summaryrefslogtreecommitdiffstats
path: root/net/sched/sch_tbf.c
blob: 18ff634337092d5f8e7cba8fe817542f1455738f (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
/*
 * net/sched/sch_tbf.c	Token Bucket Filter queue.
 *
 *		This program is free software; you can redistribute it and/or
 *		modify it under the terms of the GNU General Public License
 *		as published by the Free Software Foundation; either version
 *		2 of the License, or (at your option) any later version.
 *
 * Authors:	Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
 *		Dmitry Torokhov <dtor@mail.ru> - allow attaching inner qdiscs -
 *						 original idea by Martin Devera
 *
 */

#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/skbuff.h>
#include <net/netlink.h>
#include <net/sch_generic.h>
#include <net/pkt_sched.h>


/*	Simple Token Bucket Filter.
	=======================================

	SOURCE.
	-------

	None.

	Description.
	------------

	A data flow obeys TBF with rate R and depth B, if for any
	time interval t_i...t_f the number of transmitted bits
	does not exceed B + R*(t_f-t_i).

	Packetized version of this definition:
	The sequence of packets of sizes s_i served at moments t_i
	obeys TBF, if for any i<=k:

	s_i+....+s_k <= B + R*(t_k - t_i)

	Algorithm.
	----------

	Let N(t_i) be B/R initially and N(t) grow continuously with time as:

	N(t+delta) = min{B/R, N(t) + delta}

	If the first packet in queue has length S, it may be
	transmitted only at the time t_* when S/R <= N(t_*),
	and in this case N(t) jumps:

	N(t_* + 0) = N(t_* - 0) - S/R.



	Actually, QoS requires two TBF to be applied to a data stream.
	One of them controls steady state burst size, another
	one with rate P (peak rate) and depth M (equal to link MTU)
	limits bursts at a smaller time scale.

	It is easy to see that P>R, and B>M. If P is infinity, this double
	TBF is equivalent to a single one.

	When TBF works in reshaping mode, latency is estimated as:

	lat = max ((L-B)/R, (L-M)/P)


	NOTES.
	------

	If TBF throttles, it starts a watchdog timer, which will wake it up
	when it is ready to transmit.
	Note that the minimal timer resolution is 1/HZ.
	If no new packets arrive during this period,
	or if the device is not awaken by EOI for some previous packet,
	TBF can stop its activity for 1/HZ.


	This means, that with depth B, the maximal rate is

	R_crit = B*HZ

	F.e. for 10Mbit ethernet and HZ=100 the minimal allowed B is ~10Kbytes.

	Note that the peak rate TBF is much more tough: with MTU 1500
	P_crit = 150Kbytes/sec. So, if you need greater peak
	rates, use alpha with HZ=1000 :-)

	With classful TBF, limit is just kept for backwards compatibility.
	It is passed to the default bfifo qdisc - if the inner qdisc is
	changed the limit is not effective anymore.
*/

struct tbf_sched_data {
/* Parameters */
	u32		limit;		/* Maximal length of backlog: bytes */
	u32		max_size;
	s64		buffer;		/* Token bucket depth/rate: MUST BE >= MTU/B */
	s64		mtu;
	struct psched_ratecfg rate;
	struct psched_ratecfg peak;

/* Variables */
	s64	tokens;			/* Current number of B tokens */
	s64	ptokens;		/* Current number of P tokens */
	s64	t_c;			/* Time check-point */
	struct Qdisc	*qdisc;		/* Inner qdisc, default - bfifo queue */
	struct qdisc_watchdog watchdog;	/* Watchdog timer */
};


/* Time to Length, convert time in ns to length in bytes
 * to determinate how many bytes can be sent in given time.
 */
static u64 psched_ns_t2l(const struct psched_ratecfg *r,
			 u64 time_in_ns)
{
	/* The formula is :
	 * len = (time_in_ns * r->rate_bytes_ps) / NSEC_PER_SEC
	 */
	u64 len = time_in_ns * r->rate_bytes_ps;

	do_div(len, NSEC_PER_SEC);

	if (unlikely(r->linklayer == TC_LINKLAYER_ATM)) {
		do_div(len, 53);
		len = len * 48;
	}

	if (len > r->overhead)
		len -= r->overhead;
	else
		len = 0;

	return len;
}

/*
 * Return length of individual segments of a gso packet,
 * including all headers (MAC, IP, TCP/UDP)
 */
static unsigned int skb_gso_mac_seglen(const struct sk_buff *skb)
{
	unsigned int hdr_len = skb_transport_header(skb) - skb_mac_header(skb);
	return hdr_len + skb_gso_transport_seglen(skb);
}

/* GSO packet is too big, segment it so that tbf can transmit
 * each segment in time
 */
static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch)
{
	struct tbf_sched_data *q = qdisc_priv(sch);
	struct sk_buff *segs, *nskb;
	netdev_features_t features = netif_skb_features(skb);
	int ret, nb;

