summaryrefslogtreecommitdiff
path: root/net/ipv6/datagram.c
blob: 01468fab3d3db103388f17d960d46e2f44f4e2f6 (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
/*
 *	common UDP/RAW code
 *	Linux INET6 implementation 
 *
 *	Authors:
 *	Pedro Roque		<roque@di.fc.ul.pt>	
 *
 *	$Id: datagram.c,v 1.24 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.
 */

#include <linux/errno.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/interrupt.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/in6.h>
#include <linux/ipv6.h>
#include <linux/route.h>

#include <net/ipv6.h>
#include <net/ndisc.h>
#include <net/addrconf.h>
#include <net/transp_v6.h>
#include <net/ip6_route.h>
#include <net/tcp_states.h>

#include <linux/errqueue.h>
#include <asm/uaccess.h>

int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
	struct sockaddr_in6	*usin = (struct sockaddr_in6 *) uaddr;
	struct inet_sock      	*inet = inet_sk(sk);
	struct ipv6_pinfo      	*np = inet6_sk(sk);
	struct in6_addr		*daddr, *final_p = NULL, final;
	struct dst_entry	*dst;
	struct flowi		fl;
	struct ip6_flowlabel	*flowlabel = NULL;
	int			addr_type;
	int			err;

	if (usin->sin6_family == AF_INET) {
		if (__ipv6_only_sock(sk))
			return -EAFNOSUPPORT;
		err = ip4_datagram_connect(sk, uaddr, addr_len);
		goto ipv4_connected;
	}

	if (addr_len < SIN6_LEN_RFC2133)
	  	return -EINVAL;

	if (usin->sin6_family != AF_INET6) 
	  	return -EAFNOSUPPORT;

	memset(&fl, 0, sizeof(fl));
	if (np->sndflow) {
		fl.fl6_flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK;
		if (fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) {
			flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel);
			if (flowlabel == NULL)
				return -EINVAL;
			ipv6_addr_copy(&usin->sin6_addr, &flowlabel->dst);
		}
	}

	addr_type = ipv6_addr_type(&usin->sin6_addr);

	if (addr_type == IPV6_ADDR_ANY) {
		/*
		 *	connect to self
		 */
		usin->sin6_addr.s6_addr[15] = 0x01;
	}

	daddr = &usin->sin6_addr;

	if (addr_type == IPV6_ADDR_MAPPED) {
		struct sockaddr_in sin;

		if (__ipv6_only_sock(sk)) {
			err = -ENETUNREACH;
			goto out;
		}
		sin.sin_family = AF_INET;
		sin.sin_addr.s_addr = daddr->s6_addr32[3];
		sin.sin_port = usin->sin6_port;

		err = ip4_datagram_connect(sk, 
					   (struct sockaddr*) &sin, 
					   sizeof(sin));

ipv4_connected:
		if (err)
			goto out;
		
		ipv6_addr_set(&np->daddr, 0, 0, htonl(0x0000ffff), inet->daddr);

		if (ipv6_addr_any(&np->saddr)) {
			ipv6_addr_set(&np->saddr, 0, 0, htonl(0x0000ffff),
				      inet->saddr);
		}

		if (ipv6_addr_any(&np->rcv_saddr)) {
			ipv6_addr_set(&np->rcv_saddr, 0, 0, htonl(0x0000ffff),
				      inet->rcv_saddr);
		}
		goto out;
	}

	if (addr_type&IPV6_ADDR_LINKLOCAL) {
		if (addr_len >= sizeof(struct sockaddr_in6) &&
		    usin->sin6_scope_id) {
			if (sk->sk_bound_dev_if &&
			    sk->sk_bound_dev_if != usin->sin6_scope_id) {
				err = -EINVAL;
				goto out;
			}
			sk->sk_bound_dev_if = usin->sin6_scope_id;
			if (!sk->sk_bound_dev_if &&
			    (addr_type & IPV6_ADDR_MULTICAST))
				fl.oif = np->mcast_oif;
		}

