From 3760cd20402d4c131e1994c968ecb055fa0f74bc Mon Sep 17 00:00:00 2001 From: "Chen, Gong" Date: Wed, 11 Jun 2014 13:59:45 -0700 Subject: CPER: Adjust code flow of some functions Some codes can be reorganzied as a common function for other usages. Signed-off-by: Chen, Gong Signed-off-by: Tony Luck --- drivers/firmware/efi/cper.c | 155 ++++++++++++++++++++++++++++---------------- 1 file changed, 100 insertions(+), 55 deletions(-) (limited to 'drivers/firmware/efi') diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c index 1491dd4f08f9..ac33a9fed341 100644 --- a/drivers/firmware/efi/cper.c +++ b/drivers/firmware/efi/cper.c @@ -34,6 +34,9 @@ #include #define INDENT_SP " " + +static char rcd_decode_str[CPER_REC_LEN]; + /* * CPER record ID need to be unique even after reboot, because record * ID is used as index for ERST storage, while CPER records from @@ -50,18 +53,19 @@ u64 cper_next_record_id(void) } EXPORT_SYMBOL_GPL(cper_next_record_id); -static const char *cper_severity_strs[] = { +static const char * const severity_strs[] = { "recoverable", "fatal", "corrected", "info", }; -static const char *cper_severity_str(unsigned int severity) +const char *cper_severity_str(unsigned int severity) { - return severity < ARRAY_SIZE(cper_severity_strs) ? - cper_severity_strs[severity] : "unknown"; + return severity < ARRAY_SIZE(severity_strs) ? + severity_strs[severity] : "unknown"; } +EXPORT_SYMBOL_GPL(cper_severity_str); /* * cper_print_bits - print strings for set bits @@ -100,32 +104,32 @@ void cper_print_bits(const char *pfx, unsigned int bits, printk("%s\n", buf); } -static const char * const cper_proc_type_strs[] = { +static const char * const proc_type_strs[] = { "IA32/X64", "IA64", }; -static const char * const cper_proc_isa_strs[] = { +static const char * const proc_isa_strs[] = { "IA32", "IA64", "X64", }; -static const char * const cper_proc_error_type_strs[] = { +static const char * const proc_error_type_strs[] = { "cache error", "TLB error", "bus error", "micro-architectural error", }; -static const char * const cper_proc_op_strs[] = { +static const char * const proc_op_strs[] = { "unknown or generic", "data read", "data write", "instruction execution", }; -static const char * const cper_proc_flag_strs[] = { +static const char * const proc_flag_strs[] = { "restartable", "precise IP", "overflow", @@ -137,26 +141,26 @@ static void cper_print_proc_generic(const char *pfx, { if (proc->validation_bits & CPER_PROC_VALID_TYPE) printk("%s""processor_type: %d, %s\n", pfx, proc->proc_type, - proc->proc_type < ARRAY_SIZE(cper_proc_type_strs) ? - cper_proc_type_strs[proc->proc_type] : "unknown"); + proc->proc_type < ARRAY_SIZE(proc_type_strs) ? + proc_type_strs[proc->proc_type] : "unknown"); if (proc->validation_bits & CPER_PROC_VALID_ISA) printk("%s""processor_isa: %d, %s\n", pfx, proc->proc_isa, - proc->proc_isa < ARRAY_SIZE(cper_proc_isa_strs) ? - cper_proc_isa_strs[proc->proc_isa] : "unknown"); + proc->proc_isa < ARRAY_SIZE(proc_isa_strs) ? + proc_isa_strs[proc->proc_isa] : "unknown"); if (proc->validation_bits & CPER_PROC_VALID_ERROR_TYPE) { printk("%s""error_type: 0x%02x\n", pfx, proc->proc_error_type); cper_print_bits(pfx, proc->proc_error_type, - cper_proc_error_type_strs, - ARRAY_SIZE(cper_proc_error_type_strs)); + proc_error_type_strs, + ARRAY_SIZE(proc_error_type_strs)); } if (proc->validation_bits & CPER_PROC_VALID_OPERATION) printk("%s""operation: %d, %s\n", pfx, proc->operation, - proc->operation < ARRAY_SIZE(cper_proc_op_strs) ? - cper_proc_op_strs[proc->operation] : "unknown"); + proc->operation < ARRAY_SIZE(proc_op_strs) ? + proc_op_strs[proc->operation] : "unknown"); if (proc->validation_bits & CPER_PROC_VALID_FLAGS) { printk("%s""flags: 0x%02x\n", pfx, proc->flags); - cper_print_bits(pfx, proc->flags, cper_proc_flag_strs, - ARRAY_SIZE(cper_proc_flag_strs)); + cper_print_bits(pfx, proc->flags, proc_flag_strs, + ARRAY_SIZE(proc_flag_strs)); } if (proc->validation_bits & CPER_PROC_VALID_LEVEL) printk("%s""level: %d\n", pfx, proc->level); @@ -177,7 +181,7 @@ static void cper_print_proc_generic(const char *pfx, printk("%s""IP: 0x%016llx\n", pfx, proc->ip); } -static const char *cper_mem_err_type_strs[] = { +static const char * const mem_err_type_strs[] = { "unknown", "no error", "single-bit ECC", @@ -196,58 +200,99 @@ static const char *cper_mem_err_type_strs[] = { "physical memory map-out event", }; -static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem) +const char *cper_mem_err_type_str(unsigned int etype) { - if (mem->validation_bits & CPER_MEM_VALID_ERROR_STATUS) - printk("%s""error_status: 0x%016llx\n", pfx, mem->error_status); - if (mem->validation_bits & CPER_MEM_VALID_PA) - printk("%s""physical_address: 0x%016llx\n", - pfx, mem->physical_addr); - if (mem->validation_bits & CPER_MEM_VALID_PA_MASK) - printk("%s""physical_address_mask: 0x%016llx\n", - pfx, mem->physical_addr_mask); + return etype < ARRAY_SIZE(mem_err_type_strs) ? + mem_err_type_strs[etype] : "unknown"; +} +EXPORT_SYMBOL_GPL(cper_mem_err_type_str); + +static int cper_mem_err_location(const struct cper_sec_mem_err *mem, char *msg) +{ + u32 len, n; + + if (!msg) + return 0; + + n = 0; + len = CPER_REC_LEN - 1; if (mem->validation_bits & CPER_MEM_VALID_NODE) - pr_debug("node: %d\n", mem->node); + n += scnprintf(msg + n, len - n, "node: %d ", mem->node); if (mem->validation_bits & CPER_MEM_VALID_CARD) - pr_debug("card: %d\n", mem->card); + n += scnprintf(msg + n, len - n, "card: %d ", mem->card); if (mem->validation_bits & CPER_MEM_VALID_MODULE) - pr_debug("module: %d\n", mem->module); + n += scnprintf(msg + n, len - n, "module: %d ", mem->module); if (mem->validation_bits & CPER_MEM_VALID_RANK_NUMBER) - pr_debug("rank: %d\n", mem->rank); + n += scnprintf(msg + n, len - n, "rank: %d ", mem->rank); if (mem->validation_bits & CPER_MEM_VALID_BANK) - pr_debug("bank: %d\n", mem->bank); + n += scnprintf(msg + n, len - n, "bank: %d ", mem->bank); if (mem->validation_bits & CPER_MEM_VALID_DEVICE) - pr_debug("device: %d\n", mem->device); + n += scnprintf(msg + n, len - n, "device: %d ", mem->device); if (mem->validation_bits & CPER_MEM_VALID_ROW) - pr_debug("row: %d\n", mem->row); + n += scnprintf(msg + n, len - n, "row: %d ", mem->row); if (mem->validation_bits & CPER_MEM_VALID_COLUMN) - pr_debug("column: %d\n", mem->column); + n += scnprintf(msg + n, len - n, "column: %d ", mem->column); if (mem->validation_bits & CPER_MEM_VALID_BIT_POSITION) - pr_debug("bit_position: %d\n", mem->bit_pos); + n += scnprintf(msg + n, len - n, "bit_position: %d ", + mem->bit_pos); if (mem->validation_bits & CPER_MEM_VALID_REQUESTOR_ID) - pr_debug("requestor_id: 0x%016llx\n", mem->requestor_id); + n += scnprintf(msg + n, len - n, "requestor_id: 0x%016llx ", + mem->requestor_id); if (mem->validation_bits & CPER_MEM_VALID_RESPONDER_ID) - pr_debug("responder_id: 0x%016llx\n", mem->responder_id); + n += scnprintf(msg + n, len - n, "responder_id: 0x%016llx ", + mem->responder_id); if (mem->validation_bits & CPER_MEM_VALID_TARGET_ID) - pr_debug("target_id: 0x%016llx\n", mem->target_id); + scnprintf(msg + n, len - n, "target_id: 0x%016llx ", + mem->target_id); + + msg[n] = '\0'; + return n; +} + +static int cper_dimm_err_location(const struct cper_sec_mem_err *mem, char *msg) +{ + u32 len, n; + const char *bank = NULL, *device = NULL; + + if (!msg || !