Backported amdgpu ttm deadlock fixes for 4.14

index 180ce6296416..bee77d31895b 100644
@@ -440,28 +440,29 @@ static void ttm_bo_cleanup_refs_or_queue(struct ttm_buffer_object *bo)
 	struct ttm_bo_global *glob = bo->glob;
 	int ret;
 
+	ret = ttm_bo_individualize_resv(bo);
+	if (ret) {
+		/* Last resort, if we fail to allocate memory for the
+		 * fences block for the BO to become idle
+		 */
+		reservation_object_wait_timeout_rcu(bo->resv, true, false,
+						    30 * HZ);
+		spin_lock(&glob->lru_lock);
+		goto error;
+	}
+
 	spin_lock(&glob->lru_lock);
 	ret = __ttm_bo_reserve(bo, false, true, NULL);
-
 	if (!ret) {
-		if (!ttm_bo_wait(bo, false, true)) {
+		if (reservation_object_test_signaled_rcu(&bo->ttm_resv, true)) {
 			ttm_bo_del_from_lru(bo);
 			spin_unlock(&glob->lru_lock);
+			if (bo->resv != &bo->ttm_resv)
+				reservation_object_unlock(&bo->ttm_resv);
 			ttm_bo_cleanup_memtype_use(bo);
-
 			return;
 		}
 
-		ret = ttm_bo_individualize_resv(bo);
-		if (ret) {
-			/* Last resort, if we fail to allocate memory for the
-			 * fences block for the BO to become idle and free it.
-			 */
-			spin_unlock(&glob->lru_lock);
-			ttm_bo_wait(bo, true, true);
-			ttm_bo_cleanup_memtype_use(bo);
-			return;
-		}
 		ttm_bo_flush_all_fences(bo);
 
 		/*

@@ -474,11 +475,12 @@ static void ttm_bo_cleanup_refs_or_queue(struct ttm_buffer_object *bo)
 			ttm_bo_add_to_lru(bo);
 		}
 
-		if (bo->resv != &bo->ttm_resv)
-			reservation_object_unlock(&bo->ttm_resv);
 		__ttm_bo_unreserve(bo);
 	}
+	if (bo->resv != &bo->ttm_resv)
+		reservation_object_unlock(&bo->ttm_resv);
 
+error:
 	kref_get(&bo->list_kref);
 	list_add_tail(&bo->ddestroy, &bdev->ddestroy);
 	spin_unlock(&glob->lru_lock);

index dec3a815455d..b44d9d7db347 100644
@@ -266,8 +266,7 @@ EXPORT_SYMBOL(reservation_object_add_excl_fence);
 * @dst: the destination reservation object
 * @src: the source reservation object
 *
-* Copy all fences from src to dst. Both src->lock as well as dst-lock must be
-* held.
+* Copy all fences from src to dst. dst-lock must be held.
 */
 int reservation_object_copy_fences(struct reservation_object *dst,
 				   struct reservation_object *src)

@@ -277,33 +276,62 @@ int reservation_object_copy_fences(struct reservation_object *dst,
 	size_t size;
 	unsigned i;
 
-	src_list = reservation_object_get_list(src);
+	rcu_read_lock();
+	src_list = rcu_dereference(src->fence);
 
+retry:
 	if (src_list) {
-		size = offsetof(typeof(*src_list),
-				shared[src_list->shared_count]);
+		unsigned shared_count = src_list->shared_count;
+
+		size = offsetof(typeof(*src_list), shared[shared_count]);
+		rcu_read_unlock();
+
 		dst_list = kmalloc(size, GFP_KERNEL);
 		if (!dst_list)
 			return -ENOMEM;
 
-		dst_list->shared_count = src_list->shared_count;
-		dst_list->shared_max = src_list->shared_count;
-		for (i = 0; i < src_list->shared_count; ++i)
-			dst_list->shared[i] =
-				dma_fence_get(src_list->shared[i]);
+		rcu_read_lock();
+		src_list = rcu_dereference(src->fence);
+		if (!src_list || src_list->shared_count > shared_count) {
+			kfree(dst_list);
+			goto retry;
+		}
+
+		dst_list->shared_count = 0;
+		dst_list->shared_max = shared_count;
+		for (i = 0; i < src_list->shared_count; ++i) {
+			struct dma_fence *fence;
+
+			fence = rcu_dereference(src_list->shared[i]);
+			if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT,
+				     &fence->flags))
+				continue;
+
+			if (!dma_fence_get_rcu(fence)) {
+				kfree(dst_list);
+				src_list = rcu_dereference(src->fence);
+				goto retry;
+			}
+
+			if (dma_fence_is_signaled(fence)) {
+				dma_fence_put(fence);
+				continue;
+			}
+
+			dst_list->shared[dst_list->shared_count++] = fence;
+		}
 	} else {
 		dst_list = NULL;
 	}
 