		/* Connect to link-local address requires an interface */
		if (!sk->sk_bound_dev_if) {
			err = -EINVAL;
			goto out;
		}
	}

	ipv6_addr_copy(&np->daddr, daddr);
	np->flow_label = fl.fl6_flowlabel;

	inet->dport = usin->sin6_port;

	/*
	 *	Check for a route to destination an obtain the
	 *	destination cache for it.
	 */

	fl.proto = sk->sk_protocol;
	ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
	ipv6_addr_copy(&fl.fl6_src, &np->saddr);
	fl.oif = sk->sk_bound_dev_if;
	fl.fl_ip_dport = inet->dport;
	fl.fl_ip_sport = inet->sport;

	if (!fl.oif && (addr_type&IPV6_ADDR_MULTICAST))
		fl.oif = np->mcast_oif;

	if (flowlabel) {
		if (flowlabel->opt && flowlabel->opt->srcrt) {
			struct rt0_hdr *rt0 = (struct rt0_hdr *) flowlabel->opt->srcrt;
			ipv6_addr_copy(&final, &fl.fl6_dst);
			ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
			final_p = &final;
		}
	} else if (np->opt && np->opt->srcrt) {
		struct rt0_hdr *rt0 = (struct rt0_hdr *)np->opt->srcrt;
		ipv6_addr_copy(&final, &fl.fl6_dst);
		ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
		final_p = &final;
	}

	err = ip6_dst_lookup(sk, &dst, &fl);
	if (err)
		goto out;
	if (final_p)
		ipv6_addr_copy(&fl.fl6_dst, final_p);

	if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) {
		dst_release(dst);
		goto out;
	}

	/* source address lookup done in ip6_dst_lookup */

	if (ipv6_addr_any(&np->saddr))
		ipv6_addr_copy(&np->saddr, &fl.fl6_src);

	if (ipv6_addr_any(&np->rcv_saddr)) {
		ipv6_addr_copy(&np->rcv_saddr, &fl.fl6_src);
		inet->rcv_saddr = LOOPBACK4_IPV6;
	}

	ip6_dst_store(sk, dst,
		      ipv6_addr_equal(&fl.fl6_dst, &np->daddr) ?
		      &np->daddr : NULL);

	sk->sk_state = TCP_ESTABLISHED;
out:
	fl6_sock_release(flowlabel);
	return err;
}

void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, 
		     u16 port, u32 info, u8 *payload)
{
	struct ipv6_pinfo *np  = inet6_sk(sk);
	struct icmp6hdr *icmph = (struct icmp6hdr *)skb->h.raw;
	struct sock_exterr_skb *serr;

	if (!np->recverr)
		return;

	skb = skb_clone(skb, GFP_ATOMIC);
	if (!skb)
		return;

	serr = SKB_EXT_ERR(skb);
	serr->ee.ee_errno = err;
	serr->ee.ee_origin = SO_EE_ORIGIN_ICMP6;
	serr->ee.ee_type = icmph->icmp6_type; 
	serr->ee.ee_code = icmph->icmp6_code;
	serr->ee.ee_pad = 0;
	serr->ee.ee_info = info;
	serr->ee.ee_data = 0;
	serr->addr_offset = (u8*)&(((struct ipv6hdr*)(icmph+1))->daddr) - skb->nh.raw;
	serr->port = port;

	skb->h.raw = payload;
	__skb_pull(skb, payload - skb->data);

	if (sock_queue_err_skb(sk, skb))
		kfree_skb(skb);
}

void ipv6_local_error(struct sock *sk, int err, struct flowi *fl, u32 info)
{
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct sock_exterr_skb *serr;
	struct ipv6hdr *iph;
	struct sk_buff *skb;

	if (!np->recverr)
		return;

	skb = alloc_skb(sizeof(struct ipv6hdr), GFP_ATOMIC);
	if (!skb)
		return;

	iph = (struct ipv6hdr*)skb_put(skb, sizeof(struct ipv6hdr));
	skb->nh.ipv6h = iph;
	ipv6_addr_copy(&iph->daddr, &fl->fl6_dst);

