forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
af_inet6.c
1291 lines (1095 loc) · 29.7 KB
/
af_inet6.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
/*
* PF_INET6 socket protocol family
* Linux INET6 implementation
*
* Authors:
* Pedro Roque <[email protected]>
*
* Adapted from linux/net/ipv4/af_inet.c
*
* Fixes:
* piggy, Karl Knutson : Socket protocol table
* Hideaki YOSHIFUJI : sin6_scope_id support
* Arnaldo Melo : check proc_net_create return, cleanups
*
* 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.
*/
#define pr_fmt(fmt) "IPv6: " fmt
#include <linux/module.h>
#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/kernel.h>
#include <linux/timer.h>
#include <linux/string.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/fcntl.h>
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/proc_fs.h>
#include <linux/stat.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/icmpv6.h>
#include <linux/netfilter_ipv6.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/udp.h>
#include <net/udplite.h>
#include <net/tcp.h>
#include <net/ipip.h>
#include <net/protocol.h>
#include <net/inet_common.h>
#include <net/route.h>
#include <net/transp_v6.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
#ifdef CONFIG_IPV6_TUNNEL
#include <net/ip6_tunnel.h>
#endif
#include <asm/uaccess.h>
#include <linux/mroute6.h>
MODULE_AUTHOR("Cast of dozens");
MODULE_DESCRIPTION("IPv6 protocol stack for Linux");
MODULE_LICENSE("GPL");
/* The inetsw6 table contains everything that inet6_create needs to
* build a new socket.
*/
static struct list_head inetsw6[SOCK_MAX];
static DEFINE_SPINLOCK(inetsw6_lock);
struct ipv6_params ipv6_defaults = {
.disable_ipv6 = 0,
.autoconf = 1,
};
static int disable_ipv6_mod;
module_param_named(disable, disable_ipv6_mod, int, 0444);
MODULE_PARM_DESC(disable, "Disable IPv6 module such that it is non-functional");
module_param_named(disable_ipv6, ipv6_defaults.disable_ipv6, int, 0444);
MODULE_PARM_DESC(disable_ipv6, "Disable IPv6 on all interfaces");
module_param_named(autoconf, ipv6_defaults.autoconf, int, 0444);
MODULE_PARM_DESC(autoconf, "Enable IPv6 address autoconfiguration on all interfaces");
static __inline__ struct ipv6_pinfo *inet6_sk_generic(struct sock *sk)
{
const int offset = sk->sk_prot->obj_size - sizeof(struct ipv6_pinfo);
return (struct ipv6_pinfo *)(((u8 *)sk) + offset);
}
static int inet6_create(struct net *net, struct socket *sock, int protocol,
int kern)
{
struct inet_sock *inet;
struct ipv6_pinfo *np;
struct sock *sk;
struct inet_protosw *answer;
struct proto *answer_prot;
unsigned char answer_flags;
char answer_no_check;
int try_loading_module = 0;
int err;
if (sock->type != SOCK_RAW &&
sock->type != SOCK_DGRAM &&
!inet_ehash_secret)
build_ehash_secret();
/* Look for the requested type/protocol pair. */
