summaryrefslogtreecommitdiff
path: root/net/bridge/br_device.c
blob: 8c7b78f8bc230f5811803f83ab72ee42b71be5e2 (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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 *	Device handling code
 *	Linux ethernet bridge
 *
 *	Authors:
 *	Lennert Buytenhek		<buytenh@gnu.org>
 */

#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/netpoll.h>
#include <linux/etherdevice.h>
#include <linux/ethtool.h>
#include <linux/list.h>
#include <linux/netfilter_bridge.h>

#include <linux/uaccess.h>
#include "br_private.h"

#define COMMON_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | \
			 NETIF_F_GSO_MASK | NETIF_F_HW_CSUM)

const struct nf_br_ops __rcu *nf_br_ops __read_mostly;
EXPORT_SYMBOL_GPL(nf_br_ops);

/* net device transmit always called with BH disabled */
netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct net_bridge *br = netdev_priv(dev);
	struct net_bridge_fdb_entry *dst;
	struct net_bridge_mdb_entry *mdst;
	struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats);
	const struct nf_br_ops *nf_ops;
	u8 state = BR_STATE_FORWARDING;
	const unsigned char *dest;
	u16 vid = 0;

	rcu_read_lock();
	nf_ops = rcu_dereference(nf_br_ops);
	if (nf_ops && nf_ops->br_dev_xmit_hook(skb)) {
		rcu_read_unlock();
		return NETDEV_TX_OK;
	}

	u64_stats_update_begin(&brstats->syncp);
	brstats->tx_packets++;
	brstats->tx_bytes += skb->len;
	u64_stats_update_end(&brstats->syncp);

	br_switchdev_frame_unmark(skb);
	BR_INPUT_SKB_CB(skb)->brdev = dev;
	BR_INPUT_SKB_CB(skb)->frag_max_size = 0;

	skb_reset_mac_header(skb);
	skb_pull(skb, ETH_HLEN);

	if (!br_allowed_ingress(br, br_vlan_group_rcu(br), skb, &vid, &state))
		goto out;

	if (IS_ENABLED(CONFIG_INET) &&
	    (eth_hdr(skb)->h_proto == htons(ETH_P_ARP) ||
	     eth_hdr(skb)->h_proto == htons(ETH_P_RARP)) &&
	    br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED)) {
		br_do_proxy_suppress_arp(skb, br, vid, NULL);
	} else if (IS_ENABLED(CONFIG_IPV6) &&
		   skb->protocol == htons(ETH_P_IPV6) &&
		   br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED) &&
		   pskb_may_pull(skb, sizeof(struct ipv6hdr) +
				 sizeof(struct nd_msg)) &&
		   ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) {
			struct nd_msg *msg, _msg;

			msg = br_is_nd_neigh_msg(skb, &_msg);
			if (msg)
				br_do_suppress_nd(skb, br, vid, NULL, msg);
	}

	dest = eth_hdr(skb)->h_dest;
	if (is_broadcast_ether_addr(dest)) {
		br_flood(br, skb, BR_PKT_BROADCAST, false, true);
	} else if (is_multicast_ether_addr(dest)) {
		if (unlikely(netpoll_tx_running(dev))) {
			br_flood(br, skb, BR_PKT_MULTICAST, false, true);
			goto out;
		}
		if (br_multicast_rcv(br, NULL, skb, vid)) {
			kfree_skb(skb);
			goto out;
		}

		mdst = br_mdb_get(br, skb, vid);
		if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) &&
		    br_multicast_querier_exists(br, eth_hdr(skb)))
			br_multicast_flood(mdst, skb, false, true);
		else
			br_flood(br, skb, BR_PKT_MULTICAST, false, true);
	} else if ((dst = br_fdb_find_rcu(br, dest, vid)) != NULL) {
		br_forward(dst->dst, skb, false, true);
	} else {
		br_flood(br, skb, BR_PKT_UNICAST, false, true);
	}
out:
	rcu_read_unlock();
	return NETDEV_TX_OK;
}

