8 files changed, 90 insertions, 77 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index e94365b08f1e..2aa63ec521b8 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -528,7 +528,7 @@ retry:
 	return rq;
 }
 
-struct i915_request *intel_context_find_active_request(struct intel_context *ce)
+struct i915_request *intel_context_get_active_request(struct intel_context *ce)
 {
 	struct intel_context *parent = intel_context_to_parent(ce);
 	struct i915_request *rq, *active = NULL;
@@ -552,6 +552,8 @@ struct i915_request *intel_context_find_active_request(struct intel_context *ce)
 
 		active = rq;
 	}
+	if (active)
+		active = i915_request_get_rcu(active);
 	spin_unlock_irqrestore(&parent->guc_state.lock, flags);
 
 	return active;
diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h
index fb62b7b8cbcd..0a8d553da3f4 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.h
+++ b/drivers/gpu/drm/i915/gt/intel_context.h
@@ -268,8 +268,7 @@ 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);
+struct i915_request *intel_context_get_active_request(struct intel_context *ce);
 
 static inline bool intel_context_is_barrier(const struct intel_context *ce)
 {
diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index cbc8b857d5f7..7a4504ea35c3 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -248,8 +248,8 @@ void intel_engine_dump_active_requests(struct list_head *requests,
 ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine,
 				   ktime_t *now);
 
-struct i915_request *
-intel_engine_execlist_find_hung_request(struct intel_engine_cs *engine);
+void intel_engine_get_hung_entity(struct intel_engine_cs *engine,
+				  struct intel_context **ce, struct i915_request **rq);
 
 u32 intel_engine_context_size(struct intel_gt *gt, u8 class);
 struct intel_context *
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index c33e0d72d670..d37931e16fd9 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -2094,17 +2094,6 @@ static void print_request_ring(struct drm_printer *m, struct i915_request *rq)
 	}
 }
 
-static unsigned long list_count(struct list_head *list)
-{
-	struct list_head *pos;
-	unsigned long count = 0;
-
-	list_for_each(pos, list)
-		count++;
-
-	return count;
-}
-
 static unsigned long read_ul(void *p, size_t x)
 {
 	return *(unsigned long *)(p + x);
@@ -2196,11 +2185,11 @@ void intel_engine_dump_active_requests(struct list_head *requests,
 	}
 }
 
-static void engine_dump_active_requests(struct intel_engine_cs *engine, struct drm_printer *m)
+static void engine_dump_active_requests(struct intel_engine_cs *engine,
+					struct drm_printer *m)
 {
+	struct intel_context *hung_ce = NULL;
 	struct i915_request *hung_rq = NULL;
-	struct intel_context *ce;
-	bool guc;
 
 	/*
 	 * No need for an engine->irq_seqno_barrier() before the seqno reads.
@@ -2209,27 +2198,22 @@ static void engine_dump_active_requests(struct intel_engine_cs *engine, struct d
 	 * But the intention here is just to report an instantaneous snapshot
 	 * so that's fine.
 	 */
-	lockdep_assert_held(&engine->sched_engine->lock);
+	intel_engine_get_hung_entity(engine, &hung_ce, &hung_rq);
 
 	drm_printf(m, "\tRequests:\n");
 
-	guc = intel_uc_uses_guc_submission(&engine->gt->uc);
-	if (guc) {
-		ce = intel_engine_get_hung_context(engine);
-		if (ce)
-			hung_rq = intel_context_find_active_request(ce);
-	} else {
-		hung_rq = intel_engine_execlist_find_hung_request(engine);
-	}
-
 	if (hung_rq)
 		engine_dump_request(hung_rq, m, "\t\thung");
+	else if (hung_ce)
+		drm_printf(m, "\t\tGot hung ce but no hung rq!\n");
 
