_resources apei_resources_all = {
+	.iomem = LIST_HEAD_INIT(apei_resources_all.iomem),
+	.ioport = LIST_HEAD_INIT(apei_resources_all.ioport),
+};
+
+static int apei_res_add(struct list_head *res_list,
+			unsigned long start, unsigned long size)
+{
+	struct apei_res *res, *resn, *res_ins = NULL;
+	unsigned long end = start + size;
+
+	if (end <= start)
+		return 0;
+repeat:
+	list_for_each_entry_safe(res, resn, res_list, list) {
+		if (res->start > end || res->end < start)
+			continue;
+		else if (end <= res->end && start >= res->start) {
+			kfree(res_ins);
+			return 0;
+		}
+		list_del(&res->list);
+		res->start = start = min(res->start, start);
+		res->end = end = max(res->end, end);
+		kfree(res_ins);
+		res_ins = res;
+		goto repeat;
+	}
+
+	if (res_ins)
+		list_add(&res_ins->list, res_list);
+	else {
+		res_ins = kmalloc(sizeof(*res), GFP_KERNEL);
+		if (!res_ins)
+			return -ENOMEM;
+		res_ins->start = start;
+		res_ins->end = end;
+		list_add(&res_ins->list, res_list);
+	}
+
+	return 0;
+}
+
+static int apei_res_sub(struct list_head *res_list1,
+			struct list_head *res_list2)
+{
+	struct apei_res *res1, *resn1, *res2, *res;
+	res1 = list_entry(res_list1->next, struct apei_res, list);
+	resn1 = list_entry(res1->list.next, struct apei_res, list);
+	while (&res1->list != res_list1) {
+		list_for_each_entry(res2, res_list2, list) {
+			if (res1->start >= res2->end ||
+			    res1->end <= res2->start)
+				continue;
+			else if (res1->end <= res2->end &&
+				 res1->start >= res2->start) {
+				list_del(&res1->list);
+				kfree(res1);
+				break;
+			} else if (res1->end > res2->end &&
+				   res1->start < res2->start) {
+				res = kmalloc(sizeof(*res), GFP_KERNEL);
+				if (!res)
+					return -ENOMEM;
+				res->start = res2->end;
+				res->end = res1->end;
+				res1->end = res2->start;
+				list_add(&res->list, &res1->list);
+				resn1 = res;
+			} else {
+				if (res1->start < res2->start)
+					res1->end = res2->start;
+				else
+					res1->start = res2->end;
+			}
+		}
+		res1 = resn1;
+		resn1 = list_entry(resn1->list.next, struct apei_res, list);
+	}
+
+	return 0;
+}
+
+static void apei_res_clean(struct list_head *res_list)
+{
+	struct apei_res *res, *resn;
+
+	list_for_each_entry_safe(res, resn, res_list, list) {
+		list_del(&res->list);
+		kfree(res);
+	}
+}
+
+void apei_resources_fini(struct apei_resources *resources)
+{
+	apei_res_clean(&resources->iomem);
+	apei_res_clean(&resources->ioport);
+}
+EXPORT_SYMBOL_GPL(apei_resources_fini);
+
+static int apei_resources_merge(struct apei_resources *resources1,
+				struct apei_resources *resources2)
+{
+	int rc;
+	struct apei_res *res;
+
+	list_for_each_entry(res, &resources2->iomem, list) {
+		rc = apei_res_add(&resources1->iomem, res->start,
+				  res->end - res->start);
+		if (rc)
+			return rc;
+	}
+	list_for_each_entry(res, &resources2->ioport, list) {
+		rc = apei_res_add(&resources1->ioport, res->start,
+				  res->end - res->start);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
+int apei_resources_add(struct apei_resources *resources,
+		       unsigned long start, unsigned long size,
+		       bool iomem)
+{
+	if (iomem)
+		return apei_res_add(&resources->iomem, start, size);
+	else
+		return apei_res_add(&resources->ioport, start, size);
+}
+EXPORT_SYMBOL_GPL(apei_resources_add);
+
+/*
+ * EINJ has two groups of GARs (EINJ table entry and trigger table
+ * entry), so common resources are subtracted from the trigger table
+ * resources before the second requesting.
+ */
+int apei_resources_sub(struct apei_resources *resources1,
+		       struct apei_resources *resources2)
+{
+	int rc;
+
+	rc = apei_res_sub(&resources1->iomem, &resources2->iomem);
+	if (rc)
+		return rc;
+	return apei_res_sub(&resources1->ioport, &resources2->ioport);
+}
+EXPORT_SYMBOL_GPL(apei_resources_sub);
+
+static int apei_get_nvs_callback(__u64 start, __u64 size, void *data)
+{
+	struct apei_resources *resources = data;
+	return apei_res_add(&resources->iomem, start, size);
+}
+
+static int apei_get_nvs_resources(struct apei_resources *resources)
+{
+	return acpi_nvs_for_each_region(apei_get_nvs_callback, resources);
+}
+
+/*
+ * IO memory/port resource management mechanism is used to check
+ * whether memory/port area used by GARs conflicts with normal memory
+ * or IO memory/port of devices.
+ */
+int apei_resources_request(struct apei_resources *resources,
+			   const char *desc)
+{
+	struct apei_res *res, *res_bak = NULL;
+	struct resource *r;
+	struct apei_resources nvs_resources;
+	int rc;
+
+	rc = apei_resources_sub(resources, &apei_resources_all);
+	if (rc)
+		return rc;
+
+	/*
+	 * Some firmware uses ACPI NVS region, that has been marked as
+	 * busy, so exclude it from APEI resources to avoid false
+	 * conflict.
+	 */
+	apei_resources_init(&nvs_resources);
+	rc = apei_get_nvs_resources(&nvs_resources);
+	if (rc)
+		goto res_fini;
+	rc = apei_resources_sub(resources, &nvs_resources);
+	if (rc)
+		goto res_fini;
+
+	rc = -EINVAL;
+	list_for_each_entry(res, &resources->iomem, list) {
+		r = request_mem_region(res->start, res->end - res->start,
+				       desc);
+		if (!r) {
+			pr_err(APEI_PFX
+		"Can not request [mem %#010llx-%#010llx] for %s registers\n",
+			       (unsigned long long)res->start,
+			       (unsigned long long)res->end - 1, desc);
+			res_bak = res;
+			goto err_unmap_iomem;
+		}
+	}
+
+	list_for_each_entry(res, &resources->ioport, list) {
+		r = request_region(res->start, res->end - res->start, desc);
+		if (!r) {
+			pr_err(APEI_PFX
+		"Can not request [io  %#06llx-%#06llx] for %s registers\n",
+			       (unsigned long long)res->start,
+			       (unsigned long long)res->end - 1, desc);
+			res_bak = res;
+			goto err_unmap_ioport;
+		}
+	}
+
+	rc = apei_resources_merge(&apei_resources_all, resources);
+	if (rc) {
+		pr_err(APEI_PFX "Fail to merge resources!\n");
+		goto err_unmap_ioport;
+	}
+
+	return 0;
+err_unmap_ioport:
+	list_for_each_entry(res, &resources->ioport, list) {
+		if (res == res_bak)
+			break;
+		release_region(res->start, res->end - res->start);
+	}
+	res_bak = NULL;
+err_unmap_iomem:
+	list_for_each_entry(res, &resources->iomem, list) {
+		if (res == res_bak)
+			break;
+		release_mem_region(res->start, res->end - res->start);
+	}
+res_fini:
+	apei_resources_fini(&nvs_resources);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(apei_resources_request);
+
+void apei_resources_release(struct apei_resources *resources)
+{
+	int rc;
+	struct apei_res *res;
+
+	list_for_each_entry(res, &resources->iomem, list)
+		release_mem_region(res->start, res->end - res->start);
+	list_for_each_entry(res, &resources->ioport, list)
+		release_region(res->start, res->end - res->start);
+
+	rc = apei_resources_sub(&apei_resources_all, resources);
+	if (rc)
+		pr_err(APEI_PFX "Fail to sub resources!\n");
+}
+EXPORT_SYMBOL_GPL(apei_resources_release);
+
+static int apei_check_gar(struct acpi_generic_address *reg, u64 *paddr,
+				u32 *access_bit_width)
+{
+	u32 bit_width, bit_offset, access_size_code, space_id;
+
+	bit_width = reg->bit_width;
+	bit_offset = reg->bit_offset;
+	access_size_code = reg->access_width;
+	space_id = reg->space_id;
+	/* Handle possible alignment issues */
+	memcpy(paddr, &reg->address, sizeof(*paddr));
+	if (!*paddr) {
+		pr_warning(FW_BUG APEI_PFX
+			   "Invalid physical address in GAR [0x%llx/%u/%u/%u/%u]\n",
+			   *paddr, bit_width, bit_offset, access_size_code,
+			   space_id);
+		return -EINVAL;
+	}
+
+	if (access_size_code < 1 || access_size_code > 4) {
+		pr_warning(FW_BUG APEI_PFX
+			   "Invalid access size code in GAR [0x%llx/%u/%u/%u/%u]\n",
+			   *paddr, bit_width, bit_offset, access_size_code,
+			   space_id);
+		return -EINVAL;
+	}
+	*access_bit_width = 1UL << (access_size_code + 2);
