1 files changed, 25 insertions, 9 deletions

diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 7afcc243037c..5f3ef8b1f194 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -769,17 +769,19 @@ static void disable_scheduling_deregister(struct xe_guc *guc,
 					  struct xe_exec_queue *q)
 {
 	MAKE_SCHED_CONTEXT_ACTION(q, DISABLE);
-	struct xe_device *xe = guc_to_xe(guc);
 	int ret;
 
 	set_min_preemption_timeout(guc, q);
 	smp_rmb();
-	ret = wait_event_timeout(guc->ct.wq, !exec_queue_pending_enable(q) ||
-				 xe_guc_read_stopped(guc), HZ * 5);
+	ret = wait_event_timeout(guc->ct.wq,
+				 (!exec_queue_pending_enable(q) &&
+				  !exec_queue_pending_disable(q)) ||
+					 xe_guc_read_stopped(guc),
+				 HZ * 5);
 	if (!ret) {
 		struct xe_gpu_scheduler *sched = &q->guc->sched;
 
-		drm_warn(&xe->drm, "Pending enable failed to respond");
+		xe_gt_warn(q->gt, "Pending enable/disable failed to respond\n");
 		xe_sched_submission_start(sched);
 		xe_gt_reset_async(q->gt);
 		xe_sched_tdr_queue_imm(sched);
@@ -1101,7 +1103,8 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job)
 			 * modifying state
 			 */
 			ret = wait_event_timeout(guc->ct.wq,
-						 !exec_queue_pending_enable(q) ||
+						 (!exec_queue_pending_enable(q) &&
+						  !exec_queue_pending_disable(q)) ||
 						 xe_guc_read_stopped(guc), HZ * 5);
 			if (!ret || xe_guc_read_stopped(guc))
 				goto trigger_reset;
@@ -1330,8 +1333,8 @@ static void __guc_exec_queue_process_msg_suspend(struct xe_sched_msg *msg)
 
 	if (guc_exec_queue_allowed_to_change_state(q) && !exec_queue_suspended(q) &&
 	    exec_queue_enabled(q)) {
-		wait_event(guc->ct.wq, q->guc->resume_time != RESUME_PENDING ||
-			   xe_guc_read_stopped(guc));
+		wait_event(guc->ct.wq, (q->guc->resume_time != RESUME_PENDING ||
+			   xe_guc_read_stopped(guc)) && !exec_queue_pending_disable(q));
 
 		if (!xe_guc_read_stopped(guc)) {
 			s64 since_resume_ms =
@@ -1868,16 +1871,29 @@ static void handle_sched_done(struct xe_guc *guc, struct xe_exec_queue *q,
 		xe_gt_assert(guc_to_gt(guc), runnable_state == 0);
 		xe_gt_assert(guc_to_gt(guc), exec_queue_pending_disable(q));
 
-		clear_exec_queue_pending_disable(q);
 		if (q->guc->suspend_pending) {
 			suspend_fence_signal(q);
+			clear_exec_queue_pending_disable(q);
 		} else {
 			if (exec_queue_banned(q) || check_timeout) {
 				smp_wmb();
 				wake_up_all(&guc->ct.wq);
 			}
-			if (!check_timeout)
+			if (!check_timeout && exec_queue_destroyed(q)) {
+				/*
+				 * Make sure to clear the pending_disable only
+				 * after sampling the destroyed state. We want
+				 * to ensure we don't trigger the unregister too
+				 * early with something intending to only
+				 * disable scheduling. The caller doing the
+				 * destroy must wait for an ongoing
+				 * pending_disable before marking as destroyed.
+				 */
+				clear_exec_queue_pending_disable(q);
 				deregister_exec_queue(guc, q);
+			} else {
+				clear_exec_queue_pending_disable(q);
+			}
 		}
 	}
 }