On Wed, Jul 01, 2026 at 03:14:13PM +0530, Riana Tauro wrote:
> Add error-event support for Correctable errors in CRI. Report an error
> event to userspace for every component that has crossed the threshold on
> receiving an interrupt.
...
> +static void ras_send_error_event(struct xe_device *xe, u8 severity, u8
> component)
> +{
> + u8 drm_severity, drm_component;
> + u32 value;
> + int ret;
> +
> + drm_severity = xe_to_drm_ras_severity(severity);
> + if (drm_severity == DRM_XE_RAS_ERR_SEV_MAX) {
> + xe_warn(xe, "sysctrl: unexpected severity %u\n", severity);
This is uapi and not coming from sysctrl, so the message is a bit
misleading. But if at all it needs validation, it should be done in
drm_ras layer.
> + return;
> + }
> +
> + drm_component = xe_to_drm_ras_component(component);
> + if (drm_component == DRM_XE_RAS_ERR_COMP_MAX) {
> + xe_warn(xe, "sysctrl: unexpected component %u\n", component);
Ditto.
> + return;
> + }
> +
> + ret = xe_ras_get_counter(xe, drm_severity, drm_component, &value);
No, instead of converting back and forth just do get_counter() using
sysctrl values and send_event() afterwards.
> + if (ret)
> + return;
> +
> + xe_drm_ras_event(xe, drm_component, drm_severity, value, GFP_KERNEL);
> +}
> +
> void xe_ras_counter_threshold_crossed(struct xe_device *xe,
> struct xe_sysctrl_event_response
> *response)
> {
> 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(XE_RAS_COMP_MAX > (BITS_PER_BYTE * sizeof(sent)));
I prefer it the other way around. Also, have you tried using BITS_PER_TYPE()?
BUILD_BUG_ON(BITS_PER_TYPE(sent) < XE_RAS_COMP_MAX));
> xe_device_assert_mem_access(xe);
>
> if (!ncounters || ncounters > XE_RAS_NUM_COUNTERS)
> @@ -154,6 +211,24 @@ void xe_ras_counter_threshold_crossed(struct xe_device
> *xe,
>
> xe_warn(xe, "[RAS]: %s %s detected\n",
> comp_to_str(component), sev_to_str(severity));
> +
> + if (severity != XE_RAS_SEV_CORRECTABLE) {
> + xe_warn(xe, "sysctrl: unexpected severity %s (%u)\n",
> sev_to_str(severity),
> + severity);
This should be before "detected" log above.
> + continue;
> + }
> +
> + if (component >= XE_RAS_COMP_MAX) {
> + xe_warn(xe, "sysctrl: unexpected component %u\n",
> component);
Ditto. Also, use xx_to_str() in both cases or don't but be consistent.
Raag
> + continue;
> + }
> +
> + /* Send event once per component */
> + if (sent & BIT(component))
> + continue;
> + sent |= BIT(component);
> +
> + ras_send_error_event(xe, severity, component);
> }
> }
>
> --
> 2.47.1
>