lookup_protocol:
err = -ESOCKTNOSUPPORT;
rcu_read_lock();
list_for_each_entry_rcu(answer, &inetsw6[sock->type], list) {
err = 0;
/* Check the non-wild match. */
if (protocol == answer->protocol) {
if (protocol != IPPROTO_IP)
break;
} else {
/* Check for the two wild cases. */
if (IPPROTO_IP == protocol) {
protocol = answer->protocol;
break;
}
if (IPPROTO_IP == answer->protocol)
break;
}
err = -EPROTONOSUPPORT;
}
if (err) {
if (try_loading_module < 2) {
rcu_read_unlock();
/*
* Be more specific, e.g. net-pf-10-proto-132-type-1
* (net-pf-PF_INET6-proto-IPPROTO_SCTP-type-SOCK_STREAM)
*/
if (++try_loading_module == 1)
request_module("net-pf-%d-proto-%d-type-%d",
PF_INET6, protocol, sock->type);
/*
* Fall back to generic, e.g. net-pf-10-proto-132
* (net-pf-PF_INET6-proto-IPPROTO_SCTP)
*/
else
request_module("net-pf-%d-proto-%d",
PF_INET6, protocol);
goto lookup_protocol;
} else
goto out_rcu_unlock;
}
err = -EPERM;
if (sock->type == SOCK_RAW && !kern && !capable(CAP_NET_RAW))
goto out_rcu_unlock;
sock->ops = answer->ops;
answer_prot = answer->prot;
answer_no_check = answer->no_check;
answer_flags = answer->flags;
rcu_read_unlock();
WARN_ON(answer_prot->slab == NULL);
err = -ENOBUFS;
sk = sk_alloc(net, PF_INET6, GFP_KERNEL, answer_prot);
if (sk == NULL)
goto out;
sock_init_data(sock, sk);
err = 0;
sk->sk_no_check = answer_no_check;
if (INET_PROTOSW_REUSE & answer_flags)
sk->sk_reuse = SK_CAN_REUSE;
inet = inet_sk(sk);
inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0;
if (SOCK_RAW == sock->type) {
inet->inet_num = protocol;
if (IPPROTO_RAW == protocol)
inet->hdrincl = 1;
}
sk->sk_destruct = inet_sock_destruct;
sk->sk_family = PF_INET6;
sk->sk_protocol = protocol;
sk->sk_backlog_rcv = answer->prot->backlog_rcv;
inet_sk(sk)->pinet6 = np = inet6_sk_generic(sk);
np->hop_limit = -1;
np->mcast_hops = IPV6_DEFAULT_MCASTHOPS;
np->mc_loop = 1;
np->pmtudisc = IPV6_PMTUDISC_WANT;
np->ipv6only = net->ipv6.sysctl.bindv6only;
/* Init the ipv4 part of the socket since we can have sockets
* using v6 API for ipv4.
*/
inet->uc_ttl = -1;
inet->mc_loop = 1;
inet->mc_ttl = 1;
inet->mc_index = 0;
inet->mc_list = NULL;
inet->rcv_tos = 0;
if (ipv4_config.no_pmtu_disc)
inet->pmtudisc = IP_PMTUDISC_DONT;
else
inet->pmtudisc = IP_PMTUDISC_WANT;
/*
* Increment only the relevant sk_prot->socks debug field, this changes
* the previous behaviour of incrementing both the equivalent to
* answer->prot->socks (inet6_sock_nr) and inet_sock_nr.
*
* This allows better debug granularity as we'll know exactly how many
* UDPv6, TCPv6, etc socks were allocated, not the sum of all IPv6
* transport protocol socks. -acme
*/
sk_refcnt_debug_inc(sk);
if (inet->inet_num) {
/* It assumes that any protocol which allows
* the user to assign a number at socket
* creation time automatically shares.
