diff options
Diffstat (limited to 'drivers/acpi/apei')
| -rw-r--r-- | drivers/acpi/apei/Kconfig | 32 | ||||
| -rw-r--r-- | drivers/acpi/apei/Makefile | 3 | ||||
| -rw-r--r-- | drivers/acpi/apei/apei-base.c | 252 | ||||
| -rw-r--r-- | drivers/acpi/apei/apei-internal.h | 39 | ||||
| -rw-r--r-- | drivers/acpi/apei/cper.c | 84 | ||||
| -rw-r--r-- | drivers/acpi/apei/einj.c | 399 | ||||
| -rw-r--r-- | drivers/acpi/apei/erst-dbg.c | 243 | ||||
| -rw-r--r-- | drivers/acpi/apei/erst.c | 555 | ||||
| -rw-r--r-- | drivers/acpi/apei/ghes.c | 1020 | ||||
| -rw-r--r-- | drivers/acpi/apei/hest.c | 161 |
10 files changed, 2328 insertions, 460 deletions
diff --git a/drivers/acpi/apei/Kconfig b/drivers/acpi/apei/Kconfig index f8c668f27b5..c4dac715096 100644 --- a/drivers/acpi/apei/Kconfig +++ b/drivers/acpi/apei/Kconfig @@ -1,5 +1,8 @@ config ACPI_APEI bool "ACPI Platform Error Interface (APEI)" + select MISC_FILESYSTEMS + select PSTORE + select UEFI_CPER depends on X86 help APEI allows to report errors (for example from the chipset) @@ -8,9 +11,11 @@ config ACPI_APEI error injection. config ACPI_APEI_GHES - tristate "APEI Generic Hardware Error Source" - depends on ACPI_APEI && X86 + bool "APEI Generic Hardware Error Source" + depends on ACPI_APEI 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 @@ -21,6 +26,20 @@ config ACPI_APEI_GHES 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 @@ -28,3 +47,12 @@ config ACPI_APEI_EINJ 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. diff --git a/drivers/acpi/apei/Makefile b/drivers/acpi/apei/Makefile index b13b03a1778..5d575a95594 100644 --- a/drivers/acpi/apei/Makefile +++ b/drivers/acpi/apei/Makefile @@ -1,5 +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 +apei-y := apei-base.o hest.o erst.o diff --git a/drivers/acpi/apei/apei-base.c b/drivers/acpi/apei/apei-base.c index 216e1e948ff..8678dfe5366 100644 --- a/drivers/acpi/apei/apei-base.c +++ b/drivers/acpi/apei/apei-base.c @@ -40,7 +40,7 @@ #include <linux/rculist.h> #include <linux/interrupt.h> #include <linux/debugfs.h> -#include <acpi/atomicio.h> +#include <asm/unaligned.h> #include "apei-internal.h" @@ -70,7 +70,7 @@ int __apei_exec_read_register(struct acpi_whea_header *entry, u64 *val) { int rc; - rc = acpi_atomic_read(val, &entry->register_region); + rc = apei_read(val, &entry->register_region); if (rc) return rc; *val >>= entry->register_region.bit_offset; @@ -116,13 +116,13 @@ int __apei_exec_write_register(struct acpi_whea_header *entry, u64 val) val <<= entry->register_region.bit_offset; if (entry->flags & APEI_EXEC_PRESERVE_REGISTER) { u64 valr = 0; - rc = acpi_atomic_read(&valr, &entry->register_region); + rc = apei_read(&valr, &entry->register_region); if (rc) return rc; valr &= ~(entry->mask << entry->register_region.bit_offset); val |= valr; } - rc = acpi_atomic_write(val, &entry->register_region); + rc = apei_write(val, &entry->register_region); return rc; } @@ -157,9 +157,10 @@ EXPORT_SYMBOL_GPL(apei_exec_noop); * Interpret the specified action. Go through whole action table, * execute all instructions belong to the action. */ -int apei_exec_run(struct apei_exec_context *ctx, u8 action) +int __apei_exec_run(struct apei_exec_context *ctx, u8 action, + bool optional) { - int rc; + int rc = -ENOENT; u32 i, ip; struct acpi_whea_header *entry; apei_exec_ins_func_t run; @@ -198,9 +199,9 @@ rewind: goto rewind; } - return 0; + return !optional && rc < 0 ? rc : 0; } -EXPORT_SYMBOL_GPL(apei_exec_run); +EXPORT_SYMBOL_GPL(__apei_exec_run); typedef int (*apei_exec_entry_func_t)(struct apei_exec_context *ctx, struct acpi_whea_header *entry, @@ -242,7 +243,7 @@ static int pre_map_gar_callback(struct apei_exec_context *ctx, u8 ins = entry->instruction; if (ctx->ins_table[ins].flags & APEI_EXEC_INS_ACCESS_REGISTER) - return acpi_pre_map_gar(&entry->register_region); + return apei_map_generic_address(&entry->register_region); return 0; } @@ -275,7 +276,7 @@ static int post_unmap_gar_callback(struct apei_exec_context *ctx, u8 ins = entry->instruction; if (ctx->ins_table[ins].flags & APEI_EXEC_INS_ACCESS_REGISTER) - acpi_post_unmap_gar(&entry->register_region); + apei_unmap_generic_address(&entry->register_region); return 0; } @@ -420,6 +421,17 @@ static int apei_resources_merge(struct apei_resources *resources1, 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 @@ -437,27 +449,56 @@ int apei_resources_sub(struct apei_resources *resources1, } 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 rersource management mechanism is used to check + * 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; + 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; - apei_resources_sub(resources, &apei_resources_all); + /* + * 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 iomem region <%016llx-%016llx> for GARs.\n", + "Can not request [mem %#010llx-%#010llx] for %s registers\n", (unsigned long long)res->start, - (unsigned long long)res->end); + (unsigned long long)res->end - 1, desc); res_bak = res; goto err_unmap_iomem; } @@ -467,36 +508,43 @@ int apei_resources_request(struct apei_resources *resources, r = request_region(res->start, res->end - res->start, desc); if (!r) { pr_err(APEI_PFX - "Can not request ioport region <%016llx-%016llx> for GARs.\n", + "Can not request [io %#06llx-%#06llx] for %s registers\n", (unsigned long long)res->start, - (unsigned long long)res->end); + (unsigned long long)res->end - 1, desc); res_bak = res; goto err_unmap_ioport; } } - apei_resources_merge(&apei_resources_all, resources); + 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_mem_region(res->start, res->end - res->start); + 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_region(res->start, res->end - res->start); + release_mem_region(res->start, res->end - res->start); } - return -EINVAL; +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) @@ -504,42 +552,145 @@ void apei_resources_release(struct apei_resources *resources) list_for_each_entry(res, &resources->ioport, list) release_region(res->start, res->end - res->start); - apei_resources_sub(&apei_resources_all, resources); + 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) +static int apei_check_gar(struct acpi_generic_address *reg, u64 *paddr, + u32 *access_bit_width) { - u32 width, space_id; + u32 bit_width, bit_offset, access_size_code, space_id; - width = reg->bit_width; + 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, ®->address, sizeof(*paddr)); + *paddr = get_unaligned(®->address); if (!*paddr) { pr_warning(FW_BUG APEI_PFX - "Invalid physical address in GAR [0x%llx/%u/%u]\n", - *paddr, width, space_id); + "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 ((width != 8) && (width != 16) && (width != 32) && (width != 64)) { + if (access_size_code < 1 || access_size_code > 4) { pr_warning(FW_BUG APEI_PFX - "Invalid bit width in GAR [0x%llx/%u/%u]\n", - *paddr, width, space_id); + "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); + + /* Fixup common BIOS bug */ + if (bit_width == 32 && bit_offset == 0 && (*paddr & 0x03) == 0 && + *access_bit_width < 32) + *access_bit_width = 32; + else if (bit_width == 64 && bit_offset == 0 && (*paddr & 0x07) == 0 && + *access_bit_width < 64) + *access_bit_width = 64; + + 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]\n", - *paddr, width, space_id); + "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; +} + +int apei_map_generic_address(struct acpi_generic_address *reg) +{ + int rc; + u32 access_bit_width; + u64 address; + + rc = apei_check_gar(reg, &address, &access_bit_width); + if (rc) + return rc; + return acpi_os_map_generic_address(reg); +} +EXPORT_SYMBOL_GPL(apei_map_generic_address); + +/* 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, @@ -548,23 +699,24 @@ static int collect_res_callback(struct apei_exec_context *ctx, 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); + 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, - reg->bit_width / 8); + access_bit_width / 8); case ACPI_ADR_SPACE_SYSTEM_IO: return apei_res_add(&resources->ioport, paddr, - reg->bit_width / 8); + access_bit_width / 8); default: return -EINVAL; } @@ -592,3 +744,29 @@ struct dentry *apei_get_debugfs_dir(void) return dapei; } EXPORT_SYMBOL_GPL(apei_get_debugfs_dir); + +int apei_osc_setup(void) +{ + static u8 whea_uuid_str[] = "ed855e0c-6c90-47bf-a62a-26de0fc5ad5c"; + acpi_handle handle; + u32 capbuf[3]; + struct acpi_osc_context context = { + .uuid_str = whea_uuid_str, + .rev = 1, + .cap.length = sizeof(capbuf), + .cap.pointer = capbuf, + }; + + capbuf[OSC_QUERY_DWORD] = OSC_QUERY_ENABLE; + capbuf[OSC_SUPPORT_DWORD] = 1; + capbuf[OSC_CONTROL_DWORD] = 0; + + if (ACPI_FAILURE(acpi_get_handle(NULL, "\\_SB", &handle)) + || ACPI_FAILURE(acpi_run_osc(handle, &context))) + return -EIO; + else { + kfree(context.ret.pointer); + return 0; + } +} +EXPORT_SYMBOL_GPL(apei_osc_setup); diff --git a/drivers/acpi/apei/apei-internal.h b/drivers/acpi/apei/apei-internal.h index 18df1e94027..e5bcd919d4e 100644 --- a/drivers/acpi/apei/apei-internal.h +++ b/drivers/acpi/apei/apei-internal.h @@ -7,6 +7,7 @@ #define APEI_INTERNAL_H #include <linux/cper.h> +#include <linux/acpi.h> struct apei_exec_context; @@ -50,13 +51,34 @@ static inline u64 apei_exec_ctx_get_output(struct apei_exec_context *ctx) return ctx->value; } -int apei_exec_run(struct apei_exec_context *ctx, u8 action); +int __apei_exec_run(struct apei_exec_context *ctx, u8 action, bool optional); + +static inline int apei_exec_run(struct apei_exec_context *ctx, u8 action) +{ + return __apei_exec_run(ctx, action, 0); +} + +/* It is optional whether the firmware provides the action */ +static inline int apei_exec_run_optional(struct apei_exec_context *ctx, u8 action) +{ + return __apei_exec_run(ctx, action, 1); +} /* Common instruction implementation */ /* IP has been set in instruction function */ #define APEI_EXEC_SET_IP 1 +int apei_map_generic_address(struct acpi_generic_address *reg); + +static inline void apei_unmap_generic_address(struct acpi_generic_address *reg) +{ + acpi_os_unmap_generic_address(reg); +} + +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, @@ -84,6 +106,9 @@ static inline void