forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 17
/
options.c
1651 lines (1419 loc) · 46.3 KB
/
options.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
/* Multipath TCP
*
* Copyright (c) 2017 - 2019, Intel Corporation.
*/
#define pr_fmt(fmt) "MPTCP: " fmt
#include <linux/kernel.h>
#include <crypto/sha2.h>
#include <net/tcp.h>
#include <net/mptcp.h>
#include "protocol.h"
#include "mib.h"
#include <trace/events/mptcp.h>
static bool mptcp_cap_flag_sha256(u8 flags)
{
return (flags & MPTCP_CAP_FLAG_MASK) == MPTCP_CAP_HMAC_SHA256;
}
static void mptcp_parse_option(const struct sk_buff *skb,
const unsigned char *ptr, int opsize,
struct mptcp_options_received *mp_opt)
{
u8 subtype = *ptr >> 4;
int expected_opsize;
u16 subopt;
u8 version;
u8 flags;
u8 i;
switch (subtype) {
case MPTCPOPT_MP_CAPABLE:
/* strict size checking */
if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) {
if (skb->len > tcp_hdr(skb)->doff << 2)
expected_opsize = TCPOLEN_MPTCP_MPC_ACK_DATA;
else
expected_opsize = TCPOLEN_MPTCP_MPC_ACK;
subopt = OPTION_MPTCP_MPC_ACK;
} else {
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK) {
expected_opsize = TCPOLEN_MPTCP_MPC_SYNACK;
subopt = OPTION_MPTCP_MPC_SYNACK;
} else {
expected_opsize = TCPOLEN_MPTCP_MPC_SYN;
subopt = OPTION_MPTCP_MPC_SYN;
}
}
/* Cfr RFC 8684 Section 3.3.0:
* If a checksum is present but its use had
* not been negotiated in the MP_CAPABLE handshake, the receiver MUST
* close the subflow with a RST, as it is not behaving as negotiated.
* If a checksum is not present when its use has been negotiated, the
* receiver MUST close the subflow with a RST, as it is considered
* broken
* We parse even option with mismatching csum presence, so that
* later in subflow_data_ready we can trigger the reset.
*/
if (opsize != expected_opsize &&
(expected_opsize != TCPOLEN_MPTCP_MPC_ACK_DATA ||
opsize != TCPOLEN_MPTCP_MPC_ACK_DATA_CSUM))
break;
/* try to be gentle vs future versions on the initial syn */
version = *ptr++ & MPTCP_VERSION_MASK;
if (opsize != TCPOLEN_MPTCP_MPC_SYN) {
if (version != MPTCP_SUPPORTED_VERSION)
break;
} else if (version < MPTCP_SUPPORTED_VERSION) {
break;
}
flags = *ptr++;
if (!mptcp_cap_flag_sha256(flags) ||
(flags & MPTCP_CAP_EXTENSIBILITY))
break;
/* RFC 6824, Section 3.1:
* "For the Checksum Required bit (labeled "A"), if either
* host requires the use of checksums, checksums MUST be used.
* In other words, the only way for checksums not to be used
* is if both hosts in their SYNs set A=0."
*/
if (flags & MPTCP_CAP_CHECKSUM_REQD)
mp_opt->suboptions |= OPTION_MPTCP_CSUMREQD;
mp_opt->deny_join_id0 = !!(flags & MPTCP_CAP_DENY_JOIN_ID0);
mp_opt->suboptions |= subopt;
if (opsize >= TCPOLEN_MPTCP_MPC_SYNACK) {
mp_opt->sndr_key = get_unaligned_be64(ptr);
ptr += 8;
}
if (opsize >= TCPOLEN_MPTCP_MPC_ACK) {
mp_opt->rcvr_key = get_unaligned_be64(ptr);
ptr += 8;
}
if (opsize >= TCPOLEN_MPTCP_MPC_ACK_DATA) {
/* Section 3.1.:
* "the data parameters in a MP_CAPABLE are semantically
* equivalent to those in a DSS option and can be used
* interchangeably."
