summaryrefslogtreecommitdiffstats
path: root/net/sched/sch_netem.c
blob: e0c9fbe73b15cee32b44f4469e1ac5eeb9849267 (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
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
/*
 * net/sched/sch_netem.c	Network emulator
 *
 * 		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.
 *
 *  		Many of the algorithms and ideas for this came from
 *		NIST Net which is not copyrighted. 
 *
 * Authors:	Stephen Hemminger <shemminger@osdl.org>
 *		Catalin(ux aka Dino) BOIE <catab at umbrella dot ro>
 */

#include <linux/config.h>
#include <linux/module.h>
#include <linux/bitops.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/netdevice.h>
#include <linux/skbuff.h>
#include <linux/rtnetlink.h>

#include <net/pkt_sched.h>

/*	Network Emulation Queuing algorithm.
	====================================

	Sources: [1] Mark Carson, Darrin Santay, "NIST Net - A Linux-based
		 Network Emulation Tool
		 [2] Luigi Rizzo, DummyNet for FreeBSD

	 ----------------------------------------------------------------

	 This started out as a simple way to delay outgoing packets to
	 test TCP but has grown to include most of the functionality
	 of a full blown network emulator like NISTnet. It can delay
	 packets and add random jitter (and correlation). The random
	 distribution can be loaded from a table as well to provide
	 normal, Pareto, or experimental curves. Packet loss,
	 duplication, and reordering can also be emulated.

	 This qdisc does not do classification that can be handled in
	 layering other disciplines.  It does not need to do bandwidth
	 control either since that can be handled by using token
	 bucket or other rate control.

	 The simulator is limited by the Linux timer resolution
	 and will create packet bursts on the HZ boundary (1ms).
*/

struct netem_sched_data {
	struct Qdisc	*qdisc;
	struct sk_buff_head delayed;
	struct timer_list timer;

	u32 latency;
	u32 loss;
	u32 limit;
	u32 counter;
	u32 gap;
	u32 jitter;
	u32 duplicate;

	struct crndstate {
		unsigned long last;
		unsigned long rho;
	} delay_cor, loss_cor, dup_cor;

	struct disttable {
		u32  size;
		s16 table[0];
	} *delay_dist;
};

/* Time stamp put into socket buffer control block */
struct netem_skb_cb {
	psched_time_t	time_to_send;
};

/* init_crandom - initialize correlated random number generator
 * Use entropy source for initial seed.
 */
static void init_crandom(struct crndstate *state, unsigned long rho)
{
	state->rho = rho;
	state->last = net_random();
}

/* get_crandom - correlated random number generator
 * Next number depends on last value.
 * rho is scaled to avoid floating point.
 */
static unsigned long get_crandom(struct crndstate *state)
{
	u64 value, rho;
	unsigned long answer;

	if (state->rho == 0)	/* no correllation */
		return net_random();

	value = net_random();
	rho = (u64)state->rho + 1;
	answer = (value * ((1ull<<32) - rho) + state->last * rho) >> 32;
	state->last = answer;
	return answer;
}

/* tabledist - return a pseudo-randomly distributed value with mean mu and
 * std deviation sigma.  Uses table lookup to approximate the desired
 * distribution, and a uniformly-distributed pseudo-random source.
 */
static long tabledist(unsigned long mu, long sigma, 
		      struct crndstate *state, const struct disttable *dist)
{
	long t, x;
	unsigned long rnd;

	if (sigma == 0)
		return mu;

	rnd = get_crandom(state);

	/* default uniform distribution */
	if (dist == NULL) 
		return (rnd % (2*sigma)) - sigma + mu;

	t = dist->table[rnd % dist->size];
	x = (sigma % NETEM_DIST_SCALE) * t;
	if (x >= 0)
		x += NETEM_DIST_SCALE/2;
	else
		x -= NETEM_DIST_SCALE/2;

	return  x / NETEM_DIST_SCALE + (sigma / NETEM_DIST_SCALE) * t + mu;
}

/* Put skb in the private delayed queue. */
static int netem_delay(struct Qdisc *sch, struct sk_buff *skb)
{
	struct netem_sched_data *q = qdisc_priv(sch);
	psched_tdiff_t td;
	psched_time_t now;
	
	PSCHED_GET_TIME(now);
	td = tabledist(q->latency, q->jitter, &q->delay_cor, q->delay_dist);
	
