Free Electrons

Embedded Linux Experts

  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
/*
 * Transparent proxy support for Linux/iptables
 *
 * Copyright (C) 2007-2008 BalaBit IT Ltd.
 * Author: Krisztian Kovacs
 *
 * 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.
 *
 */
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/netfilter/x_tables.h>
#include <linux/netfilter_ipv4/ip_tables.h>
#include <net/tcp.h>
#include <net/udp.h>
#include <net/icmp.h>
#include <net/sock.h>
#include <net/inet_sock.h>
#include <net/netfilter/ipv4/nf_defrag_ipv4.h>

#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
#define XT_SOCKET_HAVE_IPV6 1
#include <linux/netfilter_ipv6/ip6_tables.h>
#include <net/inet6_hashtables.h>
#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
#endif

#include <linux/netfilter/xt_socket.h>

#if IS_ENABLED(CONFIG_NF_CONNTRACK)
#define XT_SOCKET_HAVE_CONNTRACK 1
#include <net/netfilter/nf_conntrack.h>
#endif

static void
xt_socket_put_sk(struct sock *sk)
{
	if (sk->sk_state == TCP_TIME_WAIT)
		inet_twsk_put(inet_twsk(sk));
	else
		sock_put(sk);
}

static int
extract_icmp4_fields(const struct sk_buff *skb,
		    u8 *protocol,
		    __be32 *raddr,
		    __be32 *laddr,
		    __be16 *rport,
		    __be16 *lport)
{
	unsigned int outside_hdrlen = ip_hdrlen(skb);
	struct iphdr *inside_iph, _inside_iph;
	struct icmphdr *icmph, _icmph;
	__be16 *ports, _ports[2];

	icmph = skb_header_pointer(skb, outside_hdrlen,
				   sizeof(_icmph), &_icmph);
	if (icmph == NULL)
		return 1;

	switch (icmph->type) {
	case ICMP_DEST_UNREACH:
	case ICMP_SOURCE_QUENCH:
	case ICMP_REDIRECT:
	case ICMP_TIME_EXCEEDED:
	case ICMP_PARAMETERPROB:
		break;
	default:
		return 1;
	}

	inside_iph = skb_header_pointer(skb, outside_hdrlen +
					sizeof(struct icmphdr),
					sizeof(_inside_iph), &_inside_iph);
	if (inside_iph == NULL)
		return 1;

	if (inside_iph->protocol != IPPROTO_TCP &&
	    inside_iph->protocol != IPPROTO_UDP)
		return 1;

	ports = skb_header_pointer(skb, outside_hdrlen +
				   sizeof(struct icmphdr) +
				   (inside_iph->ihl << 2),
				   sizeof(_ports), &_ports);
	if (ports == NULL)
		return 1;

	/* the inside IP packet is the one quoted from our side, thus
	 * its saddr is the local address */
	*protocol = inside_iph->protocol;
	*laddr = inside_iph->saddr;
	*lport = ports[0];
	*raddr = inside_iph->daddr;
	*rport = ports[1];

	return 0;
}

/* "socket" match based redirection (no specific rule)
 * ===================================================
 *
 * There are connections with dynamic endpoints (e.g. FTP data
 * connection) that the user is unable to add explicit rules
 * for. These are taken care of by a generic "socket" rule. It is
 * assumed that the proxy application is trusted to open such
 * connections without explicit iptables rule (except of course the
 * generic 'socket' rule). In this case the following sockets are
 * matched in preference order:
 *
 *   - match: if there's a fully established connection matching the
 *     _packet_ tuple
 *
 *   - match: if there's a non-zero bound listener (possibly with a
 *     non-local address) We don't accept zero-bound listeners, since
 *     then local services could intercept traffic going through the
 *     box.
 */
static struct sock *
xt_socket_get_sock_v4(struct net *net, const u8 protocol,
		      const __be32 saddr, const __be32 daddr,
		      const __be16 sport, const __be16 dport,
		      const struct net_device *in)
{
	switch (protocol) {
	case IPPROTO_TCP:
		return __inet_lookup(net, &tcp_hashinfo,
				     saddr, sport, daddr, dport,
				     in->ifindex);
	case IPPROTO_UDP:
		return udp4_lib_lookup(net, saddr, sport, daddr, dport,
				       in->ifindex);
	}
	return NULL;
}