*/
mp_opt->suboptions |= OPTION_MPTCP_DSS;
mp_opt->use_map = 1;
mp_opt->mpc_map = 1;
mp_opt->data_len = get_unaligned_be16(ptr);
ptr += 2;
}
if (opsize == TCPOLEN_MPTCP_MPC_ACK_DATA_CSUM) {
mp_opt->csum = get_unaligned((__force __sum16 *)ptr);
mp_opt->suboptions |= OPTION_MPTCP_CSUMREQD;
ptr += 2;
}
pr_debug("MP_CAPABLE version=%x, flags=%x, optlen=%d sndr=%llu, rcvr=%llu len=%d csum=%u",
version, flags, opsize, mp_opt->sndr_key,
mp_opt->rcvr_key, mp_opt->data_len, mp_opt->csum);
break;
case MPTCPOPT_MP_JOIN:
mp_opt->suboptions |= OPTIONS_MPTCP_MPJ;
if (opsize == TCPOLEN_MPTCP_MPJ_SYN) {
mp_opt->backup = *ptr++ & MPTCPOPT_BACKUP;
mp_opt->join_id = *ptr++;
mp_opt->token = get_unaligned_be32(ptr);
ptr += 4;
mp_opt->nonce = get_unaligned_be32(ptr);
ptr += 4;
pr_debug("MP_JOIN bkup=%u, id=%u, token=%u, nonce=%u",
mp_opt->backup, mp_opt->join_id,
mp_opt->token, mp_opt->nonce);
} else if (opsize == TCPOLEN_MPTCP_MPJ_SYNACK) {
mp_opt->backup = *ptr++ & MPTCPOPT_BACKUP;
mp_opt->join_id = *ptr++;
mp_opt->thmac = get_unaligned_be64(ptr);
ptr += 8;
mp_opt->nonce = get_unaligned_be32(ptr);
ptr += 4;
pr_debug("MP_JOIN bkup=%u, id=%u, thmac=%llu, nonce=%u",
mp_opt->backup, mp_opt->join_id,
mp_opt->thmac, mp_opt->nonce);
} else if (opsize == TCPOLEN_MPTCP_MPJ_ACK) {
ptr += 2;
memcpy(mp_opt->hmac, ptr, MPTCPOPT_HMAC_LEN);
pr_debug("MP_JOIN hmac");
} else {
mp_opt->suboptions &= ~OPTIONS_MPTCP_MPJ;
}
break;
case MPTCPOPT_DSS:
pr_debug("DSS");
ptr++;
/* we must clear 'mpc_map' be able to detect MP_CAPABLE
* map vs DSS map in mptcp_incoming_options(), and reconstruct
* map info accordingly
*/
mp_opt->mpc_map = 0;
flags = (*ptr++) & MPTCP_DSS_FLAG_MASK;
mp_opt->data_fin = (flags & MPTCP_DSS_DATA_FIN) != 0;
mp_opt->dsn64 = (flags & MPTCP_DSS_DSN64) != 0;
mp_opt->use_map = (flags & MPTCP_DSS_HAS_MAP) != 0;
mp_opt->ack64 = (flags & MPTCP_DSS_ACK64) != 0;
mp_opt->use_ack = (flags & MPTCP_DSS_HAS_ACK);
pr_debug("data_fin=%d dsn64=%d use_map=%d ack64=%d use_ack=%d",
mp_opt->data_fin, mp_opt->dsn64,
mp_opt->use_map, mp_opt->ack64,
mp_opt->use_ack);
expected_opsize = TCPOLEN_MPTCP_DSS_BASE;
if (mp_opt->use_ack) {
if (mp_opt->ack64)
expected_opsize += TCPOLEN_MPTCP_DSS_ACK64;
else
expected_opsize += TCPOLEN_MPTCP_DSS_ACK32;
}
if (mp_opt->use_map) {
if (mp_opt->dsn64)
expected_opsize += TCPOLEN_MPTCP_DSS_MAP64;
else
expected_opsize += TCPOLEN_MPTCP_DSS_MAP32;
}
/* Always parse any csum presence combination, we will enforce
* RFC 8684 Section 3.3.0 checks later in subflow_data_ready
*/
if (opsize != expected_opsize &&
opsize != expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM)
break;
mp_opt->suboptions |= OPTION_MPTCP_DSS;
if (mp_opt->use_ack) {
if (mp_opt->ack64) {
mp_opt->data_ack = get_unaligned_be64(ptr);
ptr += 8;
} else {
mp_opt->data_ack = get_unaligned_be32(ptr);
ptr += 4;
}
pr_debug("data_ack=%llu", mp_opt->data_ack);
}
if (mp_opt->use_map) {
if (mp_opt->dsn64) {
