From 3e5ea6b6a571c37ceee837ac25384c2f39e52a8b Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Tue, 6 Jun 2023 21:59:26 +0800 Subject: [PATCH] jbd2: Fix wrongly judgement for buffer head removing while doing checkpoint [ Upstream commit e34c8dd238d0c9368b746480f313055f5bab5040 ] Following process, jbd2_journal_commit_transaction // there are several dirty buffer heads in transaction->t_checkpoint_list P1 wb_workfn jbd2_log_do_checkpoint if (buffer_locked(bh)) // false __block_write_full_page trylock_buffer(bh) test_clear_buffer_dirty(bh) if (!buffer_dirty(bh)) __jbd2_journal_remove_checkpoint(jh) if (buffer_write_io_error(bh)) // false >> bh IO error occurs << jbd2_cleanup_journal_tail __jbd2_update_log_tail jbd2_write_superblock // The bh won't be replayed in next mount. , which could corrupt the ext4 image, fetch a reproducer in [Link]. Since writeback process clears buffer dirty after locking buffer head, we can fix it by try locking buffer and check dirtiness while buffer is locked, the buffer head can be removed if it is neither dirty nor locked. Link: https://bugzilla.kernel.org/show_bug.cgi?id=217490 Fixes: 470decc613ab ("[PATCH] jbd2: initial copy of files from jbd") Signed-off-by: Zhihao Cheng Signed-off-by: Zhang Yi Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20230606135928.434610-5-yi.zhang@huaweicloud.com Signed-off-by: Theodore Ts'o Signed-off-by: Sasha Levin --- fs/jbd2/checkpoint.c | 32 +++++++++++++++++--------------- 1 file changed, 17 insertions(+), 15 deletions(-) diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 25e3c20eb19f..c4e0da6db719 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -221,20 +221,6 @@ int jbd2_log_do_checkpoint(journal_t *journal) jh = transaction->t_checkpoint_list; bh = jh2bh(jh); - /* - * The buffer may be writing back, or flushing out in the - * last couple of cycles, or re-adding into a new transaction, - * need to check it again until it's unlocked. - */ - if (buffer_locked(bh)) { - get_bh(bh); - spin_unlock(&journal->j_list_lock); - wait_on_buffer(bh); - /* the journal_head may have gone by now */ - BUFFER_TRACE(bh, "brelse"); - __brelse(bh); - goto retry; - } if (jh->b_transaction != NULL) { transaction_t *t = jh->b_transaction; tid_t tid = t->t_tid; @@ -269,7 +255,22 @@ int jbd2_log_do_checkpoint(journal_t *journal) spin_lock(&journal->j_list_lock); goto restart; } - if (!buffer_dirty(bh)) { + if (!trylock_buffer(bh)) { + /* + * The buffer is locked, it may be writing back, or + * flushing out in the last couple of cycles, or + * re-adding into a new transaction, need to check + * it again until it's unlocked. + */ + get_bh(bh); + spin_unlock(&journal->j_list_lock); + wait_on_buffer(bh); + /* the journal_head may have gone by now */ + BUFFER_TRACE(bh, "brelse"); + __brelse(bh); + goto retry; + } else if (!buffer_dirty(bh)) { + unlock_buffer(bh); BUFFER_TRACE(bh, "remove from checkpoint"); /* * If the transaction was released or the checkpoint @@ -279,6 +280,7 @@ int jbd2_log_do_checkpoint(journal_t *journal) !transaction->t_checkpoint_list) goto out; } else { + unlock_buffer(bh); /* * We are about to write the buffer, it could be * raced by some other transaction shrink or buffer