7 files changed, 189 insertions, 9 deletions

diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index 50710e3..6b132ca 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -197,6 +197,9 @@ static int lowlevel_hole(struct drm_i915_private *i915,
 {
 	I915_RND_STATE(seed_prng);
 	unsigned int size;
+	struct i915_vma mock_vma;
+
+	memset(&mock_vma, 0, sizeof(struct i915_vma));
 
 	/* Keep creating larger objects until one cannot fit into the hole */
 	for (size = 12; (hole_end - hole_start) >> size; size++) {
@@ -255,8 +258,11 @@ static int lowlevel_hole(struct drm_i915_private *i915,
 			    vm->allocate_va_range(vm, addr, BIT_ULL(size)))
 				break;
 
-			vm->insert_entries(vm, obj->mm.pages, addr,
-					   I915_CACHE_NONE, 0);
+			mock_vma.pages = obj->mm.pages;
+			mock_vma.node.size = BIT_ULL(size);
+			mock_vma.node.start = addr;
+
+			vm->insert_entries(vm, &mock_vma, I915_CACHE_NONE, 0);
 		}
 		count = n;
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_vma.c b/drivers/gpu/drm/i915/selftests/i915_vma.c
index fb9072d..2e86ec1 100644
--- a/drivers/gpu/drm/i915/selftests/i915_vma.c
+++ b/drivers/gpu/drm/i915/selftests/i915_vma.c
@@ -186,16 +186,20 @@ static int igt_vma_create(void *arg)
 				goto end;
 		}
 
-		list_for_each_entry_safe(ctx, cn, &contexts, link)
+		list_for_each_entry_safe(ctx, cn, &contexts, link) {
+			list_del_init(&ctx->link);
 			mock_context_close(ctx);
+		}
 	}
 
 end:
 	/* Final pass to lookup all created contexts */
 	err = create_vmas(i915, &objects, &contexts);
 out:
-	list_for_each_entry_safe(ctx, cn, &contexts, link)
+	list_for_each_entry_safe(ctx, cn, &contexts, link) {
+		list_del_init(&ctx->link);
 		mock_context_close(ctx);
+	}
 
 	list_for_each_entry_safe(obj, on, &objects, st_link)
 		i915_gem_object_put(obj);
diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
index aa31d6c..7096c39 100644
--- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
@@ -316,6 +316,56 @@ static int igt_global_reset(void *arg)
 
 	GEM_BUG_ON(test_bit(I915_RESET_HANDOFF, &i915->gpu_error.flags));
 	clear_bit(I915_RESET_BACKOFF, &i915->gpu_error.flags);
+	wake_up_all(&i915->gpu_error.reset_queue);
+
+	if (i915_terminally_wedged(&i915->gpu_error))
+		err = -EIO;
+
+	return err;
+}
+
+static int igt_reset_engine(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	unsigned int reset_count, reset_engine_count;
+	int err = 0;
+
+	/* Check that we can issue a global GPU and engine reset */
+
+	if (!intel_has_reset_engine(i915))
+		return 0;
+
+	for_each_engine(engine, i915, id) {
+		set_bit(I915_RESET_ENGINE + engine->id, &i915->gpu_error.flags);
+		reset_count = i915_reset_count(&i915->gpu_error);
+		reset_engine_count = i915_reset_engine_count(&i915->gpu_error,
+							     engine);
+
+		err = i915_reset_engine(engine);
+		if (err) {
+			pr_err("i915_reset_engine failed\n");
+			break;
+		}
+
+		if (i915_reset_count(&i915->gpu_error) != reset_count) {
+			pr_err("Full GPU reset recorded! (engine reset expected)\n");
+			err = -EINVAL;
+			break;
+		}
+
+		if (i915_reset_engine_count(&i915->gpu_error, engine) ==
+		    reset_engine_count) {
+			pr_err("No %s engine reset recorded!\n", engine->name);
+			err = -EINVAL;
+			break;
+		}
+
+		clear_bit(I915_RESET_ENGINE + engine->id,
+			  &i915->gpu_error.flags);
+	}
+
 	if (i915_terminally_wedged(&i915->gpu_error))
 		err = -EIO;
 