static bool
socket_match(const struct sk_buff *skb, struct xt_action_param *par,
	     const struct xt_socket_mtinfo1 *info)
{
	const struct iphdr *iph = ip_hdr(skb);
	struct udphdr _hdr, *hp = NULL;
	struct sock *sk = skb->sk;
	__be32 uninitialized_var(daddr), uninitialized_var(saddr);
	__be16 uninitialized_var(dport), uninitialized_var(sport);
	u8 uninitialized_var(protocol);
#ifdef XT_SOCKET_HAVE_CONNTRACK
	struct nf_conn const *ct;
	enum ip_conntrack_info ctinfo;
#endif

	if (iph->protocol == IPPROTO_UDP || iph->protocol == IPPROTO_TCP) {
		hp = skb_header_pointer(skb, ip_hdrlen(skb),
					sizeof(_hdr), &_hdr);
		if (hp == NULL)
			return false;

		protocol = iph->protocol;
		saddr = iph->saddr;
		sport = hp->source;
		daddr = iph->daddr;
		dport = hp->dest;

	} else if (iph->protocol == IPPROTO_ICMP) {
		if (extract_icmp4_fields(skb, &protocol, &saddr, &daddr,
					&sport, &dport))
			return false;
	} else {
		return false;
	}

#ifdef XT_SOCKET_HAVE_CONNTRACK
	/* Do the lookup with the original socket address in case this is a
	 * reply packet of an established SNAT-ted connection. */

	ct = nf_ct_get(skb, &ctinfo);
	if (ct && !nf_ct_is_untracked(ct) &&
	    ((iph->protocol != IPPROTO_ICMP &&
	      ctinfo == IP_CT_ESTABLISHED_REPLY) ||
	     (iph->protocol == IPPROTO_ICMP &&
	      ctinfo == IP_CT_RELATED_REPLY)) &&
	    (ct->status & IPS_SRC_NAT_DONE)) {

		daddr = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip;
		dport = (iph->protocol == IPPROTO_TCP) ?
			ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.tcp.port :
			ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.udp.port;
	}
#endif

	if (!sk)
		sk = xt_socket_get_sock_v4(dev_net(skb->dev), protocol,
					   saddr, daddr, sport, dport,
					   par->in);
	if (sk) {
		bool wildcard;
		bool transparent = true;

		/* Ignore sockets listening on INADDR_ANY,
		 * unless XT_SOCKET_NOWILDCARD is set
		 */
		wildcard = (!(info->flags & XT_SOCKET_NOWILDCARD) &&
			    sk->sk_state != TCP_TIME_WAIT &&
			    inet_sk(sk)->inet_rcv_saddr == 0);

		/* Ignore non-transparent sockets,
		   if XT_SOCKET_TRANSPARENT is used */
		if (info->flags & XT_SOCKET_TRANSPARENT)
			transparent = ((sk->sk_state != TCP_TIME_WAIT &&
					inet_sk(sk)->transparent) ||
				       (sk->sk_state == TCP_TIME_WAIT &&
					inet_twsk(sk)->tw_transparent));

		if (sk != skb->sk)
			xt_socket_put_sk(sk);

		if (wildcard || !transparent)
			sk = NULL;
	}

	pr_debug("proto %hhu %pI4:%hu -> %pI4:%hu (orig %pI4:%hu) sock %p\n",
		 protocol, &saddr, ntohs(sport),
		 &daddr, ntohs(dport),
		 &iph->daddr, hp ? ntohs(hp->dest) : 0, sk);

	return (sk != NULL);
}

static bool
socket_mt4_v0(const struct sk_buff *skb, struct xt_action_param *par)
{
	static struct xt_socket_mtinfo1 xt_info_v0 = {
		.flags = 0,
	};

	return socket_match(skb, par, &xt_info_v0);
}

static bool
socket_mt4_v1_v2(const struct sk_buff *skb, struct xt_action_param *par)
{
	return socket_match(skb, par, par->matchinfo);
}

