aboutsummaryrefslogtreecommitdiff
path: root/net/ipv6/raw.c
blob: c45f7a5c36e96f98487ca194c5f08e5d0f931852 (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
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
/*
 *	RAW sockets for IPv6
 *	Linux INET6 implementation
 *
 *	Authors:
 *	Pedro Roque		<roque@di.fc.ul.pt>
 *
 *	Adapted from linux/net/ipv4/raw.c
 *
 *	Fixes:
 *	Hideaki YOSHIFUJI	:	sin6_scope_id support
 *	YOSHIFUJI,H.@USAGI	:	raw checksum (RFC2292(bis) compliance)
 *	Kazunori MIYAZAWA @USAGI:	change process style to use ip6_append_data
 *
 *	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/socket.h>
#include <linux/slab.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/in6.h>
#include <linux/netdevice.h>
#include <linux/if_arp.h>
#include <linux/icmpv6.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv6.h>
#include <linux/skbuff.h>
#include <linux/compat.h>
#include <asm/uaccess.h>
#include <asm/ioctls.h>

#include <net/net_namespace.h>
#include <net/ip.h>
#include <net/sock.h>
#include <net/snmp.h>

#include <net/ipv6.h>
#include <net/ndisc.h>
#include <net/protocol.h>
#include <net/ip6_route.h>
#include <net/ip6_checksum.h>
#include <net/addrconf.h>
#include <net/transp_v6.h>
#include <net/udp.h>
#include <net/inet_common.h>
#include <net/tcp_states.h>
#if IS_ENABLED(CONFIG_IPV6_MIP6)
#include <net/mip6.h>
#endif
#include <linux/mroute6.h>

#include <net/raw.h>
#include <net/rawv6.h>
#include <net/xfrm.h>

#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/export.h>

static struct raw_hashinfo raw_v6_hashinfo = {
	.lock = __RW_LOCK_UNLOCKED(raw_v6_hashinfo.lock),
};

static struct sock *__raw_v6_lookup(struct net *net, struct sock *sk,
		unsigned short num, const struct in6_addr *loc_addr,
		const struct in6_addr *rmt_addr, int dif)
{
	bool is_multicast = ipv6_addr_is_multicast(loc_addr);

	sk_for_each_from(sk)
		if (inet_sk(sk)->inet_num == num) {
			struct ipv6_pinfo *np = inet6_sk(sk);

			if (!net_eq(sock_net(sk), net))
				continue;

			if (!ipv6_addr_any(&np->daddr) &&
			    !ipv6_addr_equal(&np->daddr, rmt_addr))
				continue;

			if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)
				continue;

			if (!ipv6_addr_any(&np->rcv_saddr)) {
				if (ipv6_addr_equal(&np->rcv_saddr, loc_addr))
					goto found;
				if (is_multicast &&
				    inet6_mc_check(sk, loc_addr, rmt_addr))
					goto found;
				continue;
			}
			goto found;
		}
	sk = NULL;
found:
	return sk;
}

/*
 *	0 - deliver
 *	1 - block
 */
static int icmpv6_filter(const struct sock *sk, const struct sk_buff *skb)
{
	struct icmp6hdr *_hdr;
	const struct icmp6hdr *hdr;

	hdr = skb_header_pointer(skb, skb_transport_offset(skb),
				 sizeof(_hdr), &_hdr);
	if (hdr) {
		const __u32 *data = &raw6_sk(sk)->filter.data[0];
		unsigned int type = hdr->icmp6_type;

		return (data[type >> 5] & (1U << (type & 31))) != 0;
	}
	return 1;
}

#if IS_ENABLED(CONFIG_IPV6_MIP6)
typedef int mh_filter_t(struct sock *sock, struct sk_buff *skb);

static mh_filter_t __rcu *mh_filter __read_mostly;

int rawv6_mh_filter_register(mh_filter_t filter)
{
	rcu_assign_pointer(mh_filter, filter);
	return 0;
}
EXPORT_SYMBOL(rawv6_mh_filter_register);

int rawv6_mh_filter_unregister(mh_filter_t filter)
{
	RCU_INIT_POINTER(mh_filter, NULL);
	synchronize_rcu();
	return 0;
}
EXPORT_SYMBOL(rawv6_mh_filter_unregister);

#endif

/*
 *	demultiplex raw sockets.
 *	(should consider queueing the skb in the sock receive_queue
 *	without calling rawv6.c)
 *
 *	Caller owns SKB so we must make clones.
 */
static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr)
{
	const struct in6_addr *saddr;
	const struct in6_addr *daddr;
	struct sock *sk;
	bool delivered = false;
	__u8 hash;
	struct net *net;

	saddr = &ipv6_hdr(skb)->saddr;
	daddr = saddr + 1;

	hash = nexthdr & (RAW_HTABLE_SIZE - 1);

	read_lock(&raw_v6_hashinfo.lock);
	sk = sk_head(&raw_v6_hashinfo.ht[hash]);

	if (sk == NULL)
		goto out;

	net = dev_net(skb->dev);
	sk = __raw_v6_lookup(net, sk, nexthdr, daddr, saddr, IP6CB(skb)->iif);

	while (sk) {
		int filtered;

		delivered = true;
		switch (nexthdr) {
		case IPPROTO_ICMPV6:
			filtered = icmpv6_filter(sk, skb);
			break;