	/* Always queue at tail to keep packets in order */
	if (likely(q->delayed.qlen < q->limit)) {
		struct netem_skb_cb *cb = (struct netem_skb_cb *)skb->cb;
	
		PSCHED_TADD2(now, td, cb->time_to_send);

		pr_debug("netem_delay: skb=%p now=%llu tosend=%llu\n", skb, 
			 now, cb->time_to_send);
	
		__skb_queue_tail(&q->delayed, skb);
		return NET_XMIT_SUCCESS;
	}

	pr_debug("netem_delay: queue over limit %d\n", q->limit);
	sch->qstats.overlimits++;
	kfree_skb(skb);
	return NET_XMIT_DROP;
}

/*
 *  Move a packet that is ready to send from the delay holding
 *  list to the underlying qdisc.
 */
static int netem_run(struct Qdisc *sch)
{
	struct netem_sched_data *q = qdisc_priv(sch);
	struct sk_buff *skb;
	psched_time_t now;

	PSCHED_GET_TIME(now);

	skb = skb_peek(&q->delayed);
	if (skb) {
		const struct netem_skb_cb *cb
			= (const struct netem_skb_cb *)skb->cb;
		long delay 
			= PSCHED_US2JIFFIE(PSCHED_TDIFF(cb->time_to_send, now));
		pr_debug("netem_run: skb=%p delay=%ld\n", skb, delay);

		/* if more time remaining? */
		if (delay > 0) {
			mod_timer(&q->timer, jiffies + delay);
			return 1;
		}

		__skb_unlink(skb, &q->delayed);
		
		if (q->qdisc->enqueue(skb, q->qdisc)) {
			sch->q.qlen--;
			sch->qstats.drops++;
		} 
	}

	return 0;
}

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

	pr_debug("netem_enqueue skb=%p\n", skb);

	/* Random packet drop 0 => none, ~0 => all */
	if (q->loss && q->loss >= get_crandom(&q->loss_cor)) {
		pr_debug("netem_enqueue: random loss\n");
		sch->qstats.drops++;
		kfree_skb(skb);
		return 0;	/* lie about loss so TCP doesn't know */
	}

	/* Random duplication */
	if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor)) {
		struct sk_buff *skb2;

		skb2 = skb_clone(skb, GFP_ATOMIC);
		if (skb2 && netem_delay(sch, skb2) == NET_XMIT_SUCCESS) {
			struct Qdisc *qp;

			/* Since one packet can generate two packets in the
			 * queue, the parent's qlen accounting gets confused,
			 * so fix it.
			 */
			qp = qdisc_lookup(sch->dev, TC_H_MAJ(sch->parent));
			if (qp)
				qp->q.qlen++;

			sch->q.qlen++;
			sch->bstats.bytes += skb2->len;
			sch->bstats.packets++;
		} else
			sch->qstats.drops++;
	}

	/* If doing simple delay then gap == 0 so all packets
	 * go into the delayed holding queue
	 * otherwise if doing out of order only "1 out of gap"
	 * packets will be delayed.
	 */
	if (q->counter < q->gap) {
		++q->counter;
		ret = q->qdisc->enqueue(skb, q->qdisc);
	} else {
		q->counter = 0;
		ret = netem_delay(sch, skb);
		netem_run(sch);
	}

	if (likely(ret == NET_XMIT_SUCCESS)) {
		sch->q.qlen++;
		sch->bstats.bytes += skb->len;
		sch->bstats.packets++;
	} else
		sch->qstats.drops++;

	pr_debug("netem: enqueue ret %d\n", ret);
	return ret;
}

/* Requeue packets but don't change time stamp */
static int netem_requeue(struct sk_buff *skb, struct Qdisc *sch)
{
	struct netem_sched_data *q = qdisc_priv(sch);
	int ret;

	if ((ret = q->qdisc->ops->requeue(skb, q->qdisc)) == 0) {
		sch->q.qlen++;
		sch->qstats.requeues++;
	}

	return ret;
}

static unsigned int netem_drop(struct Qdisc* sch)
{
	struct netem_sched_data *q = qdisc_priv(sch);
	unsigned int len;