#ifdef XT_SOCKET_HAVE_IPV6

static int
extract_icmp6_fields(const struct sk_buff *skb,
		     unsigned int outside_hdrlen,
		     int *protocol,
		     const struct in6_addr **raddr,
		     const struct in6_addr **laddr,
		     __be16 *rport,
		     __be16 *lport,
		     struct ipv6hdr *ipv6_var)
{
	const struct ipv6hdr *inside_iph;
	struct icmp6hdr *icmph, _icmph;
	__be16 *ports, _ports[2];
	u8 inside_nexthdr;
	__be16 inside_fragoff;
	int inside_hdrlen;

	icmph = skb_header_pointer(skb, outside_hdrlen,
				   sizeof(_icmph), &_icmph);
	if (icmph == NULL)
		return 1;

	if (icmph->icmp6_type & ICMPV6_INFOMSG_MASK)
		return 1;

	inside_iph = skb_header_pointer(skb, outside_hdrlen + sizeof(_icmph),
					sizeof(*ipv6_var), ipv6_var);
	if (inside_iph == NULL)
		return 1;
	inside_nexthdr = inside_iph->nexthdr;

	inside_hdrlen = ipv6_skip_exthdr(skb, outside_hdrlen + sizeof(_icmph) +
					      sizeof(*ipv6_var),
					 &inside_nexthdr, &inside_fragoff);
	if (inside_hdrlen < 0)
		return 1; /* hjm: Packet has no/incomplete transport layer headers. */

	if (inside_nexthdr != IPPROTO_TCP &&
	    inside_nexthdr != IPPROTO_UDP)
		return 1;

	ports = skb_header_pointer(skb, inside_hdrlen,
				   sizeof(_ports), &_ports);
	if (ports == NULL)
		return 1;

	/* the inside IP packet is the one quoted from our side, thus
	 * its saddr is the local address */
	*protocol = inside_nexthdr;
	*laddr = &inside_iph->saddr;
	*lport = ports[0];
	*raddr = &inside_iph->daddr;
	*rport = ports[1];

	return 0;
}

static struct sock *
xt_socket_get_sock_v6(struct net *net, const u8 protocol,
		      const struct in6_addr *saddr, const struct in6_addr *daddr,
		      const __be16 sport, const __be16 dport,
		      const struct net_device *in)
{
	switch (protocol) {
	case IPPROTO_TCP:
		return inet6_lookup(net, &tcp_hashinfo,
				    saddr, sport, daddr, dport,
				    in->ifindex);
	case IPPROTO_UDP:
		return udp6_lib_lookup(net, saddr, sport, daddr, dport,
				       in->ifindex);
	}

	return NULL;
}

static bool
socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par)
{
	struct ipv6hdr ipv6_var, *iph = ipv6_hdr(skb);
	struct udphdr _hdr, *hp = NULL;
	struct sock *sk = skb->sk;
	const struct in6_addr *daddr = NULL, *saddr = NULL;
	__be16 uninitialized_var(dport), uninitialized_var(sport);
	int thoff = 0, uninitialized_var(tproto);
	const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo;

	tproto = ipv6_find_hdr(skb, &thoff, -1, NULL, NULL);
	if (tproto < 0) {
		pr_debug("unable to find transport header in IPv6 packet, dropping\n");
		return NF_DROP;
	}

	if (tproto == IPPROTO_UDP || tproto == IPPROTO_TCP) {
		hp = skb_header_pointer(skb, thoff,
					sizeof(_hdr), &_hdr);
		if (hp == NULL)
			return false;

		saddr = &iph->saddr;
		sport = hp->source;
		daddr = &iph->daddr;
		dport = hp->dest;

	} else if (tproto == IPPROTO_ICMPV6) {
		if (extract_icmp6_fields(skb, thoff, &tproto, &saddr, &daddr,
					 &sport, &dport, &ipv6_var))
			return false;
	} else {
		return false;
	}

	if (!sk)
		sk = xt_socket_get_sock_v6(dev_net(skb->dev), tproto,
					   saddr, daddr, sport, dport,
					   par->in);
	if (sk) {
		bool wildcard;
		bool transparent = true;

		/* Ignore sockets listening on INADDR_ANY
		 * unless XT_SOCKET_NOWILDCARD is set
		 */
		wildcard = (!(info->flags & XT_SOCKET_NOWILDCARD) &&
			    sk->sk_state != TCP_TIME_WAIT &&
			    ipv6_addr_any(&inet6_sk(sk)->rcv_saddr));

