drm/xe: Resume TDR after GT reset

BugLink: https://bugs.launchpad.net/bugs/2089884

[ Upstream commit 1b30f87e088b499eb74298db256da5c98e8276e2 ]

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: dd08ebf6c3 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Nirmoy Das <nirmoy.das@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240724235919.1917216-1-matthew.brost@intel.com
(cherry picked from commit 8ec5a4e5ce97d6ee9f5eb5b4ce4cfc831976fdec)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Koichiro Den <koichiro.den@canonical.com>
Signed-off-by: Roxana Nicolescu <roxana.nicolescu@canonical.com>

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)
 {

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);
 

drivers/gpu/drm/xe/xe_guc_submit.c

@@ -1525,6 +1525,7 @@ 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)