diff options
Diffstat (limited to 'drivers/acpi')
-rw-r--r-- | drivers/acpi/Kconfig | 21 | ||||
-rw-r--r-- | drivers/acpi/Makefile | 2 | ||||
-rw-r--r-- | drivers/acpi/acpi_extlog.c | 327 | ||||
-rw-r--r-- | drivers/acpi/apei/Kconfig | 2 | ||||
-rw-r--r-- | drivers/acpi/apei/Makefile | 2 | ||||
-rw-r--r-- | drivers/acpi/apei/apei-internal.h | 12 | ||||
-rw-r--r-- | drivers/acpi/apei/cper.c | 402 | ||||
-rw-r--r-- | drivers/acpi/apei/ghes.c | 58 | ||||
-rw-r--r-- | drivers/acpi/bus.c | 3 | ||||
-rw-r--r-- | drivers/acpi/processor_idle.c | 46 |
10 files changed, 400 insertions, 475 deletions
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index 589da059ce39..c95df0b8c880 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -356,4 +356,25 @@ config ACPI_BGRT source "drivers/acpi/apei/Kconfig" +config ACPI_EXTLOG + tristate "Extended Error Log support" + depends on X86_MCE && X86_LOCAL_APIC + select EFI + select UEFI_CPER + default n + help + Certain usages such as Predictive Failure Analysis (PFA) require + more information about the error than what can be described in + processor machine check banks. Most server processors log + additional information about the error in processor uncore + registers. Since the addresses and layout of these registers vary + widely from one processor to another, system software cannot + readily make use of them. To complicate matters further, some of + the additional error information cannot be constructed without + detailed knowledge about platform topology. + + Enhanced MCA Logging allows firmware to provide additional error + information to system software, synchronous with MCE or CMCI. This + driver adds support for that functionality. + endif # ACPI diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile index a55fc06db4ae..0331f91d56e6 100644 --- a/drivers/acpi/Makefile +++ b/drivers/acpi/Makefile @@ -81,3 +81,5 @@ processor-$(CONFIG_CPU_FREQ) += processor_perflib.o obj-$(CONFIG_ACPI_PROCESSOR_AGGREGATOR) += acpi_pad.o obj-$(CONFIG_ACPI_APEI) += apei/ + +obj-$(CONFIG_ACPI_EXTLOG) += acpi_extlog.o diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c new file mode 100644 index 000000000000..a6869e110ce5 --- /dev/null +++ b/drivers/acpi/acpi_extlog.c @@ -0,0 +1,327 @@ +/* + * Extended Error Log driver + * + * Copyright (C) 2013 Intel Corp. + * Author: Chen, Gong <gong.chen@intel.com> + * + * This file is licensed under GPLv2. + */ + +#include <linux/module.h> +#include <linux/acpi.h> +#include <acpi/acpi_bus.h> +#include <linux/cper.h> +#include <linux/ratelimit.h> +#include <asm/cpu.h> +#include <asm/mce.h> + +#include "apei/apei-internal.h" + +#define EXT_ELOG_ENTRY_MASK GENMASK_ULL(51, 0) /* elog entry address mask */ + +#define EXTLOG_DSM_REV 0x0 +#define EXTLOG_FN_QUERY 0x0 +#define EXTLOG_FN_ADDR 0x1 + +#define FLAG_OS_OPTIN BIT(0) +#define EXTLOG_QUERY_L1_EXIST BIT(1) +#define ELOG_ENTRY_VALID (1ULL<<63) +#define ELOG_ENTRY_LEN 0x1000 + +#define EMCA_BUG \ + "Can not request iomem region <0x%016llx-0x%016llx> - eMCA disabled\n" + +struct extlog_l1_head { + u32 ver; /* Header Version */ + u32 hdr_len; /* Header Length */ + u64 total_len; /* entire L1 Directory length including this header */ + u64 elog_base; /* MCA Error Log Directory base address */ + u64 elog_len; /* MCA Error Log Directory length */ + u32 flags; /* bit 0 - OS/VMM Opt-in */ + u8 rev0[12]; + u32 entries; /* Valid L1 Directory entries per logical processor */ + u8 rev1[12]; +}; + +static u8 extlog_dsm_uuid[] = "663E35AF-CC10-41A4-88EA-5470AF055295"; + +/* L1 table related physical address */ +static u64 elog_base; +static size_t