forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 17
/
tcp_ipv6.c
2447 lines (2095 loc) · 64 KB
/
tcp_ipv6.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
/*
* TCP over IPv6
* Linux INET6 implementation
*
* Authors:
* Pedro Roque <[email protected]>
*
* Based on:
* linux/net/ipv4/tcp.c
* linux/net/ipv4/tcp_input.c
* linux/net/ipv4/tcp_output.c
*
* Fixes:
* Hideaki YOSHIFUJI : sin6_scope_id support
* YOSHIFUJI Hideaki @USAGI and: Support IPV6_V6ONLY socket option, which
* Alexey Kuznetsov allow both IPv4 and IPv6 sockets to bind
* a single port at the same time.
* YOSHIFUJI Hideaki @USAGI: convert /proc/net/tcp6 to seq_file.
*/
#include <linux/bottom_half.h>
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/jiffies.h>
#include <linux/in.h>
#include <linux/in6.h>
#include <linux/netdevice.h>
#include <linux/init.h>
#include <linux/jhash.h>
#include <linux/ipsec.h>
#include <linux/times.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/ipv6.h>
#include <linux/icmpv6.h>
#include <linux/random.h>
#include <linux/indirect_call_wrapper.h>
#include <net/tcp.h>
#include <net/ndisc.h>
#include <net/inet6_hashtables.h>
#include <net/inet6_connection_sock.h>
#include <net/ipv6.h>
#include <net/transp_v6.h>
#include <net/addrconf.h>
#include <net/ip6_route.h>
#include <net/ip6_checksum.h>
#include <net/inet_ecn.h>
#include <net/protocol.h>
#include <net/xfrm.h>
#include <net/snmp.h>
#include <net/dsfield.h>
#include <net/timewait_sock.h>
#include <net/inet_common.h>
#include <net/secure_seq.h>
#include <net/hotdata.h>
#include <net/busy_poll.h>
#include <net/rstreason.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <crypto/hash.h>
#include <linux/scatterlist.h>
#include <trace/events/tcp.h>
static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb,
enum sk_rst_reason reason);
static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
struct request_sock *req);
INDIRECT_CALLABLE_SCOPE int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb);
static const struct inet_connection_sock_af_ops ipv6_mapped;
const struct inet_connection_sock_af_ops ipv6_specific;
#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO)
static const struct tcp_sock_af_ops tcp_sock_ipv6_specific;
static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific;
#endif
/* Helper returning the inet6 address from a given tcp socket.
* It can be used in TCP stack instead of inet6_sk(sk).
* This avoids a dereference and allow compiler optimizations.
* It is a specialized version of inet6_sk_generic().
*/
#define tcp_inet6_sk(sk) (&container_of_const(tcp_sk(sk), \
struct tcp6_sock, tcp)->inet6)
static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
if (dst && dst_hold_safe(dst)) {
rcu_assign_pointer(sk->sk_rx_dst, dst);
sk->sk_rx_dst_ifindex = skb->skb_iif;
sk->sk_rx_dst_cookie = rt6_get_cookie(dst_rt6_info(dst));
}
}
static u32 tcp_v6_init_seq(const struct sk_buff *skb)
{
return secure_tcpv6_seq(ipv6_hdr(skb)->daddr.s6_addr32,
ipv6_hdr(skb)->saddr.s6_addr32,
tcp_hdr(skb)->dest,
tcp_hdr(skb)->source);
}
static u32 tcp_v6_init_ts_off(const struct net *net, const struct sk_buff *skb)
{
return secure_tcpv6_ts_off(net, ipv6_hdr(skb)->daddr.s6_addr32,
ipv6_hdr(skb)->saddr.s6_addr32);
}
static int tcp_v6_pre_connect(struct sock *sk, struct sockaddr *uaddr,
int addr_len)
{
/* This check is replicated from tcp_v6_connect() and intended to
* prevent BPF program called below from accessing bytes that are out
* of the bound specified by user in addr_len.
