--- zzzz-none-000/linux-3.10.107/include/ras/ras_event.h 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/include/ras/ras_event.h 2021-02-04 17:41:59.000000000 +0000 @@ -8,6 +8,73 @@ #include #include #include +#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 @@ -94,6 +161,162 @@ __get_str(driver_detail)) ); +/* + * PCIe AER Trace event + * + * These events are generated when hardware detects a corrected or + * uncorrected event on a PCIe device. The event report has + * the following structure: + * + * char * dev_name - The name of the slot where the device resides + * ([domain:]bus:device.function). + * u32 status - Either the correctable or uncorrectable register + * indicating what error or errors have been seen + * u8 severity - error severity 0:NONFATAL 1:FATAL 2:CORRECTED + */ + +#define aer_correctable_errors \ + {PCI_ERR_COR_RCVR, "Receiver Error"}, \ + {PCI_ERR_COR_BAD_TLP, "Bad TLP"}, \ + {PCI_ERR_COR_BAD_DLLP, "Bad DLLP"}, \ + {PCI_ERR_COR_REP_ROLL, "RELAY_NUM Rollover"}, \ + {PCI_ERR_COR_REP_TIMER, "Replay Timer Timeout"}, \ + {PCI_ERR_COR_ADV_NFAT, "Advisory Non-Fatal Error"}, \ + {PCI_ERR_COR_INTERNAL, "Corrected Internal Error"}, \ + {PCI_ERR_COR_LOG_OVER, "Header Log Overflow"} + +#define aer_uncorrectable_errors \ + {PCI_ERR_UNC_UND, "Undefined"}, \ + {PCI_ERR_UNC_DLP, "Data Link Protocol Error"}, \ + {PCI_ERR_UNC_SURPDN, "Surprise Down Error"}, \ + {PCI_ERR_UNC_POISON_TLP,"Poisoned TLP"}, \ + {PCI_ERR_UNC_FCP, "Flow Control Protocol Error"}, \ + {PCI_ERR_UNC_COMP_TIME, "Completion Timeout"}, \ + {PCI_ERR_UNC_COMP_ABORT,"Completer Abort"}, \ + {PCI_ERR_UNC_UNX_COMP, "Unexpected Completion"}, \ + {PCI_ERR_UNC_RX_OVER, "Receiver Overflow"}, \ + {PCI_ERR_UNC_MALF_TLP, "Malformed TLP"}, \ + {PCI_ERR_UNC_ECRC, "ECRC Error"}, \ + {PCI_ERR_UNC_UNSUP, "Unsupported Request Error"}, \ + {PCI_ERR_UNC_ACSV, "ACS Violation"}, \ + {PCI_ERR_UNC_INTN, "Uncorrectable Internal Error"},\ + {PCI_ERR_UNC_MCBTLP, "MC Blocked TLP"}, \ + {PCI_ERR_UNC_ATOMEG, "AtomicOp Egress Blocked"}, \ + {PCI_ERR_UNC_TLPPRE, "TLP Prefix Blocked Error"} + +TRACE_EVENT(aer_event, + TP_PROTO(const char *dev_name, + const u32 status, + const u8 severity), + + TP_ARGS(dev_name, status, severity), + + TP_STRUCT__entry( + __string( dev_name, dev_name ) + __field( u32, status ) + __field( u8, severity ) + ), + + TP_fast_assign( + __assign_str(dev_name, dev_name); + __entry->status = status; + __entry->severity = severity; + ), + + TP_printk("%s PCIe Bus Error: severity=%s, %s\n", + __get_str(dev_name), + __entry->severity == AER_CORRECTABLE ? "Corrected" : + __entry->severity == AER_FATAL ? + "Fatal" : "Uncorrected, non-fatal", + __entry->severity == AER_CORRECTABLE ? + __print_flags(__entry->status, "|", aer_correctable_errors) : + __print_flags(__entry->status, "|", aer_uncorrectable_errors)) +); + +/* + * memory-failure recovery action result event + * + * unsigned long pfn - Page Frame Number of the corrupted page + * int type - Page types of the corrupted page + * int result - Result of recovery action + */ + +#ifdef CONFIG_MEMORY_FAILURE +#define MF_ACTION_RESULT \ + EM ( MF_IGNORED, "Ignored" ) \ + EM ( MF_FAILED, "Failed" ) \ + EM ( MF_DELAYED, "Delayed" ) \ + EMe ( MF_RECOVERED, "Recovered" ) + +#define MF_PAGE_TYPE \ + EM ( MF_MSG_KERNEL, "reserved kernel page" ) \ + EM ( MF_MSG_KERNEL_HIGH_ORDER, "high-order kernel page" ) \ + EM ( MF_MSG_SLAB, "kernel slab page" ) \ + EM ( MF_MSG_DIFFERENT_COMPOUND, "different compound page after locking" ) \ + EM ( MF_MSG_POISONED_HUGE, "huge page already hardware poisoned" ) \ + EM ( MF_MSG_HUGE, "huge page" ) \ + EM ( MF_MSG_FREE_HUGE, "free huge page" ) \ + EM ( MF_MSG_UNMAP_FAILED, "unmapping failed page" ) \ + EM ( MF_MSG_DIRTY_SWAPCACHE, "dirty swapcache page" ) \ + EM ( MF_MSG_CLEAN_SWAPCACHE, "clean swapcache page" ) \ + EM ( MF_MSG_DIRTY_MLOCKED_LRU, "dirty mlocked LRU page" ) \ + EM ( MF_MSG_CLEAN_MLOCKED_LRU, "clean mlocked LRU page" ) \ + EM ( MF_MSG_DIRTY_UNEVICTABLE_LRU, "dirty unevictable LRU page" ) \ + EM ( MF_MSG_CLEAN_UNEVICTABLE_LRU, "clean unevictable LRU page" ) \ + EM ( MF_MSG_DIRTY_LRU, "dirty LRU page" ) \ + EM ( MF_MSG_CLEAN_LRU, "clean LRU page" ) \ + EM ( MF_MSG_TRUNCATED_LRU, "already truncated LRU page" ) \ + EM ( MF_MSG_BUDDY, "free buddy page" ) \ + EM ( MF_MSG_BUDDY_2ND, "free buddy page (2nd try)" ) \ + EMe ( MF_MSG_UNKNOWN, "unknown page" ) + +/* + * First define the enums in MM_ACTION_RESULT to be exported to userspace + * via TRACE_DEFINE_ENUM(). + */ +#undef EM +#undef EMe +#define EM(a, b) TRACE_DEFINE_ENUM(a); +#define EMe(a, b) TRACE_DEFINE_ENUM(a); + +MF_ACTION_RESULT +MF_PAGE_TYPE + +/* + * Now redefine the EM() and EMe() macros to map the enums to the strings + * that will be printed in the output. + */ +#undef EM +#undef EMe +#define EM(a, b) { a, b }, +#define EMe(a, b) { a, b } + +TRACE_EVENT(memory_failure_event, + TP_PROTO(unsigned long pfn, + int type, + int result), + + TP_ARGS(pfn, type, result), + + TP_STRUCT__entry( + __field(unsigned long, pfn) + __field(int, type) + __field(int, result) + ), + + TP_fast_assign( + __entry->pfn = pfn; + __entry->type = type; + __entry->result = result; + ), + + TP_printk("pfn %#lx: recovery action for %s: %s", + __entry->pfn, + __print_symbolic(__entry->type, MF_PAGE_TYPE), + __print_symbolic(__entry->result, MF_ACTION_RESULT) + ) +); +#endif /* CONFIG_MEMORY_FAILURE */ #endif /* _TRACE_HW_EVENT_MC_H */ /* This part must be outside protection */