summaryrefslogtreecommitdiffstats
path: root/net/ipv6/addrlabel.c
blob: 2606d2fa3ac4c8e7d13071d1895cf4e6e36a4116 (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
/*
 * IPv6 Address Label subsystem
 * for the IPv6 "Default" Source Address Selection
 *
 * Copyright (C)2007 USAGI/WIDE Project
 */
/*
 * Author:
 *	YOSHIFUJI Hideaki @ USAGI/WIDE Project <yoshfuji@linux-ipv6.org>
 */

#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/rcupdate.h>
#include <linux/in6.h>
#include <linux/slab.h>
#include <net/addrconf.h>
#include <linux/if_addrlabel.h>
#include <linux/netlink.h>
#include <linux/rtnetlink.h>

#if 0
#define ADDRLABEL(x...) printk(x)
#else
#define ADDRLABEL(x...) do { ; } while (0)
#endif

/*
 * Policy Table
 */
struct ip6addrlbl_entry {
	struct in6_addr prefix;
	int prefixlen;
	int ifindex;
	int addrtype;
	u32 label;
	struct hlist_node list;
	struct rcu_head rcu;
};

/*
 * Default policy table (RFC6724 + extensions)
 *
 * prefix		addr_type	label
 * -------------------------------------------------------------------------
 * ::1/128		LOOPBACK	0
 * ::/0			N/A		1
 * 2002::/16		N/A		2
 * ::/96		COMPATv4	3
 * ::ffff:0:0/96	V4MAPPED	4
 * fc00::/7		N/A		5		ULA (RFC 4193)
 * 2001::/32		N/A		6		Teredo (RFC 4380)
 * 2001:10::/28		N/A		7		ORCHID (RFC 4843)
 * fec0::/10		N/A		11		Site-local
 *							(deprecated by RFC3879)
 * 3ffe::/16		N/A		12		6bone
 *
 * Note: 0xffffffff is used if we do not have any policies.
 * Note: Labels for ULA and 6to4 are different from labels listed in RFC6724.
 */

#define IPV6_ADDR_LABEL_DEFAULT	0xffffffffUL

static const __net_initconst struct ip6addrlbl_init_table
{
	const struct in6_addr *prefix;
	int prefixlen;
	u32 label;
} ip6addrlbl_init_table[] = {
	{	/* ::/0 */
		.prefix = &in6addr_any,
		.label = 1,
	}, {	/* fc00::/7 */
		.prefix = &(struct in6_addr){ { { 0xfc } } } ,
		.prefixlen = 7,
		.label = 5,
	}, {	/* fec0::/10 */
		.prefix = &(struct in6_addr){ { { 0xfe, 0xc0 } } },
		.prefixlen = 10,
		.label = 11,
	}, {	/* 2002::/16 */
		.prefix = &(struct in6_addr){ { { 0x20, 0x02 } } },
		.prefixlen = 16,
		.label = 2,
	}, {	/* 3ffe::/16 */
		.prefix = &(struct in6_addr){ { { 0x3f, 0xfe } } },
		.prefixlen = 16,
		.label = 12,
	}, {	/* 2001::/32 */
		.prefix = &(struct in6_addr){ { { 0x20, 0x01 } } },
		.prefixlen = 32,
		.label = 6,
	}, {	/* 2001:10::/28 */
		.prefix = &(struct in6_addr){ { { 0x20, 0x01, 0x00, 0x10 } } },
		.prefixlen = 28,
		.label = 7,
	}, {	/* ::ffff:0:0 */
		.prefix = &(struct in6_addr){ { { [10] = 0xff, [11] = 0xff } } },
		.prefixlen = 96,
		.label = 4,
	}, {	/* ::/96 */
		.prefix = &in6addr_any,
		.prefixlen = 96,
		.label = 3,
	}, {	/* ::1/128 */
		.prefix = &in6addr_loopback,
		.prefixlen = 128,
		.label = 0,
	}
};