static struct lock_class_key bridge_netdev_addr_lock_key;

static void br_set_lockdep_class(struct net_device *dev)
{
	lockdep_set_class(&dev->addr_list_lock, &bridge_netdev_addr_lock_key);
}

static int br_dev_init(struct net_device *dev)
{
	struct net_bridge *br = netdev_priv(dev);
	int err;

	br->stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
	if (!br->stats)
		return -ENOMEM;

	err = br_fdb_hash_init(br);
	if (err) {
		free_percpu(br->stats);
		return err;
	}

	err = br_mdb_hash_init(br);
	if (err) {
		free_percpu(br->stats);
		br_fdb_hash_fini(br);
		return err;
	}

	err = br_vlan_init(br);
	if (err) {
		free_percpu(br->stats);
		br_mdb_hash_fini(br);
		br_fdb_hash_fini(br);
		return err;
	}

	err = br_multicast_init_stats(br);
	if (err) {
		free_percpu(br->stats);
		br_vlan_flush(br);
		br_mdb_hash_fini(br);
		br_fdb_hash_fini(br);
	}

	br_set_lockdep_class(dev);
	return err;
}

static void br_dev_uninit(struct net_device *dev)
{
	struct net_bridge *br = netdev_priv(dev);

	br_multicast_dev_del(br);
	br_multicast_uninit_stats(br);
	br_vlan_flush(br);
	br_mdb_hash_fini(br);
	br_fdb_hash_fini(br);
	free_percpu(br->stats);
}

static int br_dev_open(struct net_device *dev)
{
	struct net_bridge *br = netdev_priv(dev);

	netdev_update_features(dev);
	netif_start_queue(dev);
	br_stp_enable_bridge(br);
	br_multicast_open(br);

	return 0;
}

static void br_dev_set_multicast_list(struct net_device *dev)
{
}

static void br_dev_change_rx_flags(struct net_device *dev, int change)
{
	if (change & IFF_PROMISC)
		br_manage_promisc(netdev_priv(dev));
}

static int br_dev_stop(struct net_device *dev)
{
	struct net_bridge *br = netdev_priv(dev);

	br_stp_disable_bridge(br);
	br_multicast_stop(br);

	netif_stop_queue(dev);

	return 0;
}

static void br_get_stats64(struct net_device *dev,
			   struct rtnl_link_stats64 *stats)
{
	struct net_bridge *br = netdev_priv(dev);
	struct pcpu_sw_netstats tmp, sum = { 0 };
	unsigned int cpu;

	for_each_possible_cpu(cpu) {
		unsigned int start;
		const struct pcpu_sw_netstats *bstats
			= per_cpu_ptr(br->stats, cpu);
		do {
			start = u64_stats_fetch_begin_irq(&bstats->syncp);
			memcpy(&tmp, bstats, sizeof(tmp));
		} while (u64_stats_fetch_retry_irq(&bstats->syncp, start));
		sum.tx_bytes   += tmp.tx_bytes;
		sum.tx_packets += tmp.tx_packets;
		sum.rx_bytes   += tmp.rx_bytes;
		sum.rx_packets += tmp.rx_packets;
	}

	stats->tx_bytes   = sum.tx_bytes;
	stats->tx_packets = sum.tx_packets;
	stats->rx_bytes   = sum.rx_bytes;
	stats->rx_packets = sum.rx_packets;
}

static int br_change_mtu(struct net_device *dev, int new_mtu)
{
	struct net_bridge *br = netdev_priv(dev);

	dev->mtu = new_mtu;

	/* this flag will be cleared if the MTU was automatically adjusted */
	br_opt_toggle(br, BROPT_MTU_SET_BY_USER, true);
#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
	/* remember the MTU in the rtable for PMTU */
	dst_metric_set(&br->fake_rtable.dst, RTAX_MTU, new_mtu);
#endif

	return 0;
}

/* Allow setting mac address to any valid ethernet address. */
static int br_set_mac_address(struct net_device *dev, void *p)
{
	struct net_bridge *br = netdev_priv(dev);
	struct sockaddr *addr = p;

	if (!is_valid_ether_addr(addr->sa_data))
		return -EADDRNOTAVAIL;

