aboutsummaryrefslogtreecommitdiff
path: root/net/ipv4/netfilter/nf_nat_core.c
blob: acdd002bb5405876522223a8e979ff4daf2d1c81 (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
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
/* NAT for netfilter; shared with compatibility layer. */

/* (C) 1999-2001 Paul `Rusty' Russell
 * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
 *
 * 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.
 */

#include <linux/module.h>
#include <linux/types.h>
#include <linux/timer.h>
#include <linux/skbuff.h>
#include <linux/gfp.h>
#include <net/checksum.h>
#include <net/icmp.h>
#include <net/ip.h>
#include <net/tcp.h>  /* For tcp_prot in getorigdst */
#include <linux/icmp.h>
#include <linux/udp.h>
#include <linux/jhash.h>

#include <linux/netfilter_ipv4.h>
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_nat.h>
#include <net/netfilter/nf_nat_protocol.h>
#include <net/netfilter/nf_nat_core.h>
#include <net/netfilter/nf_nat_helper.h>
#include <net/netfilter/nf_conntrack_helper.h>
#include <net/netfilter/nf_conntrack_l3proto.h>
#include <net/netfilter/nf_conntrack_zones.h>

static DEFINE_SPINLOCK(nf_nat_lock);

static struct nf_conntrack_l3proto *l3proto __read_mostly;

#define MAX_IP_NAT_PROTO 256
static const struct nf_nat_protocol __rcu *nf_nat_protos[MAX_IP_NAT_PROTO]
						__read_mostly;

static inline const struct nf_nat_protocol *
__nf_nat_proto_find(u_int8_t protonum)
{
	return rcu_dereference(nf_nat_protos[protonum]);
}

/* We keep an extra hash for each conntrack, for fast searching. */
static inline unsigned int
hash_by_src(const struct net *net, u16 zone,
	    const struct nf_conntrack_tuple *tuple)
{
	unsigned int hash;

	/* Original src, to ensure we map it consistently if poss. */
	hash = jhash_3words((__force u32)tuple->src.u3.ip,
			    (__force u32)tuple->src.u.all ^ zone,
			    tuple->dst.protonum, nf_conntrack_hash_rnd);
	return ((u64)hash * net->ipv4.nat_htable_size) >> 32;
}

/* Is this tuple already taken? (not by us) */
int
nf_nat_used_tuple(const struct nf_conntrack_tuple *tuple,
		  const struct nf_conn *ignored_conntrack)
{
	/* Conntrack tracking doesn't keep track of outgoing tuples; only
	   incoming ones.  NAT means they don't have a fixed mapping,
	   so we invert the tuple and look for the incoming reply.

	   We could keep a separate hash if this proves too slow. */
	struct nf_conntrack_tuple reply;

	nf_ct_invert_tuplepr(&reply, tuple);
	return nf_conntrack_tuple_taken(&reply, ignored_conntrack);
}
EXPORT_SYMBOL(nf_nat_used_tuple);

/* If we source map this tuple so reply looks like reply_tuple, will
 * that meet the constraints of range. */
static int
in_range(const struct nf_conntrack_tuple *tuple,
	 const struct nf_nat_ipv4_range *range)
{
	const struct nf_nat_protocol *proto;
	int ret = 0;

	/* If we are supposed to map IPs, then we must be in the
	   range specified, otherwise let this drag us onto a new src IP. */
	if (range->flags & NF_NAT_RANGE_MAP_IPS) {
		if (ntohl(tuple->src.u3.ip) < ntohl(range->min_ip) ||
		    ntohl(tuple->src.u3.ip) > ntohl(range->max_ip))
			return 0;
	}

	rcu_read_lock();
	proto = __nf_nat_proto_find(tuple->dst.protonum);
	if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) ||
	    proto->in_range(tuple, NF_NAT_MANIP_SRC,
			    &range->min, &range->max))
		ret = 1;
	rcu_read_unlock();

	return ret;
}

static inline int
same_src(const struct nf_conn *ct,
	 const struct nf_conntrack_tuple *tuple)
{
	const struct nf_conntrack_tuple *t;

	t = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
	return (t->dst.protonum == tuple->dst.protonum &&
		t->src.u3.ip == tuple->src.u3.ip &&
		t->src.u.all == tuple->src.u.all);
}

