commit afd09b617db3786b6ef3dc43e28fe728cfea84df upstream.
Note: this backport is only targeted for the following LTS branches:
v5.4, v4.19, v4.14, v4.9 and v4.4.
Buffer head references must be released before calling kill_bdev();
otherwise the buffer head (and its page referenced by b_data) will not
be freed by kill_bdev, and subsequently that bh will be leaked.
If blocksizes differ, sb_set_blocksize() will kill current buffers and
page cache by using kill_bdev(). And then super block will be reread
again but using correct blocksize this time. sb_set_blocksize() didn't
fully free superblock page and buffer head, and being busy, they were
not freed and instead leaked.
This can easily be reproduced by calling an infinite loop of:
systemctl start <ext4_on_lvm>.mount, and
systemctl stop <ext4_on_lvm>.mount
... since systemd creates a cgroup for each slice which it mounts, and
the bh leak get amplified by a dying memory cgroup that also never
gets freed, and memory consumption is much more easily noticed.
Fixes: ce40733ce93d ("ext4: Check for return value from sb_set_blocksize")
Fixes: ac27a0ec112a ("ext4: initial copy of files from ext3")
Link: https://lore.kernel.org/r/20210521075533.95732-1-amakhalov@xxxxxxxxxx
Signed-off-by: Alexey Makhalov <amakhalov@xxxxxxxxxx>
Signed-off-by: Theodore Ts'o <tytso@xxxxxxx>
Cc: stable@xxxxxxxxxxxxxxx # v5.4 and prior
---
fs/ext4/super.c | 11 +++++++++--
1 file changed, 9 insertions(+), 2 deletions(-)
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 0b364f5e6fdf..8650511ae6af 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -4066,14 +4066,20 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
}
if (sb->s_blocksize != blocksize) {
+ /*
+ * bh must be released before kill_bdev(), otherwise
+ * it won't be freed and its page also. kill_bdev()
+ * is called by sb_set_blocksize().
+ */
+ brelse(bh);
/* Validate the filesystem blocksize */
if (!sb_set_blocksize(sb, blocksize)) {
ext4_msg(sb, KERN_ERR, "bad block size %d",
blocksize);
+ bh = NULL;
goto failed_mount;
}
- brelse(bh);
logical_sb_block = sb_block * EXT4_MIN_BLOCK_SIZE;
offset = do_div(logical_sb_block, blocksize);
bh = sb_bread_unmovable(sb, logical_sb_block);
@@ -4748,8 +4754,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
for (i = 0; i < EXT4_MAXQUOTAS; i++)
kfree(get_qf_name(sb, sbi, i));
#endif
- ext4_blkdev_remove(sbi);
+ /* ext4_blkdev_remove() calls kill_bdev(), release bh before it. */
brelse(bh);
+ ext4_blkdev_remove(sbi);
out_fail:
sb->s_fs_info = NULL;
kfree(sbi->s_blockgroup_lock);
--
2.11.0