	/* dev_set_mac_addr() can be called by a master device on bridge's
	 * NETDEV_UNREGISTER, but since it's being destroyed do nothing
	 */
	if (dev->reg_state != NETREG_REGISTERED)
		return -EBUSY;

	spin_lock_bh(&br->lock);
	if (!ether_addr_equal(dev->dev_addr, addr->sa_data)) {
		/* Mac address will be changed in br_stp_change_bridge_id(). */
		br_stp_change_bridge_id(br, addr->sa_data);
	}
	spin_unlock_bh(&br->lock);

	return 0;
}

static void br_getinfo(struct net_device *dev, struct ethtool_drvinfo *info)
{
	strlcpy(info->driver, "bridge", sizeof(info->driver));
	strlcpy(info->version, BR_VERSION, sizeof(info->version));
	strlcpy(info->fw_version, "N/A", sizeof(info->fw_version));
	strlcpy(info->bus_info, "N/A", sizeof(info->bus_info));
}

static int br_get_link_ksettings(struct net_device *dev,
				 struct ethtool_link_ksettings *cmd)
{
	struct net_bridge *br = netdev_priv(dev);
	struct net_bridge_port *p;

	cmd->base.duplex = DUPLEX_UNKNOWN;
	cmd->base.port = PORT_OTHER;
	cmd->base.speed = SPEED_UNKNOWN;

	list_for_each_entry(p, &br->port_list, list) {
		struct ethtool_link_ksettings ecmd;
		struct net_device *pdev = p->dev;

		if (!netif_running(pdev) || !netif_oper_up(pdev))
			continue;

		if (__ethtool_get_link_ksettings(pdev, &ecmd))
			continue;

		if (ecmd.base.speed == (__u32)SPEED_UNKNOWN)
			continue;

		if (cmd->base.speed == (__u32)SPEED_UNKNOWN ||
		    cmd->base.speed < ecmd.base.speed)
			cmd->base.speed = ecmd.base.speed;
	}

	return 0;
}

static netdev_features_t br_fix_features(struct net_device *dev,
	netdev_features_t features)
{
	struct net_bridge *br = netdev_priv(dev);

	return br_features_recompute(br, features);
}

#ifdef CONFIG_NET_POLL_CONTROLLER
static void br_poll_controller(struct net_device *br_dev)
{
}

static void br_netpoll_cleanup(struct net_device *dev)
{
	struct net_bridge *br = netdev_priv(dev);
	struct net_bridge_port *p;

	list_for_each_entry(p, &br->port_list, list)
		br_netpoll_disable(p);
}

static int __br_netpoll_enable(struct net_bridge_port *p)
{
	struct netpoll *np;
	int err;

	np = kzalloc(sizeof(*p->np), GFP_KERNEL);
	if (!np)
		return -ENOMEM;

	err = __netpoll_setup(np, p->dev);
	if (err) {
		kfree(np);
		return err;
	}

	p->np = np;
	return err;
}

int br_netpoll_enable(struct net_bridge_port *p)
{
	if (!p->br->dev->npinfo)
		return 0;

	return __br_netpoll_enable(p);
}

static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni)
{
	struct net_bridge *br = netdev_priv(dev);
	struct net_bridge_port *p;
	int err = 0;

	list_for_each_entry(p, &br->port_list, list) {
		if (!p->dev)
			continue;
		err = __br_netpoll_enable(p);
		if (err)
			goto fail;
	}

out:
	return err;

fail:
	br_netpoll_cleanup(dev);
	goto out;
}

void br_netpoll_disable(struct net_bridge_port *p)
{
	struct netpoll *np = p->np;

	if (!np)
		return;

	p->np = NULL;

	__netpoll_free(np);
}

#endif

static int br_add_slave(struct net_device *dev, struct net_device *slave_dev,
			struct netlink_ext_ack *extack)

