1 files changed, 59 insertions, 15 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
index b99ac41695f3..74775ae961b2 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
@@ -70,12 +70,38 @@ static void show_heartbeat(const struct i915_request *rq,
 {
 	struct drm_printer p = drm_debug_printer("heartbeat");
 
-	intel_engine_dump(engine, &p,
-			  "%s heartbeat {seqno:%llx:%lld, prio:%d} not ticking\n",
-			  engine->name,
-			  rq->fence.context,
-			  rq->fence.seqno,
-			  rq->sched.attr.priority);
+	if (!rq) {
+		intel_engine_dump(engine, &p,
+				  "%s heartbeat not ticking\n",
+				  engine->name);
+	} else {
+		intel_engine_dump(engine, &p,
+				  "%s heartbeat {seqno:%llx:%lld, prio:%d} not ticking\n",
+				  engine->name,
+				  rq->fence.context,
+				  rq->fence.seqno,
+				  rq->sched.attr.priority);
+	}
+}
+
+static void
+reset_engine(struct intel_engine_cs *engine, struct i915_request *rq)
+{
+	if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
+		show_heartbeat(rq, engine);
+
+	if (intel_engine_uses_guc(engine))
+		/*
+		 * GuC itself is toast or GuC's hang detection
+		 * is disabled. Either way, need to find the
+		 * hang culprit manually.
+		 */
+		intel_guc_find_hung_context(engine);
+
+	intel_gt_handle_error(engine->gt, engine->mask,
+			      I915_ERROR_CAPTURE,
+			      "stopped heartbeat on %s",
+			      engine->name);
 }
 
 static void heartbeat(struct work_struct *wrk)
@@ -102,6 +128,11 @@ static void heartbeat(struct work_struct *wrk)
 	if (intel_gt_is_wedged(engine->gt))
 		goto out;
 
+	if (i915_sched_engine_disabled(engine->sched_engine)) {
+		reset_engine(engine, engine->heartbeat.systole);
+		goto out;
+	}
+
 	if (engine->heartbeat.systole) {
 		long delay = READ_ONCE(engine->props.heartbeat_interval_ms);
 
@@ -121,7 +152,7 @@ static void heartbeat(struct work_struct *wrk)
 			 * but all other contexts, including the kernel
 			 * context are stuck waiting for the signal.
 			 */
-		} else if (engine->schedule &&
+		} else if (engine->sched_engine->schedule &&
 			   rq->sched.attr.priority < I915_PRIORITY_BARRIER) {
 			/*
 			 * Gradually raise the priority of the heartbeat to
@@ -136,16 +167,10 @@ static void heartbeat(struct work_struct *wrk)
 				attr.priority = I915_PRIORITY_BARRIER;
 
 			local_bh_disable();
-			engine->schedule(rq, &attr);
+			engine->sched_engine->schedule(rq, &attr);
 			local_bh_enable();
 		} else {
-			if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
-				show_heartbeat(rq, engine);
-
-			intel_gt_handle_error(engine->gt, engine->mask,
-					      I915_ERROR_CAPTURE,
-					      "stopped heartbeat on %s",
-					      engine->name);
+			reset_engine(engine, rq);
 		}
 
 		rq->emitted_jiffies = jiffies;
@@ -194,6 +219,25 @@ void intel_engine_park_heartbeat(struct intel_engine_cs *engine)
 		i915_request_put(fetch_and_zero(&engine->heartbeat.systole));
 }
 
+void intel_gt_unpark_heartbeats(struct intel_gt *gt)
+{
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	for_each_engine(engine, gt, id)
+		if (intel_engine_pm_is_awake(engine))
+			intel_engine_unpark_heartbeat(engine);
+}
+
+void intel_gt_park_heartbeats(struct intel_gt *gt)
+{
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	for_each_engine(engine, gt, id)
+		intel_engine_park_heartbeat(engine);
+}
+
 void intel_engine_init_heartbeat(struct intel_engine_cs *engine)
 {
 	INIT_DELAYED_WORK(&engine->heartbeat.work, heartbeat);