Release 4.11 net/sched/sch_choke.c

/*
 * net/sched/sch_choke.c        CHOKE scheduler
 *
 * Copyright (c) 2011 Stephen Hemminger <shemminger@vyatta.com>
 * Copyright (c) 2011 Eric Dumazet <eric.dumazet@gmail.com>
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * version 2 as published by the Free Software Foundation.
 *
 */

#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/vmalloc.h>
#include <net/pkt_sched.h>
#include <net/pkt_cls.h>
#include <net/inet_ecn.h>
#include <net/red.h>
#include <net/flow_dissector.h>

/*
   CHOKe stateless AQM for fair bandwidth allocation
   =================================================

   CHOKe (CHOose and Keep for responsive flows, CHOose and Kill for
   unresponsive flows) is a variant of RED that penalizes misbehaving flows but
   maintains no flow state. The difference from RED is an additional step
   during the enqueuing process. If average queue size is over the
   low threshold (qmin), a packet is chosen at random from the queue.
   If both the new and chosen packet are from the same flow, both
   are dropped. Unlike RED, CHOKe is not really a "classful" qdisc because it
   needs to access packets in queue randomly. It has a minimal class
   interface to allow overriding the builtin flow classifier with
   filters.

   Source:
   R. Pan, B. Prabhakar, and K. Psounis, "CHOKe, A Stateless
   Active Queue Management Scheme for Approximating Fair Bandwidth Allocation",
   IEEE INFOCOM, 2000.

   A. Tang, J. Wang, S. Low, "Understanding CHOKe: Throughput and Spatial
   Characteristics", IEEE/ACM Transactions on Networking, 2004

 */

/* Upper bound on size of sk_buff table (packets) */

#define CHOKE_MAX_QUEUE	(128*1024 - 1)


struct choke_sched_data {
/* Parameters */
	
u32		 limit;
	
unsigned char	 flags;

	
struct red_parms parms;

/* Variables */
	
struct red_vars  vars;
	
struct tcf_proto __rcu *filter_list;
	struct {
		
u32	prob_drop;	/* Early probability drops */
		
u32	prob_mark;	/* Early probability marks */
		
u32	forced_drop;	/* Forced drops, qavg > max_thresh */
		
u32	forced_mark;	/* Forced marks, qavg > max_thresh */
		
u32	pdrop;          /* Drops due to queue limits */
		
u32	other;          /* Drops due to drop() calls */
		
u32	matched;	/* Drops to flow match */
	} 
stats;

	
unsigned int	 head;
	
unsigned int	 tail;

	
unsigned int	 tab_mask; /* size - 1 */

	
struct sk_buff **tab;
};

/* number of elements in queue including holes */


static unsigned int choke_len(const struct choke_sched_data *q)
{
	return (q->tail - q->head) & q->tab_mask;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Stephen Hemminger
28
100.00%
1
100.00%
Total
28
100.00%
1
100.00%

/* Is ECN parameter configured */


static int use_ecn(const struct choke_sched_data *q)
{
	return q->flags & TC_RED_ECN;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Stephen Hemminger
19
100.00%
1
100.00%
Total
19
100.00%
1
100.00%

/* Should packets over max just be dropped (versus marked) */


static int use_harddrop(const struct choke_sched_data *q)
{
	return q->flags & TC_RED_HARDDROP;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Stephen Hemminger
19
100.00%
1
100.00%
Total
19
100.00%
1
100.00%

/* Move head pointer forward to skip over holes */


static void choke_zap_head_holes(struct choke_sched_data *q)
{
	do {
		q->head = (q->head + 1) & q->tab_mask;
		if (q->head == q->tail)
			break;
	} while (q->tab[q->head] == NULL);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Stephen Hemminger
55
100.00%
1
100.00%
Total
55
100.00%
1
100.00%

/* Move tail pointer backwards to reuse holes */


static void choke_zap_tail_holes(struct choke_sched_data *q)
{
	do {
		q->tail = (q->tail - 1) & q->tab_mask;
		if (q->head == q->tail)
			break;
	} while (q->tab[q->tail] == NULL);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Stephen Hemminger
55
100.00%
1
100.00%
Total
55
100.00%
1
100.00%