{
	struct net_bridge *br = netdev_priv(dev);

	return br_add_if(br, slave_dev, extack);
}

static int br_del_slave(struct net_device *dev, struct net_device *slave_dev)
{
	struct net_bridge *br = netdev_priv(dev);

	return br_del_if(br, slave_dev);
}

static const struct ethtool_ops br_ethtool_ops = {
	.get_drvinfo		 = br_getinfo,
	.get_link		 = ethtool_op_get_link,
	.get_link_ksettings	 = br_get_link_ksettings,
};

static const struct net_device_ops br_netdev_ops = {
	.ndo_open		 = br_dev_open,
	.ndo_stop		 = br_dev_stop,
	.ndo_init		 = br_dev_init,
	.ndo_uninit		 = br_dev_uninit,
	.ndo_start_xmit		 = br_dev_xmit,
	.ndo_get_stats64	 = br_get_stats64,
	.ndo_set_mac_address	 = br_set_mac_address,
	.ndo_set_rx_mode	 = br_dev_set_multicast_list,
	.ndo_change_rx_flags	 = br_dev_change_rx_flags,
	.ndo_change_mtu		 = br_change_mtu,
	.ndo_do_ioctl		 = br_dev_ioctl,
#ifdef CONFIG_NET_POLL_CONTROLLER
	.ndo_netpoll_setup	 = br_netpoll_setup,
	.ndo_netpoll_cleanup	 = br_netpoll_cleanup,
	.ndo_poll_controller	 = br_poll_controller,
#endif
	.ndo_add_slave		 = br_add_slave,
	.ndo_del_slave		 = br_del_slave,
	.ndo_fix_features        = br_fix_features,
	.ndo_fdb_add		 = br_fdb_add,
	.ndo_fdb_del		 = br_fdb_delete,
	.ndo_fdb_dump		 = br_fdb_dump,
	.ndo_fdb_get		 = br_fdb_get,
	.ndo_bridge_getlink	 = br_getlink,
	.ndo_bridge_setlink	 = br_setlink,
	.ndo_bridge_dellink	 = br_dellink,
	.ndo_features_check	 = passthru_features_check,
};

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

void br_dev_setup(struct net_device *dev)
{
	struct net_bridge *br = netdev_priv(dev);

	eth_hw_addr_random(dev);
	ether_setup(dev);

	dev->netdev_ops = &br_netdev_ops;
	dev->needs_free_netdev = true;
	dev->ethtool_ops = &br_ethtool_ops;
	SET_NETDEV_DEVTYPE(dev, &br_type);
	dev->priv_flags = IFF_EBRIDGE | IFF_NO_QUEUE;

	dev->features = COMMON_FEATURES | NETIF_F_LLTX | NETIF_F_NETNS_LOCAL |
			NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
	dev->hw_features = COMMON_FEATURES | NETIF_F_HW_VLAN_CTAG_TX |
			   NETIF_F_HW_VLAN_STAG_TX;
	dev->vlan_features = COMMON_FEATURES;

	br->dev = dev;
	spin_lock_init(&br->lock);
	INIT_LIST_HEAD(&br->port_list);
	INIT_HLIST_HEAD(&br->fdb_list);
#if IS_ENABLED(CONFIG_BRIDGE_MRP)
	INIT_LIST_HEAD(&br->mrp_list);
#endif
	spin_lock_init(&br->hash_lock);

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

	ether_addr_copy(br->group_addr, eth_stp_addr);

	br->stp_enabled = BR_NO_STP;
	br->group_fwd_mask = BR_GROUPFWD_DEFAULT;
	br->group_fwd_mask_required = BR_GROUPFWD_DEFAULT;

	br->designated_root = br->bridge_id;
	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->bridge_ageing_time = br->ageing_time = BR_DEFAULT_AGEING_TIME;
	dev->max_mtu = ETH_MAX_MTU;

	br_netfilter_rtable_init(br);
	br_stp_timer_init(br);
	br_multicast_init(br);
	INIT_DELAYED_WORK(&br->gc_work, br_fdb_cleanup);
}