Home Home > GIT Browse
summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorChangwei Ge <gechangwei@live.cn>2019-09-23 15:33:37 -0700
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2019-10-07 18:57:16 +0200
commit52132ff52cadb32edf063c1b4d8a7a6c00d85e4d (patch)
tree8216445fa5e119b7977a8b83b343911c13502772
parentd4a546452dccdbc824635f9649b6aef8b65b25fb (diff)
ocfs2: wait for recovering done after direct unlock request
[ Upstream commit 0a3775e4f883912944481cf2ef36eb6383a9cc74 ] There is a scenario causing ocfs2 umount hang when multiple hosts are rebooting at the same time. NODE1 NODE2 NODE3 send unlock requset to NODE2 dies become recovery master recover NODE2 find NODE2 dead mark resource RECOVERING directly remove lock from grant list calculate usage but RECOVERING marked **miss the window of purging clear RECOVERING To reproduce this issue, crash a host and then umount ocfs2 from another node. To solve this, just let unlock progress wait for recovery done. Link: http://lkml.kernel.org/r/1550124866-20367-1-git-send-email-gechangwei@live.cn Signed-off-by: Changwei Ge <gechangwei@live.cn> Reviewed-by: Joseph Qi <joseph.qi@linux.alibaba.com> Cc: Mark Fasheh <mark@fasheh.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Junxiao Bi <junxiao.bi@oracle.com> Cc: Changwei Ge <gechangwei@live.cn> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
-rw-r--r--fs/ocfs2/dlm/dlmunlock.c23
1 files changed, 19 insertions, 4 deletions
diff --git a/fs/ocfs2/dlm/dlmunlock.c b/fs/ocfs2/dlm/dlmunlock.c
index 63d701cd1e2e..c8e9b7031d9a 100644
--- a/fs/ocfs2/dlm/dlmunlock.c
+++ b/fs/ocfs2/dlm/dlmunlock.c
@@ -105,7 +105,8 @@ static enum dlm_status dlmunlock_common(struct dlm_ctxt *dlm,
enum dlm_status status;
int actions = 0;
int in_use;
- u8 owner;
+ u8 owner;
+ int recovery_wait = 0;
mlog(0, "master_node = %d, valblk = %d\n", master_node,
flags & LKM_VALBLK);
@@ -208,9 +209,12 @@ static enum dlm_status dlmunlock_common(struct dlm_ctxt *dlm,
}
if (flags & LKM_CANCEL)
lock->cancel_pending = 0;
- else
- lock->unlock_pending = 0;
-
+ else {
+ if (!lock->unlock_pending)
+ recovery_wait = 1;
+ else
+ lock->unlock_pending = 0;
+ }
}
/* get an extra ref on lock. if we are just switching
@@ -244,6 +248,17 @@ leave:
spin_unlock(&res->spinlock);
wake_up(&res->wq);
+ if (recovery_wait) {
+ spin_lock(&res->spinlock);
+ /* Unlock request will directly succeed after owner dies,
+ * and the lock is already removed from grant list. We have to
+ * wait for RECOVERING done or we miss the chance to purge it
+ * since the removement is much faster than RECOVERING proc.
+ */
+ __dlm_wait_on_lockres_flags(res, DLM_LOCK_RES_RECOVERING);
+ spin_unlock(&res->spinlock);
+ }
+
/* let the caller's final dlm_lock_put handle the actual kfree */
if (actions & DLM_UNLOCK_FREE_LOCK) {
/* this should always be coupled with list removal */