summaryrefslogtreecommitdiff
path: root/net/bridge/br_if.c
blob: bc2b1badab889fa7511ed1a07fd996d1d65920e4 (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
/*
 *	Userspace interface
 *	Linux ethernet bridge
 *
 *	Authors:
 *	Lennert Buytenhek		<buytenh@gnu.org>
 *
 *	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.
 */

#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/ethtool.h>
#include <linux/if_arp.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/rtnetlink.h>
#include <linux/if_ether.h>
#include <net/sock.h>

#include "br_private.h"

/*
 * Determine initial path cost based on speed.
 * using recommendations from 802.1d standard
 *
 * Since driver might sleep need to not be holding any locks.
 */
static int port_cost(struct net_device *dev)
{
	if (dev->ethtool_ops && dev->ethtool_ops->get_settings) {
		struct ethtool_cmd ecmd = { .cmd = ETHTOOL_GSET, };

		if (!dev->ethtool_ops->get_settings(dev, &ecmd)) {
			switch(ecmd.speed) {
			case SPEED_10000:
				return 2;
			case SPEED_1000:
				return 4;
			case SPEED_100:
				return 19;
			case SPEED_10:
				return 100;
			}
		}
	}

	/* Old silly heuristics based on name */
	if (!strncmp(dev->name, "lec", 3))
		return 7;

	if (!strncmp(dev->name, "plip", 4))
		return 2500;

	return 100;	/* assume old 10Mbps */
}


/*
 * Check for port carrier transistions.
 * Called from work queue to allow for calling functions that
 * might sleep (such as speed check), and to debounce.
 */
void br_port_carrier_check(struct net_bridge_port *p)
{
	struct net_device *dev = p->dev;
	struct net_bridge *br = p->br;

	if (netif_carrier_ok(dev))
		p->path_cost = port_cost(dev);

	if (netif_running(br->dev)) {
		spin_lock_bh(&br->lock);
		if (netif_carrier_ok(dev)) {
			if (p->state == BR_STATE_DISABLED)
				br_stp_enable_port(p);
		} else {
			if (p->state != BR_STATE_DISABLED)
				br_stp_disable_port(p);
		}
		spin_unlock_bh(&br->lock);
	}
}

static void release_nbp(struct kobject *kobj)
{
	struct net_bridge_port *p
		= container_of(kobj, struct net_bridge_port, kobj);
	kfree(p);
}

static struct kobj_type brport_ktype = {
#ifdef CONFIG_SYSFS
	.sysfs_ops = &brport_sysfs_ops,
#endif
	.release = release_nbp,
};

static void destroy_nbp(struct net_bridge_port *p)
{
	struct net_device *dev = p->dev;

	p->br = NULL;
	p->dev = NULL;
	dev_put(dev);

	kobject_put(&p->kobj);
}

static void destroy_nbp_rcu(struct rcu_head *head)
{
	struct net_bridge_port *p =
			container_of(head, struct net_bridge_port, rcu);
	destroy_nbp(p);
}

/* Delete port(interface) from bridge is done in two steps.
 * via RCU. First step, marks device as down. That deletes
 * all the timers and stops new packets from flowing through.
 *
 * Final cleanup doesn't occur until after all CPU's finished
 * processing packets.
 *
 * Protected from multiple admin operations by RTNL mutex
 */
static void del_nbp(struct net_bridge_port *p)
{
	struct net_bridge *br = p->br;
	struct net_device *dev = p->dev;

	sysfs_remove_link(br->ifobj, dev->name);

	dev_set_promiscuity(dev, -1);

	spin_lock_bh(&br->lock);
	br_stp_disable_port(p);
	spin_unlock_bh(&br->lock);

	br_ifinfo_notify(RTM_DELLINK, p);

	br_fdb_delete_by_port(br, p, 1);

	list_del_rcu(&p->list);

	rcu_assign_pointer(dev->br_port, NULL);

	kobject_uevent(&p->kobj, KOBJ_REMOVE);
	kobject_del(&p->kobj);

	call_rcu(&p->rcu, destroy_nbp_rcu);
}

/* called with RTNL */
static void del_br(struct net_bridge *br, struct list_head *head)
{
	struct net_bridge_port *p, *n;

	list_for_each_entry_safe(p, n, &br->port_list, list) {
		del_nbp(p);
	}

	del_timer_sync(&br->gc_timer);

