ocfs2_dlm: Fix lockres ref counting bug

During umount, the umount thread migrates the lockres' and the dlm_thread
frees the empty lockres'. Due to a race, the reference counting on the
lockres goes awry leading to extra puts.

Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>

2 files changed, 6 insertions, 10 deletions

diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 6087c4749fee..dbbac184c261 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -138,8 +138,10 @@ static void dlm_unregister_domain_handlers(struct dlm_ctxt *dlm);
 
 void __dlm_unhash_lockres(struct dlm_lock_resource *lockres)
 {
-        hlist_del_init(&lockres->hash_node);
-        dlm_lockres_put(lockres);
+        if (!hlist_unhashed(&lockres->hash_node)) {
+                hlist_del_init(&lockres->hash_node);
+                dlm_lockres_put(lockres);
+        }
 }
 
 void __dlm_insert_lockres(struct dlm_ctxt *dlm,
diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c
index 6421a8fae1de..2b264c6ba039 100644
--- a/fs/ocfs2/dlm/dlmthread.c
+++ b/fs/ocfs2/dlm/dlmthread.c
@@ -256,20 +256,14 @@ static void dlm_run_purge_list(struct dlm_ctxt *dlm,
                         break;
                 }
 
-                mlog(0, "removing lockres %.*s:%p from purgelist\n",
-                     lockres->lockname.len, lockres->lockname.name, lockres);
-                list_del_init(&lockres->purge);
-                dlm_lockres_put(lockres);
-                dlm->purge_count--;
+                dlm_lockres_get(lockres);
 
                 /* This may drop and reacquire the dlm spinlock if it
                  * has to do migration. */
-                mlog(0, "calling dlm_purge_lockres!\n");
-                dlm_lockres_get(lockres);
                 if (dlm_purge_lockres(dlm, lockres))
                         BUG();
+
                 dlm_lockres_put(lockres);
-                mlog(0, "DONE calling dlm_purge_lockres!\n");
 
                 /* Avoid adding any scheduling latencies */
                 cond_resched_lock(&dlm->spinlock);