/* Drop packet from queue array by creating a "hole" */


static void choke_drop_by_idx(struct Qdisc *sch, unsigned int idx,
			      struct sk_buff **to_free)
{
	struct choke_sched_data *q = qdisc_priv(sch);
	struct sk_buff *skb = q->tab[idx];

	q->tab[idx] = NULL;

	if (idx == q->head)
		choke_zap_head_holes(q);
	if (idx == q->tail)
		choke_zap_tail_holes(q);

	qdisc_qstats_backlog_dec(sch, skb);
	qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(skb));
	qdisc_drop(skb, sch, to_free);
	--sch->q.qlen;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Stephen Hemminger
91
80.53%
1
25.00%
Américo Wang
11
9.73%
1
25.00%
Eric Dumazet
8
7.08%
1
25.00%
John Fastabend
3
2.65%
1
25.00%
Total
113
100.00%
4
100.00%


struct choke_skb_cb {
	
u16			classid;
	
u8			keys_valid;
	
struct			flow_keys_digest keys;
};



static inline struct choke_skb_cb *choke_skb_cb(const struct sk_buff *skb)
{
	qdisc_cb_private_validate(skb, sizeof(struct choke_skb_cb));
	return (struct choke_skb_cb *)qdisc_skb_cb(skb)->data;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Eric Dumazet
37
94.87%
1
50.00%
David S. Miller
2
5.13%
1
50.00%
Total
39
100.00%
2
100.00%



static inline void choke_set_classid(struct sk_buff *skb, u16 classid)
{
	choke_skb_cb(skb)->classid = classid;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Stephen Hemminger
22
91.67%
1
50.00%
Eric Dumazet
2
8.33%
1
50.00%
Total
24
100.00%
2
100.00%



static u16 choke_get_classid(const struct sk_buff *skb)
{
	return choke_skb_cb(skb)->classid;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Stephen Hemminger
18
90.00%
1
50.00%
Eric Dumazet
2
10.00%
1
50.00%
Total
20
100.00%
2
100.00%

/*
 * Compare flow of two packets
 *  Returns true only if source and destination address and port match.
 *          false for special cases
 */


static bool choke_match_flow(struct sk_buff *skb1,
			     struct sk_buff *skb2)
{
	struct flow_keys temp;

	if (skb1->protocol != skb2->protocol)
		return false;

	if (!choke_skb_cb(skb1)->keys_valid) {
		choke_skb_cb(skb1)->keys_valid = 1;
		skb_flow_dissect_flow_keys(skb1, &temp, 0);
		make_flow_keys_digest(&choke_skb_cb(skb1)->keys, &temp);
	}

	if (!choke_skb_cb(skb2)->keys_valid) {
		choke_skb_cb(skb2)->keys_valid = 1;
		skb_flow_dissect_flow_keys(skb2, &temp, 0);
		make_flow_keys_digest(&choke_skb_cb(skb2)->keys, &temp);
	}

	return !memcmp(&choke_skb_cb(skb1)->keys,
		       &choke_skb_cb(skb2)->keys,
		       sizeof(choke_skb_cb(skb1)->keys));
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Eric Dumazet
137
88.96%
2
40.00%
Tom Herbert
15
9.74%
2
40.00%
Jiri Pirko
2
1.30%
1
20.00%
Total
154
100.00%
5
100.00%

/*
 * Classify flow using either:
 *  1. pre-existing classification result in skb
 *  2. fast internal classification
 *  3. use TC filter based classification
 */


static bool choke_classify(struct sk_buff *skb,
			   struct Qdisc *sch, int *qerr)

{
	struct choke_sched_data *q = qdisc_priv(sch);
	struct tcf_result res;
	struct tcf_proto *fl;
	int result;

	fl = rcu_dereference_bh(q->filter_list);
	result = tc_classify(skb, fl, &res, false);
	if (result >= 0) {
#ifdef CONFIG_NET_CLS_ACT
		switch (result) {
		case TC_ACT_STOLEN:
		case TC_ACT_QUEUED:
			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
		case TC_ACT_SHOT:
			return false;
		}
#endif
		choke_set_classid(skb, TC_H_MIN(res.classid));
		return true;
	}

	return false;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Stephen Hemminger
104
85.95%
1
33.33%
John Fastabend
15
12.40%
1
33.33%
Daniel Borkmann
2
1.65%
1
33.33%
Total
121
100.00%
3
100.00%

/*
 * Select a packet at random from queue
 * HACK: since queue can have holes from previous deletion; retry several
 *   times to find a random skb but then just give up and return the head
 * Will return NULL if queue is empty (q->head == q->tail)
 */


static struct sk_buff *choke_peek_random(const struct choke_sched_data *q,
					 unsigned int *pidx)
{
	struct sk_buff *skb;
	int retrys = 3;

	do {
		*pidx = (q->head + prandom_u32_max(choke_len(q))) & q->tab_mask;
		skb = q->tab[*pidx];
		if (skb)
			return skb;
	} while (--retrys > 0);

	return q->tab[*pidx = q->head];
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Stephen Hemminger
90
98.90%
1
50.00%
Daniel Borkmann
1
1.10%
1
50.00%
Total
91
100.00%
2
100.00%