	br_sysfs_delbr(br->dev);
	unregister_netdevice_queue(br->dev, head);
}

static struct net_device *new_bridge_dev(struct net *net, const char *name)
{
	struct net_bridge *br;
	struct net_device *dev;

	dev = alloc_netdev(sizeof(struct net_bridge), name,
			   br_dev_setup);

	if (!dev)
		return NULL;
	dev_net_set(dev, net);

	br = netdev_priv(dev);
	br->dev = dev;

	spin_lock_init(&br->lock);
	INIT_LIST_HEAD(&br->port_list);
	spin_lock_init(&br->hash_lock);

	br->bridge_id.prio[0] = 0x80;
	br->bridge_id.prio[1] = 0x00;

	memcpy(br->group_addr, br_group_address, ETH_ALEN);

	br->feature_mask = dev->features;
	br->stp_enabled = BR_NO_STP;
	br->designated_root = br->bridge_id;
	br->root_path_cost = 0;
	br->root_port = 0;
	br->bridge_max_age = br->max_age = 20 * HZ;
	br->bridge_hello_time = br->hello_time = 2 * HZ;
	br->bridge_forward_delay = br->forward_delay = 15 * HZ;
	br->topology_change = 0;
	br->topology_change_detected = 0;
	br->ageing_time = 300 * HZ;

	br_netfilter_rtable_init(br);

	br_stp_timer_init(br);

	return dev;
}

/* find an available port number */
static int find_portno(struct net_bridge *br)
{
	int index;
	struct net_bridge_port *p;
	unsigned long *inuse;

	inuse = kcalloc(BITS_TO_LONGS(BR_MAX_PORTS), sizeof(unsigned long),
			GFP_KERNEL);
	if (!inuse)
		return -ENOMEM;

	set_bit(0, inuse);	/* zero is reserved */
	list_for_each_entry(p, &br->port_list, list) {
		set_bit(p->port_no, inuse);
	}
	index = find_first_zero_bit(inuse, BR_MAX_PORTS);
	kfree(inuse);

	return (index >= BR_MAX_PORTS) ? -EXFULL : index;
}

/* called with RTNL but without bridge lock */
static struct net_bridge_port *new_nbp(struct net_bridge *br,
				       struct net_device *dev)
{
	int index;
	struct net_bridge_port *p;

	index = find_portno(br);
	if (index < 0)
		return ERR_PTR(index);

	p = kzalloc(sizeof(*p), GFP_KERNEL);
	if (p == NULL)
		return ERR_PTR(-ENOMEM);

	p->br = br;
	dev_hold(dev);
	p->dev = dev;
	p->path_cost = port_cost(dev);
	p->priority = 0x8000 >> BR_PORT_BITS;
	p->port_no = index;
	p->flags = 0;
	br_init_port(p);
	p->state = BR_STATE_DISABLED;
	br_stp_port_timer_init(p);

	return p;
}

static struct device_type br_type = {
	.name	= "bridge",
};

int br_add_bridge(struct net *net, const char *name)
{
	struct net_device *dev;
	int ret;

	dev = new_bridge_dev(net, name);
	if (!dev)
		return -ENOMEM;

	rtnl_lock();
	if (strchr(dev->name, '%')) {
		ret = dev_alloc_name(dev, dev->name);
		if (ret < 0)
			goto out_free;
	}

	SET_NETDEV_DEVTYPE(dev, &br_type);

	ret = register_netdevice(dev);
	if (ret)
		goto out_free;

	ret = br_sysfs_addbr(dev);
	if (ret)
		unregister_netdevice(dev);
 out:
	rtnl_unlock();
	return ret;

out_free:
	free_netdev(dev);
	goto out;
}

int br_del_bridge(struct net *net, const char *name)
{
	struct net_device *dev;
	int ret = 0;

	rtnl_lock();
	dev = __dev_get_by_name(net, name);
	if (dev == NULL)
		ret =  -ENXIO; 	/* Could not find device */

	else if (!(dev->priv_flags & IFF_EBRIDGE)) {
		/* Attempt to delete non bridge device! */
		ret = -EPERM;
	}

	else if (dev->flags & IFF_UP) {
		/* Not shutdown yet. */
		ret = -EBUSY;
	}

	else
		del_br(netdev_priv(dev), NULL);

	rtnl_unlock();
	return ret;
}

/* MTU of the bridge pseudo-device: ETH_DATA_LEN or the minimum of the ports */
int br_min_mtu(const struct net_bridge *br)
{
	const struct net_bridge_port *p;
	int mtu = 0;