#if IS_ENABLED(CONFIG_IPV6_MIP6)
		case IPPROTO_MH:
		{
			/* XXX: To validate MH only once for each packet,
			 * this is placed here. It should be after checking
			 * xfrm policy, however it doesn't. The checking xfrm
			 * policy is placed in rawv6_rcv() because it is
			 * required for each socket.
			 */
			mh_filter_t *filter;

			filter = rcu_dereference(mh_filter);
			filtered = filter ? (*filter)(sk, skb) : 0;
			break;
		}
#endif
		default:
			filtered = 0;
			break;
		}

		if (filtered < 0)
			break;
		if (filtered == 0) {
			struct sk_buff *clone = skb_clone(skb, GFP_ATOMIC);

			/* Not releasing hash table! */
			if (clone) {
				nf_reset(clone);
				rawv6_rcv(sk, clone);
			}
		}
		sk = __raw_v6_lookup(net, sk_next(sk), nexthdr, daddr, saddr,
				     IP6CB(skb)->iif);
	}
out:
	read_unlock(&raw_v6_hashinfo.lock);
	return delivered;
}

bool raw6_local_deliver(struct sk_buff *skb, int nexthdr)
{
	struct sock *raw_sk;

	raw_sk = sk_head(&raw_v6_hashinfo.ht[nexthdr & (RAW_HTABLE_SIZE - 1)]);
	if (raw_sk && !ipv6_raw_deliver(skb, nexthdr))
		raw_sk = NULL;

	return raw_sk != NULL;
}

/* This cleans up af_inet6 a bit. -DaveM */
static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
	struct inet_sock *inet = inet_sk(sk);
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct sockaddr_in6 *addr = (struct sockaddr_in6 *) uaddr;
	__be32 v4addr = 0;
	int addr_type;
	int err;

	if (addr_len < SIN6_LEN_RFC2133)
		return -EINVAL;
	addr_type = ipv6_addr_type(&addr->sin6_addr);

	/* Raw sockets are IPv6 only */
	if (addr_type == IPV6_ADDR_MAPPED)
		return -EADDRNOTAVAIL;

	lock_sock(sk);

	err = -EINVAL;
	if (sk->sk_state != TCP_CLOSE)
		goto out;

	rcu_read_lock();
	/* Check if the address belongs to the host. */
	if (addr_type != IPV6_ADDR_ANY) {
		struct net_device *dev = NULL;

		if (__ipv6_addr_needs_scope_id(addr_type)) {
			if (addr_len >= sizeof(struct sockaddr_in6) &&
			    addr->sin6_scope_id) {
				/* Override any existing binding, if another
				 * one is supplied by user.
				 */
				sk->sk_bound_dev_if = addr->sin6_scope_id;
			}

			/* Binding to link-local address requires an interface */
			if (!sk->sk_bound_dev_if)
				goto out_unlock;

			err = -ENODEV;
			dev = dev_get_by_index_rcu(sock_net(sk),
						   sk->sk_bound_dev_if);
			if (!dev)
				goto out_unlock;
		}

		/* ipv4 addr of the socket is invalid.  Only the
		 * unspecified and mapped address have a v4 equivalent.
		 */
		v4addr = LOOPBACK4_IPV6;
		if (!(addr_type & IPV6_ADDR_MULTICAST))	{
			err = -EADDRNOTAVAIL;
			if (!ipv6_chk_addr(sock_net(sk), &addr->sin6_addr,
					   dev, 0)) {
				goto out_unlock;
			}
		}
	}

	inet->inet_rcv_saddr = inet->inet_saddr = v4addr;
	np->rcv_saddr = addr->sin6_addr;
	if (!(addr_type & IPV6_ADDR_MULTICAST))
		np->saddr = addr->sin6_addr;
	err = 0;
out_unlock:
	rcu_read_unlock();
out:
	release_sock(sk);
	return err;
}

static void rawv6_err(struct sock *sk, struct sk_buff *skb,
	       struct inet6_skb_parm *opt,
	       u8 type, u8 code, int offset, __be32 info)
{
	struct inet_sock *inet = inet_sk(sk);
	struct ipv6_pinfo *np = inet6_sk(sk);
	int err;
	int harderr;

