diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 9481f2c142e26ee1174653d673e6134edd9851da..e7eb4aa6ccc94e24f2d08d92d9df59db903664ab 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -51,7 +51,10 @@ struct qdisc_size_table {
 struct qdisc_skb_head {
 	struct sk_buff	*head;
 	struct sk_buff	*tail;
-	__u32		qlen;
+	union {
+		u32		qlen;
+		atomic_t	atomic_qlen;
+	};
 	spinlock_t	lock;
 };
 
@@ -408,27 +411,19 @@ 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)
+static inline u32 qdisc_qlen_sum(const struct Qdisc *q)
 {
-	__u32 qlen = q->qstats.qlen;
-	int i;
+	u32 qlen = q->qstats.qlen;
 
-	if (q->flags & TCQ_F_NOLOCK) {
-		for_each_possible_cpu(i)
-			qlen += per_cpu_ptr(q->cpu_qstats, i)->qlen;
-	} else {
+	if (q->flags & TCQ_F_NOLOCK)
+		qlen += atomic_read(&q->q.atomic_qlen);
+	else
 		qlen += q->q.qlen;
-	}
 
 	return qlen;
 }
@@ -825,14 +820,14 @@ static inline void qdisc_qstats_cpu_backlog_inc(struct Qdisc *sch,
 	this_cpu_add(sch->cpu_qstats->backlog, qdisc_pkt_len(skb));
 }
 
-static inline void qdisc_qstats_cpu_qlen_inc(struct Qdisc *sch)
+static inline void qdisc_qstats_atomic_qlen_inc(struct Qdisc *sch)
 {
-	this_cpu_inc(sch->cpu_qstats->qlen);
+	atomic_inc(&sch->q.atomic_qlen);
 }
 
-static inline void qdisc_qstats_cpu_qlen_dec(struct Qdisc *sch)
+static inline void qdisc_qstats_atomic_qlen_dec(struct Qdisc *sch)
 {
-	this_cpu_dec(sch->cpu_qstats->qlen);
+	atomic_dec(&sch->q.atomic_qlen);
 }
 
 static inline void qdisc_qstats_cpu_requeues_inc(struct Qdisc *sch)
diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c
index 9bf1b9ad17806dfaa579317408e5c4707d014cc0..ac679f74ba4754e69c51dd9b3fb9b23611782300 100644
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -291,7 +291,6 @@ __gnet_stats_copy_queue_cpu(struct gnet_stats_queue *qstats,
 	for_each_possible_cpu(i) {
 		const struct gnet_stats_queue *qcpu = per_cpu_ptr(q, i);
 
-		qstats->qlen = 0;
 		qstats->backlog += qcpu->backlog;
 		qstats->drops += qcpu->drops;
 		qstats->requeues += qcpu->requeues;
@@ -307,7 +306,6 @@ void __gnet_stats_copy_queue(struct gnet_stats_queue *qstats,
 	if (cpu) {
 		__gnet_stats_copy_queue_cpu(qstats, cpu);
 	} else {
-		qstats->qlen = q->qlen;
 		qstats->backlog = q->backlog;
 		qstats->drops = q->drops;
 		qstats->requeues = q->requeues;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 968a85fe4d4a9a0f5887989789cdd97ae7033f5a..de31f2f3b9730bc2e5d35648483d43ea2d86d008 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -68,7 +68,7 @@ static inline struct sk_buff *__skb_dequeue_bad_txq(struct Qdisc *q)
 			skb = __skb_dequeue(&q->skb_bad_txq);
 			if (qdisc_is_percpu_stats(q)) {
 				qdisc_qstats_cpu_backlog_dec(q, skb);
-				qdisc_qstats_cpu_qlen_dec(q);
+				qdisc_qstats_atomic_qlen_dec(q);
 			} else {
 				qdisc_qstats_backlog_dec(q, skb);
 				q->q.qlen--;
@@ -108,7 +108,7 @@ static inline void qdisc_enqueue_skb_bad_txq(struct Qdisc *q,
 
 	if (qdisc_is_percpu_stats(q)) {
 		qdisc_qstats_cpu_backlog_inc(q, skb);
-		qdisc_qstats_cpu_qlen_inc(q);
+		qdisc_qstats_atomic_qlen_inc(q);
 	} else {
 		qdisc_qstats_backlog_inc(q, skb);
 		q->q.qlen++;
@@ -147,7 +147,7 @@ static inline int dev_requeue_skb_locked(struct sk_buff *skb, struct Qdisc *q)
 
 		qdisc_qstats_cpu_requeues_inc(q);
 		qdisc_qstats_cpu_backlog_inc(q, skb);
-		qdisc_qstats_cpu_qlen_inc(q);
+		qdisc_qstats_atomic_qlen_inc(q);
 
 		skb = next;
 	}
@@ -252,7 +252,7 @@ static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate,
 			skb = __skb_dequeue(&q->gso_skb);
 			if (qdisc_is_percpu_stats(q)) {
 				qdisc_qstats_cpu_backlog_dec(q, skb);
-				qdisc_qstats_cpu_qlen_dec(q);
+				qdisc_qstats_atomic_qlen_dec(q);
 			} else {
 				qdisc_qstats_backlog_dec(q, skb);
 				q->q.qlen--;
@@ -645,7 +645,7 @@ static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc,
 	if (unlikely(err))
 		return qdisc_drop_cpu(skb, qdisc, to_free);
 
-	qdisc_qstats_cpu_qlen_inc(qdisc);
+	qdisc_qstats_atomic_qlen_inc(qdisc);
 	/* Note: skb can not be used after skb_array_produce(),
 	 * so we better not use qdisc_qstats_cpu_backlog_inc()
 	 */
@@ -670,7 +670,7 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc)
 	if (likely(skb)) {
 		qdisc_qstats_cpu_backlog_dec(qdisc, skb);
 		qdisc_bstats_cpu_update(qdisc, skb);
-		qdisc_qstats_cpu_qlen_dec(qdisc);
+		qdisc_qstats_atomic_qlen_dec(qdisc);
 	}
 
 	return skb;
@@ -714,7 +714,6 @@ static void pfifo_fast_reset(struct Qdisc *qdisc)
 		struct gnet_stats_queue *q = per_cpu_ptr(qdisc->cpu_qstats, i);
 
 		q->backlog = 0;
-		q->qlen = 0;
 	}
 }