	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);

	if (IS_ERR_OR_NULL(segs))
		return qdisc_reshape_fail(skb, sch);

	nb = 0;
	while (segs) {
		nskb = segs->next;
		segs->next = NULL;
		qdisc_skb_cb(segs)->pkt_len = segs->len;
		ret = qdisc_enqueue(segs, q->qdisc);
		if (ret != NET_XMIT_SUCCESS) {
			if (net_xmit_drop_count(ret))
				sch->qstats.drops++;
		} else {
			nb++;
		}
		segs = nskb;
	}
	sch->q.qlen += nb;
	if (nb > 1)
		qdisc_tree_decrease_qlen(sch, 1 - nb);
	consume_skb(skb);
	return nb > 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP;
}

static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch)
{
	struct tbf_sched_data *q = qdisc_priv(sch);
	int ret;

	if (qdisc_pkt_len(skb) > q->max_size) {
		if (skb_is_gso(skb) && skb_gso_mac_seglen(skb) <= q->max_size)
			return tbf_segment(skb, sch);
		return qdisc_reshape_fail(skb, sch);
	}
	ret = qdisc_enqueue(skb, q->qdisc);
	if (ret != NET_XMIT_SUCCESS) {
		if (net_xmit_drop_count(ret))
			sch->qstats.drops++;
		return ret;
	}

	sch->q.qlen++;
	return NET_XMIT_SUCCESS;
}

static unsigned int tbf_drop(struct Qdisc *sch)
{
	struct tbf_sched_data *q = qdisc_priv(sch);
	unsigned int len = 0;

	if (q->qdisc->ops->drop && (len = q->qdisc->ops->drop(q->qdisc)) != 0) {
		sch->q.qlen--;
		sch->qstats.drops++;
	}
	return len;
}

static bool tbf_peak_present(const struct tbf_sched_data *q)
{
	return q->peak.rate_bytes_ps;
}

static struct sk_buff *tbf_dequeue(struct Qdisc *sch)
{
	struct tbf_sched_data *q = qdisc_priv(sch);
	struct sk_buff *skb;

	skb = q->qdisc->ops->peek(q->qdisc);

	if (skb) {
		s64 now;
		s64 toks;
		s64 ptoks = 0;
		unsigned int len = qdisc_pkt_len(skb);

		now = ktime_to_ns(ktime_get());
		toks = min_t(s64, now - q->t_c, q->buffer);

		if (tbf_peak_present(q)) {
			ptoks = toks + q->ptokens;
			if (ptoks > q->mtu)
				ptoks = q->mtu;
			ptoks -= (s64) psched_l2t_ns(&q->peak, len);
		}
		toks += q->tokens;
		if (toks > q->buffer)
			toks = q->buffer;
		toks -= (s64) psched_l2t_ns(&q->rate, len);

		if ((toks|ptoks) >= 0) {
			skb = qdisc_dequeue_peeked(q->qdisc);
			if (unlikely(!skb))
				return NULL;

			q->t_c = now;
			q->tokens = toks;
			q->ptokens = ptoks;
			sch->q.qlen--;
			qdisc_unthrottled(sch);
			qdisc_bstats_update(sch, skb);
			return skb;
		}

		qdisc_watchdog_schedule_ns(&q->watchdog,
					   now + max_t(long, -toks, -ptoks));

		/* Maybe we have a shorter packet in the queue,
		   which can be sent now. It sounds cool,
		   but, however, this is wrong in principle.
		   We MUST NOT reorder packets under these circumstances.

		   Really, if we split the flow into independent
		   subflows, it would be a very good solution.
		   This is the main idea of all FQ algorithms
		   (cf. CSZ, HPFQ, HFSC)
		 */

		sch->qstats.overlimits++;
	}
	return NULL;
}

static void tbf_reset(struct Qdisc *sch)
{
	struct tbf_sched_data *q = qdisc_priv(sch);

	qdisc_reset(q->qdisc);
	sch->q.qlen = 0;
	q->t_c = ktime_to_ns(ktime_get());
	q->tokens = q->buffer;
	q->ptokens = q->mtu;
	qdisc_watchdog_cancel(&q->watchdog);
}

static const struct nla_policy tbf_policy[TCA_TBF_MAX + 1] = {
	[TCA_TBF_PARMS]	= { .len = sizeof(struct tc_tbf_qopt) },
	[TCA_TBF_RTAB]	= { .type = NLA_BINARY, .len = TC_RTAB_SIZE },
	[TCA_TBF_PTAB]	= { .type = NLA_BINARY, .len = TC_RTAB_SIZE },
	[TCA_TBF_RATE64]	= { .type = NLA_U64 },
	[TCA_TBF_PRATE64]	= { .type = NLA_U64 },
	[TCA_TBF_BURST] = { .type = NLA_U32 },
	[TCA_TBF_PBURST] = { .type = NLA_U32 },
};