	/* Report error on raw socket, if:
	   1. User requested recverr.
	   2. Socket is connected (otherwise the error indication
	      is useless without recverr and error is hard.
	 */
	if (!np->recverr && sk->sk_state != TCP_ESTABLISHED)
		return;

	harderr = icmpv6_err_convert(type, code, &err);
	if (type == ICMPV6_PKT_TOOBIG) {
		ip6_sk_update_pmtu(skb, sk, info);
		harderr = (np->pmtudisc == IPV6_PMTUDISC_DO);
	}
	if (type == NDISC_REDIRECT)
		ip6_sk_redirect(skb, sk);
	if (np->recverr) {
		u8 *payload = skb->data;
		if (!inet->hdrincl)
			payload += offset;
		ipv6_icmp_error(sk, skb, err, 0, ntohl(info), payload);
	}

	if (np->recverr || harderr) {
		sk->sk_err = err;
		sk->sk_error_report(sk);
	}
}

void raw6_icmp_error(struct sk_buff *skb, int nexthdr,
		u8 type, u8 code, int inner_offset, __be32 info)
{
	struct sock *sk;
	int hash;
	const struct in6_addr *saddr, *daddr;
	struct net *net;

	hash = nexthdr & (RAW_HTABLE_SIZE - 1);

	read_lock(&raw_v6_hashinfo.lock);
	sk = sk_head(&raw_v6_hashinfo.ht[hash]);
	if (sk != NULL) {
		/* Note: ipv6_hdr(skb) != skb->data */
		const struct ipv6hdr *ip6h = (const struct ipv6hdr *)skb->data;
		saddr = &ip6h->saddr;
		daddr = &ip6h->daddr;
		net = dev_net(skb->dev);

		while ((sk = __raw_v6_lookup(net, sk, nexthdr, saddr, daddr,
						IP6CB(skb)->iif))) {
			rawv6_err(sk, skb, NULL, type, code,
					inner_offset, info);
			sk = sk_next(sk);
		}
	}
	read_unlock(&raw_v6_hashinfo.lock);
}

static inline int rawv6_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
	if ((raw6_sk(sk)->checksum || rcu_access_pointer(sk->sk_filter)) &&
	    skb_checksum_complete(skb)) {
		atomic_inc(&sk->sk_drops);
		kfree_skb(skb);
		return NET_RX_DROP;
	}

	/* Charge it to the socket. */
	skb_dst_drop(skb);
	if (sock_queue_rcv_skb(sk, skb) < 0) {
		kfree_skb(skb);
		return NET_RX_DROP;
	}

	return 0;
}

/*
 *	This is next to useless...
 *	if we demultiplex in network layer we don't need the extra call
 *	just to queue the skb...
 *	maybe we could have the network decide upon a hint if it
 *	should call raw_rcv for demultiplexing
 */
int rawv6_rcv(struct sock *sk, struct sk_buff *skb)
{
	struct inet_sock *inet = inet_sk(sk);
	struct raw6_sock *rp = raw6_sk(sk);

	if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) {
		atomic_inc(&sk->sk_drops);
		kfree_skb(skb);
		return NET_RX_DROP;
	}

	if (!rp->checksum)
		skb->ip_summed = CHECKSUM_UNNECESSARY;

	if (skb->ip_summed == CHECKSUM_COMPLETE) {
		skb_postpull_rcsum(skb, skb_network_header(skb),
				   skb_network_header_len(skb));
		if (!csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
				     &ipv6_hdr(skb)->daddr,
				     skb->len, inet->inet_num, skb->csum))
			skb->ip_summed = CHECKSUM_UNNECESSARY;
	}
	if (!skb_csum_unnecessary(skb))
		skb->csum = ~csum_unfold(csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
							 &ipv6_hdr(skb)->daddr,
							 skb->len,
							 inet->inet_num, 0));

	if (inet->hdrincl) {
		if (skb_checksum_complete(skb)) {
			atomic_inc(&sk->sk_drops);
			kfree_skb(skb);
			return NET_RX_DROP;
		}
	}

	rawv6_rcv_skb(sk, skb);
	return 0;
}


/*
 *	This should be easy, if there is something there
 *	we return it, otherwise we block.
 */

static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk,
		  struct msghdr *msg, size_t len,
		  int noblock, int flags, int *addr_len)
{
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)msg->msg_name;
	struct sk_buff *skb;
	size_t copied;
	int err;

	if (flags & MSG_OOB)
		return -EOPNOTSUPP;

	if (addr_len)
		*addr_len=sizeof(*sin6);

	if (flags & MSG_ERRQUEUE)
		return ipv6_recv_error(sk, msg, len);

	if (np->rxpmtu && np->rxopt.bits.rxpmtu)
		return ipv6_recv_rxpmtu(sk, msg, len);

	skb = skb_recv_datagram(sk, flags, noblock, &err);
	if (!skb)
		goto out;

	copied = skb->len;
	if (copied > len) {
		copied = len;
		msg->msg_flags |= MSG_TRUNC;
	}

	if (skb_csum_unnecessary(skb)) {
		err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
	} else if (msg->msg_flags&MSG_TRUNC) {
		if (__skb_checksum_complete(skb))
			goto csum_copy_err;
		err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
	} else {
		err = skb_copy_and_csum_datagram_iovec(skb, 0, msg->msg_iov);
		if (err == -EINVAL)
			goto csum_copy_err;
	}
	if (err)
		goto out_free;

