forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 4
/
ip_sockglue.c
1785 lines (1572 loc) · 42.1 KB
/
ip_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
/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* The IP to API glue.
*
* Authors: see ip.c
*
* Fixes:
* Many : Split from ip.c , see ip.c for history.
* Martin Mares : TOS setting fixed.
* Alan Cox : Fixed a couple of oopses in Martin's
* TOS tweaks.
* Mike McLagan : Routing by source
*/
#include <linux/module.h>
#include <linux/types.h>
#include <linux/mm.h>
#include <linux/skbuff.h>
#include <linux/ip.h>
#include <linux/icmp.h>
#include <linux/inetdevice.h>
#include <linux/netdevice.h>
#include <linux/slab.h>
#include <net/sock.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/tcp_states.h>
#include <linux/udp.h>
#include <linux/igmp.h>
#include <linux/netfilter.h>
#include <linux/route.h>
#include <linux/mroute.h>
#include <net/inet_ecn.h>
#include <net/route.h>
#include <net/xfrm.h>
#include <net/compat.h>
#include <net/checksum.h>
#if IS_ENABLED(CONFIG_IPV6)
#include <net/transp_v6.h>
#endif
#include <net/ip_fib.h>
#include <linux/errqueue.h>
#include <linux/uaccess.h>
/*
* SOL_IP control messages.
*/
static void ip_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb)
{
struct in_pktinfo info = *PKTINFO_SKB_CB(skb);
info.ipi_addr.s_addr = ip_hdr(skb)->daddr;
put_cmsg(msg, SOL_IP, IP_PKTINFO, sizeof(info), &info);
}
static void ip_cmsg_recv_ttl(struct msghdr *msg, struct sk_buff *skb)
{
int ttl = ip_hdr(skb)->ttl;
put_cmsg(msg, SOL_IP, IP_TTL, sizeof(int), &ttl);
}
static void ip_cmsg_recv_tos(struct msghdr *msg, struct sk_buff *skb)
{
put_cmsg(msg, SOL_IP, IP_TOS, 1, &ip_hdr(skb)->tos);
}
static void ip_cmsg_recv_opts(struct msghdr *msg, struct sk_buff *skb)
{
if (IPCB(skb)->opt.optlen == 0)
return;
put_cmsg(msg, SOL_IP, IP_RECVOPTS, IPCB(skb)->opt.optlen,
ip_hdr(skb) + 1);
}
static void ip_cmsg_recv_retopts(struct net *net, struct msghdr *msg,
struct sk_buff *skb)
{
unsigned char optbuf[sizeof(struct ip_options) + 40];
struct ip_options *opt = (struct ip_options *)optbuf;
if (IPCB(skb)->opt.optlen == 0)
return;
if (ip_options_echo(net, opt, skb)) {
msg->msg_flags |= MSG_CTRUNC;
return;
}
ip_options_undo(opt);
put_cmsg(msg, SOL_IP, IP_RETOPTS, opt->optlen, opt->__data);
}
static void ip_cmsg_recv_fragsize(struct msghdr *msg, struct sk_buff *skb)
{
int val;
if (IPCB(skb)->frag_max_size == 0)
return;
val = IPCB(skb)->frag_max_size;
put_cmsg(msg, SOL_IP, IP_RECVFRAGSIZE, sizeof(val), &val);
}
static void ip_cmsg_recv_checksum(struct msghdr *msg, struct sk_buff *skb,
int tlen, int offset)
{
__wsum csum = skb->csum;
if (skb->ip_summed != CHECKSUM_COMPLETE)
return;