static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
{
	int err;
	struct tbf_sched_data *q = qdisc_priv(sch);
	struct nlattr *tb[TCA_TBF_MAX + 1];
	struct tc_tbf_qopt *qopt;
	struct Qdisc *child = NULL;
	struct psched_ratecfg rate;
	struct psched_ratecfg peak;
	u64 max_size;
	s64 buffer, mtu;
	u64 rate64 = 0, prate64 = 0;

	err = nla_parse_nested(tb, TCA_TBF_MAX, opt, tbf_policy);
	if (err < 0)
		return err;

	err = -EINVAL;
	if (tb[TCA_TBF_PARMS] == NULL)
		goto done;

	qopt = nla_data(tb[TCA_TBF_PARMS]);
	if (qopt->rate.linklayer == TC_LINKLAYER_UNAWARE)
		qdisc_put_rtab(qdisc_get_rtab(&qopt->rate,
					      tb[TCA_TBF_RTAB]));

	if (qopt->peakrate.linklayer == TC_LINKLAYER_UNAWARE)
			qdisc_put_rtab(qdisc_get_rtab(&qopt->peakrate,
						      tb[TCA_TBF_PTAB]));

	buffer = min_t(u64, PSCHED_TICKS2NS(qopt->buffer), ~0U);
	mtu = min_t(u64, PSCHED_TICKS2NS(qopt->mtu), ~0U);

	if (tb[TCA_TBF_RATE64])
		rate64 = nla_get_u64(tb[TCA_TBF_RATE64]);
	psched_ratecfg_precompute(&rate, &qopt->rate, rate64);

	if (tb[TCA_TBF_BURST]) {
		max_size = nla_get_u32(tb[TCA_TBF_BURST]);
		buffer = psched_l2t_ns(&rate, max_size);
	} else {
		max_size = min_t(u64, psched_ns_t2l(&rate, buffer), ~0U);
	}

	if (qopt->peakrate.rate) {
		if (tb[TCA_TBF_PRATE64])
			prate64 = nla_get_u64(tb[TCA_TBF_PRATE64]);
		psched_ratecfg_precompute(&peak, &qopt->peakrate, prate64);
		if (peak.rate_bytes_ps <= rate.rate_bytes_ps) {
			pr_warn_ratelimited("sch_tbf: peakrate %llu is lower than or equals to rate %llu !\n",
					peak.rate_bytes_ps, rate.rate_bytes_ps);
			err = -EINVAL;
			goto done;
		}

		if (tb[TCA_TBF_PBURST]) {
			u32 pburst = nla_get_u32(tb[TCA_TBF_PBURST]);
			max_size = min_t(u32, max_size, pburst);
			mtu = psched_l2t_ns(&peak, pburst);
		} else {
			max_size = min_t(u64, max_size, psched_ns_t2l(&peak, mtu));
		}
	} else {
		memset(&peak, 0, sizeof(peak));
	}

	if (max_size < psched_mtu(qdisc_dev(sch)))
		pr_warn_ratelimited("sch_tbf: burst %llu is lower than device %s mtu (%u) !\n",
				    max_size, qdisc_dev(sch)->name,
				    psched_mtu(qdisc_dev(sch)));

	if (!max_size) {
		err = -EINVAL;
		goto done;
	}

	if (q->qdisc != &noop_qdisc) {
		err = fifo_set_limit(q->qdisc, qopt->limit);
		if (err)
			goto done;
	} else if (qopt->limit > 0) {
		child = fifo_create_dflt(sch, &bfifo_qdisc_ops, qopt->limit);
		if (IS_ERR(child)) {
			err = PTR_ERR(child);
			goto done;
		}
	}

	sch_tree_lock(sch);
	if (child) {
		qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen);
		qdisc_destroy(q->qdisc);
		q->qdisc = child;
	}
	q->limit = qopt->limit;
	if (tb[TCA_TBF_PBURST])
		q->mtu = mtu;
	else
		q->mtu = PSCHED_TICKS2NS(qopt->mtu);
	q->max_size = max_size;
	if (tb[TCA_TBF_BURST])
		q->buffer = buffer;
	else
		q->buffer = PSCHED_TICKS2NS(qopt->buffer);
	q->tokens = q->buffer;
	q->ptokens = q->mtu;

	memcpy(&q->rate, &rate, sizeof(struct psched_ratecfg));
	memcpy(&q->peak, &peak, sizeof(struct psched_ratecfg));

	sch_tree_unlock(sch);
	err = 0;
done:
	return err;
}

static int tbf_init(struct Qdisc *sch, struct nlattr *opt)
{
	struct tbf_sched_data *q = qdisc_priv(sch);