+
+	if ((bit_width + bit_offset) > *access_bit_width) {
+		pr_warning(FW_BUG APEI_PFX
+			   "Invalid bit width + offset in GAR [0x%llx/%u/%u/%u/%u]\n",
+			   *paddr, bit_width, bit_offset, access_size_code,
+			   space_id);
+		return -EINVAL;
+	}
+
+	if (space_id != ACPI_ADR_SPACE_SYSTEM_MEMORY &&
+	    space_id != ACPI_ADR_SPACE_SYSTEM_IO) {
+		pr_warning(FW_BUG APEI_PFX
+			   "Invalid address space type in GAR [0x%llx/%u/%u/%u/%u]\n",
+			   *paddr, bit_width, bit_offset, access_size_code,
+			   space_id);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/* read GAR in interrupt (including NMI) or process context */
+int apei_read(u64 *val, struct acpi_generic_address *reg)
+{
+	int rc;
+	u32 access_bit_width;
+	u64 address;
+	acpi_status status;
+
+	rc = apei_check_gar(reg, &address, &access_bit_width);
+	if (rc)
+		return rc;
+
+	*val = 0;
+	switch(reg->space_id) {
+	case ACPI_ADR_SPACE_SYSTEM_MEMORY:
+		status = acpi_os_read_memory((acpi_physical_address) address,
+					       val, access_bit_width);
+		if (ACPI_FAILURE(status))
+			return -EIO;
+		break;
+	case ACPI_ADR_SPACE_SYSTEM_IO:
+		status = acpi_os_read_port(address, (u32 *)val,
+					   access_bit_width);
+		if (ACPI_FAILURE(status))
+			return -EIO;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(apei_read);
+
+/* write GAR in interrupt (including NMI) or process context */
+int apei_write(u64 val, struct acpi_generic_address *reg)
+{
+	int rc;
+	u32 access_bit_width;
+	u64 address;
+	acpi_status status;
+
+	rc = apei_check_gar(reg, &address, &access_bit_width);
+	if (rc)
+		return rc;
+
+	switch (reg->space_id) {
+	case ACPI_ADR_SPACE_SYSTEM_MEMORY:
+		status = acpi_os_write_memory((acpi_physical_address) address,
+						val, access_bit_width);
+		if (ACPI_FAILURE(status))
+			return -EIO;
+		break;
+	case ACPI_ADR_SPACE_SYSTEM_IO:
+		status = acpi_os_write_port(address, val, access_bit_width);
+		if (ACPI_FAILURE(status))
+			return -EIO;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(apei_write);
+
+static int collect_res_callback(struct apei_exec_context *ctx,
+				struct acpi_whea_header *entry,
+				void *data)
+{
+	struct apei_resources *resources = data;
+	struct acpi_generic_address *reg = &entry->register_region;
+	u8 ins = entry->instruction;
+	u32 access_bit_width;
+	u64 paddr;
+	int rc;
+
+	if (!(ctx->ins_table[ins].flags & APEI_EXEC_INS_ACCESS_REGISTER))
+		return 0;
+
+	rc = apei_check_gar(reg, &paddr, &access_bit_width);
+	if (rc)
+		return rc;
+
+	switch (reg->space_id) {
+	case ACPI_ADR_SPACE_SYSTEM_MEMORY:
+		return apei_res_add(&resources->iomem, paddr,
+				    access_bit_width / 8);
+	case ACPI_ADR_SPACE_SYSTEM_IO:
+		return apei_res_add(&resources->ioport, paddr,
+				    access_bit_width / 8);
+	default:
+		return -EINVAL;
+	}
+}
+
+/*
+ * Same register may be used by multiple instructions in GARs, so
+ * resources are collected before requesting.
+ */
+int apei_exec_collect_resources(struct apei_exec_context *ctx,
+				struct apei_resources *resources)
+{
+	return apei_exec_for_each_entry(ctx, collect_res_callback,
+					resources, NULL);
+}
+EXPORT_SYMBOL_GPL(apei_exec_collect_resources);
+
+struct dentry *apei_get_debugfs_dir(void)
+{
+	static struct dentry *dapei;
+
+	if (!dapei)
+		dapei = debugfs_create_dir("apei", NULL);
+
+	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] = 1;
+	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);

kernel/drivers/acpi/apei/apei-internal.h

@@ -0,0 +1,135 @@
+/*
+ * apei-internal.h - ACPI Platform Error Interface internal
+ * definations.
+ */
+
+#ifndef APEI_INTERNAL_H
+#define APEI_INTERNAL_H
+
+#include <linux/cper.h>
+
+struct apei_exec_context;
+
+typedef int (*apei_exec_ins_func_t)(struct apei_exec_context *ctx,
+				    struct acpi_whea_header *entry);
+
+#define APEI_EXEC_INS_ACCESS_REGISTER	0x0001
+
+struct apei_exec_ins_type {
+	u32 flags;
+	apei_exec_ins_func_t run;
+};
+
+struct apei_exec_context {
+	u32 ip;
+	u64 value;
+	u64 var1;
+	u64 var2;
+	u64 src_base;
+	u64 dst_base;
+	struct apei_exec_ins_type *ins_table;
+	u32 instructions;
+	struct acpi_whea_header *action_table;
+	u32 entries;
+};
+
+void apei_exec_ctx_init(struct apei_exec_context *ctx,
+			struct apei_exec_ins_type *ins_table,
+			u32 instructions,
+			struct acpi_whea_header *action_table,
+			u32 entries);
+
+static inline void apei_exec_ctx_set_input(struct apei_exec_context *ctx,
+					   u64 input)
+{
+	ctx->value = input;
+}
+
+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, 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 */
+
+/* IP has been set in instruction function */
+#define APEI_EXEC_SET_IP	1
+
+int apei_read(u64 *val, struct acpi_generic_address *reg);
+int apei_write(u64 val, struct acpi_generic_address *reg);
+
+int __apei_exec_read_register(struct acpi_whea_header *entry, u64 *val);
+int __apei_exec_write_register(struct acpi_whea_header *entry, u64 val);
+int apei_exec_read_register(struct apei_exec_context *ctx,
+			    struct acpi_whea_header *entry);
+int apei_exec_read_register_value(struct apei_exec_context *ctx,
+				  struct acpi_whea_header *entry);
+int apei_exec_write_register(struct apei_exec_context *ctx,
+			     struct acpi_whea_header *entry);
+int apei_exec_write_register_value(struct apei_exec_context *ctx,
+				   struct acpi_whea_header *entry);
+int apei_exec_noop(struct apei_exec_context *ctx,
+		   struct acpi_whea_header *entry);
+int apei_exec_pre_map_gars(struct apei_exec_context *ctx);
+int apei_exec_post_unmap_gars(struct apei_exec_context *ctx);
+
+struct apei_resources {
+	struct list_head iomem;
+	struct list_head ioport;
+};
+
+static inline void apei_resources_init(struct apei_resources *resources)
+{
+	INIT_LIST_HEAD(&resources->iomem);
+	INIT_LIST_HEAD(&resources->ioport);
+}
+
+void apei_resources_fini(struct apei_resources *resources);
+int apei_resources_add(struct apei_resources *resources,
+		       unsigned long start, unsigned long size,
+		       bool iomem);
+int apei_resources_sub(struct apei_resources *resources1,
+		       struct apei_resources *resources2);
+int apei_resources_request(struct apei_resources *resources,
+			   const char *desc);
+void apei_resources_release(struct apei_resources *resources);
+int apei_exec_collect_resources(struct apei_exec_context *ctx,
+				struct apei_resources *resources);
+
+struct dentry;
+struct dentry *apei_get_debugfs_dir(void);
+
+#define apei_estatus_for_each_section(estatus, section)			\
+	for (section = (struct acpi_hest_generic_data *)(estatus + 1);	\
+	     (void *)section - (void *)estatus < estatus->data_length;	\
+	     section = (void *)(section+1) + section->error_data_length)
+
+static inline u32 apei_estatus_len(struct acpi_hest_generic_status *estatus)
+{
+	if (estatus->raw_data_length)
+		return estatus->raw_data_offset + \
+			estatus->raw_data_length;
+	else
+		return sizeof(*estatus) + estatus->data_length;
+}
+
+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

kernel/drivers/acpi/apei/cper.c

@@ -0,0 +1,407 @@
+/*
+ * UEFI Common Platform Error Record (CPER) support
+ *
+ * Copyright (C) 2010, Intel Corp.
+ *	Author: Huang Ying <ying.huang@intel.com>
+ *
+ * CPER is the format used to describe platform hardware error by
+ * various APEI tables, such as ERST, BERT and HEST etc.
+ *
+ * For more information about CPER, please refer to Appendix N of UEFI
+ * Specification version 2.3.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/time.h>
+#include <linux/cper.h>
+#include <linux/acpi.h>
+#include <linux/aer.h>
+
+/*
+ * CPER record ID need to be unique even after reboot, because record
+ * ID is used as index for ERST storage, while CPER records from
+ * multiple boot may co-exist in ERST.
