forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 17
/
ipv6_sockglue.c
1501 lines (1285 loc) · 33.5 KB
/
ipv6_sockglue.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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* IPv6 BSD socket options interface
* Linux INET6 implementation
*
* Authors:
* Pedro Roque <[email protected]>
*
* Based on linux/net/ipv4/ip_sockglue.c
*
* FIXME: Make the setsockopt code POSIX compliant: That is
*
* o Truncate getsockopt returns
* o Return an optlen of the truncated length if need be
*
* Changes:
* David L Stevens <[email protected]>:
* - added multicast source filtering API for MLDv2
*/
#include <linux/module.h>
#include <linux/capability.h>
#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/mroute6.h>
#include <linux/netdevice.h>
#include <linux/if_arp.h>
#include <linux/init.h>
#include <linux/sysctl.h>
#include <linux/netfilter.h>
#include <linux/slab.h>
#include <net/sock.h>
#include <net/snmp.h>
#include <net/ipv6.h>
#include <net/ndisc.h>
#include <net/protocol.h>
#include <net/transp_v6.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
#include <net/inet_common.h>
#include <net/tcp.h>
#include <net/udp.h>
#include <net/udplite.h>
#include <net/xfrm.h>
#include <net/compat.h>
#include <net/seg6.h>
#include <linux/uaccess.h>
struct ip6_ra_chain *ip6_ra_chain;
DEFINE_RWLOCK(ip6_ra_lock);
DEFINE_STATIC_KEY_FALSE(ip6_min_hopcount);
int ip6_ra_control(struct sock *sk, int sel)
{
struct ip6_ra_chain *ra, *new_ra, **rap;
/* RA packet may be delivered ONLY to IPPROTO_RAW socket */
if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_RAW)
return -ENOPROTOOPT;
new_ra = (sel >= 0) ? kmalloc(sizeof(*new_ra), GFP_KERNEL) : NULL;
if (sel >= 0 && !new_ra)
return -ENOMEM;
write_lock_bh(&ip6_ra_lock);
for (rap = &ip6_ra_chain; (ra = *rap) != NULL; rap = &ra->next) {
if (ra->sk == sk) {
if (sel >= 0) {
write_unlock_bh(&ip6_ra_lock);
kfree(new_ra);
return -EADDRINUSE;
}
*rap = ra->next;
write_unlock_bh(&ip6_ra_lock);
sock_put(sk);
kfree(ra);
return 0;
}
}
if (!new_ra) {
write_unlock_bh(&ip6_ra_lock);
return -ENOBUFS;
}
new_ra->sk = sk;
new_ra->sel = sel;
new_ra->next = ra;
*rap = new_ra;
sock_hold(sk);
write_unlock_bh(&ip6_ra_lock);
return 0;
}
struct ipv6_txoptions *ipv6_update_options(struct sock *sk,
struct ipv6_txoptions *opt)
{
if (inet_test_bit(IS_ICSK, sk)) {
if (opt &&
!((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) &&
inet_sk(sk)->inet_daddr != LOOPBACK4_IPV6) {
struct inet_connection_sock *icsk = inet_csk(sk);
icsk->icsk_ext_hdr_len = opt->opt_flen + opt->opt_nflen;
icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie);
}
}
opt = xchg((__force struct ipv6_txoptions **)&inet6_sk(sk)->opt,
opt);
sk_dst_reset(sk);
return opt;
}
static bool setsockopt_needs_rtnl(int optname)
{
switch (optname) {
case IPV6_ADDRFORM:
case IPV6_ADD_MEMBERSHIP:
case IPV6_DROP_MEMBERSHIP:
case IPV6_JOIN_ANYCAST:
case IPV6_LEAVE_ANYCAST:
case MCAST_JOIN_GROUP:
case MCAST_LEAVE_GROUP:
case MCAST_JOIN_SOURCE_GROUP:
case MCAST_LEAVE_SOURCE_GROUP:
case MCAST_BLOCK_SOURCE:
case MCAST_UNBLOCK_SOURCE:
case MCAST_MSFILTER:
return true;
}
return false;
}
static int copy_group_source_from_sockptr(struct group_source_req *greqs,