apei_resources_init(struct apei_resources *resources) } 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, @@ -96,11 +121,11 @@ 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); \ + for (section = (struct acpi_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) +static inline u32 cper_estatus_len(struct acpi_generic_status *estatus) { if (estatus->raw_data_length) return estatus->raw_data_offset + \ @@ -109,6 +134,10 @@ static inline u32 apei_estatus_len(struct acpi_hest_generic_status *estatus) return sizeof(*estatus) + estatus->data_length; } -int apei_estatus_check_header(const struct acpi_hest_generic_status *estatus); -int apei_estatus_check(const struct acpi_hest_generic_status *estatus); +void cper_estatus_print(const char *pfx, + const struct acpi_generic_status *estatus); +int cper_estatus_check_header(const struct acpi_generic_status *estatus); +int cper_estatus_check(const struct acpi_generic_status *estatus); + +int apei_osc_setup(void); #endif diff --git a/drivers/acpi/apei/cper.c b/drivers/acpi/apei/cper.c deleted file mode 100644 index f4cf2fc4c8c..00000000000 --- a/drivers/acpi/apei/cper.c +++ /dev/null @@ -1,84 +0,0 @@ -/* - * 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> - -/* - * 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); - -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); - } - if (data_len) - return -EINVAL; - - return 0; -} -EXPORT_SYMBOL_GPL(apei_estatus_check); diff --git a/drivers/acpi/apei/einj.c b/drivers/acpi/apei/einj.c index 465c885938e..a095d4f858d 100644 --- a/drivers/acpi/apei/einj.c +++ b/drivers/acpi/apei/einj.c @@ -32,21 +32,65 @@ #include <linux/seq_file.h> #include <linux/nmi.h> #include <linux/delay.h> -#include <acpi/acpi.h> +#include <linux/mm.h> +#include <asm/unaligned.h> #include "apei-internal.h" #define EINJ_PFX "EINJ: " #define SPIN_UNIT 100 /* 100ns */ -/* Firmware should respond within 1 miliseconds */ +/* Firmware should respond within 1 milliseconds */ #define FIRMWARE_TIMEOUT (1 * NSEC_PER_MSEC) +#define ACPI5_VENDOR_BIT BIT(31) +#define MEM_ERROR_MASK (ACPI_EINJ_MEMORY_CORRECTABLE | \ + ACPI_EINJ_MEMORY_UNCORRECTABLE | \ + ACPI_EINJ_MEMORY_FATAL) + +/* + * 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. + * for error injection. This extension is used only if + * param_extension module parameter is specified. */ struct einj_parameter { u64 type; @@ -65,6 +109,9 @@ struct einj_parameter { ((struct acpi_whea_header *)((char *)(tab) + \ sizeof(struct acpi_table_einj))) +static bool param_extension; +module_param(param_extension, bool, 0); + static struct acpi_table_einj *einj_tab; static struct apei_resources einj_resources; @@ -99,7 +146,7 @@ static struct apei_exec_ins_type einj_ins_type[] = { */ static DEFINE_MUTEX(einj_mutex); -static struct einj_parameter *einj_param; +static void *einj_param; static void einj_exec_ctx_init(struct apei_exec_context *ctx) { @@ -146,10 +193,30 @@ static int einj_timedout(u64 *t) return 0; } -static u64 einj_get_parameter_address(void) +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_iomem(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_iomem(v, sizeof(*v)); +} + +static void *einj_get_parameter_address(void) { int i; - u64 paddr = 0; + u64 pa_v4 = 0, pa_v5 = 0; struct acpi_whea_header *entry; entry = EINJ_TAB_ENTRY(einj_tab); @@ -158,12 +225,38 @@ static u64 einj_get_parameter_address(void) entry->instruction == ACPI_EINJ_WRITE_REGISTER && entry->register_region.space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) - memcpy(&paddr, &entry->register_region.address, - sizeof(paddr)); + pa_v4 = get_unaligned(&entry->register_region.address); + 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) + pa_v5 = get_unaligned(&entry->register_region.address); entry++; } + if (pa_v5) { + struct set_error_type_with_address *v5param; + + v5param = acpi_os_map_iomem(pa_v5, sizeof(*v5param)); + if (v5param) { + acpi5 = 1; + check_vendor_extension(pa_v5, v5param); + return v5param; + } + } + if (param_extension && pa_v4) { + struct einj_parameter *v4param; + + v4param = acpi_os_map_iomem(pa_v4, sizeof(*v4param)); + if (!v4param) + return NULL; + if (v4param->reserved1 || v4param->reserved2) { + acpi_os_unmap_iomem(v4param, sizeof(*v4param)); + return NULL; + } + return v4param; + } - return paddr; + return NULL; } /* do sanity check to trigger table */ @@ -172,7 +265,7 @@ 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) + trigger_tab->table_size < trigger_tab->header_size) return -EINVAL; if (trigger_tab->entry_count != (trigger_tab->table_size - trigger_tab->header_size) / @@ -182,8 +275,29 @@ static int einj_check_trigger_header(struct acpi_einj_trigger *trigger_tab) 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) +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; @@ -192,14 +306,16 @@ static int __einj_error_trigger(u64 trigger_paddr) 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 iomem region <%016llx-%016llx> for Trigger table.\n", + "Can not request [mem %#010llx-%#010llx] for Trigger table\n", (unsigned long long)trigger_paddr, - (unsigned long long)trigger_paddr+sizeof(*trigger_tab)); + (unsigned long long)trigger_paddr + + sizeof(*trigger_tab) - 1); goto out; } trigger_tab = ioremap_cache(trigger_paddr, sizeof(*trigger_tab)); @@ -213,6 +329,11 @@ static int __einj_error_trigger(u64 trigger_paddr) "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), @@ -220,9 +341,9 @@ static int __einj_error_trigger(u64 trigger_paddr) "APEI EINJ Trigger Table"); if (!r) { pr_err(EINJ_PFX -"Can not request iomem region <%016llx-%016llx> for Trigger Table Entry.\n", - (unsigned long long)trigger_paddr+sizeof(*trigger_tab), - (unsigned long long)trigger_paddr + table_size); +"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); @@ -243,6 +364,30 @@ static int __einj_error_trigger(u64 trigger_paddr) 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 || acpi5) && (type & MEM_ERROR_MASK) && 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; @@ -269,7 +414,8 @@ out: return rc; } -static int __einj_error_inject(u32 type, u64 param1, u64 param2) +static int __einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2, + u64 param3, u64 param4) { struct apei_exec_context ctx; u64 val, trigger_paddr, timeout = FIRMWARE_TIMEOUT; @@ -277,16 +423,66 @@ static int __einj_error_inject(u32 type, u64 param1, u64 param2) einj_exec_ctx_init(&ctx); - rc = apei_exec_run(&ctx, ACPI_EINJ_BEGIN_OPERATION); + rc = apei_exec_run_optional(&ctx, ACPI_EINJ_BEGIN_OPERATION); if (rc) return rc; apei_exec_ctx_set_input(&ctx, type); - rc = apei_exec_run(&ctx, ACPI_EINJ_SET_ERROR_TYPE); - if (rc) - return rc; - if (einj_param) { - writeq(param1, &einj_param->param1); - writeq(param2, &einj_param->param2); + if (acpi5) { + struct set_error_type_with_address *v5param = einj_param; + + v5param->type = type; + if (type & ACPI5_VENDOR_BIT) { + 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 if (flags) { + v5param->flags = flags; + v5param->memory_address = param1; + v5param->memory_address_range = param2; + v5param->apicid = param3; + v5param->pcie_sbdf = param4; + } 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) @@ -312,29 +508,67 @@ static int __einj_error_inject(u32 type, u64 param1, u64 param2) if (rc) return rc; trigger_paddr = apei_exec_ctx_get_output(&ctx); - rc = __einj_error_trigger(trigger_paddr); - if (rc) - return rc; - rc = apei_exec_run(&ctx, ACPI_EINJ_END_OPERATION); + 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) +static int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2, + u64 param3, u64 param4) { int rc; + unsigned long pfn; + /* If user manually set "flags", make sure it is legal */ + if (flags && (flags & + ~(SETWA_FLAGS_APICID|SETWA_FLAGS_MEM|SETWA_FLAGS_PCIE_SBDF))) + return -EINVAL; + + /* + * We need extra sanity checks for memory errors. + * Other types leap directly to injection. + */ + + /* ensure param1/param2 existed */ + if (!(param_extension || acpi5)) + goto inject; + + /* ensure injection is memory related */ + if (type & ACPI5_VENDOR_BIT) { + if (vendor_flags != SETWA_FLAGS_MEM) + goto inject; + } else if (!(type & MEM_ERROR_MASK) && !(flags & SETWA_FLAGS_MEM)) + goto inject; + + /* + * Disallow crazy address masks that give BIOS leeway to pick + * injection address almost anywhere. Insist on page or + * better granularity and that target address is normal RAM. + */ + pfn = PFN_DOWN(param1 & param2); + if (!page_is_ram(pfn) || ((param2 & PAGE_MASK) != PAGE_MASK)) + return -EINVAL; + +inject: mutex_lock(&einj_mutex); - rc = __einj_error_inject(type, param1, param2); + rc = __einj_error_inject(type, flags, param1, param2, param3, param4); mutex_unlock(&einj_mutex); return rc; } static u32 error_type; +static u32 error_flags; static u64 error_param1; static u64 error_param2; +static u64 error_param3; +static u64 error_param4; static struct dentry *einj_debug_dir; static int available_error_type_show(struct seq_file *m, void *v) @@ -396,15 +630,25 @@ 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 & ACPI5_VENDOR_BIT; + tval = val & 0x7fffffff; /* Only one error type can be specified */ - if (val & (val - 1)) - return -EINVAL; - rc = einj_get_available_error_type(&available_error_type); - if (rc) - return rc; - if (!(val & available_error_type)) + 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; @@ -418,7 +662,8 @@ static int error_inject_set(void *data, u64 val) if (!error_type) return -EINVAL; - return einj_error_inject(error_type, error_param1, error_param2); + return einj_error_inject(error_type, error_flags, error_param1, error_param2, + error_param3, error_param4); } DEFINE_SIMPLE_ATTRIBUTE(error_inject_fops, NULL, @@ -426,7 +671,9 @@ DEFINE_SIMPLE_ATTRIBUTE(error_inject_fops, NULL, static int einj_check_table(struct acpi_table_einj *einj_tab) { - if (einj_tab->header_length != sizeof(struct acpi_table_einj)) + 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; @@ -441,7 +688,6 @@ static int einj_check_table(struct acpi_table_einj *einj_tab) static int __init einj_init(void) { int rc; - u64 param_paddr; acpi_status status; struct dentry *fentry; struct apei_exec_context ctx; @@ -451,10 +697,9 @@ static int __init einj_init(void) status = acpi_get_table(ACPI_SIG_EINJ, 0, (struct acpi_table_header **)&einj_tab); - if (status == AE_NOT_FOUND) { - pr_info(EINJ_PFX "Table is not found!