(mem->validation_bits & CPER_MEM_VALID_MODULE_HANDLE)) + return 0; + + n = 0; + len = CPER_REC_LEN - 1; + dmi_memdev_name(mem->mem_dev_handle, &bank, &device); + if (bank && device) + n = snprintf(msg, len, "DIMM location: %s %s ", bank, device); + else + n = snprintf(msg, len, + "DIMM location: not present. DMI handle: 0x%.4x ", + mem->mem_dev_handle); + + msg[n] = '\0'; + return n; +} + +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_PA) + printk("%s""physical_address: 0x%016llx\n", + pfx, mem->physical_addr); + if (mem->validation_bits & CPER_MEM_VALID_PA_MASK) + printk("%s""physical_address_mask: 0x%016llx\n", + pfx, mem->physical_addr_mask); + if (cper_mem_err_location(mem, rcd_decode_str)) + printk("%s%s\n", pfx, rcd_decode_str); 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"); - } - if (mem->validation_bits & CPER_MEM_VALID_MODULE_HANDLE) { - const char *bank = NULL, *device = NULL; - dmi_memdev_name(mem->mem_dev_handle, &bank, &device); - if (bank != NULL && device != NULL) - printk("%s""DIMM location: %s %s", pfx, bank, device); - else - printk("%s""DIMM DMI handle: 0x%.4x", - pfx, mem->mem_dev_handle); + cper_mem_err_type_str(etype)); } + if (cper_dimm_err_location(mem, rcd_decode_str)) + printk("%s%s\n", pfx, rcd_decode_str); } -static const char *cper_pcie_port_type_strs[] = { +static const char * const pcie_port_type_strs[] = { "PCIe end point", "legacy PCI end point", "unknown", @@ -266,8 +311,8 @@ static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie, { 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"); + pcie->port_type < ARRAY_SIZE(pcie_port_type_strs) ? + 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); -- cgit v1.2.3 From 2dfb7d51a61d7ca91b131c8db612f27d9390f2d5 Mon Sep 17 00:00:00 2001 From: "Chen, Gong" Date: Tue, 17 Jun 2014 22:33:07 -0400 Subject: trace, RAS: Add eMCA trace event interface Add trace interface to elaborate all H/W error related information. Signed-off-by: Chen, Gong Acked-by: Borislav Petkov Signed-off-by: Tony Luck --- drivers/acpi/Kconfig | 4 ++- drivers/acpi/acpi_extlog.c | 27 ++++++++++++++++--- drivers/firmware/efi/cper.c | 45 ++++++++++++++++++++++++++++--- drivers/ras/ras.c | 3 +++ include/linux/cper.h | 23 ++++++++++++++++ include/ras/ras_event.h | 64 +++++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 158 insertions(+), 8 deletions(-) (limited to 'drivers/firmware/efi') diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index a34a22841002..206942b8d105 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -370,6 +370,7 @@ config ACPI_EXTLOG tristate "Extended Error Log support" depends on X86_MCE && X86_LOCAL_APIC select UEFI_CPER + select RAS default n help Certain usages such as Predictive Failure Analysis (PFA) require @@ -384,6 +385,7 @@ config ACPI_EXTLOG Enhanced MCA Logging allows firmware to provide additional error information to system software, synchronous with MCE or CMCI. This - driver adds support for that functionality. + driver adds support for that functionality with corresponding + tracepoint which carries that information to userspace. endif # ACPI diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c index 185334114d71..e61da957f30f 100644 --- a/drivers/acpi/acpi_extlog.c +++ b/drivers/acpi/acpi_extlog.c @@ -16,6 +16,7 @@ #include #include "apei/apei-internal.h" +#include #define EXT_ELOG_ENTRY_MASK GENMASK_ULL(51, 0) /* elog entry address mask */ @@ -137,8 +138,12 @@ static int extlog_print(struct notifier_block *nb, unsigned long val, struct mce *mce = (struct mce *)data; int bank = mce->bank; int cpu = mce->extcpu; - struct acpi_generic_status *estatus; - int rc; + struct acpi_generic_status *estatus, *tmp; + struct