sockptr_t optval, int optlen)
{
if (in_compat_syscall()) {
struct compat_group_source_req gr32;
if (optlen < sizeof(gr32))
return -EINVAL;
if (copy_from_sockptr(&gr32, optval, sizeof(gr32)))
return -EFAULT;
greqs->gsr_interface = gr32.gsr_interface;
greqs->gsr_group = gr32.gsr_group;
greqs->gsr_source = gr32.gsr_source;
} else {
if (optlen < sizeof(*greqs))
return -EINVAL;
if (copy_from_sockptr(greqs, optval, sizeof(*greqs)))
return -EFAULT;
}
return 0;
}
static int do_ipv6_mcast_group_source(struct sock *sk, int optname,
sockptr_t optval, int optlen)
{
struct group_source_req greqs;
int omode, add;
int ret;
ret = copy_group_source_from_sockptr(&greqs, optval, optlen);
if (ret)
return ret;
if (greqs.gsr_group.ss_family != AF_INET6 ||
greqs.gsr_source.ss_family != AF_INET6)
return -EADDRNOTAVAIL;
if (optname == MCAST_BLOCK_SOURCE) {
omode = MCAST_EXCLUDE;
add = 1;
} else if (optname == MCAST_UNBLOCK_SOURCE) {
omode = MCAST_EXCLUDE;
add = 0;
} else if (optname == MCAST_JOIN_SOURCE_GROUP) {
struct sockaddr_in6 *psin6;
int retv;
psin6 = (struct sockaddr_in6 *)&greqs.gsr_group;
retv = ipv6_sock_mc_join_ssm(sk, greqs.gsr_interface,
&psin6->sin6_addr,
MCAST_INCLUDE);
/* prior join w/ different source is ok */
if (retv && retv != -EADDRINUSE)
return retv;
omode = MCAST_INCLUDE;
add = 1;
} else /* MCAST_LEAVE_SOURCE_GROUP */ {
omode = MCAST_INCLUDE;
add = 0;
}
return ip6_mc_source(add, omode, sk, &greqs);
}
static int ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval,
int optlen)
{
struct group_filter *gsf;
int ret;
if (optlen < GROUP_FILTER_SIZE(0))
return -EINVAL;
if (optlen > READ_ONCE(sock_net(sk)->core.sysctl_optmem_max))
return -ENOBUFS;
gsf = memdup_sockptr(optval, optlen);
if (IS_ERR(gsf))
return PTR_ERR(gsf);
/* numsrc >= (4G-140)/128 overflow in 32 bits */
ret = -ENOBUFS;
if (gsf->gf_numsrc >= 0x1ffffffU ||
gsf->gf_numsrc > sysctl_mld_max_msf)
goto out_free_gsf;
ret = -EINVAL;
if (GROUP_FILTER_SIZE(gsf->gf_numsrc) > optlen)
goto out_free_gsf;
ret = ip6_mc_msfilter(sk, gsf, gsf->gf_slist_flex);
out_free_gsf:
kfree(gsf);
return ret;
}
static int compat_ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval,
int optlen)
{
const int size0 = offsetof(struct compat_group_filter, gf_slist_flex);
struct compat_group_filter *gf32;
void *p;
int ret;
int n;
if (optlen < size0)
return -EINVAL;
if (optlen > READ_ONCE(sock_net(sk)->core.sysctl_optmem_max) - 4)
return -ENOBUFS;
p = kmalloc(optlen + 4, GFP_KERNEL);
if (!p)
return -ENOMEM;
gf32 = p + 4; /* we want ->gf_group and ->gf_slist_flex aligned */
ret = -EFAULT;
if (copy_from_sockptr(gf32, optval, optlen))
goto out_free_p;
/* numsrc >= (4G-140)/128 overflow in 32 bits */
ret = -ENOBUFS;
n = gf32->gf_numsrc;
if (n >= 0x1ffffffU || n > sysctl_mld_max_msf)
goto out_free_p;
ret = -EINVAL;
if (offsetof(struct compat_group_filter, gf_slist_flex[n]) > optlen)
goto out_free_p;
ret = ip6_mc_msfilter(sk, &(struct group_filter){
.gf_interface = gf32->gf_interface,
.gf_group = gf32->gf_group,
.gf_fmode = gf32->gf_fmode,
.gf_numsrc = gf32->gf_numsrc}, gf32->gf_slist_flex);
out_free_p:
kfree(p);
return ret;
}
static int ipv6_mcast_join_leave(struct sock *sk, int optname,
sockptr_t optval, int optlen)
{
struct sockaddr_in6 *psin6;
struct group_req greq;
if (optlen < sizeof(greq))
return -EINVAL;
if (copy_from_sockptr(&greq, optval, sizeof(greq)))
return -EFAULT;
if (greq.gr_group.ss_family != AF_INET6)
return -EADDRNOTAVAIL;
psin6 = (struct sockaddr_in6 *)&greq.gr_group;
if (optname == MCAST_JOIN_GROUP)
return ipv6_sock_mc_join(sk, greq.gr_interface,
&psin6->sin6_addr);
return ipv6_sock_mc_drop(sk, greq.gr_interface, &psin6->sin6_addr);
}
static int compat_ipv6_mcast_join_leave(struct sock *sk, int optname,
sockptr_t optval, int optlen)
{
struct compat_group_req gr32;
struct sockaddr_in6 *psin6;
if (optlen < sizeof(gr32))
return -EINVAL;
if (copy_from_sockptr(&gr32, optval, sizeof(gr32)))
return -EFAULT;
if (gr32.gr_group.ss_family != AF_INET6)
return -EADDRNOTAVAIL;
psin6 = (struct sockaddr_in6 *)&gr32.gr_group;
if (optname == MCAST_JOIN_GROUP)
return ipv6_sock_mc_join(sk, gr32.gr_interface,
&psin6->sin6_addr);
return ipv6_sock_mc_drop(sk, gr32.gr_interface, &psin6->sin6_addr);
}
static int ipv6_set_opt_hdr(struct sock *sk, int optname, sockptr_t optval,
int optlen)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct ipv6_opt_hdr *new = NULL;
struct net *net = sock_net(sk);
struct ipv6_txoptions *opt;
int err;
/* hop-by-hop / destination options are privileged option */
if (optname != IPV6_RTHDR && !sockopt_ns_capable(net->user_ns, CAP_NET_RAW))
return -EPERM;
/* remove any sticky options header with a zero option
* length, per RFC3542.
*/
if (optlen > 0) {
if (sockptr_is_null(optval))
return -EINVAL;
if (optlen < sizeof(struct ipv6_opt_hdr) ||
optlen & 0x7 ||
optlen > 8 * 255)
return -EINVAL;
new = memdup_sockptr(optval, optlen);
if (IS_ERR(new))
return PTR_ERR(new);
if (unlikely(ipv6_optlen(new) > optlen)) {
kfree(new);
return -EINVAL;
}
}
opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk));
opt = ipv6_renew_options(sk, opt, optname, new);
kfree(new);
if (IS_ERR(opt))
return PTR_ERR(opt);
/* routing header option needs extra check */
err = -EINVAL;
if (optname == IPV6_RTHDR && opt && opt->srcrt) {
struct ipv6_rt_hdr *rthdr = opt->srcrt;
switch (rthdr->type) {
#if IS_ENABLED(CONFIG_IPV6_MIP6)
case IPV6_SRCRT_TYPE_2:
if (rthdr->hdrlen != 2 || rthdr->segments_left != 1)
goto sticky_done;
break;
#endif
case IPV6_SRCRT_TYPE_4:
{
struct ipv6_sr_hdr *srh =
(struct ipv6_sr_hdr *)opt->srcrt;
if (!seg6_validate_srh(srh, optlen, false))
goto sticky_done;
break;
}
default:
goto sticky_done;
}
}
err = 0;
opt = ipv6_update_options(sk, opt);
sticky_done:
if (opt) {
atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
txopt_put(opt);
}
return err;
}
int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
sockptr_t optval, unsigned int optlen)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct net *net = sock_net(sk);
int val, valbool;
int retv = -ENOPROTOOPT;
bool needs_rtnl = setsockopt_needs_rtnl(optname);
if (sockptr_is_null(optval))
val = 0;
else {
if (optlen >= sizeof(int)) {
if (copy_from_sockptr(&val, optval, sizeof(val)))
return -EFAULT;
} else
val = 0;
}
valbool = (val != 0);
if (ip6_mroute_opt(optname))
return ip6_mroute_setsockopt(sk, optname, optval, optlen);
/* Handle options that can be set without locking the socket. */
switch (optname) {