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

static struct sk_buff *netem_dequeue(struct Qdisc *sch)
{
	struct netem_sched_data *q = qdisc_priv(sch);
	struct sk_buff *skb;
	int pending;

	pending = netem_run(sch);

	skb = q->qdisc->dequeue(q->qdisc);
	if (skb) {
		pr_debug("netem_dequeue: return skb=%p\n", skb);
		sch->q.qlen--;
		sch->flags &= ~TCQ_F_THROTTLED;
	}
	else if (pending) {
		pr_debug("netem_dequeue: throttling\n");
		sch->flags |= TCQ_F_THROTTLED;
	} 

	return skb;
}

static void netem_watchdog(unsigned long arg)
{
	struct Qdisc *sch = (struct Qdisc *)arg;

	pr_debug("netem_watchdog qlen=%d\n", sch->q.qlen);
	sch->flags &= ~TCQ_F_THROTTLED;
	netif_schedule(sch->dev);
}

static void netem_reset(struct Qdisc *sch)
{
	struct netem_sched_data *q = qdisc_priv(sch);

	qdisc_reset(q->qdisc);
	skb_queue_purge(&q->delayed);

	sch->q.qlen = 0;
	sch->flags &= ~TCQ_F_THROTTLED;
	del_timer_sync(&q->timer);
}

static int set_fifo_limit(struct Qdisc *q, int limit)
{
        struct rtattr *rta;
	int ret = -ENOMEM;

	rta = kmalloc(RTA_LENGTH(sizeof(struct tc_fifo_qopt)), GFP_KERNEL);
	if (rta) {
		rta->rta_type = RTM_NEWQDISC;
		rta->rta_len = RTA_LENGTH(sizeof(struct tc_fifo_qopt)); 
		((struct tc_fifo_qopt *)RTA_DATA(rta))->limit = limit;
		
		ret = q->ops->change(q, rta);
		kfree(rta);
	}
	return ret;
}

/*
 * Distribution data is a variable size payload containing
 * signed 16 bit values.
 */
static int get_dist_table(struct Qdisc *sch, const struct rtattr *attr)
{
	struct netem_sched_data *q = qdisc_priv(sch);
	unsigned long n = RTA_PAYLOAD(attr)/sizeof(__s16);
	const __s16 *data = RTA_DATA(attr);
	struct disttable *d;
	int i;

	if (n > 65536)
		return -EINVAL;

	d = kmalloc(sizeof(*d) + n*sizeof(d->table[0]), GFP_KERNEL);
	if (!d)
		return -ENOMEM;

	d->size = n;
	for (i = 0; i < n; i++)
		d->table[i] = data[i];
	
	spin_lock_bh(&sch->dev->queue_lock);
	d = xchg(&q->delay_dist, d);
	spin_unlock_bh(&sch->dev->queue_lock);

	kfree(d);
	return 0;
}

static int get_correlation(struct Qdisc *sch, const struct rtattr *attr)
{
	struct netem_sched_data *q = qdisc_priv(sch);
	const struct tc_netem_corr *c = RTA_DATA(attr);

	if (RTA_PAYLOAD(attr) != sizeof(*c))
		return -EINVAL;

	init_crandom(&q->delay_cor, c->delay_corr);
	init_crandom(&q->loss_cor, c->loss_corr);
	init_crandom(&q->dup_cor, c->dup_corr);
	return 0;
}

static int netem_change(struct Qdisc *sch, struct rtattr *opt)
{
	struct netem_sched_data *q = qdisc_priv(sch);
	struct tc_netem_qopt *qopt;
	int ret;
	
	if (opt == NULL || RTA_PAYLOAD(opt) < sizeof(*qopt))
		return -EINVAL;

	qopt = RTA_DATA(opt);
	ret = set_fifo_limit(q->qdisc, qopt->limit);
	if (ret) {
		pr_debug("netem: can't set fifo limit\n");
		return ret;
	}
	
	q->latency = qopt->latency;
	q->jitter = qopt->jitter;
	q->limit = qopt->limit;
	q->gap = qopt->gap;
	q->loss = qopt->loss;
	q->duplicate = qopt->duplicate;

	/* Handle nested options after initial queue options.
	 * Should have put all options in nested format but too late now.
	 */ 
	if (RTA_PAYLOAD(opt) > sizeof(*qopt)) {
		struct rtattr *tb[TCA_NETEM_MAX];
		if (rtattr_parse(tb, TCA_NETEM_MAX, 
				 RTA_DATA(opt) + sizeof(*qopt),
				 RTA_PAYLOAD(opt) - sizeof(*qopt)))
			return -EINVAL;

		if (tb[TCA_NETEM_CORR-1]) {
			ret = get_correlation(sch, tb[TCA_NETEM_CORR-1]);
			if (ret)
				return ret;
		}