		/* Ignore non-transparent sockets,
		   if XT_SOCKET_TRANSPARENT is used */
		if (info->flags & XT_SOCKET_TRANSPARENT)
			transparent = ((sk->sk_state != TCP_TIME_WAIT &&
					inet_sk(sk)->transparent) ||
				       (sk->sk_state == TCP_TIME_WAIT &&
					inet_twsk(sk)->tw_transparent));

		if (sk != skb->sk)
			xt_socket_put_sk(sk);

		if (wildcard || !transparent)
			sk = NULL;
	}

	pr_debug("proto %hhd %pI6:%hu -> %pI6:%hu "
		 "(orig %pI6:%hu) sock %p\n",
		 tproto, saddr, ntohs(sport),
		 daddr, ntohs(dport),
		 &iph->daddr, hp ? ntohs(hp->dest) : 0, sk);

	return (sk != NULL);
}
#endif

static int socket_mt_v1_check(const struct xt_mtchk_param *par)
{
	const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo;

	if (info->flags & ~XT_SOCKET_FLAGS_V1) {
		pr_info("unknown flags 0x%x\n", info->flags & ~XT_SOCKET_FLAGS_V1);
		return -EINVAL;
	}
	return 0;
}

static int socket_mt_v2_check(const struct xt_mtchk_param *par)
{
	const struct xt_socket_mtinfo2 *info = (struct xt_socket_mtinfo2 *) par->matchinfo;

	if (info->flags & ~XT_SOCKET_FLAGS_V2) {
		pr_info("unknown flags 0x%x\n", info->flags & ~XT_SOCKET_FLAGS_V2);
		return -EINVAL;
	}
	return 0;
}

static struct xt_match socket_mt_reg[] __read_mostly = {
	{
		.name		= "socket",
		.revision	= 0,
		.family		= NFPROTO_IPV4,
		.match		= socket_mt4_v0,
		.hooks		= (1 << NF_INET_PRE_ROUTING) |
				  (1 << NF_INET_LOCAL_IN),
		.me		= THIS_MODULE,
	},
	{
		.name		= "socket",
		.revision	= 1,
		.family		= NFPROTO_IPV4,
		.match		= socket_mt4_v1_v2,
		.checkentry	= socket_mt_v1_check,
		.matchsize	= sizeof(struct xt_socket_mtinfo1),
		.hooks		= (1 << NF_INET_PRE_ROUTING) |
				  (1 << NF_INET_LOCAL_IN),
		.me		= THIS_MODULE,
	},
#ifdef XT_SOCKET_HAVE_IPV6
	{
		.name		= "socket",
		.revision	= 1,
		.family		= NFPROTO_IPV6,
		.match		= socket_mt6_v1_v2,
		.checkentry	= socket_mt_v1_check,
		.matchsize	= sizeof(struct xt_socket_mtinfo1),
		.hooks		= (1 << NF_INET_PRE_ROUTING) |
				  (1 << NF_INET_LOCAL_IN),
		.me		= THIS_MODULE,
	},
#endif
	{
		.name		= "socket",
		.revision	= 2,
		.family		= NFPROTO_IPV4,
		.match		= socket_mt4_v1_v2,
		.checkentry	= socket_mt_v2_check,
		.matchsize	= sizeof(struct xt_socket_mtinfo1),
		.hooks		= (1 << NF_INET_PRE_ROUTING) |
				  (1 << NF_INET_LOCAL_IN),
		.me		= THIS_MODULE,
	},
#ifdef XT_SOCKET_HAVE_IPV6
	{
		.name		= "socket",
		.revision	= 2,
		.family		= NFPROTO_IPV6,
		.match		= socket_mt6_v1_v2,
		.checkentry	= socket_mt_v2_check,
		.matchsize	= sizeof(struct xt_socket_mtinfo1),
		.hooks		= (1 << NF_INET_PRE_ROUTING) |
				  (1 << NF_INET_LOCAL_IN),
		.me		= THIS_MODULE,
	},
#endif
};

static int __init socket_mt_init(void)
{
	nf_defrag_ipv4_enable();
#ifdef XT_SOCKET_HAVE_IPV6
	nf_defrag_ipv6_enable();
#endif

	return xt_register_matches(socket_mt_reg, ARRAY_SIZE(socket_mt_reg));
}

static void __exit socket_mt_exit(void)
{
	xt_unregister_matches(socket_mt_reg, ARRAY_SIZE(socket_mt_reg));
}

module_init(socket_mt_init);
module_exit(socket_mt_exit);

MODULE_LICENSE("GPL");
MODULE_AUTHOR("Krisztian Kovacs, Balazs Scheidler");
MODULE_DESCRIPTION("x_tables socket match module");
MODULE_ALIAS("ipt_socket");
MODULE_ALIAS("ip6t_socket");