/*
 * Compare new packet with random packet in queue
 * returns true if matched and sets *pidx
 */


static bool choke_match_random(const struct choke_sched_data *q,
			       struct sk_buff *nskb,
			       unsigned int *pidx)
{
	struct sk_buff *oskb;

	if (q->head == q->tail)
		return false;

	oskb = choke_peek_random(q, pidx);
	if (rcu_access_pointer(q->filter_list))
		return choke_get_classid(nskb) == choke_get_classid(oskb);

	return choke_match_flow(oskb, nskb);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Stephen Hemminger
74
96.10%
1
50.00%
John Fastabend
3
3.90%
1
50.00%
Total
77
100.00%
2
100.00%



static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch,
			 struct sk_buff **to_free)
{
	int ret = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
	struct choke_sched_data *q = qdisc_priv(sch);
	const struct red_parms *p = &q->parms;

	if (rcu_access_pointer(q->filter_list)) {
		/* If using external classifiers, get result and record it. */
		if (!choke_classify(skb, sch, &ret))
			goto other_drop;	/* Packet was eaten by filter */
	}

	choke_skb_cb(skb)->keys_valid = 0;
	/* Compute average queue usage (see RED) */
	q->vars.qavg = red_calc_qavg(p, &q->vars, sch->q.qlen);
	if (red_is_idling(&q->vars))
		red_end_of_idle_period(&q->vars);

	/* Is queue small? */
	if (q->vars.qavg <= p->qth_min)
		q->vars.qcount = -1;
	else {
		unsigned int idx;

		/* Draw a packet at random from queue and compare flow */
		if (choke_match_random(q, skb, &idx)) {
			q->stats.matched++;
			choke_drop_by_idx(sch, idx, to_free);
			goto congestion_drop;
		}

		/* Queue is large, always mark/drop */
		if (q->vars.qavg > p->qth_max) {
			q->vars.qcount = -1;

			qdisc_qstats_overlimit(sch);
			if (use_harddrop(q) || !use_ecn(q) ||
			    !INET_ECN_set_ce(skb)) {
				q->stats.forced_drop++;
				goto congestion_drop;
			}

			q->stats.forced_mark++;
		} else if (++q->vars.qcount) {
			if (red_mark_probability(p, &q->vars, q->vars.qavg)) {
				q->vars.qcount = 0;
				q->vars.qR = red_random(p);

				qdisc_qstats_overlimit(sch);
				if (!use_ecn(q) || !INET_ECN_set_ce(skb)) {
					q->stats.prob_drop++;
					goto congestion_drop;
				}

				q->stats.prob_mark++;
			}
		} else
			q->vars.qR = red_random(p);
	}

	/* Admit new packet */
	if (sch->q.qlen < q->limit) {
		q->tab[q->tail] = skb;
		q->tail = (q->tail + 1) & q->tab_mask;
		++sch->q.qlen;
		qdisc_qstats_backlog_inc(sch, skb);
		return NET_XMIT_SUCCESS;
	}

	q->stats.pdrop++;
	return qdisc_drop(skb, sch, to_free);

congestion_drop:
	qdisc_drop(skb, sch, to_free);
	return NET_XMIT_CN;

other_drop:
	if (ret & __NET_XMIT_BYPASS)
		qdisc_qstats_drop(sch);
	__qdisc_drop(skb, to_free);
	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Stephen Hemminger
374
79.07%
1
14.29%
Eric Dumazet
77
16.28%
4
57.14%
John Fastabend
22
4.65%
2
28.57%
Total
473
100.00%
7
100.00%



static struct sk_buff *choke_dequeue(struct Qdisc *sch)
{
	struct choke_sched_data *q = qdisc_priv(sch);
	struct sk_buff *skb;

	if (q->head == q->tail) {
		if (!red_is_idling(&q->vars))
			red_start_of_idle_period(&q->vars);
		return NULL;
	}

	skb = q->tab[q->head];
	q->tab[q->head] = NULL;
	choke_zap_head_holes(q);
	--sch->q.qlen;
	qdisc_qstats_backlog_dec(sch, skb);
	qdisc_bstats_update(sch, skb);

