aboutsummaryrefslogtreecommitdiff
path: root/net/netfilter/xt_TPROXY.c
blob: ef8a926752a97542f6f2f8eeb378e150958bff3d (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
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
/*
 * Transparent proxy support for Linux/iptables
 *
 * Copyright (c) 2006-2010 BalaBit IT Ltd.
 * Author: Balazs Scheidler, 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/ip.h>
#include <net/checksum.h>
#include <net/udp.h>
#include <net/tcp.h>
#include <net/inet_sock.h>
#include <net/inet_hashtables.h>
#include <linux/inetdevice.h>
#include <linux/netfilter/x_tables.h>
#include <linux/netfilter_ipv4/ip_tables.h>

#include <net/netfilter/ipv4/nf_defrag_ipv4.h>

#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
#define XT_TPROXY_HAVE_IPV6 1
#include <net/if_inet6.h>
#include <net/addrconf.h>
#include <net/inet6_hashtables.h>
#include <linux/netfilter_ipv6/ip6_tables.h>
#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
#endif

#include <linux/netfilter/xt_TPROXY.h>

enum nf_tproxy_lookup_t {
	 NFT_LOOKUP_LISTENER,
	 NFT_LOOKUP_ESTABLISHED,
};

static bool tproxy_sk_is_transparent(struct sock *sk)
{
	if (sk->sk_state != TCP_TIME_WAIT) {
		if (inet_sk(sk)->transparent)
			return true;
		sock_put(sk);
	} else {
		if (inet_twsk(sk)->tw_transparent)
			return true;
		inet_twsk_put(inet_twsk(sk));
	}
	return false;
}

static inline __be32
tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr)
{
	struct in_device *indev;
	__be32 laddr;

	if (user_laddr)
		return user_laddr;

	laddr = 0;
	rcu_read_lock();
	indev = __in_dev_get_rcu(skb->dev);
	for_primary_ifa(indev) {
		laddr = ifa->ifa_local;
		break;
	} endfor_ifa(indev);
	rcu_read_unlock();

	return laddr ? laddr : daddr;
}

/*
 * This is used when the user wants to intercept a connection matching
 * an explicit iptables rule. In this case the sockets are assumed
 * matching in preference order:
 *
 *   - match: if there's a fully established connection matching the
 *     _packet_ tuple, it is returned, assuming the redirection
 *     already took place and we process a packet belonging to an
 *     established connection
 *
 *   - match: if there's a listening socket matching the redirection
 *     (e.g. on-port & on-ip of the connection), it is returned,
 *     regardless if it was bound to 0.0.0.0 or an explicit
 *     address. The reasoning is that if there's an explicit rule, it
 *     does not really matter if the listener is bound to an interface
 *     or to 0. The user already stated that he wants redirection
 *     (since he added the rule).
 *
 * Please note that there's an overlap between what a TPROXY target
 * and a socket match will match. Normally if you have both rules the
 * "socket" match will be the first one, effectively all packets
 * belonging to established connections going through that one.
 */
static inline struct sock *
nf_tproxy_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,
		      const enum nf_tproxy_lookup_t lookup_type)
{
	struct sock *sk;

	switch (protocol) {
	case IPPROTO_TCP:
		switch (lookup_type) {
		case NFT_LOOKUP_LISTENER:
			sk = inet_lookup_listener(net, &tcp_hashinfo,
						    saddr, sport,
						    daddr, dport,
						    in->ifindex);

			/* NOTE: we return listeners even if bound to
			 * 0.0.0.0, those are filtered out in
			 * xt_socket, since xt_TPROXY needs 0 bound
			 * listeners too
			 */
			break;
		case NFT_LOOKUP_ESTABLISHED:
			sk = inet_lookup_established(net, &tcp_hashinfo,
						    saddr, sport, daddr, dport,
						    in->ifindex);
			break;
		default:
			BUG();
		}
		break;
	case IPPROTO_UDP:
		sk = udp4_lib_lookup(net, saddr, sport, daddr, dport,
				     in->ifindex);
		if (sk) {
			int connected = (sk->sk_state == TCP_ESTABLISHED);
			int wildcard = (inet_sk(sk)->inet_rcv_saddr == 0);

