nfsd: don't allow CLOSE to proceed until refcount on stateid drops

Once we remove client_mutex protection, it'll be possible to have an
in-flight operation using an openstateid when a CLOSE call comes in.
If that happens, we can't just put the sc_file reference and clear its
pointer without risking an oops.

Fix this by ensuring that v4.0 CLOSE operations wait for the refcount
to drop before proceeding to do so.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>

fs/nfsd/nfs4state.c

@@ -85,6 +85,12 @@ static DEFINE_MUTEX(client_mutex);
  */
 static DEFINE_SPINLOCK(state_lock);
 
+/*
+ * A waitqueue for all in-progress 4.0 CLOSE operations that are waiting for
+ * the refcount on the open stateid to drop.
+ */
+static DECLARE_WAIT_QUEUE_HEAD(close_wq);
+
 static struct kmem_cache *openowner_slab;
 static struct kmem_cache *lockowner_slab;
 static struct kmem_cache *file_slab;
@@ -640,8 +646,10 @@ nfs4_put_stid(struct nfs4_stid *s)
 
 	might_lock(&clp->cl_lock);
 
-	if (!atomic_dec_and_lock(&s->sc_count, &clp->cl_lock))
+	if (!atomic_dec_and_lock(&s->sc_count, &clp->cl_lock)) {
+		wake_up_all(&close_wq);
 		return;
+	}
 	idr_remove(&clp->cl_stateids, s->sc_stateid.si_opaque.so_id);
 	spin_unlock(&clp->cl_lock);
 	s->sc_free(s);
@@ -3070,6 +3078,17 @@ move_to_close_lru(struct nfs4_ol_stateid *s, struct net *net)
 
 	dprintk("NFSD: move_to_close_lru nfs4_openowner %p\n", oo);
 
+	/*
+	 * We know that we hold one reference via nfsd4_close, and another
+	 * "persistent" reference for the client. If the refcount is higher
+	 * than 2, then there are still calls in progress that are using this
+	 * stateid. We can't put the sc_file reference until they are finished.
+	 * Wait for the refcount to drop to 2. Since it has been unhashed,
+	 * there should be no danger of the refcount going back up again at
+	 * this point.
+	 */
+	wait_event(close_wq, atomic_read(&s->st_stid.sc_count) == 2);
+
 	release_all_access(s);
 	if (s->st_stid.sc_file) {
 		put_nfs4_file(s->st_stid.sc_file);