+ */
+u64 cper_next_record_id(void)
+{
+	static atomic64_t seq;
+
+	if (!atomic64_read(&seq))
+		atomic64_set(&seq, ((u64)get_seconds()) << 32);
+
+	return atomic64_inc_return(&seq);
+}
+EXPORT_SYMBOL_GPL(cper_next_record_id);
+
+static const char *cper_severity_strs[] = {
+	"recoverable",
+	"fatal",
+	"corrected",
+	"info",
+};
+
+static const char *cper_severity_str(unsigned int severity)
+{
+	return severity < ARRAY_SIZE(cper_severity_strs) ?
+		cper_severity_strs[severity] : "unknown";
+}
+
+/*
+ * cper_print_bits - print strings for set bits
+ * @pfx: prefix for each line, including log level and prefix string
+ * @bits: bit mask
+ * @strs: string array, indexed by bit position
+ * @strs_size: size of the string array: @strs
+ *
+ * For each set bit in @bits, print the corresponding string in @strs.
+ * If the output length is longer than 80, multiple line will be
+ * printed, with @pfx is printed at the beginning of each line.
+ */
+void cper_print_bits(const char *pfx, unsigned int bits,
+		     const char *strs[], unsigned int strs_size)
+{
+	int i, len = 0;
+	const char *str;
+	char buf[84];
+
+	for (i = 0; i < strs_size; i++) {
+		if (!(bits & (1U << i)))
+			continue;
+		str = strs[i];
+		if (!str)
+			continue;
+		if (len && len + strlen(str) + 2 > 80) {
+			printk("%s\n", buf);
+			len = 0;
+		}
+		if (!len)
+			len = snprintf(buf, sizeof(buf), "%s%s", pfx, str);
+		else
+			len += snprintf(buf+len, sizeof(buf)-len, ", %s", str);
+	}
+	if (len)
+		printk("%s\n", buf);
+}
+
+static const char *cper_proc_type_strs[] = {
+	"IA32/X64",
+	"IA64",
+};
+
+static const char *cper_proc_isa_strs[] = {
+	"IA32",
+	"IA64",
+	"X64",
+};
+
+static const char *cper_proc_error_type_strs[] = {
+	"cache error",
+	"TLB error",
+	"bus error",
+	"micro-architectural error",
+};
+
+static const char *cper_proc_op_strs[] = {
+	"unknown or generic",
+	"data read",
+	"data write",
+	"instruction execution",
+};
+
+static const char *cper_proc_flag_strs[] = {
+	"restartable",
+	"precise IP",
+	"overflow",
+	"corrected",
+};
+
+static void cper_print_proc_generic(const char *pfx,
+				    const struct cper_sec_proc_generic *proc)
+{
+	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");
+	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");
+	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));
+	}
+	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");
+	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));
+	}
+	if (proc->validation_bits & CPER_PROC_VALID_LEVEL)
+		printk("%s""level: %d\n", pfx, proc->level);
+	if (proc->validation_bits & CPER_PROC_VALID_VERSION)
+		printk("%s""version_info: 0x%016llx\n", pfx, proc->cpu_version);
+	if (proc->validation_bits & CPER_PROC_VALID_ID)
+		printk("%s""processor_id: 0x%016llx\n", pfx, proc->proc_id);
+	if (proc->validation_bits & CPER_PROC_VALID_TARGET_ADDRESS)
+		printk("%s""target_address: 0x%016llx\n",
+		       pfx, proc->target_addr);
+	if (proc->validation_bits & CPER_PROC_VALID_REQUESTOR_ID)
+		printk("%s""requestor_id: 0x%016llx\n",
+		       pfx, proc->requestor_id);
+	if (proc->validation_bits & CPER_PROC_VALID_RESPONDER_ID)
+		printk("%s""responder_id: 0x%016llx\n",
+		       pfx, proc->responder_id);
+	if (proc->validation_bits & CPER_PROC_VALID_IP)
+		printk("%s""IP: 0x%016llx\n", pfx, proc->ip);
+}
+
+static const char *cper_mem_err_type_strs[] = {
+	"unknown",
+	"no error",
+	"single-bit ECC",
+	"multi-bit ECC",
+	"single-symbol chipkill ECC",
+	"multi-symbol chipkill ECC",
+	"master abort",
+	"target abort",
+	"parity error",
+	"watchdog timeout",
+	"invalid address",
+	"mirror Broken",
+	"memory sparing",
+	"scrub corrected error",
+	"scrub uncorrected error",
+};
+
+static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem)
+{
+	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_PHYSICAL_ADDRESS)
+		printk("%s""physical_address: 0x%016llx\n",
+		       pfx, mem->physical_addr);
+	if (mem->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS_MASK)
+		printk("%s""physical_address_mask: 0x%016llx\n",
+		       pfx, mem->physical_addr_mask);
+	if (mem->validation_bits & CPER_MEM_VALID_NODE)
+		printk("%s""node: %d\n", pfx, mem->node);
+	if (mem->validation_bits & CPER_MEM_VALID_CARD)
+		printk("%s""card: %d\n", pfx, mem->card);
+	if (mem->validation_bits & CPER_MEM_VALID_MODULE)
+		printk("%s""module: %d\n", pfx, mem->module);
+	if (mem->validation_bits & CPER_MEM_VALID_BANK)
+		printk("%s""bank: %d\n", pfx, mem->bank);
+	if (mem->validation_bits & CPER_MEM_VALID_DEVICE)
+		printk("%s""device: %d\n", pfx, mem->device);
+	if (mem->validation_bits & CPER_MEM_VALID_ROW)
+		printk("%s""row: %d\n", pfx, mem->row);
+	if (mem->validation_bits & CPER_MEM_VALID_COLUMN)
+		printk("%s""column: %d\n", pfx, mem->column);
+	if (mem->validation_bits & CPER_MEM_VALID_BIT_POSITION)
+		printk("%s""bit_position: %d\n", pfx, mem->bit_pos);
+	if (mem->validation_bits & CPER_MEM_VALID_REQUESTOR_ID)
+		printk("%s""requestor_id: 0x%016llx\n", pfx, mem->requestor_id);
+	if (mem->validation_bits & CPER_MEM_VALID_RESPONDER_ID)
+		printk("%s""responder_id: 0x%016llx\n", pfx, mem->responder_id);
+	if (mem->validation_bits & CPER_MEM_VALID_TARGET_ID)
+		printk("%s""target_id: 0x%016llx\n", pfx, mem->target_id);
+	if (mem->validation_bits & CPER_MEM_VALID_ERROR_TYPE) {
+		u8 etype = mem->error_type;
+		printk("%s""error_type: %d, %s\n", pfx, etype,
+		       etype < ARRAY_SIZE(cper_mem_err_type_strs) ?
+		       cper_mem_err_type_strs[etype] : "unknown");
+	}
+}
+
+static const char *cper_pcie_port_type_strs[] = {
+	"PCIe end point",
+	"legacy PCI end point",
+	"unknown",
+	"unknown",
+	"root port",
+	"upstream switch port",
+	"downstream switch port",
+	"PCIe to PCI/PCI-X bridge",
+	"PCI/PCI-X to PCIe bridge",
+	"root complex integrated endpoint device",
+	"root complex event collector",
+};
+
+static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie,
+			    const struct acpi_hest_generic_data *gdata)
+{
+	if (pcie->validation_bits & CPER_PCIE_VALID_PORT_TYPE)
+		printk("%s""port_type: %d, %s\n", pfx, pcie->port_type,
+		       pcie->port_type < ARRAY_SIZE(cper_pcie_port_type_strs) ?
