dlm: fix missing lkb refcount handling

commit 1689c169134f4b5a39156122d799b7dca76d8ddb upstream.

We always call hold_lkb(lkb) if we increment lkb->lkb_wait_count.
So, we always need to call unhold_lkb(lkb) if we decrement
lkb->lkb_wait_count. This patch will add missing unhold_lkb(lkb) if we
decrement lkb->lkb_wait_count. In case of setting lkb->lkb_wait_count to
zero we need to countdown until reaching zero and call unhold_lkb(lkb).
The waiters list unhold_lkb(lkb) can be removed because it's done for
the last lkb_wait_count decrement iteration as it's done in
_remove_from_waiters().

This issue was discovered by a dlm gfs2 test case which use excessively
dlm_unlock(LKF_CANCEL) feature. Probably the lkb->lkb_wait_count value
never reached above 1 if this feature isn't used and so it was not
discovered before.

The testcase ended in a rsb on the rsb keep data structure with a
refcount of 1 but no lkb was associated with it, which is itself
an invalid behaviour. A side effect of that was a condition in which
the dlm was sending remove messages in a looping behaviour. With this
patch that has not been reproduced.

Cc: [email protected]
Signed-off-by: Alexander Aring <[email protected]>
Signed-off-by: David Teigland <[email protected]>
Signed-off-by: Greg Kroah-Hartman <[email protected]>

Author: Alexander Aring

fs/dlm/lock.c

@@ -1555,6 +1555,7 @@ static int _remove_from_waiters(struct dlm_lkb *lkb, int mstype,
 		lkb->lkb_wait_type = 0;
 		lkb->lkb_flags &= ~DLM_IFL_OVERLAP_CANCEL;
 		lkb->lkb_wait_count--;
+		unhold_lkb(lkb);
 		goto out_del;
 	}
 
@@ -1581,6 +1582,7 @@ static int _remove_from_waiters(struct dlm_lkb *lkb, int mstype,
 		log_error(ls, "remwait error %x reply %d wait_type %d overlap",
 			  lkb->lkb_id, mstype, lkb->lkb_wait_type);
 		lkb->lkb_wait_count--;
+		unhold_lkb(lkb);
 		lkb->lkb_wait_type = 0;
 	}
 
@@ -5314,11 +5316,16 @@ int dlm_recover_waiters_post(struct dlm_ls *ls)
 		lkb->lkb_flags &= ~DLM_IFL_OVERLAP_UNLOCK;
 		lkb->lkb_flags &= ~DLM_IFL_OVERLAP_CANCEL;
 		lkb->lkb_wait_type = 0;
-		lkb->lkb_wait_count = 0;
+		/* drop all wait_count references we still
+		 * hold a reference for this iteration.
+		 */
+		while (lkb->lkb_wait_count) {
+			lkb->lkb_wait_count--;
+			unhold_lkb(lkb);
+		}
 		mutex_lock(&ls->ls_waiters_mutex);
 		list_del_init(&lkb->lkb_wait_reply);
 		mutex_unlock(&ls->ls_waiters_mutex);
-		unhold_lkb(lkb); /* for waiters list */
 
 		if (oc || ou) {
 			/* do an unlock or cancel instead of resending */