case IPV6_UNICAST_HOPS:
if (optlen < sizeof(int))
return -EINVAL;
if (val > 255 || val < -1)
return -EINVAL;
WRITE_ONCE(np->hop_limit, val);
return 0;
case IPV6_MULTICAST_LOOP:
if (optlen < sizeof(int))
return -EINVAL;
if (val != valbool)
return -EINVAL;
inet6_assign_bit(MC6_LOOP, sk, valbool);
return 0;
case IPV6_MULTICAST_HOPS:
if (sk->sk_type == SOCK_STREAM)
return retv;
if (optlen < sizeof(int))
return -EINVAL;
if (val > 255 || val < -1)
return -EINVAL;
WRITE_ONCE(np->mcast_hops,
val == -1 ? IPV6_DEFAULT_MCASTHOPS : val);
return 0;
case IPV6_MTU:
if (optlen < sizeof(int))
return -EINVAL;
if (val && val < IPV6_MIN_MTU)
return -EINVAL;
WRITE_ONCE(np->frag_size, val);
return 0;
case IPV6_MINHOPCOUNT:
if (optlen < sizeof(int))
return -EINVAL;
if (val < 0 || val > 255)
return -EINVAL;
if (val)
static_branch_enable(&ip6_min_hopcount);
/* tcp_v6_err() and tcp_v6_rcv() might read min_hopcount
* while we are changing it.
*/
WRITE_ONCE(np->min_hopcount, val);
return 0;
case IPV6_RECVERR_RFC4884:
if (optlen < sizeof(int))
return -EINVAL;
if (val < 0 || val > 1)
return -EINVAL;
inet6_assign_bit(RECVERR6_RFC4884, sk, valbool);
return 0;
case IPV6_MULTICAST_ALL:
if (optlen < sizeof(int))
return -EINVAL;
inet6_assign_bit(MC6_ALL, sk, valbool);
return 0;
case IPV6_AUTOFLOWLABEL:
inet6_assign_bit(AUTOFLOWLABEL, sk, valbool);
inet6_set_bit(AUTOFLOWLABEL_SET, sk);
return 0;
case IPV6_DONTFRAG:
inet6_assign_bit(DONTFRAG, sk, valbool);
return 0;
case IPV6_RECVERR:
if (optlen < sizeof(int))
return -EINVAL;
inet6_assign_bit(RECVERR6, sk, valbool);
if (!val)
skb_errqueue_purge(&sk->sk_error_queue);
return 0;
case IPV6_ROUTER_ALERT_ISOLATE:
if (optlen < sizeof(int))
return -EINVAL;
inet6_assign_bit(RTALERT_ISOLATE, sk, valbool);
return 0;
case IPV6_MTU_DISCOVER:
if (optlen < sizeof(int))
return -EINVAL;
if (val < IPV6_PMTUDISC_DONT || val > IPV6_PMTUDISC_OMIT)
return -EINVAL;
WRITE_ONCE(np->pmtudisc, val);
return 0;
case IPV6_FLOWINFO_SEND:
if (optlen < sizeof(int))
return -EINVAL;
inet6_assign_bit(SNDFLOW, sk, valbool);
return 0;
case IPV6_ADDR_PREFERENCES:
if (optlen < sizeof(int))
return -EINVAL;
return ip6_sock_set_addr_preferences(sk, val);
case IPV6_MULTICAST_IF:
if (sk->sk_type == SOCK_STREAM)
return -ENOPROTOOPT;
if (optlen < sizeof(int))
return -EINVAL;
if (val) {
struct net_device *dev;
int bound_dev_if, midx;
rcu_read_lock();
dev = dev_get_by_index_rcu(net, val);
if (!dev) {
rcu_read_unlock();
return -ENODEV;
}
midx = l3mdev_master_ifindex_rcu(dev);
rcu_read_unlock();
bound_dev_if = READ_ONCE(sk->sk_bound_dev_if);
if (bound_dev_if &&
bound_dev_if != val &&
(!midx || midx != bound_dev_if))
return -EINVAL;
}
WRITE_ONCE(np->mcast_oif, val);
return 0;
case IPV6_UNICAST_IF:
{
struct net_device *dev;
int ifindex;
if (optlen != sizeof(int))
return -EINVAL;
ifindex = (__force int)ntohl((__force __be32)val);
if (!ifindex) {
WRITE_ONCE(np->ucast_oif, 0);
return 0;
}
dev = dev_get_by_index(net, ifindex);
if (!dev)
return -EADDRNOTAVAIL;
dev_put(dev);
if (READ_ONCE(sk->sk_bound_dev_if))
return -EINVAL;
WRITE_ONCE(np->ucast_oif, ifindex);
return 0;
}
}
if (needs_rtnl)
rtnl_lock();
sockopt_lock_sock(sk);
/* Another thread has converted the socket into IPv4 with
* IPV6_ADDRFORM concurrently.