/* Only called for SRC manip */
static int
find_appropriate_src(struct net *net, u16 zone,
		     const struct nf_conntrack_tuple *tuple,
		     struct nf_conntrack_tuple *result,
		     const struct nf_nat_ipv4_range *range)
{
	unsigned int h = hash_by_src(net, zone, tuple);
	const struct nf_conn_nat *nat;
	const struct nf_conn *ct;
	const struct hlist_node *n;

	rcu_read_lock();
	hlist_for_each_entry_rcu(nat, n, &net->ipv4.nat_bysource[h], bysource) {
		ct = nat->ct;
		if (same_src(ct, tuple) && nf_ct_zone(ct) == zone) {
			/* Copy source part from reply tuple. */
			nf_ct_invert_tuplepr(result,
				       &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
			result->dst = tuple->dst;

			if (in_range(result, range)) {
				rcu_read_unlock();
				return 1;
			}
		}
	}
	rcu_read_unlock();
	return 0;
}

/* For [FUTURE] fragmentation handling, we want the least-used
   src-ip/dst-ip/proto triple.  Fairness doesn't come into it.  Thus
   if the range specifies 1.2.3.4 ports 10000-10005 and 1.2.3.5 ports
   1-65535, we don't do pro-rata allocation based on ports; we choose
   the ip with the lowest src-ip/dst-ip/proto usage.
*/
static void
find_best_ips_proto(u16 zone, struct nf_conntrack_tuple *tuple,
		    const struct nf_nat_ipv4_range *range,
		    const struct nf_conn *ct,
		    enum nf_nat_manip_type maniptype)
{
	__be32 *var_ipp;
	/* Host order */
	u_int32_t minip, maxip, j;

	/* No IP mapping?  Do nothing. */
	if (!(range->flags & NF_NAT_RANGE_MAP_IPS))
		return;

	if (maniptype == NF_NAT_MANIP_SRC)
		var_ipp = &tuple->src.u3.ip;
	else
		var_ipp = &tuple->dst.u3.ip;

	/* Fast path: only one choice. */
	if (range->min_ip == range->max_ip) {
		*var_ipp = range->min_ip;
		return;
	}

	/* Hashing source and destination IPs gives a fairly even
	 * spread in practice (if there are a small number of IPs
	 * involved, there usually aren't that many connections
	 * anyway).  The consistency means that servers see the same
	 * client coming from the same IP (some Internet Banking sites
	 * like this), even across reboots. */
	minip = ntohl(range->min_ip);
	maxip = ntohl(range->max_ip);
	j = jhash_2words((__force u32)tuple->src.u3.ip,
			 range->flags & NF_NAT_RANGE_PERSISTENT ?
				0 : (__force u32)tuple->dst.u3.ip ^ zone, 0);
	j = ((u64)j * (maxip - minip + 1)) >> 32;
	*var_ipp = htonl(minip + j);
}

/* Manipulate the tuple into the range given.  For NF_INET_POST_ROUTING,
 * we change the source to map into the range.  For NF_INET_PRE_ROUTING
 * and NF_INET_LOCAL_OUT, we change the destination to map into the
 * range.  It might not be possible to get a unique tuple, but we try.
 * At worst (or if we race), we will end up with a final duplicate in
 * __ip_conntrack_confirm and drop the packet. */
static void
get_unique_tuple(struct nf_conntrack_tuple *tuple,
		 const struct nf_conntrack_tuple *orig_tuple,
		 const struct nf_nat_ipv4_range *range,
		 struct nf_conn *ct,
		 enum nf_nat_manip_type maniptype)
{
	struct net *net = nf_ct_net(ct);
	const struct nf_nat_protocol *proto;
	u16 zone = nf_ct_zone(ct);

	/* 1) If this srcip/proto/src-proto-part is currently mapped,
	   and that same mapping gives a unique tuple within the given
	   range, use that.

