/*
* net/sched/sch_fq.c Fair Queue Packet Scheduler (per flow pacing)
*
- * Copyright (C) 2013 Eric Dumazet <edumazet@google.com>
+ * Copyright (C) 2013-2015 Eric Dumazet <edumazet@google.com>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
#include <net/pkt_sched.h>
#include <net/sock.h>
#include <net/tcp_states.h>
+#include <net/tcp.h>
/*
* Per flow structure, dynamically allocated
u32 flow_refill_delay;
u32 flow_max_rate; /* optional max rate per flow */
u32 flow_plimit; /* max packets per flow */
+ u32 orphan_mask; /* mask for orphaned skb */
struct rb_root *fq_root;
u8 rate_enable;
u8 fq_trees_log;
if (unlikely((skb->priority & TC_PRIO_MAX) == TC_PRIO_CONTROL))
return &q->internal;
- if (unlikely(!sk)) {
+ /* SYNACK messages are attached to a listener socket.
+ * 1) They are not part of a 'flow' yet
+ * 2) We do not want to rate limit them (eg SYNFLOOD attack),
+ * especially if the listener set SO_MAX_PACING_RATE
+ * 3) We pretend they are orphaned
+ */
+ if (!sk || sk->sk_state == TCP_LISTEN) {
+ unsigned long hash = skb_get_hash(skb) & q->orphan_mask;
+
/* By forcing low order bit to 1, we make sure to not
* collide with a local flow (socket pointers are word aligned)
*/
- sk = (struct sock *)(skb_get_hash(skb) | 1L);
+ sk = (struct sock *)((hash << 1) | 1UL);
+ skb_orphan(skb);
}
root = &q->fq_root[hash_32((u32)(long)sk, q->fq_trees_log)];
goto begin;
}
- if (unlikely(f->head && now < f->time_next_packet)) {
+ skb = f->head;
+ if (unlikely(skb && now < f->time_next_packet &&
+ !skb_is_tcp_pure_ack(skb))) {
head->first = f->next;
fq_flow_set_throttled(q, f);
goto begin;
goto begin;
}
prefetch(&skb->end);
- f->time_next_packet = now;
f->credit -= qdisc_pkt_len(skb);
if (f->credit > 0 || !q->rate_enable)
goto out;
+ /* Do not pace locally generated ack packets */
+ if (skb_is_tcp_pure_ack(skb))
+ goto out;
+
rate = q->flow_max_rate;
- if (skb->sk && skb->sk->sk_state != TCP_TIME_WAIT)
+ if (skb->sk)
rate = min(skb->sk->sk_pacing_rate, rate);
if (rate != ~0U) {
q->flow_refill_delay = usecs_to_jiffies(usecs_delay);
}
+ if (tb[TCA_FQ_ORPHAN_MASK])
+ q->orphan_mask = nla_get_u32(tb[TCA_FQ_ORPHAN_MASK]);
+
if (!err) {
sch_tree_unlock(sch);
err = fq_resize(sch, fq_log);
q->delayed = RB_ROOT;
q->fq_root = NULL;
q->fq_trees_log = ilog2(1024);
+ q->orphan_mask = 1024 - 1;
qdisc_watchdog_init(&q->watchdog, sch);
if (opt)
nla_put_u32(skb, TCA_FQ_FLOW_MAX_RATE, q->flow_max_rate) ||
nla_put_u32(skb, TCA_FQ_FLOW_REFILL_DELAY,
jiffies_to_usecs(q->flow_refill_delay)) ||
+ nla_put_u32(skb, TCA_FQ_ORPHAN_MASK, q->orphan_mask) ||
nla_put_u32(skb, TCA_FQ_BUCKETS_LOG, q->fq_trees_log))
goto nla_put_failure;