*/
inet->inet_sport = htons(inet->inet_num);
sk->sk_prot->hash(sk);
}
if (sk->sk_prot->init) {
err = sk->sk_prot->init(sk);
if (err) {
sk_common_release(sk);
goto out;
}
}
out:
return err;
out_rcu_unlock:
rcu_read_unlock();
goto out;
}
/* bind for INET6 API */
int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
{
struct sockaddr_in6 *addr = (struct sockaddr_in6 *)uaddr;
struct sock *sk = sock->sk;
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct net *net = sock_net(sk);
__be32 v4addr = 0;
unsigned short snum;
int addr_type = 0;
int err = 0;
/* If the socket has its own bind function then use it. */
if (sk->sk_prot->bind)
return sk->sk_prot->bind(sk, uaddr, addr_len);
if (addr_len < SIN6_LEN_RFC2133)
return -EINVAL;
if (addr->sin6_family != AF_INET6)
return -EAFNOSUPPORT;
addr_type = ipv6_addr_type(&addr->sin6_addr);
if ((addr_type & IPV6_ADDR_MULTICAST) && sock->type == SOCK_STREAM)
return -EINVAL;
snum = ntohs(addr->sin6_port);
if (snum && snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE))
return -EACCES;
lock_sock(sk);
/* Check these errors (active socket, double bind). */
if (sk->sk_state != TCP_CLOSE || inet->inet_num) {
err = -EINVAL;
goto out;
}
/* Check if the address belongs to the host. */
if (addr_type == IPV6_ADDR_MAPPED) {
int chk_addr_ret;
/* Binding to v4-mapped address on a v6-only socket
* makes no sense
*/
if (np->ipv6only) {
err = -EINVAL;
goto out;
}
/* Reproduce AF_INET checks to make the bindings consistent */
v4addr = addr->sin6_addr.s6_addr32[3];
chk_addr_ret = inet_addr_type(net, v4addr);
if (!sysctl_ip_nonlocal_bind &&
!(inet->freebind || inet->transparent) &&
v4addr != htonl(INADDR_ANY) &&
chk_addr_ret != RTN_LOCAL &&
chk_addr_ret != RTN_MULTICAST &&
chk_addr_ret != RTN_BROADCAST) {
err = -EADDRNOTAVAIL;
goto out;
}
} else {
if (addr_type != IPV6_ADDR_ANY) {
struct net_device *dev = NULL;
rcu_read_lock();
if (addr_type & IPV6_ADDR_LINKLOCAL) {
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) {
err = -EINVAL;
goto out_unlock;
}
dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if);
if (!dev) {
err = -ENODEV;
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)) {
if (!(inet->freebind || inet->transparent) &&
!ipv6_chk_addr(net, &addr->sin6_addr,
dev, 0)) {
err = -EADDRNOTAVAIL;
goto out_unlock;
}
}
rcu_read_unlock();
}
}
inet->inet_rcv_saddr = v4addr;
inet->inet_saddr = v4addr;
np->rcv_saddr = addr->sin6_addr;
if (!(addr_type & IPV6_ADDR_MULTICAST))
np->saddr = addr->sin6_addr;
/* Make sure we are allowed to bind here. */
if (sk->sk_prot->get_port(sk, snum)) {
inet_reset_saddr(sk);
err = -EADDRINUSE;
goto out;
}
if (addr_type != IPV6_ADDR_ANY) {
sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
if (addr_type != IPV6_ADDR_MAPPED)
np->ipv6only = 1;
}
if (snum)
sk->sk_userlocks |= SOCK_BINDPORT_LOCK;
inet->inet_sport = htons(inet->inet_num);
inet->inet_dport = 0;
inet->inet_daddr = 0;
out:
release_sock(sk);
return err;
out_unlock:
rcu_read_unlock();
goto out;
}
EXPORT_SYMBOL(inet6_bind);
int inet6_release(struct socket *sock)
{
struct sock *sk = sock->sk;
if (sk == NULL)
return -EINVAL;
/* Free mc lists */
ipv6_sock_mc_close(sk);
/* Free ac lists */
ipv6_sock_ac_close(sk);
return inet_release(sock);
}
EXPORT_SYMBOL(inet6_release);
void inet6_destroy_sock(struct sock *sk)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct sk_buff *skb;
struct ipv6_txoptions *opt;
/* Release rx options */
skb = xchg(&np->pktoptions, NULL);
if (skb != NULL)
kfree_skb(skb);
skb = xchg(&np->rxpmtu, NULL);
if (skb != NULL)
kfree_skb(skb);
/* Free flowlabels */
fl6_free_socklist(sk);
/* Free tx options */
opt = xchg(&np->opt, NULL);
if (opt != NULL)
sock_kfree_s(sk, opt, opt->tot_len);
}
EXPORT_SYMBOL_GPL(inet6_destroy_sock);
/*
* This does both peername and sockname.
