drm/xe: Resume TDR after GT reset

[ 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: dd08ebf6c352 ("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>

diff --git a/drivers/gpu/drm/xe/xe_gpu_scheduler.c b/drivers/gpu/drm/xe/xe_gpu_scheduler.c
index e4ad1d6ce1d5ff8bb37906d0f7b587bd70bb2f3b..7f24e58cc992f2530ce153f4a742b369551f904a 100644 (file)
--- 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 10c6bb9c938681f1e1113501ffeec4b35bfdb4d0..6aac7fe686735aa24293dbbcfdfef5de4266147a 100644 (file)
--- 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 0a496612c810fa5ab67cb8fba56f5b459052bce2..958dde8422d7e7bf071cbf2468b6d71b7d4473c2 100644 (file)
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1500,6 +1500,7 @@ 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)