Currently when a RAS error is reported it is not timestamped.
The ACPI 6.1 spec adds the timestamp field to the generic error
data entry v3 structure. The timestamp of when the firmware
generated the error is now being reported.
Signed-off-by: Jonathan (Zhixiong) Zhang <zjzhang@xxxxxxxxxxxxxx>
Signed-off-by: Richard Ruigrok <rruigrok@xxxxxxxxxxxxxx>
Signed-off-by: Tyler Baicar <tbaicar@xxxxxxxxxxxxxx>
Signed-off-by: Naveen Kaje <nkaje@xxxxxxxxxxxxxx>
---
drivers/acpi/apei/ghes.c | 14 +++++++---
drivers/firmware/efi/cper.c | 67
+++++++++++++++++++++++++++++++++++++--------
include/acpi/ghes.h | 10 +++++++
include/linux/cper.h | 12 ++++++++
4 files changed, 88 insertions(+), 15 deletions(-)
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 7d020b0..7610f08 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -419,7 +419,8 @@ static void ghes_handle_memory_failure(struct
acpi_hest_generic_data *gdata, int
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);
+
+ mem_err = acpi_hest_generic_data_payload(gdata);
if (!(mem_err->validation_bits & CPER_MEM_VALID_PA))
return;
@@ -449,14 +450,18 @@ static void ghes_do_proc(struct ghes *ghes,
{
int sev, sec_sev;
struct acpi_hest_generic_data *gdata;
+ uuid_le sec_type;
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,
+ sec_type = *(uuid_le *)gdata->section_type;
+
+ if (!uuid_le_cmp(sec_type,
CPER_SEC_PLATFORM_MEM)) {
struct cper_sec_mem_err *mem_err;
- mem_err = (struct cper_sec_mem_err *)(gdata+1);
+
+ mem_err = acpi_hest_generic_data_payload(gdata);
ghes_edac_report_mem_error(ghes, sev, mem_err);
arch_apei_report_mem_error(sev, mem_err);
@@ -466,7 +471,8 @@ static void ghes_do_proc(struct ghes *ghes,
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);
+
+ pcie_err = acpi_hest_generic_data_payload(gdata);
if (sev == GHES_SEV_RECOVERABLE &&
sec_sev == GHES_SEV_RECOVERABLE &&
pcie_err->validation_bits &
CPER_PCIE_VALID_DEVICE_ID &&
diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index d425374..af7e1e9 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -32,6 +32,9 @@
#include <linux/acpi.h>
#include <linux/pci.h>
#include <linux/aer.h>
+#include <linux/printk.h>
+#include <linux/bcd.h>
+#include <acpi/ghes.h>
#define INDENT_SP " "
@@ -386,13 +389,37 @@ static void cper_print_pcie(const char *pfx,
const struct cper_sec_pcie *pcie,
pfx, pcie->bridge.secondary_status, pcie->bridge.control);
}
+static void cper_estatus_print_section_v300(const char *pfx,
+ const struct acpi_hest_generic_data_v300 *gdata)
+{
+ __u8 hour, min, sec, day, mon, year, century, *timestamp;
+
+ if (gdata->validation_bits & ACPI_HEST_GEN_VALID_TIMESTAMP) {
+ timestamp = (__u8 *)&(gdata->time_stamp);
+ sec = bcd2bin(timestamp[0]);
+ min = bcd2bin(timestamp[1]);
+ hour = bcd2bin(timestamp[2]);
+ day = bcd2bin(timestamp[4]);
+ mon = bcd2bin(timestamp[5]);
+ year = bcd2bin(timestamp[6]);
+ century = bcd2bin(timestamp[7]);
+ printk("%stime: %7s %02d%02d-%02d-%02d %02d:%02d:%02d\n", pfx,
+ 0x01 & *(timestamp + 3) ? "precise" : "", century,
+ year, mon, day, hour, min, sec);
+ }
+}
+
static void cper_estatus_print_section(
- const char *pfx, const struct acpi_hest_generic_data *gdata, int
sec_no)
+ const char *pfx, struct acpi_hest_generic_data *gdata, int sec_no)
{
uuid_le *sec_type = (uuid_le *)gdata->section_type;
__u16 severity;
char newpfx[64];
+ if (acpi_hest_generic_data_version(gdata))
+ cper_estatus_print_section_v300(pfx,
+ (const struct acpi_hest_generic_data_v300 *)gdata);
+
severity = gdata->error_severity;
printk("%s""Error %d, type: %s\n", pfx, sec_no,
cper_severity_str(severity));
@@ -403,14 +430,18 @@ static void cper_estatus_print_section(
snprintf(newpfx, sizeof(newpfx), "%s%s", pfx, INDENT_SP);
if (!uuid_le_cmp(*sec_type, CPER_SEC_PROC_GENERIC)) {
- struct cper_sec_proc_generic *proc_err = (void *)(gdata + 1);
+ struct cper_sec_proc_generic *proc_err;
+
+ proc_err = acpi_hest_generic_data_payload(gdata);
printk("%s""section_type: general processor error\n", newpfx);
if (gdata->error_data_length >= sizeof(*proc_err))
cper_print_proc_generic(newpfx, 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);
+ struct cper_sec_mem_err *mem_err;
+
+ mem_err = acpi_hest_generic_data_payload(gdata);
printk("%s""section_type: memory error\n", newpfx);
if (gdata->error_data_length >=
sizeof(struct cper_sec_mem_err_old))
@@ -419,7 +450,9 @@ static void cper_estatus_print_section(
else
goto err_section_too_small;
} else if (!uuid_le_cmp(*sec_type, CPER_SEC_PCIE)) {
- struct cper_sec_pcie *pcie = (void *)(gdata + 1);
+ struct cper_sec_pcie *pcie;
+
+ pcie = acpi_hest_generic_data_payload(gdata);
printk("%s""section_type: PCIe error\n", newpfx);
if (gdata->error_data_length >= sizeof(*pcie))
cper_print_pcie(newpfx, pcie, gdata);
@@ -438,6 +471,7 @@ void cper_estatus_print(const char *pfx,
const struct acpi_hest_generic_status *estatus)
{
struct acpi_hest_generic_data *gdata;
+ struct acpi_hest_generic_data_v300 *gdata_v3 = NULL;
unsigned int data_len, gedata_len;
int sec_no = 0;
char newpfx[64];
@@ -451,12 +485,22 @@ void cper_estatus_print(const char *pfx,
printk("%s""event severity: %s\n", pfx,
cper_severity_str(severity));
data_len = estatus->data_length;
gdata = (struct acpi_hest_generic_data *)(estatus + 1);
+ if (acpi_hest_generic_data_version(gdata))
+ gdata_v3 = (struct acpi_hest_generic_data_v300 *)gdata;