		if (tb[TCA_NETEM_DELAY_DIST-1]) {
			ret = get_dist_table(sch, tb[TCA_NETEM_DELAY_DIST-1]);
			if (ret)
				return ret;
		}
	}


	return 0;
}

static int netem_init(struct Qdisc *sch, struct rtattr *opt)
{
	struct netem_sched_data *q = qdisc_priv(sch);
	int ret;

	if (!opt)
		return -EINVAL;

	skb_queue_head_init(&q->delayed);
	init_timer(&q->timer);
	q->timer.function = netem_watchdog;
	q->timer.data = (unsigned long) sch;
	q->counter = 0;

	q->qdisc = qdisc_create_dflt(sch->dev, &pfifo_qdisc_ops);
	if (!q->qdisc) {
		pr_debug("netem: qdisc create failed\n");
		return -ENOMEM;
	}

	ret = netem_change(sch, opt);
	if (ret) {
		pr_debug("netem: change failed\n");
		qdisc_destroy(q->qdisc);
	}
	return ret;
}

static void netem_destroy(struct Qdisc *sch)
{
	struct netem_sched_data *q = qdisc_priv(sch);

	del_timer_sync(&q->timer);
	qdisc_destroy(q->qdisc);
	kfree(q->delay_dist);
}

static int netem_dump(struct Qdisc *sch, struct sk_buff *skb)
{
	const struct netem_sched_data *q = qdisc_priv(sch);
	unsigned char	 *b = skb->tail;
	struct rtattr *rta = (struct rtattr *) b;
	struct tc_netem_qopt qopt;
	struct tc_netem_corr cor;

	qopt.latency = q->latency;
	qopt.jitter = q->jitter;
	qopt.limit = q->limit;
	qopt.loss = q->loss;
	qopt.gap = q->gap;
	qopt.duplicate = q->duplicate;
	RTA_PUT(skb, TCA_OPTIONS, sizeof(qopt), &qopt);

	cor.delay_corr = q->delay_cor.rho;
	cor.loss_corr = q->loss_cor.rho;
	cor.dup_corr = q->dup_cor.rho;
	RTA_PUT(skb, TCA_NETEM_CORR, sizeof(cor), &cor);
	rta->rta_len = skb->tail - b;

	return skb->len;

rtattr_failure:
	skb_trim(skb, b - skb->data);
	return -1;
}

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

	if (cl != 1) 	/* only one class */
		return -ENOENT;

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

	return 0;
}

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

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

	sch_tree_lock(sch);
	*old = xchg(&q->qdisc, new);
	qdisc_reset(*old);
	sch->q.qlen = 0;
	sch_tree_unlock(sch);

	return 0;
}

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

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

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

static int netem_change_class(struct Qdisc *sch, u32 classid, u32 parentid, 
			    struct rtattr **tca, unsigned long *arg)
{
	return -ENOSYS;
}

static int netem_delete(struct Qdisc *sch, unsigned long arg)
{
	return -ENOSYS;
}

static void netem_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 struct tcf_proto **netem_find_tcf(struct Qdisc *sch, unsigned long cl)
{
	return NULL;
}

static struct Qdisc_class_ops netem_class_ops = {
	.graft		=	netem_graft,
	.leaf		=	netem_leaf,
	.get		=	netem_get,
	.put		=	netem_put,
	.change		=	netem_change_class,
	.delete		=	netem_delete,
	.walk		=	netem_walk,
	.tcf_chain	=	netem_find_tcf,
	.dump		=	netem_dump_class,
};

static struct Qdisc_ops netem_qdisc_ops = {
	.id		=	"netem",
	.cl_ops		=	&netem_class_ops,
	.priv_size	=	sizeof(struct netem_sched_data),
	.enqueue	=	netem_enqueue,
	.dequeue	=	netem_dequeue,
	.requeue	=	netem_requeue,
	.drop		=	netem_drop,
	.init		=	netem_init,
	.reset		=	netem_reset,
	.destroy	=	netem_destroy,
	.change		=	netem_change,
	.dump		=	netem_dump,
	.owner		=	THIS_MODULE,
};


static int __init netem_module_init(void)
{
	return register_qdisc(&netem_qdisc_ops);
}
static void __exit netem_module_exit(void)
{
	unregister_qdisc(&netem_qdisc_ops);
}
module_init(netem_module_init)
module_exit(netem_module_exit)
MODULE_LICENSE("GPL");
OpenPOWER on IntegriCloud