@@ -404,6 +454,7 @@ fini:
 unlock:
 	mutex_unlock(&i915->drm.struct_mutex);
 	clear_bit(I915_RESET_BACKOFF, &i915->gpu_error.flags);
+	wake_up_all(&i915->gpu_error.reset_queue);
 
 	if (i915_terminally_wedged(&i915->gpu_error))
 		return -EIO;
@@ -519,11 +570,117 @@ fini:
 unlock:
 	mutex_unlock(&i915->drm.struct_mutex);
 	clear_bit(I915_RESET_BACKOFF, &i915->gpu_error.flags);
+	wake_up_all(&i915->gpu_error.reset_queue);
+
+	if (i915_terminally_wedged(&i915->gpu_error))
+		return -EIO;
+
+	return err;
+}
+
+static int igt_render_engine_reset_fallback(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct intel_engine_cs *engine = i915->engine[RCS];
+	struct hang h;
+	struct drm_i915_gem_request *rq;
+	unsigned int reset_count, reset_engine_count;
+	int err = 0;
+
+	/* Check that we can issue a global GPU and engine reset */
+
+	if (!intel_has_reset_engine(i915))
+		return 0;
+
+	set_bit(I915_RESET_BACKOFF, &i915->gpu_error.flags);
+	mutex_lock(&i915->drm.struct_mutex);
+
+	err = hang_init(&h, i915);
+	if (err)
+		goto err_unlock;
+
+	rq = hang_create_request(&h, engine, i915->kernel_context);
+	if (IS_ERR(rq)) {
+		err = PTR_ERR(rq);
+		goto err_fini;
+	}
+
+	i915_gem_request_get(rq);
+	__i915_add_request(rq, true);
+
+	/* make reset engine fail */
+	rq->fence.error = -EIO;
+
+	if (!wait_for_hang(&h, rq)) {
+		pr_err("Failed to start request %x\n", rq->fence.seqno);
+		err = -EIO;
+		goto err_request;
+	}
+
+	reset_engine_count = i915_reset_engine_count(&i915->gpu_error, engine);
+	reset_count = fake_hangcheck(rq);
+
+	/* unlock since we'll call handle_error */
+	mutex_unlock(&i915->drm.struct_mutex);
+	clear_bit(I915_RESET_BACKOFF, &i915->gpu_error.flags);
+	wake_up_all(&i915->gpu_error.reset_queue);
+
+	i915_handle_error(i915, intel_engine_flag(engine), "live test");
+
+	if (i915_reset_engine_count(&i915->gpu_error, engine) !=
+	    reset_engine_count) {
+		pr_err("render engine reset recorded! (full reset expected)\n");
+		err = -EINVAL;
+		goto out_rq;
+	}
+
+	if (i915_reset_count(&i915->gpu_error) == reset_count) {
+		pr_err("No full GPU reset recorded!\n");
+		err = -EINVAL;
+		goto out_rq;
+	}
+
+	/*
+	 * by using fence.error = -EIO, full reset sets the wedged flag, do one
+	 * more full reset to re-enable the hw.
+	 */
+	if (i915_terminally_wedged(&i915->gpu_error)) {
+		set_bit(I915_RESET_BACKOFF, &i915->gpu_error.flags);
+		rq->fence.error = 0;
+
+		mutex_lock(&i915->drm.struct_mutex);
+		set_bit(I915_RESET_HANDOFF, &i915->gpu_error.flags);
+		i915_reset(i915);
+		GEM_BUG_ON(test_bit(I915_RESET_HANDOFF,
+				    &i915->gpu_error.flags));
+		mutex_unlock(&i915->drm.struct_mutex);
+
+		if (i915_reset_count(&i915->gpu_error) == reset_count) {
+			pr_err("No full GPU reset recorded!\n");
+			err = -EINVAL;
+			goto out_rq;
+		}
+	}
+
+out_rq:
+	i915_gem_request_put(rq);
+	hang_fini(&h);
+out_backoff:
+	clear_bit(I915_RESET_BACKOFF, &i915->gpu_error.flags);
+	wake_up_all(&i915->gpu_error.reset_queue);
 
 	if (i915_terminally_wedged(&i915->gpu_error))
 		return -EIO;
 
 	return err;
+
+err_request:
+	i915_gem_request_put(rq);
+err_fini:
+	hang_fini(&h);
+err_unlock:
+	mutex_unlock(&i915->drm.struct_mutex);
+	goto out_backoff;
 }
 