+		       cper_pcie_port_type_strs[pcie->port_type] : "unknown");
+	if (pcie->validation_bits & CPER_PCIE_VALID_VERSION)
+		printk("%s""version: %d.%d\n", pfx,
+		       pcie->version.major, pcie->version.minor);
+	if (pcie->validation_bits & CPER_PCIE_VALID_COMMAND_STATUS)
+		printk("%s""command: 0x%04x, status: 0x%04x\n", pfx,
+		       pcie->command, pcie->status);
+	if (pcie->validation_bits & CPER_PCIE_VALID_DEVICE_ID) {
+		const __u8 *p;
+		printk("%s""device_id: %04x:%02x:%02x.%x\n", pfx,
+		       pcie->device_id.segment, pcie->device_id.bus,
+		       pcie->device_id.device, pcie->device_id.function);
+		printk("%s""slot: %d\n", pfx,
+		       pcie->device_id.slot >> CPER_PCIE_SLOT_SHIFT);
+		printk("%s""secondary_bus: 0x%02x\n", pfx,
+		       pcie->device_id.secondary_bus);
+		printk("%s""vendor_id: 0x%04x, device_id: 0x%04x\n", pfx,
+		       pcie->device_id.vendor_id, pcie->device_id.device_id);
+		p = pcie->device_id.class_code;
+		printk("%s""class_code: %02x%02x%02x\n", pfx, p[0], p[1], p[2]);
+	}
+	if (pcie->validation_bits & CPER_PCIE_VALID_SERIAL_NUMBER)
+		printk("%s""serial number: 0x%04x, 0x%04x\n", pfx,
+		       pcie->serial_number.lower, pcie->serial_number.upper);
+	if (pcie->validation_bits & CPER_PCIE_VALID_BRIDGE_CONTROL_STATUS)
+		printk(
+	"%s""bridge: secondary_status: 0x%04x, control: 0x%04x\n",
+	pfx, pcie->bridge.secondary_status, pcie->bridge.control);
+#ifdef CONFIG_ACPI_APEI_PCIEAER
+	if (pcie->validation_bits & CPER_PCIE_VALID_AER_INFO) {
+		struct aer_capability_regs *aer_regs = (void *)pcie->aer_info;
+		cper_print_aer(pfx, gdata->error_severity, aer_regs);
+	}
+#endif
+}
+
+static const char *apei_estatus_section_flag_strs[] = {
+	"primary",
+	"containment warning",
+	"reset",
+	"threshold exceeded",
+	"resource not accessible",
+	"latent error",
+};
+
+static void apei_estatus_print_section(
+	const char *pfx, const struct acpi_hest_generic_data *gdata, int sec_no)
+{
+	uuid_le *sec_type = (uuid_le *)gdata->section_type;
+	__u16 severity;
+
+	severity = gdata->error_severity;
+	printk("%s""section: %d, severity: %d, %s\n", pfx, sec_no, severity,
+	       cper_severity_str(severity));
+	printk("%s""flags: 0x%02x\n", pfx, gdata->flags);
+	cper_print_bits(pfx, gdata->flags, apei_estatus_section_flag_strs,
+			ARRAY_SIZE(apei_estatus_section_flag_strs));
+	if (gdata->validation_bits & CPER_SEC_VALID_FRU_ID)
+		printk("%s""fru_id: %pUl\n", pfx, (uuid_le *)gdata->fru_id);
+	if (gdata->validation_bits & CPER_SEC_VALID_FRU_TEXT)
+		printk("%s""fru_text: %.20s\n", pfx, gdata->fru_text);
+
+	if (!uuid_le_cmp(*sec_type, CPER_SEC_PROC_GENERIC)) {
+		struct cper_sec_proc_generic *proc_err = (void *)(gdata + 1);
+		printk("%s""section_type: general processor error\n", pfx);
+		if (gdata->error_data_length >= sizeof(*proc_err))
+			cper_print_proc_generic(pfx, proc_err);
+		else
+			goto err_section_too_small;
+	} else if (!uuid_le_cmp(*sec_type, CPER_SEC_PLATFORM_MEM)) {
+		struct cper_sec_mem_err *mem_err = (void *)(gdata + 1);
+		printk("%s""section_type: memory error\n", pfx);
+		if (gdata->error_data_length >= sizeof(*mem_err))
+			cper_print_mem(pfx, mem_err);
+		else
+			goto err_section_too_small;
+	} else if (!uuid_le_cmp(*sec_type, CPER_SEC_PCIE)) {
+		struct cper_sec_pcie *pcie = (void *)(gdata + 1);
+		printk("%s""section_type: PCIe error\n", pfx);
+		if (gdata->error_data_length >= sizeof(*pcie))
+			cper_print_pcie(pfx, pcie, gdata);
+		else
+			goto err_section_too_small;
+	} else
+		printk("%s""section type: unknown, %pUl\n", pfx, sec_type);
+
+	return;
+
+err_section_too_small:
+	pr_err(FW_WARN "error section length is too small\n");
+}
+
+void apei_estatus_print(const char *pfx,
+			const struct acpi_hest_generic_status *estatus)
+{
+	struct acpi_hest_generic_data *gdata;
+	unsigned int data_len, gedata_len;
+	int sec_no = 0;
+	__u16 severity;
+
+	printk("%s""APEI generic hardware error status\n", pfx);
+	severity = estatus->error_severity;
+	printk("%s""severity: %d, %s\n", pfx, severity,
+	       cper_severity_str(severity));
+	data_len = estatus->data_length;
+	gdata = (struct acpi_hest_generic_data *)(estatus + 1);
+	while (data_len > sizeof(*gdata)) {
+		gedata_len = gdata->error_data_length;
+		apei_estatus_print_section(pfx, gdata, sec_no);
+		data_len -= gedata_len + sizeof(*gdata);
+		gdata = (void *)(gdata + 1) + gedata_len;
+		sec_no++;
+	}
+}
+EXPORT_SYMBOL_GPL(apei_estatus_print);
+
+int apei_estatus_check_header(const struct acpi_hest_generic_status *estatus)
+{
+	if (estatus->data_length &&
+	    estatus->data_length < sizeof(struct acpi_hest_generic_data))
+		return -EINVAL;
+	if (estatus->raw_data_length &&
+	    estatus->raw_data_offset < sizeof(*estatus) + estatus->data_length)
+		return -EINVAL;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(apei_estatus_check_header);
+
+int apei_estatus_check(const struct acpi_hest_generic_status *estatus)
+{
+	struct acpi_hest_generic_data *gdata;
+	unsigned int data_len, gedata_len;
+	int rc;
+
+	rc = apei_estatus_check_header(estatus);
+	if (rc)
+		return rc;
+	data_len = estatus->data_length;
+	gdata = (struct acpi_hest_generic_data *)(estatus + 1);
+	while (data_len > sizeof(*gdata)) {
+		gedata_len = gdata->error_data_length;
+		if (gedata_len > data_len - sizeof(*gdata))
+			return -EINVAL;
+		data_len -= gedata_len + sizeof(*gdata);
+		gdata = (void *)(gdata + 1) + gedata_len;
+	}
+	if (data_len)
+		return -EINVAL;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(apei_estatus_check);

kernel/drivers/acpi/apei/einj.c

@@ -0,0 +1,773 @@
+/*
+ * APEI Error INJection support
+ *
+ * EINJ provides a hardware error injection mechanism, this is useful
+ * for debugging and testing of other APEI and RAS features.
+ *
+ * For more information about EINJ, please refer to ACPI Specification
+ * version 4.0, section 17.5.
+ *
+ * Copyright 2009-2010 Intel Corp.
+ *   Author: Huang Ying <ying.huang@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/nmi.h>
+#include <linux/delay.h>
+#include <acpi/acpi.h>
+
+#include "apei-internal.h"
+
+#define EINJ_PFX "EINJ: "
+
+#define SPIN_UNIT		100			/* 100ns */
+/* Firmware should respond within 1 milliseconds */
+#define FIRMWARE_TIMEOUT	(1 * NSEC_PER_MSEC)
+
+/*
+ * ACPI version 5 provides a SET_ERROR_TYPE_WITH_ADDRESS action.
+ */
+static int acpi5;
+
+struct set_error_type_with_address {
+	u32	type;
+	u32	vendor_extension;
+	u32	flags;
+	u32	apicid;
+	u64	memory_address;
+	u64	memory_address_range;
+	u32	pcie_sbdf;
+};
+enum {
+	SETWA_FLAGS_APICID = 1,
+	SETWA_FLAGS_MEM = 2,
+	SETWA_FLAGS_PCIE_SBDF = 4,
+};
+
+/*
+ * Vendor extensions for platform specific operations
+ */
+struct vendor_error_type_extension {
+	u32	length;
+	u32	pcie_sbdf;
+	u16	vendor_id;
+	u16	device_id;
+	u8	rev_id;
+	u8	reserved[3];
+};
+
+static u32 notrigger;
+
+static u32 vendor_flags;
+static struct debugfs_blob_wrapper vendor_blob;
+static char vendor_dev[64];
+
+/*
+ * 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.  This extension is used only if
+ * param_extension module parameter is specified.
+ */
+struct einj_parameter {
+	u64 type;
+	u64 reserved1;
+	u64 reserved2;
+	u64 param1;
+	u64 param2;
+};
+
+#define EINJ_OP_BUSY			0x1
+#define EINJ_STATUS_SUCCESS		0x0
+#define EINJ_STATUS_FAIL		0x1
+#define EINJ_STATUS_INVAL		0x2
+
+#define EINJ_TAB_ENTRY(tab)						\
+	((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;
+
+static struct apei_exec_ins_type einj_ins_type[] = {
+	[ACPI_EINJ_READ_REGISTER] = {
+		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
+		.run   = apei_exec_read_register,
+	},
+	[ACPI_EINJ_READ_REGISTER_VALUE] = {
+		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
+		.run   = apei_exec_read_register_value,
+	},
+	[ACPI_EINJ_WRITE_REGISTER] = {
+		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
+		.run   = apei_exec_write_register,
+	},
+	[ACPI_EINJ_WRITE_REGISTER_VALUE] = {
+		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
+		.run   = apei_exec_write_register_value,
+	},
+	[ACPI_EINJ_NOOP] = {
+		.flags = 0,
+		.run   = apei_exec_noop,
+	},
+};
+
+/*
+ * Prevent EINJ interpreter to run simultaneously, because the
+ * corresponding firmware implementation may not work properly when
+ * invoked simultaneously.
