summaryrefslogtreecommitdiff
path: root/net/ipv6/ipv6_sockglue.c
blob: 7516b8829a9dd3724d8d52c4353bea9705e9f777 (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
/*
 *	IPv6 BSD socket options interface
 *	Linux INET6 implementation 
 *
 *	Authors:
 *	Pedro Roque		<roque@di.fc.ul.pt>	
 *
 *	Based on linux/net/ipv4/ip_sockglue.c
 *
 *	$Id: ipv6_sockglue.c,v 1.41 2002/02/01 22:01:04 davem Exp $
 *
 *	This program is free software; you can redistribute it and/or
 *      modify it under the terms of the GNU General Public License
 *      as published by the Free Software Foundation; either version
 *      2 of the License, or (at your option) any later version.
 *
 *	FIXME: Make the setsockopt code POSIX compliant: That is
 *
 *	o	Return -EINVAL for setsockopt of short lengths
 *	o	Truncate getsockopt returns
 *	o	Return an optlen of the truncated length if need be
 *
 *	Changes:
 *	David L Stevens <dlstevens@us.ibm.com>:
 *		- added multicast source filtering API for MLDv2
 */

#include <linux/module.h>
#include <linux/config.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/sched.h>
#include <linux/net.h>
#include <linux/in6.h>
#include <linux/netdevice.h>
#include <linux/if_arp.h>
#include <linux/init.h>
#include <linux/sysctl.h>
#include <linux/netfilter.h>

#include <net/sock.h>
#include <net/snmp.h>
#include <net/ipv6.h>
#include <net/ndisc.h>
#include <net/protocol.h>
#include <net/transp_v6.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
#include <net/inet_common.h>
#include <net/tcp.h>
#include <net/udp.h>
#include <net/xfrm.h>

#include <asm/uaccess.h>

DEFINE_SNMP_STAT(struct ipstats_mib, ipv6_statistics);

static struct packet_type ipv6_packet_type = {
	.type = __constant_htons(ETH_P_IPV6), 
	.func = ipv6_rcv,
};

struct ip6_ra_chain *ip6_ra_chain;
DEFINE_RWLOCK(ip6_ra_lock);

int ip6_ra_control(struct sock *sk, int sel, void (*destructor)(struct sock *))
{
	struct ip6_ra_chain *ra, *new_ra, **rap;

	/* RA packet may be delivered ONLY to IPPROTO_RAW socket */
	if (sk->sk_type != SOCK_RAW || inet_sk(sk)->num != IPPROTO_RAW)
		return -EINVAL;

	new_ra = (sel>=0) ? kmalloc(sizeof(*new_ra), GFP_KERNEL) : NULL;

	write_lock_bh(&ip6_ra_lock);
	for (rap = &ip6_ra_chain; (ra=*rap) != NULL; rap = &ra->next) {
		if (ra->sk == sk) {
			if (sel>=0) {
				write_unlock_bh(&ip6_ra_lock);
				if (new_ra)
					kfree(new_ra);
				return -EADDRINUSE;
			}

			*rap = ra->next;
			write_unlock_bh(&ip6_ra_lock);

			if (ra->destructor)
				ra->destructor(sk);
			sock_put(sk);
			kfree(ra);
			return 0;
		}
	}
	if (new_ra == NULL) {
		write_unlock_bh(&ip6_ra_lock);
		return -ENOBUFS;
	}
	new_ra->sk = sk;
	new_ra->sel = sel;
	new_ra->destructor = destructor;
	new_ra->next = ra;
	*rap = new_ra;
	sock_hold(sk);
	write_unlock_bh(&ip6_ra_lock);
	return 0;
}

int ipv6_setsockopt(struct sock *sk, int level, int optname,
		    char __user *optval, int optlen)
{
	struct ipv6_pinfo *np = inet6_sk(sk);
	int val, valbool;
	int retv = -ENOPROTOOPT;

	if (level == SOL_IP && sk->sk_type != SOCK_RAW)
		return udp_prot.setsockopt(sk, level, optname, optval, optlen);

	if(level!=SOL_IPV6)
		goto out;

	if (optval == NULL)
		val=0;
	else if (get_user(val, (int __user *) optval))
		return -EFAULT;

	valbool = (val!=0);

	lock_sock(sk);