	ASSERT_RTNL();

	if (list_empty(&br->port_list))
		mtu = ETH_DATA_LEN;
	else {
		list_for_each_entry(p, &br->port_list, list) {
			if (!mtu  || p->dev->mtu < mtu)
				mtu = p->dev->mtu;
		}
	}
	return mtu;
}

/*
 * Recomputes features using slave's features
 */
void br_features_recompute(struct net_bridge *br)
{
	struct net_bridge_port *p;
	unsigned long features, mask;

	features = mask = br->feature_mask;
	if (list_empty(&br->port_list))
		goto done;

	features &= ~NETIF_F_ONE_FOR_ALL;

	list_for_each_entry(p, &br->port_list, list) {
		features = netdev_increment_features(features,
						     p->dev->features, mask);
	}

done:
	br->dev->features = netdev_fix_features(features, NULL);
}

/* called with RTNL */
int br_add_if(struct net_bridge *br, struct net_device *dev)
{
	struct net_bridge_port *p;
	int err = 0;

	/* Don't allow bridging non-ethernet like devices */
	if ((dev->flags & IFF_LOOPBACK) ||
	    dev->type != ARPHRD_ETHER || dev->addr_len != ETH_ALEN)
		return -EINVAL;

	/* No bridging of bridges */
	if (dev->netdev_ops->ndo_start_xmit == br_dev_xmit)
		return -ELOOP;

	/* Device is already being bridged */
	if (dev->br_port != NULL)
		return -EBUSY;

	/* No bridging devices that dislike that (e.g. wireless) */
	if (dev->priv_flags & IFF_DONT_BRIDGE)
		return -EOPNOTSUPP;

	p = new_nbp(br, dev);
	if (IS_ERR(p))
		return PTR_ERR(p);

	err = dev_set_promiscuity(dev, 1);
	if (err)
		goto put_back;

	err = kobject_init_and_add(&p->kobj, &brport_ktype, &(dev->dev.kobj),
				   SYSFS_BRIDGE_PORT_ATTR);
	if (err)
		goto err0;

	err = br_fdb_insert(br, p, dev->dev_addr);
	if (err)
		goto err1;

	err = br_sysfs_addif(p);
	if (err)
		goto err2;

	rcu_assign_pointer(dev->br_port, p);
	dev_disable_lro(dev);

	list_add_rcu(&p->list, &br->port_list);

	spin_lock_bh(&br->lock);
	br_stp_recalculate_bridge_id(br);
	br_features_recompute(br);

	if ((dev->flags & IFF_UP) && netif_carrier_ok(dev) &&
	    (br->dev->flags & IFF_UP))
		br_stp_enable_port(p);
	spin_unlock_bh(&br->lock);

	br_ifinfo_notify(RTM_NEWLINK, p);

	dev_set_mtu(br->dev, br_min_mtu(br));

	kobject_uevent(&p->kobj, KOBJ_ADD);

	return 0;
err2:
	br_fdb_delete_by_port(br, p, 1);
err1:
	kobject_put(&p->kobj);
	p = NULL; /* kobject_put frees */
err0:
	dev_set_promiscuity(dev, -1);
put_back:
	dev_put(dev);
	kfree(p);
	return err;
}

/* called with RTNL */
int br_del_if(struct net_bridge *br, struct net_device *dev)
{
	struct net_bridge_port *p = dev->br_port;

	if (!p || p->br != br)
		return -EINVAL;

	del_nbp(p);

	spin_lock_bh(&br->lock);
	br_stp_recalculate_bridge_id(br);
	br_features_recompute(br);
	spin_unlock_bh(&br->lock);

	return 0;
}

void __net_exit br_net_exit(struct net *net)
{
	struct net_device *dev;
	LIST_HEAD(list);

	rtnl_lock();
	for_each_netdev(net, dev)
		if (dev->priv_flags & IFF_EBRIDGE)
			del_br(netdev_priv(dev), &list);

	unregister_netdevice_many(&list);
	rtnl_unlock();

}