[PATCH] drm/xe: Resume TDR after GT reset

[Nirmoy Das]

On 7/25/2024 1:59 AM, Matthew Brost wrote:
> Not starting the TDR after GT reset on exec queue which have been
> restarted can lead to jobs being able to be run forever. Fix this by
> restarting the TDR.
>
> Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
> Signed-off-by: Matthew Brost <matthew.brost at intel.com>

Reviewed-by: Nirmoy Das <nirmoy.das at intel.com>

> ---
>  drivers/gpu/drm/xe/xe_gpu_scheduler.c | 5 +++++
>  drivers/gpu/drm/xe/xe_gpu_scheduler.h | 2 ++
>  drivers/gpu/drm/xe/xe_guc_submit.c    | 1 +
>  3 files changed, 8 insertions(+)
>
> diff --git a/drivers/gpu/drm/xe/xe_gpu_scheduler.c b/drivers/gpu/drm/xe/xe_gpu_scheduler.c
> index e4ad1d6ce1d5..7f24e58cc992 100644
> --- a/drivers/gpu/drm/xe/xe_gpu_scheduler.c
> +++ b/drivers/gpu/drm/xe/xe_gpu_scheduler.c
> @@ -90,6 +90,11 @@ void xe_sched_submission_stop(struct xe_gpu_scheduler *sched)
>  	cancel_work_sync(&sched->work_process_msg);
>  }
>  
> +void xe_sched_submission_resume_tdr(struct xe_gpu_scheduler *sched)
> +{
> +	drm_sched_resume_timeout(&sched->base, sched->base.timeout);
> +}
> +
>  void xe_sched_add_msg(struct xe_gpu_scheduler *sched,
>  		      struct xe_sched_msg *msg)
>  {
> diff --git a/drivers/gpu/drm/xe/xe_gpu_scheduler.h b/drivers/gpu/drm/xe/xe_gpu_scheduler.h
> index 10c6bb9c9386..6aac7fe68673 100644
> --- a/drivers/gpu/drm/xe/xe_gpu_scheduler.h
> +++ b/drivers/gpu/drm/xe/xe_gpu_scheduler.h
> @@ -22,6 +22,8 @@ void xe_sched_fini(struct xe_gpu_scheduler *sched);
>  void xe_sched_submission_start(struct xe_gpu_scheduler *sched);
>  void xe_sched_submission_stop(struct xe_gpu_scheduler *sched);
>  
> +void xe_sched_submission_resume_tdr(struct xe_gpu_scheduler *sched);
> +
>  void xe_sched_add_msg(struct xe_gpu_scheduler *sched,
>  		      struct xe_sched_msg *msg);
>  
> diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
> index 460808507947..2327e11ae311 100644
> --- a/drivers/gpu/drm/xe/xe_guc_submit.c
> +++ b/drivers/gpu/drm/xe/xe_guc_submit.c
> @@ -1768,6 +1768,7 @@ static void guc_exec_queue_start(struct xe_exec_queue *q)
>  	}
>  
>  	xe_sched_submission_start(sched);
> +	xe_sched_submission_resume_tdr(sched);
>  }
>  
>  int xe_guc_submit_start(struct xe_guc *guc)