btrfs: remove free space items when disabling space cache v1

When the filesystem transitions from space cache v1 to v2 or to
nospace_cache, it removes the old cached data, but does not remove
the FREE_SPACE items nor the free space inodes they point to. This
doesn't cause any issues besides being a bit inefficient, since these
items no longer do anything useful.

To fix it, when we are mounting, and plan to disable the space cache,
destroy each block group's free space item and free space inode.
The code to remove the items is lifted from the existing use case of
removing the block group, with a light adaptation to handle whether or
not we have already looked up the free space inode.

Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Boris Burkov <boris@bur.io>
Signed-off-by: David Sterba <dsterba@suse.com>

3 files changed, 100 insertions, 41 deletions

diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 614b6b5b3102..fbc74bb41322 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -848,8 +848,6 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	struct btrfs_path *path;
 	struct btrfs_block_group *block_group;
 	struct btrfs_free_cluster *cluster;
-	struct btrfs_root *tree_root = fs_info->tree_root;
-	struct btrfs_key key;
 	struct inode *inode;
 	struct kobject *kobj = NULL;
 	int ret;
@@ -927,42 +925,9 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	spin_unlock(&trans->transaction->dirty_bgs_lock);
 	mutex_unlock(&trans->transaction->cache_write_mutex);
 
-	if (!IS_ERR(inode)) {
-		ret = btrfs_orphan_add(trans, BTRFS_I(inode));
-		if (ret) {
-			btrfs_add_delayed_iput(inode);
-			goto out;
-		}
-		clear_nlink(inode);
-		/* One for the block groups ref */
-		spin_lock(&block_group->lock);
-		if (block_group->iref) {
-			block_group->iref = 0;
-			block_group->inode = NULL;
-			spin_unlock(&block_group->lock);
-			iput(inode);
-		} else {
-			spin_unlock(&block_group->lock);
-		}
-		/* One for our lookup ref */
-		btrfs_add_delayed_iput(inode);
-	}
-
-	key.objectid = BTRFS_FREE_SPACE_OBJECTID;
-	key.type = 0;
-	key.offset = block_group->start;
-
-	ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1);
-	if (ret < 0)
+	ret = btrfs_remove_free_space_inode(trans, inode, block_group);
+	if (ret)
 		goto out;
-	if (ret > 0)
-		btrfs_release_path(path);
-	if (ret == 0) {
-		ret = btrfs_del_item(trans, tree_root, path);
-		if (ret)
-			goto out;
-		btrfs_release_path(path);
-	}
 
 	spin_lock(&fs_info->block_group_cache_lock);
 	rb_erase(&block_group->cache_node,
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index e71def319655..4d8897879c9c 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -206,6 +206,65 @@ int create_free_space_inode(struct btrfs_trans_handle *trans,
 					 ino, block_group->start);
 }
 
