1 files changed, 100 insertions, 40 deletions

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 53f3ed3244d5..88e881b100cf 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -1352,6 +1352,16 @@ static ktime_t guc_engine_busyness(struct intel_engine_cs *engine, ktime_t *now)
 	return ns_to_ktime(total);
 }
 
+static void guc_enable_busyness_worker(struct intel_guc *guc)
+{
+	mod_delayed_work(system_highpri_wq, &guc->timestamp.work, guc->timestamp.ping_delay);
+}
+
+static void guc_cancel_busyness_worker(struct intel_guc *guc)
+{
+	cancel_delayed_work_sync(&guc->timestamp.work);
+}
+
 static void __reset_guc_busyness_stats(struct intel_guc *guc)
 {
 	struct intel_gt *gt = guc_to_gt(guc);
@@ -1360,7 +1370,7 @@ static void __reset_guc_busyness_stats(struct intel_guc *guc)
 	unsigned long flags;
 	ktime_t unused;
 
-	cancel_delayed_work_sync(&guc->timestamp.work);
+	guc_cancel_busyness_worker(guc);
 
 	spin_lock_irqsave(&guc->timestamp.lock, flags);
 
@@ -1416,8 +1426,7 @@ static void guc_timestamp_ping(struct work_struct *wrk)
 
 	intel_gt_reset_unlock(gt, srcu);
 
-	mod_delayed_work(system_highpri_wq, &guc->timestamp.work,
-			 guc->timestamp.ping_delay);
+	guc_enable_busyness_worker(guc);
 }
 
 static int guc_action_enable_usage_stats(struct intel_guc *guc)
@@ -1432,20 +1441,26 @@ static int guc_action_enable_usage_stats(struct intel_guc *guc)
 	return intel_guc_send(guc, action, ARRAY_SIZE(action));
 }
 
-static void guc_init_engine_stats(struct intel_guc *guc)
+static int guc_init_engine_stats(struct intel_guc *guc)
 {
 	struct intel_gt *gt = guc_to_gt(guc);
 	intel_wakeref_t wakeref;
+	int ret;
 
-	mod_delayed_work(system_highpri_wq, &guc->timestamp.work,
-			 guc->timestamp.ping_delay);
+	with_intel_runtime_pm(&gt->i915->runtime_pm, wakeref)
+		ret = guc_action_enable_usage_stats(guc);
 
-	with_intel_runtime_pm(&gt->i915->runtime_pm, wakeref) {
-		int ret = guc_action_enable_usage_stats(guc);
+	if (ret)
+		guc_err(guc, "Failed to enable usage stats: %pe\n", ERR_PTR(ret));
+	else
+		guc_enable_busyness_worker(guc);
 
-		if (ret)
-			guc_err(guc, "Failed to enable usage stats: %pe\n", ERR_PTR(ret));
-	}
+	return ret;
+}
+
+static void guc_fini_engine_stats(struct intel_guc *guc)
+{
+	guc_cancel_busyness_worker(guc);
 }
 
 void intel_guc_busyness_park(struct intel_gt *gt)
@@ -1460,7 +1475,7 @@ void intel_guc_busyness_park(struct intel_gt *gt)
 	 * and causes an unclaimed register access warning. Cancel the worker
 	 * synchronously here.
 	 */
-	cancel_delayed_work_sync(&guc->timestamp.work);
+	guc_cancel_busyness_worker(guc);
 
 	/*
 	 * Before parking, we should sample engine busyness stats if we need to.
@@ -1487,8 +1502,7 @@ void intel_guc_busyness_unpark(struct intel_gt *gt)
 	spin_lock_irqsave(&guc->timestamp.lock, flags);
 	guc_update_pm_timestamp(guc, &unused);
 	spin_unlock_irqrestore(&guc->timestamp.lock, flags);
-	mod_delayed_work(system_highpri_wq, &guc->timestamp.work,
-			 guc->timestamp.ping_delay);
+	guc_enable_busyness_worker(guc);
 }
 
 static inline bool
@@ -4102,9 +4116,11 @@ static void guc_set_default_submission(struct intel_engine_cs *engine)
 	engine->submit_request = guc_submit_request;
 }
 
-static inline void guc_kernel_context_pin(struct intel_guc *guc,
-					  struct intel_context *ce)
+static inline int guc_kernel_context_pin(struct intel_guc *guc,
+					 struct intel_context *ce)
 {
+	int ret;
+
 	/*
 	 * Note: we purposefully do not check the returns below because
 	 * the registration can only fail if a reset is just starting.
@@ -4112,16 +4128,24 @@ static inline void guc_kernel_context_pin(struct intel_guc *guc,
 	 * isn't happening and even it did this code would be run again.
 	 */
 