			/* NOTE: we return listeners even if bound to
			 * 0.0.0.0, those are filtered out in
			 * xt_socket, since xt_TPROXY needs 0 bound
			 * listeners too
			 */
			if ((lookup_type == NFT_LOOKUP_ESTABLISHED && (!connected || wildcard)) ||
			    (lookup_type == NFT_LOOKUP_LISTENER && connected)) {
				sock_put(sk);
				sk = NULL;
			}
		}
		break;
	default:
		WARN_ON(1);
		sk = NULL;
	}

	pr_debug("tproxy socket lookup: proto %u %08x:%u -> %08x:%u, lookup type: %d, sock %p\n",
		 protocol, ntohl(saddr), ntohs(sport), ntohl(daddr), ntohs(dport), lookup_type, sk);

	return sk;
}

#ifdef XT_TPROXY_HAVE_IPV6
static inline struct sock *
nf_tproxy_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,
		      const enum nf_tproxy_lookup_t lookup_type)
{
	struct sock *sk;

	switch (protocol) {
	case IPPROTO_TCP:
		switch (lookup_type) {
		case NFT_LOOKUP_LISTENER:
			sk = inet6_lookup_listener(net, &tcp_hashinfo,
						   saddr, sport,
						   daddr, ntohs(dport),
						   in->ifindex);

			/* NOTE: we return listeners even if bound to
			 * 0.0.0.0, those are filtered out in
			 * xt_socket, since xt_TPROXY needs 0 bound
			 * listeners too
			 */
			break;
		case NFT_LOOKUP_ESTABLISHED:
			sk = __inet6_lookup_established(net, &tcp_hashinfo,
							saddr, sport, daddr, ntohs(dport),
							in->ifindex);
			break;
		default:
			BUG();
		}
		break;
	case IPPROTO_UDP:
		sk = udp6_lib_lookup(net, saddr, sport, daddr, dport,
				     in->ifindex);
		if (sk) {
			int connected = (sk->sk_state == TCP_ESTABLISHED);
			int wildcard = ipv6_addr_any(&sk->sk_v6_rcv_saddr);

			/* NOTE: we return listeners even if bound to
			 * 0.0.0.0, those are filtered out in
			 * xt_socket, since xt_TPROXY needs 0 bound
			 * listeners too
			 */
			if ((lookup_type == NFT_LOOKUP_ESTABLISHED && (!connected || wildcard)) ||
			    (lookup_type == NFT_LOOKUP_LISTENER && connected)) {
				sock_put(sk);
				sk = NULL;
			}
		}
		break;
	default:
		WARN_ON(1);
		sk = NULL;
	}

	pr_debug("tproxy socket lookup: proto %u %pI6:%u -> %pI6:%u, lookup type: %d, sock %p\n",
		 protocol, saddr, ntohs(sport), daddr, ntohs(dport), lookup_type, sk);

	return sk;
}
#endif

/**
 * tproxy_handle_time_wait4 - handle IPv4 TCP TIME_WAIT reopen redirections
 * @skb:	The skb being processed.
 * @laddr:	IPv4 address to redirect to or zero.
 * @lport:	TCP port to redirect to or zero.
 * @sk:		The TIME_WAIT TCP socket found by the lookup.
 *
 * We have to handle SYN packets arriving to TIME_WAIT sockets
 * differently: instead of reopening the connection we should rather
 * redirect the new connection to the proxy if there's a listener
 * socket present.
 *
 * tproxy_handle_time_wait4() consumes the socket reference passed in.
 *
 * Returns the listener socket if there's one, the TIME_WAIT socket if
 * no such listener is found, or NULL if the TCP header is incomplete.
 */
static struct sock *
tproxy_handle_time_wait4(struct sk_buff *skb, __be32 laddr, __be16 lport,
			struct sock *sk)
{
	const struct iphdr *iph = ip_hdr(skb);
	struct tcphdr _hdr, *hp;

	hp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_hdr), &_hdr);
	if (hp == NULL) {
		inet_twsk_put(inet_twsk(sk));
		return NULL;
	}

	if (hp->syn && !hp->rst && !hp->ack && !hp->fin) {
		/* SYN to a TIME_WAIT socket, we'd rather redirect it
		 * to a listener socket if there's one */
		struct sock *sk2;

