Re: [PATCH v2 05/11] drm/xe: Skip device access during PCI error recovery

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

On 02-03-2026 03:52 pm, Riana Tauro wrote:
> When a fatal error occurs and the error_detected callback is
> invoked the device is inaccessible. The error_detected callback
> wedges the device causing the jobs to timeout.
>
> The timedout handler acquires forcewake to dump devcoredump and
> triggers a GT reset. Since the device is inacessible this causes
> errors. Skip all mmio accesses and gt reset when the device
> is in recovery.
>
> Cc: Matthew Brost <matthew.brost@intel.com>
> Cc: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
> Signed-off-by: Riana Tauro <riana.tauro@intel.com>
> ---
>   drivers/gpu/drm/xe/xe_gt.c         | 11 ++++++++---
>   drivers/gpu/drm/xe/xe_guc_submit.c |  9 +++++----
>   2 files changed, 13 insertions(+), 7 deletions(-)
>
> diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
> index b455af1e6072..6f41090063bf 100644
> --- a/drivers/gpu/drm/xe/xe_gt.c
> +++ b/drivers/gpu/drm/xe/xe_gt.c
> @@ -933,18 +933,23 @@ static void gt_reset_worker(struct work_struct *w)
>   
>   void xe_gt_reset_async(struct xe_gt *gt)
>   {
> -	xe_gt_info(gt, "trying reset from %ps\n", __builtin_return_address(0));
> +	struct xe_device *xe = gt_to_xe(gt);
> +
> +	if (xe_device_is_in_recovery(xe))
> +		return;

Need to check in_recovery flag in the gt_reset_worker() as well to skip 
GT reset when device in PCI recovery.

Thanks

-/Mallesh

>   	/* Don't do a reset while one is already in flight */
>   	if (!xe_fault_inject_gt_reset() && xe_uc_reset_prepare(&gt->uc))
>   		return;
>   
> +	xe_gt_info(gt, "trying reset from %ps\n", __builtin_return_address(0));
> +
>   	xe_gt_info(gt, "reset queued\n");
>   
>   	/* Pair with put in gt_reset_worker() if work is enqueued */
> -	xe_pm_runtime_get_noresume(gt_to_xe(gt));
> +	xe_pm_runtime_get_noresume(xe);
>   	if (!queue_work(gt->ordered_wq, &gt->reset.worker))
> -		xe_pm_runtime_put(gt_to_xe(gt));
> +		xe_pm_runtime_put(xe);
>   }
>   
>   void xe_gt_suspend_prepare(struct xe_gt *gt)
> diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
> index ca7aa4f358d0..c25658f1e44b 100644
> --- a/drivers/gpu/drm/xe/xe_guc_submit.c
> +++ b/drivers/gpu/drm/xe/xe_guc_submit.c
> @@ -1508,7 +1508,7 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job)
>   	 * If devcoredump not captured and GuC capture for the job is not ready
>   	 * do manual capture first and decide later if we need to use it
>   	 */
> -	if (!exec_queue_killed(q) && !xe->devcoredump.captured &&
> +	if (!xe_device_is_in_recovery(xe) && !exec_queue_killed(q) && !xe->devcoredump.captured &&
>   	    !xe_guc_capture_get_matching_and_lock(q)) {
>   		/* take force wake before engine register manual capture */
>   		CLASS(xe_force_wake, fw_ref)(gt_to_fw(q->gt), XE_FORCEWAKE_ALL);
> @@ -1530,8 +1530,8 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job)
>   	set_exec_queue_banned(q);
>   
>   	/* Kick job / queue off hardware */
> -	if (!wedged && (exec_queue_enabled(primary) ||
> -			exec_queue_pending_disable(primary))) {
> +	if (!xe_device_is_in_recovery(xe) && !wedged &&
> +	    (exec_queue_enabled(primary) || exec_queue_pending_disable(primary))) {
>   		int ret;
>   
>   		if (exec_queue_reset(primary))
> @@ -1599,7 +1599,8 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job)
>   
>   	trace_xe_sched_job_timedout(job);
>   
> -	if (!exec_queue_killed(q))
> +	/* Do not access device if in recovery */
> +	if (!xe_device_is_in_recovery(xe) && !exec_queue_killed(q))
>   		xe_devcoredump(q, job,
>   			       "Timedout job - seqno=%u, lrc_seqno=%u, guc_id=%d, flags=0x%lx",
>   			       xe_sched_job_seqno(job), xe_sched_job_lrc_seqno(job),