Free Electrons

Embedded Linux Experts

  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
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
/*
 *			Simple traffic shaper for Linux NET3.
 *
 *	(c) Copyright 1996 Alan Cox <alan@redhat.com>, All Rights Reserved.
 *				http://www.redhat.com
 *
 *	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.
 *	
 *	Neither Alan Cox nor CymruNet Ltd. admit liability nor provide 
 *	warranty for any of this software. This material is provided 
 *	"AS-IS" and at no charge.	
 *
 *	
 *	Algorithm:
 *
 *	Queue Frame:
 *		Compute time length of frame at regulated speed
 *		Add frame to queue at appropriate point
 *		Adjust time length computation for followup frames
 *		Any frame that falls outside of its boundaries is freed
 *
 *	We work to the following constants
 *
 *		SHAPER_QLEN	Maximum queued frames
 *		SHAPER_LATENCY	Bounding latency on a frame. Leaving this latency
 *				window drops the frame. This stops us queueing 
 *				frames for a long time and confusing a remote
 *				host.
 *		SHAPER_MAXSLIP	Maximum time a priority frame may jump forward.
 *				That bounds the penalty we will inflict on low
 *				priority traffic.
 *		SHAPER_BURST	Time range we call "now" in order to reduce
 *				system load. The more we make this the burstier
 *				the behaviour, the better local performance you
 *				get through packet clustering on routers and the
 *				worse the remote end gets to judge rtts.
 *
 *	This is designed to handle lower speed links ( < 200K/second or so). We
 *	run off a 100-150Hz base clock typically. This gives us a resolution at
 *	200Kbit/second of about 2Kbit or 256 bytes. Above that our timer
 *	resolution may start to cause much more burstiness in the traffic. We
 *	could avoid a lot of that by calling kick_shaper() at the end of the 
 *	tied device transmissions. If you run above about 100K second you 
 *	may need to tune the supposed speed rate for the right values.
 *
 *	BUGS:
 *		Downing the interface under the shaper before the shaper
 *		will render your machine defunct. Don't for now shape over
 *		PPP or SLIP therefore!
 *		This will be fixed in BETA4
 *
 * Update History :
 *
 *              bh_atomic() SMP races fixes and rewritten the locking code to
 *              be SMP safe and irq-mask friendly.
 *              NOTE: we can't use start_bh_atomic() in kick_shaper()
 *              because it's going to be recalled from an irq handler,
 *              and synchronize_bh() is a nono if called from irq context.
 *						1999  Andrea Arcangeli
 *
 *              Device statistics (tx_pakets, tx_bytes,
 *              tx_drops: queue_over_time and collisions: max_queue_exceded)
 *                               1999/06/18 Jordi Murgo <savage@apostols.org>
 *
 *		Use skb->cb for private data.
 *				 2000/03 Andi Kleen
 */
 
#include <linux/config.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/fcntl.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <linux/if_arp.h>
#include <linux/init.h>
#include <linux/if_shaper.h>

#include <net/dst.h>
#include <net/arp.h>

struct shaper_cb { 
	unsigned long	shapeclock;		/* Time it should go out */
	unsigned long	shapestamp;		/* Stamp for shaper    */
	__u32		shapelatency;		/* Latency on frame */
	__u32		shapelen;		/* Frame length in clocks */
	__u16		shapepend;		/* Pending */
}; 
#define SHAPERCB(skb) ((struct shaper_cb *) ((skb)->cb))

static int sh_debug;		/* Debug flag */

#define SHAPER_BANNER	"CymruNet Traffic Shaper BETA 0.04 for Linux 2.1\n"

static void shaper_kick(struct shaper *sh);

/*
 *	Compute clocks on a buffer
 */
  
static int shaper_clocks(struct shaper *shaper, struct sk_buff *skb)
{
 	int t=skb->len/shaper->bytespertick;
 	return t;
}

/*
 *	Set the speed of a shaper. We compute this in bytes per tick since
 *	thats how the machine wants to run. Quoted input is in bits per second
 *	as is traditional (note not BAUD). We assume 8 bit bytes. 
 */
  
static void shaper_setspeed(struct shaper *shaper, int bitspersec)
{
	shaper->bitspersec=bitspersec;
	shaper->bytespertick=(bitspersec/HZ)/8;
	if(!shaper->bytespertick)
		shaper->bytespertick++;
}

/*
 *	Throw a frame at a shaper.
 */
  

static int shaper_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct shaper *shaper = dev->priv;
 	struct sk_buff *ptr;
  
	spin_lock(&shaper->lock);
 	ptr=shaper->sendq.prev;
 	