		sk2 = nf_tproxy_get_sock_v4(dev_net(skb->dev), iph->protocol,
					    iph->saddr, laddr ? laddr : iph->daddr,
					    hp->source, lport ? lport : hp->dest,
					    skb->dev, NFT_LOOKUP_LISTENER);
		if (sk2) {
			inet_twsk_deschedule(inet_twsk(sk), &tcp_death_row);
			inet_twsk_put(inet_twsk(sk));
			sk = sk2;
		}
	}

	return sk;
}

/* assign a socket to the skb -- consumes sk */
static void
nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk)
{
	skb_orphan(skb);
	skb->sk = sk;
	skb->destructor = sock_edemux;
}

static unsigned int
tproxy_tg4(struct sk_buff *skb, __be32 laddr, __be16 lport,
	   u_int32_t mark_mask, u_int32_t mark_value)
{
	const struct iphdr *iph = ip_hdr(skb);
	struct udphdr _hdr, *hp;
	struct sock *sk;

	hp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_hdr), &_hdr);
	if (hp == NULL)
		return NF_DROP;

	/* check if there's an ongoing connection on the packet
	 * addresses, this happens if the redirect already happened
	 * and the current packet belongs to an already established
	 * connection */
	sk = nf_tproxy_get_sock_v4(dev_net(skb->dev), iph->protocol,
				   iph->saddr, iph->daddr,
				   hp->source, hp->dest,
				   skb->dev, NFT_LOOKUP_ESTABLISHED);

	laddr = tproxy_laddr4(skb, laddr, iph->daddr);
	if (!lport)
		lport = hp->dest;

	/* UDP has no TCP_TIME_WAIT state, so we never enter here */
	if (sk && sk->sk_state == TCP_TIME_WAIT)
		/* reopening a TIME_WAIT connection needs special handling */
		sk = tproxy_handle_time_wait4(skb, laddr, lport, sk);
	else if (!sk)
		/* no, there's no established connection, check if
		 * there's a listener on the redirected addr/port */
		sk = nf_tproxy_get_sock_v4(dev_net(skb->dev), iph->protocol,
					   iph->saddr, laddr,
					   hp->source, lport,
					   skb->dev, NFT_LOOKUP_LISTENER);

	/* NOTE: assign_sock consumes our sk reference */
	if (sk && tproxy_sk_is_transparent(sk)) {
		/* This should be in a separate target, but we don't do multiple
		   targets on the same rule yet */
		skb->mark = (skb->mark & ~mark_mask) ^ mark_value;

		pr_debug("redirecting: proto %hhu %pI4:%hu -> %pI4:%hu, mark: %x\n",
			 iph->protocol, &iph->daddr, ntohs(hp->dest),
			 &laddr, ntohs(lport), skb->mark);

		nf_tproxy_assign_sock(skb, sk);
		return NF_ACCEPT;
	}

	pr_debug("no socket, dropping: proto %hhu %pI4:%hu -> %pI4:%hu, mark: %x\n",
		 iph->protocol, &iph->saddr, ntohs(hp->source),
		 &iph->daddr, ntohs(hp->dest), skb->mark);
	return NF_DROP;
}

static unsigned int
tproxy_tg4_v0(struct sk_buff *skb, const struct xt_action_param *par)
{
	const struct xt_tproxy_target_info *tgi = par->targinfo;

	return tproxy_tg4(skb, tgi->laddr, tgi->lport, tgi->mark_mask, tgi->mark_value);
}

static unsigned int
tproxy_tg4_v1(struct sk_buff *skb, const struct xt_action_param *par)
{
	const struct xt_tproxy_target_info_v1 *tgi = par->targinfo;

	return tproxy_tg4(skb, tgi->laddr.ip, tgi->lport, tgi->mark_mask, tgi->mark_value);
}