	   This is only required for source (ie. NAT/masq) mappings.
	   So far, we don't do local source mappings, so multiple
	   manips not an issue.  */
	if (maniptype == NF_NAT_MANIP_SRC &&
	    !(range->flags & NF_NAT_RANGE_PROTO_RANDOM)) {
		/* try the original tuple first */
		if (in_range(orig_tuple, range)) {
			if (!nf_nat_used_tuple(orig_tuple, ct)) {
				*tuple = *orig_tuple;
				return;
			}
		} else if (find_appropriate_src(net, zone, orig_tuple, tuple,
			   range)) {
			pr_debug("get_unique_tuple: Found current src map\n");
			if (!nf_nat_used_tuple(tuple, ct))
				return;
		}
	}

	/* 2) Select the least-used IP/proto combination in the given
	   range. */
	*tuple = *orig_tuple;
	find_best_ips_proto(zone, tuple, range, ct, maniptype);

	/* 3) The per-protocol part of the manip is made to map into
	   the range to make a unique tuple. */

	rcu_read_lock();
	proto = __nf_nat_proto_find(orig_tuple->dst.protonum);

	/* Only bother mapping if it's not already in range and unique */
	if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM)) {
		if (range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) {
			if (proto->in_range(tuple, maniptype, &range->min,
					    &range->max) &&
			    (range->min.all == range->max.all ||
			     !nf_nat_used_tuple(tuple, ct)))
				goto out;
		} else if (!nf_nat_used_tuple(tuple, ct)) {
			goto out;
		}
	}

	/* Last change: get protocol to try to obtain unique tuple. */
	proto->unique_tuple(tuple, range, maniptype, ct);
out:
	rcu_read_unlock();
}

unsigned int
nf_nat_setup_info(struct nf_conn *ct,
		  const struct nf_nat_ipv4_range *range,
		  enum nf_nat_manip_type maniptype)
{
	struct net *net = nf_ct_net(ct);
	struct nf_conntrack_tuple curr_tuple, new_tuple;
	struct nf_conn_nat *nat;

	/* nat helper or nfctnetlink also setup binding */
	nat = nfct_nat(ct);
	if (!nat) {
		nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC);
		if (nat == NULL) {
			pr_debug("failed to add NAT extension\n");
			return NF_ACCEPT;
		}
	}

	NF_CT_ASSERT(maniptype == NF_NAT_MANIP_SRC ||
		     maniptype == NF_NAT_MANIP_DST);
	BUG_ON(nf_nat_initialized(ct, maniptype));

	/* What we've got will look like inverse of reply. Normally
	   this is what is in the conntrack, except for prior
	   manipulations (future optimization: if num_manips == 0,
	   orig_tp =
	   conntrack->tuplehash[IP_CT_DIR_ORIGINAL].tuple) */
	nf_ct_invert_tuplepr(&curr_tuple,
			     &ct->tuplehash[IP_CT_DIR_REPLY].tuple);

	get_unique_tuple(&new_tuple, &curr_tuple, range, ct, maniptype);

	if (!nf_ct_tuple_equal(&new_tuple, &curr_tuple)) {
		struct nf_conntrack_tuple reply;

		/* Alter conntrack table so will recognize replies. */
		nf_ct_invert_tuplepr(&reply, &new_tuple);
		nf_conntrack_alter_reply(ct, &reply);

		/* Non-atomic: we own this at the moment. */
		if (maniptype == NF_NAT_MANIP_SRC)
			ct->status |= IPS_SRC_NAT;
		else
			ct->status |= IPS_DST_NAT;
	}

	if (maniptype == NF_NAT_MANIP_SRC) {
		unsigned int srchash;

		srchash = hash_by_src(net, nf_ct_zone(ct),
				      &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
		spin_lock_bh(&nf_nat_lock);
		/* nf_conntrack_alter_reply might re-allocate exntension aera */
		nat = nfct_nat(ct);
		nat->ct = ct;
		hlist_add_head_rcu(&nat->bysource,
				   &net->ipv4.nat_bysource[srchash]);
		spin_unlock_bh(&nf_nat_lock);
	}