 	/*
 	 *	Set up our packet details
 	 */
 	 
 	SHAPERCB(skb)->shapelatency=0;
 	SHAPERCB(skb)->shapeclock=shaper->recovery;
 	if(time_before(SHAPERCB(skb)->shapeclock, jiffies))
 		SHAPERCB(skb)->shapeclock=jiffies;
 	skb->priority=0;	/* short term bug fix */
 	SHAPERCB(skb)->shapestamp=jiffies;
 	
 	/*
 	 *	Time slots for this packet.
 	 */
 	 
 	SHAPERCB(skb)->shapelen= shaper_clocks(shaper,skb);
 	
	{
		struct sk_buff *tmp;
		/*
		 *	Up our shape clock by the time pending on the queue
		 *	(Should keep this in the shaper as a variable..)
		 */
		for(tmp=skb_peek(&shaper->sendq); tmp!=NULL && 
			tmp!=(struct sk_buff *)&shaper->sendq; tmp=tmp->next)
			SHAPERCB(skb)->shapeclock+=SHAPERCB(tmp)->shapelen;
		/*
		 *	Queue over time. Spill packet.
		 */
		if(SHAPERCB(skb)->shapeclock-jiffies > SHAPER_LATENCY) {
			dev_kfree_skb(skb);
			shaper->stats.tx_dropped++;
		} else
			skb_queue_tail(&shaper->sendq, skb);
	}

	if(sh_debug)
 		printk("Frame queued.\n");
 	if(skb_queue_len(&shaper->sendq)>SHAPER_QLEN)
 	{
 		ptr=skb_dequeue(&shaper->sendq);
                dev_kfree_skb(ptr);
                shaper->stats.collisions++;
 	}
	shaper_kick(shaper);
	spin_unlock(&shaper->lock);
 	return 0;
}

/*
 *	Transmit from a shaper
 */
 
static void shaper_queue_xmit(struct shaper *shaper, struct sk_buff *skb)
{
	struct sk_buff *newskb=skb_clone(skb, GFP_ATOMIC);
	if(sh_debug)
		printk("Kick frame on %p\n",newskb);
	if(newskb)
	{
		newskb->dev=shaper->dev;
		newskb->priority=2;
		if(sh_debug)
			printk("Kick new frame to %s, %d\n",
				shaper->dev->name,newskb->priority);
		dev_queue_xmit(newskb);

                shaper->stats.tx_bytes += skb->len;
		shaper->stats.tx_packets++;

                if(sh_debug)
			printk("Kicked new frame out.\n");
		dev_kfree_skb(skb);
	}
}

/*
 *	Timer handler for shaping clock
 */
 
static void shaper_timer(unsigned long data)
{
	struct shaper *shaper = (struct shaper *)data;

	spin_lock(&shaper->lock);
	shaper_kick(shaper);
	spin_unlock(&shaper->lock);
}

/*
 *	Kick a shaper queue and try and do something sensible with the 
 *	queue. 
 */

static void shaper_kick(struct shaper *shaper)
{
	struct sk_buff *skb;
	
	/*
	 *	Walk the list (may be empty)
	 */
	 
	while((skb=skb_peek(&shaper->sendq))!=NULL)
	{
		/*
		 *	Each packet due to go out by now (within an error
		 *	of SHAPER_BURST) gets kicked onto the link 
		 */
		 
		if(sh_debug)
			printk("Clock = %ld, jiffies = %ld\n", SHAPERCB(skb)->shapeclock, jiffies);
		if(time_before_eq(SHAPERCB(skb)->shapeclock, jiffies + SHAPER_BURST))
		{
			/*
			 *	Pull the frame and get interrupts back on.
			 */
			 
			skb_unlink(skb, &shaper->sendq);
			if (shaper->recovery < 
			    SHAPERCB(skb)->shapeclock + SHAPERCB(skb)->shapelen)
				shaper->recovery = SHAPERCB(skb)->shapeclock + SHAPERCB(skb)->shapelen;
			/*
			 *	Pass on to the physical target device via
			 *	our low level packet thrower.
			 */
			
			SHAPERCB(skb)->shapepend=0;
			shaper_queue_xmit(shaper, skb);	/* Fire */
		}
		else
			break;
	}

	/*
	 *	Next kick.
	 */
	 
	if(skb!=NULL)
		mod_timer(&shaper->timer, SHAPERCB(skb)->shapeclock);
}


/*
 *	Bring the interface up. We just disallow this until a 
 *	bind.
 */

static int shaper_open(struct net_device *dev)
{
	struct shaper *shaper=dev->priv;
	
	/*
	 *	Can't open until attached.
	 *	Also can't open until speed is set, or we'll get
	 *	a division by zero.
	 */
	 
	if(shaper->dev==NULL)
		return -ENODEV;
	if(shaper->bitspersec==0)
		return -EINVAL;
	return 0;
}