\n"); + if (status == AE_NOT_FOUND) return -ENODEV; - } else if (ACPI_FAILURE(status)) { + 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; @@ -479,14 +724,6 @@ static int __init einj_init(void) einj_debug_dir, NULL, &error_type_fops); if (!fentry) goto err_cleanup; - fentry = debugfs_create_x64("param1", S_IRUSR | S_IWUSR, - einj_debug_dir, &error_param1); - if (!fentry) - goto err_cleanup; - fentry = debugfs_create_x64("param2", S_IRUSR | S_IWUSR, - einj_debug_dir, &error_param2); - if (!fentry) - goto err_cleanup; fentry = debugfs_create_file("error_inject", S_IWUSR, einj_debug_dir, NULL, &error_inject_fops); if (!fentry) @@ -503,11 +740,47 @@ static int __init einj_init(void) rc = apei_exec_pre_map_gars(&ctx); if (rc) goto err_release; - param_paddr = einj_get_parameter_address(); - if (param_paddr) { - einj_param = ioremap(param_paddr, sizeof(*einj_param)); - rc = -ENOMEM; - if (!einj_param) + + rc = -ENOMEM; + einj_param = einj_get_parameter_address(); + if ((param_extension || acpi5) && einj_param) { + fentry = debugfs_create_x32("flags", S_IRUSR | S_IWUSR, + einj_debug_dir, &error_flags); + if (!fentry) + goto err_unmap; + fentry = debugfs_create_x64("param1", S_IRUSR | S_IWUSR, + einj_debug_dir, &error_param1); + if (!fentry) + goto err_unmap; + fentry = debugfs_create_x64("param2", S_IRUSR | S_IWUSR, + einj_debug_dir, &error_param2); + if (!fentry) + goto err_unmap; + fentry = debugfs_create_x64("param3", S_IRUSR | S_IWUSR, + einj_debug_dir, &error_param3); + if (!fentry) + goto err_unmap; + fentry = debugfs_create_x64("param4", S_IRUSR | S_IWUSR, + einj_debug_dir, &error_param4); + if (!fentry) + goto err_unmap; + + fentry = debugfs_create_x32("notrigger", S_IRUSR | S_IWUSR, + einj_debug_dir, ¬rigger); + 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; } @@ -516,6 +789,13 @@ static int __init einj_init(void) 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_iomem(einj_param, size); + } apei_exec_post_unmap_gars(&ctx); err_release: apei_resources_release(&einj_resources); @@ -531,8 +811,13 @@ static void __exit einj_exit(void) { struct apei_exec_context ctx; - if (einj_param) - iounmap(einj_param); + if (einj_param) { + acpi_size size = (acpi5) ? + sizeof(struct set_error_type_with_address) : + sizeof(struct einj_parameter); + + acpi_os_unmap_iomem(einj_param, size); + } einj_exec_ctx_init(&ctx); apei_exec_post_unmap_gars(&ctx); apei_resources_release(&einj_resources); diff --git a/drivers/acpi/apei/erst-dbg.c b/drivers/acpi/apei/erst-dbg.c new file mode 100644 index 00000000000..04ab5c9d3ce --- /dev/null +++ b/drivers/acpi/apei/erst-dbg.c @@ -0,0 +1,243 @@ +/* + * 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) { + /* + * If the persistent store is empty initially, the function + * 'erst_read' below will return "-ENOENT" value. This causes + * 'retry_next' label is entered again. The returned value + * should be zero indicating the read operation is EOF. + */ + len = 0; + + 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"); diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c index 864dd46c346..ed65e9c4b5b 100644 --- a/drivers/acpi/apei/erst.c +++ b/drivers/acpi/apei/erst.c @@ -2,7 +2,7 @@ * APEI Error Record Serialization Table support * * ERST is a way provided by APEI to save and retrieve hardware error - * infomation to and from a persistent store. + * information to and from a persistent store. * * For more information about ERST, please refer to ACPI Specification * version 4.0, section 17.4. @@ -33,11 +33,14 @@ #include <linux/uaccess.h> #include <linux/cper.h> #include <linux/nmi.h> +#include <linux/hardirq.h> +#include <linux/pstore.h> #include <acpi/apei.h> #include "apei-internal.h" -#define ERST_PFX "ERST: " +#undef pr_fmt +#define pr_fmt(fmt) "ERST: " fmt /* ERST command status */ #define ERST_STATUS_SUCCESS 0x0 @@ -52,7 +55,7 @@ sizeof(struct acpi_table_erst))) #define SPIN_UNIT 100 /* 100ns */ -/* Firmware should respond within 1 miliseconds */ +/* Firmware should respond within 1 milliseconds */ #define FIRMWARE_TIMEOUT (1 * NSEC_PER_MSEC) #define FIRMWARE_MAX_STALL 50 /* 50us */ @@ -85,7 +88,7 @@ static struct erst_erange { * It is used to provide exclusive accessing for ERST Error Log * Address Range too. */ -static DEFINE_SPINLOCK(erst_lock); +static DEFINE_RAW_SPINLOCK(erst_lock); static inline int erst_errno(int command_status) { @@ -107,8 +110,7 @@ static inline int erst_errno(int command_status) static int erst_timedout(u64 *t, u64 spin_unit) { if ((s64)*t < spin_unit) { - pr_warning(FW_WARN ERST_PFX - "Firmware does not respond in time\n"); + pr_warn(FW_WARN "Firmware does not respond in time.\n"); return 1; } *t -= spin_unit; @@ -184,8 +186,8 @@ static int erst_exec_stall(struct apei_exec_context *ctx, if (ctx->value > FIRMWARE_MAX_STALL) { if (!in_nmi()) - pr_warning(FW_WARN ERST_PFX - "Too long stall time for stall instruction: %llx.\n", + pr_warn(FW_WARN + "Too long stall time for stall instruction: 0x%llx.\n", ctx->value); stall_time = FIRMWARE_MAX_STALL; } else @@ -204,8 +206,8 @@ static int erst_exec_stall_while_true(struct apei_exec_context *ctx, if (ctx->var1 > FIRMWARE_MAX_STALL) { if (!in_nmi()) - pr_warning(FW_WARN ERST_PFX - "Too long stall time for stall while true instruction: %llx.\n", + pr_warn(FW_WARN + "Too long stall time for stall while true instruction: 0x%llx.\n", ctx->var1); stall_time = FIRMWARE_MAX_STALL; } else @@ -265,13 +267,31 @@ static int erst_exec_move_data(struct apei_exec_context *ctx, { int rc; u64 offset; + void *src, *dst; + + /* ioremap does not work in interrupt context */ + if (in_interrupt()) { + pr_warn("MOVE_DATA can not be used in interrupt context.\n"); + return -EBUSY; + } rc = __apei_exec_read_register(entry, &offset); if (rc) return rc; - memmove((void *)ctx->dst_base + offset, - (void *)ctx->src_base + offset, - ctx->var2); + + src = ioremap(ctx->src_base + offset, ctx->var2); + if (!src) + return -ENOMEM; + dst = ioremap(ctx->dst_base + offset, ctx->var2); + if (!dst) { + iounmap(src); + return -ENOMEM; + } + + memmove(dst, src, ctx->var2); + + iounmap(src); + iounmap(dst); return 0; } @@ -403,14 +423,30 @@ ssize_t erst_get_record_count(void) if (erst_disable) return -ENODEV; - spin_lock_irqsave(&erst_lock, flags); + raw_spin_lock_irqsave(&erst_lock, flags); count = __erst_get_record_count(); - spin_unlock_irqrestore(&erst_lock, flags); + raw_spin_unlock_irqrestore(&erst_lock, flags); return count; } EXPORT_SYMBOL_GPL(erst_get_record_count); +#define ERST_RECORD_ID_CACHE_SIZE_MIN 16 +#define ERST_RECORD_ID_CACHE_SIZE_MAX 1024 + +struct erst_record_id_cache { + struct mutex lock; + u64 *entries; + int len; + int size; + int refcount; +}; + +static struct erst_record_id_cache erst_record_id_cache = { + .lock = __MUTEX_INITIALIZER(erst_record_id_cache.lock), + .refcount = 0, +}; + static int __erst_get_next_record_id(u64 *record_id) { struct apei_exec_context ctx; @@ -425,26 +461,178 @@ static int __erst_get_next_record_id(u64 *record_id) return 0; } +int erst_get_record_id_begin(int *pos) +{ + int rc; + + if (erst_disable) + return -ENODEV; + + rc = mutex_lock_interruptible(&erst_record_id_cache.lock); + if (rc) + return rc; + erst_record_id_cache.refcount++; + mutex_unlock(&erst_record_id_cache.lock); + + *pos = 0; + + return 0; +} +EXPORT_SYMBOL_GPL(erst_get_record_id_begin); + +/* erst_record_id_cache.lock must be held by caller */ +static int __erst_record_id_cache_add_one(void) +{ + u64 id, prev_id, first_id; + int i, rc; + u64 *entries; + unsigned long flags; + + id = prev_id = first_id = APEI_ERST_INVALID_RECORD_ID; +retry: + raw_spin_lock_irqsave(&erst_lock, flags); + rc = __erst_get_next_record_id(&id); + raw_spin_unlock_irqrestore(&erst_lock, flags); + if (rc == -ENOENT) + return 0; + if (rc) + return rc; + if (id == APEI_ERST_INVALID_RECORD_ID) + return 0; + /* can not skip current ID, or loop back to first ID */ + if (id == prev_id || id == first_id) + return 0; + if (first_id == APEI_ERST_INVALID_RECORD_ID) + first_id = id; + prev_id = id; + + entries = erst_record_id_cache.entries; + for (i = 0; i < erst_record_id_cache.len; i++) { + if (entries[i] == id) + break; + } + /* record id already in cache, try next */ + if (i < erst_record_id_cache.len) + goto retry; + if (erst_record_id_cache.len >= erst_record_id_cache.size) { + int new_size, alloc_size; + u64 *new_entries; + + new_size = erst_record_id_cache.size * 2; + new_size = clamp_val(new_size, ERST_RECORD_ID_CACHE_SIZE_MIN, + ERST_RECORD_ID_CACHE_SIZE_MAX); + if (new_size <= erst_record_id_cache.size) { + if (printk_ratelimit()) + pr_warn(FW_WARN "too many record IDs!\n"); + return 0; + } + alloc_size = new_size * sizeof(entries[0]); + if (alloc_size < PAGE_SIZE) + new_entries = kmalloc(alloc_size, GFP_KERNEL); + else + new_entries = vmalloc(alloc_size); + if (!new_entries) + return -ENOMEM; + memcpy(new_entries, entries, + erst_record_id_cache.len * sizeof(entries[0])); + if (erst_record_id_cache.size < PAGE_SIZE) + kfree(entries); + else + vfree(entries); + erst_record_id_cache.entries = entries = new_entries; + erst_record_id_cache.size = new_size; + } + entries[i] = id; + erst_record_id_cache.len++; + + return 1; +} + /* * Get the record ID of an existing error record on the persistent * storage. If there is no error record on the persistent storage, the * returned record_id is APEI_ERST_INVALID_RECORD_ID. */ -int erst_get_next_record_id(u64 *record_id) +int erst_get_record_id_next(int *pos, u64 *record_id) { - int rc; - unsigned long flags; + int rc = 0; + u64 *entries; if (erst_disable) return -ENODEV; - spin_lock_irqsave(&erst_lock, flags); - rc = __erst_get_next_record_id(record_id); - spin_unlock_irqrestore(&erst_lock, flags); + /* must be enclosed by erst_get_record_id_begin/end */ + BUG_ON(!erst_record_id_cache.refcount); + BUG_ON(*pos < 0 || *pos > erst_record_id_cache.len); + + mutex_lock(&erst_record_id_cache.lock); + entries = erst_record_id_cache.entries; + for (; *pos < erst_record_id_cache.len; (*pos)++) + if (entries[*pos] != APEI_ERST_INVALID_RECORD_ID) + break; + /* found next record id in cache */ + if (*pos < erst_record_id_cache.len) { + *record_id = entries[*pos]; + (*pos)++; + goto out_unlock; + } + + /* Try to add one more record ID to cache */ + rc = __erst_record_id_cache_add_one(); + if (rc < 0) + goto out_unlock; + /* successfully add one new ID */ + if (rc == 1) { + *record_id = erst_record_id_cache.entries[*pos]; + (*pos)++; + rc = 0; + } else { + *pos = -1; + *record_id = APEI_ERST_INVALID_RECORD_ID; + } +out_unlock: + mutex_unlock(&erst_record_id_cache.lock); return rc; } -EXPORT_SYMBOL_GPL(erst_get_next_record_id); +EXPORT_SYMBOL_GPL(erst_get_record_id_next); + +/* erst_record_id_cache.lock must be held by caller */ +static void __erst_record_id_cache_compact(void) +{ + int i, wpos = 0; + u64 *entries; + + if (erst_record_id_cache.refcount) + return; + + entries = erst_record_id_cache.entries; + for (i = 0; i < erst_record_id_cache.len; i++) { + if (entries[i] == APEI_ERST_INVALID_RECORD_ID) + continue; + if (wpos != i) + entries[wpos] = entries[i]; + wpos++; + } + erst_record_id_cache.len = wpos; +} + +void erst_get_record_id_end(void) +{ + /* + * erst_disable != 0 should be detected by invoker via the + * return value of erst_get_record_id_begin/next, so this + * function should not be called for erst_disable != 0. + */ + BUG_ON(erst_disable); + + mutex_lock(&erst_record_id_cache.lock); + erst_record_id_cache.refcount--; + BUG_ON(erst_record_id_cache.refcount < 0); + __erst_record_id_cache_compact(); + mutex_unlock(&erst_record_id_cache.lock); +} +EXPORT_SYMBOL_GPL(erst_get_record_id_end); static int __erst_write_to_storage(u64 offset) { @@ -454,7 +642,7 @@ static int __erst_write_to_storage(u64 offset) int rc; erst_exec_ctx_init(&ctx); - rc = apei_exec_run(&ctx, ACPI_ERST_BEGIN_WRITE); + rc = apei_exec_run_optional(&ctx, ACPI_ERST_BEGIN_WRITE); if (rc) return rc; apei_exec_ctx_set_input(&ctx, offset); @@ -478,7 +666,7 @@ static int __erst_write_to_storage(u64 offset) if (rc) return rc; val = apei_exec_ctx_get_output(&ctx); - rc = apei_exec_run(&ctx, ACPI_ERST_END); + rc = apei_exec_run_optional(&ctx, ACPI_ERST_END); if (rc) return rc; @@ -493,7 +681,7 @@ static int __erst_read_from_storage(u64 record_id, u64 offset) int rc; erst_exec_ctx_init(&ctx); - rc = apei_exec_run(&ctx, ACPI_ERST_BEGIN_READ); + rc = apei_exec_run_optional(&ctx, ACPI_ERST_BEGIN_READ); if (rc) return rc; apei_exec_ctx_set_input(&ctx, offset); @@ -521,7 +709,7 @@ static int __erst_read_from_storage(u64 record_id, u64 offset) if (rc) return rc; val = apei_exec_ctx_get_output(&ctx); - rc = apei_exec_run(&ctx, ACPI_ERST_END); + rc = apei_exec_run_optional(&ctx, ACPI_ERST_END); if (rc) return rc; @@ -536,7 +724,7 @@ static int __erst_clear_from_storage(u64 record_id) int rc; erst_exec_ctx_init(&ctx); - rc = apei_exec_run(&ctx, ACPI_ERST_BEGIN_CLEAR); + rc = apei_exec_run_optional(&ctx, ACPI_ERST_BEGIN_CLEAR); if (rc) return rc; apei_exec_ctx_set_input(&ctx, record_id); @@ -560,7 +748,7 @@ static int __erst_clear_from_storage(u64 record_id) if (rc) return rc; val = apei_exec_ctx_get_output(&ctx); - rc = apei_exec_run(&ctx, ACPI_ERST_END); + rc = apei_exec_run_optional(&ctx, ACPI_ERST_END); if (rc) return rc; @@ -571,8 +759,7 @@ static int __erst_clear_from_storage(u64 record_id) static void pr_unimpl_nvram(void) { if (printk_ratelimit()) - pr_warning(ERST_PFX - "NVRAM ERST Log Address Range is not implemented yet\n"); + pr_warn("NVRAM ERST Log Address Range not implemented yet.\n"); } static int __erst_write_to_nvram(const struct cper_record_header *record) @@ -606,17 +793,17 @@ int erst_write(const struct cper_record_header *record) return -EINVAL; if (erst_erange.attr & ERST_RANGE_NVRAM) { - if (!spin_trylock_irqsave(&erst_lock, flags)) + if (!raw_spin_trylock_irqsave(&erst_lock, flags)) return -EBUSY; rc = __erst_write_to_nvram(record); - spin_unlock_irqrestore(&erst_lock, flags); + raw_spin_unlock_irqrestore(&erst_lock, flags); return rc; } if (record->record_length > erst_erange.size) return -EINVAL; - if (!spin_trylock_irqsave(&erst_lock, flags)) + if (!raw_spin_trylock_irqsave(&erst_lock, flags)) return -EBUSY; memcpy(erst_erange.vaddr, record, record->record_length); rcd_erange = erst_erange.vaddr; @@ -624,7 +811,7 @@ int erst_write(const struct cper_record_header *record) memcpy(&rcd_erange->persistence_information, "ER", 2); rc = __erst_write_to_storage(0); - spin_unlock_irqrestore(&erst_lock, flags); + raw_spin_unlock_irqrestore(&erst_lock, flags); return rc; } @@ -678,63 +865,41 @@ ssize_t erst_read(u64 record_id, struct cper_record_header *record, if (erst_disable) return -ENODEV; - spin_lock_irqsave(&erst_lock, flags); + raw_spin_lock_irqsave(&erst_lock, flags); len = __erst_read(record_id, record, buflen); - spin_unlock_irqrestore(&erst_lock, flags); + raw_spin_unlock_irqrestore(&erst_lock, flags); return len; } EXPORT_SYMBOL_GPL(erst_read); -/* - * If return value > buflen, the buffer size is not big enough, - * else if return value = 0, there is no more record to read, - * else if return value < 0, something goes wrong, - * else everything is OK, and return value is record length - */ -ssize_t erst_read_next(struct cper_record_header *record, size_t buflen) -{ - int rc; - ssize_t len; - unsigned long flags; - u64 record_id; - - if (erst_disable) - return -ENODEV; - - spin_lock_irqsave(&erst_lock, flags); - rc = __erst_get_next_record_id(&record_id); - if (rc) { - spin_unlock_irqrestore(&erst_lock, flags); - return rc; - } - /* no more record */ - if (record_id == APEI_ERST_INVALID_RECORD_ID) { - spin_unlock_irqrestore(&erst_lock, flags); - return 0; - } - - len = __erst_read(record_id, record, buflen); - spin_unlock_irqrestore(&erst_lock, flags); - - return len; -} -EXPORT_SYMBOL_GPL(erst_read_next); - int erst_clear(u64 record_id) { - int rc; + int rc, i; unsigned long flags; + u64 *entries; if (erst_disable) return -ENODEV; - spin_lock_irqsave(&erst_lock, flags); + rc = mutex_lock_interruptible(&erst_record_id_cache.lock); + if (rc) + return rc; + raw_spin_lock_irqsave(&erst_lock, flags); if (erst_erange.attr & ERST_RANGE_NVRAM) rc = __erst_clear_from_nvram(record_id); else rc = __erst_clear_from_storage(record_id); - spin_unlock_irqrestore(&erst_lock, flags); - + raw_spin_unlock_irqrestore(&erst_lock, flags); + if (rc) + goto out; + entries = erst_record_id_cache.entries; + for (i = 0; i < erst_record_id_cache.len; i++) { + if (entries[i] == record_id) + entries[i] = APEI_ERST_INVALID_RECORD_ID; + } + __erst_record_id_cache_compact(); +out: + mutex_unlock(&erst_record_id_cache.lock); return rc; } EXPORT_SYMBOL_GPL(erst_clear); @@ -749,7 +914,9 @@ __setup("erst_disable", setup_erst_disable); static int erst_check_table(struct acpi_table_erst *erst_tab) { - if (erst_tab->header_length != sizeof(struct acpi_table_erst)) + if ((erst_tab->header_length != + (sizeof(struct acpi_table_erst) - sizeof(erst_tab->header))) + && (erst_tab->header_length != sizeof(struct acpi_table_erst))) return -EINVAL; if (erst_tab->header.length < sizeof(struct acpi_table_erst)) return -EINVAL; @@ -761,6 +928,196 @@ static int erst_check_table(struct acpi_table_erst *erst_tab) return 0; } +static int erst_open_pstore(struct pstore_info *psi); +static int erst_close_pstore(struct pstore_info *psi); +static ssize_t erst_reader(u64 *id, enum pstore_type_id *type, int *count, + struct timespec *time, char **buf, + bool *compressed, struct pstore_info *psi); +static int erst_writer(enum pstore_type_id type, enum kmsg_dump_reason reason, + u64 *id, unsigned int part, int count, bool compressed, + size_t size, struct pstore_info *psi); +static int erst_clearer(enum pstore_type_id type, u64 id, int count, + struct timespec time, struct pstore_info *psi); + +static struct pstore_info erst_info = { + .owner = THIS_MODULE, + .name = "erst", + .flags = PSTORE_FLAGS_FRAGILE, + .open = erst_open_pstore, + .close = erst_close_pstore, + .read = erst_reader, + .write = erst_writer, + .erase = erst_clearer +}; + +#define CPER_CREATOR_PSTORE \ + UUID_LE(0x75a574e3, 0x5052, 0x4b29, 0x8a, 0x8e, 0xbe, 0x2c, \ + 0x64, 0x90, 0xb8, 0x9d) +#define CPER_SECTION_TYPE_DMESG \ + UUID_LE(0xc197e04e, 0xd545, 0x4a70, 0x9c, 0x17, 0xa5, 0x54, \ + 0x94, 0x19, 0xeb, 0x12) +#define CPER_SECTION_TYPE_DMESG_Z \ + UUID_LE(0x4f118707, 0x04dd, 0x4055, 0xb5, 0xdd, 0x95, 0x6d, \ + 0x34, 0xdd, 0xfa, 0xc6) +#define CPER_SECTION_TYPE_MCE \ + UUID_LE(0xfe08ffbe, 0x95e4, 0x4be7, 0xbc, 0x73, 0x40, 0x96, \ + 0x04, 0x4a, 0x38, 0xfc) + +struct cper_pstore_record { + struct cper_record_header hdr; + struct cper_section_descriptor sec_hdr; + char data[]; +} __packed; + +static int reader_pos; + +static int erst_open_pstore(struct pstore_info *psi) +{ + int rc; + + if (erst_disable) + return -ENODEV; + + rc = erst_get_record_id_begin(&reader_pos); + + return rc; +} + +static int erst_close_pstore(struct pstore_info *psi) +{ + erst_get_record_id_end(); + + return 0; +} + +static ssize_t erst_reader(u64 *id, enum pstore_type_id *type, int *count, + struct timespec *time, char **buf, + bool *compressed, struct pstore_info *psi) +{ + int rc; + ssize_t len = 0; + u64 record_id; + struct cper_pstore_record *rcd; + size_t rcd_len = sizeof(*rcd) + erst_info.bufsize; + + if (erst_disable) + return -ENODEV; + + rcd = kmalloc(rcd_len, GFP_KERNEL); + if (!rcd) { + rc = -ENOMEM; + goto out; + } +skip: + rc = erst_get_record_id_next(&reader_pos, &record_id); + if (rc) + goto out; + + /* no more record */ + if (record_id == APEI_ERST_INVALID_RECORD_ID) { + rc = -EINVAL; + goto out; + } + + len = erst_read(record_id, &rcd->hdr, rcd_len); + /* The record may be cleared by others, try read next record */ + if (len == -ENOENT) + goto skip; + else if (len < sizeof(*rcd)) { + rc = -EIO; + goto out; + } + if (uuid_le_cmp(rcd->hdr.creator_id, CPER_CREATOR_PSTORE) != 0) + goto skip; + + *buf = kmalloc(len, GFP_KERNEL); + if (*buf == NULL) { + rc = -ENOMEM; + goto out; + } + memcpy(*buf, rcd->data, len - sizeof(*rcd)); + *id = record_id; + *compressed = false; + if (uuid_le_cmp(rcd->sec_hdr.section_type, + CPER_SECTION_TYPE_DMESG_Z) == 0) { + *type = PSTORE_TYPE_DMESG; + *compressed = true; + } else if (uuid_le_cmp(rcd->sec_hdr.section_type, + CPER_SECTION_TYPE_DMESG) == 0) + *type = PSTORE_TYPE_DMESG; + else if (uuid_le_cmp(rcd->sec_hdr.section_type, + CPER_SECTION_TYPE_MCE) == 0) + *type = PSTORE_TYPE_MCE; + else + *type = PSTORE_TYPE_UNKNOWN; + + if (rcd->hdr.validation_bits & CPER_VALID_TIMESTAMP) + time->tv_sec = rcd->hdr.timestamp; + else + time->tv_sec = 0; + time->tv_nsec = 0; + +out: + kfree(rcd); + return (rc < 0) ? rc : (len - sizeof(*rcd)); +} + +static int erst_writer(enum pstore_type_id type, enum kmsg_dump_reason reason, + u64 *id, unsigned int part, int count, bool compressed, + size_t size, struct pstore_info *psi) +{ + struct cper_pstore_record *rcd = (struct cper_pstore_record *) + (erst_info.buf - sizeof(*rcd)); + int ret; + + memset(rcd, 0, sizeof(*rcd)); + memcpy(rcd->hdr.signature, CPER_SIG_RECORD, CPER_SIG_SIZE); + rcd->hdr.revision = CPER_RECORD_REV; + rcd->hdr.signature_end = CPER_SIG_END; + rcd->hdr.section_count = 1; + rcd->hdr.error_severity = CPER_SEV_FATAL; + /* timestamp valid. platform_id, partition_id are invalid */ + rcd->hdr.validation_bits = CPER_VALID_TIMESTAMP; + rcd->hdr.timestamp = get_seconds(); + rcd->hdr.record_length = sizeof(*rcd) + size; + rcd->hdr.creator_id = CPER_CREATOR_PSTORE; + rcd->hdr.notification_type = CPER_NOTIFY_MCE; + rcd->hdr.record_id = cper_next_record_id(); + rcd->hdr.flags = CPER_HW_ERROR_FLAGS_PREVERR; + + rcd->sec_hdr.section_offset = sizeof(*rcd); + rcd->sec_hdr.section_length = size; + rcd->sec_hdr.revision = CPER_SEC_REV; + /* fru_id and fru_text is invalid */ + rcd->sec_hdr.validation_bits = 0; + rcd->sec_hdr.flags = CPER_SEC_PRIMARY; + switch (type) { + case PSTORE_TYPE_DMESG: + if (compressed) + rcd->sec_hdr.section_type = CPER_SECTION_TYPE_DMESG_Z; + else + rcd->sec_hdr.section_type = CPER_SECTION_TYPE_DMESG; + break; + case PSTORE_TYPE_MCE: + rcd->sec_hdr.section_type = CPER_SECTION_TYPE_MCE; + break; + default: + return -EINVAL; + } + rcd->sec_hdr.section_severity = CPER_SEV_FATAL; + + ret = erst_write(&rcd->hdr); + *id = rcd->hdr.record_id; + + return ret; +} + +static int erst_clearer(enum pstore_type_id type, u64 id, int count, + struct timespec time, struct pstore_info *psi) +{ + return erst_clear(id); +} + static int __init erst_init(void) { int rc = 0; @@ -768,31 +1125,31 @@ static int __init erst_init(void) struct apei_exec_context ctx; struct apei_resources erst_resources; struct resource *r; + char *buf; if (acpi_disabled) goto err; if (erst_disable) { - pr_info(ERST_PFX + pr_info( "Error Record Serialization Table (ERST) support is disabled.\n"); goto err; } status = acpi_get_table(ACPI_SIG_ERST, 0, (struct acpi_table_header **)&erst_tab); - if (status == AE_NOT_FOUND) { - pr_info(ERST_PFX "Table is not found!\n"); + if (status == AE_NOT_FOUND) goto err; - } else if (ACPI_FAILURE(status)) { + else if (ACPI_FAILURE(status)) { const char *msg = acpi_format_exception(status); - pr_err(ERST_PFX "Failed to get table, %s\n", msg); + pr_err("Failed to get table, %s\n", msg); rc = -EINVAL; goto err; } rc = erst_check_table(erst_tab); if (rc) { - pr_err(FW_BUG ERST_PFX "ERST table is invalid\n"); + pr_err(FW_BUG "ERST table is invalid.\n"); goto err; } @@ -810,21 +1167,19 @@ static int __init erst_init(void) rc = erst_get_erange(&erst_erange); if (rc) { if (rc == -ENODEV) - pr_info(ERST_PFX + pr_info( "The corresponding hardware device or firmware implementation " "is not available.\n"); else - pr_err(ERST_PFX - "Failed to get Error Log Address Range.\n"); + pr_err("Failed to get Error Log Address Range.\n"); goto err_unmap_reg; } r = request_mem_region(erst_erange.base, erst_erange.size, "APEI ERST"); if (!r) { - pr_err(ERST_PFX - "Can not request iomem region <0x%16llx-0x%16llx> for ERST.\n", - (unsigned long long)erst_erange.base, - (unsigned long long)erst_erange.base + erst_erange.size); + pr_err("Can not request [mem %#010llx-%#010llx] for ERST.\n", + (unsigned long long)erst_erange.base, + (unsigned long long)erst_erange.base + erst_erange.size - 1); rc = -EIO; goto err_unmap_reg; } @@ -834,9 +1189,29 @@ static int __init erst_init(void) if (!erst_erange.vaddr) goto err_release_erange; - pr_info(ERST_PFX + pr_info( "Error Record Serialization Table (ERST) support is initialized.\n"); + buf = kmalloc(erst_erange.size, GFP_KERNEL); + spin_lock_init(&erst_info.buf_lock); + if (buf) { + erst_info.buf = buf + sizeof(struct cper_pstore_record); + erst_info.bufsize = erst_erange.size - + sizeof(struct cper_pstore_record); + rc = pstore_register(&erst_info); + if (rc) { + if (rc != -EPERM) + pr_info( + "Could not register with persistent store.\n"); + erst_info.buf = NULL; + erst_info.bufsize = 0; + kfree(buf); + } + } else + pr_err( + "Failed to allocate %lld bytes for persistent store error log.\n", + erst_erange.size); + return 0; err_release_erange: diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index fd0cc016a09..dab7cb7349d 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -12,11 +12,7 @@ * For more information about Generic Hardware Error Source, please * refer to ACPI Specification version 4.0, section 17.3.2.6 * - * Now, only SCI notification type and memory errors are - * supported. More notification type and hardware error type will be - * added later. - * - * Copyright 2010 Intel Corp. + * Copyright 2010,2011 Intel Corp. * Author: Huang Ying <ying.huang@intel.com> * * This program is free software; you can redistribute it and/or @@ -39,54 +35,224 @@ #include <linux/acpi.h> #include <linux/io.h> #include <linux/interrupt.h> +#include <linux/timer.h> #include <linux/cper.h> #include <linux/kdebug.h> -#include <acpi/apei.h> -#include <acpi/atomicio.h> -#include <acpi/hed.h> +#include <linux/platform_device.h> +#include <linux/mutex.h> +#include <linux/ratelimit.h> +#include <linux/vmalloc.h> +#include <linux/irq_work.h> +#include <linux/llist.h> +#include <linux/genalloc.h> +#include <linux/pci.h> +#include <linux/aer.h> + +#include <acpi/ghes.h> #include <asm/mce.h> +#include <asm/tlbflush.h> +#include <asm/nmi.h> #include "apei-internal.h" #define GHES_PFX "GHES: " #define GHES_ESTATUS_MAX_SIZE 65536 +#define GHES_ESOURCE_PREALLOC_MAX_SIZE 65536 + +#define GHES_ESTATUS_POOL_MIN_ALLOC_ORDER 3 + +/* This is just an estimation for memory pool allocation */ +#define GHES_ESTATUS_CACHE_AVG_SIZE 512 + +#define GHES_ESTATUS_CACHES_SIZE 4 + +#define GHES_ESTATUS_IN_CACHE_MAX_NSEC 10000000000ULL +/* Prevent too many caches are allocated because of RCU */ +#define GHES_ESTATUS_CACHE_ALLOCED_MAX (GHES_ESTATUS_CACHES_SIZE * 3 / 2) + +#define GHES_ESTATUS_CACHE_LEN(estatus_len) \ + (sizeof(struct ghes_estatus_cache) + (estatus_len)) +#define GHES_ESTATUS_FROM_CACHE(estatus_cache) \ + ((struct acpi_generic_status *) \ + ((struct ghes_estatus_cache *)(estatus_cache) + 1)) + +#define GHES_ESTATUS_NODE_LEN(estatus_len) \ + (sizeof(struct ghes_estatus_node) + (estatus_len)) +#define GHES_ESTATUS_FROM_NODE(estatus_node) \ + ((struct acpi_generic_status *) \ + ((struct ghes_estatus_node *)(estatus_node) + 1)) + +bool ghes_disable; +module_param_named(disable, ghes_disable, bool, 0); + +static int ghes_panic_timeout __read_mostly = 30; /* - * One struct ghes is created for each generic hardware error - * source. + * All error sources notified with SCI shares one notifier function, + * so they need to be linked and checked one by one. This is applied + * to NMI too. * - * It provides the context for APEI hardware error timer/IRQ/SCI/NMI - * handler. Handler for one generic hardware error source is only - * triggered after the previous one is done. So handler can uses - * struct ghes without locking. - * - * estatus: memory buffer for error status block, allocated during - * HEST parsing. + * RCU is used for these lists, so ghes_list_mutex is only used for + * list changing, not for traversing. */ -#define GHES_TO_CLEAR 0x0001 +static LIST_HEAD(ghes_sci); +static LIST_HEAD(ghes_nmi); +static DEFINE_MUTEX(ghes_list_mutex); -struct ghes { - struct acpi_hest_generic *generic; - struct acpi_hest_generic_status *estatus; - struct list_head list; - u64 buffer_paddr; - unsigned long flags; -}; +/* + * NMI may be triggered on any CPU, so ghes_nmi_lock is used for + * mutual exclusion. + */ +static DEFINE_RAW_SPINLOCK(ghes_nmi_lock); /* - * Error source lists, one list for each notification method. The - * members in lists are struct ghes. - * - * The list members are only added in HEST parsing and deleted during - * module_exit, that is, single-threaded. So no lock is needed for - * that. - * - * But the mutual exclusion is needed between members adding/deleting - * and timer/IRQ/SCI/NMI handler, which may traverse the list. RCU is - * used for that. + * 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 + * a special version of atomic ioremap is implemented for that. */ -static LIST_HEAD(ghes_sci); + +/* + * Two virtual pages are used, one for NMI context, the other for + * IRQ/PROCESS context + */ +#define GHES_IOREMAP_PAGES 2 +#define GHES_IOREMAP_NMI_PAGE(base) (base) +#define GHES_IOREMAP_IRQ_PAGE(base) ((base) + PAGE_SIZE) + +/* virtual memory area for atomic ioremap */ +static struct vm_struct *ghes_ioremap_area; +/* + * These 2 spinlock is used to prevent atomic ioremap virtual memory + * area from being mapped simultaneously. + */ +static DEFINE_RAW_SPINLOCK(ghes_ioremap_lock_nmi); +static DEFINE_SPINLOCK(ghes_ioremap_lock_irq); + +/* + * printk is not safe in NMI context. So in NMI handler, we allocate + * required memory from lock-less memory allocator + * (ghes_estatus_pool), save estatus into it, put them into lock-less + * list (ghes_estatus_llist), then delay printk into IRQ context via + * irq_work (ghes_proc_irq_work). ghes_estatus_size_request record + * required pool size by all NMI error source. + */ +static struct gen_pool *ghes_estatus_pool; +static unsigned long ghes_estatus_pool_size_request; +static struct llist_head ghes_estatus_llist; +static struct irq_work ghes_proc_irq_work; + +struct ghes_estatus_cache *ghes_estatus_caches[GHES_ESTATUS_CACHES_SIZE]; +static atomic_t ghes_estatus_cache_alloced; + +static int ghes_ioremap_init(void) +{ + ghes_ioremap_area = __get_vm_area(PAGE_SIZE * GHES_IOREMAP_PAGES, + VM_IOREMAP, VMALLOC_START, VMALLOC_END); + if (!ghes_ioremap_area) { + pr_err(GHES_PFX "Failed to allocate virtual memory area for atomic ioremap.