forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathdatagram.c
1049 lines (883 loc) · 24.8 KB
/
datagram.c
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
/*
* common UDP/RAW code
* Linux INET6 implementation
*
* Authors:
* Pedro Roque <[email protected]>
*
* 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/capability.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/kernel.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 <linux/slab.h>
#include <linux/export.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 <net/dsfield.h>
#include <linux/errqueue.h>
#include <linux/uaccess.h>
static bool ipv6_mapped_addr_any(const struct in6_addr *a)
{
return ipv6_addr_v4mapped(a) && (a->s6_addr32[3] == 0);
}
static void ip6_datagram_flow_key_init(struct flowi6 *fl6, struct sock *sk)
{
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
memset(fl6, 0, sizeof(*fl6));
fl6->flowi6_proto = sk->sk_protocol;
fl6->daddr = sk->sk_v6_daddr;
fl6->saddr = np->saddr;
fl6->flowi6_oif = sk->sk_bound_dev_if;
fl6->flowi6_mark = sk->sk_mark;
fl6->fl6_dport = inet->inet_dport;
fl6->fl6_sport = inet->inet_sport;
fl6->flowlabel = np->flow_label;
fl6->flowi6_uid = sk->sk_uid;
if (!fl6->flowi6_oif)
fl6->flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
if (!fl6->flowi6_oif && ipv6_addr_is_multicast(&fl6->daddr))
fl6->flowi6_oif = np->mcast_oif;
security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
}
int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr)
{
struct ip6_flowlabel *flowlabel = NULL;
struct in6_addr *final_p, final;
struct ipv6_txoptions *opt;
struct dst_entry *dst;
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct flowi6 fl6;
int err = 0;
if (np->sndflow && (np->flow_label & IPV6_FLOWLABEL_MASK)) {
flowlabel = fl6_sock_lookup(sk, np->flow_label);
if (!flowlabel)
return -EINVAL;
}
ip6_datagram_flow_key_init(&fl6, sk);
rcu_read_lock();
opt = flowlabel ? flowlabel->opt : rcu_dereference(np->opt);
final_p = fl6_update_dst(&fl6, opt, &final);
rcu_read_unlock();
dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
goto out;
}
if (fix_sk_saddr) {
if (ipv6_addr_any(&np->saddr))
np->saddr = fl6.saddr;
if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
sk->sk_v6_rcv_saddr = fl6.saddr;
inet->inet_rcv_saddr = LOOPBACK4_IPV6;
if (sk->sk_prot->rehash)
sk->sk_prot->rehash(sk);
}
}
ip6_sk_dst_store_flow(sk, dst, &fl6);
out:
fl6_sock_release(flowlabel);
return err;
}
void ip6_datagram_release_cb(struct sock *sk)
{
struct dst_entry *dst;
if (ipv6_addr_v4mapped(&sk->sk_v6_daddr))
return;
rcu_read_lock();
dst = __sk_dst_get(sk);
if (!dst || !dst->obsolete ||
dst->ops->check(dst, inet6_sk(sk)->dst_cookie)) {
rcu_read_unlock();
return;
}
rcu_read_unlock();
ip6_datagram_dst_update(sk, false);
}
EXPORT_SYMBOL_GPL(ip6_datagram_release_cb);
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, old_daddr;
__be32 fl6_flowlabel = 0;
__be32 old_fl6_flowlabel;
__be16 old_dport;
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;
if (np->sndflow)
fl6_flowlabel = usin->sin6_flowinfo & IPV6_FLOWINFO_MASK;
if (ipv6_addr_any(&usin->sin6_addr)) {
/*
* connect to self
*/
if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK),
&usin->sin6_addr);
else
usin->sin6_addr = in6addr_loopback;
}
addr_type = ipv6_addr_type(&usin->sin6_addr);
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_v4mapped(inet->inet_daddr, &sk->sk_v6_daddr);
if (ipv6_addr_any(&np->saddr) ||
ipv6_mapped_addr_any(&np->saddr))
ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr);
if (ipv6_addr_any(&sk->sk_v6_rcv_saddr) ||
ipv6_mapped_addr_any(&sk->sk_v6_rcv_saddr)) {
ipv6_addr_set_v4mapped(inet->inet_rcv_saddr,
&sk->sk_v6_rcv_saddr);
if (sk->sk_prot->rehash)
sk->sk_prot->rehash(sk);
}
goto out;
}
if (__ipv6_addr_needs_scope_id(addr_type)) {
if (addr_len >= sizeof(struct sockaddr_in6) &&
usin->sin6_scope_id) {
if (!sk_dev_equal_l3scope(sk, 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))
sk->sk_bound_dev_if = np->mcast_oif;
/* Connect to link-local address requires an interface */
if (!sk->sk_bound_dev_if) {
err = -EINVAL;
goto out;
}
}
/* save the current peer information before updating it */
old_daddr = sk->sk_v6_daddr;
old_fl6_flowlabel = np->flow_label;
old_dport = inet->inet_dport;
sk->sk_v6_daddr = *daddr;
np->flow_label = fl6_flowlabel;
inet->inet_dport = usin->sin6_port;
/*
* Check for a route to destination an obtain the
* destination cache for it.