#ifdef XT_TPROXY_HAVE_IPV6

static inline const struct in6_addr *
tproxy_laddr6(struct sk_buff *skb, const struct in6_addr *user_laddr,
	      const struct in6_addr *daddr)
{
	struct inet6_dev *indev;
	struct inet6_ifaddr *ifa;
	struct in6_addr *laddr;

	if (!ipv6_addr_any(user_laddr))
		return user_laddr;
	laddr = NULL;

	rcu_read_lock();
	indev = __in6_dev_get(skb->dev);
	if (indev)
		list_for_each_entry(ifa, &indev->addr_list, if_list) {
			if (ifa->flags & (IFA_F_TENTATIVE | IFA_F_DEPRECATED))
				continue;

			laddr = &ifa->addr;
			break;
		}
	rcu_read_unlock();

	return laddr ? laddr : daddr;
}

/**
 * tproxy_handle_time_wait6 - handle IPv6 TCP TIME_WAIT reopen redirections
 * @skb:	The skb being processed.
 * @tproto:	Transport protocol.
 * @thoff:	Transport protocol header offset.
 * @par:	Iptables target parameters.
 * @sk:		The TIME_WAIT TCP socket found by the lookup.
 *
 * We have to handle SYN packets arriving to TIME_WAIT sockets
 * differently: instead of reopening the connection we should rather
 * redirect the new connection to the proxy if there's a listener
 * socket present.
 *
 * tproxy_handle_time_wait6() consumes the socket reference passed in.
 *
 * Returns the listener socket if there's one, the TIME_WAIT socket if
 * no such listener is found, or NULL if the TCP header is incomplete.
 */
static struct sock *
tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff,
			 const struct xt_action_param *par,
			 struct sock *sk)
{
	const struct ipv6hdr *iph = ipv6_hdr(skb);
	struct tcphdr _hdr, *hp;
	const struct xt_tproxy_target_info_v1 *tgi = par->targinfo;

	hp = skb_header_pointer(skb, thoff, sizeof(_hdr), &_hdr);
	if (hp == NULL) {
		inet_twsk_put(inet_twsk(sk));
		return NULL;
	}

	if (hp->syn && !hp->rst && !hp->ack && !hp->fin) {
		/* SYN to a TIME_WAIT socket, we'd rather redirect it
		 * to a listener socket if there's one */
		struct sock *sk2;

		sk2 = nf_tproxy_get_sock_v6(dev_net(skb->dev), tproto,
					    &iph->saddr,
					    tproxy_laddr6(skb, &tgi->laddr.in6, &iph->daddr),
					    hp->source,
					    tgi->lport ? tgi->lport : hp->dest,
					    skb->dev, NFT_LOOKUP_LISTENER);
		if (sk2) {
			inet_twsk_deschedule(inet_twsk(sk), &tcp_death_row);
			inet_twsk_put(inet_twsk(sk));
			sk = sk2;
		}
	}

	return sk;
}

static unsigned int
tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par)
{
	const struct ipv6hdr *iph = ipv6_hdr(skb);
	const struct xt_tproxy_target_info_v1 *tgi = par->targinfo;
	struct udphdr _hdr, *hp;
	struct sock *sk;
	const struct in6_addr *laddr;
	__be16 lport;
	int thoff = 0;
	int tproto;

	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;
	}

	hp = skb_header_pointer(skb, thoff, sizeof(_hdr), &_hdr);
	if (hp == NULL) {
		pr_debug("unable to grab transport header contents in IPv6 packet, dropping\n");
		return NF_DROP;
	}

	/* check if there's an ongoing connection on the packet
	 * addresses, this happens if the redirect already happened
	 * and the current packet belongs to an already established
	 * connection */
	sk = nf_tproxy_get_sock_v6(dev_net(skb->dev), tproto,
				   &iph->saddr, &iph->daddr,
				   hp->source, hp->dest,
				   par->in, NFT_LOOKUP_ESTABLISHED);

	laddr = tproxy_laddr6(skb, &tgi->laddr.in6, &iph->daddr);
	lport = tgi->lport ? tgi->lport : hp->dest;

	/* UDP has no TCP_TIME_WAIT state, so we never enter here */
	if (sk && sk->sk_state == TCP_TIME_WAIT)
		/* reopening a TIME_WAIT connection needs special handling */
		sk = tproxy_handle_time_wait6(skb, tproto, thoff, par, sk);
	else if (!sk)
		/* no there's no established connection, check if
		 * there's a listener on the redirected addr/port */
		sk = nf_tproxy_get_sock_v6(dev_net(skb->dev), tproto,
					   &iph->saddr, laddr,
					   hp->source, lport,
					   par->in, NFT_LOOKUP_LISTENER);

