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>

1 files changed, 14 insertions, 9 deletions

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 7ecb6127e980..ed56474cfe3b 100644
--- a/include/net/sch_generic.h
+++ b/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);
-		qdisc_qstats_backlog_dec(sch, skb);
-		sch->q.qlen--;
+		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);
 	}