aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv6/udp.c
blob: 023beda6b22445f52f75e13fc3e0000b78d42342 (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
/*
 *	UDP over IPv6
 *	Linux INET6 implementation
 *
 *	Authors:
 *	Pedro Roque		<roque@di.fc.ul.pt>
 *
 *	Based on linux/ipv4/udp.c
 *
 *	Fixes:
 *	Hideaki YOSHIFUJI	:	sin6_scope_id support
 *	YOSHIFUJI Hideaki @USAGI and:	Support IPV6_V6ONLY socket option, which
 *	Alexey Kuznetsov		allow both IPv4 and IPv6 sockets to bind
 *					a single port at the same time.
 *      Kazunori MIYAZAWA @USAGI:       change process style to use ip6_append_data
 *      YOSHIFUJI Hideaki @USAGI:	convert /proc/net/udp6 to seq_file.
 *
 *	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/sockios.h>
#include <linux/net.h>
#include <linux/in6.h>
#include <linux/netdevice.h>
#include <linux/if_arp.h>
#include <linux/ipv6.h>
#include <linux/icmpv6.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/skbuff.h>
#include <asm/uaccess.h>

#include <net/ndisc.h>
#include <net/protocol.h>
#include <net/transp_v6.h>
#include <net/ip6_route.h>
#include <net/raw.h>
#include <net/tcp_states.h>
#include <net/ip6_checksum.h>
#include <net/xfrm.h>

#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include "udp_impl.h"

int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2)
{
	const struct in6_addr *sk_rcv_saddr6 = &inet6_sk(sk)->rcv_saddr;
	const struct in6_addr *sk2_rcv_saddr6 = inet6_rcv_saddr(sk2);
	__be32 sk_rcv_saddr = inet_sk(sk)->rcv_saddr;
	__be32 sk2_rcv_saddr = inet_rcv_saddr(sk2);
	int sk_ipv6only = ipv6_only_sock(sk);
	int sk2_ipv6only = inet_v6_ipv6only(sk2);
	int addr_type = ipv6_addr_type(sk_rcv_saddr6);
	int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED;

	/* if both are mapped, treat as IPv4 */
	if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED)
		return (!sk2_ipv6only &&
			(!sk_rcv_saddr || !sk2_rcv_saddr ||
			  sk_rcv_saddr == sk2_rcv_saddr));

	if (addr_type2 == IPV6_ADDR_ANY &&
	    !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED))
		return 1;

	if (addr_type == IPV6_ADDR_ANY &&
	    !(sk_ipv6only && addr_type2 == IPV6_ADDR_MAPPED))
		return 1;

	if (sk2_rcv_saddr6 &&
	    ipv6_addr_equal(sk_rcv_saddr6, sk2_rcv_saddr6))
		return 1;

	return 0;
}

int udp_v6_get_port(struct sock *sk, unsigned short snum)
{
	return udp_lib_get_port(sk, snum, ipv6_rcv_saddr_equal);
}

static inline int compute_score(struct sock *sk, struct net *net,
				unsigned short hnum,
				struct in6_addr *saddr, __be16 sport,
				struct in6_addr *daddr, __be16 dport,
				int dif)
{
	int score = -1;

	if (net_eq(sock_net(sk), net) && sk->sk_hash == hnum &&
			sk->sk_family == PF_INET6) {
		struct ipv6_pinfo *np = inet6_sk(sk);
		struct inet_sock *inet = inet_sk(sk);

		score = 0;
		if (inet->dport) {
			if (inet->dport != sport)
				return -1;
			score++;
		}
		if (!ipv6_addr_any(&np->rcv_saddr)) {
			if (!ipv6_addr_equal(&np->rcv_saddr, daddr))
				return -1;
			score++;
		}
		if (!ipv6_addr_any(&np->daddr)) {
			if (!ipv6_addr_equal(&np->daddr, saddr))
				return -1;
			score++;
		}
		if (sk->sk_bound_dev_if) {
			if (sk->sk_bound_dev_if != dif)
				return -1;
			score++;
		}
	}
	return score;
}

static struct sock *__udp6_lib_lookup(struct net *net,
				      struct in6_addr *saddr, __be16 sport,
				      struct in6_addr *daddr, __be16 dport,
				      int dif, struct udp_table *udptable)
{
	struct sock *sk, *result;
	struct hlist_nulls_node *node;
	unsigned short hnum = ntohs(dport);
	unsigned int hash = udp_hashfn(net, hnum);
	struct udp_hslot *hslot = &udptable->hash[hash];
	int score, badness;

	rcu_read_lock();
begin:
	result = NULL;
	badness = -1;
	sk_nulls_for_each_rcu(sk, node, &hslot->head) {
		score = compute_score(sk, net, hnum, saddr, sport, daddr, dport, dif);
		if (score > badness) {
			result = sk;
			badness = score;
		}
	}
	/*
	 * if the nulls value we got at the end of this lookup is
	 * not the expected one, we must restart lookup.
	 * We probably met an item that was moved to another chain.
	 */
	if (get_nulls_value(node) != hash)
		goto begin;

	if (result) {
		if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt)))
			result = NULL;
		else if (unlikely(compute_score(result, net, hnum, saddr, sport,
					daddr, dport, dif) < badness)) {
			sock_put(result);
			goto begin;
		}
	}
	rcu_read_unlock();
	return result;
}

static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb,
					  __be16 sport, __be16 dport,
					  struct udp_table *udptable)
{
	struct sock *sk;
	struct ipv6hdr *iph = ipv6_hdr(skb);

	if (unlikely(sk = skb_steal_sock(skb)))
		return sk;
	return __udp6_lib_lookup(dev_net(skb_dst(skb)->dev), &iph->saddr, sport,
				 &iph->daddr, dport, inet6_iif(skb),
				 udptable);
}

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

int udpv6_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 inet_sock *inet = inet_sk(sk);
	struct sk_buff *skb;
	unsigned int ulen, copied;
	int peeked;
	int err;
	int is_udplite = IS_UDPLITE(sk);
	int is_udp4;

	if (addr_len)
		*addr_len=sizeof(struct sockaddr_in6);

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

try_again:
	skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
				  &peeked, &err);
	if (!skb)
		goto out;

	ulen = skb->len - sizeof(struct udphdr);
	copied = len;
	if (copied > ulen)
		copied = ulen;
	else if (copied < ulen)
		msg->msg_flags |= MSG_TRUNC;

	is_udp4 = (skb->protocol == htons(ETH_P_IP));

	/*
	 * If checksum is needed at all, try to do it while copying the
	 * data.  If the data is truncated, or if we only want a partial
	 * coverage checksum (UDP-Lite), do it before the copy.
	 */

	if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) {
		if (udp_lib_checksum_complete(skb))
			goto csum_copy_err;
	}

	if (skb_csum_unnecessary(skb))
		err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr),
					      msg->msg_iov, copied       );
	else {
		err = skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov);
		if (err == -EINVAL)
			goto csum_copy_err;
	}
	if (err)
		goto out_free;

	if (!peeked) {
		if (is_udp4)
			UDP_INC_STATS_USER(sock_net(sk),
					UDP_MIB_INDATAGRAMS, is_udplite);
		else
			UDP6_INC_STATS_USER(sock_net(sk),
					UDP_MIB_INDATAGRAMS, is_udplite);
	}

	sock_recv_timestamp(msg, sk, skb);

	/* Copy the address. */
	if (msg->msg_name) {
		struct sockaddr_in6 *sin6;

		sin6 = (struct sockaddr_in6 *) msg->msg_name;
		sin6->sin6_family = AF_INET6;
		sin6->sin6_port = udp_hdr(skb)->source;
		sin6->sin6_flowinfo = 0;
		sin6->sin6_scope_id = 0;

		if (is_udp4)
			ipv6_addr_set(&sin6->sin6_addr, 0, 0,
				      htonl(0xffff), ip_hdr(skb)->saddr);
		else {
			ipv6_addr_copy(&sin6->sin6_addr,
				       &ipv6_hdr(skb)->saddr);
			if (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL)
				sin6->sin6_scope_id = IP6CB(skb)->iif;
		}

	}
	if (is_udp4) {
		if (inet->cmsg_flags)
			ip_cmsg_recv(msg, skb);
	} else {
		if (np->rxopt.all)
			datagram_recv_ctl(sk, msg, skb);
	}

	err = copied;
	if (flags & MSG_TRUNC)
		err = ulen;

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

csum_copy_err:
	lock_sock(sk);
	if (!skb_kill_datagram(sk, skb, flags)) {
		if (is_udp4)
			UDP_INC_STATS_USER(sock_net(sk),
					UDP_MIB_INERRORS, is_udplite);
		else
			UDP6_INC_STATS_USER(sock_net(sk),
					UDP_MIB_INERRORS, is_udplite);
	}
	release_sock(sk);

	if (flags & MSG_DONTWAIT)
		return -EAGAIN;
	goto try_again;
}

void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
		    int type, int code, int offset, __be32 info,
		    struct udp_table *udptable)
{
	struct ipv6_pinfo *np;
	struct ipv6hdr *hdr = (struct ipv6hdr*)skb->data;
	struct in6_addr *saddr = &hdr->saddr;
	struct in6_addr *daddr = &hdr->daddr;
	struct udphdr *uh = (struct udphdr*)(skb->data+offset);
	struct sock *sk;
	int err;

	sk = __udp6_lib_lookup(dev_net(skb->dev), daddr, uh->dest,
			       saddr, uh->source, inet6_iif(skb), udptable);
	if (sk == NULL)
		return;

	np = inet6_sk(sk);

	if (!icmpv6_err_convert(type, code, &err) && !np->recverr)
		goto out;

	if (sk->sk_state != TCP_ESTABLISHED && !np->recverr)
		goto out;

	if (np->recverr)
		ipv6_icmp_error(sk, skb, err, uh->dest, ntohl(info), (u8 *)(uh+1));

	sk->sk_err = err;
	sk->sk_error_report(sk);
out:
	sock_put(sk);
}

static __inline__ void udpv6_err(struct sk_buff *skb,
				 struct inet6_skb_parm *opt, int type,
				 int code, int offset, __be32 info     )
{
	__udp6_lib_err(skb, opt, type, code, offset, info, &udp_table);
}

int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
{
	struct udp_sock *up = udp_sk(sk);
	int rc;
	int is_udplite = IS_UDPLITE(sk);

	if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
		goto drop;

	/*
	 * UDP-Lite specific tests, ignored on UDP sockets (see net/ipv4/udp.c).
	 */
	if ((is_udplite & UDPLITE_RECV_CC)  &&  UDP_SKB_CB(skb)->partial_cov) {

		if (up->pcrlen == 0) {          /* full coverage was set  */
			LIMIT_NETDEBUG(KERN_WARNING "UDPLITE6: partial coverage"
				" %d while full coverage %d requested\n",
				UDP_SKB_CB(skb)->cscov, skb->len);
			goto drop;
		}
		if (UDP_SKB_CB(skb)->cscov  <  up->pcrlen) {
			LIMIT_NETDEBUG(KERN_WARNING "UDPLITE6: coverage %d "
						    "too small, need min %d\n",
				       UDP_SKB_CB(skb)->cscov, up->pcrlen);
			goto drop;
		}
	}

	if (sk->sk_filter) {
		if (udp_lib_checksum_complete(skb))
			goto drop;
	}

	if ((rc = sock_queue_rcv_skb(sk,skb)) < 0) {
		/* Note that an ENOMEM error is charged twice */
		if (rc == -ENOMEM) {
			UDP6_INC_STATS_BH(sock_net(sk),
					UDP_MIB_RCVBUFERRORS, is_udplite);
			atomic_inc(&sk->sk_drops);
		}
		goto drop;
	}

	return 0;
drop:
	UDP6_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
	kfree_skb(skb);
	return -1;
}

static struct sock *udp_v6_mcast_next(struct net *net, struct sock *sk,
				      __be16 loc_port, struct in6_addr *loc_addr,
				      __be16 rmt_port, struct in6_addr *rmt_addr,
				      int dif)
{
	struct hlist_nulls_node *node;
	struct sock *s = sk;
	unsigned short num = ntohs(loc_port);

	sk_nulls_for_each_from(s, node) {
		struct inet_sock *inet = inet_sk(s);

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

		if (s->sk_hash == num && s->sk_family == PF_INET6) {
			struct ipv6_pinfo *np = inet6_sk(s);
			if (inet->dport) {
				if (inet->dport != rmt_port)
					continue;
			}
			if (!ipv6_addr_any(&np->daddr) &&
			    !ipv6_addr_equal(&np->daddr, rmt_addr))
				continue;

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

			if (!ipv6_addr_any(&np->rcv_saddr)) {
				if (!ipv6_addr_equal(&np->rcv_saddr, loc_addr))
					continue;
			}
			if (!inet6_mc_check(s, loc_addr, rmt_addr))
				continue;
			return s;
		}
	}
	return NULL;
}

/*
 * Note: called only from the BH handler context,
 * so we don't need to lock the hashes.
 */
static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
		struct in6_addr *saddr, struct in6_addr *daddr,
		struct udp_table *udptable)
{
	struct sock *sk, *sk2;
	const struct udphdr *uh = udp_hdr(skb);
	struct udp_hslot *hslot = &udptable->hash[udp_hashfn(net, ntohs(uh->dest))];
	int dif;

	spin_lock(&hslot->lock);
	sk = sk_nulls_head(&hslot->head);
	dif = inet6_iif(skb);
	sk = udp_v6_mcast_next(net, sk, uh->dest, daddr, uh->source, saddr, dif);
	if (!sk) {
		kfree_skb(skb);
		goto out;
	}

	sk2 = sk;
	while ((sk2 = udp_v6_mcast_next(net, sk_nulls_next(sk2), uh->dest, daddr,
					uh->source, saddr, dif))) {
		struct sk_buff *buff = skb_clone(skb, GFP_ATOMIC);
		if (buff) {
			bh_lock_sock(sk2);
			if (!sock_owned_by_user(sk2))
				udpv6_queue_rcv_skb(sk2, buff);
			else
				sk_add_backlog(sk2, buff);
			bh_unlock_sock(sk2);
		}
	}
	bh_lock_sock(sk);
	if (!sock_owned_by_user(sk))
		udpv6_queue_rcv_skb(sk, skb);
	else
		sk_add_backlog(sk, skb);
	bh_unlock_sock(sk);
out:
	spin_unlock(&hslot->lock);
	return 0;
}

static inline int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh,
				 int proto)
{
	int err;

	UDP_SKB_CB(skb)->partial_cov = 0;
	UDP_SKB_CB(skb)->cscov = skb->len;

	if (proto == IPPROTO_UDPLITE) {
		err = udplite_checksum_init(skb, uh);
		if (err)
			return err;
	}

	if (uh->check == 0) {
		/* RFC 2460 section 8.1 says that we SHOULD log
		   this error. Well, it is reasonable.
		 */
		LIMIT_NETDEBUG(KERN_INFO "IPv6: udp checksum is 0\n");
		return 1;
	}
	if (skb->ip_summed == CHECKSUM_COMPLETE &&
	    !csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr,
			     skb->len, proto, 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, proto, 0));

	return 0;
}

int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
		   int proto)
{
	struct sock *sk;
	struct udphdr *uh;
	struct net_device *dev = skb->dev;
	struct in6_addr *saddr, *daddr;
	u32 ulen = 0;
	struct net *net = dev_net(skb->dev);

	if (!pskb_may_pull(skb, sizeof(struct udphdr)))
		goto short_packet;

	saddr = &ipv6_hdr(skb)->saddr;
	daddr = &ipv6_hdr(skb)->daddr;
	uh = udp_hdr(skb);

	ulen = ntohs(uh->len);
	if (ulen > skb->len)
		goto short_packet;

	if (proto == IPPROTO_UDP) {
		/* UDP validates ulen. */

		/* Check for jumbo payload */
		if (ulen == 0)
			ulen = skb->len;

		if (ulen < sizeof(*uh))
			goto short_packet;

		if (ulen < skb->len) {
			if (pskb_trim_rcsum(skb, ulen))
				goto short_packet;
			saddr = &ipv6_hdr(skb)->saddr;
			daddr = &ipv6_hdr(skb)->daddr;
			uh = udp_hdr(skb);
		}
	}

	if (udp6_csum_init(skb, uh, proto))
		goto discard;

	/*
	 *	Multicast receive code
	 */
	if (ipv6_addr_is_multicast(daddr))
		return __udp6_lib_mcast_deliver(net, skb,
				saddr, daddr, udptable);

	/* Unicast */

	/*
	 * check socket cache ... must talk to Alan about his plans
	 * for sock caches... i'll skip this for now.
	 */
	sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest, udptable);

	if (sk == NULL) {
		if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
			goto discard;

		if (udp_lib_checksum_complete(skb))
			goto discard;
		UDP6_INC_STATS_BH(net, UDP_MIB_NOPORTS,
				proto == IPPROTO_UDPLITE);

		icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0, dev);

		kfree_skb(skb);
		return 0;
	}

	/* deliver */

	bh_lock_sock(sk);
	if (!sock_owned_by_user(sk))
		udpv6_queue_rcv_skb(sk, skb);
	else
		sk_add_backlog(sk, skb);
	bh_unlock_sock(sk);
	sock_put(sk);
	return 0;

short_packet:
	LIMIT_NETDEBUG(KERN_DEBUG "UDP%sv6: short packet: %d/%u\n",
		       proto == IPPROTO_UDPLITE ? "-Lite" : "",
		       ulen, skb->len);

discard:
	UDP6_INC_STATS_BH(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE);
	kfree_skb(skb);
	return 0;
}

static __inline__ int udpv6_rcv(struct sk_buff *skb)
{
	return __udp6_lib_rcv(skb, &udp_table, IPPROTO_UDP);
}

/*
 * Throw away all pending data and cancel the corking. Socket is locked.
 */
static void udp_v6_flush_pending_frames(struct sock *sk)
{
	struct udp_sock *up = udp_sk(sk);

	if (up->pending == AF_INET)
		udp_flush_pending_frames(sk);
	else if (up->pending) {
		up->len = 0;
		up->pending = 0;
		ip6_flush_pending_frames(sk);
	}
}

/*
 *	Sending
 */

static int udp_v6_push_pending_frames(struct sock *sk)
{
	struct sk_buff *skb;
	struct udphdr *uh;
	struct udp_sock  *up = udp_sk(sk);
	struct inet_sock *inet = inet_sk(sk);
	struct flowi *fl = &inet->cork.fl;
	int err = 0;
	int is_udplite = IS_UDPLITE(sk);
	__wsum csum = 0;

	/* Grab the skbuff where UDP header space exists. */
	if ((skb = skb_peek(&sk->sk_write_queue)) == NULL)
		goto out;

	/*
	 * Create a UDP header
	 */
	uh = udp_hdr(skb);
	uh->source = fl->fl_ip_sport;
	uh->dest = fl->fl_ip_dport;
	uh->len = htons(up->len);
	uh->check = 0;

	if (is_udplite)
		csum = udplite_csum_outgoing(sk, skb);
	 else
		csum = udp_csum_outgoing(sk, skb);

	/* add protocol-dependent pseudo-header */
	uh->check = csum_ipv6_magic(&fl->fl6_src, &fl->fl6_dst,
				    up->len, fl->proto, csum   );
	if (uh->check == 0)
		uh->check = CSUM_MANGLED_0;

	err = ip6_push_pending_frames(sk);
out:
	up->len = 0;
	up->pending = 0;
	if (!err)
		UDP6_INC_STATS_USER(sock_net(sk),
				UDP_MIB_OUTDATAGRAMS, is_udplite);
	return err;
}

int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk,
		  struct msghdr *msg, size_t len)
{
	struct ipv6_txoptions opt_space;
	struct udp_sock *up = udp_sk(sk);
	struct inet_sock *inet = inet_sk(sk);
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) msg->msg_name;
	struct in6_addr *daddr, *final_p = NULL, final;
	struct ipv6_txoptions *opt = NULL;
	struct ip6_flowlabel *flowlabel = NULL;
	struct flowi fl;
	struct dst_entry *dst;
	int addr_len = msg->msg_namelen;
	int ulen = len;
	int hlimit = -1;
	int tclass = -1;
	int corkreq = up->corkflag || msg->msg_flags&MSG_MORE;
	int err;
	int connected = 0;
	int is_udplite = IS_UDPLITE(sk);
	int (*getfrag)(void *, char *, int, int, int, struct sk_buff *);

	/* destination address check */
	if (sin6) {
		if (addr_len < offsetof(struct sockaddr, sa_data))
			return -EINVAL;

		switch (sin6->sin6_family) {
		case AF_INET6:
			if (addr_len < SIN6_LEN_RFC2133)
				return -EINVAL;
			daddr = &sin6->sin6_addr;
			break;
		case AF_INET:
			goto do_udp_sendmsg;
		case AF_UNSPEC:
			msg->msg_name = sin6 = NULL;
			msg->msg_namelen = addr_len = 0;
			daddr = NULL;
			break;
		default:
			return -EINVAL;
		}
	} else if (!up->pending) {
		if (sk->sk_state != TCP_ESTABLISHED)
			return -EDESTADDRREQ;
		daddr = &np->daddr;
	} else
		daddr = NULL;

	if (daddr) {
		if (ipv6_addr_v4mapped(daddr)) {
			struct sockaddr_in sin;
			sin.sin_family = AF_INET;
			sin.sin_port = sin6 ? sin6->sin6_port : inet->dport;
			sin.sin_addr.s_addr = daddr->s6_addr32[3];
			msg->msg_name = &sin;
			msg->msg_namelen = sizeof(sin);
do_udp_sendmsg:
			if (__ipv6_only_sock(sk))
				return -ENETUNREACH;
			return udp_sendmsg(iocb, sk, msg, len);
		}
	}

	if (up->pending == AF_INET)
		return udp_sendmsg(iocb, sk, msg, len);

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

	if (up->pending) {
		/*
		 * There are pending frames.
		 * The socket lock must be held while it's corked.
		 */
		lock_sock(sk);
		if (likely(up->pending)) {
			if (unlikely(up->pending != AF_INET6)) {
				release_sock(sk);
				return -EAFNOSUPPORT;
			}
			dst = NULL;
			goto do_append_data;
		}
		release_sock(sk);
	}
	ulen += sizeof(struct udphdr);

	memset(&fl, 0, sizeof(fl));

	if (sin6) {
		if (sin6->sin6_port == 0)
			return -EINVAL;

		fl.fl_ip_dport = sin6->sin6_port;
		daddr = &sin6->sin6_addr;

		if (np->sndflow) {
			fl.fl6_flowlabel = sin6->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;
				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_type(daddr)&IPV6_ADDR_LINKLOCAL)
			fl.oif = sin6->sin6_scope_id;
	} else {
		if (sk->sk_state != TCP_ESTABLISHED)
			return -EDESTADDRREQ;

		fl.fl_ip_dport = inet->dport;
		daddr = &np->daddr;
		fl.fl6_flowlabel = np->flow_label;
		connected = 1;
	}

	if (!fl.oif)
		fl.oif = sk->sk_bound_dev_if;

	if (!fl.oif)
		fl.oif = np->sticky_pktinfo.ipi6_ifindex;

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

		err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit, &tclass);
		if (err < 0) {
			fl6_sock_release(flowlabel);
			return err;
		}
		if ((fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) {
			flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel);
			if (flowlabel == NULL)
				return -EINVAL;
		}
		if (!(opt->opt_nflen|opt->opt_flen))
			opt = NULL;
		connected = 0;
	}
	if (opt == NULL)
		opt = np->opt;
	if (flowlabel)
		opt = fl6_merge_options(&opt_space, flowlabel, opt);
	opt = ipv6_fixup_options(&opt_space, opt);

	fl.proto = sk->sk_protocol;
	if (!ipv6_addr_any(daddr))
		ipv6_addr_copy(&fl.fl6_dst, daddr);
	else
		fl.fl6_dst.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */
	if (ipv6_addr_any(&fl.fl6_src) && !ipv6_addr_any(&np->saddr))
		ipv6_addr_copy(&fl.fl6_src, &np->saddr);
	fl.fl_ip_sport = inet->sport;

	/* merge ip6_build_xmit from ip6_output */
	if (opt && opt->srcrt) {
		struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt;
		ipv6_addr_copy(&final, &fl.fl6_dst);
		ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
		final_p = &final;
		connected = 0;
	}

	if (!fl.oif && ipv6_addr_is_multicast(&fl.fl6_dst)) {
		fl.oif = np->mcast_oif;
		connected = 0;
	}

	security_sk_classify_flow(sk, &fl);

	err = ip6_sk_dst_lookup(sk, &dst, &fl);
	if (err)
		goto out;
	if (final_p)
		ipv6_addr_copy(&fl.fl6_dst, final_p);

	err = __xfrm_lookup(sock_net(sk), &dst, &fl, sk, XFRM_LOOKUP_WAIT);
	if (err < 0) {
		if (err == -EREMOTE)
			err = ip6_dst_blackhole(sk, &dst, &fl);
		if (err < 0)
			goto out;
	}

	if (hlimit < 0) {
		if (ipv6_addr_is_multicast(&fl.fl6_dst))
			hlimit = np->mcast_hops;
		else
			hlimit = np->hop_limit;
		if (hlimit < 0)
			hlimit = ip6_dst_hoplimit(dst);
	}

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

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

	lock_sock(sk);
	if (unlikely(up->pending)) {
		/* The socket is already corked while preparing it. */
		/* ... which is an evident application bug. --ANK */
		release_sock(sk);

		LIMIT_NETDEBUG(KERN_DEBUG "udp cork app bug 2\n");
		err = -EINVAL;
		goto out;
	}

	up->pending = AF_INET6;

do_append_data:
	up->len += ulen;
	getfrag  =  is_udplite ?  udplite_getfrag : ip_generic_getfrag;
	err = ip6_append_data(sk, getfrag, msg->msg_iov, ulen,
		sizeof(struct udphdr), hlimit, tclass, opt, &fl,
		(struct rt6_info*)dst,
		corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags);
	if (err)
		udp_v6_flush_pending_frames(sk);
	else if (!corkreq)
		err = udp_v6_push_pending_frames(sk);
	else if (unlikely(skb_queue_empty(&sk->sk_write_queue)))
		up->pending = 0;

	if (dst) {
		if (connected) {
			ip6_dst_store(sk, dst,
				      ipv6_addr_equal(&fl.fl6_dst, &np->daddr) ?
				      &np->daddr : NULL,
#ifdef CONFIG_IPV6_SUBTREES
				      ipv6_addr_equal(&fl.fl6_src, &np->saddr) ?
				      &np->saddr :
#endif
				      NULL);
		} else {
			dst_release(dst);
		}
		dst = NULL;
	}

	if (err > 0)
		err = np->recverr ? net_xmit_errno(err) : 0;
	release_sock(sk);
out:
	dst_release(dst);
	fl6_sock_release(flowlabel);
	if (!err)
		return len;
	/*
	 * ENOBUFS = no kernel mem, SOCK_NOSPACE = no sndbuf space.  Reporting
	 * ENOBUFS might not be good (it's not tunable per se), but otherwise
	 * we don't have a good statistic (IpOutDiscards but it can be too many
	 * things).  We could add another new stat but at least for now that
	 * seems like overkill.
	 */
	if (err == -ENOBUFS || test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
		UDP6_INC_STATS_USER(sock_net(sk),
				UDP_MIB_SNDBUFERRORS, is_udplite);
	}
	return err;

do_confirm:
	dst_confirm(dst);
	if (!(msg->msg_flags&MSG_PROBE) || len)
		goto back_from_confirm;
	err = 0;
	goto out;
}

void udpv6_destroy_sock(struct sock *sk)
{
	lock_sock(sk);
	udp_v6_flush_pending_frames(sk);
	release_sock(sk);

	inet6_destroy_sock(sk);
}

/*
 *	Socket option code for UDP
 */
int udpv6_setsockopt(struct sock *sk, int level, int optname,
		     char __user *optval, int optlen)
{
	if (level == SOL_UDP  ||  level == SOL_UDPLITE)
		return udp_lib_setsockopt(sk, level, optname, optval, optlen,
					  udp_v6_push_pending_frames);
	return ipv6_setsockopt(sk, level, optname, optval, optlen);
}

#ifdef CONFIG_COMPAT
int compat_udpv6_setsockopt(struct sock *sk, int level, int optname,
			    char __user *optval, int optlen)
{
	if (level == SOL_UDP  ||  level == SOL_UDPLITE)
		return udp_lib_setsockopt(sk, level, optname, optval, optlen,
					  udp_v6_push_pending_frames);
	return compat_ipv6_setsockopt(sk, level, optname, optval, optlen);
}
#endif

int udpv6_getsockopt(struct sock *sk, int level, int optname,
		     char __user *optval, int __user *optlen)
{
	if (level == SOL_UDP  ||  level == SOL_UDPLITE)
		return udp_lib_getsockopt(sk, level, optname, optval, optlen);
	return ipv6_getsockopt(sk, level, optname, optval, optlen);
}

#ifdef CONFIG_COMPAT
int compat_udpv6_getsockopt(struct sock *sk, int level, int optname,
			    char __user *optval, int __user *optlen)
{
	if (level == SOL_UDP  ||  level == SOL_UDPLITE)
		return udp_lib_getsockopt(sk, level, optname, optval, optlen);
	return compat_ipv6_getsockopt(sk, level, optname, optval, optlen);
}
#endif

static struct inet6_protocol udpv6_protocol = {
	.handler	=	udpv6_rcv,
	.err_handler	=	udpv6_err,
	.flags		=	INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
};