	/* Copy the address. */
	if (sin6) {
		sin6->sin6_family = AF_INET6;
		sin6->sin6_port = 0;
		sin6->sin6_addr = ipv6_hdr(skb)->saddr;
		sin6->sin6_flowinfo = 0;
		sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr,
							  IP6CB(skb)->iif);
	}

	sock_recv_ts_and_drops(msg, sk, skb);

	if (np->rxopt.all)
		ip6_datagram_recv_ctl(sk, msg, skb);

	err = copied;
	if (flags & MSG_TRUNC)
		err = skb->len;

out_free:
	skb_free_datagram(sk, skb);
out:
	return err;

csum_copy_err:
	skb_kill_datagram(sk, skb, flags);

	/* Error for blocking case is chosen to masquerade
	   as some normal condition.
	 */
	err = (flags&MSG_DONTWAIT) ? -EAGAIN : -EHOSTUNREACH;
	goto out;
}

static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
				     struct raw6_sock *rp)
{
	struct sk_buff *skb;
	int err = 0;
	int offset;
	int len;
	int total_len;
	__wsum tmp_csum;
	__sum16 csum;

	if (!rp->checksum)
		goto send;

	if ((skb = skb_peek(&sk->sk_write_queue)) == NULL)
		goto out;

	offset = rp->offset;
	total_len = inet_sk(sk)->cork.base.length;
	if (offset >= total_len - 1) {
		err = -EINVAL;
		ip6_flush_pending_frames(sk);
		goto out;
	}

	/* should be check HW csum miyazawa */
	if (skb_queue_len(&sk->sk_write_queue) == 1) {
		/*
		 * Only one fragment on the socket.
		 */
		tmp_csum = skb->csum;
	} else {
		struct sk_buff *csum_skb = NULL;
		tmp_csum = 0;

		skb_queue_walk(&sk->sk_write_queue, skb) {
			tmp_csum = csum_add(tmp_csum, skb->csum);

			if (csum_skb)
				continue;

			len = skb->len - skb_transport_offset(skb);
			if (offset >= len) {
				offset -= len;
				continue;
			}

			csum_skb = skb;
		}

		skb = csum_skb;
	}

	offset += skb_transport_offset(skb);
	if (skb_copy_bits(skb, offset, &csum, 2))
		BUG();

	/* in case cksum was not initialized */
	if (unlikely(csum))
		tmp_csum = csum_sub(tmp_csum, csum_unfold(csum));

	csum = csum_ipv6_magic(&fl6->saddr, &fl6->daddr,
			       total_len, fl6->flowi6_proto, tmp_csum);

	if (csum == 0 && fl6->flowi6_proto == IPPROTO_UDP)
		csum = CSUM_MANGLED_0;

	if (skb_store_bits(skb, offset, &csum, 2))
		BUG();

send:
	err = ip6_push_pending_frames(sk);
out:
	return err;
}

static int rawv6_send_hdrinc(struct sock *sk, void *from, int length,
			struct flowi6 *fl6, struct dst_entry **dstp,
			unsigned int flags)
{
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct ipv6hdr *iph;
	struct sk_buff *skb;
	int err;
	struct rt6_info *rt = (struct rt6_info *)*dstp;
	int hlen = LL_RESERVED_SPACE(rt->dst.dev);
	int tlen = rt->dst.dev->needed_tailroom;

	if (length > rt->dst.dev->mtu) {
		ipv6_local_error(sk, EMSGSIZE, fl6, rt->dst.dev->mtu);
		return -EMSGSIZE;
	}
	if (flags&MSG_PROBE)
		goto out;

	skb = sock_alloc_send_skb(sk,
				  length + hlen + tlen + 15,
				  flags & MSG_DONTWAIT, &err);
	if (skb == NULL)
		goto error;
	skb_reserve(skb, hlen);

	skb->priority = sk->sk_priority;
	skb->mark = sk->sk_mark;
	skb_dst_set(skb, &rt->dst);
	*dstp = NULL;

	skb_put(skb, length);
	skb_reset_network_header(skb);
	iph = ipv6_hdr(skb);

	skb->ip_summed = CHECKSUM_NONE;

	skb->transport_header = skb->network_header;
	err = memcpy_fromiovecend((void *)iph, from, 0, length);
	if (err)
		goto error_fault;