elog_size; +static u64 l1_dirbase; +static size_t l1_size; + +/* L1 table related virtual address */ +static void __iomem *extlog_l1_addr; +static void __iomem *elog_addr; + +static void *elog_buf; + +static u64 *l1_entry_base; +static u32 l1_percpu_entry; + +#define ELOG_IDX(cpu, bank) \ + (cpu_physical_id(cpu) * l1_percpu_entry + (bank)) + +#define ELOG_ENTRY_DATA(idx) \ + (*(l1_entry_base + (idx))) + +#define ELOG_ENTRY_ADDR(phyaddr) \ + (phyaddr - elog_base + (u8 *)elog_addr) + +static struct acpi_generic_status *extlog_elog_entry_check(int cpu, int bank) +{ + int idx; + u64 data; + struct acpi_generic_status *estatus; + + WARN_ON(cpu < 0); + idx = ELOG_IDX(cpu, bank); + data = ELOG_ENTRY_DATA(idx); + if ((data & ELOG_ENTRY_VALID) == 0) + return NULL; + + data &= EXT_ELOG_ENTRY_MASK; + estatus = (struct acpi_generic_status *)ELOG_ENTRY_ADDR(data); + + /* if no valid data in elog entry, just return */ + if (estatus->block_status == 0) + return NULL; + + return estatus; +} + +static void __print_extlog_rcd(const char *pfx, + struct acpi_generic_status *estatus, int cpu) +{ + static atomic_t seqno; + unsigned int curr_seqno; + char pfx_seq[64]; + + if (!pfx) { + if (estatus->error_severity <= CPER_SEV_CORRECTED) + pfx = KERN_INFO; + else + pfx = KERN_ERR; + } + curr_seqno = atomic_inc_return(&seqno); + snprintf(pfx_seq, sizeof(pfx_seq), "%s{%u}", pfx, curr_seqno); + printk("%s""Hardware error detected on CPU%d\n", pfx_seq, cpu); + cper_estatus_print(pfx_seq, estatus); +} + +static int print_extlog_rcd(const char *pfx, + struct acpi_generic_status *estatus, int cpu) +{ + /* 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 (estatus->error_severity == CPER_SEV_CORRECTED || + (estatus->error_severity == CPER_SEV_INFORMATIONAL)) + ratelimit = &ratelimit_corrected; + else + ratelimit = &ratelimit_uncorrected; + if (__ratelimit(ratelimit)) { + __print_extlog_rcd(pfx, estatus, cpu); + return 0; + } + + return 1; +} + +static int extlog_print(struct notifier_block *nb, unsigned long val, + void *data) +{ + struct mce *mce = (struct mce *)data; + int bank = mce->bank; + int cpu = mce->extcpu; + struct acpi_generic_status *estatus; + int rc; + + estatus = extlog_elog_entry_check(cpu, bank); + if (estatus == NULL) + return NOTIFY_DONE; + + memcpy(elog_buf, (void *)estatus, ELOG_ENTRY_LEN); + /* clear record status to enable BIOS to update it again */ + estatus->block_status = 0; + + rc = print_extlog_rcd(NULL, (struct acpi_generic_status *)elog_buf, cpu); + + return NOTIFY_DONE; +} + +static int extlog_get_dsm(acpi_handle handle, int rev, int func, u64 *ret) +{ + struct acpi_buffer buf = {ACPI_ALLOCATE_BUFFER, NULL}; + struct acpi_object_list input; + union acpi_object params[4], *obj; + u8 uuid[16]; + int i; + + acpi_str_to_uuid(extlog_dsm_uuid, uuid); + input.count = 4; + input.pointer = params; + params[0].type = ACPI_TYPE_BUFFER; + params[0].buffer.length = 16; + params[0].buffer.pointer = uuid; + params[1].type = ACPI_TYPE_INTEGER; + params[1].integer.value = rev; + params[2].type = ACPI_TYPE_INTEGER; + params[2].integer.value = func; + params[3].type = ACPI_TYPE_PACKAGE; + params[3].package.count = 0; + params[3].package.elements = NULL; + + if (ACPI_FAILURE(acpi_evaluate_object(handle, "_DSM", &input, &buf))) + return -1; + + *ret = 0; + obj = (union acpi_object *)buf.pointer; + if (obj->type == ACPI_TYPE_INTEGER) { + *ret = obj->integer.value; + } else if (obj->type == ACPI_TYPE_BUFFER) { + if (obj->buffer.length <= 8) { + for (i = 0; i < obj->buffer.length; i++) + *ret |= (obj->buffer.pointer[i] << (i * 8)); + } + } + kfree(buf.pointer); + + return 0; +} + +static bool extlog_get_l1addr(void) +{ + acpi_handle handle; + u64 ret; + + if (ACPI_FAILURE(acpi_get_handle(NULL, "\\_SB", &handle))) + return false; + + if (extlog_get_dsm(handle, EXTLOG_DSM_REV, EXTLOG_FN_QUERY, &ret) || + !