From 86b652b93adb57d8fed8edd532ed2eb8a791950d Mon Sep 17 00:00:00 2001 From: piaojun Date: Tue, 2 Aug 2016 14:02:13 -0700 Subject: ocfs2/dlm: disable BUG_ON when DLM_LOCK_RES_DROPPING_REF is cleared before dlm_deref_lockres_done_handler We found a BUG situation in which DLM_LOCK_RES_DROPPING_REF is cleared unexpected that described below. To solve the bug, we disable the BUG_ON and purge lockres in dlm_do_local_recovery_cleanup. Node 1 Node 2(master) dlm_purge_lockres dlm_deref_lockres_handler DLM_LOCK_RES_SETREF_INPROG is set response DLM_DEREF_RESPONSE_INPROG receive DLM_DEREF_RESPONSE_INPROG stop puring in dlm_purge_lockres and wait for DLM_DEREF_RESPONSE_DONE dispatch dlm_deref_lockres_worker response DLM_DEREF_RESPONSE_DONE receive DLM_DEREF_RESPONSE_DONE and prepare to purge lockres Node 2 goes down find Node2 down and do local clean up for Node2: dlm_do_local_recovery_cleanup -> clear DLM_LOCK_RES_DROPPING_REF when purging lockres, BUG_ON happens because DLM_LOCK_RES_DROPPING_REF is clear: dlm_deref_lockres_done_handler ->BUG_ON(!(res->state & DLM_LOCK_RES_DROPPING_REF)); [akpm@linux-foundation.org: fix duplicated write to `ret'] Fixes: 60d663cb5273 ("ocfs2/dlm: add DEREF_DONE message") Link: http://lkml.kernel.org/r/57845055.9080702@huawei.com Signed-off-by: Jun Piao Reviewed-by: Joseph Qi Reviewed-by: Jiufei Xue Reviewed-by: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/dlm/dlmmaster.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'fs/ocfs2/dlm') diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 13719d3f35f8..525dc06468c4 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -2416,7 +2416,17 @@ int dlm_deref_lockres_done_handler(struct o2net_msg *msg, u32 len, void *data, } spin_lock(&res->spinlock); - BUG_ON(!(res->state & DLM_LOCK_RES_DROPPING_REF)); + if (!(res->state & DLM_LOCK_RES_DROPPING_REF)) { + spin_unlock(&res->spinlock); + spin_unlock(&dlm->spinlock); + mlog(ML_NOTICE, "%s:%.*s: node %u sends deref done " + "but it is already derefed!\n", dlm->name, + res->lockname.len, res->lockname.name, node); + dlm_lockres_put(res); + ret = 0; + goto done; + } + if (!list_empty(&res->purge)) { mlog(0, "%s: Removing res %.*s from purgelist\n", dlm->name, res->lockname.len, res->lockname.name); @@ -2456,7 +2466,6 @@ int dlm_deref_lockres_done_handler(struct o2net_msg *msg, u32 len, void *data, spin_unlock(&dlm->spinlock); ret = 0; - done: dlm_put(dlm); return ret; -- cgit v1.2.3