if (offset != 0) {
int tend_off = skb_transport_offset(skb) + tlen;
csum = csum_sub(csum, skb_checksum(skb, tend_off, offset, 0));
}
put_cmsg(msg, SOL_IP, IP_CHECKSUM, sizeof(__wsum), &csum);
}
static void ip_cmsg_recv_security(struct msghdr *msg, struct sk_buff *skb)
{
char *secdata;
u32 seclen, secid;
int err;
err = security_socket_getpeersec_dgram(NULL, skb, &secid);
if (err)
return;
err = security_secid_to_secctx(secid, &secdata, &seclen);
if (err)
return;
put_cmsg(msg, SOL_IP, SCM_SECURITY, seclen, secdata);
security_release_secctx(secdata, seclen);
}
static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
{
__be16 _ports[2], *ports;
struct sockaddr_in sin;
/* 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 = skb_header_pointer(skb, skb_transport_offset(skb),
sizeof(_ports), &_ports);
if (!ports)
return;
sin.sin_family = AF_INET;
sin.sin_addr.s_addr = ip_hdr(skb)->daddr;
sin.sin_port = ports[1];
memset(sin.sin_zero, 0, sizeof(sin.sin_zero));
put_cmsg(msg, SOL_IP, IP_ORIGDSTADDR, sizeof(sin), &sin);
}
void ip_cmsg_recv_offset(struct msghdr *msg, struct sock *sk,
struct sk_buff *skb, int tlen, int offset)
{
unsigned long flags = inet_cmsg_flags(inet_sk(sk));
if (!flags)
return;
/* Ordered by supposed usage frequency */
if (flags & IP_CMSG_PKTINFO) {
ip_cmsg_recv_pktinfo(msg, skb);
flags &= ~IP_CMSG_PKTINFO;
if (!flags)
return;
}
if (flags & IP_CMSG_TTL) {
ip_cmsg_recv_ttl(msg, skb);
flags &= ~IP_CMSG_TTL;
if (!flags)
return;
}
if (flags & IP_CMSG_TOS) {
ip_cmsg_recv_tos(msg, skb);
flags &= ~IP_CMSG_TOS;
if (!flags)
return;
}
if (flags & IP_CMSG_RECVOPTS) {
ip_cmsg_recv_opts(msg, skb);
flags &= ~IP_CMSG_RECVOPTS;
if (!flags)
return;
}
if (flags & IP_CMSG_RETOPTS) {
ip_cmsg_recv_retopts(sock_net(sk), msg, skb);
flags &= ~IP_CMSG_RETOPTS;
if (!flags)
return;
}
if (flags & IP_CMSG_PASSSEC) {
ip_cmsg_recv_security(msg, skb);
flags &= ~IP_CMSG_PASSSEC;
if (!flags)
return;
}
if (flags & IP_CMSG_ORIGDSTADDR) {
ip_cmsg_recv_dstaddr(msg, skb);
flags &= ~IP_CMSG_ORIGDSTADDR;
if (!flags)
return;
}
if (flags & IP_CMSG_CHECKSUM)
ip_cmsg_recv_checksum(msg, skb, tlen, offset);
if (flags & IP_CMSG_RECVFRAGSIZE)
ip_cmsg_recv_fragsize(msg, skb);
}
EXPORT_SYMBOL(ip_cmsg_recv_offset);
int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc,
bool allow_ipv6)
{
int err, val;
struct cmsghdr *cmsg;
struct net *net = sock_net(sk);
for_each_cmsghdr(cmsg, msg) {
if (!CMSG_OK(msg, cmsg))
return -EINVAL;
#if IS_ENABLED(CONFIG_IPV6)
if (allow_ipv6 &&
cmsg->cmsg_level == SOL_IPV6 &&
cmsg->cmsg_type == IPV6_PKTINFO) {
struct in6_pktinfo *src_info;
if (cmsg->cmsg_len < CMSG_LEN(sizeof(*src_info)))
return -EINVAL;
src_info = (struct in6_pktinfo *)CMSG_DATA(cmsg);