/* Find label */
static bool __ip6addrlbl_match(const struct ip6addrlbl_entry *p,
			       const struct in6_addr *addr,
			       int addrtype, int ifindex)
{
	if (p->ifindex && p->ifindex != ifindex)
		return false;
	if (p->addrtype && p->addrtype != addrtype)
		return false;
	if (!ipv6_prefix_equal(addr, &p->prefix, p->prefixlen))
		return false;
	return true;
}

static struct ip6addrlbl_entry *__ipv6_addr_label(struct net *net,
						  const struct in6_addr *addr,
						  int type, int ifindex)
{
	struct ip6addrlbl_entry *p;

	hlist_for_each_entry_rcu(p, &net->ipv6.ip6addrlbl_table.head, list) {
		if (__ip6addrlbl_match(p, addr, type, ifindex))
			return p;
	}
	return NULL;
}

u32 ipv6_addr_label(struct net *net,
		    const struct in6_addr *addr, int type, int ifindex)
{
	u32 label;
	struct ip6addrlbl_entry *p;

	type &= IPV6_ADDR_MAPPED | IPV6_ADDR_COMPATv4 | IPV6_ADDR_LOOPBACK;

	rcu_read_lock();
	p = __ipv6_addr_label(net, addr, type, ifindex);
	label = p ? p->label : IPV6_ADDR_LABEL_DEFAULT;
	rcu_read_unlock();

	ADDRLABEL(KERN_DEBUG "%s(addr=%pI6, type=%d, ifindex=%d) => %08x\n",
		  __func__, addr, type, ifindex, label);

	return label;
}

/* allocate one entry */
static struct ip6addrlbl_entry *ip6addrlbl_alloc(const struct in6_addr *prefix,
						 int prefixlen, int ifindex,
						 u32 label)
{
	struct ip6addrlbl_entry *newp;
	int addrtype;

	ADDRLABEL(KERN_DEBUG "%s(prefix=%pI6, prefixlen=%d, ifindex=%d, label=%u)\n",
		  __func__, prefix, prefixlen, ifindex, (unsigned int)label);

	addrtype = ipv6_addr_type(prefix) & (IPV6_ADDR_MAPPED | IPV6_ADDR_COMPATv4 | IPV6_ADDR_LOOPBACK);

	switch (addrtype) {
	case IPV6_ADDR_MAPPED:
		if (prefixlen > 96)
			return ERR_PTR(-EINVAL);
		if (prefixlen < 96)
			addrtype = 0;
		break;
	case IPV6_ADDR_COMPATv4:
		if (prefixlen != 96)
			addrtype = 0;
		break;
	case IPV6_ADDR_LOOPBACK:
		if (prefixlen != 128)
			addrtype = 0;
		break;
	}

	newp = kmalloc(sizeof(*newp), GFP_KERNEL);
	if (!newp)
		return ERR_PTR(-ENOMEM);

	ipv6_addr_prefix(&newp->prefix, prefix, prefixlen);
	newp->prefixlen = prefixlen;
	newp->ifindex = ifindex;
	newp->addrtype = addrtype;
	newp->label = label;
	INIT_HLIST_NODE(&newp->list);
	return newp;
}

/* add a label */
static int __ip6addrlbl_add(struct net *net, struct ip6addrlbl_entry *newp,
			    int replace)
{
	struct ip6addrlbl_entry *last = NULL, *p = NULL;
	struct hlist_node *n;
	int ret = 0;

	ADDRLABEL(KERN_DEBUG "%s(newp=%p, replace=%d)\n", __func__, newp,
		  replace);

	hlist_for_each_entry_safe(p, n,	&net->ipv6.ip6addrlbl_table.head, list) {
		if (p->prefixlen == newp->prefixlen &&
		    p->ifindex == newp->ifindex &&
		    ipv6_addr_equal(&p->prefix, &newp->prefix)) {
			if (!replace) {
				ret = -EEXIST;
				goto out;
			}
			hlist_replace_rcu(&p->list, &newp->list);
			kfree_rcu(p, rcu);
			goto out;
		} else if ((p->prefixlen == newp->prefixlen && !p->ifindex) ||
			   (p->prefixlen < newp->prefixlen)) {
			hlist_add_before_rcu(&newp->list, &p->list);
			goto out;
		}
		last = p;
	}
	if (last)
		hlist_add_behind_rcu(&newp->list, &last->list);
	else
		hlist_add_head_rcu(&newp->list, &net->ipv6.ip6addrlbl_table.head);
out:
	if (!ret)
		net->ipv6.ip6addrlbl_table.seq++;
	return ret;
}