*/
err = ip6_datagram_dst_update(sk, true);
if (err) {
/* Restore the socket peer info, to keep it consistent with
* the old socket state
*/
sk->sk_v6_daddr = old_daddr;
np->flow_label = old_fl6_flowlabel;
inet->inet_dport = old_dport;
goto out;
}
sk->sk_state = TCP_ESTABLISHED;
sk_set_txhash(sk);
out:
return err;
}
EXPORT_SYMBOL_GPL(__ip6_datagram_connect);
int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
int res;
lock_sock(sk);
res = __ip6_datagram_connect(sk, uaddr, addr_len);
release_sock(sk);
return res;
}
EXPORT_SYMBOL_GPL(ip6_datagram_connect);
int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr *uaddr,
int addr_len)
{
DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, uaddr);
if (sin6->sin6_family != AF_INET6)
return -EAFNOSUPPORT;
return ip6_datagram_connect(sk, uaddr, addr_len);
}
EXPORT_SYMBOL_GPL(ip6_datagram_connect_v6_only);
void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err,
__be16 port, u32 info, u8 *payload)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct icmp6hdr *icmph = icmp6_hdr(skb);
struct sock_exterr_skb *serr;
if (!np->recverr)
return;
skb = skb_clone(skb, GFP_ATOMIC);
if (!skb)
return;
skb->protocol = htons(ETH_P_IPV6);
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_network_header(skb);
serr->port = port;
__skb_pull(skb, payload - skb->data);
skb_reset_transport_header(skb);
if (sock_queue_err_skb(sk, skb))
kfree_skb(skb);
}
void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info)
{
const 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;
skb->protocol = htons(ETH_P_IPV6);
skb_put(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
iph = ipv6_hdr(skb);
iph->daddr = fl6->daddr;
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_network_header(skb);
serr->port = fl6->fl6_dport;
__skb_pull(skb, skb_tail_pointer(skb) - skb->data);
skb_reset_transport_header(skb);
if (sock_queue_err_skb(sk, skb))
kfree_skb(skb);
}
void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct ipv6hdr *iph;
struct sk_buff *skb;
struct ip6_mtuinfo *mtu_info;
if (!np->rxopt.bits.rxpmtu)
return;
skb = alloc_skb(sizeof(struct ipv6hdr), GFP_ATOMIC);
if (!skb)
return;
skb_put(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
iph = ipv6_hdr(skb);
iph->daddr = fl6->daddr;
mtu_info = IP6CBMTU(skb);
mtu_info->ip6m_mtu = mtu;
mtu_info->ip6m_addr.sin6_family = AF_INET6;
mtu_info->ip6m_addr.sin6_port = 0;
mtu_info->ip6m_addr.sin6_flowinfo = 0;
mtu_info->ip6m_addr.sin6_scope_id = fl6->flowi6_oif;
mtu_info->ip6m_addr.sin6_addr = ipv6_hdr(skb)->daddr;
__skb_pull(skb, skb_tail_pointer(skb) - skb->data);
skb_reset_transport_header(skb);
skb = xchg(&np->rxpmtu, skb);
kfree_skb(skb);
}
/* For some errors we have valid addr_offset even with zero payload and
* zero port. Also, addr_offset should be supported if port is set.