	if (opt == NULL)
		return -EINVAL;

	q->t_c = ktime_to_ns(ktime_get());
	qdisc_watchdog_init(&q->watchdog, sch);
	q->qdisc = &noop_qdisc;

	return tbf_change(sch, opt);
}

static void tbf_destroy(struct Qdisc *sch)
{
	struct tbf_sched_data *q = qdisc_priv(sch);

	qdisc_watchdog_cancel(&q->watchdog);
	qdisc_destroy(q->qdisc);
}

static int tbf_dump(struct Qdisc *sch, struct sk_buff *skb)
{
	struct tbf_sched_data *q = qdisc_priv(sch);
	struct nlattr *nest;
	struct tc_tbf_qopt opt;

	sch->qstats.backlog = q->qdisc->qstats.backlog;
	nest = nla_nest_start(skb, TCA_OPTIONS);
	if (nest == NULL)
		goto nla_put_failure;

	opt.limit = q->limit;
	psched_ratecfg_getrate(&opt.rate, &q->rate);
	if (tbf_peak_present(q))
		psched_ratecfg_getrate(&opt.peakrate, &q->peak);
	else
		memset(&opt.peakrate, 0, sizeof(opt.peakrate));
	opt.mtu = PSCHED_NS2TICKS(q->mtu);
	opt.buffer = PSCHED_NS2TICKS(q->buffer);
	if (nla_put(skb, TCA_TBF_PARMS, sizeof(opt), &opt))
		goto nla_put_failure;
	if (q->rate.rate_bytes_ps >= (1ULL << 32) &&
	    nla_put_u64(skb, TCA_TBF_RATE64, q->rate.rate_bytes_ps))
		goto nla_put_failure;
	if (tbf_peak_present(q) &&
	    q->peak.rate_bytes_ps >= (1ULL << 32) &&
	    nla_put_u64(skb, TCA_TBF_PRATE64, q->peak.rate_bytes_ps))
		goto nla_put_failure;

	return nla_nest_end(skb, nest);

nla_put_failure:
	nla_nest_cancel(skb, nest);
	return -1;
}

static int tbf_dump_class(struct Qdisc *sch, unsigned long cl,
			  struct sk_buff *skb, struct tcmsg *tcm)
{
	struct tbf_sched_data *q = qdisc_priv(sch);

	tcm->tcm_handle |= TC_H_MIN(1);
	tcm->tcm_info = q->qdisc->handle;

	return 0;
}

static int tbf_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
		     struct Qdisc **old)
{
	struct tbf_sched_data *q = qdisc_priv(sch);

	if (new == NULL)
		new = &noop_qdisc;

	sch_tree_lock(sch);
	*old = q->qdisc;
	q->qdisc = new;
	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
	qdisc_reset(*old);
	sch_tree_unlock(sch);

	return 0;
}

static struct Qdisc *tbf_leaf(struct Qdisc *sch, unsigned long arg)
{
	struct tbf_sched_data *q = qdisc_priv(sch);
	return q->qdisc;
}

static unsigned long tbf_get(struct Qdisc *sch, u32 classid)
{
	return 1;
}

static void tbf_put(struct Qdisc *sch, unsigned long arg)
{
}

static void tbf_walk(struct Qdisc *sch, struct qdisc_walker *walker)
{
	if (!walker->stop) {
		if (walker->count >= walker->skip)
			if (walker->fn(sch, 1, walker) < 0) {
				walker->stop = 1;
				return;
			}
		walker->count++;
	}
}

static const struct Qdisc_class_ops tbf_class_ops = {
	.graft		=	tbf_graft,
	.leaf		=	tbf_leaf,
	.get		=	tbf_get,
	.put		=	tbf_put,
	.walk		=	tbf_walk,
	.dump		=	tbf_dump_class,
};

static struct Qdisc_ops tbf_qdisc_ops __read_mostly = {
	.next		=	NULL,
	.cl_ops		=	&tbf_class_ops,
	.id		=	"tbf",
	.priv_size	=	sizeof(struct tbf_sched_data),
	.enqueue	=	tbf_enqueue,
	.dequeue	=	tbf_dequeue,
	.peek		=	qdisc_peek_dequeued,
	.drop		=	tbf_drop,
	.init		=	tbf_init,
	.reset		=	tbf_reset,
	.destroy	=	tbf_destroy,
	.change		=	tbf_change,
	.dump		=	tbf_dump,
	.owner		=	THIS_MODULE,
};

static int __init tbf_module_init(void)
{
	return register_qdisc(&tbf_qdisc_ops);
}

static void __exit tbf_module_exit(void)
{
	unregister_qdisc(&tbf_qdisc_ops);
}
module_init(tbf_module_init)
module_exit(tbf_module_exit)
MODULE_LICENSE("GPL");