From 136f49b9171074872f2a14ad0ab10486d1ba13ca Mon Sep 17 00:00:00 2001 From: Junxiao Bi Date: Thu, 18 Dec 2014 16:17:37 -0800 Subject: [PATCH] ocfs2: fix journal commit deadlock For buffer write, page lock will be got in write_begin and released in write_end, in ocfs2_write_end_nolock(), before it unlock the page in ocfs2_free_write_ctxt(), it calls ocfs2_run_deallocs(), this will ask for the read lock of journal->j_trans_barrier. Holding page lock and ask for journal->j_trans_barrier breaks the locking order. This will cause a deadlock with journal commit threads, ocfs2cmt will get write lock of journal->j_trans_barrier first, then it wakes up kjournald2 to do the commit work, at last it waits until done. To commit journal, kjournald2 needs flushing data first, it needs get the cache page lock. Since some ocfs2 cluster locks are holding by write process, this deadlock may hung the whole cluster. unlock pages before ocfs2_run_deallocs() can fix the locking order, also put unlock before ocfs2_commit_trans() to make page lock is unlocked before j_trans_barrier to preserve unlocking order. Signed-off-by: Junxiao Bi Reviewed-by: Wengang Wang Cc: Reviewed-by: Mark Fasheh Cc: Joel Becker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/aops.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index d9f222987f24..46d93e941f3d 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -894,7 +894,7 @@ void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages) } } -static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc) +static void ocfs2_unlock_pages(struct ocfs2_write_ctxt *wc) { int i; @@ -915,7 +915,11 @@ static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc) page_cache_release(wc->w_target_page); } ocfs2_unlock_and_free_pages(wc->w_pages, wc->w_num_pages); +} +static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc) +{ + ocfs2_unlock_pages(wc); brelse(wc->w_di_bh); kfree(wc); } @@ -2042,11 +2046,19 @@ out_write_size: ocfs2_update_inode_fsync_trans(handle, inode, 1); ocfs2_journal_dirty(handle, wc->w_di_bh); + /* unlock pages before dealloc since it needs acquiring j_trans_barrier + * lock, or it will cause a deadlock since journal commit threads holds + * this lock and will ask for the page lock when flushing the data. + * put it here to preserve the unlock order. + */ + ocfs2_unlock_pages(wc); + ocfs2_commit_trans(osb, handle); ocfs2_run_deallocs(osb, &wc->w_dealloc); - ocfs2_free_write_ctxt(wc); + brelse(wc->w_di_bh); + kfree(wc); return copied; } -- 2.30.2