*/
static inline bool ipv6_datagram_support_addr(struct sock_exterr_skb *serr)
{
return serr->ee.ee_origin == SO_EE_ORIGIN_ICMP6 ||
serr->ee.ee_origin == SO_EE_ORIGIN_ICMP ||
serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL || serr->port;
}
/* IPv6 supports cmsg on all origins aside from SO_EE_ORIGIN_LOCAL.
*
* At one point, excluding local errors was a quick test to identify icmp/icmp6
* errors. This is no longer true, but the test remained, so the v6 stack,
* unlike v4, also honors cmsg requests on all wifi and timestamp errors.
*/
static bool ip6_datagram_support_cmsg(struct sk_buff *skb,
struct sock_exterr_skb *serr)
{
if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP ||
serr->ee.ee_origin == SO_EE_ORIGIN_ICMP6)
return true;
if (serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL)
return false;
if (!IP6CB(skb)->iif)
return false;
return true;
}
/*
* Handle MSG_ERRQUEUE
*/
int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct sock_exterr_skb *serr;
struct sk_buff *skb;
DECLARE_SOCKADDR(struct sockaddr_in6 *, sin, msg->msg_name);
struct {
struct sock_extended_err ee;
struct sockaddr_in6 offender;
} errhdr;
int err;
int copied;
err = -EAGAIN;
skb = sock_dequeue_err_skb(sk);
if (!skb)
goto out;
copied = skb->len;
if (copied > len) {
msg->msg_flags |= MSG_TRUNC;
copied = len;
}
err = skb_copy_datagram_msg(skb, 0, msg, copied);
if (unlikely(err)) {
kfree_skb(skb);
return err;
}
sock_recv_timestamp(msg, sk, skb);
serr = SKB_EXT_ERR(skb);
if (sin && ipv6_datagram_support_addr(serr)) {
const unsigned char *nh = skb_network_header(skb);
sin->sin6_family = AF_INET6;
sin->sin6_flowinfo = 0;
sin->sin6_port = serr->port;
if (skb->protocol == htons(ETH_P_IPV6)) {
const struct ipv6hdr *ip6h = container_of((struct in6_addr *)(nh + serr->addr_offset),
struct ipv6hdr, daddr);
sin->sin6_addr = ip6h->daddr;
if (np->sndflow)
sin->sin6_flowinfo = ip6_flowinfo(ip6h);
sin->sin6_scope_id =
ipv6_iface_scope_id(&sin->sin6_addr,
IP6CB(skb)->iif);
} else {
ipv6_addr_set_v4mapped(*(__be32 *)(nh + serr->addr_offset),
&sin->sin6_addr);
sin->sin6_scope_id = 0;
}
*addr_len = sizeof(*sin);
}
memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err));
sin = &errhdr.offender;
memset(sin, 0, sizeof(*sin));
if (ip6_datagram_support_cmsg(skb, serr)) {
sin->sin6_family = AF_INET6;
if (np->rxopt.all)
ip6_datagram_recv_common_ctl(sk, msg, skb);
if (skb->protocol == htons(ETH_P_IPV6)) {
sin->sin6_addr = ipv6_hdr(skb)->saddr;
if (np->rxopt.all)
ip6_datagram_recv_specific_ctl(sk, msg, skb);
sin->sin6_scope_id =
ipv6_iface_scope_id(&sin->sin6_addr,
IP6CB(skb)->iif);
} else {
ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr,