(ret & EXTLOG_QUERY_L1_EXIST)) + return false; + + if (extlog_get_dsm(handle, EXTLOG_DSM_REV, EXTLOG_FN_ADDR, &ret)) + return false; + + l1_dirbase = ret; + /* Spec says L1 directory must be 4K aligned, bail out if it isn't */ + if (l1_dirbase & ((1 << 12) - 1)) { + pr_warn(FW_BUG "L1 Directory is invalid at physical %llx\n", + l1_dirbase); + return false; + } + + return true; +} +static struct notifier_block extlog_mce_dec = { + .notifier_call = extlog_print, +}; + +static int __init extlog_init(void) +{ + struct extlog_l1_head *l1_head; + void __iomem *extlog_l1_hdr; + size_t l1_hdr_size; + struct resource *r; + u64 cap; + int rc; + + rc = -ENODEV; + + rdmsrl(MSR_IA32_MCG_CAP, cap); + if (!(cap & MCG_ELOG_P)) + return rc; + + if (!extlog_get_l1addr()) + return rc; + + rc = -EINVAL; + /* get L1 header to fetch necessary information */ + l1_hdr_size = sizeof(struct extlog_l1_head); + r = request_mem_region(l1_dirbase, l1_hdr_size, "L1 DIR HDR"); + if (!r) { + pr_warn(FW_BUG EMCA_BUG, + (unsigned long long)l1_dirbase, + (unsigned long long)l1_dirbase + l1_hdr_size); + goto err; + } + + extlog_l1_hdr = acpi_os_map_memory(l1_dirbase, l1_hdr_size); + l1_head = (struct extlog_l1_head *)extlog_l1_hdr; + l1_size = l1_head->total_len; + l1_percpu_entry = l1_head->entries; + elog_base = l1_head->elog_base; + elog_size = l1_head->elog_len; + acpi_os_unmap_memory(extlog_l1_hdr, l1_hdr_size); + release_mem_region(l1_dirbase, l1_hdr_size); + + /* remap L1 header again based on completed information */ + r = request_mem_region(l1_dirbase, l1_size, "L1 Table"); + if (!r) { + pr_warn(FW_BUG EMCA_BUG, + (unsigned long long)l1_dirbase, + (unsigned long long)l1_dirbase + l1_size); + goto err; + } + extlog_l1_addr = acpi_os_map_memory(l1_dirbase, l1_size); + l1_entry_base = (u64 *)((u8 *)extlog_l1_addr + l1_hdr_size); + + /* remap elog table */ + r = request_mem_region(elog_base, elog_size, "Elog Table"); + if (!r) { + pr_warn(FW_BUG EMCA_BUG, + (unsigned long long)elog_base, + (unsigned long long)elog_base + elog_size); + goto err_release_l1_dir; + } + elog_addr = acpi_os_map_memory(elog_base, elog_size); + + rc = -ENOMEM; + /* allocate buffer to save elog record */ + elog_buf = kmalloc(ELOG_ENTRY_LEN, GFP_KERNEL); + if (elog_buf == NULL) + goto err_release_elog; + + mce_register_decode_chain(&extlog_mce_dec); + /* enable OS to be involved to take over management from BIOS */ + ((struct extlog_l1_head *)extlog_l1_addr)->flags |= FLAG_OS_OPTIN; + + return 0; + +err_release_elog: + if (elog_addr) + acpi_os_unmap_memory(elog_addr, elog_size); + release_mem_region(elog_base, elog_size); +err_release_l1_dir: + if (extlog_l1_addr) + acpi_os_unmap_memory(extlog_l1_addr, l1_size); + release_mem_region(l1_dirbase, l1_size); +err: + pr_warn(FW_BUG "Extended error log disabled because of problems parsing f/w tables\n"); + return rc; +} + +static void __exit extlog_exit(void) +{ + mce_unregister_decode_chain(&extlog_mce_dec); + ((struct extlog_l1_head *)extlog_l1_addr)->flags &= ~FLAG_OS_OPTIN; + if (extlog_l1_addr) + acpi_os_unmap_memory(extlog_l1_addr, l1_size); + if (elog_addr) + acpi_os_unmap_memory(elog_addr, elog_size); + release_mem_region(elog_base, elog_size); + release_mem_region(l1_dirbase, l1_size); + kfree(elog_buf); +} + +module_init(extlog_init); +module_exit(extlog_exit); + +MODULE_AUTHOR("Chen, Gong <gong.chen@intel.com>"); +MODULE_DESCRIPTION("Extended MCA Error Log Driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/acpi/apei/Kconfig b/drivers/acpi/apei/Kconfig index f0c1ce95a0ec..786294bb682c 100644 --- a/drivers/acpi/apei/Kconfig +++ b/drivers/acpi/apei/Kconfig @@ -2,6 +2,8 @@ config ACPI_APEI bool "ACPI Platform Error Interface (APEI)" select MISC_FILESYSTEMS select PSTORE + select EFI + select UEFI_CPER depends on X86 help APEI allows to report errors (for example from the chipset) diff --git a/drivers/acpi/apei/Makefile b/drivers/acpi/apei/Makefile index d1d1bc0a4ee1..5d575a955940 100644 --- a/drivers/acpi/apei/Makefile +++ b/drivers/acpi/apei/Makefile @@ -3,4 +3,4 @@ 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-internal.h b/drivers/acpi/apei/apei-internal.h index f220d642136e..21ba34a73883 100644 --- a/drivers/acpi/apei/apei-internal.h +++ b/drivers/acpi/apei/apei-internal.h @@ -122,11 +122,11 @@ 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 + \ @@ -135,10 +135,10 @@ static inline u32 apei_estatus_len(struct acpi_hest_generic_status *estatus) return sizeof(*estatus) + estatus->data_length; } -void apei_estatus_print(const char *pfx, - const struct acpi_hest_generic_status *estatus); -int apei_estatus_check_header(const struct acpi_hest_generic_status *estatus); -int apei_estatus_check(const struct acpi_hest_generic_status *estatus); +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 33dc6a004802..000000000000 --- a/drivers/acpi/apei/cper.c +++ /dev/null @@ -1,402 +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> -#include <linux/pci.h> -#include <linux/aer.h> - -/* - * CPER record ID need to be unique even after reboot, because record - * ID is used as index for ERST storage, while CPER records from - * multiple boot may co-exist in ERST. - */ -u64 cper_next_record_id(void) -{ - static atomic64_t seq; - - if (!atomic64_read(&seq)) - atomic64_set(&seq, ((u64)get_seconds()) << 32); - - return atomic64_inc_return(&seq); -} -EXPORT_SYMBOL_GPL(cper_next_record_id); - -static const char *cper_severity_strs[] = { - "recoverable", - "fatal", - "corrected", - "info", -}; - -static const char *cper_severity_str(unsigned int severity) -{ - return severity < ARRAY_SIZE(cper_severity_strs) ? - cper_severity_strs[severity] : "unknown"; -} - -/* - * cper_print_bits - print strings for set bits - * @pfx: prefix for each line, including log level and prefix string - * @bits: bit mask - * @strs: string array, indexed by bit position - * @strs_size: size of the string array: @strs - * - * For each set bit in @bits, print the corresponding string in @strs. - * If the output length is longer than 80, multiple line will be - * printed, with @pfx is printed at the beginning of each line. - */ -void cper_print_bits(const char *pfx, unsigned int bits, - const char *strs[], unsigned int strs_size) -{ - int i, len = 0; - const char *str; - char buf[84]; - - for (i = 0; i < strs_size; i++) { - if (!(bits & (1U << i))) - continue; - str = strs[i]; - if (!str) - continue; - if (len && len + strlen(str) + 2 > 80) { - printk("%s\n", buf); - len = 0; - } - if (!len) - len = snprintf(buf, sizeof(buf), "%s%s", pfx, str); - else - len += snprintf(buf+len, sizeof(buf)-len, ", %s", str); - } - if (len) - printk("%s\n", buf); -} - -static const char *cper_proc_type_strs[] = { - "IA32/X64", - "IA64", -}; - -static const char *cper_proc_isa_strs[] = { - "IA32", - "IA64", - "X64", -}; - -static const char *cper_proc_error_type_strs[] = { - "cache error", - "TLB error", - "bus error", - "micro-architectural error", -}; - -static const char *cper_proc_op_strs[] = { - "unknown