	serr = SKB_EXT_ERR(skb);
	serr->ee.ee_errno = err;
	serr->ee.ee_origin = SO_EE_ORIGIN_LOCAL;
	serr->ee.ee_type = 0; 
	serr->ee.ee_code = 0;
	serr->ee.ee_pad = 0;
	serr->ee.ee_info = info;
	serr->ee.ee_data = 0;
	serr->addr_offset = (u8*)&iph->daddr - skb->nh.raw;
	serr->port = fl->fl_ip_dport;

	skb->h.raw = skb->tail;
	__skb_pull(skb, skb->tail - skb->data);

	if (sock_queue_err_skb(sk, skb))
		kfree_skb(skb);
}

/* 
 *	Handle MSG_ERRQUEUE
 */
int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len)
{
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct sock_exterr_skb *serr;
	struct sk_buff *skb, *skb2;
	struct sockaddr_in6 *sin;
	struct {
		struct sock_extended_err ee;
		struct sockaddr_in6	 offender;
	} errhdr;
	int err;
	int copied;

	err = -EAGAIN;
	skb = skb_dequeue(&sk->sk_error_queue);
	if (skb == NULL)
		goto out;

	copied = skb->len;
	if (copied > len) {
		msg->msg_flags |= MSG_TRUNC;
		copied = len;
	}
	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
	if (err)
		goto out_free_skb;

	sock_recv_timestamp(msg, sk, skb);

	serr = SKB_EXT_ERR(skb);

	sin = (struct sockaddr_in6 *)msg->msg_name;
	if (sin) {
		sin->sin6_family = AF_INET6;
		sin->sin6_flowinfo = 0;
		sin->sin6_port = serr->port; 
		sin->sin6_scope_id = 0;
		if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP6) {
			ipv6_addr_copy(&sin->sin6_addr,
			  (struct in6_addr *)(skb->nh.raw + serr->addr_offset));
			if (np->sndflow)
				sin->sin6_flowinfo = *(u32*)(skb->nh.raw + serr->addr_offset - 24) & IPV6_FLOWINFO_MASK;
			if (ipv6_addr_type(&sin->sin6_addr) & IPV6_ADDR_LINKLOCAL)
				sin->sin6_scope_id = IP6CB(skb)->iif;
		} else {
			ipv6_addr_set(&sin->sin6_addr, 0, 0,
				      htonl(0xffff),
				      *(u32*)(skb->nh.raw + serr->addr_offset));
		}
	}

	memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err));
	sin = &errhdr.offender;
	sin->sin6_family = AF_UNSPEC;
	if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL) {
		sin->sin6_family = AF_INET6;
		sin->sin6_flowinfo = 0;
		sin->sin6_scope_id = 0;
		if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP6) {
			ipv6_addr_copy(&sin->sin6_addr, &skb->nh.ipv6h->saddr);
			if (np->rxopt.all)
				datagram_recv_ctl(sk, msg, skb);
			if (ipv6_addr_type(&sin->sin6_addr) & IPV6_ADDR_LINKLOCAL)
				sin->sin6_scope_id = IP6CB(skb)->iif;
		} else {
			struct inet_sock *inet = inet_sk(sk);

			ipv6_addr_set(&sin->sin6_addr, 0, 0,
				      htonl(0xffff),
				      skb->nh.iph->saddr);
			if (inet->cmsg_flags)
				ip_cmsg_recv(msg, skb);
		}
	}

	put_cmsg(msg, SOL_IPV6, IPV6_RECVERR, sizeof(errhdr), &errhdr);

	/* Now we could try to dump offended packet options */

	msg->msg_flags |= MSG_ERRQUEUE;
	err = copied;

	/* Reset and regenerate socket error */
	spin_lock_bh(&sk->sk_error_queue.lock);
	sk->sk_err = 0;
	if ((skb2 = skb_peek(&sk->sk_error_queue)) != NULL) {
		sk->sk_err = SKB_EXT_ERR(skb2)->ee.ee_errno;
		spin_unlock_bh(&sk->sk_error_queue.lock);
		sk->sk_error_report(sk);
	} else {
		spin_unlock_bh(&sk->sk_error_queue.lock);
	}

out_free_skb:	
	kfree_skb(skb);
out:
	return err;
}



int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb)
{
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct inet6_skb_parm *opt = IP6CB(skb);

	if (np->rxopt.bits.rxinfo) {
		struct in6_pktinfo src_info;

		src_info.ipi6_ifindex = opt->iif;
		ipv6_addr_copy(&src_info.ipi6_addr, &skb->nh.ipv6h->daddr);
		put_cmsg(msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info);
	}

	if (np->rxopt.bits.rxhlim) {
		int hlim = skb->nh.ipv6h->hop_limit;
		put_cmsg(msg, SOL_IPV6, IPV6_HOPLIMIT, sizeof(hlim), &hlim);
	}

	if (np->rxopt.bits.rxflow && (*(u32*)skb->nh.raw & IPV6_FLOWINFO_MASK)) {
		u32 flowinfo = *(u32*)skb->nh.raw & IPV6_FLOWINFO_MASK;
		put_cmsg(msg, SOL_IPV6, IPV6_FLOWINFO, sizeof(flowinfo), &flowinfo);
	}
	if (np->rxopt.bits.hopopts && opt->hop) {
		u8 *ptr = skb->nh.raw + opt->hop;
		put_cmsg(msg, SOL_IPV6, IPV6_HOPOPTS, (ptr[1]+1)<<3, ptr);
	}
	if (np->rxopt.bits.dstopts && opt->dst0) {
		u8 *ptr = skb->nh.raw + opt->dst0;
		put_cmsg(msg, SOL_IPV6, IPV6_DSTOPTS, (ptr[1]+1)<<3, ptr);
	}
	if (np->rxopt.bits.srcrt && opt->srcrt) {
		struct ipv6_rt_hdr *rthdr = (struct ipv6_rt_hdr *)(skb->nh.raw + opt->srcrt);
		put_cmsg(msg, SOL_IPV6, IPV6_RTHDR, (rthdr->hdrlen+1) << 3, rthdr);
	}
	if (np->rxopt.bits.dstopts && opt->dst1) {
		u8 *ptr = skb->nh.raw + opt->dst1;
		put_cmsg(msg, SOL_IPV6, IPV6_DSTOPTS, (ptr[1]+1)<<3, ptr);
	}
	return 0;
}

int datagram_send_ctl(struct msghdr *msg, struct flowi *fl,
		      struct ipv6_txoptions *opt,
		      int *hlimit)
{
	struct in6_pktinfo *src_info;
	struct cmsghdr *cmsg;
	struct ipv6_rt_hdr *rthdr;
	struct ipv6_opt_hdr *hdr;
	int len;
	int err = 0;

	for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) {
		int addr_type;
		struct net_device *dev = NULL;

		if (!CMSG_OK(msg, cmsg)) {
			err = -EINVAL;
			goto exit_f;
		}

		if (cmsg->cmsg_level != SOL_IPV6)
			continue;

		switch (cmsg->cmsg_type) {
 		case IPV6_PKTINFO:
 			if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct in6_pktinfo))) {
				err = -EINVAL;
				goto exit_f;
			}

			src_info = (struct in6_pktinfo *)CMSG_DATA(cmsg);
			
			if (src_info->ipi6_ifindex) {
				if (fl->oif && src_info->ipi6_ifindex != fl->oif)
					return -EINVAL;
				fl->oif = src_info->ipi6_ifindex;
			}

			addr_type = ipv6_addr_type(&src_info->ipi6_addr);

			if (addr_type == IPV6_ADDR_ANY)
				break;
			
