[Cluster-devel] GFS2: Move glock ref count drop out of finish_xmote

[Steven Whitehouse]

There have been a couple of instances reported recently where the
glock ref count has hit zero too soon. Since the only time when
this can happen is on the demote path (in other cases the ref count
is held elevated by the callers, as well as in the lock operation
itself) there is a good chance that the culprit is at the end
of finish_xmote.

This patch removes the ref count drop from the end of finish_xmote
and moves it into the callers of that function. This will ensure
that in future the ref count cannot be dropped too early.

Signed-off-by: Steven Whitehouse <swhiteho at redhat.com>

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index a3f90ad..3bc7d98 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -513,7 +513,6 @@ retry:
 			GLOCK_BUG_ON(gl, 1);
 		}
 		spin_unlock(&gl->gl_spin);
-		gfs2_glock_put(gl);
 		return;
 	}
 
@@ -524,8 +523,6 @@ retry:
 		if (glops->go_xmote_bh) {
 			spin_unlock(&gl->gl_spin);
 			rv = glops->go_xmote_bh(gl, gh);
-			if (rv == -EAGAIN)
-				return;
 			spin_lock(&gl->gl_spin);
 			if (rv) {
 				do_error(gl, rv);
@@ -540,7 +537,6 @@ out:
 	clear_bit(GLF_LOCK, &gl->gl_flags);
 out_locked:
 	spin_unlock(&gl->gl_spin);
-	gfs2_glock_put(gl);
 }
 
 static unsigned int gfs2_lm_lock(struct gfs2_sbd *sdp, void *lock,
@@ -600,7 +596,6 @@ __acquires(&gl->gl_spin)
 
 	if (!(ret & LM_OUT_ASYNC)) {
 		finish_xmote(gl, ret);
-		gfs2_glock_hold(gl);
 		if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
 			gfs2_glock_put(gl);
 	} else {
@@ -712,9 +707,12 @@ static void glock_work_func(struct work_struct *work)
 {
 	unsigned long delay = 0;
 	struct gfs2_glock *gl = container_of(work, struct gfs2_glock, gl_work.work);
+	int drop_ref = 0;
 
-	if (test_and_clear_bit(GLF_REPLY_PENDING, &gl->gl_flags))
+	if (test_and_clear_bit(GLF_REPLY_PENDING, &gl->gl_flags)) {
 		finish_xmote(gl, gl->gl_reply);
+		drop_ref = 1;
+	}
 	down_read(&gfs2_umount_flush_sem);
 	spin_lock(&gl->gl_spin);
 	if (test_and_clear_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&
@@ -732,6 +730,8 @@ static void glock_work_func(struct work_struct *work)
 	if (!delay ||
 	    queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0)
 		gfs2_glock_put(gl);
+	if (drop_ref)
+		gfs2_glock_put(gl);
 }
 
 /**