*/
if (addr_len < SIN6_LEN_RFC2133)
return -EINVAL;
sock_owned_by_me(sk);
return BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr, &addr_len);
}
static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
int addr_len)
{
struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr;
struct inet_connection_sock *icsk = inet_csk(sk);
struct in6_addr *saddr = NULL, *final_p, final;
struct inet_timewait_death_row *tcp_death_row;
struct ipv6_pinfo *np = tcp_inet6_sk(sk);
struct inet_sock *inet = inet_sk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct net *net = sock_net(sk);
struct ipv6_txoptions *opt;
struct dst_entry *dst;
struct flowi6 fl6;
int addr_type;
int err;
if (addr_len < SIN6_LEN_RFC2133)
return -EINVAL;
if (usin->sin6_family != AF_INET6)
return -EAFNOSUPPORT;
memset(&fl6, 0, sizeof(fl6));
if (inet6_test_bit(SNDFLOW, sk)) {
fl6.flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK;
IP6_ECN_flow_init(fl6.flowlabel);
if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) {
struct ip6_flowlabel *flowlabel;
flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
if (IS_ERR(flowlabel))
return -EINVAL;
fl6_sock_release(flowlabel);
}
}
/*
* connect() to INADDR_ANY means loopback (BSD'ism).
*/
if (ipv6_addr_any(&usin->sin6_addr)) {
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);
if (addr_type & IPV6_ADDR_MULTICAST)
return -ENETUNREACH;
if (addr_type&IPV6_ADDR_LINKLOCAL) {
if (addr_len >= sizeof(struct sockaddr_in6) &&
usin->sin6_scope_id) {
/* If interface is set while binding, indices
* must coincide.
*/
if (!sk_dev_equal_l3scope(sk, usin->sin6_scope_id))
return -EINVAL;
sk->sk_bound_dev_if = usin->sin6_scope_id;
}
/* Connect to link-local address requires an interface */
if (!sk->sk_bound_dev_if)
return -EINVAL;
}
if (tp->rx_opt.ts_recent_stamp &&
!ipv6_addr_equal(&sk->sk_v6_daddr, &usin->sin6_addr)) {
tp->rx_opt.ts_recent = 0;
tp->rx_opt.ts_recent_stamp = 0;
WRITE_ONCE(tp->write_seq, 0);
}
sk->sk_v6_daddr = usin->sin6_addr;
np->flow_label = fl6.flowlabel;
/*
* TCP over IPv4
*/
if (addr_type & IPV6_ADDR_MAPPED) {
u32 exthdrlen = icsk->icsk_ext_hdr_len;
struct sockaddr_in sin;
if (ipv6_only_sock(sk))
return -ENETUNREACH;
sin.sin_family = AF_INET;
sin.sin_port = usin->sin6_port;
sin.sin_addr.s_addr = usin->sin6_addr.s6_addr32[3];
/* Paired with READ_ONCE() in tcp_(get|set)sockopt() */
WRITE_ONCE(icsk->icsk_af_ops, &ipv6_mapped);
if (sk_is_mptcp(sk))
mptcpv6_handle_mapped(sk, true);
sk->sk_backlog_rcv = tcp_v4_do_rcv;
#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO)
tp->af_specific = &tcp_sock_ipv6_mapped_specific;
#endif
err = tcp_v4_connect(sk, (struct sockaddr *)&sin, sizeof(sin));
