aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
blob: 5863579800c1c347687d3a0cccb4baf15836b26d (plain) (blame)
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
/*
 * Copyright (C)2004 USAGI/WIDE Project
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 *
 * Author:
 *	Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp>
 */

#include <linux/types.h>
#include <linux/ipv6.h>
#include <linux/in6.h>
#include <linux/netfilter.h>
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/icmp.h>
#include <net/ipv6.h>
#include <net/inet_frag.h>

#include <linux/netfilter_bridge.h>
#include <linux/netfilter_ipv6.h>
#include <linux/netfilter_ipv6/ip6_tables.h>
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_helper.h>
#include <net/netfilter/nf_conntrack_l4proto.h>
#include <net/netfilter/nf_conntrack_l3proto.h>
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_conntrack_zones.h>
#include <net/netfilter/nf_conntrack_seqadj.h>
#include <net/netfilter/ipv6/nf_conntrack_ipv6.h>
#include <net/netfilter/nf_nat_helper.h>
#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
#include <net/netfilter/nf_log.h>

static int conntrack6_net_id;
static DEFINE_MUTEX(register_ipv6_hooks);

struct conntrack6_net {
	unsigned int users;
};

static bool ipv6_pkt_to_tuple(const struct sk_buff *skb, unsigned int nhoff,
			      struct nf_conntrack_tuple *tuple)
{
	const u_int32_t *ap;
	u_int32_t _addrs[8];

	ap = skb_header_pointer(skb, nhoff + offsetof(struct ipv6hdr, saddr),
				sizeof(_addrs), _addrs);
	if (ap == NULL)
		return false;

	memcpy(tuple->src.u3.ip6, ap, sizeof(tuple->src.u3.ip6));
	memcpy(tuple->dst.u3.ip6, ap + 4, sizeof(tuple->dst.u3.ip6));

	return true;
}

static bool ipv6_invert_tuple(struct nf_conntrack_tuple *tuple,
			      const struct nf_conntrack_tuple *orig)
{
	memcpy(tuple->src.u3.ip6, orig->dst.u3.ip6, sizeof(tuple->src.u3.ip6));
	memcpy(tuple->dst.u3.ip6, orig->src.u3.ip6, sizeof(tuple->dst.u3.ip6));

	return true;
}

static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
			    unsigned int *dataoff, u_int8_t *protonum)
{
	unsigned int extoff = nhoff + sizeof(struct ipv6hdr);
	__be16 frag_off;
	int protoff;
	u8 nexthdr;

	if (skb_copy_bits(skb, nhoff + offsetof(struct ipv6hdr, nexthdr),
			  &nexthdr, sizeof(nexthdr)) != 0) {
		pr_debug("ip6_conntrack_core: can't get nexthdr\n");
		return -NF_ACCEPT;
	}
	protoff = ipv6_skip_exthdr(skb, extoff, &nexthdr, &frag_off);
	/*
	 * (protoff == skb->len) means the packet has not data, just
	 * IPv6 and possibly extensions headers, but it is tracked anyway
	 */
	if (protoff < 0 || (frag_off & htons(~0x7)) != 0) {
		pr_debug("ip6_conntrack_core: can't find proto in pkt\n");
		return -NF_ACCEPT;
	}

	*dataoff = protoff;
	*protonum = nexthdr;
	return NF_ACCEPT;
}

static unsigned int ipv6_helper(void *priv,
				struct sk_buff *skb,
				const struct nf_hook_state *state)
{
	struct nf_conn *ct;
	const struct nf_conn_help *help;
	const struct nf_conntrack_helper *helper;
	enum ip_conntrack_info ctinfo;
	__be16 frag_off;
	int protoff;
	u8 nexthdr;