	/* It's done. */
	if (maniptype == NF_NAT_MANIP_DST)
		ct->status |= IPS_DST_NAT_DONE;
	else
		ct->status |= IPS_SRC_NAT_DONE;

	return NF_ACCEPT;
}
EXPORT_SYMBOL(nf_nat_setup_info);

/* Returns true if succeeded. */
static bool
manip_pkt(u_int16_t proto,
	  struct sk_buff *skb,
	  unsigned int iphdroff,
	  const struct nf_conntrack_tuple *target,
	  enum nf_nat_manip_type maniptype)
{
	struct iphdr *iph;
	const struct nf_nat_protocol *p;

	if (!skb_make_writable(skb, iphdroff + sizeof(*iph)))
		return false;

	iph = (void *)skb->data + iphdroff;

	/* Manipulate protcol part. */

	/* rcu_read_lock()ed by nf_hook_slow */
	p = __nf_nat_proto_find(proto);
	if (!p->manip_pkt(skb, iphdroff, target, maniptype))
		return false;

	iph = (void *)skb->data + iphdroff;

	if (maniptype == NF_NAT_MANIP_SRC) {
		csum_replace4(&iph->check, iph->saddr, target->src.u3.ip);
		iph->saddr = target->src.u3.ip;
	} else {
		csum_replace4(&iph->check, iph->daddr, target->dst.u3.ip);
		iph->daddr = target->dst.u3.ip;
	}
	return true;
}

/* Do packet manipulations according to nf_nat_setup_info. */
unsigned int nf_nat_packet(struct nf_conn *ct,
			   enum ip_conntrack_info ctinfo,
			   unsigned int hooknum,
			   struct sk_buff *skb)
{
	enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
	unsigned long statusbit;
	enum nf_nat_manip_type mtype = HOOK2MANIP(hooknum);

	if (mtype == NF_NAT_MANIP_SRC)
		statusbit = IPS_SRC_NAT;
	else
		statusbit = IPS_DST_NAT;

	/* Invert if this is reply dir. */
	if (dir == IP_CT_DIR_REPLY)
		statusbit ^= IPS_NAT_MASK;

	/* Non-atomic: these bits don't change. */
	if (ct->status & statusbit) {
		struct nf_conntrack_tuple target;

		/* We are aiming to look like inverse of other direction. */
		nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple);

		if (!manip_pkt(target.dst.protonum, skb, 0, &target, mtype))
			return NF_DROP;
	}
	return NF_ACCEPT;
}
EXPORT_SYMBOL_GPL(nf_nat_packet);

/* Dir is direction ICMP is coming from (opposite to packet it contains) */
int nf_nat_icmp_reply_translation(struct nf_conn *ct,
				  enum ip_conntrack_info ctinfo,
				  unsigned int hooknum,
				  struct sk_buff *skb)
{
	struct {
		struct icmphdr icmp;
		struct iphdr ip;
	} *inside;
	struct nf_conntrack_tuple target;
	int hdrlen = ip_hdrlen(skb);
	enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
	unsigned long statusbit;
	enum nf_nat_manip_type manip = HOOK2MANIP(hooknum);

	if (!skb_make_writable(skb, hdrlen + sizeof(*inside)))
		return 0;

	inside = (void *)skb->data + hdrlen;

	/* We're actually going to mangle it beyond trivial checksum
	   adjustment, so make sure the current checksum is correct. */
	if (nf_ip_checksum(skb, hooknum, hdrlen, 0))
		return 0;

	/* Must be RELATED */
	NF_CT_ASSERT(skb->nfctinfo == IP_CT_RELATED ||
		     skb->nfctinfo == IP_CT_RELATED_REPLY);