/* add a label */
static int ip6addrlbl_add(struct net *net,
			  const struct in6_addr *prefix, int prefixlen,
			  int ifindex, u32 label, int replace)
{
	struct ip6addrlbl_entry *newp;
	int ret = 0;

	ADDRLABEL(KERN_DEBUG "%s(prefix=%pI6, prefixlen=%d, ifindex=%d, label=%u, replace=%d)\n",
		  __func__, prefix, prefixlen, ifindex, (unsigned int)label,
		  replace);

	newp = ip6addrlbl_alloc(prefix, prefixlen, ifindex, label);
	if (IS_ERR(newp))
		return PTR_ERR(newp);
	spin_lock(&net->ipv6.ip6addrlbl_table.lock);
	ret = __ip6addrlbl_add(net, newp, replace);
	spin_unlock(&net->ipv6.ip6addrlbl_table.lock);
	if (ret)
		kfree(newp);
	return ret;
}

/* remove a label */
static int __ip6addrlbl_del(struct net *net,
			    const struct in6_addr *prefix, int prefixlen,
			    int ifindex)
{
	struct ip6addrlbl_entry *p = NULL;
	struct hlist_node *n;
	int ret = -ESRCH;

	ADDRLABEL(KERN_DEBUG "%s(prefix=%pI6, prefixlen=%d, ifindex=%d)\n",
		  __func__, prefix, prefixlen, ifindex);

	hlist_for_each_entry_safe(p, n, &net->ipv6.ip6addrlbl_table.head, list) {
		if (p->prefixlen == prefixlen &&
		    p->ifindex == ifindex &&
		    ipv6_addr_equal(&p->prefix, prefix)) {
			hlist_del_rcu(&p->list);
			kfree_rcu(p, rcu);
			ret = 0;
			break;
		}
	}
	return ret;
}

static int ip6addrlbl_del(struct net *net,
			  const struct in6_addr *prefix, int prefixlen,
			  int ifindex)
{
	struct in6_addr prefix_buf;
	int ret;

	ADDRLABEL(KERN_DEBUG "%s(prefix=%pI6, prefixlen=%d, ifindex=%d)\n",
		  __func__, prefix, prefixlen, ifindex);

	ipv6_addr_prefix(&prefix_buf, prefix, prefixlen);
	spin_lock(&net->ipv6.ip6addrlbl_table.lock);
	ret = __ip6addrlbl_del(net, &prefix_buf, prefixlen, ifindex);
	spin_unlock(&net->ipv6.ip6addrlbl_table.lock);
	return ret;
}

/* add default label */
static int __net_init ip6addrlbl_net_init(struct net *net)
{
	int err = 0;
	int i;

	ADDRLABEL(KERN_DEBUG "%s\n", __func__);

	spin_lock_init(&net->ipv6.ip6addrlbl_table.lock);
	INIT_HLIST_HEAD(&net->ipv6.ip6addrlbl_table.head);

	for (i = 0; i < ARRAY_SIZE(ip6addrlbl_init_table); i++) {
		int ret = ip6addrlbl_add(net,
					 ip6addrlbl_init_table[i].prefix,
					 ip6addrlbl_init_table[i].prefixlen,
					 0,
					 ip6addrlbl_init_table[i].label, 0);
		/* XXX: should we free all rules when we catch an error? */
		if (ret && (!err || err != -ENOMEM))
			err = ret;
	}
	return err;
}

static void __net_exit ip6addrlbl_net_exit(struct net *net)
{
	struct ip6addrlbl_entry *p = NULL;
	struct hlist_node *n;

