1 files changed, 34 insertions, 3 deletions

diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index fbbe6a487bbb..80062e1d3f66 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -276,10 +276,26 @@ static struct workqueue_struct *get_submit_wq(struct xe_guc *guc)
 }
 #endif
 
+static void xe_guc_submit_fini(struct xe_guc *guc)
+{
+	struct xe_device *xe = guc_to_xe(guc);
+	struct xe_gt *gt = guc_to_gt(guc);
+	int ret;
+
+	ret = wait_event_timeout(guc->submission_state.fini_wq,
+				 xa_empty(&guc->submission_state.exec_queue_lookup),
+				 HZ * 5);
+
+	drain_workqueue(xe->destroy_wq);
+
+	xe_gt_assert(gt, ret);
+}
+
 static void guc_submit_fini(struct drm_device *drm, void *arg)
 {
 	struct xe_guc *guc = arg;
 
+	xe_guc_submit_fini(guc);
 	xa_destroy(&guc->submission_state.exec_queue_lookup);
 	free_submit_wq(guc);
 }
@@ -290,9 +306,15 @@ static void guc_submit_wedged_fini(void *arg)
 	struct xe_exec_queue *q;
 	unsigned long index;
 
-	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q)
-		if (exec_queue_wedged(q))
+	mutex_lock(&guc->submission_state.lock);
+	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) {
+		if (exec_queue_wedged(q)) {
+			mutex_unlock(&guc->submission_state.lock);
 			xe_exec_queue_put(q);
+			mutex_lock(&guc->submission_state.lock);
+		}
+	}
+	mutex_unlock(&guc->submission_state.lock);
 }
 
 static const struct xe_exec_queue_ops guc_exec_queue_ops;
@@ -345,6 +367,8 @@ int xe_guc_submit_init(struct xe_guc *guc, unsigned int num_ids)
 
 	xa_init(&guc->submission_state.exec_queue_lookup);
 
+	init_waitqueue_head(&guc->submission_state.fini_wq);
+
 	primelockdep(guc);
 
 	return drmm_add_action_or_reset(&xe->drm, guc_submit_fini, guc);
@@ -361,6 +385,9 @@ static void __release_guc_id(struct xe_guc *guc, struct xe_exec_queue *q, u32 xa
 
 	xe_guc_id_mgr_release_locked(&guc->submission_state.idm,
 				     q->guc->id, q->width);
+
+	if (xa_empty(&guc->submission_state.exec_queue_lookup))
+		wake_up(&guc->submission_state.fini_wq);
 }
 
 static int alloc_guc_id(struct xe_guc *guc, struct xe_exec_queue *q)
@@ -1268,13 +1295,16 @@ static void __guc_exec_queue_fini_async(struct work_struct *w)
 
 static void guc_exec_queue_fini_async(struct xe_exec_queue *q)
 {
+	struct xe_guc *guc = exec_queue_to_guc(q);
+	struct xe_device *xe = guc_to_xe(guc);
+
 	INIT_WORK(&q->guc->fini_async, __guc_exec_queue_fini_async);
 
 	/* We must block on kernel engines so slabs are empty on driver unload */
 	if (q->flags & EXEC_QUEUE_FLAG_PERMANENT || exec_queue_wedged(q))
 		__guc_exec_queue_fini_async(&q->guc->fini_async);
 	else
-		queue_work(system_wq, &q->guc->fini_async);
+		queue_work(xe->destroy_wq, &q->guc->fini_async);
 }
 
 static void __guc_exec_queue_fini(struct xe_guc *guc, struct xe_exec_queue *q)
@@ -1796,6 +1826,7 @@ 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)