if (err) {
icsk->icsk_ext_hdr_len = exthdrlen;
/* Paired with READ_ONCE() in tcp_(get|set)sockopt() */
WRITE_ONCE(icsk->icsk_af_ops, &ipv6_specific);
if (sk_is_mptcp(sk))
mptcpv6_handle_mapped(sk, false);
sk->sk_backlog_rcv = tcp_v6_do_rcv;
#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO)
tp->af_specific = &tcp_sock_ipv6_specific;
#endif
goto failure;
}
np->saddr = sk->sk_v6_rcv_saddr;
return err;
}
if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr))
saddr = &sk->sk_v6_rcv_saddr;
fl6.flowi6_proto = IPPROTO_TCP;
fl6.daddr = sk->sk_v6_daddr;
fl6.saddr = saddr ? *saddr : np->saddr;
fl6.flowlabel = ip6_make_flowinfo(np->tclass, np->flow_label);
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.flowi6_mark = sk->sk_mark;
fl6.fl6_dport = usin->sin6_port;
fl6.fl6_sport = inet->inet_sport;
fl6.flowi6_uid = sk->sk_uid;
opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk));
final_p = fl6_update_dst(&fl6, opt, &final);
security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6));
dst = ip6_dst_lookup_flow(net, sk, &fl6, final_p);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
goto failure;
}
tp->tcp_usec_ts = dst_tcp_usec_ts(dst);
tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row;
if (!saddr) {
saddr = &fl6.saddr;
err = inet_bhash2_update_saddr(sk, saddr, AF_INET6);
if (err)
goto failure;
}
/* set the source address */
np->saddr = *saddr;
inet->inet_rcv_saddr = LOOPBACK4_IPV6;
sk->sk_gso_type = SKB_GSO_TCPV6;
ip6_dst_store(sk, dst, NULL, NULL);
icsk->icsk_ext_hdr_len = 0;
if (opt)
icsk->icsk_ext_hdr_len = opt->opt_flen +
opt->opt_nflen;
tp->rx_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
inet->inet_dport = usin->sin6_port;
tcp_set_state(sk, TCP_SYN_SENT);
err = inet6_hash_connect(tcp_death_row, sk);
if (err)
goto late_failure;
sk_set_txhash(sk);
if (likely(!tp->repair)) {
if (!tp->write_seq)
WRITE_ONCE(tp->write_seq,
secure_tcpv6_seq(np->saddr.s6_addr32,
sk->sk_v6_daddr.s6_addr32,
inet->inet_sport,
inet->inet_dport));
tp->tsoffset = secure_tcpv6_ts_off(net, np->saddr.s6_addr32,
sk->sk_v6_daddr.s6_addr32);
}
if (tcp_fastopen_defer_connect(sk, &err))
return err;
if (err)
goto late_failure;
err = tcp_connect(sk);
if (err)
goto late_failure;
return 0;
late_failure:
tcp_set_state(sk, TCP_CLOSE);
inet_bhash2_reset_saddr(sk);
failure:
inet->inet_dport = 0;
sk->sk_route_caps = 0;
return err;
}
static void tcp_v6_mtu_reduced(struct sock *sk)
{
struct dst_entry *dst;
u32 mtu;
if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
return;
mtu = READ_ONCE(tcp_sk(sk)->mtu_info);
/* Drop requests trying to increase our current mss.
* Check done in __ip6_rt_update_pmtu() is too late.