	switch (optname) {

	case IPV6_ADDRFORM:
		if (val == PF_INET) {
			struct ipv6_txoptions *opt;
			struct sk_buff *pktopt;

			if (sk->sk_protocol != IPPROTO_UDP &&
			    sk->sk_protocol != IPPROTO_TCP)
				break;

			if (sk->sk_state != TCP_ESTABLISHED) {
				retv = -ENOTCONN;
				break;
			}

			if (ipv6_only_sock(sk) ||
			    !(ipv6_addr_type(&np->daddr) & IPV6_ADDR_MAPPED)) {
				retv = -EADDRNOTAVAIL;
				break;
			}

			fl6_free_socklist(sk);
			ipv6_sock_mc_close(sk);

			/*
			 * Sock is moving from IPv6 to IPv4 (sk_prot), so
			 * remove it from the refcnt debug socks count in the
			 * original family...
			 */
			sk_refcnt_debug_dec(sk);

			if (sk->sk_protocol == IPPROTO_TCP) {
				struct tcp_sock *tp = tcp_sk(sk);

				local_bh_disable();
				sock_prot_dec_use(sk->sk_prot);
				sock_prot_inc_use(&tcp_prot);
				local_bh_enable();
				sk->sk_prot = &tcp_prot;
				tp->af_specific = &ipv4_specific;
				sk->sk_socket->ops = &inet_stream_ops;
				sk->sk_family = PF_INET;
				tcp_sync_mss(sk, tp->pmtu_cookie);
			} else {
				local_bh_disable();
				sock_prot_dec_use(sk->sk_prot);
				sock_prot_inc_use(&udp_prot);
				local_bh_enable();
				sk->sk_prot = &udp_prot;
				sk->sk_socket->ops = &inet_dgram_ops;
				sk->sk_family = PF_INET;
			}
			opt = xchg(&np->opt, NULL);
			if (opt)
				sock_kfree_s(sk, opt, opt->tot_len);
			pktopt = xchg(&np->pktoptions, NULL);
			if (pktopt)
				kfree_skb(pktopt);

			sk->sk_destruct = inet_sock_destruct;
			/*
			 * ... and add it to the refcnt debug socks count
			 * in the new family. -acme
			 */
			sk_refcnt_debug_inc(sk);
			module_put(THIS_MODULE);
			retv = 0;
			break;
		}
		goto e_inval;

	case IPV6_V6ONLY:
		if (inet_sk(sk)->num)
			goto e_inval;
		np->ipv6only = valbool;
		retv = 0;
		break;

	case IPV6_PKTINFO:
		np->rxopt.bits.rxinfo = valbool;
		retv = 0;
		break;

	case IPV6_HOPLIMIT:
		np->rxopt.bits.rxhlim = valbool;
		retv = 0;
		break;

	case IPV6_RTHDR:
		if (val < 0 || val > 2)
			goto e_inval;
		np->rxopt.bits.srcrt = val;
		retv = 0;
		break;

	case IPV6_HOPOPTS:
		np->rxopt.bits.hopopts = valbool;
		retv = 0;
		break;

	case IPV6_DSTOPTS:
		np->rxopt.bits.dstopts = valbool;
		retv = 0;
		break;

	case IPV6_FLOWINFO:
		np->rxopt.bits.rxflow = valbool;
		retv = 0;
		break;

	case IPV6_PKTOPTIONS:
	{
		struct ipv6_txoptions *opt = NULL;
		struct msghdr msg;
		struct flowi fl;
		int junk;

		fl.fl6_flowlabel = 0;
		fl.oif = sk->sk_bound_dev_if;

		if (optlen == 0)
			goto update;

		/* 1K is probably excessive
		 * 1K is surely not enough, 2K per standard header is 16K.
		 */
		retv = -EINVAL;
		if (optlen > 64*1024)
			break;

		opt = sock_kmalloc(sk, sizeof(*opt) + optlen, GFP_KERNEL);
		retv = -ENOBUFS;
		if (opt == NULL)
			break;

		memset(opt, 0, sizeof(*opt));
		opt->tot_len = sizeof(*opt) + optlen;
		retv = -EFAULT;
		if (copy_from_user(opt+1, optval, optlen))
			goto done;

		msg.msg_controllen = optlen;
		msg.msg_control = (void*)(opt+1);