			if (addr_type & IPV6_ADDR_LINKLOCAL) {
				if (!src_info->ipi6_ifindex)
					return -EINVAL;
				else {
					dev = dev_get_by_index(src_info->ipi6_ifindex);
					if (!dev)
						return -ENODEV;
				}
			}
			if (!ipv6_chk_addr(&src_info->ipi6_addr, dev, 0)) {
				if (dev)
					dev_put(dev);
				err = -EINVAL;
				goto exit_f;
			}
			if (dev)
				dev_put(dev);

			ipv6_addr_copy(&fl->fl6_src, &src_info->ipi6_addr);
			break;

		case IPV6_FLOWINFO:
                        if (cmsg->cmsg_len < CMSG_LEN(4)) {
				err = -EINVAL;
				goto exit_f;
			}

			if (fl->fl6_flowlabel&IPV6_FLOWINFO_MASK) {
				if ((fl->fl6_flowlabel^*(u32 *)CMSG_DATA(cmsg))&~IPV6_FLOWINFO_MASK) {
					err = -EINVAL;
					goto exit_f;
				}
			}
			fl->fl6_flowlabel = IPV6_FLOWINFO_MASK & *(u32 *)CMSG_DATA(cmsg);
			break;

		case IPV6_HOPOPTS:
                        if (opt->hopopt || cmsg->cmsg_len < CMSG_LEN(sizeof(struct ipv6_opt_hdr))) {
				err = -EINVAL;
				goto exit_f;
			}

			hdr = (struct ipv6_opt_hdr *)CMSG_DATA(cmsg);
			len = ((hdr->hdrlen + 1) << 3);
			if (cmsg->cmsg_len < CMSG_LEN(len)) {
				err = -EINVAL;
				goto exit_f;
			}
			if (!capable(CAP_NET_RAW)) {
				err = -EPERM;
				goto exit_f;
			}
			opt->opt_nflen += len;
			opt->hopopt = hdr;
			break;

		case IPV6_DSTOPTS:
                        if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct ipv6_opt_hdr))) {
				err = -EINVAL;
				goto exit_f;
			}

			hdr = (struct ipv6_opt_hdr *)CMSG_DATA(cmsg);
			len = ((hdr->hdrlen + 1) << 3);
			if (cmsg->cmsg_len < CMSG_LEN(len)) {
				err = -EINVAL;
				goto exit_f;
			}
			if (!capable(CAP_NET_RAW)) {
				err = -EPERM;
				goto exit_f;
			}
			if (opt->dst1opt) {
				err = -EINVAL;
				goto exit_f;
			}
			opt->opt_flen += len;
			opt->dst1opt = hdr;
			break;

		case IPV6_RTHDR:
                        if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct ipv6_rt_hdr))) {
				err = -EINVAL;
				goto exit_f;
			}

			rthdr = (struct ipv6_rt_hdr *)CMSG_DATA(cmsg);

			/*
			 *	TYPE 0
			 */
			if (rthdr->type) {
				err = -EINVAL;
				goto exit_f;
			}

			len = ((rthdr->hdrlen + 1) << 3);

                        if (cmsg->cmsg_len < CMSG_LEN(len)) {
				err = -EINVAL;
				goto exit_f;
			}

			/* segments left must also match */
			if ((rthdr->hdrlen >> 1) != rthdr->segments_left) {
				err = -EINVAL;
				goto exit_f;
			}

			opt->opt_nflen += len;
			opt->srcrt = rthdr;

			if (opt->dst1opt) {
				int dsthdrlen = ((opt->dst1opt->hdrlen+1)<<3);

				opt->opt_nflen += dsthdrlen;
				opt->dst0opt = opt->dst1opt;
				opt->dst1opt = NULL;
				opt->opt_flen -= dsthdrlen;
			}

			break;

		case IPV6_HOPLIMIT:
			if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) {
				err = -EINVAL;
				goto exit_f;
			}

			*hlimit = *(int *)CMSG_DATA(cmsg);
			break;

		default:
			LIMIT_NETDEBUG(KERN_DEBUG "invalid cmsg type: %d\n",
			               cmsg->cmsg_type);
			err = -EINVAL;
			break;
		};
	}

exit_f:
	return err;
}