+ */
+static DEFINE_MUTEX(einj_mutex);
+
+static void *einj_param;
+
+static void einj_exec_ctx_init(struct apei_exec_context *ctx)
+{
+	apei_exec_ctx_init(ctx, einj_ins_type, ARRAY_SIZE(einj_ins_type),
+			   EINJ_TAB_ENTRY(einj_tab), einj_tab->entries);
+}
+
+static int __einj_get_available_error_type(u32 *type)
+{
+	struct apei_exec_context ctx;
+	int rc;
+
+	einj_exec_ctx_init(&ctx);
+	rc = apei_exec_run(&ctx, ACPI_EINJ_GET_ERROR_TYPE);
+	if (rc)
+		return rc;
+	*type = apei_exec_ctx_get_output(&ctx);
+
+	return 0;
+}
+
+/* Get error injection capabilities of the platform */
+static int einj_get_available_error_type(u32 *type)
+{
+	int rc;
+
+	mutex_lock(&einj_mutex);
+	rc = __einj_get_available_error_type(type);
+	mutex_unlock(&einj_mutex);
+
+	return rc;
+}
+
+static int einj_timedout(u64 *t)
+{
+	if ((s64)*t < SPIN_UNIT) {
+		pr_warning(FW_WARN EINJ_PFX
+			   "Firmware does not respond in time\n");
+		return 1;
+	}
+	*t -= SPIN_UNIT;
+	ndelay(SPIN_UNIT);
+	touch_nmi_watchdog();
+	return 0;
+}
+
+static void check_vendor_extension(u64 paddr,
+				   struct set_error_type_with_address *v5param)
+{
+	int	offset = v5param->vendor_extension;
+	struct	vendor_error_type_extension *v;
+	u32	sbdf;
+
+	if (!offset)
+		return;
+	v = acpi_os_map_memory(paddr + offset, sizeof(*v));
+	if (!v)
+		return;
+	sbdf = v->pcie_sbdf;
+	sprintf(vendor_dev, "%x:%x:%x.%x vendor_id=%x device_id=%x rev_id=%x\n",
+		sbdf >> 24, (sbdf >> 16) & 0xff,
+		(sbdf >> 11) & 0x1f, (sbdf >> 8) & 0x7,
+		 v->vendor_id, v->device_id, v->rev_id);
+	acpi_os_unmap_memory(v, sizeof(*v));
+}
+
+static void *einj_get_parameter_address(void)
+{
+	int i;
+	u64 paddrv4 = 0, paddrv5 = 0;
+	struct acpi_whea_header *entry;
+
+	entry = EINJ_TAB_ENTRY(einj_tab);
+	for (i = 0; i < einj_tab->entries; i++) {
+		if (entry->action == ACPI_EINJ_SET_ERROR_TYPE &&
+		    entry->instruction == ACPI_EINJ_WRITE_REGISTER &&
+		    entry->register_region.space_id ==
+		    ACPI_ADR_SPACE_SYSTEM_MEMORY)
+			memcpy(&paddrv4, &entry->register_region.address,
+			       sizeof(paddrv4));
+		if (entry->action == ACPI_EINJ_SET_ERROR_TYPE_WITH_ADDRESS &&
+		    entry->instruction == ACPI_EINJ_WRITE_REGISTER &&
+		    entry->register_region.space_id ==
+		    ACPI_ADR_SPACE_SYSTEM_MEMORY)
+			memcpy(&paddrv5, &entry->register_region.address,
+			       sizeof(paddrv5));
+		entry++;
+	}
+	if (paddrv5) {
+		struct set_error_type_with_address *v5param;
+
+		v5param = acpi_os_map_memory(paddrv5, sizeof(*v5param));
+		if (v5param) {
+			acpi5 = 1;
+			check_vendor_extension(paddrv5, v5param);
+			return v5param;
+		}
+	}
+	if (param_extension && paddrv4) {
+		struct einj_parameter *v4param;
+
+		v4param = acpi_os_map_memory(paddrv4, sizeof(*v4param));
+		if (!v4param)
+			return NULL;
+		if (v4param->reserved1 || v4param->reserved2) {
+			acpi_os_unmap_memory(v4param, sizeof(*v4param));
+			return NULL;
+		}
+		return v4param;
+	}
+
+	return NULL;
+}
+
+/* do sanity check to trigger table */
+static int einj_check_trigger_header(struct acpi_einj_trigger *trigger_tab)
+{
+	if (trigger_tab->header_size != sizeof(struct acpi_einj_trigger))
+		return -EINVAL;
+	if (trigger_tab->table_size > PAGE_SIZE ||
+	    trigger_tab->table_size < trigger_tab->header_size)
+		return -EINVAL;
+	if (trigger_tab->entry_count !=
+	    (trigger_tab->table_size - trigger_tab->header_size) /
+	    sizeof(struct acpi_einj_entry))
+		return -EINVAL;
+
+	return 0;
+}
+
+static struct acpi_generic_address *einj_get_trigger_parameter_region(
+	struct acpi_einj_trigger *trigger_tab, u64 param1, u64 param2)
+{
+	int i;
+	struct acpi_whea_header *entry;
+
+	entry = (struct acpi_whea_header *)
+		((char *)trigger_tab + sizeof(struct acpi_einj_trigger));
+	for (i = 0; i < trigger_tab->entry_count; i++) {
+		if (entry->action == ACPI_EINJ_TRIGGER_ERROR &&
+		entry->instruction == ACPI_EINJ_WRITE_REGISTER_VALUE &&
+		entry->register_region.space_id ==
+			ACPI_ADR_SPACE_SYSTEM_MEMORY &&
+		(entry->register_region.address & param2) == (param1 & param2))
+			return &entry->register_region;
+		entry++;
+	}
+
+	return NULL;
+}
+/* Execute instructions in trigger error action table */
+static int __einj_error_trigger(u64 trigger_paddr, u32 type,
+				u64 param1, u64 param2)
+{
+	struct acpi_einj_trigger *trigger_tab = NULL;
+	struct apei_exec_context trigger_ctx;
+	struct apei_resources trigger_resources;
+	struct acpi_whea_header *trigger_entry;
+	struct resource *r;
+	u32 table_size;
+	int rc = -EIO;
+	struct acpi_generic_address *trigger_param_region = NULL;
+
+	r = request_mem_region(trigger_paddr, sizeof(*trigger_tab),
+			       "APEI EINJ Trigger Table");
+	if (!r) {
+		pr_err(EINJ_PFX
+	"Can not request [mem %#010llx-%#010llx] for Trigger table\n",
+		       (unsigned long long)trigger_paddr,
+		       (unsigned long long)trigger_paddr +
+			    sizeof(*trigger_tab) - 1);
+		goto out;
+	}
+	trigger_tab = ioremap_cache(trigger_paddr, sizeof(*trigger_tab));
+	if (!trigger_tab) {
+		pr_err(EINJ_PFX "Failed to map trigger table!\n");
+		goto out_rel_header;
+	}
+	rc = einj_check_trigger_header(trigger_tab);
+	if (rc) {
+		pr_warning(FW_BUG EINJ_PFX
+			   "The trigger error action table is invalid\n");
+		goto out_rel_header;
+	}
+
+	/* No action structures in the TRIGGER_ERROR table, nothing to do */
+	if (!trigger_tab->entry_count)
+		goto out_rel_header;
+
+	rc = -EIO;
+	table_size = trigger_tab->table_size;
+	r = request_mem_region(trigger_paddr + sizeof(*trigger_tab),
+			       table_size - sizeof(*trigger_tab),
+			       "APEI EINJ Trigger Table");
+	if (!r) {
+		pr_err(EINJ_PFX
+"Can not request [mem %#010llx-%#010llx] for Trigger Table Entry\n",
+		       (unsigned long long)trigger_paddr + sizeof(*trigger_tab),
+		       (unsigned long long)trigger_paddr + table_size - 1);
+		goto out_rel_header;
+	}
+	iounmap(trigger_tab);
+	trigger_tab = ioremap_cache(trigger_paddr, table_size);
+	if (!trigger_tab) {
+		pr_err(EINJ_PFX "Failed to map trigger table!\n");
+		goto out_rel_entry;
+	}
+	trigger_entry = (struct acpi_whea_header *)
+		((char *)trigger_tab + sizeof(struct acpi_einj_trigger));
+	apei_resources_init(&trigger_resources);
+	apei_exec_ctx_init(&trigger_ctx, einj_ins_type,
+			   ARRAY_SIZE(einj_ins_type),
+			   trigger_entry, trigger_tab->entry_count);
+	rc = apei_exec_collect_resources(&trigger_ctx, &trigger_resources);
+	if (rc)
+		goto out_fini;
+	rc = apei_resources_sub(&trigger_resources, &einj_resources);
+	if (rc)
+		goto out_fini;
+	/*
+	 * Some firmware will access target address specified in
+	 * param1 to trigger the error when injecting memory error.
+	 * This will cause resource conflict with regular memory.  So
+	 * remove it from trigger table resources.
