ocfs2/dlm: fix race between convert and recovery

There is a race window between dlmconvert_remote and
dlm_move_lockres_to_recovery_list, which will cause a lock with
OCFS2_LOCK_BUSY in grant list, thus system hangs.

dlmconvert_remote
{
        spin_lock(&res->spinlock);
        list_move_tail(&lock->list, &res->converting);
        lock->convert_pending = 1;
        spin_unlock(&res->spinlock);

        status = dlm_send_remote_convert_request();
        >>>>>> race window, master has queued ast and return DLM_NORMAL,
               and then down before sending ast.
               this node detects master down and calls
               dlm_move_lockres_to_recovery_list, which will revert the
               lock to grant list.
               Then OCFS2_LOCK_BUSY won't be cleared as new master won't
               send ast any more because it thinks already be authorized.

        spin_lock(&res->spinlock);
        lock->convert_pending = 0;
        if (status != DLM_NORMAL)
                dlm_revert_pending_convert(res, lock);
        spin_unlock(&res->spinlock);
}

In this case, check if res->state has DLM_LOCK_RES_RECOVERING bit set
(res is still in recovering) or res master changed (new master has
finished recovery), reset the status to DLM_RECOVERING, then it will
retry convert.

Signed-off-by: Joseph Qi <joseph.qi@huawei.com>
Reported-by: Yiwen Jiang <jiangyiwen@huawei.com>
Reviewed-by: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Mark Fasheh <mfasheh@suse.de>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Tariq Saeed <tariq.x.saeed@oracle.com>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
Joseph Qi 2016-03-25 14:21:26 -07:00 committed by Linus Torvalds
parent 28888681b4
commit ac7cf246df
1 changed files with 10 additions and 1 deletions

View File

@ -262,6 +262,7 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm,
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);
@ -316,11 +317,19 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm,
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 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
* DLM_RECOVERING and retry convert */
if (status != DLM_NORMAL) {
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);
status = DLM_RECOVERING;
}
bail:
spin_unlock(&res->spinlock);