*/
int inet6_getname(struct socket *sock, struct sockaddr *uaddr,
int *uaddr_len, int peer)
{
struct sockaddr_in6 *sin = (struct sockaddr_in6 *)uaddr;
struct sock *sk = sock->sk;
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
sin->sin6_family = AF_INET6;
sin->sin6_flowinfo = 0;
sin->sin6_scope_id = 0;
if (peer) {
if (!inet->inet_dport)
return -ENOTCONN;
if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT)) &&
peer == 1)
return -ENOTCONN;
sin->sin6_port = inet->inet_dport;
sin->sin6_addr = np->daddr;
if (np->sndflow)
sin->sin6_flowinfo = np->flow_label;
} else {
if (ipv6_addr_any(&np->rcv_saddr))
sin->sin6_addr = np->saddr;
else
sin->sin6_addr = np->rcv_saddr;
sin->sin6_port = inet->inet_sport;
}
if (ipv6_addr_type(&sin->sin6_addr) & IPV6_ADDR_LINKLOCAL)
sin->sin6_scope_id = sk->sk_bound_dev_if;
*uaddr_len = sizeof(*sin);
return 0;
}
EXPORT_SYMBOL(inet6_getname);
int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
struct sock *sk = sock->sk;
struct net *net = sock_net(sk);
switch (cmd) {
case SIOCGSTAMP:
return sock_get_timestamp(sk, (struct timeval __user *)arg);
case SIOCGSTAMPNS:
return sock_get_timestampns(sk, (struct timespec __user *)arg);
case SIOCADDRT:
case SIOCDELRT:
return ipv6_route_ioctl(net, cmd, (void __user *)arg);
case SIOCSIFADDR:
return addrconf_add_ifaddr(net, (void __user *) arg);
case SIOCDIFADDR:
return addrconf_del_ifaddr(net, (void __user *) arg);
case SIOCSIFDSTADDR:
return addrconf_set_dstaddr(net, (void __user *) arg);
default:
if (!sk->sk_prot->ioctl)
return -ENOIOCTLCMD;
return sk->sk_prot->ioctl(sk, cmd, arg);
}
/*NOTREACHED*/
return 0;
}
EXPORT_SYMBOL(inet6_ioctl);
const struct proto_ops inet6_stream_ops = {
.family = PF_INET6,
.owner = THIS_MODULE,
.release = inet6_release,
.bind = inet6_bind,
.connect = inet_stream_connect, /* ok */
.socketpair = sock_no_socketpair, /* a do nothing */
.accept = inet_accept, /* ok */
.getname = inet6_getname,
.poll = tcp_poll, /* ok */
.ioctl = inet6_ioctl, /* must change */
.listen = inet_listen, /* ok */
.shutdown = inet_shutdown, /* ok */
.setsockopt = sock_common_setsockopt, /* ok */
.getsockopt = sock_common_getsockopt, /* ok */
.sendmsg = inet_sendmsg, /* ok */
.recvmsg = inet_recvmsg, /* ok */
.mmap = sock_no_mmap,
.sendpage = inet_sendpage,
.splice_read = tcp_splice_read,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_sock_common_setsockopt,
.compat_getsockopt = compat_sock_common_getsockopt,
#endif
};
const struct proto_ops inet6_dgram_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 = udp_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 = inet_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 const struct net_proto_family inet6_family_ops = {
.family = PF_INET6,
.create = inet6_create,
.owner = THIS_MODULE,
};
int inet6_register_protosw(struct inet_protosw *p)
{
struct list_head *lh;
struct inet_protosw *answer;
struct list_head *last_perm;
int protocol = p->protocol;
int ret;
spin_lock_bh(&inetsw6_lock);
ret = -EINVAL;
if (p->type >= SOCK_MAX)
goto out_illegal;
/* If we are trying to override a permanent protocol, bail. */
answer = NULL;
ret = -EPERM;
last_perm = &inetsw6[p->type];
list_for_each(lh, &inetsw6[p->type]) {
answer = list_entry(lh, struct inet_protosw, list);
/* Check only the non-wild match. */
if (INET_PROTOSW_PERMANENT & answer->flags) {
if (protocol == answer->protocol)
break;
last_perm = lh;
}
answer = NULL;
}
if (answer)
goto out_permanent;
/* Add the new entry after the last permanent entry if any, so that
* the new entry does not override a permanent entry when matched with
* a wild-card protocol. But it is allowed to override any existing
* non-permanent entry. This means that when we remove this entry, the
* system automatically returns to the old behavior.