+	 */
+	if (param_extension && (type & 0x0038) && param2) {
+		struct apei_resources addr_resources;
+		apei_resources_init(&addr_resources);
+		trigger_param_region = einj_get_trigger_parameter_region(
+			trigger_tab, param1, param2);
+		if (trigger_param_region) {
+			rc = apei_resources_add(&addr_resources,
+				trigger_param_region->address,
+				trigger_param_region->bit_width/8, true);
+			if (rc)
+				goto out_fini;
+			rc = apei_resources_sub(&trigger_resources,
+					&addr_resources);
+		}
+		apei_resources_fini(&addr_resources);
+		if (rc)
+			goto out_fini;
+	}
+	rc = apei_resources_request(&trigger_resources, "APEI EINJ Trigger");
+	if (rc)
+		goto out_fini;
+	rc = apei_exec_pre_map_gars(&trigger_ctx);
+	if (rc)
+		goto out_release;
+
+	rc = apei_exec_run(&trigger_ctx, ACPI_EINJ_TRIGGER_ERROR);
+
+	apei_exec_post_unmap_gars(&trigger_ctx);
+out_release:
+	apei_resources_release(&trigger_resources);
+out_fini:
+	apei_resources_fini(&trigger_resources);
+out_rel_entry:
+	release_mem_region(trigger_paddr + sizeof(*trigger_tab),
+			   table_size - sizeof(*trigger_tab));
+out_rel_header:
+	release_mem_region(trigger_paddr, sizeof(*trigger_tab));
+out:
+	if (trigger_tab)
+		iounmap(trigger_tab);
+
+	return rc;
+}
+
+static int __einj_error_inject(u32 type, u64 param1, u64 param2)
+{
+	struct apei_exec_context ctx;
+	u64 val, trigger_paddr, timeout = FIRMWARE_TIMEOUT;
+	int rc;
+
+	einj_exec_ctx_init(&ctx);
+
+	rc = apei_exec_run_optional(&ctx, ACPI_EINJ_BEGIN_OPERATION);
+	if (rc)
+		return rc;
+	apei_exec_ctx_set_input(&ctx, type);
+	if (acpi5) {
+		struct set_error_type_with_address *v5param = einj_param;
+
+		v5param->type = type;
+		if (type & 0x80000000) {
+			switch (vendor_flags) {
+			case SETWA_FLAGS_APICID:
+				v5param->apicid = param1;
+				break;
+			case SETWA_FLAGS_MEM:
+				v5param->memory_address = param1;
+				v5param->memory_address_range = param2;
+				break;
+			case SETWA_FLAGS_PCIE_SBDF:
+				v5param->pcie_sbdf = param1;
+				break;
+			}
+			v5param->flags = vendor_flags;
+		} else {
+			switch (type) {
+			case ACPI_EINJ_PROCESSOR_CORRECTABLE:
+			case ACPI_EINJ_PROCESSOR_UNCORRECTABLE:
+			case ACPI_EINJ_PROCESSOR_FATAL:
+				v5param->apicid = param1;
+				v5param->flags = SETWA_FLAGS_APICID;
+				break;
+			case ACPI_EINJ_MEMORY_CORRECTABLE:
+			case ACPI_EINJ_MEMORY_UNCORRECTABLE:
+			case ACPI_EINJ_MEMORY_FATAL:
+				v5param->memory_address = param1;
+				v5param->memory_address_range = param2;
+				v5param->flags = SETWA_FLAGS_MEM;
+				break;
+			case ACPI_EINJ_PCIX_CORRECTABLE:
+			case ACPI_EINJ_PCIX_UNCORRECTABLE:
+			case ACPI_EINJ_PCIX_FATAL:
+				v5param->pcie_sbdf = param1;
+				v5param->flags = SETWA_FLAGS_PCIE_SBDF;
+				break;
+			}
+		}
+	} else {
+		rc = apei_exec_run(&ctx, ACPI_EINJ_SET_ERROR_TYPE);
+		if (rc)
+			return rc;
+		if (einj_param) {
+			struct einj_parameter *v4param = einj_param;
+			v4param->param1 = param1;
+			v4param->param2 = param2;
+		}
+	}
+	rc = apei_exec_run(&ctx, ACPI_EINJ_EXECUTE_OPERATION);
+	if (rc)
+		return rc;
+	for (;;) {
+		rc = apei_exec_run(&ctx, ACPI_EINJ_CHECK_BUSY_STATUS);
+		if (rc)
+			return rc;
+		val = apei_exec_ctx_get_output(&ctx);
+		if (!(val & EINJ_OP_BUSY))
+			break;
+		if (einj_timedout(&timeout))
+			return -EIO;
+	}
+	rc = apei_exec_run(&ctx, ACPI_EINJ_GET_COMMAND_STATUS);
+	if (rc)
+		return rc;
+	val = apei_exec_ctx_get_output(&ctx);
+	if (val != EINJ_STATUS_SUCCESS)
+		return -EBUSY;
+
+	rc = apei_exec_run(&ctx, ACPI_EINJ_GET_TRIGGER_TABLE);
+	if (rc)
+		return rc;
+	trigger_paddr = apei_exec_ctx_get_output(&ctx);
+	if (notrigger == 0) {
+		rc = __einj_error_trigger(trigger_paddr, type, param1, param2);
+		if (rc)
+			return rc;
+	}
+	rc = apei_exec_run_optional(&ctx, ACPI_EINJ_END_OPERATION);
+
+	return rc;
+}
+
+/* Inject the specified hardware error */
+static int einj_error_inject(u32 type, u64 param1, u64 param2)
+{
+	int rc;
+
+	mutex_lock(&einj_mutex);
+	rc = __einj_error_inject(type, param1, param2);
+	mutex_unlock(&einj_mutex);
+
+	return rc;
+}
+
+static u32 error_type;
+static u64 error_param1;
+static u64 error_param2;
+static struct dentry *einj_debug_dir;
+
+static int available_error_type_show(struct seq_file *m, void *v)
+{
+	int rc;
+	u32 available_error_type = 0;
+
+	rc = einj_get_available_error_type(&available_error_type);
+	if (rc)
+		return rc;
+	if (available_error_type & 0x0001)
+		seq_printf(m, "0x00000001\tProcessor Correctable\n");
+	if (available_error_type & 0x0002)
+		seq_printf(m, "0x00000002\tProcessor Uncorrectable non-fatal\n");
+	if (available_error_type & 0x0004)
+		seq_printf(m, "0x00000004\tProcessor Uncorrectable fatal\n");
+	if (available_error_type & 0x0008)
+		seq_printf(m, "0x00000008\tMemory Correctable\n");
+	if (available_error_type & 0x0010)
+		seq_printf(m, "0x00000010\tMemory Uncorrectable non-fatal\n");
+	if (available_error_type & 0x0020)
+		seq_printf(m, "0x00000020\tMemory Uncorrectable fatal\n");
+	if (available_error_type & 0x0040)
+		seq_printf(m, "0x00000040\tPCI Express Correctable\n");
+	if (available_error_type & 0x0080)
+		seq_printf(m, "0x00000080\tPCI Express Uncorrectable non-fatal\n");
+	if (available_error_type & 0x0100)
+		seq_printf(m, "0x00000100\tPCI Express Uncorrectable fatal\n");
+	if (available_error_type & 0x0200)
+		seq_printf(m, "0x00000200\tPlatform Correctable\n");
+	if (available_error_type & 0x0400)
+		seq_printf(m, "0x00000400\tPlatform Uncorrectable non-fatal\n");
+	if (available_error_type & 0x0800)
+		seq_printf(m, "0x00000800\tPlatform Uncorrectable fatal\n");
+
+	return 0;
+}
+
+static int available_error_type_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, available_error_type_show, NULL);
+}
+
+static const struct file_operations available_error_type_fops = {
+	.open		= available_error_type_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int error_type_get(void *data, u64 *val)
+{
+	*val = error_type;
+
+	return 0;
+}
+
+static int error_type_set(void *data, u64 val)
+{
+	int rc;
+	u32 available_error_type = 0;
+	u32 tval, vendor;
+
+	/*
+	 * Vendor defined types have 0x80000000 bit set, and
+	 * are not enumerated by ACPI_EINJ_GET_ERROR_TYPE
+	 */
+	vendor = val & 0x80000000;
+	tval = val & 0x7fffffff;
+
+	/* Only one error type can be specified */
+	if (tval & (tval - 1))
+		return -EINVAL;
+	if (!vendor) {
+		rc = einj_get_available_error_type(&available_error_type);
+		if (rc)
+			return rc;
+		if (!(val & available_error_type))
+			return -EINVAL;
+	}
+	error_type = val;
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(error_type_fops, error_type_get,
+			error_type_set, "0x%llx\n");
+
+static int error_inject_set(void *data, u64 val)
+{
+	if (!error_type)
+		return -EINVAL;
+
+	return einj_error_inject(error_type, error_param1, error_param2);
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(error_inject_fops, NULL,
+			error_inject_set, "%llu\n");
+
+static int einj_check_table(struct acpi_table_einj *einj_tab)
+{
+	if ((einj_tab->header_length !=
+	     (sizeof(struct acpi_table_einj) - sizeof(einj_tab->header)))
+	    && (einj_tab->header_length != sizeof(struct acpi_table_einj)))
+		return -EINVAL;
+	if (einj_tab->header.length < sizeof(struct acpi_table_einj))
+		return -EINVAL;
+	if (einj_tab->entries !=
+	    (einj_tab->header.length - sizeof(struct acpi_table_einj)) /
+	    sizeof(struct acpi_einj_entry))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int __init einj_init(void)
+{
+	int rc;
+	acpi_status status;
+	struct dentry *fentry;
+	struct apei_exec_context ctx;
+
+	if (acpi_disabled)
+		return -ENODEV;
+
+	status = acpi_get_table(ACPI_SIG_EINJ, 0,
+				(struct acpi_table_header **)&einj_tab);
+	if (status == AE_NOT_FOUND)
+		return -ENODEV;
+	else if (ACPI_FAILURE(status)) {
+		const char *msg = acpi_format_exception(status);
+		pr_err(EINJ_PFX "Failed to get table, %s\n", msg);
+		return -EINVAL;
+	}