+	new = dma_fence_get_rcu_safe(&src->fence_excl);
+	rcu_read_unlock();
+
 	kfree(dst->staged);
 	dst->staged = NULL;
 
 	src_list = reservation_object_get_list(dst);
-
 	old = reservation_object_get_excl(dst);
-	new = reservation_object_get_excl(src);
-
-	dma_fence_get(new);
 
 	preempt_disable();
 	write_seqcount_begin(&dst->seq);

index bd20ff018512..591c6dc2c1f7 100644
@@ -2586,7 +2586,8 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 {
 	struct amdgpu_bo_va_mapping *mapping, *tmp;
 	bool prt_fini_needed = !!adev->gart.gart_funcs->set_prt;
-	int i;
+	struct amdgpu_bo *root;
+	int i, r;
 
 	amd_sched_entity_fini(vm->entity.sched, &vm->entity);
 

@@ -2609,7 +2610,15 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 		amdgpu_vm_free_mapping(adev, vm, mapping, NULL);
 	}
 
-	amdgpu_vm_free_levels(&vm->root);
+	root = amdgpu_bo_ref(vm->root.bo);
+	r = amdgpu_bo_reserve(root, true);
+	if (r) {
+		dev_err(adev->dev, "Leaking page tables because BO reservation failed\n");
+	} else {
+		amdgpu_vm_free_levels(&vm->root);
+		amdgpu_bo_unreserve(root);
+	}
+	amdgpu_bo_unref(&root);
 	dma_fence_put(vm->last_dir_update);
 	for (i = 0; i < AMDGPU_MAX_VMHUBS; i++)
 		amdgpu_vm_free_reserved_vmid(adev, vm, i);

index bee77d31895b..c088703777e2 100644
@@ -150,8 +150,7 @@ static void ttm_bo_release_list(struct kref *list_kref)
 	ttm_tt_destroy(bo->ttm);
 	atomic_dec(&bo->glob->bo_count);
 	dma_fence_put(bo->moving);
-	if (bo->resv == &bo->ttm_resv)
-		reservation_object_fini(&bo->ttm_resv);
+	reservation_object_fini(&bo->ttm_resv);
 	mutex_destroy(&bo->wu_mutex);
 	if (bo->destroy)
 		bo->destroy(bo);

@@ -402,14 +401,11 @@ static int ttm_bo_individualize_resv(struct ttm_buffer_object *bo)
 	if (bo->resv == &bo->ttm_resv)
 		return 0;
 
-	reservation_object_init(&bo->ttm_resv);
 	BUG_ON(!reservation_object_trylock(&bo->ttm_resv));
 
 	r = reservation_object_copy_fences(&bo->ttm_resv, bo->resv);
-	if (r) {
+	if (r)
 		reservation_object_unlock(&bo->ttm_resv);
-		reservation_object_fini(&bo->ttm_resv);
-	}
 
 	return r;
 }

@@ -459,6 +455,7 @@ static void ttm_bo_cleanup_refs_or_queue(struct ttm_buffer_object *bo)
 			spin_unlock(&glob->lru_lock);
 			if (bo->resv != &bo->ttm_resv)
 				reservation_object_unlock(&bo->ttm_resv);
+
 			ttm_bo_cleanup_memtype_use(bo);
 			return;
 		}

@@ -1205,8 +1202,8 @@ int ttm_bo_init_reserved(struct ttm_bo_device *bdev,
 		lockdep_assert_held(&bo->resv->lock.base);
 	} else {
 		bo->resv = &bo->ttm_resv;
-		reservation_object_init(&bo->ttm_resv);
 	}
+	reservation_object_init(&bo->ttm_resv);
 	atomic_inc(&bo->glob->bo_count);
 	drm_vma_node_reset(&bo->vma_node);
 	bo->priority = 0;