*/
list_add_rcu(&p->list, last_perm);
ret = 0;
out:
spin_unlock_bh(&inetsw6_lock);
return ret;
out_permanent:
pr_err("Attempt to override permanent protocol %d\n", protocol);
goto out;
out_illegal:
pr_err("Ignoring attempt to register invalid socket type %d\n",
p->type);
goto out;
}
EXPORT_SYMBOL(inet6_register_protosw);
void
inet6_unregister_protosw(struct inet_protosw *p)
{
if (INET_PROTOSW_PERMANENT & p->flags) {
pr_err("Attempt to unregister permanent protocol %d\n",
p->protocol);
} else {
spin_lock_bh(&inetsw6_lock);
list_del_rcu(&p->list);
spin_unlock_bh(&inetsw6_lock);
synchronize_net();
}
}
EXPORT_SYMBOL(inet6_unregister_protosw);
int inet6_sk_rebuild_header(struct sock *sk)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct dst_entry *dst;
dst = __sk_dst_check(sk, np->dst_cookie);
if (dst == NULL) {
struct inet_sock *inet = inet_sk(sk);
struct in6_addr *final_p, final;
struct flowi6 fl6;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = sk->sk_protocol;
fl6.daddr = np->daddr;
fl6.saddr = np->saddr;
fl6.flowlabel = np->flow_label;
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;
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
final_p = fl6_update_dst(&fl6, np->opt, &final);
dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false);
if (IS_ERR(dst)) {
sk->sk_route_caps = 0;
sk->sk_err_soft = -PTR_ERR(dst);
return PTR_ERR(dst);
}
__ip6_dst_store(sk, dst, NULL, NULL);
}
return 0;
}
EXPORT_SYMBOL_GPL(inet6_sk_rebuild_header);
bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb)
{
const struct ipv6_pinfo *np = inet6_sk(sk);
const struct inet6_skb_parm *opt = IP6CB(skb);
if (np->rxopt.all) {
if ((opt->hop && (np->rxopt.bits.hopopts ||
np->rxopt.bits.ohopopts)) ||
((IPV6_FLOWINFO_MASK &
*(__be32 *)skb_network_header(skb)) &&
np->rxopt.bits.rxflow) ||
(opt->srcrt && (np->rxopt.bits.srcrt ||
np->rxopt.bits.osrcrt)) ||
((opt->dst1 || opt->dst0) &&
(np->rxopt.bits.dstopts || np->rxopt.bits.odstopts)))
return true;
}
return false;
}
EXPORT_SYMBOL_GPL(ipv6_opt_accepted);
static int ipv6_gso_pull_exthdrs(struct sk_buff *skb, int proto)
{
const struct inet6_protocol *ops = NULL;
for (;;) {
struct ipv6_opt_hdr *opth;
int len;
if (proto != NEXTHDR_HOP) {
ops = rcu_dereference(inet6_protos[proto]);
if (unlikely(!ops))
break;
if (!(ops->flags & INET6_PROTO_GSO_EXTHDR))
break;
}
if (unlikely(!pskb_may_pull(skb, 8)))
break;
opth = (void *)skb->data;
len = ipv6_optlen(opth);
if (unlikely(!pskb_may_pull(skb, len)))
break;
proto = opth->nexthdr;
__skb_pull(skb, len);
}
return proto;
}
static int ipv6_gso_send_check(struct sk_buff *skb)
{
const struct ipv6hdr *ipv6h;
const struct inet6_protocol *ops;
int err = -EINVAL;
if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
goto out;
ipv6h = ipv6_hdr(skb);
__skb_pull(skb, sizeof(*ipv6h));
err = -EPROTONOSUPPORT;
