Re: [PATCH 1/2] drm/xe/xe_ras: Add Fabric error handling

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

[-- Attachment #1: Type: text/plain, Size: 2928 bytes --]


On 25-08-2026 07:41 pm, Riana Tauro wrote:
> SAF MHB errors are collected and classifed under Fabric error component
> by System controller. For SAF_MHB errors, if the cause is data
> payload parity error then log and return.
>
> For all other errors and causes, request a Secondary Bus Reset (SBR)
>
> Signed-off-by: Riana Tauro<riana.tauro@intel.com>
> ---
>   drivers/gpu/drm/xe/xe_ras.c       | 20 ++++++++++++++++++++
>   drivers/gpu/drm/xe/xe_ras_types.h |  4 ++++
>   2 files changed, 24 insertions(+)
>
> diff --git a/drivers/gpu/drm/xe/xe_ras.c b/drivers/gpu/drm/xe/xe_ras.c
> index d25d25f77531..586dc28a638a 100644
> --- a/drivers/gpu/drm/xe/xe_ras.c
> +++ b/drivers/gpu/drm/xe/xe_ras.c
> @@ -394,6 +394,23 @@ static u8 handle_device_memory_errors(struct xe_device *xe, struct xe_ras_error_
>   	return XE_RAS_RECOVERY_ACTION_RECOVERED;
>   }
>   
> +static u8 handle_fabric_errors(struct xe_device *xe, struct xe_ras_error_array *arr)
> +{
> +	struct xe_ras_error_product *product = &arr->counter.product;
> +	struct xe_ras_ieh_error *info = (void *)arr->details;
> +
> +	if ((info->global_error_status & XE_RAS_FAB_IEH_SAF_MHB) &&
> +	    product->cause.cause == XE_RAS_FAB_CAUSE_PAYLOAD) {
> +		xe_log_comp_recoverable(xe, FABRIC, &arr->counter, sizeof(arr->counter),
> +					"SAF MHB error detected\n");

We need to convert RAS to CPER severity and make use of xe_log_comp 
SIGID helper function with arr->counter.common.severity.

Helper function will take care of severity.

> +		return XE_RAS_RECOVERY_ACTION_RECOVERED;
> +	}
> +
> +	xe_log_comp_fatal(xe, FABRIC, &arr->counter, sizeof(arr->counter),
> +			  "Other errors detected\n");
ditto
> +	return XE_RAS_RECOVERY_ACTION_RESET;
> +}
> +
>   void xe_ras_counter_threshold_crossed(struct xe_device *xe,
>   				      struct xe_sysctrl_event_response *response)
>   {
> @@ -555,6 +572,9 @@ enum xe_ras_recovery_action xe_ras_process_errors(struct xe_device *xe)
>   			case XE_RAS_COMP_DEVICE_MEMORY:
>   				action = handle_device_memory_errors(xe, arr);
>   				break;
> +			case XE_RAS_COMP_FABRIC:
> +				action = handle_fabric_errors(xe, arr);
> +				break;
>   			default:
>   				/* For any other component, reset */
>   				action = XE_RAS_RECOVERY_ACTION_RESET;
> diff --git a/drivers/gpu/drm/xe/xe_ras_types.h b/drivers/gpu/drm/xe/xe_ras_types.h
> index 99b2466e2062..73517fd0d415 100644
> --- a/drivers/gpu/drm/xe/xe_ras_types.h
> +++ b/drivers/gpu/drm/xe/xe_ras_types.h
> @@ -12,6 +12,10 @@
>   #define XE_RAS_NUM_ERROR_ARR			3
>   /* Error bits in IEH global error status register */
>   #define XE_RAS_SOC_IEH_PUNIT			BIT(1)
> +/* Bits 16-31 represent individual SAF MHB unit */
> +#define XE_RAS_FAB_IEH_SAF_MHB			GENMASK(31, 16)
> +/* Fabric Data payload parity errors */
> +#define XE_RAS_FAB_CAUSE_PAYLOAD		BIT(2)
>   /* Device memory error categories */
>   #define XE_RAS_MEMORY_DB_ECC			BIT(1)
>   #define XE_RAS_MEMORY_POISON			BIT(2)

[-- Attachment #2: Type: text/html, Size: 3941 bytes --]