+
+	rc = einj_check_table(einj_tab);
+	if (rc) {
+		pr_warning(FW_BUG EINJ_PFX "EINJ table is invalid\n");
+		return -EINVAL;
+	}
+
+	rc = -ENOMEM;
+	einj_debug_dir = debugfs_create_dir("einj", apei_get_debugfs_dir());
+	if (!einj_debug_dir)
+		goto err_cleanup;
+	fentry = debugfs_create_file("available_error_type", S_IRUSR,
+				     einj_debug_dir, NULL,
+				     &available_error_type_fops);
+	if (!fentry)
+		goto err_cleanup;
+	fentry = debugfs_create_file("error_type", S_IRUSR | S_IWUSR,
+				     einj_debug_dir, NULL, &error_type_fops);
+	if (!fentry)
+		goto err_cleanup;
+	fentry = debugfs_create_file("error_inject", S_IWUSR,
+				     einj_debug_dir, NULL, &error_inject_fops);
+	if (!fentry)
+		goto err_cleanup;
+
+	apei_resources_init(&einj_resources);
+	einj_exec_ctx_init(&ctx);
+	rc = apei_exec_collect_resources(&ctx, &einj_resources);
+	if (rc)
+		goto err_fini;
+	rc = apei_resources_request(&einj_resources, "APEI EINJ");
+	if (rc)
+		goto err_fini;
+	rc = apei_exec_pre_map_gars(&ctx);
+	if (rc)
+		goto err_release;
+
+	einj_param = einj_get_parameter_address();
+	if ((param_extension || acpi5) && einj_param) {
+		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;
+
+		fentry = debugfs_create_x32("notrigger", S_IRUSR | S_IWUSR,
+					    einj_debug_dir, &notrigger);
+		if (!fentry)
+			goto err_unmap;
+	}
+
+	if (vendor_dev[0]) {
+		vendor_blob.data = vendor_dev;
+		vendor_blob.size = strlen(vendor_dev);
+		fentry = debugfs_create_blob("vendor", S_IRUSR,
+					     einj_debug_dir, &vendor_blob);
+		if (!fentry)
+			goto err_unmap;
+		fentry = debugfs_create_x32("vendor_flags", S_IRUSR | S_IWUSR,
+					    einj_debug_dir, &vendor_flags);
+		if (!fentry)
+			goto err_unmap;
+	}
+
+	pr_info(EINJ_PFX "Error INJection is initialized.\n");
+
+	return 0;
+
+err_unmap:
+	if (einj_param) {
+		acpi_size size = (acpi5) ?
+			sizeof(struct set_error_type_with_address) :
+			sizeof(struct einj_parameter);
+
+		acpi_os_unmap_memory(einj_param, size);
+	}
+	apei_exec_post_unmap_gars(&ctx);
+err_release:
+	apei_resources_release(&einj_resources);
+err_fini:
+	apei_resources_fini(&einj_resources);
+err_cleanup:
+	debugfs_remove_recursive(einj_debug_dir);
+
+	return rc;
+}
+
+static void __exit einj_exit(void)
+{
+	struct apei_exec_context ctx;
+
+	if (einj_param) {
+		acpi_size size = (acpi5) ?
+			sizeof(struct set_error_type_with_address) :
+			sizeof(struct einj_parameter);
+
+		acpi_os_unmap_memory(einj_param, size);
+	}
+	einj_exec_ctx_init(&ctx);
+	apei_exec_post_unmap_gars(&ctx);
+	apei_resources_release(&einj_resources);
+	apei_resources_fini(&einj_resources);
+	debugfs_remove_recursive(einj_debug_dir);
+}
+
+module_init(einj_init);
+module_exit(einj_exit);
+
+MODULE_AUTHOR("Huang Ying");
+MODULE_DESCRIPTION("APEI Error INJection support");
+MODULE_LICENSE("GPL");

kernel/drivers/acpi/apei/erst-dbg.c

@@ -0,0 +1,234 @@
+/*
+ * APEI Error Record Serialization Table debug support
+ *
+ * ERST is a way provided by APEI to save and retrieve hardware error
+ * information to and from a persistent store. This file provide the
+ * debugging/testing support for ERST kernel support and firmware
+ * implementation.
+ *
+ * Copyright 2010 Intel Corp.
+ *   Author: Huang Ying <ying.huang@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/uaccess.h>
+#include <acpi/apei.h>
+#include <linux/miscdevice.h>
+
+#include "apei-internal.h"
+
+#define ERST_DBG_PFX			"ERST DBG: "
+
+#define ERST_DBG_RECORD_LEN_MAX		0x4000
+
+static void *erst_dbg_buf;
+static unsigned int erst_dbg_buf_len;
+
+/* Prevent erst_dbg_read/write from being invoked concurrently */
+static DEFINE_MUTEX(erst_dbg_mutex);
+
+static int erst_dbg_open(struct inode *inode, struct file *file)
+{
+	int rc, *pos;
+
+	if (erst_disable)
+		return -ENODEV;
+
+	pos = (int *)&file->private_data;
+
+	rc = erst_get_record_id_begin(pos);
+	if (rc)
+		return rc;
+
+	return nonseekable_open(inode, file);
+}
+
+static int erst_dbg_release(struct inode *inode, struct file *file)
+{
+	erst_get_record_id_end();
+
+	return 0;
+}
+
+static long erst_dbg_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
+{
+	int rc;
+	u64 record_id;
+	u32 record_count;
+
+	switch (cmd) {
+	case APEI_ERST_CLEAR_RECORD:
+		rc = copy_from_user(&record_id, (void __user *)arg,
+				    sizeof(record_id));
+		if (rc)
+			return -EFAULT;
+		return erst_clear(record_id);
+	case APEI_ERST_GET_RECORD_COUNT:
+		rc = erst_get_record_count();
+		if (rc < 0)
+			return rc;
+		record_count = rc;
+		rc = put_user(record_count, (u32 __user *)arg);
+		if (rc)
+			return rc;
+		return 0;
+	default:
+		return -ENOTTY;
+	}
+}
+
+static ssize_t erst_dbg_read(struct file *filp, char __user *ubuf,
+			     size_t usize, loff_t *off)
+{
+	int rc, *pos;
+	ssize_t len = 0;
+	u64 id;
+
+	if (*off)
+		return -EINVAL;
+
+	if (mutex_lock_interruptible(&erst_dbg_mutex) != 0)
+		return -EINTR;
+
+	pos = (int *)&filp->private_data;
+
+retry_next:
+	rc = erst_get_record_id_next(pos, &id);
+	if (rc)
+		goto out;
+	/* no more record */
+	if (id == APEI_ERST_INVALID_RECORD_ID)
+		goto out;
+retry:
+	rc = len = erst_read(id, erst_dbg_buf, erst_dbg_buf_len);
+	/* The record may be cleared by others, try read next record */
+	if (rc == -ENOENT)
+		goto retry_next;
+	if (rc < 0)
+		goto out;
+	if (len > ERST_DBG_RECORD_LEN_MAX) {
+		pr_warning(ERST_DBG_PFX
+			   "Record (ID: 0x%llx) length is too long: %zd\n",
+			   id, len);
+		rc = -EIO;
+		goto out;
+	}
+	if (len > erst_dbg_buf_len) {
+		void *p;
+		rc = -ENOMEM;
+		p = kmalloc(len, GFP_KERNEL);
+		if (!p)
+			goto out;
+		kfree(erst_dbg_buf);
+		erst_dbg_buf = p;
+		erst_dbg_buf_len = len;
+		goto retry;
+	}
+
+	rc = -EINVAL;
+	if (len > usize)
+		goto out;
+
+	rc = -EFAULT;
+	if (copy_to_user(ubuf, erst_dbg_buf, len))
+		goto out;
+	rc = 0;
+out:
+	mutex_unlock(&erst_dbg_mutex);
+	return rc ? rc : len;
+}
+
+static ssize_t erst_dbg_write(struct file *filp, const char __user *ubuf,
+			      size_t usize, loff_t *off)
+{
+	int rc;
+	struct cper_record_header *rcd;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (usize > ERST_DBG_RECORD_LEN_MAX) {
+		pr_err(ERST_DBG_PFX "Too long record to be written\n");
+		return -EINVAL;
+	}
+
+	if (mutex_lock_interruptible(&erst_dbg_mutex))
+		return -EINTR;
+	if (usize > erst_dbg_buf_len) {
+		void *p;
+		rc = -ENOMEM;
+		p = kmalloc(usize, GFP_KERNEL);
+		if (!p)
+			goto out;
+		kfree(erst_dbg_buf);
+		erst_dbg_buf = p;
+		erst_dbg_buf_len = usize;
+	}
+	rc = copy_from_user(erst_dbg_buf, ubuf, usize);
+	if (rc) {
+		rc = -EFAULT;
+		goto out;
+	}
+	rcd = erst_dbg_buf;
+	rc = -EINVAL;
+	if (rcd->record_length != usize)
+		goto out;
+
+	rc = erst_write(erst_dbg_buf);
+
+out:
+	mutex_unlock(&erst_dbg_mutex);
+	return rc < 0 ? rc : usize;
+}
+
+static const struct file_operations erst_dbg_ops = {
+	.owner		= THIS_MODULE,
+	.open		= erst_dbg_open,
+	.release	= erst_dbg_release,
+	.read		= erst_dbg_read,
+	.write		= erst_dbg_write,
+	.unlocked_ioctl	= erst_dbg_ioctl,
+	.llseek		= no_llseek,
+};
+
+static struct miscdevice erst_dbg_dev = {
+	.minor	= MISC_DYNAMIC_MINOR,
+	.name	= "erst_dbg",
+	.fops	= &erst_dbg_ops,
+};
+
+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);
+}
+
+static __exit void erst_dbg_exit(void)
+{
+	misc_deregister(&erst_dbg_dev);
+	kfree(erst_dbg_buf);
+}
+
+module_init(erst_dbg_init);
+module_exit(erst_dbg_exit);
+
+MODULE_AUTHOR("Huang Ying");
+MODULE_DESCRIPTION("APEI Error Record Serialization Table debug support");
+MODULE_LICENSE("GPL");

kernel/drivers/acpi/apei/hest.c

@@ -0,0 +1,246 @@
+/*
+ * APEI Hardware Error Souce Table support
+ *
+ * HEST describes error sources in detail; communicates operational
+ * parameters (i.e. severity levels, masking bits, and threshold
+ * values) to Linux as necessary. It also allows the BIOS to report
+ * non-standard error sources to Linux (for example, chipset-specific
+ * error registers).