		retv = datagram_send_ctl(&msg, &fl, opt, &junk);
		if (retv)
			goto done;
update:
		retv = 0;
		if (sk->sk_type == SOCK_STREAM) {
			if (opt) {
				struct tcp_sock *tp = tcp_sk(sk);
				if (!((1 << sk->sk_state) &
				      (TCPF_LISTEN | TCPF_CLOSE))
				    && inet_sk(sk)->daddr != LOOPBACK4_IPV6) {
					tp->ext_header_len = opt->opt_flen + opt->opt_nflen;
					tcp_sync_mss(sk, tp->pmtu_cookie);
				}
			}
			opt = xchg(&np->opt, opt);
			sk_dst_reset(sk);
		} else {
			write_lock(&sk->sk_dst_lock);
			opt = xchg(&np->opt, opt);
			write_unlock(&sk->sk_dst_lock);
			sk_dst_reset(sk);
		}

done:
		if (opt)
			sock_kfree_s(sk, opt, opt->tot_len);
		break;
	}
	case IPV6_UNICAST_HOPS:
		if (val > 255 || val < -1)
			goto e_inval;
		np->hop_limit = val;
		retv = 0;
		break;

	case IPV6_MULTICAST_HOPS:
		if (sk->sk_type == SOCK_STREAM)
			goto e_inval;
		if (val > 255 || val < -1)
			goto e_inval;
		np->mcast_hops = val;
		retv = 0;
		break;

	case IPV6_MULTICAST_LOOP:
		np->mc_loop = valbool;
		retv = 0;
		break;

	case IPV6_MULTICAST_IF:
		if (sk->sk_type == SOCK_STREAM)
			goto e_inval;
		if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != val)
			goto e_inval;

		if (__dev_get_by_index(val) == NULL) {
			retv = -ENODEV;
			break;
		}
		np->mcast_oif = val;
		retv = 0;
		break;
	case IPV6_ADD_MEMBERSHIP:
	case IPV6_DROP_MEMBERSHIP:
	{
		struct ipv6_mreq mreq;

		retv = -EFAULT;
		if (copy_from_user(&mreq, optval, sizeof(struct ipv6_mreq)))
			break;

		if (optname == IPV6_ADD_MEMBERSHIP)
			retv = ipv6_sock_mc_join(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_multiaddr);
		else
			retv = ipv6_sock_mc_drop(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_multiaddr);
		break;
	}
	case IPV6_JOIN_ANYCAST:
	case IPV6_LEAVE_ANYCAST:
	{
		struct ipv6_mreq mreq;

		if (optlen != sizeof(struct ipv6_mreq))
			goto e_inval;

		retv = -EFAULT;
		if (copy_from_user(&mreq, optval, sizeof(struct ipv6_mreq)))
			break;

		if (optname == IPV6_JOIN_ANYCAST)
			retv = ipv6_sock_ac_join(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_acaddr);
		else
			retv = ipv6_sock_ac_drop(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_acaddr);
		break;
	}
	case MCAST_JOIN_GROUP:
	case MCAST_LEAVE_GROUP:
	{
		struct group_req greq;
		struct sockaddr_in6 *psin6;

		retv = -EFAULT;
		if (copy_from_user(&greq, optval, sizeof(struct group_req)))
			break;
		if (greq.gr_group.ss_family != AF_INET6) {
			retv = -EADDRNOTAVAIL;
			break;
		}
		psin6 = (struct sockaddr_in6 *)&greq.gr_group;
		if (optname == MCAST_JOIN_GROUP)
			retv = ipv6_sock_mc_join(sk, greq.gr_interface,
				&psin6->sin6_addr);
		else
			retv = ipv6_sock_mc_drop(sk, greq.gr_interface,
				&psin6->sin6_addr);
		break;
	}
	case MCAST_JOIN_SOURCE_GROUP:
	case MCAST_LEAVE_SOURCE_GROUP:
	case MCAST_BLOCK_SOURCE:
	case MCAST_UNBLOCK_SOURCE:
	{
		struct group_source_req greqs;
		int omode, add;