	/* NOTE: assign_sock consumes our sk reference */
	if (sk && tproxy_sk_is_transparent(sk)) {
		/* This should be in a separate target, but we don't do multiple
		   targets on the same rule yet */
		skb->mark = (skb->mark & ~tgi->mark_mask) ^ tgi->mark_value;

		pr_debug("redirecting: proto %hhu %pI6:%hu -> %pI6:%hu, mark: %x\n",
			 tproto, &iph->saddr, ntohs(hp->source),
			 laddr, ntohs(lport), skb->mark);

		nf_tproxy_assign_sock(skb, sk);
		return NF_ACCEPT;
	}

	pr_debug("no socket, dropping: proto %hhu %pI6:%hu -> %pI6:%hu, mark: %x\n",
		 tproto, &iph->saddr, ntohs(hp->source),
		 &iph->daddr, ntohs(hp->dest), skb->mark);

	return NF_DROP;
}

static int tproxy_tg6_check(const struct xt_tgchk_param *par)
{
	const struct ip6t_ip6 *i = par->entryinfo;

	if ((i->proto == IPPROTO_TCP || i->proto == IPPROTO_UDP)
	    && !(i->flags & IP6T_INV_PROTO))
		return 0;

	pr_info("Can be used only in combination with "
		"either -p tcp or -p udp\n");
	return -EINVAL;
}
#endif

static int tproxy_tg4_check(const struct xt_tgchk_param *par)
{
	const struct ipt_ip *i = par->entryinfo;

	if ((i->proto == IPPROTO_TCP || i->proto == IPPROTO_UDP)
	    && !(i->invflags & IPT_INV_PROTO))
		return 0;

	pr_info("Can be used only in combination with "
		"either -p tcp or -p udp\n");
	return -EINVAL;
}

static struct xt_target tproxy_tg_reg[] __read_mostly = {
	{
		.name		= "TPROXY",
		.family		= NFPROTO_IPV4,
		.table		= "mangle",
		.target		= tproxy_tg4_v0,
		.revision	= 0,
		.targetsize	= sizeof(struct xt_tproxy_target_info),
		.checkentry	= tproxy_tg4_check,
		.hooks		= 1 << NF_INET_PRE_ROUTING,
		.me		= THIS_MODULE,
	},
	{
		.name		= "TPROXY",
		.family		= NFPROTO_IPV4,
		.table		= "mangle",
		.target		= tproxy_tg4_v1,
		.revision	= 1,
		.targetsize	= sizeof(struct xt_tproxy_target_info_v1),
		.checkentry	= tproxy_tg4_check,
		.hooks		= 1 << NF_INET_PRE_ROUTING,
		.me		= THIS_MODULE,
	},
#ifdef XT_TPROXY_HAVE_IPV6
	{
		.name		= "TPROXY",
		.family		= NFPROTO_IPV6,
		.table		= "mangle",
		.target		= tproxy_tg6_v1,
		.revision	= 1,
		.targetsize	= sizeof(struct xt_tproxy_target_info_v1),
		.checkentry	= tproxy_tg6_check,
		.hooks		= 1 << NF_INET_PRE_ROUTING,
		.me		= THIS_MODULE,
	},
#endif

};

static int __init tproxy_tg_init(void)
{
	nf_defrag_ipv4_enable();
#ifdef XT_TPROXY_HAVE_IPV6
	nf_defrag_ipv6_enable();
#endif

	return xt_register_targets(tproxy_tg_reg, ARRAY_SIZE(tproxy_tg_reg));
}

static void __exit tproxy_tg_exit(void)
{
	xt_unregister_targets(tproxy_tg_reg, ARRAY_SIZE(tproxy_tg_reg));
}

module_init(tproxy_tg_init);
module_exit(tproxy_tg_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Balazs Scheidler, Krisztian Kovacs");
MODULE_DESCRIPTION("Netfilter transparent proxy (TPROXY) target module.");
MODULE_ALIAS("ipt_TPROXY");
MODULE_ALIAS("ip6t_TPROXY");