 int intel_hangcheck_live_selftests(struct drm_i915_private *i915)
@@ -531,8 +688,10 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915)
 	static const struct i915_subtest tests[] = {
 		SUBTEST(igt_hang_sanitycheck),
 		SUBTEST(igt_global_reset),
+		SUBTEST(igt_reset_engine),
 		SUBTEST(igt_wait_reset),
 		SUBTEST(igt_reset_queue),
+		SUBTEST(igt_render_engine_reset_fallback),
 	};
 
 	if (!intel_has_gpu_reset(i915))
diff --git a/drivers/gpu/drm/i915/selftests/mock_context.c b/drivers/gpu/drm/i915/selftests/mock_context.c
index f8b9cc2..9c7c681 100644
--- a/drivers/gpu/drm/i915/selftests/mock_context.c
+++ b/drivers/gpu/drm/i915/selftests/mock_context.c
@@ -48,7 +48,7 @@ mock_context(struct drm_i915_private *i915,
 	if (!ctx->vma_lut.ht)
 		goto err_free;
 
-	ret = ida_simple_get(&i915->context_hw_ida,
+	ret = ida_simple_get(&i915->contexts.hw_ida,
 			     0, MAX_CONTEXT_HW_ID, GFP_KERNEL);
 	if (ret < 0)
 		goto err_vma_ht;
@@ -86,3 +86,12 @@ void mock_context_close(struct i915_gem_context *ctx)
 
 	i915_gem_context_put(ctx);
 }
+
+void mock_init_contexts(struct drm_i915_private *i915)
+{
+	INIT_LIST_HEAD(&i915->contexts.list);
+	ida_init(&i915->contexts.hw_ida);
+
+	INIT_WORK(&i915->contexts.free_work, contexts_free_worker);
+	init_llist_head(&i915->contexts.free_list);
+}
diff --git a/drivers/gpu/drm/i915/selftests/mock_context.h b/drivers/gpu/drm/i915/selftests/mock_context.h
index 2427e5c..383941a 100644
--- a/drivers/gpu/drm/i915/selftests/mock_context.h
+++ b/drivers/gpu/drm/i915/selftests/mock_context.h
@@ -25,6 +25,8 @@
 #ifndef __MOCK_CONTEXT_H
 #define __MOCK_CONTEXT_H
 
+void mock_init_contexts(struct drm_i915_private *i915);
+
 struct i915_gem_context *
 mock_context(struct drm_i915_private *i915,
 	     const char *name);
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index 627e2aa..47613d2 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -57,11 +57,12 @@ static void mock_device_release(struct drm_device *dev)
 
 	cancel_delayed_work_sync(&i915->gt.retire_work);
 	cancel_delayed_work_sync(&i915->gt.idle_work);
+	flush_workqueue(i915->wq);
 
 	mutex_lock(&i915->drm.struct_mutex);
 	for_each_engine(engine, i915, id)
 		mock_engine_free(engine);
-	i915_gem_context_fini(i915);
+	i915_gem_contexts_fini(i915);
 	mutex_unlock(&i915->drm.struct_mutex);
 
 	drain_workqueue(i915->wq);
@@ -160,7 +161,7 @@ struct drm_i915_private *mock_gem_device(void)
 	INIT_LIST_HEAD(&i915->mm.unbound_list);
 	INIT_LIST_HEAD(&i915->mm.bound_list);
 
-	ida_init(&i915->context_hw_ida);
+	mock_init_contexts(i915);
 
 	INIT_DELAYED_WORK(&i915->gt.retire_work, mock_retire_work_handler);
 	INIT_DELAYED_WORK(&i915->gt.idle_work, mock_idle_work_handler);
diff --git a/drivers/gpu/drm/i915/selftests/mock_gtt.c b/drivers/gpu/drm/i915/selftests/mock_gtt.c
index a61309c..f2118cf 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gtt.c
@@ -33,8 +33,7 @@ static void mock_insert_page(struct i915_address_space *vm,
 }
 
 static void mock_insert_entries(struct i915_address_space *vm,
-				struct sg_table *st,
-				u64 start,
+				struct i915_vma *vma,
 				enum i915_cache_level level, u32 flags)
 {
 }