summaryrefslogtreecommitdiffstats
path: root/net/bridge/br_if.c
blob: 9b46d2dc4c224e39e865adf3956c5528da9b68f9 (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
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
/*
 *	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/etherdevice.h>
#include <linux/netpoll.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 <linux/slab.h>
#include <net/dsa.h>
#include <net/sock.h>
#include <linux/if_vlan.h>
#include <net/switchdev.h>
#include <net/net_namespace.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)
{
	struct ethtool_link_ksettings ecmd;

	if (!__ethtool_get_link_ksettings(dev, &ecmd)) {
		switch (ecmd.base.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 transitions. */
void br_port_carrier_check(struct net_bridge_port *p, bool *notified)
{
	struct net_device *dev = p->dev;
	struct net_bridge *br = p->br;

	if (!(p->flags & BR_ADMIN_COST) &&
	    netif_running(dev) && netif_oper_up(dev))
		p->path_cost = port_cost(dev);

	*notified = false;
	if (!netif_running(br->dev))
		return;

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

static void br_port_set_promisc(struct net_bridge_port *p)
{
	int err = 0;

	if (br_promisc_port(p))
		return;

	err = dev_set_promiscuity(p->dev, 1);
	if (err)
		return;

	br_fdb_unsync_static(p->br, p);
	p->flags |= BR_PROMISC;
}

static void br_port_clear_promisc(struct net_bridge_port *p)
{
	int err;

	/* Check if the port is already non-promisc or if it doesn't
	 * support UNICAST filtering.  Without unicast filtering support
	 * we'll end up re-enabling promisc mode anyway, so just check for
	 * it here.
	 */
	if (!br_promisc_port(p) || !(p->dev->priv_flags & IFF_UNICAST_FLT))
		return;

	/* Since we'll be clearing the promisc mode, program the port
	 * first so that we don't have interruption in traffic.
	 */
	err = br_fdb_sync_static(p->br, p);
	if (err)
		return;

	dev_set_promiscuity(p->dev, -1);
	p->flags &= ~BR_PROMISC;
}

/* When a port is added or removed or when certain port flags
 * change, this function is called to automatically manage
 * promiscuity setting of all the bridge ports.  We are always called
 * under RTNL so can skip using rcu primitives.
 */
void br_manage_promisc(struct net_bridge *br)
{
	struct net_bridge_port *p;
	bool set_all = false;

	/* If vlan filtering is disabled or bridge interface is placed
	 * into promiscuous mode, place all ports in promiscuous mode.
	 */
	if ((br->dev->flags & IFF_PROMISC) || !br_vlan_enabled(br->dev))
		set_all = true;

	list_for_each_entry(p, &br->port_list, list) {
		if (set_all) {
			br_port_set_promisc(p);
		} else {
			/* If the number of auto-ports is <= 1, then all other
			 * ports will have their output configuration
			 * statically specified through fdbs.  Since ingress
			 * on the auto-port becomes forwarding/egress to other
			 * ports and egress configuration is statically known,
			 * we can say that ingress configuration of the
			 * auto-port is also statically known.
			 * This lets us disable promiscuous mode and write
			 * this config to hw.
			 */
			if (br->auto_cnt == 0 ||
			    (br->auto_cnt == 1 && br_auto_port(p)))
				br_port_clear_promisc(p);
			else
				br_port_set_promisc(p);
		}
	}
}

int nbp_backup_change(struct net_bridge_port *p,
		      struct net_device *backup_dev)
{
	struct net_bridge_port *old_backup = rtnl_dereference(p->backup_port);
	struct net_bridge_port *backup_p = NULL;

	ASSERT_RTNL();

	if (backup_dev) {
		if (!br_port_exists(backup_dev))
			return -ENOENT;

		backup_p = br_port_get_rtnl(backup_dev);
		if (backup_p->br != p->br)
			return -EINVAL;
	}

	if (p == backup_p)
		return -EINVAL;

	if (old_backup == backup_p)
		return 0;

	/* if the backup link is already set, clear it */
	if (old_backup)
		old_backup->backup_redirected_cnt--;

	if (backup_p)
		backup_p->backup_redirected_cnt++;
	rcu_assign_pointer(p->backup_port, backup_p);

	return 0;
}

static void nbp_backup_clear(struct net_bridge_port *p)
{
	nbp_backup_change(p, NULL);
	if (p->backup_redirected_cnt) {
		struct net_bridge_port *cur_p;

		list_for_each_entry(cur_p, &p->br->port_list, list) {
			struct net_bridge_port *backup_p;

			backup_p = rtnl_dereference(cur_p->backup_port);
			if (backup_p == p)
				nbp_backup_change(cur_p, NULL);
		}
	}

