From 53cf978457325d8fb2cdecd7981b31a8229e446e Mon Sep 17 00:00:00 2001 From: Xiaoguang Wang Date: Thu, 31 Jan 2019 23:42:11 -0500 Subject: jbd2: fix deadlock while checkpoint thread waits commit thread to finish This issue was found when I tried to put checkpoint work in a separate thread, the deadlock below happened: Thread1 | Thread2 __jbd2_log_wait_for_space | jbd2_log_do_checkpoint (hold j_checkpoint_mutex)| if (jh->b_transaction != NULL) | ... | jbd2_log_start_commit(journal, tid); |jbd2_update_log_tail | will lock j_checkpoint_mutex, | but will be blocked here. | jbd2_log_wait_commit(journal, tid); | wait_event(journal->j_wait_done_commit, | !tid_gt(tid, journal->j_commit_sequence)); | ... |wake_up(j_wait_done_commit) } | then deadlock occurs, Thread1 will never be waken up. To fix this issue, drop j_checkpoint_mutex in jbd2_log_do_checkpoint() when we are going to wait for transaction commit. Reviewed-by: Jan Kara Signed-off-by: Xiaoguang Wang Signed-off-by: Theodore Ts'o --- fs/jbd2/checkpoint.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) (limited to 'fs/jbd2/checkpoint.c') diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 26f8d7e46462..02e0b79753e7 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -113,7 +113,7 @@ void __jbd2_log_wait_for_space(journal_t *journal) nblocks = jbd2_space_needed(journal); while (jbd2_log_space_left(journal) < nblocks) { write_unlock(&journal->j_state_lock); - mutex_lock(&journal->j_checkpoint_mutex); + mutex_lock_io(&journal->j_checkpoint_mutex); /* * Test again, another process may have checkpointed while we @@ -276,9 +276,22 @@ restart: "JBD2: %s: Waiting for Godot: block %llu\n", journal->j_devname, (unsigned long long) bh->b_blocknr); + if (batch_count) + __flush_batch(journal, &batch_count); jbd2_log_start_commit(journal, tid); + /* + * jbd2_journal_commit_transaction() may want + * to take the checkpoint_mutex if JBD2_FLUSHED + * is set, jbd2_update_log_tail() called by + * jbd2_journal_commit_transaction() may also take + * checkpoint_mutex. So we need to temporarily + * drop it. + */ + mutex_unlock(&journal->j_checkpoint_mutex); jbd2_log_wait_commit(journal, tid); - goto retry; + mutex_lock_io(&journal->j_checkpoint_mutex); + spin_lock(&journal->j_list_lock); + goto restart; } if (!buffer_dirty(bh)) { if (unlikely(buffer_write_io_error(bh)) && !result) -- cgit v1.2.3-59-g8ed1b