*/
if (tcp_mtu_to_mss(sk, mtu) >= tcp_sk(sk)->mss_cache)
return;
dst = inet6_csk_update_pmtu(sk, mtu);
if (!dst)
return;
if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) {
tcp_sync_mss(sk, dst_mtu(dst));
tcp_simple_retransmit(sk);
}
}
static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
const struct tcphdr *th = (struct tcphdr *)(skb->data+offset);
struct net *net = dev_net(skb->dev);
struct request_sock *fastopen;
struct ipv6_pinfo *np;
struct tcp_sock *tp;
__u32 seq, snd_una;
struct sock *sk;
bool fatal;
int err;
sk = __inet6_lookup_established(net, net->ipv4.tcp_death_row.hashinfo,
&hdr->daddr, th->dest,
&hdr->saddr, ntohs(th->source),
skb->dev->ifindex, inet6_sdif(skb));
if (!sk) {
__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
ICMP6_MIB_INERRORS);
return -ENOENT;
}
if (sk->sk_state == TCP_TIME_WAIT) {
/* To increase the counter of ignored icmps for TCP-AO */
tcp_ao_ignore_icmp(sk, AF_INET6, type, code);
inet_twsk_put(inet_twsk(sk));
return 0;
}
seq = ntohl(th->seq);
fatal = icmpv6_err_convert(type, code, &err);
if (sk->sk_state == TCP_NEW_SYN_RECV) {
tcp_req_err(sk, seq, fatal);
return 0;
}
if (tcp_ao_ignore_icmp(sk, AF_INET6, type, code)) {
sock_put(sk);
return 0;
}
bh_lock_sock(sk);
if (sock_owned_by_user(sk) && type != ICMPV6_PKT_TOOBIG)
__NET_INC_STATS(net, LINUX_MIB_LOCKDROPPEDICMPS);
if (sk->sk_state == TCP_CLOSE)
goto out;
if (static_branch_unlikely(&ip6_min_hopcount)) {
/* min_hopcount can be changed concurrently from do_ipv6_setsockopt() */
if (ipv6_hdr(skb)->hop_limit < READ_ONCE(tcp_inet6_sk(sk)->min_hopcount)) {
__NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP);
goto out;
}
}
tp = tcp_sk(sk);
/* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */
fastopen = rcu_dereference(tp->fastopen_rsk);
snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una;
if (sk->sk_state != TCP_LISTEN &&
!between(seq, snd_una, tp->snd_nxt)) {
__NET_INC_STATS(net, LINUX_MIB_OUTOFWINDOWICMPS);
goto out;
}
np = tcp_inet6_sk(sk);
if (type == NDISC_REDIRECT) {
if (!sock_owned_by_user(sk)) {
struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
if (dst)
dst->ops->redirect(dst, sk, skb);
}
goto out;
}
if (type == ICMPV6_PKT_TOOBIG) {
u32 mtu = ntohl(info);
/* We are not interested in TCP_LISTEN and open_requests
* (SYN-ACKs send out by Linux are always <576bytes so
* they should go through unfragmented).
*/
if (sk->sk_state == TCP_LISTEN)
goto out;
if (!ip6_sk_accept_pmtu(sk))
goto out;
if (mtu < IPV6_MIN_MTU)
goto out;
WRITE_ONCE(tp->mtu_info, mtu);
if (!sock_owned_by_user(sk))
tcp_v6_mtu_reduced(sk);
else if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED,
&sk->sk_tsq_flags))
sock_hold(sk);
goto out;
}
/* Might be for an request_sock */
switch (sk->sk_state) {
case TCP_SYN_SENT:
case TCP_SYN_RECV:
/* Only in fast or simultaneous open. If a fast open socket is
* already accepted it is treated as a connected one below.
*/
if (fastopen && !fastopen->sk)
break;
ipv6_icmp_error(sk, skb, err, th->dest, ntohl(info), (u8 *)th);
if (!sock_owned_by_user(sk)) {
WRITE_ONCE(sk->sk_err, err);
sk_error_report(sk); /* Wake people up to see the error (see connect in sock.c) */
tcp_done(sk);
} else {
WRITE_ONCE(sk->sk_err_soft, err);
}
goto out;
case TCP_LISTEN:
break;
default:
/* check if this ICMP message allows revert of backoff.
