diff options
Diffstat (limited to 'net/sched/sch_fq.c')
-rw-r--r-- | net/sched/sch_fq.c | 103 |
1 files changed, 30 insertions, 73 deletions
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 4808713c73b9..4b1af706896c 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -92,8 +92,8 @@ struct fq_sched_data { u32 quantum; u32 initial_quantum; u32 flow_refill_delay; - u32 flow_max_rate; /* optional max rate per flow */ u32 flow_plimit; /* max packets per flow */ + unsigned long flow_max_rate; /* optional max rate per flow */ u32 orphan_mask; /* mask for orphaned skb */ u32 low_rate_threshold; struct rb_root *fq_root; @@ -106,7 +106,6 @@ struct fq_sched_data { u64 stat_gc_flows; u64 stat_internal_packets; - u64 stat_tcp_retrans; u64 stat_throttled; u64 stat_flows_plimit; u64 stat_pkts_too_long; @@ -319,7 +318,7 @@ static struct sk_buff *fq_dequeue_head(struct Qdisc *sch, struct fq_flow *flow) if (skb) { flow->head = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); flow->qlen--; qdisc_qstats_backlog_dec(sch, skb); sch->q.qlen--; @@ -327,62 +326,17 @@ static struct sk_buff *fq_dequeue_head(struct Qdisc *sch, struct fq_flow *flow) return skb; } -/* We might add in the future detection of retransmits - * For the time being, just return false - */ -static bool skb_is_retransmit(struct sk_buff *skb) -{ - return false; -} - -/* add skb to flow queue - * flow queue is a linked list, kind of FIFO, except for TCP retransmits - * We special case tcp retransmits to be transmitted before other packets. - * We rely on fact that TCP retransmits are unlikely, so we do not waste - * a separate queue or a pointer. - * head-> [retrans pkt 1] - * [retrans pkt 2] - * [ normal pkt 1] - * [ normal pkt 2] - * [ normal pkt 3] - * tail-> [ normal pkt 4] - */ static void flow_queue_add(struct fq_flow *flow, struct sk_buff *skb) { - struct sk_buff *prev, *head = flow->head; + struct sk_buff *head = flow->head; skb->next = NULL; - if (!head) { + if (!head) flow->head = skb; - flow->tail = skb; - return; - } - if (likely(!skb_is_retransmit(skb))) { + else flow->tail->next = skb; - flow->tail = skb; - return; - } - /* This skb is a tcp retransmit, - * find the last retrans packet in the queue - */ - prev = NULL; - while (skb_is_retransmit(head)) { - prev = head; - head = head->next; - if (!head) - break; - } - if (!prev) { /* no rtx packet in queue, become the new head */ - skb->next = flow->head; - flow->head = skb; - } else { - if (prev == flow->tail) - flow->tail = skb; - else - skb->next = prev->next; - prev->next = skb; - } + flow->tail = skb; } static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch, @@ -401,8 +355,6 @@ static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch, } f->qlen++; - if (skb_is_retransmit(skb)) - q->stat_tcp_retrans++; qdisc_qstats_backlog_inc(sch, skb); if (fq_flow_is_detached(f)) { struct sock *sk = skb->sk; @@ -464,7 +416,8 @@ static struct sk_buff *fq_dequeue(struct Qdisc *sch) struct fq_flow_head *head; struct sk_buff *skb; struct fq_flow *f; - u32 rate, plen; + unsigned long rate; + u32 plen; skb = fq_dequeue_head(sch, &q->internal); if (skb) @@ -491,11 +444,16 @@ begin: } 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; + if (skb) { + u64 time_next_packet = max_t(u64, ktime_to_ns(skb->tstamp), + f->time_next_packet); + + if (now < time_next_packet) { + head->first = f->next; + f->time_next_packet = time_next_packet; + fq_flow_set_throttled(q, f); + goto begin; + } } skb = fq_dequeue_head(sch, f); @@ -513,11 +471,7 @@ begin: prefetch(&skb->end); f->credit -= qdisc_pkt_len(skb); - if (!q->rate_enable) - goto out; - - /* Do not pace locally generated ack packets */ - if (skb_is_tcp_pure_ack(skb)) + if (ktime_to_ns(skb->tstamp) || !q->rate_enable) goto out; rate = q->flow_max_rate; @@ -532,11 +486,11 @@ begin: if (f->credit > 0) goto out; } - if (rate != ~0U) { + if (rate != ~0UL) { u64 len = (u64)plen * NSEC_PER_SEC; if (likely(rate)) - do_div(len, rate); + len = div64_ul(len, rate); /* Since socket rate can change later, * clamp the delay to 1 second. * Really, providers of too big packets should be fixed ! @@ -748,9 +702,11 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt, pr_warn_ratelimited("sch_fq: defrate %u ignored.\n", nla_get_u32(tb[TCA_FQ_FLOW_DEFAULT_RATE])); - if (tb[TCA_FQ_FLOW_MAX_RATE]) - q->flow_max_rate = nla_get_u32(tb[TCA_FQ_FLOW_MAX_RATE]); + if (tb[TCA_FQ_FLOW_MAX_RATE]) { + u32 rate = nla_get_u32(tb[TCA_FQ_FLOW_MAX_RATE]); + q->flow_max_rate = (rate == ~0U) ? ~0UL : rate; + } if (tb[TCA_FQ_LOW_RATE_THRESHOLD]) q->low_rate_threshold = nla_get_u32(tb[TCA_FQ_LOW_RATE_THRESHOLD]); @@ -813,7 +769,7 @@ static int fq_init(struct Qdisc *sch, struct nlattr *opt, q->quantum = 2 * psched_mtu(qdisc_dev(sch)); q->initial_quantum = 10 * psched_mtu(qdisc_dev(sch)); q->flow_refill_delay = msecs_to_jiffies(40); - q->flow_max_rate = ~0U; + q->flow_max_rate = ~0UL; q->time_next_delayed_flow = ~0ULL; q->rate_enable = 1; q->new_flows.first = NULL; @@ -823,7 +779,7 @@ static int fq_init(struct Qdisc *sch, struct nlattr *opt, q->fq_trees_log = ilog2(1024); q->orphan_mask = 1024 - 1; q->low_rate_threshold = 550000 / 8; - qdisc_watchdog_init(&q->watchdog, sch); + qdisc_watchdog_init_clockid(&q->watchdog, sch, CLOCK_MONOTONIC); if (opt) err = fq_change(sch, opt, extack); @@ -849,7 +805,8 @@ static int fq_dump(struct Qdisc *sch, struct sk_buff *skb) 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_MAX_RATE, q->flow_max_rate) || + nla_put_u32(skb, TCA_FQ_FLOW_MAX_RATE, + min_t(unsigned long, q->flow_max_rate, ~0U)) || 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) || @@ -873,7 +830,7 @@ static int fq_dump_stats(struct Qdisc *sch, struct gnet_dump *d) st.gc_flows = q->stat_gc_flows; st.highprio_packets = q->stat_internal_packets; - st.tcp_retrans = q->stat_tcp_retrans; + st.tcp_retrans = 0; st.throttled = q->stat_throttled; st.flows_plimit = q->stat_flows_plimit; st.pkts_too_long = q->stat_pkts_too_long; |