		if (optlen != sizeof(struct group_source_req))
			goto e_inval;
		if (copy_from_user(&greqs, optval, sizeof(greqs))) {
			retv = -EFAULT;
			break;
		}
		if (greqs.gsr_group.ss_family != AF_INET6 ||
		    greqs.gsr_source.ss_family != AF_INET6) {
			retv = -EADDRNOTAVAIL;
			break;
		}
		if (optname == MCAST_BLOCK_SOURCE) {
			omode = MCAST_EXCLUDE;
			add = 1;
		} else if (optname == MCAST_UNBLOCK_SOURCE) {
			omode = MCAST_EXCLUDE;
			add = 0;
		} else if (optname == MCAST_JOIN_SOURCE_GROUP) {
			struct sockaddr_in6 *psin6;

			psin6 = (struct sockaddr_in6 *)&greqs.gsr_group;
			retv = ipv6_sock_mc_join(sk, greqs.gsr_interface,
				&psin6->sin6_addr);
			/* prior join w/ different source is ok */
			if (retv && retv != -EADDRINUSE)
				break;
			omode = MCAST_INCLUDE;
			add = 1;
		} else /* MCAST_LEAVE_SOURCE_GROUP */ {
			omode = MCAST_INCLUDE;
			add = 0;
		}
		retv = ip6_mc_source(add, omode, sk, &greqs);
		break;
	}
	case MCAST_MSFILTER:
	{
		extern int sysctl_mld_max_msf;
		struct group_filter *gsf;

		if (optlen < GROUP_FILTER_SIZE(0))
			goto e_inval;
		if (optlen > sysctl_optmem_max) {
			retv = -ENOBUFS;
			break;
		}
		gsf = (struct group_filter *)kmalloc(optlen,GFP_KERNEL);
		if (gsf == 0) {
			retv = -ENOBUFS;
			break;
		}
		retv = -EFAULT;
		if (copy_from_user(gsf, optval, optlen)) {
			kfree(gsf);
			break;
		}
		/* numsrc >= (4G-140)/128 overflow in 32 bits */
		if (gsf->gf_numsrc >= 0x1ffffffU ||
		    gsf->gf_numsrc > sysctl_mld_max_msf) {
			kfree(gsf);
			retv = -ENOBUFS;
			break;
		}
		if (GROUP_FILTER_SIZE(gsf->gf_numsrc) > optlen) {
			kfree(gsf);
			retv = -EINVAL;
			break;
		}
		retv = ip6_mc_msfilter(sk, gsf);
		kfree(gsf);

		break;
	}
	case IPV6_ROUTER_ALERT:
		retv = ip6_ra_control(sk, val, NULL);
		break;
	case IPV6_MTU_DISCOVER:
		if (val<0 || val>2)
			goto e_inval;
		np->pmtudisc = val;
		retv = 0;
		break;
	case IPV6_MTU:
		if (val && val < IPV6_MIN_MTU)
			goto e_inval;
		np->frag_size = val;
		retv = 0;
		break;
	case IPV6_RECVERR:
		np->recverr = valbool;
		if (!val)
			skb_queue_purge(&sk->sk_error_queue);
		retv = 0;
		break;
	case IPV6_FLOWINFO_SEND:
		np->sndflow = valbool;
		retv = 0;
		break;
	case IPV6_FLOWLABEL_MGR:
		retv = ipv6_flowlabel_opt(sk, optval, optlen);
		break;
	case IPV6_IPSEC_POLICY:
	case IPV6_XFRM_POLICY:
		retv = -EPERM;
		if (!capable(CAP_NET_ADMIN))
			break;
		retv = xfrm_user_policy(sk, optname, optval, optlen);
		break;

#ifdef CONFIG_NETFILTER
	default:
		retv = nf_setsockopt(sk, PF_INET6, optname, optval, 
					    optlen);
		break;
#endif

	}
	release_sock(sk);

out:
	return retv;

e_inval:
	release_sock(sk);
	return -EINVAL;
}

int ipv6_getsockopt(struct sock *sk, int level, int optname,
		    char __user *optval, int __user *optlen)
{
	struct ipv6_pinfo *np = inet6_sk(sk);
	int len;
	int val;

	if (level == SOL_IP && sk->sk_type != SOCK_RAW)
		return udp_prot.getsockopt(sk, level, optname, optval, optlen);
	if(level!=SOL_IPV6)
		return -ENOPROTOOPT;
	if (get_user(len, optlen))
		return -EFAULT;
	switch (optname) {
	case IPV6_ADDRFORM:
		if (sk->sk_protocol != IPPROTO_UDP &&
		    sk->sk_protocol != IPPROTO_TCP)
			return -EINVAL;
		if (sk->sk_state != TCP_ESTABLISHED)
			return -ENOTCONN;
		val = sk->sk_family;
		break;
	case MCAST_MSFILTER:
	{
		struct group_filter gsf;
		int err;

