drm/i915: Reset GPU immediately if submission is disabled

If submission is disabled by the backend for any reason, reset the GPU
immediately in the heartbeat code as the backend can't be reenabled
until the GPU is reset.

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: John Harrison <John.C.Harrison@Intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210727002348.97202-10-matthew.brost@intel.com

1 files changed, 49 insertions, 13 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
index b6a305e6a974..0b16f19c384e 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
@@ -70,12 +70,30 @@ 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);
+
+	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 +120,11 @@ 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);
 
@@ -139,13 +162,7 @@ static void heartbeat(struct work_struct *wrk)
 			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 +211,25 @@ 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);