ext4: fix reserved space counter leakage

When ext4_insert_delayed block receives and recovers from an error from
ext4_es_insert_delayed_block(), e.g., ENOMEM, it does not release the
space it has reserved for that block insertion as it should. One effect
of this bug is that s_dirtyclusters_counter is not decremented and
remains incorrectly elevated until the file system has been unmounted.
This can result in premature ENOSPC returns and apparent loss of free
space.

Another effect of this bug is that
/sys/fs/ext4/<dev>/delayed_allocation_blocks can remain non-zero even
after syncfs has been executed on the filesystem.

Besides, add check for s_dirtyclusters_counter when inode is going to be
evicted and freed. s_dirtyclusters_counter can still keep non-zero until
inode is written back in .evict_inode(), and thus the check is delayed
to .destroy_inode().

Fixes: 9ac997cbdcd6 ("ext4: let ext4 maintain extent status tree")
Cc: stable@kernel.org
Suggested-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Signed-off-by: Jeffle Xu <jefflexu@linux.alibaba.com>
Reviewed-by: Eric Whitney <enwlinux@gmail.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Link: https://lore.kernel.org/r/20210823061358.84473-1-jefflexu@linux.alibaba.com

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 2a076d236ba112695ae252170e188291c4113f94..9df1ab070fa541dcb4b3947eb6bac0de8580cf4b 100644 (file)
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1628,6 +1628,7 @@ static int ext4_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk)
        struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
        int ret;
        bool allocated = false;
+       bool reserved = false;
 
        /*
         * If the cluster containing lblk is shared with a delayed,
@@ -1644,6 +1645,7 @@ static int ext4_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk)
                ret = ext4_da_reserve_space(inode);
                if (ret != 0)   /* ENOSPC */
                        goto errout;
+               reserved = true;
        } else {   /* bigalloc */
                if (!ext4_es_scan_clu(inode, &ext4_es_is_delonly, lblk)) {
                        if (!ext4_es_scan_clu(inode,
@@ -1656,6 +1658,7 @@ static int ext4_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk)
                                        ret = ext4_da_reserve_space(inode);
                                        if (ret != 0)   /* ENOSPC */
                                                goto errout;
+                                       reserved = true;
                                } else {
                                        allocated = true;
                                }
@@ -1666,6 +1669,8 @@ static int ext4_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk)
        }
 
        ret = ext4_es_insert_delayed_block(inode, lblk, allocated);
+       if (ret && reserved)
+               ext4_da_release_space(inode, 1);
 
 errout:
        return ret;

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index feca816b6bf30f257ed865de59645da3760cec08..a52f1572daa535d5c3dc0b49b0accddb9f09b1ad 100644 (file)
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1352,6 +1352,12 @@ static void ext4_destroy_inode(struct inode *inode)
                                true);
                dump_stack();
        }
+
+       if (EXT4_I(inode)->i_reserved_data_blocks)
+               ext4_msg(inode->i_sb, KERN_ERR,
+                        "Inode %lu (%p): i_reserved_data_blocks (%u) not cleared!",
+                        inode->i_ino, EXT4_I(inode),
+                        EXT4_I(inode)->i_reserved_data_blocks);
 }
 
 static void init_once(void *foo)