&sin->sin6_addr);
if (inet_sk(sk)->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;
consume_skb(skb);
out:
return err;
}
EXPORT_SYMBOL_GPL(ipv6_recv_error);
/*
* Handle IPV6_RECVPATHMTU
*/
int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len,
int *addr_len)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct sk_buff *skb;
struct ip6_mtuinfo mtu_info;
DECLARE_SOCKADDR(struct sockaddr_in6 *, sin, msg->msg_name);
int err;
int copied;
err = -EAGAIN;
skb = xchg(&np->rxpmtu, NULL);
if (!skb)
goto out;
copied = skb->len;
if (copied > len) {
msg->msg_flags |= MSG_TRUNC;
copied = len;
}
err = skb_copy_datagram_msg(skb, 0, msg, copied);
if (err)
goto out_free_skb;
sock_recv_timestamp(msg, sk, skb);
memcpy(&mtu_info, IP6CBMTU(skb), sizeof(mtu_info));
if (sin) {
sin->sin6_family = AF_INET6;
sin->sin6_flowinfo = 0;
sin->sin6_port = 0;
sin->sin6_scope_id = mtu_info.ip6m_addr.sin6_scope_id;
sin->sin6_addr = mtu_info.ip6m_addr.sin6_addr;
*addr_len = sizeof(*sin);
}
put_cmsg(msg, SOL_IPV6, IPV6_PATHMTU, sizeof(mtu_info), &mtu_info);
err = copied;
out_free_skb:
kfree_skb(skb);
out:
return err;
}
void ip6_datagram_recv_common_ctl(struct sock *sk, struct msghdr *msg,
struct sk_buff *skb)
{
struct ipv6_pinfo *np = inet6_sk(sk);
bool is_ipv6 = skb->protocol == htons(ETH_P_IPV6);
if (np->rxopt.bits.rxinfo) {
struct in6_pktinfo src_info;
if (is_ipv6) {
src_info.ipi6_ifindex = IP6CB(skb)->iif;
src_info.ipi6_addr = ipv6_hdr(skb)->daddr;
} else {
src_info.ipi6_ifindex =
PKTINFO_SKB_CB(skb)->ipi_ifindex;
ipv6_addr_set_v4mapped(ip_hdr(skb)->daddr,
&src_info.ipi6_addr);
}
if (src_info.ipi6_ifindex >= 0)
put_cmsg(msg, SOL_IPV6, IPV6_PKTINFO,
sizeof(src_info), &src_info);
}
}
void ip6_datagram_recv_specific_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);
unsigned char *nh = skb_network_header(skb);
if (np->rxopt.bits.rxhlim) {
int hlim = ipv6_hdr(skb)->hop_limit;
put_cmsg(msg, SOL_IPV6, IPV6_HOPLIMIT, sizeof(hlim), &hlim);
}
if (np->rxopt.bits.rxtclass) {
int tclass = ipv6_get_dsfield(ipv6_hdr(skb));
put_cmsg(msg, SOL_IPV6, IPV6_TCLASS, sizeof(tclass), &tclass);
}
if (np->rxopt.bits.rxflow) {
__be32 flowinfo = ip6_flowinfo((struct ipv6hdr *)nh);
if (flowinfo)
put_cmsg(msg, SOL_IPV6, IPV6_FLOWINFO, sizeof(flowinfo), &flowinfo);
}
/* HbH is allowed only once */
if (np->rxopt.bits.hopopts && (opt->flags & IP6SKB_HOPBYHOP)) {
u8 *ptr = nh + sizeof(struct ipv6hdr);
put_cmsg(msg, SOL_IPV6, IPV6_HOPOPTS, (ptr[1]+1)<<3, ptr);
}
if (opt->lastopt &&
(np->rxopt.bits.dstopts || np->rxopt.bits.srcrt)) {
/*
* Silly enough, but we need to reparse in order to
* report extension headers (except for HbH)
* in order.
