pkt_sched: fq: fix non TCP flows pacing

Steinar reported FQ pacing was not working for UDP flows.

It looks like the initial sk->sk_pacing_rate value of 0 was
a wrong choice. We should init it to ~0U (unlimited)

Then, TCA_FQ_FLOW_DEFAULT_RATE should be removed because it makes
no real sense. The default rate is really unlimited, and we
need to avoid a zero divide.

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

diff --git a/net/core/sock.c b/net/core/sock.c
index 5b6beba494a350cb28adfc7724487f1a13e6c011..0b39e7ae43837e602ff473b641675fbf22b83b5c 100644 (file)
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2319,6 +2319,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
        sk->sk_ll_usec          =       sysctl_net_busy_read;
 #endif
 
+       sk->sk_pacing_rate = ~0U;
        /*
         * Before updating sk_refcnt, we must commit prior changes to memory
         * (Documentation/RCU/rculist_nulls.txt for details)

diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 48501a2baf75ed050a2c7da081d458c39f116f60..a9dfdda9ed1d55d17643f36ba05d9ac04ce1557d 100644 (file)
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -472,20 +472,16 @@ begin:
        if (f->credit > 0 || !q->rate_enable)
                goto out;
 
-       if (skb->sk && skb->sk->sk_state != TCP_TIME_WAIT) {
-               rate = skb->sk->sk_pacing_rate ?: q->flow_default_rate;
+       rate = q->flow_max_rate;
+       if (skb->sk && skb->sk->sk_state != TCP_TIME_WAIT)
+               rate = min(skb->sk->sk_pacing_rate, rate);
 
-               rate = min(rate, q->flow_max_rate);
-       } else {
-               rate = q->flow_max_rate;
-               if (rate == ~0U)
-                       goto out;
-       }
-       if (rate) {
+       if (rate != ~0U) {
                u32 plen = max(qdisc_pkt_len(skb), q->quantum);
                u64 len = (u64)plen * NSEC_PER_SEC;
 
-               do_div(len, rate);
+               if (likely(rate))
+                       do_div(len, rate);
                /* Since socket rate can change later,
                 * clamp the delay to 125 ms.
                 * TODO: maybe segment the too big skb, as in commit
@@ -735,12 +731,14 @@ static int fq_dump(struct Qdisc *sch, struct sk_buff *skb)
        if (opts == NULL)
                goto nla_put_failure;
 
+       /* TCA_FQ_FLOW_DEFAULT_RATE is not used anymore,
+        * do not bother giving its value
+        */
        if (nla_put_u32(skb, TCA_FQ_PLIMIT, sch->limit) ||
            nla_put_u32(skb, TCA_FQ_FLOW_PLIMIT, q->flow_plimit) ||
            nla_put_u32(skb, TCA_FQ_QUANTUM, q->quantum) ||
            nla_put_u32(skb, TCA_FQ_INITIAL_QUANTUM, q->initial_quantum) ||
            nla_put_u32(skb, TCA_FQ_RATE_ENABLE, q->rate_enable) ||
-           nla_put_u32(skb, TCA_FQ_FLOW_DEFAULT_RATE, q->flow_default_rate) ||
            nla_put_u32(skb, TCA_FQ_FLOW_MAX_RATE, q->flow_max_rate) ||
            nla_put_u32(skb, TCA_FQ_BUCKETS_LOG, q->fq_trees_log))
                goto nla_put_failure;