From 8163ea90d89b7012dd1fa4b28edf5db0c641eca7 Mon Sep 17 00:00:00 2001 From: Heming Zhao via Ocfs2-devel Date: Fri, 17 Feb 2023 08:37:17 +0800 Subject: ocfs2: fix defrag path triggering jbd2 ASSERT commit 60eed1e3d45045623e46944ebc7c42c30a4350f0 upstream. code path: ocfs2_ioctl_move_extents ocfs2_move_extents ocfs2_defrag_extent __ocfs2_move_extent + ocfs2_journal_access_di + ocfs2_split_extent //sub-paths call jbd2_journal_restart + ocfs2_journal_dirty //crash by jbs2 ASSERT crash stacks: PID: 11297 TASK: ffff974a676dcd00 CPU: 67 COMMAND: "defragfs.ocfs2" #0 [ffffb25d8dad3900] machine_kexec at ffffffff8386fe01 #1 [ffffb25d8dad3958] __crash_kexec at ffffffff8395959d #2 [ffffb25d8dad3a20] crash_kexec at ffffffff8395a45d #3 [ffffb25d8dad3a38] oops_end at ffffffff83836d3f #4 [ffffb25d8dad3a58] do_trap at ffffffff83833205 #5 [ffffb25d8dad3aa0] do_invalid_op at ffffffff83833aa6 #6 [ffffb25d8dad3ac0] invalid_op at ffffffff84200d18 [exception RIP: jbd2_journal_dirty_metadata+0x2ba] RIP: ffffffffc09ca54a RSP: ffffb25d8dad3b70 RFLAGS: 00010207 RAX: 0000000000000000 RBX: ffff9706eedc5248 RCX: 0000000000000000 RDX: 0000000000000001 RSI: ffff97337029ea28 RDI: ffff9706eedc5250 RBP: ffff9703c3520200 R8: 000000000f46b0b2 R9: 0000000000000000 R10: 0000000000000001 R11: 00000001000000fe R12: ffff97337029ea28 R13: 0000000000000000 R14: ffff9703de59bf60 R15: ffff9706eedc5250 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018 #7 [ffffb25d8dad3ba8] ocfs2_journal_dirty at ffffffffc137fb95 [ocfs2] #8 [ffffb25d8dad3be8] __ocfs2_move_extent at ffffffffc139a950 [ocfs2] #9 [ffffb25d8dad3c80] ocfs2_defrag_extent at ffffffffc139b2d2 [ocfs2] Analysis This bug has the same root cause of 'commit 7f27ec978b0e ("ocfs2: call ocfs2_journal_access_di() before ocfs2_journal_dirty() in ocfs2_write_end_nolock()")'. For this bug, jbd2_journal_restart() is called by ocfs2_split_extent() during defragmenting. How to fix For ocfs2_split_extent() can handle journal operations totally by itself. Caller doesn't need to call journal access/dirty pair, and caller only needs to call journal start/stop pair. The fix method is to remove journal access/dirty from __ocfs2_move_extent(). The discussion for this patch: https://oss.oracle.com/pipermail/ocfs2-devel/2023-February/000647.html Link: https://lkml.kernel.org/r/20230217003717.32469-1-heming.zhao@suse.com Signed-off-by: Heming Zhao Reviewed-by: Joseph Qi Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Changwei Ge Cc: Gang He Cc: Jun Piao Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/ocfs2/move_extents.c | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'fs') diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c index 192cad0662d8..6251748c695b 100644 --- a/fs/ocfs2/move_extents.c +++ b/fs/ocfs2/move_extents.c @@ -105,14 +105,6 @@ static int __ocfs2_move_extent(handle_t *handle, */ replace_rec.e_flags = ext_flags & ~OCFS2_EXT_REFCOUNTED; - ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), - context->et.et_root_bh, - OCFS2_JOURNAL_ACCESS_WRITE); - if (ret) { - mlog_errno(ret); - goto out; - } - ret = ocfs2_split_extent(handle, &context->et, path, index, &replace_rec, context->meta_ac, &context->dealloc); @@ -121,8 +113,6 @@ static int __ocfs2_move_extent(handle_t *handle, goto out; } - ocfs2_journal_dirty(handle, context->et.et_root_bh); - context->new_phys_cpos = new_p_cpos; /* -- cgit v1.2.3