if (!ipv6_addr_v4mapped(&src_info->ipi6_addr))
return -EINVAL;
if (src_info->ipi6_ifindex)
ipc->oif = src_info->ipi6_ifindex;
ipc->addr = src_info->ipi6_addr.s6_addr32[3];
continue;
}
#endif
if (cmsg->cmsg_level == SOL_SOCKET) {
err = __sock_cmsg_send(sk, cmsg, &ipc->sockc);
if (err)
return err;
continue;
}
if (cmsg->cmsg_level != SOL_IP)
continue;
switch (cmsg->cmsg_type) {
case IP_RETOPTS:
err = cmsg->cmsg_len - sizeof(struct cmsghdr);
/* Our caller is responsible for freeing ipc->opt */
err = ip_options_get(net, &ipc->opt,
KERNEL_SOCKPTR(CMSG_DATA(cmsg)),
err < 40 ? err : 40);
if (err)
return err;
break;
case IP_PKTINFO:
{
struct in_pktinfo *info;
if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct in_pktinfo)))
return -EINVAL;
info = (struct in_pktinfo *)CMSG_DATA(cmsg);
if (info->ipi_ifindex)
ipc->oif = info->ipi_ifindex;
ipc->addr = info->ipi_spec_dst.s_addr;
break;
}
case IP_TTL:
if (cmsg->cmsg_len != CMSG_LEN(sizeof(int)))
return -EINVAL;
val = *(int *)CMSG_DATA(cmsg);
if (val < 1 || val > 255)
return -EINVAL;
ipc->ttl = val;
break;
case IP_TOS:
if (cmsg->cmsg_len == CMSG_LEN(sizeof(int)))
val = *(int *)CMSG_DATA(cmsg);
else if (cmsg->cmsg_len == CMSG_LEN(sizeof(u8)))
val = *(u8 *)CMSG_DATA(cmsg);
else
return -EINVAL;
if (val < 0 || val > 255)
return -EINVAL;
ipc->tos = val;
ipc->priority = rt_tos2priority(ipc->tos);
break;
case IP_PROTOCOL:
if (cmsg->cmsg_len != CMSG_LEN(sizeof(int)))
return -EINVAL;
val = *(int *)CMSG_DATA(cmsg);
if (val < 1 || val > 255)
return -EINVAL;
ipc->protocol = val;
break;
default:
return -EINVAL;
}
}
return 0;
}
static void ip_ra_destroy_rcu(struct rcu_head *head)
{
struct ip_ra_chain *ra = container_of(head, struct ip_ra_chain, rcu);
sock_put(ra->saved_sk);
kfree(ra);
}
int ip_ra_control(struct sock *sk, unsigned char on,
void (*destructor)(struct sock *))
{
struct ip_ra_chain *ra, *new_ra;
struct ip_ra_chain __rcu **rap;
struct net *net = sock_net(sk);
if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num == IPPROTO_RAW)
return -EINVAL;
new_ra = on ? kmalloc(sizeof(*new_ra), GFP_KERNEL) : NULL;
if (on && !new_ra)
return -ENOMEM;
mutex_lock(&net->ipv4.ra_mutex);
for (rap = &net->ipv4.ra_chain;
(ra = rcu_dereference_protected(*rap,
lockdep_is_held(&net->ipv4.ra_mutex))) != NULL;
rap = &ra->next) {
if (ra->sk == sk) {
if (on) {
mutex_unlock(&net->ipv4.ra_mutex);
kfree(new_ra);
return -EADDRINUSE;
}
/* dont let ip_call_ra_chain() use sk again */
ra->sk = NULL;
RCU_INIT_POINTER(*rap, ra->next);
mutex_unlock(&net->ipv4.ra_mutex);
if (ra->destructor)
ra->destructor(sk);
/*
* Delay sock_put(sk) and kfree(ra) after one rcu grace
* period. This guarantee ip_call_ra_chain() dont need
* to mess with socket refcounts.
*/
ra->saved_sk = sk;
call_rcu(&ra->rcu, ip_ra_destroy_rcu);
return 0;
}
}
if (!new_ra) {
mutex_unlock(&net->ipv4.ra_mutex);
return -ENOBUFS;
}
new_ra->sk = sk;
new_ra->destructor = destructor;
RCU_INIT_POINTER(new_ra->next, ra);
rcu_assign_pointer(*rap, new_ra);
sock_hold(sk);
mutex_unlock(&net->ipv4.ra_mutex);
return 0;
}
static void ipv4_icmp_error_rfc4884(const struct sk_buff *skb,
struct sock_ee_data_rfc4884 *out)
{
switch (icmp_hdr(skb)->type) {
case ICMP_DEST_UNREACH:
case ICMP_TIME_EXCEEDED:
case ICMP_PARAMETERPROB:
ip_icmp_error_rfc4884(skb, out, sizeof(struct icmphdr),
icmp_hdr(skb)->un.reserved[1] * 4);
}
}
void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err,
__be16 port, u32 info, u8 *payload)
{
struct sock_exterr_skb *serr;
skb = skb_clone(skb, GFP_ATOMIC);
if (!skb)
return;
serr = SKB_EXT_ERR(skb);
serr->ee.ee_errno = err;
serr->ee.ee_origin = SO_EE_ORIGIN_ICMP;
serr->ee.ee_type = icmp_hdr(skb)->type;
serr->ee.ee_code = icmp_hdr(skb)->code;
serr->ee.ee_pad = 0;
serr->ee.ee_info = info;
serr->ee.ee_data = 0;
serr->addr_offset = (u8 *)&(((struct iphdr *)(icmp_hdr(skb) + 1))->daddr) -
skb_network_header(skb);
serr->port = port;
if (skb_pull(skb, payload - skb->data)) {
if (inet_test_bit(RECVERR_RFC4884, sk))
ipv4_icmp_error_rfc4884(skb, &serr->ee.ee_rfc4884);
skb_reset_transport_header(skb);
if (sock_queue_err_skb(sk, skb) == 0)
return;
}
kfree_skb(skb);
}
EXPORT_SYMBOL_GPL(ip_icmp_error);
void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 info)
{
struct sock_exterr_skb *serr;
struct iphdr *iph;
struct sk_buff *skb;
if (!inet_test_bit(RECVERR, sk))
return;
skb = alloc_skb(sizeof(struct iphdr), GFP_ATOMIC);
if (!skb)
return;
skb_put(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
iph = ip_hdr(skb);
iph->daddr = 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 = port;
__skb_pull(skb, skb_tail_pointer(skb) - skb->data);
skb_reset_transport_header(skb);
if (sock_queue_err_skb(sk, 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 ipv4_datagram_support_addr(struct sock_exterr_skb *serr)
{
return serr->ee.ee_origin == SO_EE_ORIGIN_ICMP ||
serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL || serr->port;
}
/* IPv4 supports cmsg on all imcp errors and some timestamps
*
* Timestamp code paths do not initialize the fields expected by cmsg:
* the PKTINFO fields in skb->cb[]. Fill those in here.
*/
static bool ipv4_datagram_support_cmsg(const struct sock *sk,
struct sk_buff *skb,
int ee_origin)
{
struct in_pktinfo *info;
if (ee_origin == SO_EE_ORIGIN_ICMP)
return true;
if (ee_origin == SO_EE_ORIGIN_LOCAL)
return false;
/* Support IP_PKTINFO on tstamp packets if requested, to correlate
* timestamp with egress dev. Not possible for packets without iif
* or without payload (SOF_TIMESTAMPING_OPT_TSONLY).
