net: sched: helpers to sum qlen and qlen for per cpu logic

Add qdisc qlen helper routines for lockless qdiscs to use.

The qdisc qlen is no longer used in the hotpath but it is reported
via stats query on the qdisc so it still needs to be tracked. This
adds the per cpu operations needed along with a helper to return
the summation of per cpu stats.
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

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;

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)