Update the GHES error processing logic to taint the kernel when
a recoverable or corrected hardware error is detected.
If the error severity is GHES_SEV_RECOVERABLE or GHES_SEV_CORRECTED, the
TAINT_HW_ERROR_RECOVERED flag is set. This allows users and support
tools to identify systems that have experienced hardware issues that
were recovered at runtime, improving traceability and diagnostics.
Signed-off-by: Breno Leitao <leitao@xxxxxxxxxx>
---
drivers/acpi/apei/ghes.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 3d44f926afe8e..f323cefe234b9 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -1102,13 +1102,16 @@ static int ghes_proc(struct ghes *ghes)
{
struct acpi_hest_generic_status *estatus = ghes->estatus;
u64 buf_paddr;
- int rc;
+ int rc, sev;
rc = ghes_read_estatus(ghes, estatus, &buf_paddr, FIX_APEI_GHES_IRQ);
if (rc)
goto out;
- if (ghes_severity(estatus->error_severity) >= GHES_SEV_PANIC)
+ sev = ghes_severity(estatus->error_severity);
+ if (sev == GHES_SEV_RECOVERABLE || sev == GHES_SEV_CORRECTED)
+ add_taint(TAINT_HW_ERROR_RECOVERED, LOCKDEP_STILL_OK);
+ else if (sev >= GHES_SEV_PANIC)
__ghes_panic(ghes, estatus, buf_paddr, FIX_APEI_GHES_IRQ);
if (!ghes_estatus_cached(estatus)) {
--
2.47.1