*/
info = PKTINFO_SKB_CB(skb);
if (!(READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_CMSG) ||
!info->ipi_ifindex)
return false;
info->ipi_spec_dst.s_addr = ip_hdr(skb)->saddr;
return true;
}
/*
* Handle MSG_ERRQUEUE
*/
int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
{
struct sock_exterr_skb *serr;
struct sk_buff *skb;
DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name);
struct {
struct sock_extended_err ee;
struct sockaddr_in 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 && ipv4_datagram_support_addr(serr)) {
sin->sin_family = AF_INET;
sin->sin_addr.s_addr = *(__be32 *)(skb_network_header(skb) +
serr->addr_offset);
sin->sin_port = serr->port;
memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
*addr_len = sizeof(*sin);
}
memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err));
sin = &errhdr.offender;
memset(sin, 0, sizeof(*sin));
if (ipv4_datagram_support_cmsg(sk, skb, serr->ee.ee_origin)) {
sin->sin_family = AF_INET;
sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
if (inet_cmsg_flags(inet_sk(sk)))
ip_cmsg_recv(msg, skb);
}
put_cmsg(msg, SOL_IP, IP_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;
}
void __ip_sock_set_tos(struct sock *sk, int val)
{
u8 old_tos = inet_sk(sk)->tos;
if (sk->sk_type == SOCK_STREAM) {
val &= ~INET_ECN_MASK;
val |= old_tos & INET_ECN_MASK;
}
if (old_tos != val) {
WRITE_ONCE(inet_sk(sk)->tos, val);
WRITE_ONCE(sk->sk_priority, rt_tos2priority(val));
sk_dst_reset(sk);
}
}
void ip_sock_set_tos(struct sock *sk, int val)
{
sockopt_lock_sock(sk);
__ip_sock_set_tos(sk, val);
sockopt_release_sock(sk);
}
EXPORT_SYMBOL(ip_sock_set_tos);
void ip_sock_set_freebind(struct sock *sk)
{
inet_set_bit(FREEBIND, sk);
}
EXPORT_SYMBOL(ip_sock_set_freebind);
void ip_sock_set_recverr(struct sock *sk)
{
inet_set_bit(RECVERR, sk);
}
EXPORT_SYMBOL(ip_sock_set_recverr);
int ip_sock_set_mtu_discover(struct sock *sk, int val)
{
if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_OMIT)
return -EINVAL;
WRITE_ONCE(inet_sk(sk)->pmtudisc, val);
return 0;
}
EXPORT_SYMBOL(ip_sock_set_mtu_discover);
void ip_sock_set_pktinfo(struct sock *sk)
{
inet_set_bit(PKTINFO, sk);
}
EXPORT_SYMBOL(ip_sock_set_pktinfo);
/*
* Socket option code for IP. This is the end of the line after any
* TCP,UDP etc options on an IP socket.
*/
static bool setsockopt_needs_rtnl(int optname)
{
switch (optname) {
case IP_ADD_MEMBERSHIP:
case IP_ADD_SOURCE_MEMBERSHIP:
case IP_BLOCK_SOURCE:
case IP_DROP_MEMBERSHIP:
case IP_DROP_SOURCE_MEMBERSHIP:
case IP_MSFILTER:
case IP_UNBLOCK_SOURCE:
case MCAST_BLOCK_SOURCE:
case MCAST_MSFILTER:
case MCAST_JOIN_GROUP:
case MCAST_JOIN_SOURCE_GROUP:
case MCAST_LEAVE_GROUP:
case MCAST_LEAVE_SOURCE_GROUP:
case MCAST_UNBLOCK_SOURCE:
return true;
}
return false;
}
static int set_mcast_msfilter(struct sock *sk, int ifindex,
int numsrc, int fmode,
struct sockaddr_storage *group,
struct sockaddr_storage *list)
{
struct ip_msfilter *msf;
struct sockaddr_in *psin;
int err, i;
msf = kmalloc(IP_MSFILTER_SIZE(numsrc), GFP_KERNEL);
if (!msf)
return -ENOBUFS;
psin = (struct sockaddr_in *)group;
if (psin->sin_family != AF_INET)
goto Eaddrnotavail;
msf->imsf_multiaddr = psin->sin_addr.s_addr;
msf->imsf_interface = 0;
msf->imsf_fmode = fmode;