	/* Redirects on non-null nats must be dropped, else they'll
	   start talking to each other without our translation, and be
	   confused... --RR */
	if (inside->icmp.type == ICMP_REDIRECT) {
		/* If NAT isn't finished, assume it and drop. */
		if ((ct->status & IPS_NAT_DONE_MASK) != IPS_NAT_DONE_MASK)
			return 0;

		if (ct->status & IPS_NAT_MASK)
			return 0;
	}

	if (manip == NF_NAT_MANIP_SRC)
		statusbit = IPS_SRC_NAT;
	else
		statusbit = IPS_DST_NAT;

	/* Invert if this is reply dir. */
	if (dir == IP_CT_DIR_REPLY)
		statusbit ^= IPS_NAT_MASK;

	if (!(ct->status & statusbit))
		return 1;

	pr_debug("icmp_reply_translation: translating error %p manip %u "
		 "dir %s\n", skb, manip,
		 dir == IP_CT_DIR_ORIGINAL ? "ORIG" : "REPLY");

	/* Change inner back to look like incoming packet.  We do the
	   opposite manip on this hook to normal, because it might not
	   pass all hooks (locally-generated ICMP).  Consider incoming
	   packet: PREROUTING (DST manip), routing produces ICMP, goes
	   through POSTROUTING (which must correct the DST manip). */
	if (!manip_pkt(inside->ip.protocol, skb, hdrlen + sizeof(inside->icmp),
		       &ct->tuplehash[!dir].tuple, !manip))
		return 0;

	if (skb->ip_summed != CHECKSUM_PARTIAL) {
		/* Reloading "inside" here since manip_pkt inner. */
		inside = (void *)skb->data + hdrlen;
		inside->icmp.checksum = 0;
		inside->icmp.checksum =
			csum_fold(skb_checksum(skb, hdrlen,
					       skb->len - hdrlen, 0));
	}

	/* Change outer to look the reply to an incoming packet
	 * (proto 0 means don't invert per-proto part). */
	nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple);
	if (!manip_pkt(0, skb, 0, &target, manip))
		return 0;

	return 1;
}
EXPORT_SYMBOL_GPL(nf_nat_icmp_reply_translation);

/* Protocol registration. */
int nf_nat_protocol_register(const struct nf_nat_protocol *proto)
{
	int ret = 0;

	spin_lock_bh(&nf_nat_lock);
	if (rcu_dereference_protected(
			nf_nat_protos[proto->protonum],
			lockdep_is_held(&nf_nat_lock)
			) != &nf_nat_unknown_protocol) {
		ret = -EBUSY;
		goto out;
	}
	RCU_INIT_POINTER(nf_nat_protos[proto->protonum], proto);
 out:
	spin_unlock_bh(&nf_nat_lock);
	return ret;
}
EXPORT_SYMBOL(nf_nat_protocol_register);

/* No one stores the protocol anywhere; simply delete it. */
void nf_nat_protocol_unregister(const struct nf_nat_protocol *proto)
{
	spin_lock_bh(&nf_nat_lock);
	RCU_INIT_POINTER(nf_nat_protos[proto->protonum],
			   &nf_nat_unknown_protocol);
	spin_unlock_bh(&nf_nat_lock);
	synchronize_rcu();
}
EXPORT_SYMBOL(nf_nat_protocol_unregister);

/* No one using conntrack by the time this called. */
static void nf_nat_cleanup_conntrack(struct nf_conn *ct)
{
	struct nf_conn_nat *nat = nf_ct_ext_find(ct, NF_CT_EXT_NAT);

	if (nat == NULL || nat->ct == NULL)
		return;

