drm/xe: Call __guc_exec_queue_fini_async direct for KERNEL exec_queues

Usually we call __guc_exec_queue_fini_async via a worker as the
exec_queue fini can be done from within the GPU scheduler which creates
a circular dependency without a worker. Kernel exec_queues are fini'd at
driver unload (not from within the GPU scheduler) so it is safe to
directly call __guc_exec_queue_fini_async.

Suggested-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>

Author: mbrost05

drivers/gpu/drm/xe/xe_guc_submit.c

@@ -956,27 +956,19 @@ static void __guc_exec_queue_fini_async(struct work_struct *w)
 	xe_sched_entity_fini(&ge->entity);
 	xe_sched_fini(&ge->sched);
 
-	if (!(q->flags & EXEC_QUEUE_FLAG_KERNEL)) {
-		kfree(ge);
-		xe_exec_queue_fini(q);
-	}
+	kfree(ge);
+	xe_exec_queue_fini(q);
 }
 
 static void guc_exec_queue_fini_async(struct xe_exec_queue *q)
 {
-	bool kernel = q->flags & EXEC_QUEUE_FLAG_KERNEL;
-
 	INIT_WORK(&q->guc->fini_async, __guc_exec_queue_fini_async);
-	queue_work(system_wq, &q->guc->fini_async);
 
 	/* We must block on kernel engines so slabs are empty on driver unload */
-	if (kernel) {
-		struct xe_guc_exec_queue *ge = q->guc;
-
-		flush_work(&ge->fini_async);
-		kfree(ge);
-		xe_exec_queue_fini(q);
-	}
+	if (q->flags & EXEC_QUEUE_FLAG_KERNEL)
+		__guc_exec_queue_fini_async(&q->guc->fini_async);
+	else
+		queue_work(system_wq, &q->guc->fini_async);
 }
 
 static void __guc_exec_queue_fini(struct xe_guc *guc, struct xe_exec_queue *q)