+ *
+ * For more information about HEST, please refer to ACPI Specification
+ * version 4.0, section 17.3.2.
+ *
+ * Copyright 2009 Intel Corp.
+ *   Author: Huang Ying <ying.huang@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation;
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/acpi.h>
+#include <linux/kdebug.h>
+#include <linux/highmem.h>
+#include <linux/io.h>
+#include <linux/platform_device.h>
+#include <acpi/apei.h>
+
+#include "apei-internal.h"
+
+#define HEST_PFX "HEST: "
+
+bool hest_disable;
+EXPORT_SYMBOL_GPL(hest_disable);
+
+/* HEST table parsing */
+
+static struct acpi_table_hest *__read_mostly hest_tab;
+
+static const int hest_esrc_len_tab[ACPI_HEST_TYPE_RESERVED] = {
+	[ACPI_HEST_TYPE_IA32_CHECK] = -1,	/* need further calculation */
+	[ACPI_HEST_TYPE_IA32_CORRECTED_CHECK] = -1,
+	[ACPI_HEST_TYPE_IA32_NMI] = sizeof(struct acpi_hest_ia_nmi),
+	[ACPI_HEST_TYPE_AER_ROOT_PORT] = sizeof(struct acpi_hest_aer_root),
+	[ACPI_HEST_TYPE_AER_ENDPOINT] = sizeof(struct acpi_hest_aer),
+	[ACPI_HEST_TYPE_AER_BRIDGE] = sizeof(struct acpi_hest_aer_bridge),
+	[ACPI_HEST_TYPE_GENERIC_ERROR] = sizeof(struct acpi_hest_generic),
+};
+
+static int hest_esrc_len(struct acpi_hest_header *hest_hdr)
+{
+	u16 hest_type = hest_hdr->type;
+	int len;
+
+	if (hest_type >= ACPI_HEST_TYPE_RESERVED)
+		return 0;
+
+	len = hest_esrc_len_tab[hest_type];
+
+	if (hest_type == ACPI_HEST_TYPE_IA32_CORRECTED_CHECK) {
+		struct acpi_hest_ia_corrected *cmc;
+		cmc = (struct acpi_hest_ia_corrected *)hest_hdr;
+		len = sizeof(*cmc) + cmc->num_hardware_banks *
+			sizeof(struct acpi_hest_ia_error_bank);
+	} else if (hest_type == ACPI_HEST_TYPE_IA32_CHECK) {
+		struct acpi_hest_ia_machine_check *mc;
+		mc = (struct acpi_hest_ia_machine_check *)hest_hdr;
+		len = sizeof(*mc) + mc->num_hardware_banks *
+			sizeof(struct acpi_hest_ia_error_bank);
+	}
+	BUG_ON(len == -1);
+
+	return len;
+};
+
+int apei_hest_parse(apei_hest_func_t func, void *data)
+{
+	struct acpi_hest_header *hest_hdr;
+	int i, rc, len;
+
+	if (hest_disable)
+		return -EINVAL;
+
+	hest_hdr = (struct acpi_hest_header *)(hest_tab + 1);
+	for (i = 0; i < hest_tab->error_source_count; i++) {
+		len = hest_esrc_len(hest_hdr);
+		if (!len) {
+			pr_warning(FW_WARN HEST_PFX
+				   "Unknown or unused hardware error source "
+				   "type: %d for hardware error source: %d.\n",
+				   hest_hdr->type, hest_hdr->source_id);
+			return -EINVAL;
+		}
+		if ((void *)hest_hdr + len >
+		    (void *)hest_tab + hest_tab->header.length) {
+			pr_warning(FW_BUG HEST_PFX
+		"Table contents overflow for hardware error source: %d.\n",
+				hest_hdr->source_id);
+			return -EINVAL;
+		}
+
+		rc = func(hest_hdr, data);
+		if (rc)
+			return rc;
+
+		hest_hdr = (void *)hest_hdr + len;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(apei_hest_parse);
+
+struct ghes_arr {
+	struct platform_device **ghes_devs;
+	unsigned int count;
+};
+
+static int __init hest_parse_ghes_count(struct acpi_hest_header *hest_hdr, void *data)
+{
+	int *count = data;
+
+	if (hest_hdr->type == ACPI_HEST_TYPE_GENERIC_ERROR)
+		(*count)++;
+	return 0;
+}
+
+static int __init hest_parse_ghes(struct acpi_hest_header *hest_hdr, void *data)
+{
+	struct platform_device *ghes_dev;
+	struct ghes_arr *ghes_arr = data;
+	int rc, i;
+
+	if (hest_hdr->type != ACPI_HEST_TYPE_GENERIC_ERROR)
+		return 0;
+
+	if (!((struct acpi_hest_generic *)hest_hdr)->enabled)
+		return 0;
+	for (i = 0; i < ghes_arr->count; i++) {
+		struct acpi_hest_header *hdr;
+		ghes_dev = ghes_arr->ghes_devs[i];
+		hdr = *(struct acpi_hest_header **)ghes_dev->dev.platform_data;
+		if (hdr->source_id == hest_hdr->source_id) {
+			pr_warning(FW_WARN HEST_PFX "Duplicated hardware error source ID: %d.\n",
+				   hdr->source_id);
+			return -EIO;
+		}
+	}
+	ghes_dev = platform_device_alloc("GHES", hest_hdr->source_id);
+	if (!ghes_dev)
+		return -ENOMEM;
+
+	rc = platform_device_add_data(ghes_dev, &hest_hdr, sizeof(void *));
+	if (rc)
+		goto err;
+
+	rc = platform_device_add(ghes_dev);
+	if (rc)
+		goto err;
+	ghes_arr->ghes_devs[ghes_arr->count++] = ghes_dev;
+
+	return 0;
+err:
+	platform_device_put(ghes_dev);
+	return rc;
+}
+
+static int __init hest_ghes_dev_register(unsigned int ghes_count)
+{
+	int rc, i;
+	struct ghes_arr ghes_arr;
+
+	ghes_arr.count = 0;
+	ghes_arr.ghes_devs = kmalloc(sizeof(void *) * ghes_count, GFP_KERNEL);
+	if (!ghes_arr.ghes_devs)
+		return -ENOMEM;
+
+	rc = apei_hest_parse(hest_parse_ghes, &ghes_arr);
+	if (rc)
+		goto err;
+out:
+	kfree(ghes_arr.ghes_devs);
+	return rc;
+err:
+	for (i = 0; i < ghes_arr.count; i++)
+		platform_device_unregister(ghes_arr.ghes_devs[i]);
+	goto out;
+}
+
+static int __init setup_hest_disable(char *str)
+{
+	hest_disable = 1;
+	return 0;
+}
+
+__setup("hest_disable", setup_hest_disable);
+
+void __init acpi_hest_init(void)
+{
+	acpi_status status;
+	int rc = -ENODEV;
+	unsigned int ghes_count = 0;
+
+	if (hest_disable) {
+		pr_info(HEST_PFX "Table parsing disabled.\n");
+		return;
+	}
+
+	if (acpi_disabled)
+		goto err;
+
+	status = acpi_get_table(ACPI_SIG_HEST, 0,
+				(struct acpi_table_header **)&hest_tab);
+	if (status == AE_NOT_FOUND)
+		goto err;
+	else if (ACPI_FAILURE(status)) {
+		const char *msg = acpi_format_exception(status);
+		pr_err(HEST_PFX "Failed to get table, %s\n", msg);
+		rc = -EINVAL;
+		goto err;
+	}
+
+	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;
+}