ext4: fix reserved space counter leakage

commit 6fed83957f21eff11c8496e9f24253b03d2bc1dc upstream.

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: 51865fda28e5 ("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
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 18a5321b5ef37d6500cb3fd9464fd3e68c13a140..63a292db758771fc70c3824a316717c45bb09c89 100644 (file)
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1641,6 +1641,7 @@ 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,
@@ -1657,6 +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 {   /* bigalloc */
                if (!ext4_es_scan_clu(inode, &ext4_es_is_delonly, lblk)) {
                        if (!ext4_es_scan_clu(inode,
@@ -1669,6 +1671,7 @@ 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;
                                }
@@ -1679,6 +1682,8 @@ 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 e5e896b6200ac0d6115a48a40775fca85178c935..cbeb024296719a1961a3f2626ece090815928d9b 100644 (file)
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1356,6 +1356,12 @@ 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)