*/
if (unlikely(sk->sk_family != AF_INET6))
goto unlock;
switch (optname) {
case IPV6_ADDRFORM:
if (optlen < sizeof(int))
goto e_inval;
if (val == PF_INET) {
if (sk->sk_type == SOCK_RAW)
break;
if (sk->sk_protocol == IPPROTO_UDP ||
sk->sk_protocol == IPPROTO_UDPLITE) {
struct udp_sock *up = udp_sk(sk);
if (up->pending == AF_INET6) {
retv = -EBUSY;
break;
}
} else if (sk->sk_protocol == IPPROTO_TCP) {
if (sk->sk_prot != &tcpv6_prot) {
retv = -EBUSY;
break;
}
} else {
break;
}
if (sk->sk_state != TCP_ESTABLISHED) {
retv = -ENOTCONN;
break;
}
if (ipv6_only_sock(sk) ||
!ipv6_addr_v4mapped(&sk->sk_v6_daddr)) {
retv = -EADDRNOTAVAIL;
break;
}
__ipv6_sock_mc_close(sk);
__ipv6_sock_ac_close(sk);
if (sk->sk_protocol == IPPROTO_TCP) {
struct inet_connection_sock *icsk = inet_csk(sk);
sock_prot_inuse_add(net, sk->sk_prot, -1);
sock_prot_inuse_add(net, &tcp_prot, 1);
/* Paired with READ_ONCE(sk->sk_prot) in inet6_stream_ops */
WRITE_ONCE(sk->sk_prot, &tcp_prot);
/* Paired with READ_ONCE() in tcp_(get|set)sockopt() */
WRITE_ONCE(icsk->icsk_af_ops, &ipv4_specific);
WRITE_ONCE(sk->sk_socket->ops, &inet_stream_ops);
WRITE_ONCE(sk->sk_family, PF_INET);
tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
} else {
struct proto *prot = &udp_prot;
if (sk->sk_protocol == IPPROTO_UDPLITE)
prot = &udplite_prot;
sock_prot_inuse_add(net, sk->sk_prot, -1);
sock_prot_inuse_add(net, prot, 1);
/* Paired with READ_ONCE(sk->sk_prot) in inet6_dgram_ops */
WRITE_ONCE(sk->sk_prot, prot);
WRITE_ONCE(sk->sk_socket->ops, &inet_dgram_ops);
WRITE_ONCE(sk->sk_family, PF_INET);
}
/* Disable all options not to allocate memory anymore,
* but there is still a race. See the lockless path
* in udpv6_sendmsg() and ipv6_local_rxpmtu().