rcu_read_lock();
ops = rcu_dereference(inet6_protos[
ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr)]);
if (likely(ops && ops->gso_send_check)) {
skb_reset_transport_header(skb);
err = ops->gso_send_check(skb);
}
rcu_read_unlock();
out:
return err;
}
static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
netdev_features_t features)
{
struct sk_buff *segs = ERR_PTR(-EINVAL);
struct ipv6hdr *ipv6h;
const struct inet6_protocol *ops;
int proto;
struct frag_hdr *fptr;
unsigned int unfrag_ip6hlen;
u8 *prevhdr;
int offset = 0;
if (!(features & NETIF_F_V6_CSUM))
features &= ~NETIF_F_SG;
if (unlikely(skb_shinfo(skb)->gso_type &
~(SKB_GSO_UDP |
SKB_GSO_DODGY |
SKB_GSO_TCP_ECN |
SKB_GSO_TCPV6 |
0)))
goto out;
if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
goto out;
ipv6h = ipv6_hdr(skb);
__skb_pull(skb, sizeof(*ipv6h));
segs = ERR_PTR(-EPROTONOSUPPORT);
proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr);
rcu_read_lock();
ops = rcu_dereference(inet6_protos[proto]);
if (likely(ops && ops->gso_segment)) {
skb_reset_transport_header(skb);
segs = ops->gso_segment(skb, features);
}
rcu_read_unlock();
if (IS_ERR(segs))
goto out;
for (skb = segs; skb; skb = skb->next) {
ipv6h = ipv6_hdr(skb);
ipv6h->payload_len = htons(skb->len - skb->mac_len -
sizeof(*ipv6h));
if (proto == IPPROTO_UDP) {
unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr);
fptr = (struct frag_hdr *)(skb_network_header(skb) +
unfrag_ip6hlen);
fptr->frag_off = htons(offset);
if (skb->next != NULL)
fptr->frag_off |= htons(IP6_MF);
offset += (ntohs(ipv6h->payload_len) -
sizeof(struct frag_hdr));
}
}
out:
return segs;
}
struct ipv6_gro_cb {
struct napi_gro_cb napi;
int proto;
};
#define IPV6_GRO_CB(skb) ((struct ipv6_gro_cb *)(skb)->cb)
static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
struct sk_buff *skb)
{
const struct inet6_protocol *ops;
struct sk_buff **pp = NULL;
struct sk_buff *p;
struct ipv6hdr *iph;
unsigned int nlen;
unsigned int hlen;
unsigned int off;
int flush = 1;
int proto;
__wsum csum;
off = skb_gro_offset(skb);
hlen = off + sizeof(*iph);
iph = skb_gro_header_fast(skb, off);
if (skb_gro_header_hard(skb, hlen)) {
iph = skb_gro_header_slow(skb, hlen, off);
if (unlikely(!iph))
goto out;
}
skb_gro_pull(skb, sizeof(*iph));
skb_set_transport_header(skb, skb_gro_offset(skb));
flush += ntohs(iph->payload_len) != skb_gro_len(skb);
rcu_read_lock();
proto = iph->nexthdr;
ops = rcu_dereference(inet6_protos[proto]);
if (!ops || !ops->gro_receive) {
__pskb_pull(skb, skb_gro_offset(skb));
proto = ipv6_gso_pull_exthdrs(skb, proto);
skb_gro_pull(skb, -skb_transport_offset(skb));
skb_reset_transport_header(skb);
__skb_push(skb, skb_gro_offset(skb));
ops = rcu_dereference(inet6_protos[proto]);
if (!ops || !ops->gro_receive)
goto out_unlock;
iph = ipv6_hdr(skb);
}
IPV6_GRO_CB(skb)->proto = proto;
