@@ -288,6 +288,19 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm,
status = DLM_DENIED;
goto bail;
}
+
+ if (lock->ml.type == type && lock->ml.convert_type == LKM_IVMODE) {
+ mlog(0, "last convert request returned DLM_RECOVERING, but "
+ "owner has already queued and sent ast to me. res %.*s, "
+ "(cookie=%u:%llu, type=%d, conv=%d)\n",
+ res->lockname.len, res->lockname.name,
+ dlm_get_lock_cookie_node(be64_to_cpu(lock->ml.cookie)),
+ dlm_get_lock_cookie_seq(be64_to_cpu(lock->ml.cookie)),
+ lock->ml.type, lock->ml.convert_type);
+ status = DLM_NORMAL;
+ goto bail;
+ }
+
res->state |= DLM_LOCK_RES_IN_PROGRESS;
/* move lock to local convert queue */
/* do not alter lock refcount. switching lists. */
@@ -2053,7 +2053,6 @@ void dlm_move_lockres_to_recovery_list(struct dlm_ctxt *dlm,
dlm_lock_get(lock);
if (lock->convert_pending) {
/* move converting lock back to granted */
- BUG_ON(i != DLM_CONVERTING_LIST);
mlog(0, "node died with convert pending "
"on %.*s. move back to granted list.\n",
res->lockname.len, res->lockname.name);
This is a note to let you know that I have just added a patch titled ocfs2/dlm: fix BUG in dlm_move_lockres_to_recovery_list to the linux-3.16.y-queue branch of the 3.16.y-ckt extended stable tree which can be found at: http://kernel.ubuntu.com/git/ubuntu/linux.git/log/?h=linux-3.16.y-queue This patch is scheduled to be released in version 3.16.7-ckt27. If you, or anyone else, feels it should not be added to this tree, please reply to this email. For more information about the 3.16.y-ckt tree, see https://wiki.ubuntu.com/Kernel/Dev/ExtendedStable Thanks. -Luis ---8<------------------------------------------------------------ From 45258c744da52d2ef15800388aadc36c6963cf08 Mon Sep 17 00:00:00 2001 From: Joseph Qi <joseph.qi@huawei.com> Date: Fri, 25 Mar 2016 14:21:29 -0700 Subject: ocfs2/dlm: fix BUG in dlm_move_lockres_to_recovery_list commit be12b299a83fc807bbaccd2bcb8ec50cbb0cb55c upstream. When master handles convert request, it queues ast first and then returns status. This may happen that the ast is sent before the request status because the above two messages are sent by two threads. And right after the ast is sent, if master down, it may trigger BUG in dlm_move_lockres_to_recovery_list in the requested node because ast handler moves it to grant list without clear lock->convert_pending. So remove BUG_ON statement and check if the ast is processed in dlmconvert_remote. Signed-off-by: Joseph Qi <joseph.qi@huawei.com> Reported-by: Yiwen Jiang <jiangyiwen@huawei.com> Cc: 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> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Luis Henriques <luis.henriques@canonical.com> --- fs/ocfs2/dlm/dlmconvert.c | 13 +++++++++++++ fs/ocfs2/dlm/dlmrecovery.c | 1 - 2 files changed, 13 insertions(+), 1 deletion(-)