Re: [PATCH v5 08/13] drm/xe/xe_ras: Report core compute errors using SIGID

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

On 23-10-2026 10:04 am, Badal Nilawar wrote:
> Use xe_log_* helpers to report core compute errors.
>
> Example:
> 	xe 0000:03:00.0: [drm] *ERROR* SIGID=203 (02020012000a000200000800)
> [Hardware Error]: CORE_COMPUTE: Uncorrectable error detected, type 2
>
> 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>
> ---
> v5:
>    - Print uncorr error type in sig id log (Riana)
> v2:
>    - Pass RAS firmware reported severity to xe_log
> ---
>   drivers/gpu/drm/xe/xe_ras.c | 8 ++++++--
>   1 file changed, 6 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/xe/xe_ras.c b/drivers/gpu/drm/xe/xe_ras.c
> index 5ebfc6e8dfc7..1f94dd1fb91b 100644
> --- a/drivers/gpu/drm/xe/xe_ras.c
> +++ b/drivers/gpu/drm/xe/xe_ras.c
> @@ -577,13 +577,17 @@ static void ras_send_error_event(struct xe_device *xe, u8 severity, u8 component
>   	xe_drm_ras_event(xe, drm_component, drm_severity, value);
>   }
>   
> -static u8 handle_core_compute_errors(struct xe_ras_error_array *arr)
> +static u8 handle_core_compute_errors(struct xe_device *xe, struct xe_ras_error_array *arr)
>   {
>   	struct xe_ras_compute_error *error_info = (void *)arr->details;
> +	u8 cper_sev = ras_sev_to_cper_sev(arr->counter.common.severity);
>   	u8 uncorr_type;
>   
>   	uncorr_type = FIELD_GET(CORE_COMPUTE_UNCORR_TYPE, error_info->log_header);
>   
> +	xe_log_comp(xe, cper_sev, CORE_COMPUTE, &arr->counter, sizeof(arr->counter),
> +		    "Uncorrectable error detected, type %u\n", uncorr_type);
> +
>   	/* Request a reset if error is global */
>   	if (uncorr_type == GLOBAL_UNCORR_ERROR)
>   		return XE_RAS_RECOVERY_ACTION_RESET;
> @@ -867,7 +871,7 @@ enum xe_ras_recovery_action xe_ras_process_errors(struct xe_device *xe)
>   
>   			switch (component) {
>   			case XE_RAS_COMP_CORE_COMPUTE:
> -				action = handle_core_compute_errors(arr);
> +				action = handle_core_compute_errors(xe, arr);
>   				break;
>   			case XE_RAS_COMP_SOC_INTERNAL:
>   				action = handle_soc_internal_errors(xe, arr);