	/* Remove all labels belonging to the exiting net */
	spin_lock(&net->ipv6.ip6addrlbl_table.lock);
	hlist_for_each_entry_safe(p, n, &net->ipv6.ip6addrlbl_table.head, list) {
		hlist_del_rcu(&p->list);
		kfree_rcu(p, rcu);
	}
	spin_unlock(&net->ipv6.ip6addrlbl_table.lock);
}

static struct pernet_operations ipv6_addr_label_ops = {
	.init = ip6addrlbl_net_init,
	.exit = ip6addrlbl_net_exit,
};

int __init ipv6_addr_label_init(void)
{
	return register_pernet_subsys(&ipv6_addr_label_ops);
}

void ipv6_addr_label_cleanup(void)
{
	unregister_pernet_subsys(&ipv6_addr_label_ops);
}

static const struct nla_policy ifal_policy[IFAL_MAX+1] = {
	[IFAL_ADDRESS]		= { .len = sizeof(struct in6_addr), },
	[IFAL_LABEL]		= { .len = sizeof(u32), },
};

static bool addrlbl_ifindex_exists(struct net *net, int ifindex)
{

	struct net_device *dev;

	rcu_read_lock();
	dev = dev_get_by_index_rcu(net, ifindex);
	rcu_read_unlock();

	return dev != NULL;
}

static int ip6addrlbl_newdel(struct sk_buff *skb, struct nlmsghdr *nlh,
			     struct netlink_ext_ack *extack)
{
	struct net *net = sock_net(skb->sk);
	struct ifaddrlblmsg *ifal;
	struct nlattr *tb[IFAL_MAX+1];
	struct in6_addr *pfx;
	u32 label;
	int err = 0;

	err = nlmsg_parse(nlh, sizeof(*ifal), tb, IFAL_MAX, ifal_policy,
			  extack);
	if (err < 0)
		return err;

	ifal = nlmsg_data(nlh);

	if (ifal->ifal_family != AF_INET6 ||
	    ifal->ifal_prefixlen > 128)
		return -EINVAL;

	if (!tb[IFAL_ADDRESS])
		return -EINVAL;
	pfx = nla_data(tb[IFAL_ADDRESS]);

	if (!tb[IFAL_LABEL])
		return -EINVAL;
	label = nla_get_u32(tb[IFAL_LABEL]);
	if (label == IPV6_ADDR_LABEL_DEFAULT)
		return -EINVAL;

	switch (nlh->nlmsg_type) {
	case RTM_NEWADDRLABEL:
		if (ifal->ifal_index &&
		    !addrlbl_ifindex_exists(net, ifal->ifal_index))
			return -EINVAL;

		err = ip6addrlbl_add(net, pfx, ifal->ifal_prefixlen,
				     ifal->ifal_index, label,
				     nlh->nlmsg_flags & NLM_F_REPLACE);
		break;
	case RTM_DELADDRLABEL:
		err = ip6addrlbl_del(net, pfx, ifal->ifal_prefixlen,
				     ifal->ifal_index);
		break;
	default:
		err = -EOPNOTSUPP;
	}
	return err;
}

static void ip6addrlbl_putmsg(struct nlmsghdr *nlh,
			      int prefixlen, int ifindex, u32 lseq)
{
	struct ifaddrlblmsg *ifal = nlmsg_data(nlh);
	ifal->ifal_family = AF_INET6;
	ifal->ifal_prefixlen = prefixlen;
	ifal->ifal_flags = 0;
	ifal->ifal_index = ifindex;
	ifal->ifal_seq = lseq;
};

static int ip6addrlbl_fill(struct sk_buff *skb,
			   struct ip6addrlbl_entry *p,
			   u32 lseq,
			   u32 portid, u32 seq, int event,
			   unsigned int flags)
{
	struct nlmsghdr *nlh = nlmsg_put(skb, portid, seq, event,
					 sizeof(struct ifaddrlblmsg), flags);
	if (!nlh)
		return -EMSGSIZE;

