Re: [PATCH v5 2/3] drm/xe/xe_ras: Report correctable error events to userspace

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

On Mon, Jul 20, 2026 at 01:52:11PM +0530, Riana Tauro wrote:
> When an interrupt is received indicating that error counter has crossed
> its threshold, read the current counter value and deliver a drm_ras error
> event to userspace for each affected component.
> 
> To avoid sending duplicate events when the same component appears multiple
> times in the response. Send the error-event once per component.

...

> +void xe_drm_ras_event(struct xe_device *xe, u8 component, u8 severity, u32 value)
> +{
> +	struct xe_drm_ras *ras = &xe->ras;
> +	struct xe_drm_ras_counter *info;
> +	struct drm_ras_node *node;
> +	int ret;
> +
> +	/* Event is supported only if drm_ras is enabled */
> +	if (!xe->info.has_drm_ras)
> +		return;
> +
> +	if (component >= DRM_XE_RAS_ERR_COMP_MAX) {

IIUC this is error_id and should be validated against first/last counter
range in drm_ras layer (similar to registration code).

> +		drm_warn(&xe->drm, "unsupported component %u\n", component);
> +		return;
> +	}
> +
> +	if (severity >= DRM_XE_RAS_ERR_SEV_MAX) {
> +		drm_warn(&xe->drm, "unsupported severity %u\n", severity);
> +		return;
> +	}
> +
> +	node = &ras->node[severity];
> +	info = ras->info[severity];
> +
> +	if (!info || !info[component].name)
> +		return;
> +
> +	ret = drm_ras_nl_error_event(node, component, info[component].name, value);
> +	if (ret)
> +		drm_err_ratelimited(&xe->drm, "drm_ras error-event failed: %d for %s %s\n", ret,
> +				    info[component].name, error_severity[severity]);
> +}

...

> +static void ras_send_error_event(struct xe_device *xe, u8 severity, u8 component)
> +{
> +	struct xe_ras_error_class counter = {0};
> +	u8 drm_severity, drm_component;
> +	u32 value;
> +	int ret;
> +
> +	counter.common.severity = severity;
> +	counter.common.component = component;
> +
> +	ret = get_counter(xe, &counter, &value);
> +	if (ret)
> +		return;
> +
> +	drm_severity = xe_to_drm_ras_severity(severity);
> +	drm_component = xe_to_drm_ras_component(component);
> +
> +	xe_drm_ras_event(xe, drm_component, drm_severity, value);
> +}

This entire function can be dropped. See below.

>  static u8 handle_core_compute_errors(struct xe_ras_error_array *arr)
>  {
>  	struct xe_ras_compute_error *error_info = (void *)arr->details;
> @@ -312,8 +364,10 @@ void xe_ras_counter_threshold_crossed(struct xe_device *xe,
>  	struct xe_ras_threshold_crossed *pending = (void *)&response->data;
>  	struct xe_ras_error_class *errors = pending->counters;
>  	u32 id, ncounters = pending->ncounters;
> +	u8 sent = 0;
>  
>  	BUILD_BUG_ON(sizeof(response->data) < sizeof(*pending));
> +	BUILD_BUG_ON(BITS_PER_TYPE(sent) < XE_RAS_COMP_MAX);
>  	xe_device_assert_mem_access(xe);
>  
>  	if (!ncounters || ncounters > XE_RAS_NUM_COUNTERS)
> @@ -327,8 +381,21 @@ void xe_ras_counter_threshold_crossed(struct xe_device *xe,
>  		severity = errors[id].common.severity;
>  		component = errors[id].common.component;
>  
> +		if (severity != XE_RAS_SEV_CORRECTABLE) {
> +			xe_warn(xe, "sysctrl: unexpected severity %s (%u)\n", sev_to_str(severity),
> +				severity);

Sanity checks are good, but I think this needs to be extended a bit.
I have something[1] more robust, feel free to reuse.

[1] https://lore.kernel.org/intel-xe/20260721082953.640497-1-raag.jadav@intel.com

> +			continue;
> +		}
> +
>  		xe_warn(xe, "[RAS]: %s %s detected\n",
>  			comp_to_str(component), sev_to_str(severity));
> +
> +		/* Send event once per component */
> +		if (sent & BIT(component))
> +			continue;
> +		sent |= BIT(component);

With [1] in place you can just get_counter(&counter) and drm_ras_event()
directly.

Raag

> +		ras_send_error_event(xe, severity, component);
>  	}
>  }
>  
> -- 
> 2.47.1
>