Commit fcf37549 authored by Zhang Yi's avatar Zhang Yi Committed by Theodore Ts'o
Browse files

jbd2: ensure abort the journal if detect IO error when writing original buffer back



Although we merged c044f3d8 ("jbd2: abort journal if free a async
write error metadata buffer"), there is a race between
jbd2_journal_try_to_free_buffers() and jbd2_journal_destroy(), so the
jbd2_log_do_checkpoint() may still fail to detect the buffer write
io error flag which may lead to filesystem inconsistency.

jbd2_journal_try_to_free_buffers()     ext4_put_super()
                                        jbd2_journal_destroy()
  __jbd2_journal_remove_checkpoint()
  detect buffer write error              jbd2_log_do_checkpoint()
                                         jbd2_cleanup_journal_tail()
                                           <--- lead to inconsistency
  jbd2_journal_abort()

Fix this issue by introducing a new atomic flag which only have one
JBD2_CHECKPOINT_IO_ERROR bit now, and set it in
__jbd2_journal_remove_checkpoint() when freeing a checkpoint buffer
which has write_io_error flag. Then jbd2_journal_destroy() will detect
this mark and abort the journal to prevent updating log tail.

Signed-off-by: default avatarZhang Yi <yi.zhang@huawei.com>
Reviewed-by: default avatarJan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20210610112440.3438139-3-yi.zhang@huawei.com


Signed-off-by: default avatarTheodore Ts'o <tytso@mit.edu>
parent 1866cba8
Loading
Loading
Loading
Loading
+12 −0
Original line number Diff line number Diff line
@@ -564,6 +564,7 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh)
	struct transaction_chp_stats_s *stats;
	transaction_t *transaction;
	journal_t *journal;
	struct buffer_head *bh = jh2bh(jh);

	JBUFFER_TRACE(jh, "entry");

@@ -575,6 +576,17 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh)
	journal = transaction->t_journal;

	JBUFFER_TRACE(jh, "removing from transaction");

	/*
	 * If we have failed to write the buffer out to disk, the filesystem
	 * may become inconsistent. We cannot abort the journal here since
	 * we hold j_list_lock and we have to be careful about races with
	 * jbd2_journal_destroy(). So mark the writeback IO error in the
	 * journal here and we abort the journal later from a better context.
	 */
	if (buffer_write_io_error(bh))
		set_bit(JBD2_CHECKPOINT_IO_ERROR, &journal->j_atomic_flags);

	__buffer_unlink(jh);
	jh->b_cp_transaction = NULL;
	jbd2_journal_put_journal_head(jh);
+14 −0
Original line number Diff line number Diff line
@@ -1610,6 +1610,10 @@ int jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid,

	if (is_journal_aborted(journal))
		return -EIO;
	if (test_bit(JBD2_CHECKPOINT_IO_ERROR, &journal->j_atomic_flags)) {
		jbd2_journal_abort(journal, -EIO);
		return -EIO;
	}

	BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex));
	jbd_debug(1, "JBD2: updating superblock (start %lu, seq %u)\n",
@@ -2091,6 +2095,16 @@ int jbd2_journal_destroy(journal_t *journal)
	J_ASSERT(journal->j_checkpoint_transactions == NULL);
	spin_unlock(&journal->j_list_lock);

	/*
	 * OK, all checkpoint transactions have been checked, now check the
	 * write out io error flag and abort the journal if some buffer failed
	 * to write back to the original location, otherwise the filesystem
	 * may become inconsistent.
	 */
	if (!is_journal_aborted(journal) &&
	    test_bit(JBD2_CHECKPOINT_IO_ERROR, &journal->j_atomic_flags))
		jbd2_journal_abort(journal, -EIO);

	if (journal->j_sb_buffer) {
		if (!is_journal_aborted(journal)) {
			mutex_lock_io(&journal->j_checkpoint_mutex);
+11 −0
Original line number Diff line number Diff line
@@ -779,6 +779,11 @@ struct journal_s
	 */
	unsigned long		j_flags;

	/**
	 * @j_atomic_flags: Atomic journaling state flags.
	 */
	unsigned long		j_atomic_flags;

	/**
	 * @j_errno:
	 *
@@ -1375,6 +1380,12 @@ JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit, FAST_COMMIT)
#define JBD2_JOURNAL_FLUSH_VALID	(JBD2_JOURNAL_FLUSH_DISCARD | \
					JBD2_JOURNAL_FLUSH_ZEROOUT)

/*
 * Journal atomic flag definitions
 */
#define JBD2_CHECKPOINT_IO_ERROR	0x001	/* Detect io error while writing
						 * buffer back to disk */

/*
 * Function declarations for the journaling transaction and buffer
 * management