	IP6_UPD_PO_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len);
	err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL,
		      rt->dst.dev, dst_output);
	if (err > 0)
		err = net_xmit_errno(err);
	if (err)
		goto error;
out:
	return 0;

error_fault:
	err = -EFAULT;
	kfree_skb(skb);
error:
	IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
	if (err == -ENOBUFS && !np->recverr)
		err = 0;
	return err;
}

static int rawv6_probe_proto_opt(struct flowi6 *fl6, struct msghdr *msg)
{
	struct iovec *iov;
	u8 __user *type = NULL;
	u8 __user *code = NULL;
	u8 len = 0;
	int probed = 0;
	int i;

	if (!msg->msg_iov)
		return 0;

	for (i = 0; i < msg->msg_iovlen; i++) {
		iov = &msg->msg_iov[i];
		if (!iov)
			continue;

		switch (fl6->flowi6_proto) {
		case IPPROTO_ICMPV6:
			/* check if one-byte field is readable or not. */
			if (iov->iov_base && iov->iov_len < 1)
				break;

			if (!type) {
				type = iov->iov_base;
				/* check if code field is readable or not. */
				if (iov->iov_len > 1)
					code = type + 1;
			} else if (!code)
				code = iov->iov_base;

			if (type && code) {
				if (get_user(fl6->fl6_icmp_type, type) ||
				    get_user(fl6->fl6_icmp_code, code))
					return -EFAULT;
				probed = 1;
			}
			break;
		case IPPROTO_MH:
			if (iov->iov_base && iov->iov_len < 1)
				break;
			/* check if type field is readable or not. */
			if (iov->iov_len > 2 - len) {
				u8 __user *p = iov->iov_base;
				if (get_user(fl6->fl6_mh_type, &p[2 - len]))
					return -EFAULT;
				probed = 1;
			} else
				len += iov->iov_len;

			break;
		default:
			probed = 1;
			break;
		}
		if (probed)
			break;
	}
	return 0;
}

static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
		   struct msghdr *msg, size_t len)
{
	struct ipv6_txoptions opt_space;
	struct sockaddr_in6 * sin6 = (struct sockaddr_in6 *) msg->msg_name;
	struct in6_addr *daddr, *final_p, final;
	struct inet_sock *inet = inet_sk(sk);
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct raw6_sock *rp = raw6_sk(sk);
	struct ipv6_txoptions *opt = NULL;
	struct ip6_flowlabel *flowlabel = NULL;
	struct dst_entry *dst = NULL;
	struct flowi6 fl6;
	int addr_len = msg->msg_namelen;
	int hlimit = -1;
	int tclass = -1;
	int dontfrag = -1;
	u16 proto;
	int err;

	/* Rough check on arithmetic overflow,
	   better check is made in ip6_append_data().
	 */
	if (len > INT_MAX)
		return -EMSGSIZE;

	/* Mirror BSD error message compatibility */
	if (msg->msg_flags & MSG_OOB)
		return -EOPNOTSUPP;

	/*
	 *	Get and verify the address.
	 */
	memset(&fl6, 0, sizeof(fl6));

	fl6.flowi6_mark = sk->sk_mark;

	if (sin6) {
		if (addr_len < SIN6_LEN_RFC2133)
			return -EINVAL;

		if (sin6->sin6_family && sin6->sin6_family != AF_INET6)
			return -EAFNOSUPPORT;

		/* port is the proto value [0..255] carried in nexthdr */
		proto = ntohs(sin6->sin6_port);

		if (!proto)
			proto = inet->inet_num;
		else if (proto != inet->inet_num)
			return -EINVAL;

		if (proto > 255)
			return -EINVAL;

		daddr = &sin6->sin6_addr;
		if (np->sndflow) {
			fl6.flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK;
			if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) {
				flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
				if (flowlabel == NULL)
					return -EINVAL;
				daddr = &flowlabel->dst;
			}
		}

		/*
		 * Otherwise it will be difficult to maintain
		 * sk->sk_dst_cache.
		 */
		if (sk->sk_state == TCP_ESTABLISHED &&
		    ipv6_addr_equal(daddr, &np->daddr))
			daddr = &np->daddr;

		if (addr_len >= sizeof(struct sockaddr_in6) &&
		    sin6->sin6_scope_id &&
		    __ipv6_addr_needs_scope_id(__ipv6_addr_type(daddr)))
			fl6.flowi6_oif = sin6->sin6_scope_id;
	} else {
		if (sk->sk_state != TCP_ESTABLISHED)
			return -EDESTADDRREQ;

		proto = inet->inet_num;
		daddr = &np->daddr;
		fl6.flowlabel = np->flow_label;
	}

	if (fl6.flowi6_oif == 0)
		fl6.flowi6_oif = sk->sk_bound_dev_if;

	if (msg->msg_controllen) {
		opt = &opt_space;
		memset(opt, 0, sizeof(struct ipv6_txoptions));
		opt->tot_len = sizeof(struct ipv6_txoptions);

		err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt,
					    &hlimit, &tclass, &dontfrag);
		if (err < 0) {
			fl6_sock_release(flowlabel);
			return err;
		}
		if ((fl6.flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) {
			flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
			if (flowlabel == NULL)
				return -EINVAL;
		}
		if (!(opt->opt_nflen|opt->opt_flen))
			opt = NULL;
	}
	if (opt == NULL)
		opt = np->opt;
	if (flowlabel)
		opt = fl6_merge_options(&opt_space, flowlabel, opt);
	opt = ipv6_fixup_options(&opt_space, opt);

	fl6.flowi6_proto = proto;
	err = rawv6_probe_proto_opt(&fl6, msg);
	if (err)
		goto out;

