@@ -502,8 +502,17 @@ int ocfs2_find_slot(struct ocfs2_super *osb)
trace_ocfs2_find_slot(osb->slot_num);
status = ocfs2_update_disk_slot(osb, si, osb->slot_num);
- if (status < 0)
+ if (status < 0) {
mlog_errno(status);
+ /*
+ * if write block failed, invalidate slot to avoid overwrite slot during
+ * dismount in case another node rightly has mounted
+ */
+ spin_lock(&osb->osb_lock);
+ ocfs2_invalidate_slot(si, osb->slot_num);
+ osb->slot_num = OCFS2_INVALID_SLOT;
+ spin_unlock(&osb->osb_lock);
+ }
bail:
return status;
The following case will lead to slot overwritten. N1 N2 mount ocfs2 volume, find and allocate slot 0, then set osb->slot_num to 0, begin to write slot info to disk mount ocfs2 volume, wait for super lock write block fail because of storage link down, unlock super lock got super lock and also allocate slot 0 then unlock super lock mount fail and then dismount, since osb->slot_num is 0, try to put invalid slot to disk. And it will succeed if storage link restores. N2 slot info is now overwritten Once another node say N3 mount, it will find and allocate slot 0 again, which will lead to mount hung because journal has already been locked by N2. so when write slot info failed, invalidate slot in advance to avoid overwrite slot. Signed-off-by: Yiwen Jiang <jiangyiwen@huawei.com> Reviewed-by: Joseph Qi <joseph.qi@huawei.com> --- fs/ocfs2/slot_map.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-)