\n"); + return -ENOMEM; + } + + return 0; +} + +static void ghes_ioremap_exit(void) +{ + free_vm_area(ghes_ioremap_area); +} + +static void __iomem *ghes_ioremap_pfn_nmi(u64 pfn) +{ + unsigned long vaddr; + + vaddr = (unsigned long)GHES_IOREMAP_NMI_PAGE(ghes_ioremap_area->addr); + ioremap_page_range(vaddr, vaddr + PAGE_SIZE, + pfn << PAGE_SHIFT, PAGE_KERNEL); + + return (void __iomem *)vaddr; +} + +static void __iomem *ghes_ioremap_pfn_irq(u64 pfn) +{ + unsigned long vaddr; + + vaddr = (unsigned long)GHES_IOREMAP_IRQ_PAGE(ghes_ioremap_area->addr); + ioremap_page_range(vaddr, vaddr + PAGE_SIZE, + pfn << PAGE_SHIFT, PAGE_KERNEL); + + return (void __iomem *)vaddr; +} + +static void ghes_iounmap_nmi(void __iomem *vaddr_ptr) +{ + unsigned long vaddr = (unsigned long __force)vaddr_ptr; + void *base = ghes_ioremap_area->addr; + + BUG_ON(vaddr != (unsigned long)GHES_IOREMAP_NMI_PAGE(base)); + unmap_kernel_range_noflush(vaddr, PAGE_SIZE); + __flush_tlb_one(vaddr); +} + +static void ghes_iounmap_irq(void __iomem *vaddr_ptr) +{ + unsigned long vaddr = (unsigned long __force)vaddr_ptr; + void *base = ghes_ioremap_area->addr; + + BUG_ON(vaddr != (unsigned long)GHES_IOREMAP_IRQ_PAGE(base)); + unmap_kernel_range_noflush(vaddr, PAGE_SIZE); + __flush_tlb_one(vaddr); +} + +static int ghes_estatus_pool_init(void) +{ + ghes_estatus_pool = gen_pool_create(GHES_ESTATUS_POOL_MIN_ALLOC_ORDER, -1); + if (!ghes_estatus_pool) + return -ENOMEM; + return 0; +} + +static void ghes_estatus_pool_free_chunk_page(struct gen_pool *pool, + struct gen_pool_chunk *chunk, + void *data) +{ + free_page(chunk->start_addr); +} + +static void ghes_estatus_pool_exit(void) +{ + gen_pool_for_each_chunk(ghes_estatus_pool, + ghes_estatus_pool_free_chunk_page, NULL); + gen_pool_destroy(ghes_estatus_pool); +} + +static int ghes_estatus_pool_expand(unsigned long len) +{ + unsigned long i, pages, size, addr; + int ret; + + ghes_estatus_pool_size_request += PAGE_ALIGN(len); + size = gen_pool_size(ghes_estatus_pool); + if (size >= ghes_estatus_pool_size_request) + return 0; + pages = (ghes_estatus_pool_size_request - size) / PAGE_SIZE; + for (i = 0; i < pages; i++) { + addr = __get_free_page(GFP_KERNEL); + if (!addr) + return -ENOMEM; + ret = gen_pool_add(ghes_estatus_pool, addr, PAGE_SIZE, -1); + if (ret) + return ret; + } + + return 0; +} + +static void ghes_estatus_pool_shrink(unsigned long len) +{ + ghes_estatus_pool_size_request -= PAGE_ALIGN(len); +} static struct ghes *ghes_new(struct acpi_hest_generic *generic) { @@ -98,8 +264,7 @@ static struct ghes *ghes_new(struct acpi_hest_generic *generic) if (!ghes) return ERR_PTR(-ENOMEM); ghes->generic = generic; - INIT_LIST_HEAD(&ghes->list); - rc = acpi_pre_map_gar(&generic->error_status_address); + rc = apei_map_generic_address(&generic->error_status_address); if (rc) goto err_free; error_block_length = generic->error_block_length; @@ -119,7 +284,7 @@ static struct ghes *ghes_new(struct acpi_hest_generic *generic) return ghes; err_unmap: - acpi_post_unmap_gar(&generic->error_status_address); + apei_unmap_generic_address(&generic->error_status_address); err_free: kfree(ghes); return ERR_PTR(rc); @@ -128,49 +293,61 @@ err_free: static void ghes_fini(struct ghes *ghes) { kfree(ghes->estatus); - acpi_post_unmap_gar(&ghes->generic->error_status_address); + apei_unmap_generic_address(&ghes->generic->error_status_address); } -enum { - GHES_SER_NO = 0x0, - GHES_SER_CORRECTED = 0x1, - GHES_SER_RECOVERABLE = 0x2, - GHES_SER_PANIC = 0x3, -}; - static inline int ghes_severity(int severity) { switch (severity) { - case CPER_SER_INFORMATIONAL: - return GHES_SER_NO; - case CPER_SER_CORRECTED: - return GHES_SER_CORRECTED; - case CPER_SER_RECOVERABLE: - return GHES_SER_RECOVERABLE; - case CPER_SER_FATAL: - return GHES_SER_PANIC; + case CPER_SEV_INFORMATIONAL: + return GHES_SEV_NO; + case CPER_SEV_CORRECTED: + return GHES_SEV_CORRECTED; + case CPER_SEV_RECOVERABLE: + return GHES_SEV_RECOVERABLE; + case CPER_SEV_FATAL: + return GHES_SEV_PANIC; default: - /* Unkown, go panic */ - return GHES_SER_PANIC; + /* Unknown, go panic */ + return GHES_SEV_PANIC; } } -/* SCI handler run in work queue, so ioremap can be used here */ -static int ghes_copy_tofrom_phys(void *buffer, u64 paddr, u32 len, - int from_phys) +static void ghes_copy_tofrom_phys(void *buffer, u64 paddr, u32 len, + int from_phys) { - void *vaddr; - - vaddr = ioremap_cache(paddr, len); - if (!vaddr) - return -ENOMEM; - if (from_phys) - memcpy(buffer, vaddr, len); - else - memcpy(vaddr, buffer, len); - iounmap(vaddr); + void __iomem *vaddr; + unsigned long flags = 0; + int in_nmi = in_nmi(); + u64 offset; + u32 trunk; - return 0; + while (len > 0) { + offset = paddr - (paddr & PAGE_MASK); + if (in_nmi) { + raw_spin_lock(&ghes_ioremap_lock_nmi); + vaddr = ghes_ioremap_pfn_nmi(paddr >> PAGE_SHIFT); + } else { + spin_lock_irqsave(&ghes_ioremap_lock_irq, flags); + vaddr = ghes_ioremap_pfn_irq(paddr >> PAGE_SHIFT); + } + trunk = PAGE_SIZE - offset; + trunk = min(trunk, len); + if (from_phys) + memcpy_fromio(buffer, vaddr + offset, trunk); + else + memcpy_toio(vaddr + offset, buffer, trunk); + len -= trunk; + paddr += trunk; + buffer += trunk; + if (in_nmi) { + ghes_iounmap_nmi(vaddr); + raw_spin_unlock(&ghes_ioremap_lock_nmi); + } else { + ghes_iounmap_irq(vaddr); + spin_unlock_irqrestore(&ghes_ioremap_lock_irq, flags); + } + } } static int ghes_read_estatus(struct ghes *ghes, int silent) @@ -180,7 +357,7 @@ static int ghes_read_estatus(struct ghes *ghes, int silent) u32 len; int rc; - rc = acpi_atomic_read(&buf_paddr, &g->error_status_address); + rc = apei_read(&buf_paddr, &g->error_status_address); if (rc) { if (!silent && printk_ratelimit()) pr_warning(FW_WARN GHES_PFX @@ -191,10 +368,8 @@ static int ghes_read_estatus(struct ghes *ghes, int silent) if (!buf_paddr) return -ENOENT; - rc = ghes_copy_tofrom_phys(ghes->estatus, buf_paddr, - sizeof(*ghes->estatus), 1); - if (rc) - return rc; + ghes_copy_tofrom_phys(ghes->estatus, buf_paddr, + sizeof(*ghes->estatus), 1); if (!ghes->estatus->block_status) return -ENOENT; @@ -202,24 +377,22 @@ static int ghes_read_estatus(struct ghes *ghes, int silent) ghes->flags |= GHES_TO_CLEAR; rc = -EIO; - len = apei_estatus_len(ghes->estatus); + len = cper_estatus_len(ghes->estatus); if (len < sizeof(*ghes->estatus)) goto err_read_block; if (len > ghes->generic->error_block_length) goto err_read_block; - if (apei_estatus_check_header(ghes->estatus)) + if (cper_estatus_check_header(ghes->estatus)) goto err_read_block; - rc = ghes_copy_tofrom_phys(ghes->estatus + 1, - buf_paddr + sizeof(*ghes->estatus), - len - sizeof(*ghes->estatus), 1); - if (rc) - return rc; - if (apei_estatus_check(ghes->estatus)) + ghes_copy_tofrom_phys(ghes->estatus + 1, + buf_paddr + sizeof(*ghes->estatus), + len - sizeof(*ghes->estatus), 1); + if (cper_estatus_check(ghes->estatus)) goto err_read_block; rc = 0; err_read_block: - if (rc && !silent) + if (rc && !silent && printk_ratelimit()) pr_warning(FW_WARN GHES_PFX "Failed to read error status block!\n"); return rc; @@ -235,28 +408,261 @@ static void ghes_clear_estatus(struct ghes *ghes) ghes->flags &= ~GHES_TO_CLEAR; } -static void ghes_do_proc(struct ghes *ghes) +static void ghes_handle_memory_failure(struct acpi_generic_data *gdata, int sev) { - int ser, processed = 0; - struct acpi_hest_generic_data *gdata; +#ifdef CONFIG_ACPI_APEI_MEMORY_FAILURE + unsigned long pfn; + int flags = -1; + int sec_sev = ghes_severity(gdata->error_severity); + struct cper_sec_mem_err *mem_err; + mem_err = (struct cper_sec_mem_err *)(gdata + 1); - ser = ghes_severity(ghes->estatus->error_severity); - apei_estatus_for_each_section(ghes->estatus, gdata) { -#ifdef CONFIG_X86_MCE + if (!(mem_err->validation_bits & CPER_MEM_VALID_PA)) + return; + + pfn = mem_err->physical_addr >> PAGE_SHIFT; + if (!pfn_valid(pfn)) { + pr_warn_ratelimited(FW_WARN GHES_PFX + "Invalid address in generic error data: %#llx\n", + mem_err->physical_addr); + return; + } + + /* iff following two events can be handled properly by now */ + if (sec_sev == GHES_SEV_CORRECTED && + (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED)) + flags = MF_SOFT_OFFLINE; + if (sev == GHES_SEV_RECOVERABLE && sec_sev == GHES_SEV_RECOVERABLE) + flags = 0; + + if (flags != -1) + memory_failure_queue(pfn, 0, flags); +#endif +} + +static void ghes_do_proc(struct ghes *ghes, + const struct acpi_generic_status *estatus) +{ + int sev, sec_sev; + struct acpi_generic_data *gdata; + + sev = ghes_severity(estatus->error_severity); + apei_estatus_for_each_section(estatus, gdata) { + sec_sev = ghes_severity(gdata->error_severity); if (!uuid_le_cmp(*(uuid_le *)gdata->section_type, CPER_SEC_PLATFORM_MEM)) { - apei_mce_report_mem_error( - ser == GHES_SER_CORRECTED, - (struct cper_sec_mem_err *)(gdata+1)); - processed = 1; + struct cper_sec_mem_err *mem_err; + mem_err = (struct cper_sec_mem_err *)(gdata+1); + ghes_edac_report_mem_error(ghes, sev, mem_err); + +#ifdef CONFIG_X86_MCE + apei_mce_report_mem_error(sev, mem_err); +#endif + ghes_handle_memory_failure(gdata, sev); + } +#ifdef CONFIG_ACPI_APEI_PCIEAER + else if (!uuid_le_cmp(*(uuid_le *)gdata->section_type, + CPER_SEC_PCIE)) { + struct cper_sec_pcie *pcie_err; + pcie_err = (struct cper_sec_pcie *)(gdata+1); + if (sev == GHES_SEV_RECOVERABLE && + sec_sev == GHES_SEV_RECOVERABLE && + pcie_err->validation_bits & CPER_PCIE_VALID_DEVICE_ID && + pcie_err->validation_bits & CPER_PCIE_VALID_AER_INFO) { + unsigned int devfn; + int aer_severity; + + devfn = PCI_DEVFN(pcie_err->device_id.device, + pcie_err->device_id.function); + aer_severity = cper_severity_to_aer(sev); + + /* + * If firmware reset the component to contain + * the error, we must reinitialize it before + * use, so treat it as a fatal AER error. + */ + if (gdata->flags & CPER_SEC_RESET) + aer_severity = AER_FATAL; + + aer_recover_queue(pcie_err->device_id.segment, + pcie_err->device_id.bus, + devfn, aer_severity, + (struct