	if (!ipv6_addr_any(daddr))
		fl6.daddr = *daddr;
	else
		fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */
	if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr))
		fl6.saddr = np->saddr;

	final_p = fl6_update_dst(&fl6, opt, &final);

	if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
		fl6.flowi6_oif = np->mcast_oif;
	else if (!fl6.flowi6_oif)
		fl6.flowi6_oif = np->ucast_oif;
	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));

	dst = ip6_dst_lookup_flow(sk, &fl6, final_p, true);
	if (IS_ERR(dst)) {
		err = PTR_ERR(dst);
		goto out;
	}
	if (hlimit < 0) {
		if (ipv6_addr_is_multicast(&fl6.daddr))
			hlimit = np->mcast_hops;
		else
			hlimit = np->hop_limit;
		if (hlimit < 0)
			hlimit = ip6_dst_hoplimit(dst);
	}

	if (tclass < 0)
		tclass = np->tclass;

	if (dontfrag < 0)
		dontfrag = np->dontfrag;

	if (msg->msg_flags&MSG_CONFIRM)
		goto do_confirm;

back_from_confirm:
	if (inet->hdrincl)
		err = rawv6_send_hdrinc(sk, msg->msg_iov, len, &fl6, &dst, msg->msg_flags);
	else {
		lock_sock(sk);
		err = ip6_append_data(sk, ip_generic_getfrag, msg->msg_iov,
			len, 0, hlimit, tclass, opt, &fl6, (struct rt6_info*)dst,
			msg->msg_flags, dontfrag);

		if (err)
			ip6_flush_pending_frames(sk);
		else if (!(msg->msg_flags & MSG_MORE))
			err = rawv6_push_pending_frames(sk, &fl6, rp);
		release_sock(sk);
	}
done:
	dst_release(dst);
out:
	fl6_sock_release(flowlabel);
	return err<0?err:len;
do_confirm:
	dst_confirm(dst);
	if (!(msg->msg_flags & MSG_PROBE) || len)
		goto back_from_confirm;
	err = 0;
	goto done;
}

static int rawv6_seticmpfilter(struct sock *sk, int level, int optname,
			       char __user *optval, int optlen)
{
	switch (optname) {
	case ICMPV6_FILTER:
		if (optlen > sizeof(struct icmp6_filter))
			optlen = sizeof(struct icmp6_filter);
		if (copy_from_user(&raw6_sk(sk)->filter, optval, optlen))
			return -EFAULT;
		return 0;
	default:
		return -ENOPROTOOPT;
	}

	return 0;
}

static int rawv6_geticmpfilter(struct sock *sk, int level, int optname,
			       char __user *optval, int __user *optlen)
{
	int len;

	switch (optname) {
	case ICMPV6_FILTER:
		if (get_user(len, optlen))
			return -EFAULT;
		if (len < 0)
			return -EINVAL;
		if (len > sizeof(struct icmp6_filter))
			len = sizeof(struct icmp6_filter);
		if (put_user(len, optlen))
			return -EFAULT;
		if (copy_to_user(optval, &raw6_sk(sk)->filter, len))
			return -EFAULT;
		return 0;
	default:
		return -ENOPROTOOPT;
	}

	return 0;
}


static int do_rawv6_setsockopt(struct sock *sk, int level, int optname,
			    char __user *optval, unsigned int optlen)
{
	struct raw6_sock *rp = raw6_sk(sk);
	int val;

	if (get_user(val, (int __user *)optval))
		return -EFAULT;

	switch (optname) {
	case IPV6_CHECKSUM:
		if (inet_sk(sk)->inet_num == IPPROTO_ICMPV6 &&
		    level == IPPROTO_IPV6) {
			/*
			 * RFC3542 tells that IPV6_CHECKSUM socket
			 * option in the IPPROTO_IPV6 level is not
			 * allowed on ICMPv6 sockets.
			 * If you want to set it, use IPPROTO_RAW
			 * level IPV6_CHECKSUM socket option
			 * (Linux extension).
			 */
			return -EINVAL;
		}

		/* You may get strange result with a positive odd offset;
		   RFC2292bis agrees with me. */
		if (val > 0 && (val&1))
			return -EINVAL;
		if (val < 0) {
			rp->checksum = 0;
		} else {
			rp->checksum = 1;
			rp->offset = val;
		}

		return 0;

	default:
		return -ENOPROTOOPT;
	}
}

static int rawv6_setsockopt(struct sock *sk, int level, int optname,
			  char __user *optval, unsigned int optlen)
{
	switch (level) {
	case SOL_RAW:
		break;

	case SOL_ICMPV6:
		if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6)
			return -EOPNOTSUPP;
		return rawv6_seticmpfilter(sk, level, optname, optval, optlen);
	case SOL_IPV6:
		if (optname == IPV6_CHECKSUM)
			break;
	default:
		return ipv6_setsockopt(sk, level, optname, optval, optlen);
	}