*/
np->rxopt.all = 0;
inet6_cleanup_sock(sk);
module_put(THIS_MODULE);
retv = 0;
break;
}
goto e_inval;
case IPV6_V6ONLY:
if (optlen < sizeof(int) ||
inet_sk(sk)->inet_num)
goto e_inval;
sk->sk_ipv6only = valbool;
retv = 0;
break;
case IPV6_RECVPKTINFO:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxinfo = valbool;
retv = 0;
break;
case IPV6_2292PKTINFO:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxoinfo = valbool;
retv = 0;
break;
case IPV6_RECVHOPLIMIT:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxhlim = valbool;
retv = 0;
break;
case IPV6_2292HOPLIMIT:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxohlim = valbool;
retv = 0;
break;
case IPV6_RECVRTHDR:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.srcrt = valbool;
retv = 0;
break;
case IPV6_2292RTHDR:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.osrcrt = valbool;
retv = 0;
break;
case IPV6_RECVHOPOPTS:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.hopopts = valbool;
retv = 0;
break;
case IPV6_2292HOPOPTS:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.ohopopts = valbool;
retv = 0;
break;
case IPV6_RECVDSTOPTS:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.dstopts = valbool;
retv = 0;
break;
case IPV6_2292DSTOPTS:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.odstopts = valbool;
retv = 0;
break;
case IPV6_TCLASS:
if (optlen < sizeof(int))
goto e_inval;
if (val < -1 || val > 0xff)
goto e_inval;
/* RFC 3542, 6.5: default traffic class of 0x0 */
if (val == -1)
val = 0;
if (sk->sk_type == SOCK_STREAM) {
val &= ~INET_ECN_MASK;
val |= np->tclass & INET_ECN_MASK;
}
if (np->tclass != val) {
np->tclass = val;
sk_dst_reset(sk);
}
retv = 0;
break;
case IPV6_RECVTCLASS:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxtclass = valbool;
retv = 0;
break;
case IPV6_FLOWINFO:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxflow = valbool;
retv = 0;
break;
case IPV6_RECVPATHMTU:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxpmtu = valbool;
retv = 0;
break;
case IPV6_TRANSPARENT:
if (valbool && !sockopt_ns_capable(net->user_ns, CAP_NET_RAW) &&
!sockopt_ns_capable(net->user_ns, CAP_NET_ADMIN)) {
retv = -EPERM;
break;
}
if (optlen < sizeof(int))
goto e_inval;
/* we don't have a separate transparent bit for IPV6 we use the one in the IPv4 socket */
inet_assign_bit(TRANSPARENT, sk, valbool);
retv = 0;
break;
case IPV6_FREEBIND:
if (optlen < sizeof(int))
goto e_inval;
/* we also don't have a separate freebind bit for IPV6 */
inet_assign_bit(FREEBIND, sk, valbool);
retv = 0;
break;
case IPV6_RECVORIGDSTADDR:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxorigdstaddr = valbool;
retv = 0;
break;
case IPV6_HOPOPTS:
case IPV6_RTHDRDSTOPTS:
case IPV6_RTHDR:
case IPV6_DSTOPTS:
retv = ipv6_set_opt_hdr(sk, optname, optval, optlen);
break;
case IPV6_PKTINFO:
{
struct in6_pktinfo pkt;
if (optlen == 0)
goto e_inval;
else if (optlen < sizeof(struct in6_pktinfo) ||
sockptr_is_null(optval))
goto e_inval;
if (copy_from_sockptr(&pkt, optval, sizeof(pkt))) {
retv = -EFAULT;
break;
}
if (!sk_dev_equal_l3scope(sk, pkt.ipi6_ifindex))
goto e_inval;
np->sticky_pktinfo.ipi6_ifindex = pkt.ipi6_ifindex;
np->sticky_pktinfo.ipi6_addr = pkt.ipi6_addr;
retv = 0;
break;
}
case IPV6_2292PKTOPTIONS:
{
struct ipv6_txoptions *opt = NULL;
struct msghdr msg;
struct flowi6 fl6;
struct ipcm6_cookie ipc6;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.flowi6_mark = sk->sk_mark;
if (optlen == 0)
goto update;
/* 1K is probably excessive
* 1K is surely not enough, 2K per standard header is 16K.