aer_capability_regs *) + pcie_err->aer_info); + } + } #endif } +} + +static void __ghes_print_estatus(const char *pfx, + const struct acpi_hest_generic *generic, + const struct acpi_generic_status *estatus) +{ + static atomic_t seqno; + unsigned int curr_seqno; + char pfx_seq[64]; + + if (pfx == NULL) { + if (ghes_severity(estatus->error_severity) <= + GHES_SEV_CORRECTED) + pfx = KERN_WARNING; + else + pfx = KERN_ERR; + } + curr_seqno = atomic_inc_return(&seqno); + snprintf(pfx_seq, sizeof(pfx_seq), "%s{%u}" HW_ERR, pfx, curr_seqno); + printk("%s""Hardware error from APEI Generic Hardware Error Source: %d\n", + pfx_seq, generic->header.source_id); + cper_estatus_print(pfx_seq, estatus); +} + +static int ghes_print_estatus(const char *pfx, + const struct acpi_hest_generic *generic, + const struct acpi_generic_status *estatus) +{ + /* Not more than 2 messages every 5 seconds */ + static DEFINE_RATELIMIT_STATE(ratelimit_corrected, 5*HZ, 2); + static DEFINE_RATELIMIT_STATE(ratelimit_uncorrected, 5*HZ, 2); + struct ratelimit_state *ratelimit; + + if (ghes_severity(estatus->error_severity) <= GHES_SEV_CORRECTED) + ratelimit = &ratelimit_corrected; + else + ratelimit = &ratelimit_uncorrected; + if (__ratelimit(ratelimit)) { + __ghes_print_estatus(pfx, generic, estatus); + return 1; + } + return 0; +} + +/* + * GHES error status reporting throttle, to report more kinds of + * errors, instead of just most frequently occurred errors. + */ +static int ghes_estatus_cached(struct acpi_generic_status *estatus) +{ + u32 len; + int i, cached = 0; + unsigned long long now; + struct ghes_estatus_cache *cache; + struct acpi_generic_status *cache_estatus; + + len = cper_estatus_len(estatus); + rcu_read_lock(); + for (i = 0; i < GHES_ESTATUS_CACHES_SIZE; i++) { + cache = rcu_dereference(ghes_estatus_caches[i]); + if (cache == NULL) + continue; + if (len != cache->estatus_len) + continue; + cache_estatus = GHES_ESTATUS_FROM_CACHE(cache); + if (memcmp(estatus, cache_estatus, len)) + continue; + atomic_inc(&cache->count); + now = sched_clock(); + if (now - cache->time_in < GHES_ESTATUS_IN_CACHE_MAX_NSEC) + cached = 1; + break; + } + rcu_read_unlock(); + return cached; +} + +static struct ghes_estatus_cache *ghes_estatus_cache_alloc( + struct acpi_hest_generic *generic, + struct acpi_generic_status *estatus) +{ + int alloced; + u32 len, cache_len; + struct ghes_estatus_cache *cache; + struct acpi_generic_status *cache_estatus; + + alloced = atomic_add_return(1, &ghes_estatus_cache_alloced); + if (alloced > GHES_ESTATUS_CACHE_ALLOCED_MAX) { + atomic_dec(&ghes_estatus_cache_alloced); + return NULL; + } + len = cper_estatus_len(estatus); + cache_len = GHES_ESTATUS_CACHE_LEN(len); + cache = (void *)gen_pool_alloc(ghes_estatus_pool, cache_len); + if (!cache) { + atomic_dec(&ghes_estatus_cache_alloced); + return NULL; + } + cache_estatus = GHES_ESTATUS_FROM_CACHE(cache); + memcpy(cache_estatus, estatus, len); + cache->estatus_len = len; + atomic_set(&cache->count, 0); + cache->generic = generic; + cache->time_in = sched_clock(); + return cache; +} + +static void ghes_estatus_cache_free(struct ghes_estatus_cache *cache) +{ + u32 len; + + len = cper_estatus_len(GHES_ESTATUS_FROM_CACHE(cache)); + len = GHES_ESTATUS_CACHE_LEN(len); + gen_pool_free(ghes_estatus_pool, (unsigned long)cache, len); + atomic_dec(&ghes_estatus_cache_alloced); +} + +static void ghes_estatus_cache_rcu_free(struct rcu_head *head) +{ + struct ghes_estatus_cache *cache; + + cache = container_of(head, struct ghes_estatus_cache, rcu); + ghes_estatus_cache_free(cache); +} + +static void ghes_estatus_cache_add( + struct acpi_hest_generic *generic, + struct acpi_generic_status *estatus) +{ + int i, slot = -1, count; + unsigned long long now, duration, period, max_period = 0; + struct ghes_estatus_cache *cache, *slot_cache = NULL, *new_cache; - if (!processed && printk_ratelimit()) - pr_warning(GHES_PFX - "Unknown error record from generic hardware error source: %d\n", - ghes->generic->header.source_id); + new_cache = ghes_estatus_cache_alloc(generic, estatus); + if (new_cache == NULL) + return; + rcu_read_lock(); + now = sched_clock(); + for (i = 0; i < GHES_ESTATUS_CACHES_SIZE; i++) { + cache = rcu_dereference(ghes_estatus_caches[i]); + if (cache == NULL) { + slot = i; + slot_cache = NULL; + break; + } + duration = now - cache->time_in; + if (duration >= GHES_ESTATUS_IN_CACHE_MAX_NSEC) { + slot = i; + slot_cache = cache; + break; + } + count = atomic_read(&cache->count); + period = duration; + do_div(period, (count + 1)); + if (period > max_period) { + max_period = period; + slot = i; + slot_cache = cache; + } + } + /* new_cache must be put into array after its contents are written */ + smp_wmb(); + if (slot != -1 && cmpxchg(ghes_estatus_caches + slot, + slot_cache, new_cache) == slot_cache) { + if (slot_cache) + call_rcu(&slot_cache->rcu, ghes_estatus_cache_rcu_free); + } else + ghes_estatus_cache_free(new_cache); + rcu_read_unlock(); } static int ghes_proc(struct ghes *ghes) @@ -266,13 +672,52 @@ static int ghes_proc(struct ghes *ghes) rc = ghes_read_estatus(ghes, 0); if (rc) goto out; - ghes_do_proc(ghes); - + if (!ghes_estatus_cached(ghes->estatus)) { + if (ghes_print_estatus(NULL, ghes->generic, ghes->estatus)) + ghes_estatus_cache_add(ghes->generic, ghes->estatus); + } + ghes_do_proc(ghes, ghes->estatus); out: ghes_clear_estatus(ghes); return 0; } +static void ghes_add_timer(struct ghes *ghes) +{ + struct acpi_hest_generic *g = ghes->generic; + unsigned long expire; + + if (!g->notify.poll_interval) { + pr_warning(FW_WARN GHES_PFX "Poll interval is 0 for generic hardware error source: %d, disabled.\n", + g->header.source_id); + return; + } + expire = jiffies + msecs_to_jiffies(g->notify.poll_interval); + ghes->timer.expires = round_jiffies_relative(expire); + add_timer(&ghes->timer); +} + +static void ghes_poll_func(unsigned long data) +{ + struct ghes *ghes = (void *)data; + + ghes_proc(ghes); + if (!(ghes->flags & GHES_EXITING)) + ghes_add_timer(ghes); +} + +static irqreturn_t ghes_irq_func(int irq, void *data) +{ + struct ghes *ghes = data; + int rc; + + rc = ghes_proc(ghes); + if (rc) + return IRQ_NONE; + + return IRQ_HANDLED; +} + static int ghes_notify_sci(struct notifier_block *this, unsigned long event, void *data) { @@ -289,35 +734,200 @@ static int ghes_notify_sci(struct notifier_block *this, return ret; } +static struct llist_node *llist_nodes_reverse(struct llist_node *llnode) +{ + struct llist_node *next, *tail = NULL; + + while (llnode) { + next = llnode->next; + llnode->next = tail; + tail = llnode; + llnode = next; + } + + return tail; +} + +static void ghes_proc_in_irq(struct irq_work *irq_work) +{ + struct llist_node *llnode, *next; + struct ghes_estatus_node *estatus_node; + struct acpi_hest_generic *generic; + struct acpi_generic_status *estatus; + u32 len, node_len; + + llnode = llist_del_all(&ghes_estatus_llist); + /* + * Because the time order of estatus in list is reversed, + * revert it back to proper order. + */ + llnode = llist_nodes_reverse(llnode); + while (llnode) { + next = llnode->next; + estatus_node = llist_entry(llnode, struct ghes_estatus_node, + llnode); + estatus = GHES_ESTATUS_FROM_NODE(estatus_node); + len = cper_estatus_len(estatus); + node_len = GHES_ESTATUS_NODE_LEN(len); + ghes_do_proc(estatus_node->ghes, estatus); + if (!ghes_estatus_cached(estatus)) { + generic = estatus_node->generic; + if (ghes_print_estatus(NULL, generic, estatus)) + ghes_estatus_cache_add(generic, estatus); + } + gen_pool_free(ghes_estatus_pool, (unsigned long)estatus_node, + node_len); + llnode = next; + } +} + +static void ghes_print_queued_estatus(void) +{ + struct llist_node *llnode; + struct ghes_estatus_node *estatus_node; + struct acpi_hest_generic *generic; + struct acpi_generic_status *estatus; + u32 len, node_len; + + llnode = llist_del_all(&ghes_estatus_llist); + /* + * Because the time order of estatus in list is reversed, + * revert it back to proper order. + */ + llnode = llist_nodes_reverse(llnode); + while (llnode) { + estatus_node = llist_entry(llnode, struct ghes_estatus_node, + llnode); + estatus = GHES_ESTATUS_FROM_NODE(estatus_node); + len = cper_estatus_len(estatus); + node_len = GHES_ESTATUS_NODE_LEN(len); + generic = estatus_node->generic; + ghes_print_estatus(NULL, generic, estatus); + llnode = llnode->next; + } +} + +static int ghes_notify_nmi(unsigned int cmd, struct pt_regs *regs) +{ + struct ghes *ghes, *ghes_global = NULL; + int sev, sev_global = -1; + int ret = NMI_DONE; + + raw_spin_lock(&ghes_nmi_lock); + list_for_each_entry_rcu(ghes, &ghes_nmi, list) { + if (ghes_read_estatus(ghes, 1)) { + ghes_clear_estatus(ghes); + continue; + } + sev = ghes_severity(ghes->estatus->error_severity); + if (sev > sev_global) { + sev_global = sev; + ghes_global = ghes; + } + ret = NMI_HANDLED; + } + + if (ret == NMI_DONE) + goto out; + + if (sev_global >= GHES_SEV_PANIC) { + oops_begin(); + ghes_print_queued_estatus(); + __ghes_print_estatus(KERN_EMERG, ghes_global->generic, + ghes_global->estatus); + /* reboot to log the error! */ + if (panic_timeout == 0) + panic_timeout = ghes_panic_timeout; + panic("Fatal hardware error!"); + } + + list_for_each_entry_rcu(ghes, &ghes_nmi, list) { +#ifdef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG + u32 len, node_len; + struct ghes_estatus_node *estatus_node; + struct acpi_generic_status *estatus; +#endif + if (!