	return skb;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Stephen Hemminger
108
95.58%
1
33.33%
John Fastabend
3
2.65%
1
33.33%
Eric Dumazet
2
1.77%
1
33.33%
Total
113
100.00%
3
100.00%



static void choke_reset(struct Qdisc *sch)
{
	struct choke_sched_data *q = qdisc_priv(sch);

	while (q->head != q->tail) {
		struct sk_buff *skb = q->tab[q->head];

		q->head = (q->head + 1) & q->tab_mask;
		if (!skb)
			continue;
		rtnl_qdisc_drop(skb, sch);
	}

	sch->q.qlen = 0;
	sch->qstats.backlog = 0;
	memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *));
	q->head = q->tail = 0;
	red_restart(&q->vars);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Américo Wang
93
69.40%
1
25.00%
Stephen Hemminger
28
20.90%
1
25.00%
Eric Dumazet
13
9.70%
2
50.00%
Total
134
100.00%
4
100.00%


static const struct nla_policy choke_policy[TCA_CHOKE_MAX + 1] = {
	[TCA_CHOKE_PARMS]	= { .len = sizeof(struct tc_red_qopt) },
	[TCA_CHOKE_STAB]	= { .len = RED_STAB_SIZE },
	[TCA_CHOKE_MAX_P]	= { .type = NLA_U32 },
};




static void choke_free(void *addr)
{
	kvfree(addr);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Stephen Hemminger
14
93.33%
1
50.00%
Américo Wang
1
6.67%
1
50.00%
Total
15
100.00%
2
100.00%



static int choke_change(struct Qdisc *sch, struct nlattr *opt)
{
	struct choke_sched_data *q = qdisc_priv(sch);
	struct nlattr *tb[TCA_CHOKE_MAX + 1];
	const struct tc_red_qopt *ctl;
	int err;
	struct sk_buff **old = NULL;
	unsigned int mask;
	u32 max_P;

	if (opt == NULL)
		return -EINVAL;

	err = nla_parse_nested(tb, TCA_CHOKE_MAX, opt, choke_policy);
	if (err < 0)
		return err;

	if (tb[TCA_CHOKE_PARMS] == NULL ||
	    tb[TCA_CHOKE_STAB] == NULL)
		return -EINVAL;

	max_P = tb[TCA_CHOKE_MAX_P] ? nla_get_u32(tb[TCA_CHOKE_MAX_P]) : 0;

	ctl = nla_data(tb[TCA_CHOKE_PARMS]);

	if (ctl->limit > CHOKE_MAX_QUEUE)
		return -EINVAL;

	mask = roundup_pow_of_two(ctl->limit + 1) - 1;
	if (mask != q->tab_mask) {
		struct sk_buff **ntab;

		ntab = kcalloc(mask + 1, sizeof(struct sk_buff *),
			       GFP_KERNEL | __GFP_NOWARN);
		if (!ntab)
			ntab = vzalloc((mask + 1) * sizeof(struct sk_buff *));
		if (!ntab)
			return -ENOMEM;

		sch_tree_lock(sch);
		old = q->tab;
		if (old) {
			unsigned int oqlen = sch->q.qlen, tail = 0;
			unsigned dropped = 0;

			while (q->head != q->tail) {
				struct sk_buff *skb = q->tab[q->head];

				q->head = (q->head + 1) & q->tab_mask;
				if (!skb)
					continue;
				if (tail < mask) {
					ntab[tail++] = skb;
					continue;
				}
				dropped += qdisc_pkt_len(skb);
				qdisc_qstats_backlog_dec(sch, skb);
				--sch->q.qlen;
				rtnl_qdisc_drop(skb, sch);
			}
			qdisc_tree_reduce_backlog(sch, oqlen - sch->q.qlen, dropped);
			q->head = 0;
			q->tail = tail;
		}

		q->tab_mask = mask;
		q->tab = ntab;
	} else
		sch_tree_lock(sch);

	q->flags = ctl->flags;
	q->limit = ctl->limit;

	red_set_parms(&q->parms, ctl->qth_min, ctl->qth_max, ctl->Wlog,
		      ctl->Plog, ctl->Scell_log,
		      nla_data(tb[TCA_CHOKE_STAB]),
		      max_P);
	red_set_vars(&q->vars);

	if (q->head == q->tail)
		red_end_of_idle_period(&q->vars);

	sch_tree_unlock(sch);
	choke_free(old);
	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Stephen Hemminger
447
89.58%
1
14.29%
Eric Dumazet
32
6.41%
3
42.86%
Américo Wang
15
3.01%
1
14.29%
John Fastabend
3
0.60%
1
14.29%
Joe Perches
2
0.40%
1
14.29%
Total
499
100.00%
7
100.00%