	return do_rawv6_setsockopt(sk, level, optname, optval, optlen);
}

#ifdef CONFIG_COMPAT
static int compat_rawv6_setsockopt(struct sock *sk, int level, int optname,
				   char __user *optval, unsigned int optlen)
{
	switch (level) {
	case SOL_RAW:
		break;
	case SOL_ICMPV6:
		if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6)
			return -EOPNOTSUPP;
		return rawv6_seticmpfilter(sk, level, optname, optval, optlen);
	case SOL_IPV6:
		if (optname == IPV6_CHECKSUM)
			break;
	default:
		return compat_ipv6_setsockopt(sk, level, optname,
					      optval, optlen);
	}
	return do_rawv6_setsockopt(sk, level, optname, optval, optlen);
}
#endif

static int do_rawv6_getsockopt(struct sock *sk, int level, int optname,
			    char __user *optval, int __user *optlen)
{
	struct raw6_sock *rp = raw6_sk(sk);
	int val, len;

	if (get_user(len,optlen))
		return -EFAULT;

	switch (optname) {
	case IPV6_CHECKSUM:
		/*
		 * We allow getsockopt() for IPPROTO_IPV6-level
		 * IPV6_CHECKSUM socket option on ICMPv6 sockets
		 * since RFC3542 is silent about it.
		 */
		if (rp->checksum == 0)
			val = -1;
		else
			val = rp->offset;
		break;

	default:
		return -ENOPROTOOPT;
	}

	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;
}

static int rawv6_getsockopt(struct sock *sk, int level, int optname,
			  char __user *optval, int __user *optlen)
{
	switch (level) {
	case SOL_RAW:
		break;

	case SOL_ICMPV6:
		if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6)
			return -EOPNOTSUPP;
		return rawv6_geticmpfilter(sk, level, optname, optval, optlen);
	case SOL_IPV6:
		if (optname == IPV6_CHECKSUM)
			break;
	default:
		return ipv6_getsockopt(sk, level, optname, optval, optlen);
	}

	return do_rawv6_getsockopt(sk, level, optname, optval, optlen);
}

#ifdef CONFIG_COMPAT
static int compat_rawv6_getsockopt(struct sock *sk, int level, int optname,
				   char __user *optval, int __user *optlen)
{
	switch (level) {
	case SOL_RAW:
		break;
	case SOL_ICMPV6:
		if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6)
			return -EOPNOTSUPP;
		return rawv6_geticmpfilter(sk, level, optname, optval, optlen);
	case SOL_IPV6:
		if (optname == IPV6_CHECKSUM)
			break;
	default:
		return compat_ipv6_getsockopt(sk, level, optname,
					      optval, optlen);
	}
	return do_rawv6_getsockopt(sk, level, optname, optval, optlen);
}
#endif

static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg)
{
	switch (cmd) {
	case SIOCOUTQ: {
		int amount = sk_wmem_alloc_get(sk);

		return put_user(amount, (int __user *)arg);
	}
	case SIOCINQ: {
		struct sk_buff *skb;
		int amount = 0;

		spin_lock_bh(&sk->sk_receive_queue.lock);
		skb = skb_peek(&sk->sk_receive_queue);
		if (skb != NULL)
			amount = skb_tail_pointer(skb) -
				skb_transport_header(skb);
		spin_unlock_bh(&sk->sk_receive_queue.lock);
		return put_user(amount, (int __user *)arg);
	}

	default:
#ifdef CONFIG_IPV6_MROUTE
		return ip6mr_ioctl(sk, cmd, (void __user *)arg);
#else
		return -ENOIOCTLCMD;
#endif
	}
}

#ifdef CONFIG_COMPAT
static int compat_rawv6_ioctl(struct sock *sk, unsigned int cmd, unsigned long arg)
{
	switch (cmd) {
	case SIOCOUTQ:
	case SIOCINQ:
		return -ENOIOCTLCMD;
	default:
#ifdef CONFIG_IPV6_MROUTE
		return ip6mr_compat_ioctl(sk, cmd, compat_ptr(arg));
#else
		return -ENOIOCTLCMD;
#endif
	}
}
#endif

static void rawv6_close(struct sock *sk, long timeout)
{
	if (inet_sk(sk)->inet_num == IPPROTO_RAW)
		ip6_ra_control(sk, -1);
	ip6mr_sk_done(sk);
	sk_common_release(sk);
}

static void raw6_destroy(struct sock *sk)
{
	lock_sock(sk);
	ip6_flush_pending_frames(sk);
	release_sock(sk);

	inet6_destroy_sock(sk);
}

static int rawv6_init_sk(struct sock *sk)
{
	struct raw6_sock *rp = raw6_sk(sk);

	switch (inet_sk(sk)->inet_num) {
	case IPPROTO_ICMPV6:
		rp->checksum = 1;
		rp->offset   = 2;
		break;
	case IPPROTO_MH:
		rp->checksum = 1;
		rp->offset   = 4;
		break;
	default:
		break;
	}
	return 0;
}