msf->imsf_numsrc = numsrc;
for (i = 0; i < numsrc; ++i) {
psin = (struct sockaddr_in *)&list[i];
if (psin->sin_family != AF_INET)
goto Eaddrnotavail;
msf->imsf_slist_flex[i] = psin->sin_addr.s_addr;
}
err = ip_mc_msfilter(sk, msf, ifindex);
kfree(msf);
return err;
Eaddrnotavail:
kfree(msf);
return -EADDRNOTAVAIL;
}
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_mcast_group_source(struct sock *sk, int optname,
sockptr_t optval, int optlen)
{
struct group_source_req greqs;
struct ip_mreq_source mreqs;
struct sockaddr_in *psin;
int omode, add, err;
err = copy_group_source_from_sockptr(&greqs, optval, optlen);
if (err)
return err;
if (greqs.gsr_group.ss_family != AF_INET ||
greqs.gsr_source.ss_family != AF_INET)
return -EADDRNOTAVAIL;
psin = (struct sockaddr_in *)&greqs.gsr_group;
mreqs.imr_multiaddr = psin->sin_addr.s_addr;
psin = (struct sockaddr_in *)&greqs.gsr_source;
mreqs.imr_sourceaddr = psin->sin_addr.s_addr;
mreqs.imr_interface = 0; /* use index for mc_source */
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 ip_mreqn mreq;
psin = (struct sockaddr_in *)&greqs.gsr_group;
mreq.imr_multiaddr = psin->sin_addr;
mreq.imr_address.s_addr = 0;
mreq.imr_ifindex = greqs.gsr_interface;
err = ip_mc_join_group_ssm(sk, &mreq, MCAST_INCLUDE);
if (err && err != -EADDRINUSE)
return err;
greqs.gsr_interface = mreq.imr_ifindex;
omode = MCAST_INCLUDE;
add = 1;
} else /* MCAST_LEAVE_SOURCE_GROUP */ {
omode = MCAST_INCLUDE;
add = 0;
}
return ip_mc_source(add, omode, sk, &mreqs, greqs.gsr_interface);
}
static int ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, int optlen)
{
struct group_filter *gsf = NULL;
int err;
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 */
err = -ENOBUFS;
if (gsf->gf_numsrc >= 0x1ffffff ||
gsf->gf_numsrc > READ_ONCE(sock_net(sk)->ipv4.sysctl_igmp_max_msf))
goto out_free_gsf;
err = -EINVAL;
if (GROUP_FILTER_SIZE(gsf->gf_numsrc) > optlen)
goto out_free_gsf;
err = set_mcast_msfilter(sk, gsf->gf_interface, gsf->gf_numsrc,
gsf->gf_fmode, &gsf->gf_group,
gsf->gf_slist_flex);
out_free_gsf:
kfree(gsf);
return err;
}
static int compat_ip_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;
unsigned int n;
void *p;
int err;
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 */
err = -EFAULT;
if (copy_from_sockptr(gf32, optval, optlen))
goto out_free_gsf;
/* numsrc >= (4G-140)/128 overflow in 32 bits */
n = gf32->gf_numsrc;
err = -ENOBUFS;
if (n >= 0x1ffffff)
goto out_free_gsf;
err = -EINVAL;
if (offsetof(struct compat_group_filter, gf_slist_flex[n]) > optlen)
goto out_free_gsf;
/* numsrc >= (4G-140)/128 overflow in 32 bits */
err = -ENOBUFS;
if (n > READ_ONCE(sock_net(sk)->ipv4.sysctl_igmp_max_msf))
goto out_free_gsf;
err = set_mcast_msfilter(sk, gf32->gf_interface, n, gf32->gf_fmode,
&gf32->gf_group, gf32->gf_slist_flex);
out_free_gsf:
kfree(p);
return err;
}
static int ip_mcast_join_leave(struct sock *sk, int optname,
sockptr_t optval, int optlen)
{
struct ip_mreqn mreq = { };
struct sockaddr_in *psin;
struct group_req greq;
if (optlen < sizeof(struct group_req))
return -EINVAL;
if (copy_from_sockptr(&greq, optval, sizeof(greq)))
return -EFAULT;
psin = (struct sockaddr_in *)&greq.gr_group;
if (psin->sin_family != AF_INET)
return -EINVAL;
mreq.imr_multiaddr = psin->sin_addr;