	/* This is where we call the helper: as the packet goes out. */
	ct = nf_ct_get(skb, &ctinfo);
	if (!ct || ctinfo == IP_CT_RELATED_REPLY)
		return NF_ACCEPT;

	help = nfct_help(ct);
	if (!help)
		return NF_ACCEPT;
	/* rcu_read_lock()ed by nf_hook_thresh */
	helper = rcu_dereference(help->helper);
	if (!helper)
		return NF_ACCEPT;

	nexthdr = ipv6_hdr(skb)->nexthdr;
	protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr,
				   &frag_off);
	if (protoff < 0 || (frag_off & htons(~0x7)) != 0) {
		pr_debug("proto header not found\n");
		return NF_ACCEPT;
	}

	return helper->help(skb, protoff, ct, ctinfo);
}

static unsigned int ipv6_confirm(void *priv,
				 struct sk_buff *skb,
				 const struct nf_hook_state *state)
{
	struct nf_conn *ct;
	enum ip_conntrack_info ctinfo;
	unsigned char pnum = ipv6_hdr(skb)->nexthdr;
	int protoff;
	__be16 frag_off;

	ct = nf_ct_get(skb, &ctinfo);
	if (!ct || ctinfo == IP_CT_RELATED_REPLY)
		goto out;

	protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum,
				   &frag_off);
	if (protoff < 0 || (frag_off & htons(~0x7)) != 0) {
		pr_debug("proto header not found\n");
		goto out;
	}

	/* adjust seqs for loopback traffic only in outgoing direction */
	if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) &&
	    !nf_is_loopback_packet(skb)) {
		if (!nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) {
			NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop);
			return NF_DROP;
		}
	}
out:
	/* We've seen it coming out the other side: confirm it */
	return nf_conntrack_confirm(skb);
}

static unsigned int ipv6_conntrack_in(void *priv,
				      struct sk_buff *skb,
				      const struct nf_hook_state *state)
{
	return nf_conntrack_in(state->net, PF_INET6, state->hook, skb);
}

static unsigned int ipv6_conntrack_local(void *priv,
					 struct sk_buff *skb,
					 const struct nf_hook_state *state)
{
	/* root is playing with raw sockets. */
	if (skb->len < sizeof(struct ipv6hdr)) {
		net_notice_ratelimited("ipv6_conntrack_local: packet too short\n");
		return NF_ACCEPT;
	}
	return nf_conntrack_in(state->net, PF_INET6, state->hook, skb);
}

static const struct nf_hook_ops ipv6_conntrack_ops[] = {
	{
		.hook		= ipv6_conntrack_in,
		.pf		= NFPROTO_IPV6,
		.hooknum	= NF_INET_PRE_ROUTING,
		.priority	= NF_IP6_PRI_CONNTRACK,
	},
	{
		.hook		= ipv6_conntrack_local,
		.pf		= NFPROTO_IPV6,
		.hooknum	= NF_INET_LOCAL_OUT,
		.priority	= NF_IP6_PRI_CONNTRACK,
	},
	{
		.hook		= ipv6_helper,
		.pf		= NFPROTO_IPV6,
		.hooknum	= NF_INET_POST_ROUTING,
		.priority	= NF_IP6_PRI_CONNTRACK_HELPER,
	},
	{
		.hook		= ipv6_confirm,
		.pf		= NFPROTO_IPV6,
		.hooknum	= NF_INET_POST_ROUTING,
		.priority	= NF_IP6_PRI_LAST,
	},
	{
		.hook		= ipv6_helper,
		.pf		= NFPROTO_IPV6,
		.hooknum	= NF_INET_LOCAL_IN,
		.priority	= NF_IP6_PRI_CONNTRACK_HELPER,
	},
	{
		.hook		= ipv6_confirm,
		.pf		= NFPROTO_IPV6,
		.hooknum	= NF_INET_LOCAL_IN,
		.priority	= NF_IP6_PRI_LAST-1,
	},
};

static int
ipv6_getorigdst(struct sock *sk, int optval, void __user *user, int *len)
{
	struct nf_conntrack_tuple tuple = { .src.l3num = NFPROTO_IPV6 };
	const struct ipv6_pinfo *inet6 = inet6_sk(sk);
	const struct inet_sock *inet = inet_sk(sk);
	const struct nf_conntrack_tuple_hash *h;
	struct sockaddr_in6 sin6;
	struct nf_conn *ct;
	__be32 flow_label;
	int bound_dev_if;

	lock_sock(sk);
	tuple.src.u3.in6 = sk->sk_v6_rcv_saddr;
	tuple.src.u.tcp.port = inet->inet_sport;
	tuple.dst.u3.in6 = sk->sk_v6_daddr;
	tuple.dst.u.tcp.port = inet->inet_dport;
	tuple.dst.protonum = sk->sk_protocol;
	bound_dev_if = sk->sk_bound_dev_if;
	flow_label = inet6->flow_label;
	release_sock(sk);