* (see RFC 6069)
*/
if (!fastopen && type == ICMPV6_DEST_UNREACH &&
code == ICMPV6_NOROUTE)
tcp_ld_RTO_revert(sk, seq);
}
if (!sock_owned_by_user(sk) && inet6_test_bit(RECVERR6, sk)) {
WRITE_ONCE(sk->sk_err, err);
sk_error_report(sk);
} else {
WRITE_ONCE(sk->sk_err_soft, err);
}
out:
bh_unlock_sock(sk);
sock_put(sk);
return 0;
}
static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
struct flowi *fl,
struct request_sock *req,
struct tcp_fastopen_cookie *foc,
enum tcp_synack_type synack_type,
struct sk_buff *syn_skb)
{
struct inet_request_sock *ireq = inet_rsk(req);
const struct ipv6_pinfo *np = tcp_inet6_sk(sk);
struct ipv6_txoptions *opt;
struct flowi6 *fl6 = &fl->u.ip6;
struct sk_buff *skb;
int err = -ENOMEM;
u8 tclass;
/* First, grab a route. */
if (!dst && (dst = inet6_csk_route_req(sk, fl6, req,
IPPROTO_TCP)) == NULL)
goto done;
skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb);
if (skb) {
__tcp_v6_send_check(skb, &ireq->ir_v6_loc_addr,
&ireq->ir_v6_rmt_addr);
fl6->daddr = ireq->ir_v6_rmt_addr;
if (inet6_test_bit(REPFLOW, sk) && ireq->pktopts)
fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));
tclass = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) ?
(tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) |
(np->tclass & INET_ECN_MASK) :
np->tclass;
if (!INET_ECN_is_capable(tclass) &&
tcp_bpf_ca_needs_ecn((struct sock *)req))
tclass |= INET_ECN_ECT_0;
rcu_read_lock();
opt = ireq->ipv6_opt;
if (!opt)
opt = rcu_dereference(np->opt);
err = ip6_xmit(sk, skb, fl6, skb->mark ? : READ_ONCE(sk->sk_mark),
opt, tclass, READ_ONCE(sk->sk_priority));
rcu_read_unlock();
err = net_xmit_eval(err);
}
done:
return err;
}
static void tcp_v6_reqsk_destructor(struct request_sock *req)
{
kfree(inet_rsk(req)->ipv6_opt);
consume_skb(inet_rsk(req)->pktopts);
}
#ifdef CONFIG_TCP_MD5SIG
static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(const struct sock *sk,
const struct in6_addr *addr,
int l3index)
{
return tcp_md5_do_lookup(sk, l3index,
(union tcp_md5_addr *)addr, AF_INET6);
}
static struct tcp_md5sig_key *tcp_v6_md5_lookup(const struct sock *sk,
const struct sock *addr_sk)
{
int l3index;
l3index = l3mdev_master_ifindex_by_index(sock_net(sk),
addr_sk->sk_bound_dev_if);
return tcp_v6_md5_do_lookup(sk, &addr_sk->sk_v6_daddr,
l3index);
}
static int tcp_v6_parse_md5_keys(struct sock *sk, int optname,
sockptr_t optval, int optlen)
{
struct tcp_md5sig cmd;
struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&cmd.tcpm_addr;
union tcp_ao_addr *addr;
int l3index = 0;
u8 prefixlen;
bool l3flag;
u8 flags;
if (optlen < sizeof(cmd))
return -EINVAL;
if (copy_from_sockptr(&cmd, optval, sizeof(cmd)))
return -EFAULT;
if (sin6->sin6_family != AF_INET6)
return -EINVAL;
flags = cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX;
l3flag = cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX;
if (optname == TCP_MD5SIG_EXT &&
cmd.tcpm_flags & TCP_MD5SIG_FLAG_PREFIX) {
prefixlen = cmd.tcpm_prefixlen;
if (prefixlen > 128 || (ipv6_addr_v4mapped(&sin6->sin6_addr) &&
prefixlen > 32))
return -EINVAL;
} else {
prefixlen = ipv6_addr_v4mapped(&sin6->sin6_addr) ? 32 : 128;
}
if (optname == TCP_MD5SIG_EXT && cmd.tcpm_ifindex &&
cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX) {
struct net_device *dev;
rcu_read_lock();
dev = dev_get_by_index_rcu(sock_net(sk), cmd.tcpm_ifindex);
if (dev && netif_is_l3_master(dev))
l3index = dev->ifindex;
rcu_read_unlock();
/* ok to reference set/not set outside of rcu;
* right now device MUST be an L3 master
*/
if (!dev || !l3index)
return -EINVAL;
}
if (!cmd.tcpm_keylen) {
if (ipv6_addr_v4mapped(&sin6->sin6_addr))
return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3],
AF_INET, prefixlen,
l3index, flags);
return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr,
AF_INET6, prefixlen, l3index, flags);
}
if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN)
return -EINVAL;
if (ipv6_addr_v4mapped(&sin6->sin6_addr)) {
addr = (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3];
/* Don't allow keys for peers that have a matching TCP-AO key.
