Re: [PATCH v4 11/12] drm/xe/xe_ras: Report soc internal errors using SIGID

["Mallesh, Koujalagi" <mallesh.koujalagi@intel.com>]

On 09-10-2026 04:16 pm, Badal Nilawar wrote:
> Use xe_log_* helpers to report soc internal errors.
>
> Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
> Signed-off-by: Badal Nilawar <badal.nilawar@intel.com>
LGTM,
Reviewed-by: Mallesh Koujalagi <mallesh.koujalagi@intel.com>
> Cc: Riana Tauro <riana.tauro@intel.com>
> ---
>   drivers/gpu/drm/xe/xe_ras.c | 12 +++++-------
>   1 file changed, 5 insertions(+), 7 deletions(-)
>
> diff --git a/drivers/gpu/drm/xe/xe_ras.c b/drivers/gpu/drm/xe/xe_ras.c
> index 6647300c7f17..af2970941b59 100644
> --- a/drivers/gpu/drm/xe/xe_ras.c
> +++ b/drivers/gpu/drm/xe/xe_ras.c
> @@ -366,7 +366,6 @@ static u8 handle_soc_internal_errors(struct xe_device *xe, struct xe_ras_error_a
>   {
>   	struct xe_ras_soc_error *info = (void *)arr->details;
>   	struct xe_ras_soc_error_source *source = &info->source;
> -	struct xe_ras_error_class *counter = &arr->counter;
>   
>   	if (source->csc) {
>   		struct xe_ras_csc_error *csc_error = (void *)info->details;
> @@ -380,9 +379,8 @@ static u8 handle_soc_internal_errors(struct xe_device *xe, struct xe_ras_error_a
>   		 * is required.
>   		 */
>   		if (csc_error->hec_fw_error) {
> -			xe_err(xe, "[RAS]: CSC %s detected: 0x%x\n",
> -			       sev_to_str(counter->common.severity),
> -			       csc_error->hec_fw_error);
> +			xe_log_comp_fatal(xe, SOC_INTERNAL, &arr->counter, sizeof(arr->counter),
> +					  "CSC error detected: 0x%x\n", csc_error->hec_fw_error);
>   			xe_survivability_mode_runtime_enable(xe);
>   			return XE_RAS_RECOVERY_ACTION_DISCONNECT;
>   		}
> @@ -390,9 +388,9 @@ static u8 handle_soc_internal_errors(struct xe_device *xe, struct xe_ras_error_a
>   		struct xe_ras_ieh_error *ieh_error = (void *)info->details;
>   
>   		if (ieh_error->global_error_status & XE_RAS_SOC_IEH_PUNIT) {
> -			xe_err(xe, "[RAS]: PUNIT %s detected: 0x%x\n",
> -			       sev_to_str(counter->common.severity),
> -			       ieh_error->global_error_status);
> +			xe_log_comp_fatal(xe, SOC_INTERNAL, &arr->counter, sizeof(arr->counter),
> +					  "PUNIT error detected: 0x%x\n",
> +					  ieh_error->global_error_status);
>   			punit_error_handler(xe);
>   			return XE_RAS_RECOVERY_ACTION_DISCONNECT;
>   		}