mp_opt->data_seq = get_unaligned_be64(ptr);
ptr += 8;
} else {
mp_opt->data_seq = get_unaligned_be32(ptr);
ptr += 4;
}
mp_opt->subflow_seq = get_unaligned_be32(ptr);
ptr += 4;
mp_opt->data_len = get_unaligned_be16(ptr);
ptr += 2;
if (opsize == expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM) {
mp_opt->suboptions |= OPTION_MPTCP_CSUMREQD;
mp_opt->csum = get_unaligned((__force __sum16 *)ptr);
ptr += 2;
}
pr_debug("data_seq=%llu subflow_seq=%u data_len=%u csum=%d:%u",
mp_opt->data_seq, mp_opt->subflow_seq,
mp_opt->data_len, !!(mp_opt->suboptions & OPTION_MPTCP_CSUMREQD),
mp_opt->csum);
}
break;
case MPTCPOPT_ADD_ADDR:
mp_opt->echo = (*ptr++) & MPTCP_ADDR_ECHO;
if (!mp_opt->echo) {
if (opsize == TCPOLEN_MPTCP_ADD_ADDR ||
opsize == TCPOLEN_MPTCP_ADD_ADDR_PORT)
mp_opt->addr.family = AF_INET;
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
else if (opsize == TCPOLEN_MPTCP_ADD_ADDR6 ||
opsize == TCPOLEN_MPTCP_ADD_ADDR6_PORT)
mp_opt->addr.family = AF_INET6;
#endif
else
break;
} else {
if (opsize == TCPOLEN_MPTCP_ADD_ADDR_BASE ||
opsize == TCPOLEN_MPTCP_ADD_ADDR_BASE_PORT)
mp_opt->addr.family = AF_INET;
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
else if (opsize == TCPOLEN_MPTCP_ADD_ADDR6_BASE ||
opsize == TCPOLEN_MPTCP_ADD_ADDR6_BASE_PORT)
mp_opt->addr.family = AF_INET6;
#endif
else
break;
}
mp_opt->suboptions |= OPTION_MPTCP_ADD_ADDR;
mp_opt->addr.id = *ptr++;
mp_opt->addr.port = 0;
mp_opt->ahmac = 0;
if (mp_opt->addr.family == AF_INET) {
memcpy((u8 *)&mp_opt->addr.addr.s_addr, (u8 *)ptr, 4);
ptr += 4;
if (opsize == TCPOLEN_MPTCP_ADD_ADDR_PORT ||
opsize == TCPOLEN_MPTCP_ADD_ADDR_BASE_PORT) {
mp_opt->addr.port = htons(get_unaligned_be16(ptr));
ptr += 2;
}
}
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
else {
memcpy(mp_opt->addr.addr6.s6_addr, (u8 *)ptr, 16);
ptr += 16;
if (opsize == TCPOLEN_MPTCP_ADD_ADDR6_PORT ||
opsize == TCPOLEN_MPTCP_ADD_ADDR6_BASE_PORT) {
mp_opt->addr.port = htons(get_unaligned_be16(ptr));
ptr += 2;
}
}
#endif
if (!mp_opt->echo) {
mp_opt->ahmac = get_unaligned_be64(ptr);
ptr += 8;
}
pr_debug("ADD_ADDR%s: id=%d, ahmac=%llu, echo=%d, port=%d",
(mp_opt->addr.family == AF_INET6) ? "6" : "",
mp_opt->addr.id, mp_opt->ahmac, mp_opt->echo, ntohs(mp_opt->addr.port));
break;
case MPTCPOPT_RM_ADDR:
if (opsize < TCPOLEN_MPTCP_RM_ADDR_BASE + 1 ||
opsize > TCPOLEN_MPTCP_RM_ADDR_BASE + MPTCP_RM_IDS_MAX)
break;
ptr++;
mp_opt->suboptions |= OPTION_MPTCP_RM_ADDR;
mp_opt->rm_list.nr = opsize - TCPOLEN_MPTCP_RM_ADDR_BASE;
for (i = 0; i < mp_opt->rm_list.nr; i++)
mp_opt->rm_list.ids[i] = *ptr++;
pr_debug("RM_ADDR: rm_list_nr=%d", mp_opt->rm_list.nr);
break;
case MPTCPOPT_MP_PRIO:
if (opsize != TCPOLEN_MPTCP_PRIO)
break;
mp_opt->suboptions |= OPTION_MPTCP_PRIO;
mp_opt->backup = *ptr++ & MPTCP_PRIO_BKUP;
pr_debug("MP_PRIO: prio=%d", mp_opt->backup);
break;
case MPTCPOPT_MP_FASTCLOSE:
if (opsize != TCPOLEN_MPTCP_FASTCLOSE)
break;
ptr += 2;