	NF_CT_ASSERT(nat->ct->status & IPS_SRC_NAT_DONE);

	spin_lock_bh(&nf_nat_lock);
	hlist_del_rcu(&nat->bysource);
	spin_unlock_bh(&nf_nat_lock);
}

static void nf_nat_move_storage(void *new, void *old)
{
	struct nf_conn_nat *new_nat = new;
	struct nf_conn_nat *old_nat = old;
	struct nf_conn *ct = old_nat->ct;

	if (!ct || !(ct->status & IPS_SRC_NAT_DONE))
		return;

	spin_lock_bh(&nf_nat_lock);
	hlist_replace_rcu(&old_nat->bysource, &new_nat->bysource);
	spin_unlock_bh(&nf_nat_lock);
}

static struct nf_ct_ext_type nat_extend __read_mostly = {
	.len		= sizeof(struct nf_conn_nat),
	.align		= __alignof__(struct nf_conn_nat),
	.destroy	= nf_nat_cleanup_conntrack,
	.move		= nf_nat_move_storage,
	.id		= NF_CT_EXT_NAT,
	.flags		= NF_CT_EXT_F_PREALLOC,
};

#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)

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

static const struct nla_policy protonat_nla_policy[CTA_PROTONAT_MAX+1] = {
	[CTA_PROTONAT_PORT_MIN]	= { .type = NLA_U16 },
	[CTA_PROTONAT_PORT_MAX]	= { .type = NLA_U16 },
};

static int nfnetlink_parse_nat_proto(struct nlattr *attr,
				     const struct nf_conn *ct,
				     struct nf_nat_ipv4_range *range)
{
	struct nlattr *tb[CTA_PROTONAT_MAX+1];
	const struct nf_nat_protocol *npt;
	int err;

	err = nla_parse_nested(tb, CTA_PROTONAT_MAX, attr, protonat_nla_policy);
	if (err < 0)
		return err;

	rcu_read_lock();
	npt = __nf_nat_proto_find(nf_ct_protonum(ct));
	if (npt->nlattr_to_range)
		err = npt->nlattr_to_range(tb, range);
	rcu_read_unlock();
	return err;
}

static const struct nla_policy nat_nla_policy[CTA_NAT_MAX+1] = {
	[CTA_NAT_MINIP]		= { .type = NLA_U32 },
	[CTA_NAT_MAXIP]		= { .type = NLA_U32 },
	[CTA_NAT_PROTO]		= { .type = NLA_NESTED },
};

static int
nfnetlink_parse_nat(const struct nlattr *nat,
		    const struct nf_conn *ct, struct nf_nat_ipv4_range *range)
{
	struct nlattr *tb[CTA_NAT_MAX+1];
	int err;

	memset(range, 0, sizeof(*range));

	err = nla_parse_nested(tb, CTA_NAT_MAX, nat, nat_nla_policy);
	if (err < 0)
		return err;

	if (tb[CTA_NAT_MINIP])
		range->min_ip = nla_get_be32(tb[CTA_NAT_MINIP]);

	if (!tb[CTA_NAT_MAXIP])
		range->max_ip = range->min_ip;
	else
		range->max_ip = nla_get_be32(tb[CTA_NAT_MAXIP]);

	if (range->min_ip)
		range->flags |= NF_NAT_RANGE_MAP_IPS;

	if (!tb[CTA_NAT_PROTO])
		return 0;

	err = nfnetlink_parse_nat_proto(tb[CTA_NAT_PROTO], ct, range);
	if (err < 0)
		return err;

	return 0;
}

static int
nfnetlink_parse_nat_setup(struct nf_conn *ct,
			  enum nf_nat_manip_type manip,
			  const struct nlattr *attr)
{
	struct nf_nat_ipv4_range range;

	if (nfnetlink_parse_nat(attr, ct, &range) < 0)
		return -EINVAL;
	if (nf_nat_initialized(ct, manip))
		return -EEXIST;

	return nf_nat_setup_info(ct, &range, manip);
}
#else
static int
nfnetlink_parse_nat_setup(struct nf_conn *ct,
			  enum nf_nat_manip_type manip,
			  const struct nlattr *attr)
{
	return -EOPNOTSUPP;
}
#endif

static int __net_init nf_nat_net_init(struct net *net)
{
	/* Leave them the same for the moment. */
	net->ipv4.nat_htable_size = net->ct.htable_size;
	net->ipv4.nat_bysource = nf_ct_alloc_hashtable(&net->ipv4.nat_htable_size, 0);
	if (!net->ipv4.nat_bysource)
		return -ENOMEM;
	return 0;
}