*
* Also note that IPV6_RECVRTHDRDSTOPTS is NOT
* (and WILL NOT be) defined because
* IPV6_RECVDSTOPTS is more generic. --yoshfuji
*/
unsigned int off = sizeof(struct ipv6hdr);
u8 nexthdr = ipv6_hdr(skb)->nexthdr;
while (off <= opt->lastopt) {
unsigned int len;
u8 *ptr = nh + off;
switch (nexthdr) {
case IPPROTO_DSTOPTS:
nexthdr = ptr[0];
len = (ptr[1] + 1) << 3;
if (np->rxopt.bits.dstopts)
put_cmsg(msg, SOL_IPV6, IPV6_DSTOPTS, len, ptr);
break;
case IPPROTO_ROUTING:
nexthdr = ptr[0];
len = (ptr[1] + 1) << 3;
if (np->rxopt.bits.srcrt)
put_cmsg(msg, SOL_IPV6, IPV6_RTHDR, len, ptr);
break;
case IPPROTO_AH:
nexthdr = ptr[0];
len = (ptr[1] + 2) << 2;
break;
default:
nexthdr = ptr[0];
len = (ptr[1] + 1) << 3;
break;
}
off += len;
}
}
/* socket options in old style */
if (np->rxopt.bits.rxoinfo) {
struct in6_pktinfo src_info;
src_info.ipi6_ifindex = opt->iif;
src_info.ipi6_addr = ipv6_hdr(skb)->daddr;
put_cmsg(msg, SOL_IPV6, IPV6_2292PKTINFO, sizeof(src_info), &src_info);
}
if (np->rxopt.bits.rxohlim) {
int hlim = ipv6_hdr(skb)->hop_limit;
put_cmsg(msg, SOL_IPV6, IPV6_2292HOPLIMIT, sizeof(hlim), &hlim);
}
if (np->rxopt.bits.ohopopts && (opt->flags & IP6SKB_HOPBYHOP)) {
u8 *ptr = nh + sizeof(struct ipv6hdr);
put_cmsg(msg, SOL_IPV6, IPV6_2292HOPOPTS, (ptr[1]+1)<<3, ptr);
}
if (np->rxopt.bits.odstopts && opt->dst0) {
u8 *ptr = nh + opt->dst0;
put_cmsg(msg, SOL_IPV6, IPV6_2292DSTOPTS, (ptr[1]+1)<<3, ptr);
}
if (np->rxopt.bits.osrcrt && opt->srcrt) {
struct ipv6_rt_hdr *rthdr = (struct ipv6_rt_hdr *)(nh + opt->srcrt);
put_cmsg(msg, SOL_IPV6, IPV6_2292RTHDR, (rthdr->hdrlen+1) << 3, rthdr);
}
if (np->rxopt.bits.odstopts && opt->dst1) {
u8 *ptr = nh + opt->dst1;
put_cmsg(msg, SOL_IPV6, IPV6_2292DSTOPTS, (ptr[1]+1)<<3, ptr);
}
if (np->rxopt.bits.rxorigdstaddr) {
struct sockaddr_in6 sin6;
__be16 *ports;
int end;
end = skb_transport_offset(skb) + 4;
if (end <= 0 || pskb_may_pull(skb, end)) {
/* All current transport protocols have the port numbers in the
* first four bytes of the transport header and this function is
* written with this assumption in mind.
*/
ports = (__be16 *)skb_transport_header(skb);
sin6.sin6_family = AF_INET6;
sin6.sin6_addr = ipv6_hdr(skb)->daddr;
sin6.sin6_port = ports[1];
sin6.sin6_flowinfo = 0;
sin6.sin6_scope_id =
ipv6_iface_scope_id(&ipv6_hdr(skb)->daddr,
opt->iif);
put_cmsg(msg, SOL_IPV6, IPV6_ORIGDSTADDR, sizeof(sin6), &sin6);
}
}
if (np->rxopt.bits.recvfragsize && opt->frag_max_size) {
int val = opt->frag_max_size;
put_cmsg(msg, SOL_IPV6, IPV6_RECVFRAGSIZE, sizeof(val), &val);
}
}
void ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg,
struct sk_buff *skb)
{
ip6_datagram_recv_common_ctl(sk, msg, skb);
ip6_datagram_recv_specific_ctl(sk, msg, skb);
}
EXPORT_SYMBOL_GPL(ip6_datagram_recv_ctl);
int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
struct msghdr *msg, struct flowi6 *fl6,
struct ipcm6_cookie *ipc6)
{
struct in6_pktinfo *src_info;
struct cmsghdr *cmsg;
struct ipv6_rt_hdr *rthdr;
struct ipv6_opt_hdr *hdr;
struct ipv6_txoptions *opt = ipc6->opt;
int len;
int err = 0;
for_each_cmsghdr(cmsg, msg) {
int addr_type;