+/*
+ * inode is an optional sink: if it is NULL, btrfs_remove_free_space_inode
+ * handles lookup, otherwise it takes ownership and iputs the inode.
+ * Don't reuse an inode pointer after passing it into this function.
+ */
+int btrfs_remove_free_space_inode(struct btrfs_trans_handle *trans,
+				  struct inode *inode,
+				  struct btrfs_block_group *block_group)
+{
+	struct btrfs_path *path;
+	struct btrfs_key key;
+	int ret = 0;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	if (!inode)
+		inode = lookup_free_space_inode(block_group, path);
+	if (IS_ERR(inode)) {
+		if (PTR_ERR(inode) != -ENOENT)
+			ret = PTR_ERR(inode);
+		goto out;
+	}
+	ret = btrfs_orphan_add(trans, BTRFS_I(inode));
+	if (ret) {
+		btrfs_add_delayed_iput(inode);
+		goto out;
+	}
+	clear_nlink(inode);
+	/* One for the block groups ref */
+	spin_lock(&block_group->lock);
+	if (block_group->iref) {
+		block_group->iref = 0;
+		block_group->inode = NULL;
+		spin_unlock(&block_group->lock);
+		iput(inode);
+	} else {
+		spin_unlock(&block_group->lock);
+	}
+	/* One for the lookup ref */
+	btrfs_add_delayed_iput(inode);
+
+	key.objectid = BTRFS_FREE_SPACE_OBJECTID;
+	key.type = 0;
+	key.offset = block_group->start;
+	ret = btrfs_search_slot(trans, trans->fs_info->tree_root, &key, path,
+				-1, 1);
+	if (ret) {
+		if (ret > 0)
+			ret = 0;
+		goto out;
+	}
+	ret = btrfs_del_item(trans, trans->fs_info->tree_root, path);
+out:
+	btrfs_free_path(path);
+	return ret;
+}
+
 int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info,
 				       struct btrfs_block_rsv *rsv)
 {
@@ -3768,24 +3827,56 @@ bool btrfs_free_space_cache_v1_active(struct btrfs_fs_info *fs_info)
 	return btrfs_super_cache_generation(fs_info->super_copy);
 }
 
+static int cleanup_free_space_cache_v1(struct btrfs_fs_info *fs_info,
+				       struct btrfs_trans_handle *trans)
+{
+	struct btrfs_block_group *block_group;
+	struct rb_node *node;
+	int ret;
+
+	btrfs_info(fs_info, "cleaning free space cache v1");
+
+	node = rb_first(&fs_info->block_group_cache_tree);
+	while (node) {
+		block_group = rb_entry(node, struct btrfs_block_group, cache_node);
+		ret = btrfs_remove_free_space_inode(trans, NULL, block_group);
+		if (ret)
+			goto out;
+		node = rb_next(node);
+	}
+out:
+	return ret;
+}
+
 int btrfs_set_free_space_cache_v1_active(struct btrfs_fs_info *fs_info, bool active)
 {
 	struct btrfs_trans_handle *trans;
 	int ret;
 
 	/*
-	 * update_super_roots will appropriately set
-	 * super_copy->cache_generation based on the SPACE_CACHE option, so all
-	 * we have to do is trigger a transaction commit.
+	 * update_super_roots will appropriately set or unset
+	 * super_copy->cache_generation based on SPACE_CACHE and
+	 * BTRFS_FS_CLEANUP_SPACE_CACHE_V1. For this reason, we need a
+	 * transaction commit whether we are enabling space cache v1 and don't
+	 * have any other work to do, or are disabling it and removing free
+	 * space inodes.
 	 */
 	trans = btrfs_start_transaction(fs_info->tree_root, 0);
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
 
-	if (!active)
+	if (!active) {
 		set_bit(BTRFS_FS_CLEANUP_SPACE_CACHE_V1, &fs_info->flags);
+		ret = cleanup_free_space_cache_v1(fs_info, trans);
+		if (ret) {
+			btrfs_abort_transaction(trans, ret);
+			btrfs_end_transaction(trans);
+			goto out;
+		}
+	}
 
 	ret = btrfs_commit_transaction(trans);
+out:
 	clear_bit(BTRFS_FS_CLEANUP_SPACE_CACHE_V1, &fs_info->flags);
 
 	return ret;
diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h
index 3eff615c30b8..ecb09a02d544 100644
--- a/fs/btrfs/free-space-cache.h
+++ b/fs/btrfs/free-space-cache.h
@@ -82,6 +82,9 @@ struct inode *lookup_free_space_inode(struct btrfs_block_group *block_group,
 int create_free_space_inode(struct btrfs_trans_handle *trans,
 			    struct btrfs_block_group *block_group,
 			    struct btrfs_path *path);
+int btrfs_remove_free_space_inode(struct btrfs_trans_handle *trans,
+				  struct inode *inode,
+				  struct btrfs_block_group *block_group);
 
 int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info,
 				       struct btrfs_block_rsv *rsv);