	WARN_ON(rcu_access_pointer(p->backup_port) || p->backup_redirected_cnt);
}

static void nbp_update_port_count(struct net_bridge *br)
{
	struct net_bridge_port *p;
	u32 cnt = 0;

	list_for_each_entry(p, &br->port_list, list) {
		if (br_auto_port(p))
			cnt++;
	}
	if (br->auto_cnt != cnt) {
		br->auto_cnt = cnt;
		br_manage_promisc(br);
	}
}

static void nbp_delete_promisc(struct net_bridge_port *p)
{
	/* If port is currently promiscuous, unset promiscuity.
	 * Otherwise, it is a static port so remove all addresses
	 * from it.
	 */
	dev_set_allmulti(p->dev, -1);
	if (br_promisc_port(p))
		dev_set_promiscuity(p->dev, -1);
	else
		br_fdb_unsync_static(p->br, p);
}

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

static void brport_get_ownership(struct kobject *kobj, kuid_t *uid, kgid_t *gid)
{
	struct net_bridge_port *p = kobj_to_brport(kobj);

	net_ns_get_ownership(dev_net(p->dev), uid, gid);
}

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

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);
}

static unsigned get_max_headroom(struct net_bridge *br)
{
	unsigned max_headroom = 0;
	struct net_bridge_port *p;

	list_for_each_entry(p, &br->port_list, list) {
		unsigned dev_headroom = netdev_get_fwd_headroom(p->dev);

		if (dev_headroom > max_headroom)
			max_headroom = dev_headroom;
	}

	return max_headroom;
}

static void update_headroom(struct net_bridge *br, int new_hr)
{
	struct net_bridge_port *p;

	list_for_each_entry(p, &br->port_list, list)
		netdev_set_rx_headroom(p->dev, new_hr);

	br->dev->needed_headroom = new_hr;
}

/* 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, p->dev->name);

	nbp_delete_promisc(p);

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

	br_ifinfo_notify(RTM_DELLINK, NULL, p);

	list_del_rcu(&p->list);
	if (netdev_get_fwd_headroom(dev) == br->dev->needed_headroom)
		update_headroom(br, get_max_headroom(br));
	netdev_reset_rx_headroom(dev);

	nbp_vlan_flush(p);
	br_fdb_delete_by_port(br, p, 0, 1);
	switchdev_deferred_process();
	nbp_backup_clear(p);

	nbp_update_port_count(br);

	netdev_upper_dev_unlink(dev, br->dev);

	dev->priv_flags &= ~IFF_BRIDGE_PORT;

	netdev_rx_handler_unregister(dev);

	br_multicast_del_port(p);

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

	br_netpoll_disable(p);

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

/* Delete bridge device */
void br_dev_delete(struct net_device *dev, struct list_head *head)
{
	struct net_bridge *br = netdev_priv(dev);
	struct net_bridge_port *p, *n;

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

	br_recalculate_neigh_suppress_enabled(br);

	br_fdb_delete_by_port(br, NULL, 0, 1);

	cancel_delayed_work_sync(&br->gc_work);

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

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

	inuse = bitmap_zalloc(BR_MAX_PORTS, 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);
	bitmap_free(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)
{
	struct net_bridge_port *p;
	int index, err;

	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 = BR_LEARNING | BR_FLOOD | BR_MCAST_FLOOD | BR_BCAST_FLOOD;
	br_init_port(p);
	br_set_state(p, BR_STATE_DISABLED);
	br_stp_port_timer_init(p);
	err = br_multicast_add_port(p);
	if (err) {
		dev_put(dev);
		kfree(p);
		p = ERR_PTR(err);
	}

	return p;
}

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

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

	if (!dev)
		return -ENOMEM;

	dev_net_set(dev, net);
	dev->rtnl_link_ops = &br_link_ops;

	res = register_netdev(dev);
	if (res)
		free_netdev(dev);
	return res;
}

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
		br_dev_delete(dev, NULL);

	rtnl_unlock();
	return ret;
}

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

	list_for_each_entry(p, &br->port_list, list)
		if (!ret_mtu || ret_mtu > p->dev->mtu)
			ret_mtu = p->dev->mtu;

	return ret_mtu ? ret_mtu : ETH_DATA_LEN;
}

void br_mtu_auto_adjust(struct net_bridge *br)
{
	ASSERT_RTNL();

	/* if the bridge MTU was manually configured don't mess with it */
	if (br_opt_get(br, BROPT_MTU_SET_BY_USER))
		return;

	/* change to the minimum MTU and clear the flag which was set by
	 * the bridge ndo_change_mtu callback
	 */
	dev_set_mtu(br->dev, br_mtu_min(br));
	br_opt_toggle(br, BROPT_MTU_SET_BY_USER, false);
}

static void br_set_gso_limits(struct net_bridge *br)
{
	unsigned int gso_max_size = GSO_MAX_SIZE;
	u16 gso_max_segs = GSO_MAX_SEGS;
	const struct net_bridge_port *p;

	list_for_each_entry(p, &br->port_list, list) {
		gso_max_size = min(gso_max_size, p->dev->gso_max_size);
		gso_max_segs = min(gso_max_segs, p->dev->gso_max_segs);
	}
	br->dev->gso_max_size = gso_max_size;
	br->dev->gso_max_segs = gso_max_segs;
}

