drm/xe: Resume TDR after GT reset

[ Upstream commit 1b30f87 ] 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: dd08ebf ("drm/xe: Introduce a new DRM driver for Intel GPUs") Signed-off-by: Matthew Brost <[email protected]> Reviewed-by: Nirmoy Das <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected] (cherry picked from commit 8ec5a4e) Signed-off-by: Lucas De Marchi <[email protected]> Signed-off-by: Sasha Levin <[email protected]>
ChimeraOS · Oct 10, 2024 · 8e0f384 · 8e0f384
1 parent d88f9ba
commit 8e0f384
Show file tree

Hide file tree

Showing 3 changed files with 8 additions and 0 deletions.
diff --git 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
@@ -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
@@ -1740,6 +1740,7 @@ 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)