struct proto rawv6_prot = {
	.name		   = "RAWv6",
	.owner		   = THIS_MODULE,
	.close		   = rawv6_close,
	.destroy	   = raw6_destroy,
	.connect	   = ip6_datagram_connect,
	.disconnect	   = udp_disconnect,
	.ioctl		   = rawv6_ioctl,
	.init		   = rawv6_init_sk,
	.setsockopt	   = rawv6_setsockopt,
	.getsockopt	   = rawv6_getsockopt,
	.sendmsg	   = rawv6_sendmsg,
	.recvmsg	   = rawv6_recvmsg,
	.bind		   = rawv6_bind,
	.backlog_rcv	   = rawv6_rcv_skb,
	.hash		   = raw_hash_sk,
	.unhash		   = raw_unhash_sk,
	.obj_size	   = sizeof(struct raw6_sock),
	.h.raw_hash	   = &raw_v6_hashinfo,
#ifdef CONFIG_COMPAT
	.compat_setsockopt = compat_rawv6_setsockopt,
	.compat_getsockopt = compat_rawv6_getsockopt,
	.compat_ioctl	   = compat_rawv6_ioctl,
#endif
};

#ifdef CONFIG_PROC_FS
static int raw6_seq_show(struct seq_file *seq, void *v)
{
	if (v == SEQ_START_TOKEN) {
		seq_puts(seq, IPV6_SEQ_DGRAM_HEADER);
	} else {
		struct sock *sp = v;
		__u16 srcp  = inet_sk(sp)->inet_num;
		ip6_dgram_sock_seq_show(seq, v, srcp, 0,
					raw_seq_private(seq)->bucket);
	}
	return 0;
}

static const struct seq_operations raw6_seq_ops = {
	.start =	raw_seq_start,
	.next =		raw_seq_next,
	.stop =		raw_seq_stop,
	.show =		raw6_seq_show,
};

static int raw6_seq_open(struct inode *inode, struct file *file)
{
	return raw_seq_open(inode, file, &raw_v6_hashinfo, &raw6_seq_ops);
}

static const struct file_operations raw6_seq_fops = {
	.owner =	THIS_MODULE,
	.open =		raw6_seq_open,
	.read =		seq_read,
	.llseek =	seq_lseek,
	.release =	seq_release_net,
};

static int __net_init raw6_init_net(struct net *net)
{
	if (!proc_create("raw6", S_IRUGO, net->proc_net, &raw6_seq_fops))
		return -ENOMEM;

	return 0;
}

static void __net_exit raw6_exit_net(struct net *net)
{
	remove_proc_entry("raw6", net->proc_net);
}

static struct pernet_operations raw6_net_ops = {
	.init = raw6_init_net,
	.exit = raw6_exit_net,
};

int __init raw6_proc_init(void)
{
	return register_pernet_subsys(&raw6_net_ops);
}

void raw6_proc_exit(void)
{
	unregister_pernet_subsys(&raw6_net_ops);
}
#endif	/* CONFIG_PROC_FS */

/* Same as inet6_dgram_ops, sans udp_poll.  */
static const struct proto_ops inet6_sockraw_ops = {
	.family		   = PF_INET6,
	.owner		   = THIS_MODULE,
	.release	   = inet6_release,
	.bind		   = inet6_bind,
	.connect	   = inet_dgram_connect,	/* ok		*/
	.socketpair	   = sock_no_socketpair,	/* a do nothing	*/
	.accept		   = sock_no_accept,		/* a do nothing	*/
	.getname	   = inet6_getname,
	.poll		   = datagram_poll,		/* ok		*/
	.ioctl		   = inet6_ioctl,		/* must change  */
	.listen		   = sock_no_listen,		/* ok		*/
	.shutdown	   = inet_shutdown,		/* ok		*/
	.setsockopt	   = sock_common_setsockopt,	/* ok		*/
	.getsockopt	   = sock_common_getsockopt,	/* ok		*/
	.sendmsg	   = inet_sendmsg,		/* ok		*/
	.recvmsg	   = sock_common_recvmsg,	/* ok		*/
	.mmap		   = sock_no_mmap,
	.sendpage	   = sock_no_sendpage,
#ifdef CONFIG_COMPAT
	.compat_setsockopt = compat_sock_common_setsockopt,
	.compat_getsockopt = compat_sock_common_getsockopt,
#endif
};

static struct inet_protosw rawv6_protosw = {
	.type		= SOCK_RAW,
	.protocol	= IPPROTO_IP,	/* wild card */
	.prot		= &rawv6_prot,
	.ops		= &inet6_sockraw_ops,
	.no_check	= UDP_CSUM_DEFAULT,
	.flags		= INET_PROTOSW_REUSE,
};

int __init rawv6_init(void)
{
	int ret;

	ret = inet6_register_protosw(&rawv6_protosw);
	if (ret)
		goto out;
out:
	return ret;
}

void rawv6_exit(void)
{
	inet6_unregister_protosw(&rawv6_protosw);
}