* See the comment in tcp_ao_add_cmd()
*/
if (tcp_ao_required(sk, addr, AF_INET,
l3flag ? l3index : -1, false))
return -EKEYREJECTED;
return tcp_md5_do_add(sk, addr,
AF_INET, prefixlen, l3index, flags,
cmd.tcpm_key, cmd.tcpm_keylen);
}
addr = (union tcp_md5_addr *)&sin6->sin6_addr;
/* Don't allow keys for peers that have a matching TCP-AO key.
* See the comment in tcp_ao_add_cmd()
*/
if (tcp_ao_required(sk, addr, AF_INET6, l3flag ? l3index : -1, false))
return -EKEYREJECTED;
return tcp_md5_do_add(sk, addr, AF_INET6, prefixlen, l3index, flags,
cmd.tcpm_key, cmd.tcpm_keylen);
}
static int tcp_v6_md5_hash_headers(struct tcp_sigpool *hp,
const struct in6_addr *daddr,
const struct in6_addr *saddr,
const struct tcphdr *th, int nbytes)
{
struct tcp6_pseudohdr *bp;
struct scatterlist sg;
struct tcphdr *_th;
bp = hp->scratch;
/* 1. TCP pseudo-header (RFC2460) */
bp->saddr = *saddr;
bp->daddr = *daddr;
bp->protocol = cpu_to_be32(IPPROTO_TCP);
bp->len = cpu_to_be32(nbytes);
_th = (struct tcphdr *)(bp + 1);
memcpy(_th, th, sizeof(*th));
_th->check = 0;
sg_init_one(&sg, bp, sizeof(*bp) + sizeof(*th));
ahash_request_set_crypt(hp->req, &sg, NULL,
sizeof(*bp) + sizeof(*th));
return crypto_ahash_update(hp->req);
}
static int tcp_v6_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
const struct in6_addr *daddr, struct in6_addr *saddr,
const struct tcphdr *th)
{
struct tcp_sigpool hp;
if (tcp_sigpool_start(tcp_md5_sigpool_id, &hp))
goto clear_hash_nostart;
if (crypto_ahash_init(hp.req))
goto clear_hash;
if (tcp_v6_md5_hash_headers(&hp, daddr, saddr, th, th->doff << 2))
goto clear_hash;
if (tcp_md5_hash_key(&hp, key))
goto clear_hash;
ahash_request_set_crypt(hp.req, NULL, md5_hash, 0);
if (crypto_ahash_final(hp.req))
goto clear_hash;
tcp_sigpool_end(&hp);
return 0;
clear_hash:
tcp_sigpool_end(&hp);
clear_hash_nostart:
memset(md5_hash, 0, 16);
return 1;
}
static int tcp_v6_md5_hash_skb(char *md5_hash,
const struct tcp_md5sig_key *key,
const struct sock *sk,
const struct sk_buff *skb)
{
const struct tcphdr *th = tcp_hdr(skb);
const struct in6_addr *saddr, *daddr;
struct tcp_sigpool hp;
if (sk) { /* valid for establish/request sockets */
saddr = &sk->sk_v6_rcv_saddr;
daddr = &sk->sk_v6_daddr;
} else {
const struct ipv6hdr *ip6h = ipv6_hdr(skb);
saddr = &ip6h->saddr;
daddr = &ip6h->daddr;
}
if (tcp_sigpool_start(tcp_md5_sigpool_id, &hp))
goto clear_hash_nostart;
if (crypto_ahash_init(hp.req))
goto clear_hash;
if (tcp_v6_md5_hash_headers(&hp, daddr, saddr, th, skb->len))
goto clear_hash;
if (tcp_sigpool_hash_skb_data(&hp, skb, th->doff << 2))
goto clear_hash;
if (tcp_md5_hash_key(&hp, key))
goto clear_hash;
ahash_request_set_crypt(hp.req, NULL, md5_hash, 0);
if (crypto_ahash_final(hp.req))
goto clear_hash;
tcp_sigpool_end(&hp);
return 0;
clear_hash:
tcp_sigpool_end(&hp);