*/
retv = -EINVAL;
if (optlen > 64*1024)
break;
opt = sock_kmalloc(sk, sizeof(*opt) + optlen, GFP_KERNEL);
retv = -ENOBUFS;
if (!opt)
break;
memset(opt, 0, sizeof(*opt));
refcount_set(&opt->refcnt, 1);
opt->tot_len = sizeof(*opt) + optlen;
retv = -EFAULT;
if (copy_from_sockptr(opt + 1, optval, optlen))
goto done;
msg.msg_controllen = optlen;
msg.msg_control_is_user = false;
msg.msg_control = (void *)(opt+1);
ipc6.opt = opt;
retv = ip6_datagram_send_ctl(net, sk, &msg, &fl6, &ipc6);
if (retv)
goto done;
update:
retv = 0;
opt = ipv6_update_options(sk, opt);
done:
if (opt) {
atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
txopt_put(opt);
}
break;
}
case IPV6_ADD_MEMBERSHIP:
case IPV6_DROP_MEMBERSHIP:
{
struct ipv6_mreq mreq;
if (optlen < sizeof(struct ipv6_mreq))
goto e_inval;
retv = -EPROTO;
if (inet_test_bit(IS_ICSK, sk))
break;
retv = -EFAULT;
if (copy_from_sockptr(&mreq, optval, sizeof(struct ipv6_mreq)))
break;
if (optname == IPV6_ADD_MEMBERSHIP)
retv = ipv6_sock_mc_join(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_multiaddr);
else
retv = ipv6_sock_mc_drop(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_multiaddr);
break;
}
case IPV6_JOIN_ANYCAST:
case IPV6_LEAVE_ANYCAST:
{
struct ipv6_mreq mreq;
if (optlen < sizeof(struct ipv6_mreq))
goto e_inval;
retv = -EFAULT;
if (copy_from_sockptr(&mreq, optval, sizeof(struct ipv6_mreq)))
break;
if (optname == IPV6_JOIN_ANYCAST)
retv = ipv6_sock_ac_join(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_acaddr);
else
retv = ipv6_sock_ac_drop(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_acaddr);
break;
}
case MCAST_JOIN_GROUP:
case MCAST_LEAVE_GROUP:
if (in_compat_syscall())
retv = compat_ipv6_mcast_join_leave(sk, optname, optval,
optlen);
else
retv = ipv6_mcast_join_leave(sk, optname, optval,
optlen);
break;
case MCAST_JOIN_SOURCE_GROUP:
case MCAST_LEAVE_SOURCE_GROUP:
case MCAST_BLOCK_SOURCE:
case MCAST_UNBLOCK_SOURCE:
retv = do_ipv6_mcast_group_source(sk, optname, optval, optlen);
break;
case MCAST_MSFILTER:
if (in_compat_syscall())
retv = compat_ipv6_set_mcast_msfilter(sk, optval,
optlen);
else
retv = ipv6_set_mcast_msfilter(sk, optval, optlen);
break;
case IPV6_ROUTER_ALERT:
if (optlen < sizeof(int))
goto e_inval;
retv = ip6_ra_control(sk, val);
if (retv == 0)
inet6_assign_bit(RTALERT, sk, valbool);
break;
case IPV6_FLOWLABEL_MGR:
retv = ipv6_flowlabel_opt(sk, optval, optlen);
break;
case IPV6_IPSEC_POLICY:
case IPV6_XFRM_POLICY:
retv = -EPERM;
if (!sockopt_ns_capable(net->user_ns, CAP_NET_ADMIN))
break;
retv = xfrm_user_policy(sk, optname, optval, optlen);
break;
case IPV6_RECVFRAGSIZE:
np->rxopt.bits.recvfragsize = valbool;
retv = 0;
break;
}
unlock:
sockopt_release_sock(sk);
if (needs_rtnl)
rtnl_unlock();
return retv;
e_inval:
retv = -EINVAL;
goto unlock;
}
int ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
unsigned int optlen)
{
int err;
if (level == SOL_IP && sk->sk_type != SOCK_RAW)
return udp_prot.setsockopt(sk, level, optname, optval, optlen);
if (level != SOL_IPV6)
return -ENOPROTOOPT;
err = do_ipv6_setsockopt(sk, level, optname, optval, optlen);
#ifdef CONFIG_NETFILTER
/* we need to exclude all possible ENOPROTOOPTs except default case */
if (err == -ENOPROTOOPT && optname != IPV6_IPSEC_POLICY &&
optname != IPV6_XFRM_POLICY)
err = nf_setsockopt(sk, PF_INET6, optname, optval, optlen);
#endif