(ghes->flags & GHES_TO_CLEAR)) + continue; +#ifdef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG + if (ghes_estatus_cached(ghes->estatus)) + goto next; + /* Save estatus for further processing in IRQ context */ + len = cper_estatus_len(ghes->estatus); + node_len = GHES_ESTATUS_NODE_LEN(len); + estatus_node = (void *)gen_pool_alloc(ghes_estatus_pool, + node_len); + if (estatus_node) { + estatus_node->ghes = ghes; + estatus_node->generic = ghes->generic; + estatus = GHES_ESTATUS_FROM_NODE(estatus_node); + memcpy(estatus, ghes->estatus, len); + llist_add(&estatus_node->llnode, &ghes_estatus_llist); + } +next: +#endif + ghes_clear_estatus(ghes); + } +#ifdef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG + irq_work_queue(&ghes_proc_irq_work); +#endif + +out: + raw_spin_unlock(&ghes_nmi_lock); + return ret; +} + static struct notifier_block ghes_notifier_sci = { .notifier_call = ghes_notify_sci, }; -static int hest_ghes_parse(struct acpi_hest_header *hest_hdr, void *data) +static unsigned long ghes_esource_prealloc_size( + const struct acpi_hest_generic *generic) +{ + unsigned long block_length, prealloc_records, prealloc_size; + + block_length = min_t(unsigned long, generic->error_block_length, + GHES_ESTATUS_MAX_SIZE); + prealloc_records = max_t(unsigned long, + generic->records_to_preallocate, 1); + prealloc_size = min_t(unsigned long, block_length * prealloc_records, + GHES_ESOURCE_PREALLOC_MAX_SIZE); + + return prealloc_size; +} + +static int ghes_probe(struct platform_device *ghes_dev) { struct acpi_hest_generic *generic; struct ghes *ghes = NULL; - int rc = 0; + unsigned long len; + int rc = -EINVAL; - if (hest_hdr->type != ACPI_HEST_TYPE_GENERIC_ERROR) - return 0; - - generic = (struct acpi_hest_generic *)hest_hdr; + generic = *(struct acpi_hest_generic **)ghes_dev->dev.platform_data; if (!generic->enabled) - return 0; + return -ENODEV; - if (generic->error_block_length < - sizeof(struct acpi_hest_generic_status)) { - pr_warning(FW_BUG GHES_PFX -"Invalid error block length: %u for generic hardware error source: %d\n", - generic->error_block_length, + switch (generic->notify.type) { + case ACPI_HEST_NOTIFY_POLLED: + case ACPI_HEST_NOTIFY_EXTERNAL: + case ACPI_HEST_NOTIFY_SCI: + case ACPI_HEST_NOTIFY_NMI: + break; + case ACPI_HEST_NOTIFY_LOCAL: + pr_warning(GHES_PFX "Generic hardware error source: %d notified via local interrupt is not supported!\n", generic->header.source_id); goto err; + default: + pr_warning(FW_WARN GHES_PFX "Unknown notification type: %u for generic hardware error source: %d\n", + generic->notify.type, generic->header.source_id); + goto err; } - if (generic->records_to_preallocate == 0) { - pr_warning(FW_BUG GHES_PFX -"Invalid records to preallocate: %u for generic hardware error source: %d\n", - generic->records_to_preallocate, + + rc = -EIO; + if (generic->error_block_length < + sizeof(struct acpi_generic_status)) { + pr_warning(FW_BUG GHES_PFX "Invalid error block length: %u for generic hardware error source: %d\n", + generic->error_block_length, generic->header.source_id); goto err; } @@ -327,58 +937,129 @@ static int hest_ghes_parse(struct acpi_hest_header *hest_hdr, void *data) ghes = NULL; goto err; } + + rc = ghes_edac_register(ghes, &ghes_dev->dev); + if (rc < 0) + goto err; + switch (generic->notify.type) { case ACPI_HEST_NOTIFY_POLLED: - pr_warning(GHES_PFX -"Generic hardware error source: %d notified via POLL is not supported!\n", - generic->header.source_id); + ghes->timer.function = ghes_poll_func; + ghes->timer.data = (unsigned long)ghes; + init_timer_deferrable(&ghes->timer); + ghes_add_timer(ghes); break; case ACPI_HEST_NOTIFY_EXTERNAL: - case ACPI_HEST_NOTIFY_LOCAL: - pr_warning(GHES_PFX -"Generic hardware error source: %d notified via IRQ is not supported!\n", - generic->header.source_id); + /* External interrupt vector is GSI */ + rc = acpi_gsi_to_irq(generic->notify.vector, &ghes->irq); + if (rc) { + pr_err(GHES_PFX "Failed to map GSI to IRQ for generic hardware error source: %d\n", + generic->header.source_id); + goto err_edac_unreg; + } + rc = request_irq(ghes->irq, ghes_irq_func, 0, "GHES IRQ", ghes); + if (rc) { + pr_err(GHES_PFX "Failed to register IRQ for generic hardware error source: %d\n", + generic->header.source_id); + goto err_edac_unreg; + } break; case ACPI_HEST_NOTIFY_SCI: + mutex_lock(&ghes_list_mutex); if (list_empty(&ghes_sci)) register_acpi_hed_notifier(&ghes_notifier_sci); list_add_rcu(&ghes->list, &ghes_sci); + mutex_unlock(&ghes_list_mutex); break; case ACPI_HEST_NOTIFY_NMI: - pr_warning(GHES_PFX -"Generic hardware error source: %d notified via NMI is not supported!\n", - generic->header.source_id); + 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); break; default: - pr_warning(FW_WARN GHES_PFX - "Unknown notification type: %u for generic hardware error source: %d\n", - generic->notify.type, generic->header.source_id); - break; + BUG(); } + platform_set_drvdata(ghes_dev, ghes); return 0; +err_edac_unreg: + ghes_edac_unregister(ghes); err: - if (ghes) + if (ghes) { ghes_fini(ghes); + kfree(ghes); + } return rc; } -static void ghes_cleanup(void) +static int ghes_remove(struct platform_device *ghes_dev) { - struct ghes *ghes, *nghes; - - if (!list_empty(&ghes_sci)) - unregister_acpi_hed_notifier(&ghes_notifier_sci); + struct ghes *ghes; + struct acpi_hest_generic *generic; + unsigned long len; - synchronize_rcu(); + ghes = platform_get_drvdata(ghes_dev); + generic = ghes->generic; - list_for_each_entry_safe(ghes, nghes, &ghes_sci, list) { - list_del(&ghes->list); - ghes_fini(ghes); - kfree(ghes); + ghes->flags |= GHES_EXITING; + switch (generic->notify.type) { + case ACPI_HEST_NOTIFY_POLLED: + del_timer_sync(&ghes->timer); + break; + case ACPI_HEST_NOTIFY_EXTERNAL: + free_irq(ghes->irq, ghes); + break; + case ACPI_HEST_NOTIFY_SCI: + mutex_lock(&ghes_list_mutex); + list_del_rcu(&ghes->list); + if (list_empty(&ghes_sci)) + unregister_acpi_hed_notifier(&ghes_notifier_sci); + 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); + break; + default: + BUG(); + break; } + + ghes_fini(ghes); + + ghes_edac_unregister(ghes); + + kfree(ghes); + + platform_set_drvdata(ghes_dev, NULL); + + return 0; } +static struct platform_driver ghes_platform_driver = { + .driver = { + .name = "GHES", + .owner = THIS_MODULE, + }, + .probe = ghes_probe, + .remove = ghes_remove, +}; + static int __init ghes_init(void) { int rc; @@ -391,32 +1072,54 @@ static int __init ghes_init(void) return -EINVAL; } - rc = apei_hest_parse(hest_ghes_parse, NULL); - if (rc) { - pr_err(GHES_PFX - "Error during parsing HEST generic hardware error sources.\n"); - goto err_cleanup; + if (ghes_disable) { + pr_info(GHES_PFX "GHES is not enabled!\n"); + return -EINVAL; } - if (list_empty(&ghes_sci)) { - pr_info(GHES_PFX - "No functional generic hardware error sources.\n"); - rc = -ENODEV; - goto err_cleanup; - } + init_irq_work(&ghes_proc_irq_work, ghes_proc_in_irq); + + rc = ghes_ioremap_init(); + if (rc) + goto err; - pr_info(GHES_PFX - "Generic Hardware Error Source support is initialized.\n"); + rc = ghes_estatus_pool_init(); + if (rc) + goto err_ioremap_exit; + + rc = ghes_estatus_pool_expand(GHES_ESTATUS_CACHE_AVG_SIZE * + GHES_ESTATUS_CACHE_ALLOCED_MAX); + if (rc) + goto err_pool_exit; + + rc = platform_driver_register(&ghes_platform_driver); + if (rc) + goto err_pool_exit; + + rc = apei_osc_setup(); + if (rc == 0 && osc_sb_apei_support_acked) + pr_info(GHES_PFX "APEI firmware first mode is enabled by APEI bit and WHEA _OSC.\n"); + else if (rc == 0 && !osc_sb_apei_support_acked) + pr_info(GHES_PFX "APEI firmware first mode is enabled by WHEA _OSC.\n"); + else if (rc && osc_sb_apei_support_acked) + pr_info(GHES_PFX "APEI firmware first mode is enabled by APEI bit.\n"); + else + pr_info(GHES_PFX "Failed to enable APEI firmware first mode.\n"); return 0; -err_cleanup: - ghes_cleanup(); +err_pool_exit: + ghes_estatus_pool_exit(); +err_ioremap_exit: + ghes_ioremap_exit(); +err: return rc; } static void __exit ghes_exit(void) { - ghes_cleanup(); + platform_driver_unregister(&ghes_platform_driver); + ghes_estatus_pool_exit(); + ghes_ioremap_exit(); } module_init(ghes_init); @@ -425,3 +1128,4 @@ module_exit(ghes_exit); MODULE_AUTHOR("Huang Ying"); MODULE_DESCRIPTION("APEI Generic Hardware Error Source support"); MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:GHES"); diff --git a/drivers/acpi/apei/hest.c b/drivers/acpi/apei/hest.c index e7f40d362cb..f5e37f32c71 100644 --- a/drivers/acpi/apei/hest.c +++ b/drivers/acpi/apei/hest.c @@ -34,25 +34,22 @@ #include <linux/kdebug.h> #include <linux/highmem.h> #include <linux/io.h> +#include <linux/platform_device.h> #include <acpi/apei.h> +#include <asm/mce.h> #include "apei-internal.h" #define HEST_PFX "HEST: " -int hest_disable; +bool hest_disable; EXPORT_SYMBOL_GPL(hest_disable); /* HEST table parsing */ -static struct acpi_table_hest *hest_tab; +static struct acpi_table_hest *__read_mostly hest_tab; -static int hest_void_parse(struct acpi_hest_header *hest_hdr, void *data) -{ - return 0; -} - -static int hest_esrc_len_tab[ACPI_HEST_TYPE_RESERVED] = { +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), @@ -93,7 +90,7 @@ int apei_hest_parse(apei_hest_func_t func, void *data) struct acpi_hest_header *hest_hdr; int i, rc, len; - if (hest_disable) + if (hest_disable || !hest_tab) return -EINVAL; hest_hdr = (struct acpi_hest_header *)(hest_tab + 1); @@ -125,6 +122,117 @@ int apei_hest_parse(apei_hest_func_t func, void *data) } EXPORT_SYMBOL_GPL(apei_hest_parse); +/* + * Check if firmware advertises firmware first mode. We need FF bit to be set + * along with a set of MC banks which work in FF mode. + */ +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; +} + +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; @@ -133,41 +241,42 @@ static int __init setup_hest_disable(char *str) __setup("hest_disable", setup_hest_disable); -static int __init hest_init(void) +void __init acpi_hest_init(void) { acpi_status status; int rc = -ENODEV; - - if (acpi_disabled) - goto err; + unsigned int ghes_count = 0; if (hest_disable) { - pr_info(HEST_PFX "HEST tabling parsing is disabled.\n"); - goto err; + pr_info(HEST_PFX "Table parsing disabled.\n"); + return; } status = acpi_get_table(ACPI_SIG_HEST, 0, (struct acpi_table_header **)&hest_tab); - if (status == AE_NOT_FOUND) { - pr_info(HEST_PFX "Table is not found!\n"); + if (status == AE_NOT_FOUND) goto err; - } else if (ACPI_FAILURE(status)) { + 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; } - rc = apei_hest_parse(hest_void_parse, NULL); - if (rc) - goto err; + if (!acpi_disable_cmcff) + apei_hest_parse(hest_parse_cmc, NULL); - pr_info(HEST_PFX "HEST table parsing is initialized.\n"); + 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; + } - return 0; + pr_info(HEST_PFX "Table parsing has been initialized.\n"); + return; err: hest_disable = 1; - return rc; } - -subsys_initcall(hest_init); |