or generic", - "data read", - "data write", - "instruction execution", -}; - -static const char *cper_proc_flag_strs[] = { - "restartable", - "precise IP", - "overflow", - "corrected", -}; - -static void cper_print_proc_generic(const char *pfx, - const struct cper_sec_proc_generic *proc) -{ - if (proc->validation_bits & CPER_PROC_VALID_TYPE) - printk("%s""processor_type: %d, %s\n", pfx, proc->proc_type, - proc->proc_type < ARRAY_SIZE(cper_proc_type_strs) ? - cper_proc_type_strs[proc->proc_type] : "unknown"); - if (proc->validation_bits & CPER_PROC_VALID_ISA) - printk("%s""processor_isa: %d, %s\n", pfx, proc->proc_isa, - proc->proc_isa < ARRAY_SIZE(cper_proc_isa_strs) ? - cper_proc_isa_strs[proc->proc_isa] : "unknown"); - if (proc->validation_bits & CPER_PROC_VALID_ERROR_TYPE) { - printk("%s""error_type: 0x%02x\n", pfx, proc->proc_error_type); - cper_print_bits(pfx, proc->proc_error_type, - cper_proc_error_type_strs, - ARRAY_SIZE(cper_proc_error_type_strs)); - } - if (proc->validation_bits & CPER_PROC_VALID_OPERATION) - printk("%s""operation: %d, %s\n", pfx, proc->operation, - proc->operation < ARRAY_SIZE(cper_proc_op_strs) ? - cper_proc_op_strs[proc->operation] : "unknown"); - if (proc->validation_bits & CPER_PROC_VALID_FLAGS) { - printk("%s""flags: 0x%02x\n", pfx, proc->flags); - cper_print_bits(pfx, proc->flags, cper_proc_flag_strs, - ARRAY_SIZE(cper_proc_flag_strs)); - } - if (proc->validation_bits & CPER_PROC_VALID_LEVEL) - printk("%s""level: %d\n", pfx, proc->level); - if (proc->validation_bits & CPER_PROC_VALID_VERSION) - printk("%s""version_info: 0x%016llx\n", pfx, proc->cpu_version); - if (proc->validation_bits & CPER_PROC_VALID_ID) - printk("%s""processor_id: 0x%016llx\n", pfx, proc->proc_id); - if (proc->validation_bits & CPER_PROC_VALID_TARGET_ADDRESS) - printk("%s""target_address: 0x%016llx\n", - pfx, proc->target_addr); - if (proc->validation_bits & CPER_PROC_VALID_REQUESTOR_ID) - printk("%s""requestor_id: 0x%016llx\n", - pfx, proc->requestor_id); - if (proc->validation_bits & CPER_PROC_VALID_RESPONDER_ID) - printk("%s""responder_id: 0x%016llx\n", - pfx, proc->responder_id); - if (proc->validation_bits & CPER_PROC_VALID_IP) - printk("%s""IP: 0x%016llx\n", pfx, proc->ip); -} - -static const char *cper_mem_err_type_strs[] = { - "unknown", - "no error", - "single-bit ECC", - "multi-bit ECC", - "single-symbol chipkill ECC", - "multi-symbol chipkill ECC", - "master abort", - "target abort", - "parity error", - "watchdog timeout", - "invalid address", - "mirror Broken", - "memory sparing", - "scrub corrected error", - "scrub uncorrected error", -}; - -static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem) -{ - if (mem->validation_bits & CPER_MEM_VALID_ERROR_STATUS) - printk("%s""error_status: 0x%016llx\n", pfx, mem->error_status); - if (mem->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS) - printk("%s""physical_address: 0x%016llx\n", - pfx, mem->physical_addr); - if (mem->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS_MASK) - printk("%s""physical_address_mask: 0x%016llx\n", - pfx, mem->physical_addr_mask); - if (mem->validation_bits & CPER_MEM_VALID_NODE) - printk("%s""node: %d\n", pfx, mem->node); - if (mem->validation_bits & CPER_MEM_VALID_CARD) - printk("%s""card: %d\n", pfx, mem->card); - if (mem->validation_bits & CPER_MEM_VALID_MODULE) - printk("%s""module: %d\n", pfx, mem->module); - if (mem->validation_bits & CPER_MEM_VALID_BANK) - printk("%s""bank: %d\n", pfx, mem->bank); - if (mem->validation_bits & CPER_MEM_VALID_DEVICE) - printk("%s""device: %d\n", pfx, mem->device); - if (mem->validation_bits & CPER_MEM_VALID_ROW) - printk("%s""row: %d\n", pfx, mem->row); - if (mem->validation_bits & CPER_MEM_VALID_COLUMN) - printk("%s""column: %d\n", pfx, mem->column); - if (mem->validation_bits & CPER_MEM_VALID_BIT_POSITION) - printk("%s""bit_position: %d\n", pfx, mem->bit_pos); - if (mem->validation_bits & CPER_MEM_VALID_REQUESTOR_ID) - printk("%s""requestor_id: 0x%016llx\n", pfx, mem->requestor_id); - if (mem->validation_bits & CPER_MEM_VALID_RESPONDER_ID) - printk("%s""responder_id: 0x%016llx\n", pfx, mem->responder_id); - if (mem->validation_bits & CPER_MEM_VALID_TARGET_ID) - printk("%s""target_id: 0x%016llx\n", pfx, mem->target_id); - if (mem->validation_bits & CPER_MEM_VALID_ERROR_TYPE) { - u8 etype = mem->error_type; - printk("%s""error_type: %d, %s\n", pfx, etype, - etype < ARRAY_SIZE(cper_mem_err_type_strs) ? - cper_mem_err_type_strs[etype] : "unknown"); - } -} - -static const char *cper_pcie_port_type_strs[] = { - "PCIe end point", - "legacy PCI end point", - "unknown", - "unknown", - "root port", - "upstream switch port", - "downstream switch port", - "PCIe to PCI/PCI-X bridge", - "PCI/PCI-X to PCIe bridge", - "root complex integrated endpoint device", - "root complex event collector", -}; - -static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie, - const struct acpi_hest_generic_data *gdata) -{ - if (pcie->validation_bits & CPER_PCIE_VALID_PORT_TYPE) - printk("%s""port_type: %d, %s\n", pfx, pcie->port_type, - pcie->port_type < ARRAY_SIZE(cper_pcie_port_type_strs) ? - cper_pcie_port_type_strs[pcie->port_type] : "unknown"); - if (pcie->validation_bits & CPER_PCIE_VALID_VERSION) - printk("%s""version: %d.%d\n", pfx, - pcie->version.major, pcie->version.minor); - if (pcie->validation_bits & CPER_PCIE_VALID_COMMAND_STATUS) - printk("%s""command: 0x%04x, status: 0x%04x\n", pfx, - pcie->command, pcie->status); - if (pcie->validation_bits & CPER_PCIE_VALID_DEVICE_ID) { - const __u8 *p; - printk("%s""device_id: %04x:%02x:%02x.%x\n", pfx, - pcie->device_id.segment, pcie->device_id.bus, - pcie->device_id.device, pcie->device_id.function); - printk("%s""slot: %d\n", pfx, - pcie->device_id.slot >> CPER_PCIE_SLOT_SHIFT); - printk("%s""secondary_bus: 0x%02x\n", pfx, - pcie->device_id.secondary_bus); - printk("%s""vendor_id: 0x%04x, device_id: 0x%04x\n", pfx, - pcie->device_id.vendor_id, pcie->device_id.device_id); - p = pcie->device_id.class_code; - printk("%s""class_code: %02x%02x%02x\n", pfx, p[0], p[1], p[2]); - } - if (pcie->validation_bits & CPER_PCIE_VALID_SERIAL_NUMBER) - printk("%s""serial number: 0x%04x, 0x%04x\n", pfx, - pcie->serial_number.lower, pcie->serial_number.upper); - if (pcie->validation_bits & CPER_PCIE_VALID_BRIDGE_CONTROL_STATUS) - printk( - "%s""bridge: secondary_status: 0x%04x, control: 0x%04x\n", - pfx, pcie->bridge.secondary_status, pcie->bridge.control); -} - -static const char *apei_estatus_section_flag_strs[] = { - "primary", - "containment warning", - "reset", - "threshold exceeded", - "resource not accessible", - "latent error", -}; - -static void apei_estatus_print_section( - const char *pfx, const struct acpi_hest_generic_data *gdata, int sec_no) -{ - uuid_le *sec_type = (uuid_le *)gdata->section_type; - __u16 severity; - - severity = gdata->error_severity; - printk("%s""section: %d, severity: %d, %s\n", pfx, sec_no, severity, - cper_severity_str(severity)); - printk("%s""flags: 0x%02x\n", pfx, gdata->flags); - cper_print_bits(pfx, gdata->flags, apei_estatus_section_flag_strs, - ARRAY_SIZE(apei_estatus_section_flag_strs)); - if (gdata->validation_bits & CPER_SEC_VALID_FRU_ID) - printk("%s""fru_id: %pUl\n", pfx, (uuid_le *)gdata->fru_id); - if (gdata->validation_bits & CPER_SEC_VALID_FRU_TEXT) - printk("%s""fru_text: %.20s\n", pfx, gdata->fru_text); - - if (!uuid_le_cmp(*sec_type, CPER_SEC_PROC_GENERIC)) { - struct cper_sec_proc_generic *proc_err = (void *)(gdata + 1); - printk("%s""section_type: general processor error\n", pfx); - if (gdata->error_data_length >= sizeof(*proc_err)) - cper_print_proc_generic(pfx, proc_err); - else - goto err_section_too_small; - } else if (!uuid_le_cmp(*sec_type, CPER_SEC_PLATFORM_MEM)) { - struct cper_sec_mem_err *mem_err = (void *)(gdata + 1); - printk("%s""section_type: memory error\n", pfx); - if (gdata->error_data_length >= sizeof(*mem_err)) - cper_print_mem(pfx, mem_err); - else - goto err_section_too_small; - } else if (!uuid_le_cmp(*sec_type, CPER_SEC_PCIE)) { - struct cper_sec_pcie *pcie = (void *)(gdata + 1); - printk("%s""section_type: PCIe error\n", pfx); - if (gdata->error_data_length >= sizeof(*pcie)) - cper_print_pcie(pfx, pcie, gdata); - else - goto err_section_too_small; - } else - printk("%s""section type: unknown, %pUl\n", pfx, sec_type); - - return; - -err_section_too_small: - pr_err(FW_WARN "error section length is too small\n"); -} - -void apei_estatus_print(const char *pfx, - const struct acpi_hest_generic_status *estatus) -{ - struct acpi_hest_generic_data *gdata; - unsigned int data_len, gedata_len; - int sec_no = 0; - __u16 severity; - - printk("%s""APEI generic hardware error status\n", pfx); - severity = estatus->error_severity; - printk("%s""severity: %d, %s\n", pfx, severity, - cper_severity_str(severity)); - data_len = estatus->data_length; - gdata = (struct acpi_hest_generic_data *)(estatus + 1); - while (data_len > sizeof(*gdata)) { - gedata_len = gdata->error_data_length; - apei_estatus_print_section(pfx, gdata, sec_no); - data_len -= gedata_len + sizeof(*gdata); - gdata = (void *)(gdata + 1) + gedata_len; - sec_no++; - } -} -EXPORT_SYMBOL_GPL(apei_estatus_print); - -int apei_estatus_check_header(const struct acpi_hest_generic_status *estatus) -{ - if (estatus->data_length && - estatus->data_length < sizeof(struct acpi_hest_generic_data)) - return -EINVAL; - if (estatus->raw_data_length && - estatus->raw_data_offset < sizeof(*estatus) + estatus->data_length) - return -EINVAL; - - return 0; -} -EXPORT_SYMBOL_GPL(apei_estatus_check_header); - -int apei_estatus_check(const struct acpi_hest_generic_status *estatus) -{ - struct acpi_hest_generic_data *gdata; - unsigned int data_len, gedata_len; - int rc; - - rc = apei_estatus_check_header(estatus); - if (rc) - return rc; - data_len = estatus->data_length; - gdata = (struct acpi_hest_generic_data *)(estatus + 1); - while (data_len >= sizeof(*gdata)) { - gedata_len = gdata->error_data_length; - if (gedata_len > data_len - sizeof(*gdata)) - return -EINVAL; - data_len -= gedata_len + sizeof(*gdata); - gdata = (void *)(gdata + 1) + gedata_len; - } - if (data_len) - return -EINVAL; - - return 0; -} -EXPORT_SYMBOL_GPL(apei_estatus_check); diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 8ec37bbdd699..a30bc313787b 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -75,13 +75,13 @@ #define GHES_ESTATUS_CACHE_LEN(estatus_len) \ (sizeof(struct ghes_estatus_cache) + (estatus_len)) #define GHES_ESTATUS_FROM_CACHE(estatus_cache) \ - ((struct acpi_hest_generic_status *) \ + ((struct 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_hest_generic_status *) \ +#define GHES_ESTATUS_FROM_NODE(estatus_node) \ + ((struct acpi_generic_status *) \ ((struct ghes_estatus_node *)(estatus_node) + 1)) bool ghes_disable; @@ -378,17 +378,17 @@ 