/*
 *	Closing a shaper flushes the queues.
 */
 
static int shaper_close(struct net_device *dev)
{
	struct shaper *shaper=dev->priv;
	struct sk_buff *skb;

	while ((skb = skb_dequeue(&shaper->sendq)) != NULL)
		dev_kfree_skb(skb);

	spin_lock_bh(&shaper->lock);
	shaper_kick(shaper);
	spin_unlock_bh(&shaper->lock);

	del_timer_sync(&shaper->timer);
	return 0;
}

/*
 *	Revectored calls. We alter the parameters and call the functions
 *	for our attached device. This enables us to bandwidth allocate after
 *	ARP and other resolutions and not before.
 */

static struct net_device_stats *shaper_get_stats(struct net_device *dev)
{
     	struct shaper *sh=dev->priv;
	return &sh->stats;
}

static int shaper_header(struct sk_buff *skb, struct net_device *dev, 
	unsigned short type, void *daddr, void *saddr, unsigned len)
{
	struct shaper *sh=dev->priv;
	int v;
	if(sh_debug)
		printk("Shaper header\n");
	skb->dev=sh->dev;
	v=sh->hard_header(skb,sh->dev,type,daddr,saddr,len);
	skb->dev=dev;
	return v;
}

static int shaper_rebuild_header(struct sk_buff *skb)
{
	struct shaper *sh=skb->dev->priv;
	struct net_device *dev=skb->dev;
	int v;
	if(sh_debug)
		printk("Shaper rebuild header\n");
	skb->dev=sh->dev;
	v=sh->rebuild_header(skb);
	skb->dev=dev;
	return v;
}

#if 0
static int shaper_cache(struct neighbour *neigh, struct hh_cache *hh)
{
	struct shaper *sh=neigh->dev->priv;
	struct net_device *tmp;
	int ret;
	if(sh_debug)
		printk("Shaper header cache bind\n");
	tmp=neigh->dev;
	neigh->dev=sh->dev;
	ret=sh->hard_header_cache(neigh,hh);
	neigh->dev=tmp;
	return ret;
}

static void shaper_cache_update(struct hh_cache *hh, struct net_device *dev,
	unsigned char *haddr)
{
	struct shaper *sh=dev->priv;
	if(sh_debug)
		printk("Shaper cache update\n");
	sh->header_cache_update(hh, sh->dev, haddr);
}
#endif

#ifdef CONFIG_INET

static int shaper_neigh_setup(struct neighbour *n)
{
#ifdef CONFIG_INET
	if (n->nud_state == NUD_NONE) {
		n->ops = &arp_broken_ops;
		n->output = n->ops->output;
	}
#endif	
	return 0;
}

static int shaper_neigh_setup_dev(struct net_device *dev, struct neigh_parms *p)
{
#ifdef CONFIG_INET
	if (p->tbl->family == AF_INET) {
		p->neigh_setup = shaper_neigh_setup;
		p->ucast_probes = 0;
		p->mcast_probes = 0;
	}
#endif	
	return 0;
}

#else /* !(CONFIG_INET) */

static int shaper_neigh_setup_dev(struct net_device *dev, struct neigh_parms *p)
{
	return 0;
}

#endif

static int shaper_attach(struct net_device *shdev, struct shaper *sh, struct net_device *dev)
{
	sh->dev = dev;
	sh->hard_start_xmit=dev->hard_start_xmit;
	sh->get_stats=dev->get_stats;
	if(dev->hard_header)
	{
		sh->hard_header=dev->hard_header;
		shdev->hard_header = shaper_header;
	}
	else
		shdev->hard_header = NULL;
		
	if(dev->rebuild_header)
	{
		sh->rebuild_header	= dev->rebuild_header;
		shdev->rebuild_header	= shaper_rebuild_header;
	}
	else
		shdev->rebuild_header	= NULL;
	
#if 0
	if(dev->hard_header_cache)
	{
		sh->hard_header_cache	= dev->hard_header_cache;
		shdev->hard_header_cache= shaper_cache;
	}
	else
	{
		shdev->hard_header_cache= NULL;
	}
			
	if(dev->header_cache_update)
	{
		sh->header_cache_update	= dev->header_cache_update;
		shdev->header_cache_update = shaper_cache_update;
	}
	else
		shdev->header_cache_update= NULL;
#else
	shdev->header_cache_update = NULL;
	shdev->hard_header_cache = NULL;
#endif
	shdev->neigh_setup = shaper_neigh_setup_dev;
	
	shdev->hard_header_len=dev->hard_header_len;
	shdev->type=dev->type;
	shdev->addr_len=dev->addr_len;
	shdev->mtu=dev->mtu;
	sh->bitspersec=0;
	return 0;
}