static int choke_init(struct Qdisc *sch, struct nlattr *opt)
{
	return choke_change(sch, opt);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Stephen Hemminger
24
100.00%
1
100.00%
Total
24
100.00%
1
100.00%



static int choke_dump(struct Qdisc *sch, struct sk_buff *skb)
{
	struct choke_sched_data *q = qdisc_priv(sch);
	struct nlattr *opts = NULL;
	struct tc_red_qopt opt = {
		.limit		= q->limit,
		.flags		= q->flags,
		.qth_min	= q->parms.qth_min >> q->parms.Wlog,
		.qth_max	= q->parms.qth_max >> q->parms.Wlog,
		.Wlog		= q->parms.Wlog,
		.Plog		= q->parms.Plog,
		.Scell_log	= q->parms.Scell_log,
        };

	opts = nla_nest_start(skb, TCA_OPTIONS);
	if (opts == NULL)
		goto nla_put_failure;

	if (nla_put(skb, TCA_CHOKE_PARMS, sizeof(opt), &opt) ||
	    nla_put_u32(skb, TCA_CHOKE_MAX_P, q->parms.max_P))
		goto nla_put_failure;
	return nla_nest_end(skb, opts);

nla_put_failure:
	nla_nest_cancel(skb, opts);
	return -EMSGSIZE;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Stephen Hemminger
162
89.01%
1
33.33%
Eric Dumazet
11
6.04%
1
33.33%
David S. Miller
9
4.95%
1
33.33%
Total
182
100.00%
3
100.00%



static int choke_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
{
	struct choke_sched_data *q = qdisc_priv(sch);
	struct tc_choke_xstats st = {
		.early	= q->stats.prob_drop + q->stats.forced_drop,
		.marked	= q->stats.prob_mark + q->stats.forced_mark,
		.pdrop	= q->stats.pdrop,
		.other	= q->stats.other,
		.matched = q->stats.matched,
        };

	return gnet_stats_copy_app(d, &st, sizeof(st));
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Stephen Hemminger
103
100.00%
1
100.00%
Total
103
100.00%
1
100.00%



static void choke_destroy(struct Qdisc *sch)
{
	struct choke_sched_data *q = qdisc_priv(sch);

	tcf_destroy_chain(&q->filter_list);
	choke_free(q->tab);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Stephen Hemminger
36
100.00%
1
100.00%
Total
36
100.00%
1
100.00%



static struct sk_buff *choke_peek_head(struct Qdisc *sch)
{
	struct choke_sched_data *q = qdisc_priv(sch);

	return (q->head != q->tail) ? q->tab[q->head] : NULL;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Stephen Hemminger
45
100.00%
1
100.00%
Total
45
100.00%
1
100.00%


static struct Qdisc_ops choke_qdisc_ops __read_mostly = {
	.id		=	"choke",
	.priv_size	=	sizeof(struct choke_sched_data),

	.enqueue	=	choke_enqueue,
	.dequeue	=	choke_dequeue,
	.peek		=	choke_peek_head,
	.init		=	choke_init,
	.destroy	=	choke_destroy,
	.reset		=	choke_reset,
	.change		=	choke_change,
	.dump		=	choke_dump,
	.dump_stats	=	choke_dump_stats,
	.owner		=	THIS_MODULE,
};



static int __init choke_module_init(void)
{
	return register_qdisc(&choke_qdisc_ops);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Stephen Hemminger
16
100.00%
1
100.00%
Total
16
100.00%
1
100.00%



static void __exit choke_module_exit(void)
{
	unregister_qdisc(&choke_qdisc_ops);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Stephen Hemminger
15
100.00%
1
100.00%
Total
15
100.00%
1
100.00%

module_init(choke_module_init)
module_exit(choke_module_exit)

MODULE_LICENSE("GPL");
Overall Contributors
Person
Tokens
Prop
Commits
CommitProp
Stephen Hemminger
2185
79.54%
1
4.00%
Eric Dumazet
350
12.74%
8
32.00%
Américo Wang
120
4.37%
3
12.00%
John Fastabend
50
1.82%
2
8.00%
Tom Herbert
17
0.62%
2
8.00%
David S. Miller
14
0.51%
3
12.00%
Jiri Pirko
6
0.22%
3
12.00%
Daniel Borkmann
3
0.11%
2
8.00%
Joe Perches
2
0.07%
1
4.00%
Total
2747
100.00%
25
100.00%
Directory: net/sched

Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.