acpi_generic_data *gdata; + const uuid_le *fru_id = &NULL_UUID_LE; + char *fru_text = ""; + uuid_le *sec_type; + static u32 err_seq; estatus = extlog_elog_entry_check(cpu, bank); if (estatus == NULL) @@ -148,7 +153,23 @@ static int extlog_print(struct notifier_block *nb, unsigned long val, /* clear record status to enable BIOS to update it again */ estatus->block_status = 0; - rc = print_extlog_rcd(NULL, (struct acpi_generic_status *)elog_buf, cpu); + tmp = (struct acpi_generic_status *)elog_buf; + print_extlog_rcd(NULL, tmp, cpu); + + /* log event via trace */ + err_seq++; + gdata = (struct acpi_generic_data *)(tmp + 1); + if (gdata->validation_bits & CPER_SEC_VALID_FRU_ID) + fru_id = (uuid_le *)gdata->fru_id; + if (gdata->validation_bits & CPER_SEC_VALID_FRU_TEXT) + fru_text = gdata->fru_text; + sec_type = (uuid_le *)gdata->section_type; + if (!uuid_le_cmp(*sec_type, CPER_SEC_PLATFORM_MEM)) { + struct cper_sec_mem_err *mem = (void *)(gdata + 1); + if (gdata->error_data_length >= sizeof(*mem)) + trace_extlog_mem_event(mem, err_seq, fru_id, fru_text, + (u8)gdata->error_severity); + } return NOTIFY_STOP; } diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c index ac33a9fed341..437e6fd47311 100644 --- a/drivers/firmware/efi/cper.c +++ b/drivers/firmware/efi/cper.c @@ -207,7 +207,7 @@ const char *cper_mem_err_type_str(unsigned int etype) } EXPORT_SYMBOL_GPL(cper_mem_err_type_str); -static int cper_mem_err_location(const struct cper_sec_mem_err *mem, char *msg) +static int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg) { u32 len, n; @@ -249,7 +249,7 @@ static int cper_mem_err_location(const struct cper_sec_mem_err *mem, char *msg) return n; } -static int cper_dimm_err_location(const struct cper_sec_mem_err *mem, char *msg) +static int cper_dimm_err_location(struct cper_mem_err_compact *mem, char *msg) { u32 len, n; const char *bank = NULL, *device = NULL; @@ -271,8 +271,44 @@ static int cper_dimm_err_location(const struct cper_sec_mem_err *mem, char *msg) return n; } +void cper_mem_err_pack(const struct cper_sec_mem_err *mem, + struct cper_mem_err_compact *cmem) +{ + cmem->validation_bits = mem->validation_bits; + cmem->node = mem->node; + cmem->card = mem->card; + cmem->module = mem->module; + cmem->bank = mem->bank; + cmem->device = mem->device; + cmem->row = mem->row; + cmem->column = mem->column; + cmem->bit_pos = mem->bit_pos; + cmem->requestor_id = mem->requestor_id; + cmem->responder_id = mem->responder_id; + cmem->target_id = mem->target_id; + cmem->rank = mem->rank; + cmem->mem_array_handle = mem->mem_array_handle; + cmem->mem_dev_handle = mem->mem_dev_handle; +} + +const char *cper_mem_err_unpack(struct trace_seq *p, + struct cper_mem_err_compact *cmem) +{ + const char *ret = p->buffer + p->len; + + if (cper_mem_err_location(cmem, rcd_decode_str)) + trace_seq_printf(p, "%s", rcd_decode_str); + if (cper_dimm_err_location(cmem, rcd_decode_str)) + trace_seq_printf(p, "%s", rcd_decode_str); + trace_seq_putc(p, '\0'); + + return ret; +} + static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem) { + struct cper_mem_err_compact cmem; + if (mem->validation_bits & CPER_MEM_VALID_ERROR_STATUS) printk("%s""error_status: 0x%016llx\n", pfx, mem->error_status); if (mem->validation_bits & CPER_MEM_VALID_PA) @@ -281,14 +317,15 @@ static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem) if (mem->validation_bits & CPER_MEM_VALID_PA_MASK) printk("%s""physical_address_mask: 0x%016llx\n", pfx, mem->physical_addr_mask); - if (cper_mem_err_location(mem, rcd_decode_str)) + cper_mem_err_pack(mem, &cmem); + if (cper_mem_err_location(&cmem, rcd_decode_str)) printk("%s%s\n", pfx, rcd_decode_str); if (mem->validation_bits & CPER_MEM_VALID_ERROR_TYPE) { u8 etype = mem->error_type; printk("%s""error_type: %d, %s\n", pfx, etype, cper_mem_err_type_str(etype)); } - if (cper_dimm_err_location(mem, rcd_decode_str)) + if (cper_dimm_err_location(&cmem, rcd_decode_str)) printk("%s%s\n", pfx, rcd_decode_str); } diff --git a/drivers/ras/ras.c b/drivers/ras/ras.c index 4cac43a1e25c..b67dd362b7b6 100644 --- a/drivers/ras/ras.c +++ b/drivers/ras/ras.c @@ -23,4 +23,7 @@ static int __init ras_init(void) } subsys_initcall(ras_init); +#if defined(CONFIG_ACPI_EXTLOG) || defined(CONFIG_ACPI_EXTLOG_MODULE) +EXPORT_TRACEPOINT_SYMBOL_GPL(extlog_mem_event); +#endif EXPORT_TRACEPOINT_SYMBOL_GPL(mc_event); diff --git a/include/linux/cper.h b/include/linux/cper.h index ed088b9c1298..76abba4b238e 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -22,6 +22,7 @@ #define LINUX_CPER_H #include +#include /* CPER record signature and the size */ #define CPER_SIG_RECORD "CPER" @@ -363,6 +364,24 @@ struct cper_sec_mem_err { __u16 mem_dev_handle; /* module handle in UEFI 2.4 */ }; +struct cper_mem_err_compact { + __u64 validation_bits; + __u16 node; + __u16 card; + __u16 module; + __u16 bank; + __u16 device; + __u16 row; + __u16 column; + __u16 bit_pos; + __u64 requestor_id; + __u64 responder_id; + __u64 target_id; + __u16 rank; + __u16 mem_array_handle; + __u16 mem_dev_handle; +}; + struct cper_sec_pcie { __u64 validation_bits; __u32 port_type; @@ -406,5 +425,9 @@ const char *cper_severity_str(unsigned int); const char *cper_mem_err_type_str(unsigned int); void cper_print_bits(const char *prefix, unsigned int bits, const char * const strs[], unsigned int strs_size); +void cper_mem_err_pack(const struct cper_sec_mem_err *, + struct cper_mem_err_compact *); +const char *cper_mem_err_unpack(struct trace_seq *, + struct cper_mem_err_compact *); #endif diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h index acbcbb88eaaa..47da53c27ffa 100644 --- a/include/ras/ras_event.h +++ b/include/ras/ras_event.h @@ -9,6 +9,70 @@ #include #include #include +#include + +/* + * MCE Extended Error Log trace event + * + * These events are generated when hardware detects a corrected or + * uncorrected event. + */ + +/* memory trace event */ + +#if defined(CONFIG_ACPI_EXTLOG) || defined(CONFIG_ACPI_EXTLOG_MODULE) +TRACE_EVENT(extlog_mem_event, + TP_PROTO(struct cper_sec_mem_err *mem, + u32 err_seq, + const uuid_le *fru_id, + const char *fru_text, + u8 sev), + + TP_ARGS(mem, err_seq, fru_id, fru_text, sev), + + TP_STRUCT__entry( + __field(u32, err_seq) + __field(u8, etype) + __field(u8, sev) + __field(u64, pa) + __field(u8, pa_mask_lsb) + __field_struct(uuid_le, fru_id) + __string(fru_text, fru_text) + __field_struct(struct cper_mem_err_compact, data) + ), + + TP_fast_assign( + __entry->err_seq = err_seq; + if (mem->validation_bits & CPER_MEM_VALID_ERROR_TYPE) + __entry->etype = mem->error_type; + else + __entry->etype = ~0; + __entry->sev = sev; + if (mem->validation_bits & CPER_MEM_VALID_PA) + __entry->pa = mem->physical_addr; + else + __entry->pa = ~0ull; + + if (mem->validation_bits & CPER_MEM_VALID_PA_MASK) + __entry->pa_mask_lsb = (u8)__ffs64(mem->physical_addr_mask); + else + __entry->pa_mask_lsb = ~0; + __entry->fru_id = *fru_id; + __assign_str(fru_text, fru_text); + cper_mem_err_pack(mem, &__entry->data); + ), + + TP_printk("{%d} %s error: %s physical addr: %016llx (mask lsb: %x) %sFRU: %pUl %.20s", + __entry->err_seq, + cper_severity_str(__entry->sev), + cper_mem_err_type_str(__entry->etype), + __entry->pa, + __entry->pa_mask_lsb, + cper_mem_err_unpack(p, &__entry->data), + &__entry->fru_id, + __get_str(fru_text)) +); +#endif /* * Hardware Events Report -- cgit v1.2.3