mreq.imr_ifindex = greq.gr_interface;
if (optname == MCAST_JOIN_GROUP)
return ip_mc_join_group(sk, &mreq);
return ip_mc_leave_group(sk, &mreq);
}
static int compat_ip_mcast_join_leave(struct sock *sk, int optname,
sockptr_t optval, int optlen)
{
struct compat_group_req greq;
struct ip_mreqn mreq = { };
struct sockaddr_in *psin;
if (optlen < sizeof(struct compat_group_req))
return -EINVAL;
if (copy_from_sockptr(&greq, optval, sizeof(greq)))
return -EFAULT;
psin = (struct sockaddr_in *)&greq.gr_group;
if (psin->sin_family != AF_INET)
return -EINVAL;
mreq.imr_multiaddr = psin->sin_addr;
mreq.imr_ifindex = greq.gr_interface;
if (optname == MCAST_JOIN_GROUP)
return ip_mc_join_group(sk, &mreq);
return ip_mc_leave_group(sk, &mreq);
}
DEFINE_STATIC_KEY_FALSE(ip4_min_ttl);
int do_ip_setsockopt(struct sock *sk, int level, int optname,
sockptr_t optval, unsigned int optlen)
{
struct inet_sock *inet = inet_sk(sk);
struct net *net = sock_net(sk);
int val = 0, err, retv;
bool needs_rtnl = setsockopt_needs_rtnl(optname);
switch (optname) {
case IP_PKTINFO:
case IP_RECVTTL:
case IP_RECVOPTS:
case IP_RECVTOS:
case IP_RETOPTS:
case IP_TOS:
case IP_TTL:
case IP_HDRINCL:
case IP_MTU_DISCOVER:
case IP_RECVERR:
case IP_ROUTER_ALERT:
case IP_FREEBIND:
case IP_PASSSEC:
case IP_TRANSPARENT:
case IP_MINTTL:
case IP_NODEFRAG:
case IP_BIND_ADDRESS_NO_PORT:
case IP_UNICAST_IF:
case IP_MULTICAST_TTL:
case IP_MULTICAST_ALL:
case IP_MULTICAST_LOOP:
case IP_RECVORIGDSTADDR:
case IP_CHECKSUM:
case IP_RECVFRAGSIZE:
case IP_RECVERR_RFC4884:
case IP_LOCAL_PORT_RANGE:
if (optlen >= sizeof(int)) {
if (copy_from_sockptr(&val, optval, sizeof(val)))
return -EFAULT;
} else if (optlen >= sizeof(char)) {
unsigned char ucval;
if (copy_from_sockptr(&ucval, optval, sizeof(ucval)))
return -EFAULT;
val = (int) ucval;
}
}
/* If optlen==0, it is equivalent to val == 0 */
if (optname == IP_ROUTER_ALERT) {
retv = ip_ra_control(sk, val ? 1 : 0, NULL);
if (retv == 0)
inet_assign_bit(RTALERT, sk, val);
return retv;
}
if (ip_mroute_opt(optname))
return ip_mroute_setsockopt(sk, optname, optval, optlen);
/* Handle options that can be set without locking the socket. */
switch (optname) {
case IP_PKTINFO:
inet_assign_bit(PKTINFO, sk, val);
return 0;
case IP_RECVTTL:
inet_assign_bit(TTL, sk, val);
return 0;
case IP_RECVTOS:
inet_assign_bit(TOS, sk, val);
return 0;
case IP_RECVOPTS:
inet_assign_bit(RECVOPTS, sk, val);
return 0;
case IP_RETOPTS:
inet_assign_bit(RETOPTS, sk, val);
return 0;
case IP_PASSSEC:
inet_assign_bit(PASSSEC, sk, val);
return 0;
case IP_RECVORIGDSTADDR:
inet_assign_bit(ORIGDSTADDR, sk, val);
return 0;
case IP_RECVFRAGSIZE:
if (sk->sk_type != SOCK_RAW && sk->sk_type != SOCK_DGRAM)
return -EINVAL;
inet_assign_bit(RECVFRAGSIZE, sk, val);
return 0;
case IP_RECVERR:
inet_assign_bit(RECVERR, sk, val);
if (!val)
skb_errqueue_purge(&sk->sk_error_queue);
return 0;
case IP_RECVERR_RFC4884:
if (val < 0 || val > 1)
return -EINVAL;
inet_assign_bit(RECVERR_RFC4884, sk, val);
return 0;
case IP_FREEBIND:
if (optlen < 1)
return -EINVAL;
inet_assign_bit(FREEBIND, sk, val);
return 0;
case IP_HDRINCL:
if (sk->sk_type != SOCK_RAW)
return -ENOPROTOOPT;
inet_assign_bit(HDRINCL, sk, val);
return 0;
case IP_MULTICAST_LOOP:
if (optlen < 1)
return -EINVAL;