From 26fb5290240dc31cae99b8b4dd2af7f46dfcba6b Mon Sep 17 00:00:00 2001
From: Zhihao Cheng <chengzhihao1@huawei.com>
Date: Wed, 15 Mar 2023 09:31:23 +0800
Subject: [PATCH] ext4: Fix reusing stale buffer heads from last failed
mounting
Git-commit: 26fb5290240dc31cae99b8b4dd2af7f46dfcba6b
Patch-mainline: v6.5-rc1
References: bsc#1213020
Following process makes ext4 load stale buffer heads from last failed
mounting in a new mounting operation:
mount_bdev
ext4_fill_super
| ext4_load_and_init_journal
| ext4_load_journal
| jbd2_journal_load
| load_superblock
| journal_get_superblock
| set_buffer_verified(bh) // buffer head is verified
| jbd2_journal_recover // failed caused by EIO
| goto failed_mount3a // skip 'sb->s_root' initialization
deactivate_locked_super
kill_block_super
generic_shutdown_super
if (sb->s_root)
// false, skip ext4_put_super->invalidate_bdev->
// invalidate_mapping_pages->mapping_evict_folio->
// filemap_release_folio->try_to_free_buffers, which
// cannot drop buffer head.
blkdev_put
blkdev_put_whole
if (atomic_dec_and_test(&bdev->bd_openers))
// false, systemd-udev happens to open the device. Then
// blkdev_flush_mapping->kill_bdev->truncate_inode_pages->
// truncate_inode_folio->truncate_cleanup_folio->
// folio_invalidate->block_invalidate_folio->
// filemap_release_folio->try_to_free_buffers will be skipped,
// dropping buffer head is missed again.
Second mount:
ext4_fill_super
ext4_load_and_init_journal
ext4_load_journal
ext4_get_journal
jbd2_journal_init_inode
journal_init_common
bh = getblk_unmovable
bh = __find_get_block // Found stale bh in last failed mounting
journal->j_sb_buffer = bh
jbd2_journal_load
load_superblock
journal_get_superblock
if (buffer_verified(bh))
// true, skip journal->j_format_version = 2, value is 0
jbd2_journal_recover
do_one_pass
next_log_block += count_tags(journal, bh)
// According to journal_tag_bytes(), 'tag_bytes' calculating is
// affected by jbd2_has_feature_csum3(), jbd2_has_feature_csum3()
// returns false because 'j->j_format_version >= 2' is not true,
// then we get wrong next_log_block. The do_one_pass may exit
// early whenoccuring non JBD2_MAGIC_NUMBER in 'next_log_block'.
The filesystem is corrupted here, journal is partially replayed, and
new journal sequence number actually is already used by last mounting.
The invalidate_bdev() can drop all buffer heads even racing with bare
reading block device(eg. systemd-udev), so we can fix it by invalidating
bdev in error handling path in __ext4_fill_super().
Fetch a reproducer in [Link].
Link: https://bugzilla.kernel.org/show_bug.cgi?id=217171
Fixes: 25ed6e8a54df ("jbd2: enable journal clients to enable v2 checksumming")
Cc: stable@vger.kernel.org # v3.5
Signed-off-by: Zhihao Cheng <chengzhihao1@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20230315013128.3911115-2-chengzhihao1@huawei.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Acked-by: Jan Kara <jack@suse.cz>
---
fs/ext4/super.c | 13 +++++++------
1 file changed, 7 insertions(+), 6 deletions(-)
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -817,6 +817,12 @@ static void ext4_blkdev_remove(struct ex
struct block_device *bdev;
bdev = sbi->journal_bdev;
if (bdev) {
+ /*
+ * Invalidate the journal device's buffers. We don't want them
+ * floating about in memory - the physical journal device may
+ * hotswapped, and it breaks the `ro-after' testing code.
+ */
+ invalidate_bdev(bdev);
ext4_blkdev_put(bdev);
sbi->journal_bdev = NULL;
}
@@ -944,13 +950,7 @@ static void ext4_put_super(struct super_
sync_blockdev(sb->s_bdev);
invalidate_bdev(sb->s_bdev);
if (sbi->journal_bdev && sbi->journal_bdev != sb->s_bdev) {
- /*
- * Invalidate the journal device's buffers. We don't want them
- * floating about in memory - the physical journal device may
- * hotswapped, and it breaks the `ro-after' testing code.
- */
sync_blockdev(sbi->journal_bdev);
- invalidate_bdev(sbi->journal_bdev);
ext4_blkdev_remove(sbi);
}
if (sbi->s_mb_cache) {
@@ -4516,6 +4516,7 @@ failed_mount:
brelse(bh);
ext4_blkdev_remove(sbi);
out_fail:
+ invalidate_bdev(sb->s_bdev);
sb->s_fs_info = NULL;
kfree(sbi->s_blockgroup_lock);
out_free_base: