net_sched: gen_estimator: complete rewrite of rate estimators

1) Old code was hard to maintain, due to complex lock chains.
   (We probably will be able to remove some kfree_rcu() in callers)

2) Using a single timer to update all estimators does not scale.

3) Code was buggy on 32bit kernel (WRITE_ONCE() on 64bit quantity
   is not supposed to work well)

In this rewrite :

- I removed the RB tree that had to be scanned in
  gen_estimator_active(). qdisc dumps should be much faster.

- Each estimator has its own timer.

- Estimations are maintained in net_rate_estimator structure,
  instead of dirtying the qdisc. Minor, but part of the simplification.

- Reading the estimator uses RCU and a seqcount to provide proper
  support for 32bit kernels.

- We reduce memory need when estimators are not used, since
  we store a pointer, instead of the bytes/packets counters.

- xt_rateest_mt() no longer has to grab a spinlock.
  (In the future, xt_rateest_tg() could be switched to per cpu counters)

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 12 insertions, 9 deletions

diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index c990b73a6c85..0ba91d1ce994 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -142,8 +142,7 @@ static int tcf_act_police_init(struct net *net, struct nlattr *nla,
 			goto failure_unlock;
 	} else if (tb[TCA_POLICE_AVRATE] &&
 		   (ret == ACT_P_CREATED ||
-		    !gen_estimator_active(&police->tcf_bstats,
-					  &police->tcf_rate_est))) {
+		    !gen_estimator_active(&police->tcf_rate_est))) {
 		err = -EINVAL;
 		goto failure_unlock;
 	}
@@ -216,13 +215,17 @@ static int tcf_act_police(struct sk_buff *skb, const struct tc_action *a,
 	bstats_update(&police->tcf_bstats, skb);
 	tcf_lastuse_update(&police->tcf_tm);
 
-	if (police->tcfp_ewma_rate &&
-	    police->tcf_rate_est.bps >= police->tcfp_ewma_rate) {
-		police->tcf_qstats.overlimits++;
-		if (police->tcf_action == TC_ACT_SHOT)
-			police->tcf_qstats.drops++;
-		spin_unlock(&police->tcf_lock);
-		return police->tcf_action;
+	if (police->tcfp_ewma_rate) {
+		struct gnet_stats_rate_est64 sample;
+
+		if (!gen_estimator_read(&police->tcf_rate_est, &sample) ||
+		    sample.bps >= police->tcfp_ewma_rate) {
+			police->tcf_qstats.overlimits++;
+			if (police->tcf_action == TC_ACT_SHOT)
+				police->tcf_qstats.drops++;
+			spin_unlock(&police->tcf_lock);
+			return police->tcf_action;
+		}
 	}
 
 	if (qdisc_pkt_len(skb) <= police->tcfp_mtu) {