clear_hash_nostart:
memset(md5_hash, 0, 16);
return 1;
}
#endif
static void tcp_v6_init_req(struct request_sock *req,
const struct sock *sk_listener,
struct sk_buff *skb,
u32 tw_isn)
{
bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags);
struct inet_request_sock *ireq = inet_rsk(req);
const struct ipv6_pinfo *np = tcp_inet6_sk(sk_listener);
ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
/* So that link locals have meaning */
if ((!sk_listener->sk_bound_dev_if || l3_slave) &&
ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
ireq->ir_iif = tcp_v6_iif(skb);
if (!tw_isn &&
(ipv6_opt_accepted(sk_listener, skb, &TCP_SKB_CB(skb)->header.h6) ||
np->rxopt.bits.rxinfo ||
np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim ||
np->rxopt.bits.rxohlim || inet6_test_bit(REPFLOW, sk_listener))) {
refcount_inc(&skb->users);
ireq->pktopts = skb;
}
}
static struct dst_entry *tcp_v6_route_req(const struct sock *sk,
struct sk_buff *skb,
struct flowi *fl,
struct request_sock *req,
u32 tw_isn)
{
tcp_v6_init_req(req, sk, skb, tw_isn);
if (security_inet_conn_request(sk, skb, req))
return NULL;
return inet6_csk_route_req(sk, &fl->u.ip6, req, IPPROTO_TCP);
}
struct request_sock_ops tcp6_request_sock_ops __read_mostly = {
.family = AF_INET6,
.obj_size = sizeof(struct tcp6_request_sock),
.rtx_syn_ack = tcp_rtx_synack,
.send_ack = tcp_v6_reqsk_send_ack,
.destructor = tcp_v6_reqsk_destructor,
.send_reset = tcp_v6_send_reset,
.syn_ack_timeout = tcp_syn_ack_timeout,
};
const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {
.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) -
sizeof(struct ipv6hdr),
#ifdef CONFIG_TCP_MD5SIG
.req_md5_lookup = tcp_v6_md5_lookup,
.calc_md5_hash = tcp_v6_md5_hash_skb,
#endif
#ifdef CONFIG_TCP_AO
.ao_lookup = tcp_v6_ao_lookup_rsk,
.ao_calc_key = tcp_v6_ao_calc_key_rsk,
.ao_synack_hash = tcp_v6_ao_synack_hash,
#endif
#ifdef CONFIG_SYN_COOKIES
.cookie_init_seq = cookie_v6_init_sequence,
#endif
.route_req = tcp_v6_route_req,
.init_seq = tcp_v6_init_seq,
.init_ts_off = tcp_v6_init_ts_off,
.send_synack = tcp_v6_send_synack,
};
static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 seq,
u32 ack, u32 win, u32 tsval, u32 tsecr,
int oif, int rst, u8 tclass, __be32 label,
u32 priority, u32 txhash, struct tcp_key *key)
{
const struct tcphdr *th = tcp_hdr(skb);
struct tcphdr *t1;
struct sk_buff *buff;
struct flowi6 fl6;
struct net *net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev);
struct sock *ctl_sk = net->ipv6.tcp_sk;
unsigned int tot_len = sizeof(struct tcphdr);
__be32 mrst = 0, *topt;
struct dst_entry *dst;
__u32 mark = 0;
if (tsecr)
tot_len += TCPOLEN_TSTAMP_ALIGNED;
if (tcp_key_is_md5(key))
tot_len += TCPOLEN_MD5SIG_ALIGNED;
if (tcp_key_is_ao(key))
tot_len += tcp_ao_len_aligned(key->ao_key);
#ifdef CONFIG_MPTCP