/* ------------------------------------------------------------------------ */
#ifdef CONFIG_PROC_FS

static void udp6_sock_seq_show(struct seq_file *seq, struct sock *sp, int bucket)
{
	struct inet_sock *inet = inet_sk(sp);
	struct ipv6_pinfo *np = inet6_sk(sp);
	struct in6_addr *dest, *src;
	__u16 destp, srcp;

	dest  = &np->daddr;
	src   = &np->rcv_saddr;
	destp = ntohs(inet->dport);
	srcp  = ntohs(inet->sport);
	seq_printf(seq,
		   "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
		   "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d\n",
		   bucket,
		   src->s6_addr32[0], src->s6_addr32[1],
		   src->s6_addr32[2], src->s6_addr32[3], srcp,
		   dest->s6_addr32[0], dest->s6_addr32[1],
		   dest->s6_addr32[2], dest->s6_addr32[3], destp,
		   sp->sk_state,
		   sk_wmem_alloc_get(sp),
		   sk_rmem_alloc_get(sp),
		   0, 0L, 0,
		   sock_i_uid(sp), 0,
		   sock_i_ino(sp),
		   atomic_read(&sp->sk_refcnt), sp,
		   atomic_read(&sp->sk_drops));
}

int udp6_seq_show(struct seq_file *seq, void *v)
{
	if (v == SEQ_START_TOKEN)
		seq_printf(seq,
			   "  sl  "
			   "local_address                         "
			   "remote_address                        "
			   "st tx_queue rx_queue tr tm->when retrnsmt"
			   "   uid  timeout inode ref pointer drops\n");
	else
		udp6_sock_seq_show(seq, v, ((struct udp_iter_state *)seq->private)->bucket);
	return 0;
}

static struct udp_seq_afinfo udp6_seq_afinfo = {
	.name		= "udp6",
	.family		= AF_INET6,
	.udp_table	= &udp_table,
	.seq_fops	= {
		.owner	=	THIS_MODULE,
	},
	.seq_ops	= {
		.show		= udp6_seq_show,
	},
};

int udp6_proc_init(struct net *net)
{
	return udp_proc_register(net, &udp6_seq_afinfo);
}

void udp6_proc_exit(struct net *net) {
	udp_proc_unregister(net, &udp6_seq_afinfo);
}
#endif /* CONFIG_PROC_FS */

/* ------------------------------------------------------------------------ */

struct proto udpv6_prot = {
	.name		   = "UDPv6",
	.owner		   = THIS_MODULE,
	.close		   = udp_lib_close,
	.connect	   = ip6_datagram_connect,
	.disconnect	   = udp_disconnect,
	.ioctl		   = udp_ioctl,
	.destroy	   = udpv6_destroy_sock,
	.setsockopt	   = udpv6_setsockopt,
	.getsockopt	   = udpv6_getsockopt,
	.sendmsg	   = udpv6_sendmsg,
	.recvmsg	   = udpv6_recvmsg,
	.backlog_rcv	   = udpv6_queue_rcv_skb,
	.hash		   = udp_lib_hash,
	.unhash		   = udp_lib_unhash,
	.get_port	   = udp_v6_get_port,
	.memory_allocated  = &udp_memory_allocated,
	.sysctl_mem	   = sysctl_udp_mem,
	.sysctl_wmem	   = &sysctl_udp_wmem_min,
	.sysctl_rmem	   = &sysctl_udp_rmem_min,
	.obj_size	   = sizeof(struct udp6_sock),
	.slab_flags	   = SLAB_DESTROY_BY_RCU,
	.h.udp_table	   = &udp_table,
#ifdef CONFIG_COMPAT
	.compat_setsockopt = compat_udpv6_setsockopt,
	.compat_getsockopt = compat_udpv6_getsockopt,
#endif
};

static struct inet_protosw udpv6_protosw = {
	.type =      SOCK_DGRAM,
	.protocol =  IPPROTO_UDP,
	.prot =      &udpv6_prot,
	.ops =       &inet6_dgram_ops,
	.capability =-1,
	.no_check =  UDP_CSUM_DEFAULT,
	.flags =     INET_PROTOSW_PERMANENT,
};


int __init udpv6_init(void)
{
	int ret;

	ret = inet6_add_protocol(&udpv6_protocol, IPPROTO_UDP);
	if (ret)
		goto out;

	ret = inet6_register_protosw(&udpv6_protosw);
	if (ret)
		goto out_udpv6_protocol;
out:
	return ret;

out_udpv6_protocol:
	inet6_del_protocol(&udpv6_protocol, IPPROTO_UDP);
	goto out;
}

void udpv6_exit(void)
{
	inet6_unregister_protosw(&udpv6_protosw);
	inet6_del_protocol(&udpv6_protocol, IPPROTO_UDP);
}