From: Joseph Qi <joseph.qi@huawei.com>
To: ocfs2-devel@oss.oracle.com
Subject: [Ocfs2-devel] [PATCH] ocfs2/dlm: fix race between purge and get lock resource
Date: Sat, 25 Apr 2015 15:05:15 +0800 [thread overview]
Message-ID: <553B3CAB.9020102@huawei.com> (raw)
There is a race between purge and get lock resource, which will lead to
ast unfinished and system hung. The case is described below:
mkdir dlm_thread
-----------------------------------------------------------------------
o2cb_dlm_lock |
-> dlmlock |
-> dlm_get_lock_resource |
-> __dlm_lookup_lockres_full |
-> spin_unlock(&dlm->spinlock) |
| dlm_run_purge_list
| -> dlm_purge_lockres
| -> dlm_drop_lockres_ref
| -> spin_lock(&dlm->spinlock)
| -> spin_lock(&res->spinlock)
| -> ~DLM_LOCK_RES_DROPPING_REF
| -> spin_unlock(&res->spinlock)
| -> spin_unlock(&dlm->spinlock)
-> spin_lock(&tmpres->spinlock)|
DLM_LOCK_RES_DROPPING_REF cleared |
-> spin_unlock(&tmpres->spinlock) |
return the purged lockres |
So after this, once ast comes, it will ingore the ast because the
lockres cannot be found anymore. Thus the OCFS2_LOCK_BUSY won't be
cleared and corresponding thread hangs.
The &dlm->spinlock was hold when checking DLM_LOCK_RES_DROPPING_REF at
the very begining. And commit 7b791d6856 (ocfs2/dlm: Fix race during
lockres mastery) moved it up because of the possible wait.
So take the &dlm->spinlock and introduce a new wait function to fix the
race.
Signed-off-by: Joseph Qi <joseph.qi@huawei.com>
Reviewed-by: joyce.xue <xuejiufei@huawei.com>
---
fs/ocfs2/dlm/dlmcommon.h | 2 ++
fs/ocfs2/dlm/dlmmaster.c | 13 +++++++++----
fs/ocfs2/dlm/dlmthread.c | 23 +++++++++++++++++++++++
3 files changed, 34 insertions(+), 4 deletions(-)
diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
index e88ccf8..c6b76f4 100644
--- a/fs/ocfs2/dlm/dlmcommon.h
+++ b/fs/ocfs2/dlm/dlmcommon.h
@@ -1014,6 +1014,8 @@ void dlm_move_lockres_to_recovery_list(struct dlm_ctxt *dlm,
/* will exit holding res->spinlock, but may drop in function */
void __dlm_wait_on_lockres_flags(struct dlm_lock_resource *res, int flags);
+void __dlm_wait_on_lockres_flags_new(struct dlm_ctxt *dlm,
+ struct dlm_lock_resource *res, int flags);
/* will exit holding res->spinlock, but may drop in function */
static inline void __dlm_wait_on_lockres(struct dlm_lock_resource *res)
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index a6944b2..9a5f45d 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -755,13 +755,16 @@ lookup:
spin_lock(&dlm->spinlock);
tmpres = __dlm_lookup_lockres_full(dlm, lockid, namelen, hash);
if (tmpres) {
- spin_unlock(&dlm->spinlock);
spin_lock(&tmpres->spinlock);
/* Wait on the thread that is mastering the resource */
if (tmpres->owner == DLM_LOCK_RES_OWNER_UNKNOWN) {
- __dlm_wait_on_lockres(tmpres);
+ __dlm_wait_on_lockres_flags_new(dlm, tmpres,
+ (DLM_LOCK_RES_IN_PROGRESS|
+ DLM_LOCK_RES_RECOVERING|
+ DLM_LOCK_RES_MIGRATING));
BUG_ON(tmpres->owner == DLM_LOCK_RES_OWNER_UNKNOWN);
spin_unlock(&tmpres->spinlock);
+ spin_unlock(&dlm->spinlock);
dlm_lockres_put(tmpres);
tmpres = NULL;
goto lookup;
@@ -770,9 +773,10 @@ lookup:
/* Wait on the resource purge to complete before continuing */
if (tmpres->state & DLM_LOCK_RES_DROPPING_REF) {
BUG_ON(tmpres->owner == dlm->node_num);
- __dlm_wait_on_lockres_flags(tmpres,
- DLM_LOCK_RES_DROPPING_REF);
+ __dlm_wait_on_lockres_flags_new(dlm, tmpres,
+ DLM_LOCK_RES_DROPPING_REF);
spin_unlock(&tmpres->spinlock);
+ spin_unlock(&dlm->spinlock);
dlm_lockres_put(tmpres);
tmpres = NULL;
goto lookup;
@@ -782,6 +786,7 @@ lookup:
dlm_lockres_grab_inflight_ref(dlm, tmpres);
spin_unlock(&tmpres->spinlock);
+ spin_unlock(&dlm->spinlock);
if (res)
dlm_lockres_put(res);
res = tmpres;
diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c
index 69aac6f..505730a 100644
--- a/fs/ocfs2/dlm/dlmthread.c
+++ b/fs/ocfs2/dlm/dlmthread.c
@@ -77,6 +77,29 @@ repeat:
__set_current_state(TASK_RUNNING);
}
+void __dlm_wait_on_lockres_flags_new(struct dlm_ctxt *dlm,
+ struct dlm_lock_resource *res, int flags)
+{
+ DECLARE_WAITQUEUE(wait, current);
+
+ assert_spin_locked(&dlm->spinlock);
+ assert_spin_locked(&res->spinlock);
+
+ add_wait_queue(&res->wq, &wait);
+repeat:
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ if (res->state & flags) {
+ spin_unlock(&res->spinlock);
+ spin_unlock(&dlm->spinlock);
+ schedule();
+ spin_lock(&dlm->spinlock);
+ spin_lock(&res->spinlock);
+ goto repeat;
+ }
+ remove_wait_queue(&res->wq, &wait);
+ __set_current_state(TASK_RUNNING);
+}
+
int __dlm_lockres_has_locks(struct dlm_lock_resource *res)
{
if (list_empty(&res->granted) &&
--
1.8.4.3
next reply other threads:[~2015-04-25 7:05 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-04-25 7:05 Joseph Qi [this message]
2015-04-25 8:09 ` [Ocfs2-devel] [PATCH] ocfs2/dlm: fix race between purge and get lock resource Greg KH
2015-04-28 20:32 ` Andrew Morton
2015-04-29 0:51 ` Joseph Qi
2015-04-30 7:04 ` Junxiao Bi
2015-04-29 21:44 ` Mark Fasheh
2015-04-30 2:15 ` Joseph Qi
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=553B3CAB.9020102@huawei.com \
--to=joseph.qi@huawei.com \
--cc=ocfs2-devel@oss.oracle.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox