7 files changed, 91 insertions, 26 deletions
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index 0bf4a13e9759..237b70e98744 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -509,6 +509,26 @@ retry:
 	return rq;
 }
 
+struct i915_request *intel_context_find_active_request(struct intel_context *ce)
+{
+	struct i915_request *rq, *active = NULL;
+	unsigned long flags;
+
+	GEM_BUG_ON(!intel_engine_uses_guc(ce->engine));
+
+	spin_lock_irqsave(&ce->guc_active.lock, flags);
+	list_for_each_entry_reverse(rq, &ce->guc_active.requests,
+				    sched.link) {
+		if (i915_request_completed(rq))
+			break;
+
+		active = rq;
+	}
+	spin_unlock_irqrestore(&ce->guc_active.lock, flags);
+
+	return active;
+}
+
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftest_context.c"
 #endif
diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h
index 974ef85320c2..2ed9bf5f91a5 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.h
+++ b/drivers/gpu/drm/i915/gt/intel_context.h
@@ -200,6 +200,9 @@ int intel_context_prepare_remote_request(struct intel_context *ce,
 
 struct i915_request *intel_context_create_request(struct intel_context *ce);
 
+struct i915_request *
+intel_context_find_active_request(struct intel_context *ce);
+
 static inline bool intel_context_is_barrier(const struct intel_context *ce)
 {
 	return test_bit(CONTEXT_BARRIER_BIT, &ce->flags);
diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index 8fc76dc8bf98..1db2d3efc71f 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -245,7 +245,7 @@ ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine,
 				   ktime_t *now);
 
 struct i915_request *
-intel_engine_find_active_request(struct intel_engine_cs *engine);
+intel_engine_execlist_find_hung_request(struct intel_engine_cs *engine);
 
 u32 intel_engine_context_size(struct intel_gt *gt, u8 class);
 struct intel_context *
@@ -313,4 +313,23 @@ intel_engine_get_sibling(struct intel_engine_cs *engine, unsigned int sibling)
 	return engine->cops->get_sibling(engine, sibling);
 }
 
+static inline void
+intel_engine_set_hung_context(struct intel_engine_cs *engine,
+			      struct intel_context *ce)
+{
+	engine->hung_ce = ce;
+}
+
+static inline void
+intel_engine_clear_hung_context(struct intel_engine_cs *engine)
+{
+	intel_engine_set_hung_context(engine, NULL);
+}
+
+static inline struct intel_context *
+intel_engine_get_hung_context(struct intel_engine_cs *engine)
+{
+	return engine->hung_ce;
+}
+
 #endif /* _INTEL_RINGBUFFER_H_ */
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 1eaa658507e1..0da7868c5a13 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1731,7 +1731,7 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 	drm_printf(m, "\tRequests:\n");
 
 	spin_lock_irqsave(&engine->sched_engine->lock, flags);
-	rq = intel_engine_find_active_request(engine);
+	rq = intel_engine_execlist_find_hung_request(engine);
 	if (rq) {
 		struct intel_timeline *tl = get_timeline(rq);
 
@@ -1842,11 +1842,18 @@ static bool match_ring(struct i915_request *rq)
 }
 
 struct i915_request *
-intel_engine_find_active_request(struct intel_engine_cs *engine)
+intel_engine_execlist_find_hung_request(struct intel_engine_cs *engine)
 {
 	struct i915_request *request, *active = NULL;
 
 	/*
+	 * This search does not work in GuC submission mode. However, the GuC
+	 * will report the hanging context directly to the driver itself. So
+	 * the driver should never get here when in GuC mode.
+	 */
+	GEM_BUG_ON(intel_uc_uses_guc_submission(&engine->gt->uc));
+
+	/*
 	 * We are called by the error capture, reset and to dump engine
 	 * state at random points in time. In particular, note that neither is
 	 * crucially ordered with an interrupt. After a hang, the GPU is dead
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 1c7e2724cdae..260cce15cb62 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -298,6 +298,8 @@ struct intel_engine_cs {
 	/* keep a request in reserve for a [pm] barrier under oom */
 	struct i915_request *request_pool;
 