/* Clear NAT section of all conntracks, in case we're loaded again. */
static int clean_nat(struct nf_conn *i, void *data)
{
	struct nf_conn_nat *nat = nfct_nat(i);

	if (!nat)
		return 0;
	memset(nat, 0, sizeof(*nat));
	i->status &= ~(IPS_NAT_MASK | IPS_NAT_DONE_MASK | IPS_SEQ_ADJUST);
	return 0;
}

static void __net_exit nf_nat_net_exit(struct net *net)
{
	nf_ct_iterate_cleanup(net, &clean_nat, NULL);
	synchronize_rcu();
	nf_ct_free_hashtable(net->ipv4.nat_bysource, net->ipv4.nat_htable_size);
}

static struct pernet_operations nf_nat_net_ops = {
	.init = nf_nat_net_init,
	.exit = nf_nat_net_exit,
};

static int __init nf_nat_init(void)
{
	size_t i;
	int ret;

	need_ipv4_conntrack();

	ret = nf_ct_extend_register(&nat_extend);
	if (ret < 0) {
		printk(KERN_ERR "nf_nat_core: Unable to register extension\n");
		return ret;
	}

	ret = register_pernet_subsys(&nf_nat_net_ops);
	if (ret < 0)
		goto cleanup_extend;

	/* Sew in builtin protocols. */
	spin_lock_bh(&nf_nat_lock);
	for (i = 0; i < MAX_IP_NAT_PROTO; i++)
		RCU_INIT_POINTER(nf_nat_protos[i], &nf_nat_unknown_protocol);
	RCU_INIT_POINTER(nf_nat_protos[IPPROTO_TCP], &nf_nat_protocol_tcp);
	RCU_INIT_POINTER(nf_nat_protos[IPPROTO_UDP], &nf_nat_protocol_udp);
	RCU_INIT_POINTER(nf_nat_protos[IPPROTO_ICMP], &nf_nat_protocol_icmp);
	spin_unlock_bh(&nf_nat_lock);

	/* Initialize fake conntrack so that NAT will skip it */
	nf_ct_untracked_status_or(IPS_NAT_DONE_MASK);

	l3proto = nf_ct_l3proto_find_get((u_int16_t)AF_INET);

	BUG_ON(nf_nat_seq_adjust_hook != NULL);
	RCU_INIT_POINTER(nf_nat_seq_adjust_hook, nf_nat_seq_adjust);
	BUG_ON(nfnetlink_parse_nat_setup_hook != NULL);
	RCU_INIT_POINTER(nfnetlink_parse_nat_setup_hook,
			   nfnetlink_parse_nat_setup);
	BUG_ON(nf_ct_nat_offset != NULL);
	RCU_INIT_POINTER(nf_ct_nat_offset, nf_nat_get_offset);
	return 0;

 cleanup_extend:
	nf_ct_extend_unregister(&nat_extend);
	return ret;
}

static void __exit nf_nat_cleanup(void)
{
	unregister_pernet_subsys(&nf_nat_net_ops);
	nf_ct_l3proto_put(l3proto);
	nf_ct_extend_unregister(&nat_extend);
	RCU_INIT_POINTER(nf_nat_seq_adjust_hook, NULL);
	RCU_INIT_POINTER(nfnetlink_parse_nat_setup_hook, NULL);
	RCU_INIT_POINTER(nf_ct_nat_offset, NULL);
	synchronize_net();
}

MODULE_LICENSE("GPL");
MODULE_ALIAS("nf-nat-ipv4");

module_init(nf_nat_init);
module_exit(nf_nat_cleanup);