1 files changed, 52 insertions, 14 deletions

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 9ee75a586ae4..fc5c9b797e31 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1511,9 +1511,16 @@ int btrfs_init_fs_root(struct btrfs_root *root)
 	spin_lock_init(&root->ino_cache_lock);
 	init_waitqueue_head(&root->ino_cache_wait);
 
-	ret = get_anon_bdev(&root->anon_dev);
-	if (ret)
-		goto fail;
+	/*
+	 * Don't assign anonymous block device to roots that are not exposed to
+	 * userspace, the id pool is limited to 1M
+	 */
+	if (is_fstree(root->root_key.objectid) &&
+	    btrfs_root_refs(&root->root_item) > 0) {
+		ret = get_anon_bdev(&root->anon_dev);
+		if (ret)
+			goto fail;
+	}
 
 	mutex_lock(&root->objectid_mutex);
 	ret = btrfs_find_highest_objectid(root,
@@ -2052,7 +2059,7 @@ static void free_root_extent_buffers(struct btrfs_root *root)
 }
 
 /* helper to cleanup tree roots */
-static void free_root_pointers(struct btrfs_fs_info *info, int chunk_root)
+static void free_root_pointers(struct btrfs_fs_info *info, bool free_chunk_root)
 {
 	free_root_extent_buffers(info->tree_root);
 
@@ -2061,7 +2068,7 @@ static void free_root_pointers(struct btrfs_fs_info *info, int chunk_root)
 	free_root_extent_buffers(info->csum_root);
 	free_root_extent_buffers(info->quota_root);
 	free_root_extent_buffers(info->uuid_root);
-	if (chunk_root)
+	if (free_chunk_root)
 		free_root_extent_buffers(info->chunk_root);
 	free_root_extent_buffers(info->free_space_root);
 }
@@ -2666,7 +2673,6 @@ int open_ctree(struct super_block *sb,
 	spin_lock_init(&fs_info->fs_roots_radix_lock);
 	spin_lock_init(&fs_info->delayed_iput_lock);
 	spin_lock_init(&fs_info->defrag_inodes_lock);
-	spin_lock_init(&fs_info->tree_mod_seq_lock);
 	spin_lock_init(&fs_info->super_lock);
 	spin_lock_init(&fs_info->buffer_lock);
 	spin_lock_init(&fs_info->unused_bgs_lock);
@@ -3051,6 +3057,18 @@ retry_root_backup:
 	fs_info->generation = generation;
 	fs_info->last_trans_committed = generation;
 
+	/*
+	 * If we have a uuid root and we're not being told to rescan we need to
+	 * check the generation here so we can set the
+	 * BTRFS_FS_UPDATE_UUID_TREE_GEN bit.  Otherwise we could commit the
+	 * transaction during a balance or the log replay without updating the
+	 * uuid generation, and then if we crash we would rescan the uuid tree,
+	 * even though it was perfectly fine.
+	 */
+	if (fs_info->uuid_root && !btrfs_test_opt(fs_info, RESCAN_UUID_TREE) &&
+	    fs_info->generation == btrfs_super_uuid_tree_generation(disk_super))
+		set_bit(BTRFS_FS_UPDATE_UUID_TREE_GEN, &fs_info->flags);
+
 	ret = btrfs_verify_dev_extents(fs_info);
 	if (ret) {
 		btrfs_err(fs_info,
@@ -3161,6 +3179,7 @@ retry_root_backup:
 	/* do not make disk changes in broken FS or nologreplay is given */
 	if (btrfs_super_log_root(disk_super) != 0 &&
 	    !btrfs_test_opt(fs_info, NOLOGREPLAY)) {
+		btrfs_info(fs_info, "start tree-log replay");
 		ret = btrfs_replay_log(fs_info, fs_devices);
 		if (ret) {
 			err = ret;
@@ -3196,6 +3215,7 @@ retry_root_backup:
 	if (IS_ERR(fs_info->fs_root)) {
 		err = PTR_ERR(fs_info->fs_root);
 		btrfs_warn(fs_info, "failed to read fs tree: %d", err);
+		fs_info->fs_root = NULL;
 		goto fail_qgroup;
 	}
 
@@ -3279,8 +3299,6 @@ retry_root_backup:
 			close_ctree(fs_info);
 			return ret;
 		}
-	} else {
-		set_bit(BTRFS_FS_UPDATE_UUID_TREE_GEN, &fs_info->flags);
 	}
 	set_bit(BTRFS_FS_OPEN, &fs_info->flags);
 
@@ -3317,7 +3335,7 @@ fail_block_groups:
 	btrfs_put_block_group_cache(fs_info);
 
 fail_tree_roots:
-	free_root_pointers(fs_info, 1);
+	free_root_pointers(fs_info, true);
 	invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
 
 fail_sb_buffer:
@@ -3347,7 +3365,7 @@ recovery_tree_root:
 	if (!btrfs_test_opt(fs_info, USEBACKUPROOT))
 		goto fail_tree_roots;
 
-	free_root_pointers(fs_info, 0);
+	free_root_pointers(fs_info, false);
 
 	/* don't use the log in recovery mode, it won't be valid */
 	btrfs_set_super_log_root(disk_super, 0);
@@ -3994,6 +4012,19 @@ void close_ctree(struct btrfs_fs_info *fs_info)
 		 */
 		btrfs_delete_unused_bgs(fs_info);
 
+		/*
+		 * There might be existing delayed inode workers still running
+		 * and holding an empty delayed inode item. We must wait for
+		 * them to complete first because they can create a transaction.
+		 * This happens when someone calls btrfs_balance_delayed_items()
+		 * and then a transaction commit runs the same delayed nodes
+		 * before any delayed worker has done something with the nodes.
+		 * We must wait for any worker here and not at transaction
+		 * commit time since that could cause a deadlock.
+		 * This is a very rare case.
+		 */
+		btrfs_flush_workqueue(fs_info->delayed_workers);
+
 		ret = btrfs_commit_super(fs_info);
 		if (ret)
 			btrfs_err(fs_info, "commit super ret %d", ret);
@@ -4035,10 +4066,17 @@ void close_ctree(struct btrfs_fs_info *fs_info)
 	invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
 	btrfs_stop_all_workers(fs_info);
 
-	btrfs_free_block_groups(fs_info);
-
 	clear_bit(BTRFS_FS_OPEN, &fs_info->flags);
-	free_root_pointers(fs_info, 1);
+	free_root_pointers(fs_info, true);
+
+	/*
+	 * We must free the block groups after dropping the fs_roots as we could
+	 * have had an IO error and have left over tree log blocks that aren't
+	 * cleaned up until the fs roots are freed.  This makes the block group
+	 * accounting appear to be wrong because there's pending reserved bytes,
+	 * so make sure we do the block group cleanup afterwards.
+	 */
+	btrfs_free_block_groups(fs_info);
 
 	iput(fs_info->btree_inode);
 
@@ -4273,6 +4311,7 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
 		cond_resched();
 		spin_lock(&delayed_refs->lock);
 	}
+	btrfs_qgroup_destroy_extent_records(trans);
 
 	spin_unlock(&delayed_refs->lock);
 
@@ -4498,7 +4537,6 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
 	wake_up(&fs_info->transaction_wait);
 
 	btrfs_destroy_delayed_inodes(fs_info);
-	btrfs_assert_delayed_root_empty(fs_info);
 
 	btrfs_destroy_marked_extents(fs_info, &cur_trans->dirty_pages,
 				     EXTENT_DIRTY);