-	if (context_guc_id_invalid(ce))
-		pin_guc_id(guc, ce);
+	if (context_guc_id_invalid(ce)) {
+		ret = pin_guc_id(guc, ce);
+
+		if (ret < 0)
+			return ret;
+	}
 
 	if (!test_bit(CONTEXT_GUC_INIT, &ce->flags))
 		guc_context_init(ce);
 
-	try_context_registration(ce, true);
+	ret = try_context_registration(ce, true);
+	if (ret)
+		unpin_guc_id(guc, ce);
+
+	return ret;
 }
 
-static inline void guc_init_lrc_mapping(struct intel_guc *guc)
+static inline int guc_init_submission(struct intel_guc *guc)
 {
 	struct intel_gt *gt = guc_to_gt(guc);
 	struct intel_engine_cs *engine;
@@ -4148,9 +4172,17 @@ static inline void guc_init_lrc_mapping(struct intel_guc *guc)
 		struct intel_context *ce;
 
 		list_for_each_entry(ce, &engine->pinned_contexts_list,
-				    pinned_contexts_link)
-			guc_kernel_context_pin(guc, ce);
+				    pinned_contexts_link) {
+			int ret = guc_kernel_context_pin(guc, ce);
+
+			if (ret) {
+				/* No point in trying to clean up as i915 will wedge on failure */
+				return ret;
+			}
+		}
 	}
+
+	return 0;
 }
 
 static void guc_release(struct intel_engine_cs *engine)
@@ -4393,30 +4425,57 @@ static int guc_init_global_schedule_policy(struct intel_guc *guc)
 	return ret;
 }
 
-void intel_guc_submission_enable(struct intel_guc *guc)
+static void guc_route_semaphores(struct intel_guc *guc, bool to_guc)
 {
 	struct intel_gt *gt = guc_to_gt(guc);
+	u32 val;
 
-	/* Enable and route to GuC */
-	if (GRAPHICS_VER(gt->i915) >= 12)
-		intel_uncore_write(gt->uncore, GEN12_GUC_SEM_INTR_ENABLES,
-				   GUC_SEM_INTR_ROUTE_TO_GUC |
-				   GUC_SEM_INTR_ENABLE_ALL);
+	if (GRAPHICS_VER(gt->i915) < 12)
+		return;
+
+	if (to_guc)
+		val = GUC_SEM_INTR_ROUTE_TO_GUC | GUC_SEM_INTR_ENABLE_ALL;
+	else
+		val = 0;
 
-	guc_init_lrc_mapping(guc);
-	guc_init_engine_stats(guc);
-	guc_init_global_schedule_policy(guc);
+	intel_uncore_write(gt->uncore, GEN12_GUC_SEM_INTR_ENABLES, val);
 }
 
-void intel_guc_submission_disable(struct intel_guc *guc)
+int intel_guc_submission_enable(struct intel_guc *guc)
 {
-	struct intel_gt *gt = guc_to_gt(guc);
+	int ret;
+
+	/* Semaphore interrupt enable and route to GuC */
+	guc_route_semaphores(guc, true);
 
-	/* Note: By the time we're here, GuC may have already been reset */
+	ret = guc_init_submission(guc);
+	if (ret)
+		goto fail_sem;
+
+	ret = guc_init_engine_stats(guc);
+	if (ret)
+		goto fail_sem;
+
+	ret = guc_init_global_schedule_policy(guc);
+	if (ret)
+		goto fail_stats;
+
+	return 0;
+
+fail_stats:
+	guc_fini_engine_stats(guc);
+fail_sem:
+	guc_route_semaphores(guc, false);
+	return ret;
+}
+
+/* Note: By the time we're here, GuC may have already been reset */
+void intel_guc_submission_disable(struct intel_guc *guc)
+{
+	guc_cancel_busyness_worker(guc);
 
-	/* Disable and route to host */
-	if (GRAPHICS_VER(gt->i915) >= 12)
-		intel_uncore_write(gt->uncore, GEN12_GUC_SEM_INTR_ENABLES, 0x0);
+	/* Semaphore interrupt disable and route to host */
+	guc_route_semaphores(guc, false);
 }
 
 static bool __guc_submission_supported(struct intel_guc *guc)
@@ -4660,9 +4719,10 @@ static void guc_handle_context_reset(struct intel_guc *guc,
 {
 	trace_intel_context_reset(ce);
 
-	drm_dbg(&guc_to_gt(guc)->i915->drm, "Got GuC reset of 0x%04X, exiting = %d, banned = %d\n",
-		ce->guc_id.id, test_bit(CONTEXT_EXITING, &ce->flags),
-		test_bit(CONTEXT_BANNED, &ce->flags));
+	guc_dbg(guc, "Got context reset notification: 0x%04X on %s, exiting = %s, banned = %s\n",
+		ce->guc_id.id, ce->engine->name,
+		str_yes_no(intel_context_is_exiting(ce)),
+		str_yes_no(intel_context_is_banned(ce)));
 
 	if (likely(intel_context_is_schedulable(ce))) {
 		capture_error_state(guc, ce);