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

	if (list_empty(&br->port_list))
		return features;

	mask = features;
	features &= ~NETIF_F_ONE_FOR_ALL;

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

	return features;
}

/* called with RTNL */
int br_add_if(struct net_bridge *br, struct net_device *dev,
	      struct netlink_ext_ack *extack)
{
	struct net_bridge_port *p;
	int err = 0;
	unsigned br_hr, dev_hr;
	bool changed_addr;

	/* Don't allow bridging non-ethernet like devices, or DSA-enabled
	 * master network devices since the bridge layer rx_handler prevents
	 * the DSA fake ethertype handler to be invoked, so we do not strip off
	 * the DSA switch tag protocol header and the bridge layer just return
	 * RX_HANDLER_CONSUMED, stopping RX processing for these frames.
	 */
	if ((dev->flags & IFF_LOOPBACK) ||
	    dev->type != ARPHRD_ETHER || dev->addr_len != ETH_ALEN ||
	    !is_valid_ether_addr(dev->dev_addr) ||
	    netdev_uses_dsa(dev))
		return -EINVAL;

	/* No bridging of bridges */
	if (dev->netdev_ops->ndo_start_xmit == br_dev_xmit) {
		NL_SET_ERR_MSG(extack,
			       "Can not enslave a bridge to a bridge");
		return -ELOOP;
	}

	/* Device has master upper dev */
	if (netdev_master_upper_dev_get(dev))
		return -EBUSY;

	/* No bridging devices that dislike that (e.g. wireless) */
	if (dev->priv_flags & IFF_DONT_BRIDGE) {
		NL_SET_ERR_MSG(extack,
			       "Device does not allow enslaving to a bridge");
		return -EOPNOTSUPP;
	}

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

	call_netdevice_notifiers(NETDEV_JOIN, dev);

	err = dev_set_allmulti(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 err1;

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

	err = br_netpoll_enable(p);
	if (err)
		goto err3;

	err = netdev_rx_handler_register(dev, br_handle_frame, p);
	if (err)
		goto err4;

	dev->priv_flags |= IFF_BRIDGE_PORT;

	err = netdev_master_upper_dev_link(dev, br->dev, NULL, NULL, extack);
	if (err)
		goto err5;

	err = nbp_switchdev_mark_set(p);
	if (err)
		goto err6;

	dev_disable_lro(dev);

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

	nbp_update_port_count(br);

	netdev_update_features(br->dev);

	br_hr = br->dev->needed_headroom;
	dev_hr = netdev_get_fwd_headroom(dev);
	if (br_hr < dev_hr)
		update_headroom(br, dev_hr);
	else
		netdev_set_rx_headroom(dev, br_hr);

	if (br_fdb_insert(br, p, dev->dev_addr, 0))
		netdev_err(dev, "failed insert local address bridge forwarding table\n");

	err = nbp_vlan_init(p);
	if (err) {
		netdev_err(dev, "failed to initialize vlan filtering on this port\n");
		goto err7;
	}

	spin_lock_bh(&br->lock);
	changed_addr = br_stp_recalculate_bridge_id(br);

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

	br_ifinfo_notify(RTM_NEWLINK, NULL, p);

	if (changed_addr)
		call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev);

	br_mtu_auto_adjust(br);
	br_set_gso_limits(br);

	kobject_uevent(&p->kobj, KOBJ_ADD);

	return 0;

err7:
	list_del_rcu(&p->list);
	br_fdb_delete_by_port(br, p, 0, 1);
	nbp_update_port_count(br);
err6:
	netdev_upper_dev_unlink(dev, br->dev);
err5:
	dev->priv_flags &= ~IFF_BRIDGE_PORT;
	netdev_rx_handler_unregister(dev);
err4:
	br_netpoll_disable(p);
err3:
	sysfs_remove_link(br->ifobj, p->dev->name);
err2:
	kobject_put(&p->kobj);
	p = NULL; /* kobject_put frees */
err1:
	dev_set_allmulti(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;
	bool changed_addr;

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

	/* Since more than one interface can be attached to a bridge,
	 * there still maybe an alternate path for netconsole to use;
	 * therefore there is no reason for a NETDEV_RELEASE event.
	 */
	del_nbp(p);

	br_mtu_auto_adjust(br);
	br_set_gso_limits(br);

	spin_lock_bh(&br->lock);
	changed_addr = br_stp_recalculate_bridge_id(br);
	spin_unlock_bh(&br->lock);

	if (changed_addr)
		call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev);

	netdev_update_features(br->dev);

	return 0;
}

void br_port_flags_change(struct net_bridge_port *p, unsigned long mask)
{
	struct net_bridge *br = p->br;

	if (mask & BR_AUTO_MASK)
		nbp_update_port_count(br);

	if (mask & BR_NEIGH_SUPPRESS)
		br_recalculate_neigh_suppress_enabled(br);
}