if (!CMSG_OK(msg, cmsg)) {
err = -EINVAL;
goto exit_f;
}
if (cmsg->cmsg_level == SOL_SOCKET) {
err = __sock_cmsg_send(sk, msg, cmsg, &ipc6->sockc);
if (err)
return err;
continue;
}
if (cmsg->cmsg_level != SOL_IPV6)
continue;
switch (cmsg->cmsg_type) {
case IPV6_PKTINFO:
case IPV6_2292PKTINFO:
{
struct net_device *dev = NULL;
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 (fl6->flowi6_oif &&
src_info->ipi6_ifindex != fl6->flowi6_oif)
return -EINVAL;
fl6->flowi6_oif = src_info->ipi6_ifindex;
}
addr_type = __ipv6_addr_type(&src_info->ipi6_addr);
rcu_read_lock();
if (fl6->flowi6_oif) {
dev = dev_get_by_index_rcu(net, fl6->flowi6_oif);
if (!dev) {
rcu_read_unlock();
return -ENODEV;
}
} else if (addr_type & IPV6_ADDR_LINKLOCAL) {
rcu_read_unlock();
return -EINVAL;
}
if (addr_type != IPV6_ADDR_ANY) {
int strict = __ipv6_addr_src_scope(addr_type) <= IPV6_ADDR_SCOPE_LINKLOCAL;
if (!ipv6_can_nonlocal_bind(net, inet_sk(sk)) &&
!ipv6_chk_addr_and_flags(net, &src_info->ipi6_addr,
dev, !strict, 0,
IFA_F_TENTATIVE) &&
!ipv6_chk_acast_addr_src(net, dev,
&src_info->ipi6_addr))
err = -EINVAL;
else
fl6->saddr = src_info->ipi6_addr;
}
rcu_read_unlock();
if (err)
goto exit_f;
break;
}
case IPV6_FLOWINFO:
if (cmsg->cmsg_len < CMSG_LEN(4)) {
err = -EINVAL;
goto exit_f;
}
if (fl6->flowlabel&IPV6_FLOWINFO_MASK) {
if ((fl6->flowlabel^*(__be32 *)CMSG_DATA(cmsg))&~IPV6_FLOWINFO_MASK) {
err = -EINVAL;
goto exit_f;
}
}
fl6->flowlabel = IPV6_FLOWINFO_MASK & *(__be32 *)CMSG_DATA(cmsg);
break;
case IPV6_2292HOPOPTS:
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 (!ns_capable(net->user_ns, CAP_NET_RAW)) {
err = -EPERM;
goto exit_f;
}
opt->opt_nflen += len;
opt->hopopt = hdr;
break;
case IPV6_2292DSTOPTS:
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 (!ns_capable(net->user_ns, 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_DSTOPTS:
case IPV6_RTHDRDSTOPTS:
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 (!ns_capable(net->user_ns, CAP_NET_RAW)) {
err = -EPERM;
goto exit_f;
}
if (cmsg->cmsg_type == IPV6_DSTOPTS) {
opt->opt_flen += len;
opt->dst1opt = hdr;
} else {
opt->opt_nflen += len;
opt->dst0opt = hdr;
}
break;
case IPV6_2292RTHDR:
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);
switch (rthdr->type) {
#if IS_ENABLED(CONFIG_IPV6_MIP6)
case IPV6_SRCRT_TYPE_2:
if (rthdr->hdrlen != 2 ||
rthdr->segments_left != 1) {
err = -EINVAL;
goto exit_f;
}
break;
#endif
default:
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 (cmsg->cmsg_type == IPV6_2292RTHDR && 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_2292HOPLIMIT:
case IPV6_HOPLIMIT:
if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) {
err = -EINVAL;
goto exit_f;
}
ipc6->hlimit = *(int *)CMSG_DATA(cmsg);
if (ipc6->hlimit < -1 || ipc6->hlimit > 0xff) {
err = -EINVAL;
goto exit_f;
}
break;
case IPV6_TCLASS:
{
int tc;
err = -EINVAL;
if (cmsg->cmsg_len != CMSG_LEN(sizeof(int)))
goto exit_f;
tc = *(int *)CMSG_DATA(cmsg);
if (tc < -1 || tc > 0xff)
goto exit_f;
err = 0;
ipc6->tclass = tc;
break;
}
case IPV6_DONTFRAG:
{
int df;
err = -EINVAL;
if (cmsg->cmsg_len != CMSG_LEN(sizeof(int)))