| From e6f0c6e6170fec175fe676495f29029aecdf486c Mon Sep 17 00:00:00 2001 |
| From: Joseph Qi <joseph.qi@huawei.com> |
| Date: Mon, 19 Sep 2016 14:43:55 -0700 |
| Subject: ocfs2/dlm: fix race between convert and migration |
| |
| From: Joseph Qi <joseph.qi@huawei.com> |
| |
| commit e6f0c6e6170fec175fe676495f29029aecdf486c upstream. |
| |
| Commit ac7cf246dfdb ("ocfs2/dlm: fix race between convert and recovery") |
| checks if lockres master has changed to identify whether new master has |
| finished recovery or not. This will introduce a race that right after |
| old master does umount ( means master will change), a new convert |
| request comes. |
| |
| In this case, it will reset lockres state to DLM_RECOVERING and then |
| retry convert, and then fail with lockres->l_action being set to |
| OCFS2_AST_INVALID, which will cause inconsistent lock level between |
| ocfs2 and dlm, and then finally BUG. |
| |
| Since dlm recovery will clear lock->convert_pending in |
| dlm_move_lockres_to_recovery_list, we can use it to correctly identify |
| the race case between convert and recovery. So fix it. |
| |
| Fixes: ac7cf246dfdb ("ocfs2/dlm: fix race between convert and recovery") |
| Link: http://lkml.kernel.org/r/57CE1569.8010704@huawei.com |
| Signed-off-by: Joseph Qi <joseph.qi@huawei.com> |
| Signed-off-by: Jun Piao <piaojun@huawei.com> |
| Cc: Mark Fasheh <mfasheh@suse.de> |
| Cc: Joel Becker <jlbec@evilplan.org> |
| Cc: Junxiao Bi <junxiao.bi@oracle.com> |
| Signed-off-by: Andrew Morton <akpm@linux-foundation.org> |
| Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> |
| Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> |
| |
| --- |
| fs/ocfs2/dlm/dlmconvert.c | 12 ++++++------ |
| 1 file changed, 6 insertions(+), 6 deletions(-) |
| |
| --- a/fs/ocfs2/dlm/dlmconvert.c |
| +++ b/fs/ocfs2/dlm/dlmconvert.c |
| @@ -268,7 +268,6 @@ enum dlm_status dlmconvert_remote(struct |
| struct dlm_lock *lock, int flags, int type) |
| { |
| enum dlm_status status; |
| - u8 old_owner = res->owner; |
| |
| mlog(0, "type=%d, convert_type=%d, busy=%d\n", lock->ml.type, |
| lock->ml.convert_type, res->state & DLM_LOCK_RES_IN_PROGRESS); |
| @@ -335,7 +334,6 @@ enum dlm_status dlmconvert_remote(struct |
| |
| spin_lock(&res->spinlock); |
| res->state &= ~DLM_LOCK_RES_IN_PROGRESS; |
| - lock->convert_pending = 0; |
| /* if it failed, move it back to granted queue. |
| * if master returns DLM_NORMAL and then down before sending ast, |
| * it may have already been moved to granted queue, reset to |
| @@ -344,12 +342,14 @@ enum dlm_status dlmconvert_remote(struct |
| if (status != DLM_NOTQUEUED) |
| dlm_error(status); |
| dlm_revert_pending_convert(res, lock); |
| - } else if ((res->state & DLM_LOCK_RES_RECOVERING) || |
| - (old_owner != res->owner)) { |
| - mlog(0, "res %.*s is in recovering or has been recovered.\n", |
| - res->lockname.len, res->lockname.name); |
| + } else if (!lock->convert_pending) { |
| + mlog(0, "%s: res %.*s, owner died and lock has been moved back " |
| + "to granted list, retry convert.\n", |
| + dlm->name, res->lockname.len, res->lockname.name); |
| status = DLM_RECOVERING; |
| } |
| + |
| + lock->convert_pending = 0; |
| bail: |
| spin_unlock(&res->spinlock); |
| |