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; ghes_copy_tofrom_phys(ghes->estatus + 1, buf_paddr + sizeof(*ghes->estatus), len - sizeof(*ghes->estatus), 1); - if (apei_estatus_check(ghes->estatus)) + if (cper_estatus_check(ghes->estatus)) goto err_read_block; rc = 0; @@ -409,7 +409,7 @@ static void ghes_clear_estatus(struct ghes *ghes) ghes->flags &= ~GHES_TO_CLEAR; } -static void ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, int sev) +static void ghes_handle_memory_failure(struct acpi_generic_data *gdata, int sev) { #ifdef CONFIG_ACPI_APEI_MEMORY_FAILURE unsigned long pfn; @@ -419,7 +419,7 @@ static void ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, int if (sec_sev == GHES_SEV_CORRECTED && (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED) && - (mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS)) { + (mem_err->validation_bits & CPER_MEM_VALID_PA)) { pfn = mem_err->physical_addr >> PAGE_SHIFT; if (pfn_valid(pfn)) memory_failure_queue(pfn, 0, MF_SOFT_OFFLINE); @@ -430,7 +430,7 @@ static void ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, int } if (sev == GHES_SEV_RECOVERABLE && sec_sev == GHES_SEV_RECOVERABLE && - mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS) { + mem_err->validation_bits & CPER_MEM_VALID_PA) { pfn = mem_err->physical_addr >> PAGE_SHIFT; memory_failure_queue(pfn, 0, 0); } @@ -438,10 +438,10 @@ static void ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, int } static void ghes_do_proc(struct ghes *ghes, - const struct acpi_hest_generic_status *estatus) + const struct acpi_generic_status *estatus) { int sev, sec_sev; - struct acpi_hest_generic_data *gdata; + struct acpi_generic_data *gdata; sev = ghes_severity(estatus->error_severity); apei_estatus_for_each_section(estatus, gdata) { @@ -496,7 +496,7 @@ static void ghes_do_proc(struct ghes *ghes, static void __ghes_print_estatus(const char *pfx, const struct acpi_hest_generic *generic, - const struct acpi_hest_generic_status *estatus) + const struct acpi_generic_status *estatus) { static atomic_t seqno; unsigned int curr_seqno; @@ -513,12 +513,12 @@ static void __ghes_print_estatus(const char *pfx, 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); - apei_estatus_print(pfx_seq, estatus); + cper_estatus_print(pfx_seq, estatus); } static int ghes_print_estatus(const char *pfx, const struct acpi_hest_generic *generic, - const struct acpi_hest_generic_status *estatus) + const struct acpi_generic_status *estatus) { /* Not more than 2 messages every 5 seconds */ static DEFINE_RATELIMIT_STATE(ratelimit_corrected, 5*HZ, 2); @@ -540,15 +540,15 @@ static int ghes_print_estatus(const char *pfx, * GHES error status reporting throttle, to report more kinds of * errors, instead of just most frequently occurred errors. */ -static int ghes_estatus_cached(struct acpi_hest_generic_status *estatus) +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_hest_generic_status *cache_estatus; + struct acpi_generic_status *cache_estatus; - len = apei_estatus_len(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]); @@ -571,19 +571,19 @@ static int ghes_estatus_cached(struct acpi_hest_generic_status *estatus) static struct ghes_estatus_cache *ghes_estatus_cache_alloc( struct acpi_hest_generic *generic, - struct acpi_hest_generic_status *estatus) + struct acpi_generic_status *estatus) { int alloced; u32 len, cache_len; struct ghes_estatus_cache *cache; - struct acpi_hest_generic_status *cache_estatus; + struct acpi_generic_status *cache_estatus; alloced = atomic_add_return(1, &ghes_estatus_cache_alloced); if (alloced > GHES_ESTATUS_CACHE_ALLOCED_MAX) {< |