Re: [PATCH v4 10/12] drm/xe/xe_ras: Report core compute errors using SIGID

[Raag Jadav <raag.jadav@intel.com>]

On Fri, Oct 09, 2026 at 04:16:13PM +0530, Badal Nilawar wrote:
> Use xe_log_* helpers to report core compute errors.
> 
> Signed-off-by: Badal Nilawar <badal.nilawar@intel.com>
> Cc: Riana Tauro <riana.tauro@intel.com>
> ---
> v2:
>   - Pass RAS firmware reported severity to xe_log
> ---
>  drivers/gpu/drm/xe/xe_ras.c | 12 +++++++++---
>  1 file changed, 9 insertions(+), 3 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_ras.c b/drivers/gpu/drm/xe/xe_ras.c
> index 8ed4a6992ef1..6647300c7f17 100644
> --- a/drivers/gpu/drm/xe/xe_ras.c
> +++ b/drivers/gpu/drm/xe/xe_ras.c
> @@ -332,21 +332,27 @@ static void ras_send_error_event(struct xe_device *xe, u8 severity, u8 component
>  	xe_drm_ras_event(xe, drm_component, drm_severity, response.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);
>  
>  	/* Request a reset if error is global */
> -	if (uncorr_type == GLOBAL_UNCORR_ERROR)
> +	if (uncorr_type == GLOBAL_UNCORR_ERROR) {
> +		xe_log_comp(xe, cper_sev, CORE_COMPUTE, &arr->counter, sizeof(arr->counter),
> +			    "Global uncorrectable error detected\n");
>  		return XE_RAS_RECOVERY_ACTION_RESET;
> +	}
>  
>  	/*
>  	 * No action needed for other errors.
>  	 * Local errors are recovered using an engine reset by GuC.
>  	 */
> +	xe_log_comp(xe, cper_sev, CORE_COMPUTE, &arr->counter, sizeof(arr->counter),
> +		    "Other compute errors\n");

'Other' errors isn't telling me anything, no they are documented here.
If we don't know what they are, use 'unknown' or something more specific.

Raag

>  	return XE_RAS_RECOVERY_ACTION_RECOVERED;
>  }
>  
> @@ -592,7 +598,7 @@ 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);
> -- 
> 2.54.0
>