/* * Codel - The Controlled-Delay Active Queue Management algorithm * * Copyright (C) 2011-2012 Kathleen Nichols * Copyright (C) 2011-2012 Van Jacobson * * Implemented on linux by : * Copyright (C) 2012 Michael D. Taht * Copyright (C) 2012,2015 Eric Dumazet * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions, and the following disclaimer, * without modification. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. The names of the authors may not be used to endorse or promote products * derived from this software without specific prior written permission. * * Alternatively, provided that this notice is retained in full, this * software may be distributed under the terms of the GNU General * Public License ("GPL") version 2, in which case the provisions of the * GPL apply INSTEAD OF those given above. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH * DAMAGE. * */ #include #include #include #include #include #include #include #include #include #include #include #define DEFAULT_CODEL_LIMIT 1000 struct codel_sched_data { struct codel_params params; struct codel_vars vars; struct codel_stats stats; u32 drop_overlimit; }; /* This is the specific function called from codel_dequeue() * to dequeue a packet from queue. Note: backlog is handled in * codel, we dont need to reduce it here. */ static struct sk_buff *dequeue_func(struct codel_vars *vars, void *ctx) { struct Qdisc *sch = ctx; struct sk_buff *skb = __qdisc_dequeue_head(&sch->q); if (skb) sch->qstats.backlog -= qdisc_pkt_len(skb); prefetch(&skb->end); /* we'll need skb_shinfo() */ return skb; } static void drop_func(struct sk_buff *skb, void *ctx) { struct Qdisc *sch = ctx; kfree_skb(skb); qdisc_qstats_drop(sch); } static struct sk_buff *codel_qdisc_dequeue(struct Qdisc *sch) { struct codel_sched_data *q = qdisc_priv(sch); struct sk_buff *skb; skb = codel_dequeue(sch, &sch->qstats.backlog, &q->params, &q->vars, &q->stats, qdisc_pkt_len, codel_get_enqueue_time, drop_func, dequeue_func); /* We cant call qdisc_tree_reduce_backlog() if our qlen is 0, * or HTB crashes. Defer it for next round. */ if (q->stats.drop_count && sch->q.qlen) { qdisc_tree_reduce_backlog(sch, q->stats.drop_count, q->stats.drop_len); q->stats.drop_count = 0; q->stats.drop_len = 0; } if (skb) qdisc_bstats_update(sch, skb); return skb; } static int codel_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { struct codel_sched_data *q; if (likely(qdisc_qlen(sch) < sch->limit)) { codel_set_enqueue_time(skb); return qdisc_enqueue_tail(skb, sch); } q = qdisc_priv(sch); q->drop_overlimit++; return qdisc_drop(skb, sch, to_free); } static const struct nla_policy codel_policy[TCA_CODEL_MAX + 1] = { [TCA_CODEL_TARGET] = { .type = NLA_U32 }, [TCA_CODEL_LIMIT] = { .type = NLA_U32 }, [TCA_CODEL_INTERVAL] = { .type = NLA_U32 }, [TCA_CODEL_ECN] = { .type = NLA_U32 }, [TCA_CODEL_CE_THRESHOLD]= { .type = NLA_U32 }, }; static int codel_change(struct Qdisc *sch, struct nlattr *opt) { struct codel_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_CODEL_MAX + 1]; unsigned int qlen, dropped = 0; int err; if (!opt) return -EINVAL; err = nla_parse_nested(tb, TCA_CODEL_MAX, opt, codel_policy); if (err < 0) return err; sch_tree_lock(sch); if (tb[TCA_CODEL_TARGET]) { u32 target = nla_get_u32(tb[TCA_CODEL_TARGET]); q->params.target = ((u64)target * NSEC_PER_USEC) >> CODEL_SHIFT; } if (tb[TCA_CODEL_CE_THRESHOLD]) { u64 val = nla_get_u32(tb[TCA_CODEL_CE_THRESHOLD]); q->params.ce_threshold = (val * NSEC_PER_USEC) >> CODEL_SHIFT; } if (tb[TCA_CODEL_INTERVAL]) { u32 interval = nla_get_u32(tb[TCA_CODEL_INTERVAL]); q->params.interval = ((u64)interval * NSEC_PER_USEC) >> CODEL_SHIFT; } if (tb[TCA_CODEL_LIMIT]) sch->limit = nla_get_u32(tb[TCA_CODEL_LIMIT]); if (tb[TCA_CODEL_ECN]) q->params.ecn = !!nla_get_u32(tb[TCA_CODEL_ECN]); qlen = sch->q.qlen; while (sch->q.qlen > sch->limit) { struct sk_buff *skb = __qdisc_dequeue_head(&sch->q); dropped += qdisc_pkt_len(skb); qdisc_qstats_backlog_dec(sch, skb); rtnl_qdisc_drop(skb, sch); } qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped); sch_tree_unlock(sch); return 0; } static int codel_init(struct Qdisc *sch, struct nlattr *opt) { struct codel_sched_data *q = qdisc_priv(sch); sch->limit = DEFAULT_CODEL_LIMIT; codel_params_init(&q->params); codel_vars_init(&q->vars); codel_stats_init(&q->stats); q->params.mtu = psched_mtu(qdisc_dev(sch)); if (opt) { int err = codel_change(sch, opt); if (err) return err; } if (sch->limit >= 1) sch->flags |= TCQ_F_CAN_BYPASS; else sch->flags &= ~TCQ_F_CAN_BYPASS; return 0; } static int codel_dump(struct Qdisc *sch, struct sk_buff *skb) { struct codel_sched_data *q = qdisc_priv(sch); struct nlattr *opts; opts = nla_nest_start(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; if (nla_put_u32(skb, TCA_CODEL_TARGET, codel_time_to_us(q->params.target)) || nla_put_u32(skb, TCA_CODEL_LIMIT, sch->limit) || nla_put_u32(skb, TCA_CODEL_INTERVAL, codel_time_to_us(q->params.interval)) || nla_put_u32(skb, TCA_CODEL_ECN, q->params.ecn)) goto nla_put_failure; if (q->params.ce_threshold != CODEL_DISABLED_THRESHOLD && nla_put_u32(skb, TCA_CODEL_CE_THRESHOLD, codel_time_to_us(q->params.ce_threshold))) goto nla_put_failure; return nla_nest_end(skb, opts); nla_put_failure: nla_nest_cancel(skb, opts); return -1; } static int codel_dump_stats(struct Qdisc *sch, struct gnet_dump *d) { const struct codel_sched_data *q = qdisc_priv(sch); struct tc_codel_xstats st = { .maxpacket = q->stats.maxpacket, .count = q->vars.count, .lastcount = q->vars.lastcount, .drop_overlimit = q->drop_overlimit, .ldelay = codel_time_to_us(q->vars.ldelay), .dropping = q->vars.dropping, .ecn_mark = q->stats.ecn_mark, .ce_mark = q->stats.ce_mark, }; if (q->vars.dropping) { codel_tdiff_t delta = q->vars.drop_next - codel_get_time(); if (delta >= 0) st.drop_next = codel_time_to_us(delta); else st.drop_next = -codel_time_to_us(-delta); } return gnet_stats_copy_app(d, &st, sizeof(st)); } static void codel_reset(struct Qdisc *sch) { struct codel_sched_data *q = qdisc_priv(sch); qdisc_reset_queue(sch); codel_vars_init(&q->vars); } static struct Qdisc_ops codel_qdisc_ops __read_mostly = { .id = "codel", .priv_size = sizeof(struct codel_sched_data), .enqueue = codel_qdisc_enqueue, .dequeue = codel_qdisc_dequeue, .peek = qdisc_peek_dequeued, .init = codel_init, .reset = codel_reset, .change = codel_change, .dump = codel_dump, .dump_stats = codel_dump_stats, .owner = THIS_MODULE, }; static int __init codel_module_init(void) { return register_qdisc(&codel_qdisc_ops); } static void __exit codel_module_exit(void) { unregister_qdisc(&codel_qdisc_ops); } module_init(codel_module_init) module_exit(codel_module_exit) MODULE_DESCRIPTION("Controlled Delay queue discipline"); MODULE_AUTHOR("Dave Taht"); MODULE_AUTHOR("Eric Dumazet"); MODULE_LICENSE("Dual BSD/GPL"); insertions'>+32 2017-02-10sched: rename tcf_destroy to tcf_destroy_protoJiri Pirko2-6/+6 2017-02-10ipv4: fib: Add events for FIB replace and appendIdo Schimmel1-13/+14 2017-02-10ipv4: fib: Send notification before deleting FIB aliasIdo Schimmel1-7/+7 2017-02-10ipv4: fib: Send deletion notification with actual FIB alias typeIdo Schimmel1-2/+2 2017-02-10ipv4: fib: Only flush FIB aliases belonging to currently flushed tableIdo Schimmel1-1/+2 2017-02-09openvswitch: Pack struct sw_flow_key.Jarno Rajahalme4-34/+39 2017-02-09openvswitch: Add force commit.Jarno Rajahalme1-2/+24 2017-02-09openvswitch: Add original direction conntrack tuple to sw_flow_key.Jarno Rajahalme7-46/+227 2017-02-09openvswitch: Inherit master's labels.Jarno Rajahalme1-14/+31 2017-02-09openvswitch: Refactor labels initialization.Jarno Rajahalme1-42/+62 2017-02-09openvswitch: Simplify labels length logic.Jarno Rajahalme1-11/+9 2017-02-09openvswitch: Unionize ovs_key_ct_label with a u32 array.Jarno Rajahalme1-7/+8 2017-02-09openvswitch: Do not trigger events for unconfirmed connections.Jarno Rajahalme1-6/+22 2017-02-09openvswitch: Use inverted tuple in ovs_ct_find_existing() if NATted.Jarno Rajahalme1-2/+22 2017-02-09openvswitch: Fix comments for skb->_nfctJarno Rajahalme1-7/+7 2017-02-09net: dsa: Fix duplicate object ruleFlorian Fainelli1-1/+0 2017-02-09sctp: implement sender-side procedures for Add Incoming/Outgoing Streams Requ...Xin Long2-0/+106 2017-02-09sctp: add support for generating stream reconf add incoming/outgoing streams ...Xin Long1-0/+46 2017-02-09sctp: implement sender-side procedures for SSN/TSN Reset Request ParameterXin Long2-0/+69 2017-02-09sctp: add support for generating stream reconf ssn/tsn reset request chunkXin Long1-0/+29 2017-02-09sctp: streams should be recovered when it fails to send request.Xin Long1-2/+17 2017-02-08ipv4: fib: Notify about nexthop status changesIdo Schimmel1-0/+33 2017-02-08bridge: vlan tunnel id info range fill size calc cleanupsRoopa Prabhu1-18/+16 2017-02-08gro_cells: move to net/core/gro_cells.cEric Dumazet6-0/+100 2017-02-07Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller