diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index da2528036e2e..8f8c0afe529b 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -292,11 +292,31 @@ static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz)
 	BUILD_BUG_ON(sizeof(qcb->data) < sz);
 }
 
+static inline int qdisc_qlen_cpu(const struct Qdisc *q)
+{
+	return this_cpu_ptr(q->cpu_qstats)->qlen;
+}
+
 static inline int qdisc_qlen(const struct Qdisc *q)
 {
 	return q->q.qlen;
 }
 
+static inline int qdisc_qlen_sum(const struct Qdisc *q)
+{
+	__u32 qlen = 0;
+	int i;
+
+	if (q->flags & TCQ_F_NOLOCK) {
+		for_each_possible_cpu(i)
+			qlen += per_cpu_ptr(q->cpu_qstats, i)->qlen;
+	} else {
+		qlen = q->q.qlen;
+	}
+
+	return qlen;
+}
+
 static inline struct qdisc_skb_cb *qdisc_skb_cb(const struct sk_buff *skb)
 {
 	return (struct qdisc_skb_cb *)skb->cb;
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index a48ca41b7ecf..c669bb3b89b2 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -797,7 +797,8 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid,
 		goto nla_put_failure;
 	if (q->ops->dump && q->ops->dump(q, skb) < 0)
 		goto nla_put_failure;
-	qlen = q->q.qlen;
+
+	qlen = qdisc_qlen_sum(q);
 
 	stab = rtnl_dereference(q->stab);
 	if (stab && qdisc_dump_stab(skb, stab) < 0)