+	struct intel_context *hung_ce;
+
 	struct llist_head barrier_tasks;
 
 	struct intel_context *kernel_context; /* pinned */
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index d76494e3e271..7d6ca0d54f9e 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -726,24 +726,6 @@ __unwind_incomplete_requests(struct intel_context *ce)
 	spin_unlock_irqrestore(&sched_engine->lock, flags);
 }
 
-static struct i915_request *context_find_active_request(struct intel_context *ce)
-{
-	struct i915_request *rq, *active = NULL;
-	unsigned long flags;
-
-	spin_lock_irqsave(&ce->guc_active.lock, flags);
-	list_for_each_entry_reverse(rq, &ce->guc_active.requests,
-				    sched.link) {
-		if (i915_request_completed(rq))
-			break;
-
-		active = rq;
-	}
-	spin_unlock_irqrestore(&ce->guc_active.lock, flags);
-
-	return active;
-}
-
 static void __guc_reset_context(struct intel_context *ce, bool stalled)
 {
 	struct i915_request *rq;
@@ -757,7 +739,7 @@ static void __guc_reset_context(struct intel_context *ce, bool stalled)
 	 */
 	clr_context_enabled(ce);
 
-	rq = context_find_active_request(ce);
+	rq = intel_context_find_active_request(ce);
 	if (!rq) {
 		head = ce->ring->tail;
 		stalled = false;
@@ -2201,6 +2183,20 @@ int intel_guc_sched_done_process_msg(struct intel_guc *guc,
 	return 0;
 }
 
+static void capture_error_state(struct intel_guc *guc,
+				struct intel_context *ce)
+{
+	struct intel_gt *gt = guc_to_gt(guc);
+	struct drm_i915_private *i915 = gt->i915;
+	struct intel_engine_cs *engine = __context_to_physical_engine(ce);
+	intel_wakeref_t wakeref;
+
+	intel_engine_set_hung_context(engine, ce);
+	with_intel_runtime_pm(&i915->runtime_pm, wakeref)
+		i915_capture_error_state(gt, engine->mask);
+	atomic_inc(&i915->gpu_error.reset_engine_count[engine->uabi_class]);
+}
+
 static void guc_context_replay(struct intel_context *ce)
 {
 	struct i915_sched_engine *sched_engine = ce->engine->sched_engine;
@@ -2213,6 +2209,7 @@ static void guc_handle_context_reset(struct intel_guc *guc,
 				     struct intel_context *ce)
 {
 	trace_intel_context_reset(ce);
+	capture_error_state(guc, ce);
 	guc_context_replay(ce);
 }
 
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index a2c58b54a592..0f08bcfbe964 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1429,20 +1429,37 @@ capture_engine(struct intel_engine_cs *engine,
 {
 	struct intel_engine_capture_vma *capture = NULL;
 	struct intel_engine_coredump *ee;
-	struct i915_request *rq;
+	struct intel_context *ce;
+	struct i915_request *rq = NULL;
 	unsigned long flags;
 
 	ee = intel_engine_coredump_alloc(engine, GFP_KERNEL);
 	if (!ee)
 		return NULL;
 
-	spin_lock_irqsave(&engine->sched_engine->lock, flags);
-	rq = intel_engine_find_active_request(engine);
+	ce = intel_engine_get_hung_context(engine);
+	if (ce) {
+		intel_engine_clear_hung_context(engine);
+		rq = intel_context_find_active_request(ce);
+		if (!rq || !i915_request_started(rq))
+			goto no_request_capture;
+	} else {
+		/*
+		 * Getting here with GuC enabled means it is a forced error capture
+		 * with no actual hang. So, no need to attempt the execlist search.
+		 */
+		if (!intel_uc_uses_guc_submission(&engine->gt->uc)) {
+			spin_lock_irqsave(&engine->sched_engine->lock, flags);
+			rq = intel_engine_execlist_find_hung_request(engine);
+			spin_unlock_irqrestore(&engine->sched_engine->lock,
+					       flags);
+		}
+	}
 	if (rq)
 		capture = intel_engine_coredump_add_request(ee, rq,
 							    ATOMIC_MAYFAIL);
-	spin_unlock_irqrestore(&engine->sched_engine->lock, flags);
 	if (!capture) {
+no_request_capture:
 		kfree(ee);
 		return NULL;
 	}