static int shaper_ioctl(struct net_device *dev,  struct ifreq *ifr, int cmd)
{
	struct shaperconf *ss= (struct shaperconf *)&ifr->ifr_ifru;
	struct shaper *sh=dev->priv;
	
	if(ss->ss_cmd == SHAPER_SET_DEV || ss->ss_cmd == SHAPER_SET_SPEED)
	{
		if(!capable(CAP_NET_ADMIN))
			return -EPERM;
	}
	
	switch(ss->ss_cmd)
	{
		case SHAPER_SET_DEV:
		{
			struct net_device *them=__dev_get_by_name(ss->ss_name);
			if(them==NULL)
				return -ENODEV;
			if(sh->dev)
				return -EBUSY;
			return shaper_attach(dev,dev->priv, them);
		}
		case SHAPER_GET_DEV:
			if(sh->dev==NULL)
				return -ENODEV;
			strcpy(ss->ss_name, sh->dev->name);
			return 0;
		case SHAPER_SET_SPEED:
			shaper_setspeed(sh,ss->ss_speed);
			return 0;
		case SHAPER_GET_SPEED:
			ss->ss_speed=sh->bitspersec;
			return 0;
		default:
			return -EINVAL;
	}
}

static void shaper_init_priv(struct net_device *dev)
{
	struct shaper *sh = dev->priv;

	skb_queue_head_init(&sh->sendq);
	init_timer(&sh->timer);
	sh->timer.function=shaper_timer;
	sh->timer.data=(unsigned long)sh;
	spin_lock_init(&sh->lock);
}

/*
 *	Add a shaper device to the system
 */
 
static void __init shaper_setup(struct net_device *dev)
{
	/*
	 *	Set up the shaper.
	 */

	SET_MODULE_OWNER(dev);

	shaper_init_priv(dev);

	dev->open		= shaper_open;
	dev->stop		= shaper_close;
	dev->hard_start_xmit 	= shaper_start_xmit;
	dev->get_stats 		= shaper_get_stats;
	dev->set_multicast_list = NULL;
	
	/*
	 *	Intialise the packet queues
	 */
	 
	/*
	 *	Handlers for when we attach to a device.
	 */

	dev->hard_header 	= shaper_header;
	dev->rebuild_header 	= shaper_rebuild_header;
#if 0
	dev->hard_header_cache	= shaper_cache;
	dev->header_cache_update= shaper_cache_update;
#endif
	dev->neigh_setup	= shaper_neigh_setup_dev;
	dev->do_ioctl		= shaper_ioctl;
	dev->hard_header_len	= 0;
	dev->type		= ARPHRD_ETHER;	/* initially */
	dev->set_mac_address	= NULL;
	dev->mtu		= 1500;
	dev->addr_len		= 0;
	dev->tx_queue_len	= 10;
	dev->flags		= 0;
}
 
static int shapers = 1;
#ifdef MODULE

module_param(shapers, int, 0);
MODULE_PARM_DESC(shapers, "Traffic shaper: maximum number of shapers");

#else /* MODULE */

static int __init set_num_shapers(char *str)
{
	shapers = simple_strtol(str, NULL, 0);
	return 1;
}

__setup("shapers=", set_num_shapers);

#endif /* MODULE */

static struct net_device **devs;

static unsigned int shapers_registered = 0;

static int __init shaper_init(void)
{
	int i;
	size_t alloc_size;
	struct net_device *dev;
	char name[IFNAMSIZ];

	if (shapers < 1)
		return -ENODEV;

	alloc_size = sizeof(*dev) * shapers;
	devs = kmalloc(alloc_size, GFP_KERNEL);
	if (!devs)
		return -ENOMEM;
	memset(devs, 0, alloc_size);

	for (i = 0; i < shapers; i++) {

		snprintf(name, IFNAMSIZ, "shaper%d", i);
		dev = alloc_netdev(sizeof(struct shaper), name,
				   shaper_setup);
		if (!dev) 
			break;

		if (register_netdev(dev)) {
			free_netdev(dev);
			break;
		}

		devs[i] = dev;
		shapers_registered++;
	}

	if (!shapers_registered) {
		kfree(devs);
		devs = NULL;
	}

	return (shapers_registered ? 0 : -ENODEV);
}

static void __exit shaper_exit (void)
{
	int i;

	for (i = 0; i < shapers_registered; i++) {
		if (devs[i]) {
			unregister_netdev(devs[i]);
			free_netdev(devs[i]);
		}
	}

	kfree(devs);
	devs = NULL;
}

module_init(shaper_init);
module_exit(shaper_exit);
MODULE_LICENSE("GPL");