-	if (guc)
+	if (intel_uc_uses_guc_submission(&engine->gt->uc))
 		intel_guc_dump_active_requests(engine, hung_rq, m);
 	else
-		intel_engine_dump_active_requests(&engine->sched_engine->requests,
-						  hung_rq, m);
+		intel_execlists_dump_active_requests(engine, hung_rq, m);
+
+	if (hung_rq)
+		i915_request_put(hung_rq);
 }
 
 void intel_engine_dump(struct intel_engine_cs *engine,
@@ -2239,7 +2223,6 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 	struct i915_gpu_error * const error = &engine->i915->gpu_error;
 	struct i915_request *rq;
 	intel_wakeref_t wakeref;
-	unsigned long flags;
 	ktime_t dummy;
 
 	if (header) {
@@ -2276,13 +2259,8 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 		   i915_reset_count(error));
 	print_properties(engine, m);
 
-	spin_lock_irqsave(&engine->sched_engine->lock, flags);
 	engine_dump_active_requests(engine, m);
 
-	drm_printf(m, "\tOn hold?: %lu\n",
-		   list_count(&engine->sched_engine->hold));
-	spin_unlock_irqrestore(&engine->sched_engine->lock, flags);
-
 	drm_printf(m, "\tMMIO base:  0x%08x\n", engine->mmio_base);
 	wakeref = intel_runtime_pm_get_if_in_use(engine->uncore->rpm);
 	if (wakeref) {
@@ -2328,8 +2306,7 @@ intel_engine_create_virtual(struct intel_engine_cs **siblings,
 	return siblings[0]->cops->create_virtual(siblings, count, flags);
 }
 
-struct i915_request *
-intel_engine_execlist_find_hung_request(struct intel_engine_cs *engine)
+static struct i915_request *engine_execlist_find_hung_request(struct intel_engine_cs *engine)
 {
 	struct i915_request *request, *active = NULL;
 
@@ -2381,6 +2358,33 @@ intel_engine_execlist_find_hung_request(struct intel_engine_cs *engine)
 	return active;
 }
 
+void intel_engine_get_hung_entity(struct intel_engine_cs *engine,
+				  struct intel_context **ce, struct i915_request **rq)
+{
+	unsigned long flags;
+
+	*ce = intel_engine_get_hung_context(engine);
+	if (*ce) {
+		intel_engine_clear_hung_context(engine);
+
+		*rq = intel_context_get_active_request(*ce);
+		return;
+	}
+
+	/*
+	 * 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))
+		return;
+
+	spin_lock_irqsave(&engine->sched_engine->lock, flags);
+	*rq = engine_execlist_find_hung_request(engine);
+	if (*rq)
+		*rq = i915_request_get_rcu(*rq);
+	spin_unlock_irqrestore(&engine->sched_engine->lock, flags);
+}
+
 void xehp_enable_ccs_engines(struct intel_engine_cs *engine)
 {
 	/*
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index 2daffa7c7dfd..21cb5b69d82e 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -4148,6 +4148,33 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine,
 	spin_unlock_irqrestore(&sched_engine->lock, flags);
 }
 
+static unsigned long list_count(struct list_head *list)
+{
+	struct list_head *pos;
+	unsigned long count = 0;
+
+	list_for_each(pos, list)
+		count++;
+
+	return count;
+}
+
+void intel_execlists_dump_active_requests(struct intel_engine_cs *engine,
+					  struct i915_request *hung_rq,
+					  struct drm_printer *m)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&engine->sched_engine->lock, flags);
+
+	intel_engine_dump_active_requests(&engine->sched_engine->requests, hung_rq, m);
+
+	drm_printf(m, "\tOn hold?: %lu\n",
+		   list_count(&engine->sched_engine->hold));
+
+	spin_unlock_irqrestore(&engine->sched_engine->lock, flags);
+}
+
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftest_execlists.c"
 #endif
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.h b/drivers/gpu/drm/i915/gt/intel_execlists_submission.h
index a1aa92c983a5..d2c7d45ea062 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.h
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.h
@@ -32,6 +32,10 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine,
 							int indent),
 				   unsigned int max);
 