	if (tuple.dst.protonum != IPPROTO_TCP &&
	    tuple.dst.protonum != IPPROTO_SCTP)
		return -ENOPROTOOPT;

	if (*len < 0 || (unsigned int) *len < sizeof(sin6))
		return -EINVAL;

	h = nf_conntrack_find_get(sock_net(sk), &nf_ct_zone_dflt, &tuple);
	if (!h) {
		pr_debug("IP6T_SO_ORIGINAL_DST: Can't find %pI6c/%u-%pI6c/%u.\n",
			 &tuple.src.u3.ip6, ntohs(tuple.src.u.tcp.port),
			 &tuple.dst.u3.ip6, ntohs(tuple.dst.u.tcp.port));
		return -ENOENT;
	}

	ct = nf_ct_tuplehash_to_ctrack(h);

	sin6.sin6_family = AF_INET6;
	sin6.sin6_port = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u.tcp.port;
	sin6.sin6_flowinfo = flow_label & IPV6_FLOWINFO_MASK;
	memcpy(&sin6.sin6_addr,
		&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.in6,
					sizeof(sin6.sin6_addr));

	nf_ct_put(ct);
	sin6.sin6_scope_id = ipv6_iface_scope_id(&sin6.sin6_addr, bound_dev_if);
	return copy_to_user(user, &sin6, sizeof(sin6)) ? -EFAULT : 0;
}

#if IS_ENABLED(CONFIG_NF_CT_NETLINK)

#include <linux/netfilter/nfnetlink.h>
#include <linux/netfilter/nfnetlink_conntrack.h>

static int ipv6_tuple_to_nlattr(struct sk_buff *skb,
				const struct nf_conntrack_tuple *tuple)
{
	if (nla_put_in6_addr(skb, CTA_IP_V6_SRC, &tuple->src.u3.in6) ||
	    nla_put_in6_addr(skb, CTA_IP_V6_DST, &tuple->dst.u3.in6))
		goto nla_put_failure;
	return 0;

nla_put_failure:
	return -1;
}

static const struct nla_policy ipv6_nla_policy[CTA_IP_MAX+1] = {
	[CTA_IP_V6_SRC]	= { .len = sizeof(u_int32_t)*4 },
	[CTA_IP_V6_DST]	= { .len = sizeof(u_int32_t)*4 },
};

static int ipv6_nlattr_to_tuple(struct nlattr *tb[],
				struct nf_conntrack_tuple *t)
{
	if (!tb[CTA_IP_V6_SRC] || !tb[CTA_IP_V6_DST])
		return -EINVAL;

	t->src.u3.in6 = nla_get_in6_addr(tb[CTA_IP_V6_SRC]);
	t->dst.u3.in6 = nla_get_in6_addr(tb[CTA_IP_V6_DST]);

	return 0;
}
#endif

static int ipv6_hooks_register(struct net *net)
{
	struct conntrack6_net *cnet = net_generic(net, conntrack6_net_id);
	int err = 0;

	mutex_lock(&register_ipv6_hooks);
	cnet->users++;
	if (cnet->users > 1)
		goto out_unlock;

	err = nf_defrag_ipv6_enable(net);
	if (err < 0) {
		cnet->users = 0;
		goto out_unlock;
	}

	err = nf_register_net_hooks(net, ipv6_conntrack_ops,
				    ARRAY_SIZE(ipv6_conntrack_ops));
	if (err)
		cnet->users = 0;
 out_unlock:
	mutex_unlock(&register_ipv6_hooks);
	return err;
}

static void ipv6_hooks_unregister(struct net *net)
{
	struct conntrack6_net *cnet = net_generic(net, conntrack6_net_id);

	mutex_lock(&register_ipv6_hooks);
	if (cnet->users && (--cnet->users == 0))
		nf_unregister_net_hooks(net, ipv6_conntrack_ops,
					ARRAY_SIZE(ipv6_conntrack_ops));
	mutex_unlock(&register_ipv6_hooks);
}

const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 = {
	.l3proto		= PF_INET6,
	.pkt_to_tuple		= ipv6_pkt_to_tuple,
	.invert_tuple		= ipv6_invert_tuple,
	.get_l4proto		= ipv6_get_l4proto,
#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
	.tuple_to_nlattr	= ipv6_tuple_to_nlattr,
	.nlattr_to_tuple	= ipv6_nlattr_to_tuple,
	.nla_policy		= ipv6_nla_policy,
	.nla_size		= NLA_ALIGN(NLA_HDRLEN + sizeof(u32[4])) +
				  NLA_ALIGN(NLA_HDRLEN + sizeof(u32[4])),
#endif
	.net_ns_get		= ipv6_hooks_register,
	.net_ns_put		= ipv6_hooks_unregister,
	.me			= THIS_MODULE,
};

MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET6));
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Yasuyuki KOZAKAI @USAGI <yasuyuki.kozakai@toshiba.co.jp>");

static struct nf_sockopt_ops so_getorigdst6 = {
	.pf		= NFPROTO_IPV6,
	.get_optmin	= IP6T_SO_ORIGINAL_DST,
	.get_optmax	= IP6T_SO_ORIGINAL_DST + 1,
	.get		= ipv6_getorigdst,
	.owner		= THIS_MODULE,
};

static struct nf_conntrack_l4proto *builtin_l4proto6[] = {
	&nf_conntrack_l4proto_tcp6,
	&nf_conntrack_l4proto_udp6,
	&nf_conntrack_l4proto_icmpv6,
#ifdef CONFIG_NF_CT_PROTO_DCCP
	&nf_conntrack_l4proto_dccp6,
#endif
#ifdef CONFIG_NF_CT_PROTO_SCTP
	&nf_conntrack_l4proto_sctp6,
#endif
#ifdef CONFIG_NF_CT_PROTO_UDPLITE
	&nf_conntrack_l4proto_udplite6,
#endif
};

static int ipv6_net_init(struct net *net)
{
	return nf_ct_l4proto_pernet_register(net, builtin_l4proto6,
					     ARRAY_SIZE(builtin_l4proto6));
}

static void ipv6_net_exit(struct net *net)
{
	nf_ct_l4proto_pernet_unregister(net, builtin_l4proto6,
					ARRAY_SIZE(builtin_l4proto6));
}

static struct pernet_operations ipv6_net_ops = {
	.init = ipv6_net_init,
	.exit = ipv6_net_exit,
	.id = &conntrack6_net_id,
	.size = sizeof(struct conntrack6_net),
};

static int __init nf_conntrack_l3proto_ipv6_init(void)
{
	int ret = 0;

	need_conntrack();

#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
	if (WARN_ON(nla_policy_len(ipv6_nla_policy, CTA_IP_MAX + 1) !=
	    nf_conntrack_l3proto_ipv6.nla_size))
		return -EINVAL;
#endif

	ret = nf_register_sockopt(&so_getorigdst6);
	if (ret < 0) {
		pr_err("Unable to register netfilter socket option\n");
		return ret;
	}

	ret = register_pernet_subsys(&ipv6_net_ops);
	if (ret < 0)
		goto cleanup_sockopt;

	ret = nf_ct_l4proto_register(builtin_l4proto6,
				     ARRAY_SIZE(builtin_l4proto6));
	if (ret < 0)
		goto cleanup_pernet;

	ret = nf_ct_l3proto_register(&nf_conntrack_l3proto_ipv6);
	if (ret < 0) {
		pr_err("nf_conntrack_ipv6: can't register ipv6 proto.\n");
		goto cleanup_l4proto;
	}
	return ret;
cleanup_l4proto:
	nf_ct_l4proto_unregister(builtin_l4proto6,
				 ARRAY_SIZE(builtin_l4proto6));
 cleanup_pernet:
	unregister_pernet_subsys(&ipv6_net_ops);
 cleanup_sockopt:
	nf_unregister_sockopt(&so_getorigdst6);
	return ret;
}

static void __exit nf_conntrack_l3proto_ipv6_fini(void)
{
	synchronize_net();
	nf_ct_l3proto_unregister(&nf_conntrack_l3proto_ipv6);
	nf_ct_l4proto_unregister(builtin_l4proto6,
				 ARRAY_SIZE(builtin_l4proto6));
	unregister_pernet_subsys(&ipv6_net_ops);
	nf_unregister_sockopt(&so_getorigdst6);
}

module_init(nf_conntrack_l3proto_ipv6_init);
module_exit(nf_conntrack_l3proto_ipv6_fini);