flush--;
nlen = skb_network_header_len(skb);
for (p = *head; p; p = p->next) {
struct ipv6hdr *iph2;
if (!NAPI_GRO_CB(p)->same_flow)
continue;
iph2 = ipv6_hdr(p);
/* All fields must match except length. */
if (nlen != skb_network_header_len(p) ||
memcmp(iph, iph2, offsetof(struct ipv6hdr, payload_len)) ||
memcmp(&iph->nexthdr, &iph2->nexthdr,
nlen - offsetof(struct ipv6hdr, nexthdr))) {
NAPI_GRO_CB(p)->same_flow = 0;
continue;
}
NAPI_GRO_CB(p)->flush |= flush;
}
NAPI_GRO_CB(skb)->flush |= flush;
csum = skb->csum;
skb_postpull_rcsum(skb, iph, skb_network_header_len(skb));
pp = ops->gro_receive(head, skb);
skb->csum = csum;
out_unlock:
rcu_read_unlock();
out:
NAPI_GRO_CB(skb)->flush |= flush;
return pp;
}
static int ipv6_gro_complete(struct sk_buff *skb)
{
const struct inet6_protocol *ops;
struct ipv6hdr *iph = ipv6_hdr(skb);
int err = -ENOSYS;
iph->payload_len = htons(skb->len - skb_network_offset(skb) -
sizeof(*iph));
rcu_read_lock();
ops = rcu_dereference(inet6_protos[IPV6_GRO_CB(skb)->proto]);
if (WARN_ON(!ops || !ops->gro_complete))
goto out_unlock;
err = ops->gro_complete(skb);
out_unlock:
rcu_read_unlock();
return err;
}
static struct packet_type ipv6_packet_type __read_mostly = {
.type = cpu_to_be16(ETH_P_IPV6),
.func = ipv6_rcv,
.gso_send_check = ipv6_gso_send_check,
.gso_segment = ipv6_gso_segment,
.gro_receive = ipv6_gro_receive,
.gro_complete = ipv6_gro_complete,
};
static int __init ipv6_packet_init(void)
{
dev_add_pack(&ipv6_packet_type);
return 0;
}
static void ipv6_packet_cleanup(void)
{
dev_remove_pack(&ipv6_packet_type);
}
static int __net_init ipv6_init_mibs(struct net *net)
{
if (snmp_mib_init((void __percpu **)net->mib.udp_stats_in6,
sizeof(struct udp_mib),
__alignof__(struct udp_mib)) < 0)
return -ENOMEM;
if (snmp_mib_init((void __percpu **)net->mib.udplite_stats_in6,
sizeof(struct udp_mib),
__alignof__(struct udp_mib)) < 0)
goto err_udplite_mib;
if (snmp_mib_init((void __percpu **)net->mib.ipv6_statistics,
sizeof(struct ipstats_mib),
__alignof__(struct ipstats_mib)) < 0)
goto err_ip_mib;
if (snmp_mib_init((void __percpu **)net->mib.icmpv6_statistics,
sizeof(struct icmpv6_mib),
__alignof__(struct icmpv6_mib)) < 0)
goto err_icmp_mib;
net->mib.icmpv6msg_statistics = kzalloc(sizeof(struct icmpv6msg_mib),
GFP_KERNEL);
if (!net->mib.icmpv6msg_statistics)
goto err_icmpmsg_mib;
return 0;
err_icmpmsg_mib:
snmp_mib_free((void __percpu **)net->mib.icmpv6_statistics);
err_icmp_mib:
snmp_mib_free((void __percpu **)net->mib.ipv6_statistics);
err_ip_mib:
snmp_mib_free((void __percpu **)net->mib.udplite_stats_in6);
err_udplite_mib:
snmp_mib_free((void __percpu **)net->mib.udp_stats_in6);
return -ENOMEM;
}
static void ipv6_cleanup_mibs(struct net *net)
{
snmp_mib_free((void __percpu **)net->mib.udp_stats_in6);
snmp_mib_free((void __percpu **)net->mib.udplite_stats_in6);