net: sched: run ingress qdisc without locks

TC classifiers/actions were converted to RCU by John in the series:
http://thread.gmane.org/gmane.linux.network/329739/focus=329739
and many follow on patches.
This is the last patch from that series that finally drops
ingress spin_lock.

Single cpu ingress+u32 performance goes from 22.9 Mpps to 24.5 Mpps.

In two cpu case when both cores are receiving traffic on the same
device and go into the same ingress+u32 the performance jumps
from 4.5 + 4.5 Mpps to 23.5 + 23.5 Mpps
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/core/dev.c

@@ -3547,10 +3547,8 @@ static int ing_filter(struct sk_buff *skb, struct netdev_queue *rxq)
 
 	q = rcu_dereference(rxq->qdisc);
 	if (q != &noop_qdisc) {
-		spin_lock(qdisc_lock(q));
 		if (likely(!test_bit(__QDISC_STATE_DEACTIVATED, &q->state)))
 			result = qdisc_enqueue_root(skb, q);
-		spin_unlock(qdisc_lock(q));
 	}
 
 	return result;

net/sched/sch_ingress.c

@@ -65,11 +65,11 @@ static int ingress_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 
 	result = tc_classify(skb, fl, &res);
 
-	qdisc_bstats_update(sch, skb);
+	qdisc_bstats_update_cpu(sch, skb);
 	switch (result) {
 	case TC_ACT_SHOT:
 		result = TC_ACT_SHOT;
-		qdisc_qstats_drop(sch);
+		qdisc_qstats_drop_cpu(sch);
 		break;
 	case TC_ACT_STOLEN:
 	case TC_ACT_QUEUED:
@@ -91,6 +91,7 @@ static int ingress_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 static int ingress_init(struct Qdisc *sch, struct nlattr *opt)
 {
 	net_inc_ingress_queue();
+	sch->flags |= TCQ_F_CPUSTATS;
 
 	return 0;
 }