	ip6addrlbl_putmsg(nlh, p->prefixlen, p->ifindex, lseq);

	if (nla_put_in6_addr(skb, IFAL_ADDRESS, &p->prefix) < 0 ||
	    nla_put_u32(skb, IFAL_LABEL, p->label) < 0) {
		nlmsg_cancel(skb, nlh);
		return -EMSGSIZE;
	}

	nlmsg_end(skb, nlh);
	return 0;
}

static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
	struct net *net = sock_net(skb->sk);
	struct ip6addrlbl_entry *p;
	int idx = 0, s_idx = cb->args[0];
	int err;

	rcu_read_lock();
	hlist_for_each_entry_rcu(p, &net->ipv6.ip6addrlbl_table.head, list) {
		if (idx >= s_idx) {
			err = ip6addrlbl_fill(skb, p,
					      net->ipv6.ip6addrlbl_table.seq,
					      NETLINK_CB(cb->skb).portid,
					      cb->nlh->nlmsg_seq,
					      RTM_NEWADDRLABEL,
					      NLM_F_MULTI);
			if (err < 0)
				break;
		}
		idx++;
	}
	rcu_read_unlock();
	cb->args[0] = idx;
	return skb->len;
}

static inline int ip6addrlbl_msgsize(void)
{
	return NLMSG_ALIGN(sizeof(struct ifaddrlblmsg))
		+ nla_total_size(16)	/* IFAL_ADDRESS */
		+ nla_total_size(4);	/* IFAL_LABEL */
}

static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh,
			  struct netlink_ext_ack *extack)
{
	struct net *net = sock_net(in_skb->sk);
	struct ifaddrlblmsg *ifal;
	struct nlattr *tb[IFAL_MAX+1];
	struct in6_addr *addr;
	u32 lseq;
	int err = 0;
	struct ip6addrlbl_entry *p;
	struct sk_buff *skb;

	err = nlmsg_parse(nlh, sizeof(*ifal), tb, IFAL_MAX, ifal_policy,
			  extack);
	if (err < 0)
		return err;

	ifal = nlmsg_data(nlh);

	if (ifal->ifal_family != AF_INET6 ||
	    ifal->ifal_prefixlen != 128)
		return -EINVAL;

	if (ifal->ifal_index &&
	    !addrlbl_ifindex_exists(net, ifal->ifal_index))
		return -EINVAL;

	if (!tb[IFAL_ADDRESS])
		return -EINVAL;
	addr = nla_data(tb[IFAL_ADDRESS]);

	skb = nlmsg_new(ip6addrlbl_msgsize(), GFP_KERNEL);
	if (!skb)
		return -ENOBUFS;

	err = -ESRCH;

	rcu_read_lock();
	p = __ipv6_addr_label(net, addr, ipv6_addr_type(addr), ifal->ifal_index);
	lseq = net->ipv6.ip6addrlbl_table.seq;
	if (p)
		err = ip6addrlbl_fill(skb, p, lseq,
				      NETLINK_CB(in_skb).portid,
				      nlh->nlmsg_seq,
				      RTM_NEWADDRLABEL, 0);
	rcu_read_unlock();

	if (err < 0) {
		WARN_ON(err == -EMSGSIZE);
		kfree_skb(skb);
	} else {
		err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid);
	}
	return err;
}

void __init ipv6_addr_label_rtnl_register(void)
{
	__rtnl_register(PF_INET6, RTM_NEWADDRLABEL, ip6addrlbl_newdel,
			NULL, RTNL_FLAG_DOIT_UNLOCKED);
	__rtnl_register(PF_INET6, RTM_DELADDRLABEL, ip6addrlbl_newdel,
			NULL, RTNL_FLAG_DOIT_UNLOCKED);
	__rtnl_register(PF_INET6, RTM_GETADDRLABEL, ip6addrlbl_get,
			ip6addrlbl_dump, RTNL_FLAG_DOIT_UNLOCKED);
}