+void intel_execlists_dump_active_requests(struct intel_engine_cs *engine,
+					  struct i915_request *hung_rq,
+					  struct drm_printer *m);
+
 bool
 intel_engine_in_execlists_submission_mode(const struct intel_engine_cs *engine);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 7771a19008c6..bbeeb6dde7ae 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -288,39 +288,6 @@ static const u8 dg2_xcs_offsets[] = {
 	END
 };
 
-static const u8 mtl_xcs_offsets[] = {
-	NOP(1),
-	LRI(13, POSTED),
-	REG16(0x244),
-	REG(0x034),
-	REG(0x030),
-	REG(0x038),
-	REG(0x03c),
-	REG(0x168),
-	REG(0x140),
-	REG(0x110),
-	REG(0x1c0),
-	REG(0x1c4),
-	REG(0x1c8),
-	REG(0x180),
-	REG16(0x2b4),
-	NOP(4),
-
-	NOP(1),
-	LRI(9, POSTED),
-	REG16(0x3a8),
-	REG16(0x28c),
-	REG16(0x288),
-	REG16(0x284),
-	REG16(0x280),
-	REG16(0x27c),
-	REG16(0x278),
-	REG16(0x274),
-	REG16(0x270),
-
-	END
-};
-
 static const u8 gen8_rcs_offsets[] = {
 	NOP(1),
 	LRI(14, POSTED),
@@ -739,9 +706,7 @@ static const u8 *reg_offsets(const struct intel_engine_cs *engine)
 		else
 			return gen8_rcs_offsets;
 	} else {
-		if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 70))
-			return mtl_xcs_offsets;
-		else if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 55))
+		if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 55))
 			return dg2_xcs_offsets;
 		else if (GRAPHICS_VER(engine->i915) >= 12)
 			return gen12_xcs_offsets;
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 0a42f1807f52..c10977cb06b9 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -1702,7 +1702,7 @@ static void __guc_reset_context(struct intel_context *ce, intel_engine_mask_t st
 			goto next_context;
 
 		guilty = false;
-		rq = intel_context_find_active_request(ce);
+		rq = intel_context_get_active_request(ce);
 		if (!rq) {
 			head = ce->ring->tail;
 			goto out_replay;
@@ -1715,6 +1715,7 @@ static void __guc_reset_context(struct intel_context *ce, intel_engine_mask_t st
 		head = intel_ring_wrap(ce->ring, rq->head);
 
 		__i915_request_reset(rq, guilty);
+		i915_request_put(rq);
 out_replay:
 		guc_reset_state(ce, head, guilty);
 next_context:
@@ -4817,6 +4818,8 @@ void intel_guc_find_hung_context(struct intel_engine_cs *engine)
 
 	xa_lock_irqsave(&guc->context_lookup, flags);
 	xa_for_each(&guc->context_lookup, index, ce) {
+		bool found;
+
 		if (!kref_get_unless_zero(&ce->ref))
 			continue;
 
@@ -4833,10 +4836,18 @@ void intel_guc_find_hung_context(struct intel_engine_cs *engine)
 				goto next;
 		}
 
+		found = false;
+		spin_lock(&ce->guc_state.lock);
 		list_for_each_entry(rq, &ce->guc_state.requests, sched.link) {
 			if (i915_test_request_state(rq) != I915_REQUEST_ACTIVE)
 				continue;
 
+			found = true;
+			break;
+		}
+		spin_unlock(&ce->guc_state.lock);
+
+		if (found) {
 			intel_engine_set_hung_context(engine, ce);
 
 			/* Can only cope with one hang at a time... */
@@ -4844,6 +4855,7 @@ void intel_guc_find_hung_context(struct intel_engine_cs *engine)
 			xa_lock(&guc->context_lookup);
 			goto done;
 		}
+
 next:
 		intel_context_put(ce);
 		xa_lock(&guc->context_lookup);