summaryrefslogtreecommitdiffstats
path: root/net/bridge/br_mdb.c
blob: 6f0a2eebcb27fe3b04fc077dbab320985998b008 (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
#include <linux/err.h>
#include <linux/igmp.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/rculist.h>
#include <linux/skbuff.h>
#include <linux/if_ether.h>
#include <net/ip.h>
#include <net/netlink.h>
#if IS_ENABLED(CONFIG_IPV6)
#include <net/ipv6.h>
#endif

#include "br_private.h"

static int br_rports_fill_info(struct sk_buff *skb, struct netlink_callback *cb,
			       struct net_device *dev)
{
	struct net_bridge *br = netdev_priv(dev);
	struct net_bridge_port *p;
	struct hlist_node *n;
	struct nlattr *nest;

	if (!br->multicast_router || hlist_empty(&br->router_list))
		return 0;

	nest = nla_nest_start(skb, MDBA_ROUTER);
	if (nest == NULL)
		return -EMSGSIZE;

	hlist_for_each_entry_rcu(p, n, &br->router_list, rlist) {
		if (p && nla_put_u32(skb, MDBA_ROUTER_PORT, p->dev->ifindex))
			goto fail;
	}

	nla_nest_end(skb, nest);
	return 0;
fail:
	nla_nest_cancel(skb, nest);
	return -EMSGSIZE;
}

static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb,
			    struct net_device *dev)
{
	struct net_bridge *br = netdev_priv(dev);
	struct net_bridge_mdb_htable *mdb;
	struct nlattr *nest, *nest2;
	int i, err = 0;
	int idx = 0, s_idx = cb->args[1];

	if (br->multicast_disabled)
		return 0;

	mdb = rcu_dereference(br->mdb);
	if (!mdb)
		return 0;

	nest = nla_nest_start(skb, MDBA_MDB);
	if (nest == NULL)
		return -EMSGSIZE;

	for (i = 0; i < mdb->max; i++) {
		struct hlist_node *h;
		struct net_bridge_mdb_entry *mp;
		struct net_bridge_port_group *p, **pp;
		struct net_bridge_port *port;

		hlist_for_each_entry_rcu(mp, h, &mdb->mhash[i], hlist[mdb->ver]) {
			if (idx < s_idx)
				goto skip;

			nest2 = nla_nest_start(skb, MDBA_MDB_ENTRY);
			if (nest2 == NULL) {
				err = -EMSGSIZE;
				goto out;
			}

			for (pp = &mp->ports;
			     (p = rcu_dereference(*pp)) != NULL;
			      pp = &p->next) {
				port = p->port;
				if (port) {
					struct br_mdb_entry e;
					e.ifindex = port->dev->ifindex;
					e.addr.u.ip4 = p->addr.u.ip4;
#if IS_ENABLED(CONFIG_IPV6)
					e.addr.u.ip6 = p->addr.u.ip6;
#endif
					e.addr.proto = p->addr.proto;
					if (nla_put(skb, MDBA_MDB_ENTRY_INFO, sizeof(e), &e)) {
						nla_nest_cancel(skb, nest2);
						err = -EMSGSIZE;
						goto out;
					}
				}
			}
			nla_nest_end(skb, nest2);
		skip:
			idx++;
		}
	}

out:
	cb->args[1] = idx;
	nla_nest_end(skb, nest);
	return err;
}

static int br_mdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
	struct net_device *dev;
	struct net *net = sock_net(skb->sk);
	struct nlmsghdr *nlh = NULL;
	int idx = 0, s_idx;

	s_idx = cb->args[0];

	rcu_read_lock();

	/* In theory this could be wrapped to 0... */
	cb->seq = net->dev_base_seq + br_mdb_rehash_seq;

	for_each_netdev_rcu(net, dev) {
		if (dev->priv_flags & IFF_EBRIDGE) {
			struct br_port_msg *bpm;

			if (idx < s_idx)
				goto skip;

			nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid,
					cb->nlh->nlmsg_seq, RTM_GETMDB,
					sizeof(*bpm), NLM_F_MULTI);
			if (nlh == NULL)
				break;

			bpm = nlmsg_data(nlh);
			bpm->ifindex = dev->ifindex;
			if (br_mdb_fill_info(skb, cb, dev) < 0)
				goto out;
			if (br_rports_fill_info(skb, cb, dev) < 0)
				goto out;

			cb->args[1] = 0;
			nlmsg_end(skb, nlh);
		skip:
			idx++;
		}
	}

out:
	if (nlh)
		nlmsg_end(skb, nlh);
	rcu_read_unlock();
	cb->args[0] = idx;
	return skb->len;
}

static int nlmsg_populate_mdb_fill(struct sk_buff *skb,
				   struct net_device *dev,
				   struct br_mdb_entry *entry, u32 pid,
				   u32 seq, int type, unsigned int flags)
{
	struct nlmsghdr *nlh;
	struct br_port_msg *bpm;
	struct nlattr *nest, *nest2;

	nlh = nlmsg_put(skb, pid, seq, type, sizeof(*bpm), NLM_F_MULTI);
	if (!nlh)
		return -EMSGSIZE;

	bpm = nlmsg_data(nlh);
	bpm->family  = AF_BRIDGE;
	bpm->ifindex = dev->ifindex;
	nest = nla_nest_start(skb, MDBA_MDB);
	if (nest == NULL)
		goto cancel;
	nest2 = nla_nest_start(skb, MDBA_MDB_ENTRY);
	if (nest2 == NULL)
		goto end;

	if (nla_put(skb, MDBA_MDB_ENTRY_INFO, sizeof(*entry), entry))
		goto end;

	nla_nest_end(skb, nest2);
	nla_nest_end(skb, nest);
	return nlmsg_end(skb, nlh);

end:
	nla_nest_end(skb, nest);
cancel:
	nlmsg_cancel(skb, nlh);
	return -EMSGSIZE;
}

static inline size_t rtnl_mdb_nlmsg_size(void)
{
	return NLMSG_ALIGN(sizeof(struct br_port_msg))
		+ nla_total_size(sizeof(struct br_mdb_entry));
}

static void __br_mdb_notify(struct net_device *dev, struct br_mdb_entry *entry,
			    int type)
{
	struct net *net = dev_net(dev);
	struct sk_buff *skb;
	int err = -ENOBUFS;

	skb = nlmsg_new(rtnl_mdb_nlmsg_size(), GFP_ATOMIC);
	if (!skb)
		goto errout;

	err = nlmsg_populate_mdb_fill(skb, dev, entry, 0, 0, type, NTF_SELF);
	if (err < 0) {
		kfree_skb(skb);
		goto errout;
	}

	rtnl_notify(skb, net, 0, RTNLGRP_MDB, NULL, GFP_ATOMIC);
	return;
errout:
	rtnl_set_sk_err(net, RTNLGRP_MDB, err);
}

void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port,
		   struct br_ip *group, int type)
{
	struct br_mdb_entry entry;

	entry.ifindex = port->dev->ifindex;
	entry.addr.proto = group->proto;
	entry.addr.u.ip4 = group->u.ip4;
#if IS_ENABLED(CONFIG_IPV6)
	entry.addr.u.ip6 = group->u.ip6;
#endif
	__br_mdb_notify(dev, &entry, type);
}

static bool is_valid_mdb_entry(struct br_mdb_entry *entry)
{
	if (entry->ifindex == 0)
		return false;

	if (entry->addr.proto == htons(ETH_P_IP)) {
		if (!ipv4_is_multicast(entry->addr.u.ip4))
			return false;
		if (ipv4_is_local_multicast(entry->addr.u.ip4))
			return false;
#if IS_ENABLED(CONFIG_IPV6)
	} else if (entry->addr.proto == htons(ETH_P_IPV6)) {
		if (!ipv6_is_transient_multicast(&entry->addr.u.ip6))
			return false;
#endif
	} else
		return false;

	return true;
}

static int br_mdb_parse(struct sk_buff *skb, struct nlmsghdr *nlh,
			struct net_device **pdev, struct br_mdb_entry **pentry)
{
	struct net *net = sock_net(skb->sk);
	struct br_mdb_entry *entry;
	struct br_port_msg *bpm;
	struct nlattr *tb[MDBA_SET_ENTRY_MAX+1];
	struct net_device *dev;
	int err;

	if (!capable(CAP_NET_ADMIN))
		return -EPERM;

	err = nlmsg_parse(nlh, sizeof(*bpm), tb, MDBA_SET_ENTRY, NULL);
	if (err < 0)
		return err;

	bpm = nlmsg_data(nlh);
	if (bpm->ifindex == 0) {
		pr_info("PF_BRIDGE: br_mdb_parse() with invalid ifindex\n");
		return -EINVAL;
	}

	dev = __dev_get_by_index(net, bpm->ifindex);
	if (dev == NULL) {
		pr_info("PF_BRIDGE: br_mdb_parse() with unknown ifindex\n");
		return -ENODEV;
	}

	if (!(dev->priv_flags & IFF_EBRIDGE)) {
		pr_info("PF_BRIDGE: br_mdb_parse() with non-bridge\n");
		return -EOPNOTSUPP;
	}

	*pdev = dev;

	if (!tb[MDBA_SET_ENTRY] ||
	    nla_len(tb[MDBA_SET_ENTRY]) != sizeof(struct br_mdb_entry)) {
		pr_info("PF_BRIDGE: br_mdb_parse() with invalid attr\n");
		return -EINVAL;
	}

	entry = nla_data(tb[MDBA_SET_ENTRY]);
	if (!is_valid_mdb_entry(entry)) {
		pr_info("PF_BRIDGE: br_mdb_parse() with invalid entry\n");
		return -EINVAL;
	}