if (rst && !tcp_key_is_md5(key)) {
mrst = mptcp_reset_option(skb);
if (mrst)
tot_len += sizeof(__be32);
}
#endif
buff = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC);
if (!buff)
return;
skb_reserve(buff, MAX_TCP_HEADER);
t1 = skb_push(buff, tot_len);
skb_reset_transport_header(buff);
/* Swap the send and the receive. */
memset(t1, 0, sizeof(*t1));
t1->dest = th->source;
t1->source = th->dest;
t1->doff = tot_len / 4;
t1->seq = htonl(seq);
t1->ack_seq = htonl(ack);
t1->ack = !rst || !th->ack;
t1->rst = rst;
t1->window = htons(win);
topt = (__be32 *)(t1 + 1);
if (tsecr) {
*topt++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
(TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP);
*topt++ = htonl(tsval);
*topt++ = htonl(tsecr);
}
if (mrst)
*topt++ = mrst;
#ifdef CONFIG_TCP_MD5SIG
if (tcp_key_is_md5(key)) {
*topt++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
(TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG);
tcp_v6_md5_hash_hdr((__u8 *)topt, key->md5_key,
&ipv6_hdr(skb)->saddr,
&ipv6_hdr(skb)->daddr, t1);
}
#endif
#ifdef CONFIG_TCP_AO
if (tcp_key_is_ao(key)) {
*topt++ = htonl((TCPOPT_AO << 24) |
(tcp_ao_len(key->ao_key) << 16) |
(key->ao_key->sndid << 8) |
(key->rcv_next));
tcp_ao_hash_hdr(AF_INET6, (char *)topt, key->ao_key,
key->traffic_key,
(union tcp_ao_addr *)&ipv6_hdr(skb)->saddr,
(union tcp_ao_addr *)&ipv6_hdr(skb)->daddr,
t1, key->sne);
}
#endif
memset(&fl6, 0, sizeof(fl6));
fl6.daddr = ipv6_hdr(skb)->saddr;
fl6.saddr = ipv6_hdr(skb)->daddr;
fl6.flowlabel = label;
buff->ip_summed = CHECKSUM_PARTIAL;
__tcp_v6_send_check(buff, &fl6.saddr, &fl6.daddr);
fl6.flowi6_proto = IPPROTO_TCP;
if (rt6_need_strict(&fl6.daddr) && !oif)
fl6.flowi6_oif = tcp_v6_iif(skb);
else {
if (!oif && netif_index_is_l3_master(net, skb->skb_iif))
oif = skb->skb_iif;
fl6.flowi6_oif = oif;
}
if (sk) {
if (sk->sk_state == TCP_TIME_WAIT)
mark = inet_twsk(sk)->tw_mark;
else
mark = READ_ONCE(sk->sk_mark);
skb_set_delivery_time(buff, tcp_transmit_time(sk), true);
}
if (txhash) {
/* autoflowlabel/skb_get_hash_flowi6 rely on buff->hash */
skb_set_hash(buff, txhash, PKT_HASH_TYPE_L4);
}
fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark) ?: mark;
fl6.fl6_dport = t1->dest;
fl6.fl6_sport = t1->source;
fl6.flowi6_uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL);
security_skb_classify_flow(skb, flowi6_to_flowi_common(&fl6));
/* Pass a socket to ip6_dst_lookup either it is for RST
* Underlying function will use this to retrieve the network
* namespace
*/
if (sk && sk->sk_state != TCP_TIME_WAIT)
dst = ip6_dst_lookup_flow(net, sk, &fl6, NULL); /*sk's xfrm_policy can be referred*/
else
dst = ip6_dst_lookup_flow(net, ctl_sk, &fl6, NULL);
if (!IS_ERR(dst)) {
skb_dst_set(buff, dst);
ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL,