Btrfs: fix memory leak of block group cache

While processing delayed refs, we may update block group's statistics
and attach it to cur_trans->dirty_bgs, and later writing dirty block
groups will process the list, which happens during
btrfs_commit_transaction().

For whatever reason, the transaction is aborted and dirty_bgs
is not processed in cleanup_transaction(), we end up with memory leak
of these dirty block group cache.

Since btrfs_start_dirty_block_groups() doesn't make it go to the commit
critical section, this also adds the cleanup work inside it.

Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>

3 files changed, 75 insertions, 0 deletions

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 54bc8c7c6bcd..754de24f17af 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -4475,9 +4475,80 @@ again:
 	return 0;
 }
 
+static void btrfs_cleanup_bg_io(struct btrfs_block_group_cache *cache)
+{
+	struct inode *inode;
+
+	inode = cache->io_ctl.inode;
+	if (inode) {
+		invalidate_inode_pages2(inode->i_mapping);
+		BTRFS_I(inode)->generation = 0;
+		cache->io_ctl.inode = NULL;
+		iput(inode);
+	}
+	btrfs_put_block_group(cache);
+}
+
+void btrfs_cleanup_dirty_bgs(struct btrfs_transaction *cur_trans,
+			     struct btrfs_root *root)
+{
+	struct btrfs_block_group_cache *cache;
+
+	spin_lock(&cur_trans->dirty_bgs_lock);
+	while (!list_empty(&cur_trans->dirty_bgs)) {
+		cache = list_first_entry(&cur_trans->dirty_bgs,
+					 struct btrfs_block_group_cache,
+					 dirty_list);
+		if (!cache) {
+			btrfs_err(root->fs_info,
+				  "orphan block group dirty_bgs list");
+			spin_unlock(&cur_trans->dirty_bgs_lock);
+			return;
+		}
+
+		if (!list_empty(&cache->io_list)) {
+			spin_unlock(&cur_trans->dirty_bgs_lock);
+			list_del_init(&cache->io_list);
+			btrfs_cleanup_bg_io(cache);
+			spin_lock(&cur_trans->dirty_bgs_lock);
+		}
+
+		list_del_init(&cache->dirty_list);
+		spin_lock(&cache->lock);
+		cache->disk_cache_state = BTRFS_DC_ERROR;
+		spin_unlock(&cache->lock);
+
+		spin_unlock(&cur_trans->dirty_bgs_lock);
+		btrfs_put_block_group(cache);
+		spin_lock(&cur_trans->dirty_bgs_lock);
+	}
+	spin_unlock(&cur_trans->dirty_bgs_lock);
+
+	while (!list_empty(&cur_trans->io_bgs)) {
+		cache = list_first_entry(&cur_trans->io_bgs,
+					 struct btrfs_block_group_cache,
+					 io_list);
+		if (!cache) {
+			btrfs_err(root->fs_info,
+				  "orphan block group on io_bgs list");
+			return;
+		}
+
+		list_del_init(&cache->io_list);
+		spin_lock(&cache->lock);
+		cache->disk_cache_state = BTRFS_DC_ERROR;
+		spin_unlock(&cache->lock);
+		btrfs_cleanup_bg_io(cache);
+	}
+}
+
 void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
 				   struct btrfs_root *root)
 {
+	btrfs_cleanup_dirty_bgs(cur_trans, root);
+	ASSERT(list_empty(&cur_trans->dirty_bgs));
+	ASSERT(list_empty(&cur_trans->io_bgs));
+
 	btrfs_destroy_delayed_refs(cur_trans, root);
 
 	cur_trans->state = TRANS_STATE_COMMIT_START;
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index f19a982f5a4f..1a3237e5700f 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -136,6 +136,8 @@ int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans,
 			     struct btrfs_fs_info *fs_info);
 int btrfs_add_log_tree(struct btrfs_trans_handle *trans,
 		       struct btrfs_root *root);
+void btrfs_cleanup_dirty_bgs(struct btrfs_transaction *trans,
+			     struct btrfs_root *root);
 void btrfs_cleanup_one_transaction(struct btrfs_transaction *trans,
 				  struct btrfs_root *root);
 struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 665da8f66ff1..616c45580c23 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3694,6 +3694,8 @@ again:
 			goto again;
 		}
 		spin_unlock(&cur_trans->dirty_bgs_lock);
+	} else if (ret < 0) {
+		btrfs_cleanup_dirty_bgs(cur_trans, root);
 	}
 
 	btrfs_free_path(path);