	*pentry = entry;
	return 0;
}

static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
			    struct br_ip *group)
{
	struct net_bridge_mdb_entry *mp;
	struct net_bridge_port_group *p;
	struct net_bridge_port_group __rcu **pp;
	struct net_bridge_mdb_htable *mdb;
	int err;

	mdb = mlock_dereference(br->mdb, br);
	mp = br_mdb_ip_get(mdb, group);
	if (!mp) {
		mp = br_multicast_new_group(br, port, group);
		err = PTR_ERR(mp);
		if (IS_ERR(mp))
			return err;
	}

	for (pp = &mp->ports;
	     (p = mlock_dereference(*pp, br)) != NULL;
	     pp = &p->next) {
		if (p->port == port)
			return -EEXIST;
		if ((unsigned long)p->port < (unsigned long)port)
			break;
	}

	p = br_multicast_new_port_group(port, group, *pp);
	if (unlikely(!p))
		return -ENOMEM;
	rcu_assign_pointer(*pp, p);

	br_mdb_notify(br->dev, port, group, RTM_NEWMDB);
	return 0;
}

static int __br_mdb_add(struct net *net, struct net_bridge *br,
			struct br_mdb_entry *entry)
{
	struct br_ip ip;
	struct net_device *dev;
	struct net_bridge_port *p;
	int ret;

	if (!netif_running(br->dev) || br->multicast_disabled)
		return -EINVAL;

	dev = __dev_get_by_index(net, entry->ifindex);
	if (!dev)
		return -ENODEV;

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

	ip.proto = entry->addr.proto;
	if (ip.proto == htons(ETH_P_IP))
		ip.u.ip4 = entry->addr.u.ip4;
#if IS_ENABLED(CONFIG_IPV6)
	else
		ip.u.ip6 = entry->addr.u.ip6;
#endif

	spin_lock_bh(&br->multicast_lock);
	ret = br_mdb_add_group(br, p, &ip);
	spin_unlock_bh(&br->multicast_lock);
	return ret;
}

static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
	struct net *net = sock_net(skb->sk);
	struct br_mdb_entry *entry;
	struct net_device *dev;
	struct net_bridge *br;
	int err;

	err = br_mdb_parse(skb, nlh, &dev, &entry);
	if (err < 0)
		return err;

	br = netdev_priv(dev);

	err = __br_mdb_add(net, br, entry);
	if (!err)
		__br_mdb_notify(dev, entry, RTM_NEWMDB);
	return err;
}

static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry)
{
	struct net_bridge_mdb_htable *mdb;
	struct net_bridge_mdb_entry *mp;
	struct net_bridge_port_group *p;
	struct net_bridge_port_group __rcu **pp;
	struct br_ip ip;
	int err = -EINVAL;

	if (!netif_running(br->dev) || br->multicast_disabled)
		return -EINVAL;

	if (timer_pending(&br->multicast_querier_timer))
		return -EBUSY;

	ip.proto = entry->addr.proto;
	if (ip.proto == htons(ETH_P_IP))
		ip.u.ip4 = entry->addr.u.ip4;
#if IS_ENABLED(CONFIG_IPV6)
	else
		ip.u.ip6 = entry->addr.u.ip6;
#endif

	spin_lock_bh(&br->multicast_lock);
	mdb = mlock_dereference(br->mdb, br);

	mp = br_mdb_ip_get(mdb, &ip);
	if (!mp)
		goto unlock;

	for (pp = &mp->ports;
	     (p = mlock_dereference(*pp, br)) != NULL;
	     pp = &p->next) {
		if (!p->port || p->port->dev->ifindex != entry->ifindex)
			continue;

		if (p->port->state == BR_STATE_DISABLED)
			goto unlock;

		rcu_assign_pointer(*pp, p->next);
		hlist_del_init(&p->mglist);
		del_timer(&p->timer);
		call_rcu_bh(&p->rcu, br_multicast_free_pg);
		err = 0;

		if (!mp->ports && !mp->mglist &&
		    netif_running(br->dev))
			mod_timer(&mp->timer, jiffies);
		break;
	}

unlock:
	spin_unlock_bh(&br->multicast_lock);
	return err;
}

static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
	struct net_device *dev;
	struct br_mdb_entry *entry;
	struct net_bridge *br;
	int err;

	err = br_mdb_parse(skb, nlh, &dev, &entry);
	if (err < 0)
		return err;

	br = netdev_priv(dev);

	err = __br_mdb_del(br, entry);
	if (!err)
		__br_mdb_notify(dev, entry, RTM_DELMDB);
	return err;
}

void br_mdb_init(void)
{
	rtnl_register(PF_BRIDGE, RTM_GETMDB, NULL, br_mdb_dump, NULL);
	rtnl_register(PF_BRIDGE, RTM_NEWMDB, br_mdb_add, NULL, NULL);
	rtnl_register(PF_BRIDGE, RTM_DELMDB, br_mdb_del, NULL, NULL);
}