		if (len < GROUP_FILTER_SIZE(0))
			return -EINVAL;
		if (copy_from_user(&gsf, optval, GROUP_FILTER_SIZE(0)))
			return -EFAULT;
		lock_sock(sk);
		err = ip6_mc_msfget(sk, &gsf,
			(struct group_filter __user *)optval, optlen);
		release_sock(sk);
		return err;
	}

	case IPV6_PKTOPTIONS:
	{
		struct msghdr msg;
		struct sk_buff *skb;

		if (sk->sk_type != SOCK_STREAM)
			return -ENOPROTOOPT;

		msg.msg_control = optval;
		msg.msg_controllen = len;
		msg.msg_flags = 0;

		lock_sock(sk);
		skb = np->pktoptions;
		if (skb)
			atomic_inc(&skb->users);
		release_sock(sk);

		if (skb) {
			int err = datagram_recv_ctl(sk, &msg, skb);
			kfree_skb(skb);
			if (err)
				return err;
		} else {
			if (np->rxopt.bits.rxinfo) {
				struct in6_pktinfo src_info;
				src_info.ipi6_ifindex = np->mcast_oif;
				ipv6_addr_copy(&src_info.ipi6_addr, &np->daddr);
				put_cmsg(&msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info);
			}
			if (np->rxopt.bits.rxhlim) {
				int hlim = np->mcast_hops;
				put_cmsg(&msg, SOL_IPV6, IPV6_HOPLIMIT, sizeof(hlim), &hlim);
			}
		}
		len -= msg.msg_controllen;
		return put_user(len, optlen);
	}
	case IPV6_MTU:
	{
		struct dst_entry *dst;
		val = 0;	
		lock_sock(sk);
		dst = sk_dst_get(sk);
		if (dst) {
			val = dst_mtu(dst);
			dst_release(dst);
		}
		release_sock(sk);
		if (!val)
			return -ENOTCONN;
		break;
	}

	case IPV6_V6ONLY:
		val = np->ipv6only;
		break;

	case IPV6_PKTINFO:
		val = np->rxopt.bits.rxinfo;
		break;

	case IPV6_HOPLIMIT:
		val = np->rxopt.bits.rxhlim;
		break;

	case IPV6_RTHDR:
		val = np->rxopt.bits.srcrt;
		break;

	case IPV6_HOPOPTS:
		val = np->rxopt.bits.hopopts;
		break;

	case IPV6_DSTOPTS:
		val = np->rxopt.bits.dstopts;
		break;

	case IPV6_FLOWINFO:
		val = np->rxopt.bits.rxflow;
		break;

	case IPV6_UNICAST_HOPS:
		val = np->hop_limit;
		break;

	case IPV6_MULTICAST_HOPS:
		val = np->mcast_hops;
		break;

	case IPV6_MULTICAST_LOOP:
		val = np->mc_loop;
		break;

	case IPV6_MULTICAST_IF:
		val = np->mcast_oif;
		break;

	case IPV6_MTU_DISCOVER:
		val = np->pmtudisc;
		break;

	case IPV6_RECVERR:
		val = np->recverr;
		break;

	case IPV6_FLOWINFO_SEND:
		val = np->sndflow;
		break;

	default:
#ifdef CONFIG_NETFILTER
		lock_sock(sk);
		val = nf_getsockopt(sk, PF_INET6, optname, optval, 
				    &len);
		release_sock(sk);
		if (val >= 0)
			val = put_user(len, optlen);
		return val;
#else
		return -EINVAL;
#endif
	}
	len = min_t(unsigned int, sizeof(int), len);
	if(put_user(len, optlen))
		return -EFAULT;
	if(copy_to_user(optval,&val,len))
		return -EFAULT;
	return 0;
}

void __init ipv6_packet_init(void)
{
	dev_add_pack(&ipv6_packet_type);
}

void ipv6_packet_cleanup(void)
{
	dev_remove_pack(&ipv6_packet_type);
}