net: sched: always do stats accounting according to TCQ_F_CPUSTATS

The core sched implementation checks independently for NOLOCK flag
to acquire/release the root spin lock and for qdisc_is_percpu_stats()
to account per CPU values in many places.

This change update the last few places checking the TCQ_F_NOLOCK to
do per CPU stats accounting according to qdisc_is_percpu_stats()
value.

The above allows to clean dev_requeue_skb() implementation a bit
and makes stats update always consistent with a single flag.

v1 -> v2:
 - do not move qdisc_is_empty definition, fix build issue
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/sch_generic.h

@@ -146,9 +146,14 @@ static inline bool qdisc_is_running(struct Qdisc *qdisc)
 	return (raw_read_seqcount(&qdisc->running) & 1) ? true : false;
 }
 
+static inline bool qdisc_is_percpu_stats(const struct Qdisc *q)
+{
+	return q->flags & TCQ_F_CPUSTATS;
+}
+
 static inline bool qdisc_is_empty(const struct Qdisc *qdisc)
 {
-	if (qdisc->flags & TCQ_F_NOLOCK)
+	if (qdisc_is_percpu_stats(qdisc))
 		return qdisc->empty;
 	return !qdisc->q.qlen;
 }
@@ -490,7 +495,7 @@ static inline u32 qdisc_qlen_sum(const struct Qdisc *q)
 {
 	u32 qlen = q->qstats.qlen;
 
-	if (q->flags & TCQ_F_NOLOCK)
+	if (qdisc_is_percpu_stats(q))
 		qlen += atomic_read(&q->q.atomic_qlen);
 	else
 		qlen += q->q.qlen;
@@ -817,11 +822,6 @@ static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	return sch->enqueue(skb, sch, to_free);
 }
 
-static inline bool qdisc_is_percpu_stats(const struct Qdisc *q)
-{
-	return q->flags & TCQ_F_CPUSTATS;
-}
-
 static inline void _bstats_update(struct gnet_stats_basic_packed *bstats,
 				  __u64 bytes, __u32 packets)
 {
@@ -1113,8 +1113,13 @@ static inline struct sk_buff *qdisc_dequeue_peeked(struct Qdisc *sch)
 
 	if (skb) {
 		skb = __skb_dequeue(&sch->gso_skb);
+		if (qdisc_is_percpu_stats(sch)) {
+			qdisc_qstats_cpu_backlog_dec(sch, skb);
+			qdisc_qstats_atomic_qlen_dec(sch);
+		} else {
 			qdisc_qstats_backlog_dec(sch, skb);
 			sch->q.qlen--;
+		}
 	} else {
 		skb = sch->dequeue(sch);
 	}

net/sched/sch_generic.c

@@ -118,52 +118,36 @@ static inline void qdisc_enqueue_skb_bad_txq(struct Qdisc *q,
 		spin_unlock(lock);
 }
 
-static inline int __dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q)
+static inline void dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q)
 {
-	while (skb) {
-		struct sk_buff *next = skb->next;
-
-		__skb_queue_tail(&q->gso_skb, skb);
-		q->qstats.requeues++;
-		qdisc_qstats_backlog_inc(q, skb);
-		q->q.qlen++;	/* it's still part of the queue */
+	spinlock_t *lock = NULL;
 
-		skb = next;
+	if (q->flags & TCQ_F_NOLOCK) {
+		lock = qdisc_lock(q);
+		spin_lock(lock);
 	}
-	__netif_schedule(q);
-
-	return 0;
-}
-
-static inline int dev_requeue_skb_locked(struct sk_buff *skb, struct Qdisc *q)
-{
-	spinlock_t *lock = qdisc_lock(q);
 
-	spin_lock(lock);
 	while (skb) {
 		struct sk_buff *next = skb->next;
 
 		__skb_queue_tail(&q->gso_skb, skb);
 
+		/* it's still part of the queue */
+		if (qdisc_is_percpu_stats(q)) {
 			qdisc_qstats_cpu_requeues_inc(q);
 			qdisc_qstats_cpu_backlog_inc(q, skb);
 			qdisc_qstats_atomic_qlen_inc(q);
+		} else {
+			q->qstats.requeues++;
+			qdisc_qstats_backlog_inc(q, skb);
+			q->q.qlen++;
+		}
 
 		skb = next;
 	}
+	if (lock)
 		spin_unlock(lock);
-
 	__netif_schedule(q);
-
-	return 0;
-}
-
-static inline int dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q)
-{
-	if (q->flags & TCQ_F_NOLOCK)
-		return dev_requeue_skb_locked(skb, q);
-	else
-		return __dev_requeue_skb(skb, q);
 }
 
 static void try_bulk_dequeue_skb(struct Qdisc *q,