Add trace interface to elaborate all H/W error related information.
v5 -> v4: Add physical mask(LSB) in trace.
v4 -> v3: change ras trace dependency rule.
v3 -> v2: minor adjustment according to the suggestion from Boris.
v2 -> v1: spinlock is not needed anymore.
Signed-off-by: Chen, Gong <gong.chen@xxxxxxxxxxxxxxx>
---
drivers/acpi/Kconfig | 4 +++-
drivers/acpi/acpi_extlog.c | 58 +++++++++++++++++++++++++++++++++++++++++++---
drivers/ras/ras.c | 1 +
include/ras/ras_event.h | 57 +++++++++++++++++++++++++++++++++++++++++++++
4 files changed, 116 insertions(+), 4 deletions(-)
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index ab686b3..5af6013 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -353,6 +353,7 @@ config ACPI_EXTLOG
tristate "Extended Error Log support"
depends on X86_MCE && X86_LOCAL_APIC
select UEFI_CPER
+ select RAS_TRACE
default n
help
Certain usages such as Predictive Failure Analysis (PFA) require
@@ -367,6 +368,7 @@ 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 c4a5d87..b1dcb5b 100644
--- a/drivers/acpi/acpi_extlog.c
+++ b/drivers/acpi/acpi_extlog.c
@@ -16,6 +16,7 @@
#include <asm/mce.h>
#include "apei/apei-internal.h"
+#include <ras/ras_event.h>
#define EXT_ELOG_ENTRY_MASK GENMASK_ULL(51, 0) /* elog entry address mask */
@@ -43,6 +44,9 @@ struct extlog_l1_head {
static int old_edac_report_status;
+static char mem_location[CPER_REC_LEN];
+static char dimm_location[CPER_REC_LEN];
+
static u8 extlog_dsm_uuid[] __initdata = "663E35AF-CC10-41A4-88EA-5470AF055295";
/* L1 table related physical address */
@@ -69,6 +73,34 @@ static u32 l1_percpu_entry;
#define ELOG_ENTRY_ADDR(phyaddr) \
(phyaddr - elog_base + (u8 *)elog_addr)
+static void __trace_mem_error(const uuid_le *fru_id, char *fru_text,
+ u64 err_count, u32 severity,
+ struct cper_sec_mem_err *mem)
+{
+ u32 etype = ~0U;
+ char pa_info[64];
+ u8 n = 0;
+
+ if (mem->validation_bits & CPER_MEM_VALID_ERROR_TYPE)
+ etype = mem->error_type;
+
+ memset(pa_info, 0, 64);
+ if (mem->validation_bits & CPER_MEM_VALID_PA)
+ n = snprintf(pa_info, 63, "physical addr: 0x%016llx ",
+ mem->physical_addr);
+
+ if (mem->validation_bits & CPER_MEM_VALID_PA_MASK)
+ snprintf(pa_info + n, 63 - n, "addr LSB: 0x%x ",
+ (u8)__ffs64(mem->physical_addr_mask));
+
+ memset(mem_location, 0, CPER_REC_LEN);
+ cper_mem_err_location(mem, mem_location);
+ memset(dimm_location, 0, CPER_REC_LEN);
+ cper_dimm_err_location(mem, dimm_location);
+ trace_extlog_mem_event(etype, fru_id, err_count, severity,
+ dimm_location, pa_info, mem_location, fru_text);
+}
+
static struct acpi_generic_status *extlog_elog_entry_check(int cpu, int bank)
{
int idx;
@@ -137,8 +169,12 @@ 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 u64 err_count;
estatus = extlog_elog_entry_check(cpu, bank);
if (estatus == NULL)
@@ -148,7 +184,23 @@ 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_count++;
+ 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_err = (void *)(gdata + 1);
+ if (gdata->error_data_length >= sizeof(*mem_err))
+ __trace_mem_error(fru_id, fru_text, err_count,
+ gdata->error_severity, mem_err);
+ }
return NOTIFY_STOP;
}
diff --git a/drivers/ras/ras.c b/drivers/ras/ras.c
index 4cac43a..da227a3 100644
--- a/drivers/ras/ras.c
+++ b/drivers/ras/ras.c
@@ -23,4 +23,5 @@ static int __init ras_init(void)
}
subsys_initcall(ras_init);
+EXPORT_TRACEPOINT_SYMBOL_GPL(extlog_mem_event);
EXPORT_TRACEPOINT_SYMBOL_GPL(mc_event);
diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
index acbcbb8..ac6e6d1 100644
--- a/include/ras/ras_event.h
+++ b/include/ras/ras_event.h
@@ -9,6 +9,63 @@
#include <linux/edac.h>
#include <linux/ktime.h>
#include <linux/aer.h>
+#include <linux/cper.h>
+
+
+/*
+ * MCE Extended Error Log trace event
+ *
+ * These events are generated when hardware detects a corrected or
+ * uncorrected event.
+ *
+ */
+
+/* memory trace event */
+
+TRACE_EVENT(extlog_mem_event,
+ TP_PROTO(u32 etype,
+ const uuid_le *fru_id,
+ u64 error_count,
+ u32 severity,
+ char *dimm_info,
+ char *pa_info,
+ char *mem_loc,
+ char *fru_text),
+
+ TP_ARGS(etype, fru_id, error_count, severity, dimm_info, pa_info,
+ mem_loc, fru_text),
+
+ TP_STRUCT__entry(
+ __field(u32, etype)
+ __field(u64, error_count)
+ __field(u32, severity)
+ __string(dimm_info, dimm_info)
+ __string(pa_info, pa_info)
+ __string(mem_loc, mem_loc)
+ __dynamic_array(char, fru, CPER_REC_LEN)
+ ),
+
+ TP_fast_assign(
+ __entry->error_count = error_count;
+ __entry->severity = severity;
+ __entry->etype = etype;
+ __assign_str(dimm_info, dimm_info);
+ __assign_str(pa_info, pa_info);
+ __assign_str(mem_loc, mem_loc);
+ snprintf(__get_dynamic_array(fru), CPER_REC_LEN - 1,
+ "FRU: %pUl %.20s", fru_id, fru_text);
+ ),
+
+ TP_printk("%llu %s error%s: %s %s%s%s%s",
+ __entry->error_count,
+ cper_severity_str(__entry->severity),
+ __entry->error_count > 1 ? "s" : "",
+ cper_mem_err_type_str(__entry->etype),
+ __get_str(dimm_info),
+ __get_str(pa_info),
+ __get_str(mem_loc),
+ __get_str(fru))
+);
/*
* Hardware Events Report
--
2.0.0.rc0
--
To unsubscribe from this list: send the line "unsubscribe linux-acpi" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