mp_opt->rcvr_key = get_unaligned_be64(ptr);
ptr += 8;
mp_opt->suboptions |= OPTION_MPTCP_FASTCLOSE;
pr_debug("MP_FASTCLOSE: recv_key=%llu", mp_opt->rcvr_key);
break;
case MPTCPOPT_RST:
if (opsize != TCPOLEN_MPTCP_RST)
break;
if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_RST))
break;
mp_opt->suboptions |= OPTION_MPTCP_RST;
flags = *ptr++;
mp_opt->reset_transient = flags & MPTCP_RST_TRANSIENT;
mp_opt->reset_reason = *ptr;
pr_debug("MP_RST: transient=%u reason=%u",
mp_opt->reset_transient, mp_opt->reset_reason);
break;
case MPTCPOPT_MP_FAIL:
if (opsize != TCPOLEN_MPTCP_FAIL)
break;
ptr += 2;
mp_opt->suboptions |= OPTION_MPTCP_FAIL;
mp_opt->fail_seq = get_unaligned_be64(ptr);
pr_debug("MP_FAIL: data_seq=%llu", mp_opt->fail_seq);
break;
default:
break;
}
}
void mptcp_get_options(const struct sk_buff *skb,
struct mptcp_options_received *mp_opt)
{
const struct tcphdr *th = tcp_hdr(skb);
const unsigned char *ptr;
int length;
/* initialize option status */
mp_opt->suboptions = 0;
length = (th->doff * 4) - sizeof(struct tcphdr);
ptr = (const unsigned char *)(th + 1);
while (length > 0) {
int opcode = *ptr++;
int opsize;
switch (opcode) {
case TCPOPT_EOL:
return;
case TCPOPT_NOP: /* Ref: RFC 793 section 3.1 */
length--;
continue;
default:
if (length < 2)
return;
opsize = *ptr++;
if (opsize < 2) /* "silly options" */
return;
if (opsize > length)
return; /* don't parse partial options */
if (opcode == TCPOPT_MPTCP)
mptcp_parse_option(skb, ptr, opsize, mp_opt);
ptr += opsize - 2;
length -= opsize;
}
}
}
bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb,
unsigned int *size, struct mptcp_out_options *opts)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
/* we will use snd_isn to detect first pkt [re]transmission
* in mptcp_established_options_mp()
*/
subflow->snd_isn = TCP_SKB_CB(skb)->end_seq;
if (subflow->request_mptcp) {
opts->suboptions = OPTION_MPTCP_MPC_SYN;
opts->csum_reqd = mptcp_is_checksum_enabled(sock_net(sk));
opts->allow_join_id0 = mptcp_allow_join_id0(sock_net(sk));
*size = TCPOLEN_MPTCP_MPC_SYN;
return true;
} else if (subflow->request_join) {
pr_debug("remote_token=%u, nonce=%u", subflow->remote_token,
subflow->local_nonce);
opts->suboptions = OPTION_MPTCP_MPJ_SYN;
opts->join_id = subflow->local_id;
opts->token = subflow->remote_token;
opts->nonce = subflow->local_nonce;
opts->backup = subflow->request_bkup;
*size = TCPOLEN_MPTCP_MPJ_SYN;
return true;
}
return false;
}
static void clear_3rdack_retransmission(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
sk_stop_timer(sk, &icsk->icsk_delack_timer);
icsk->icsk_ack.timeout = 0;
icsk->icsk_ack.ato = 0;
icsk->icsk_ack.pending &= ~(ICSK_ACK_SCHED | ICSK_ACK_TIMER);
}
static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb,
bool snd_data_fin_enable,
unsigned int *size,
struct mptcp_out_options *opts)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
struct mptcp_ext *mpext;
unsigned int data_len;
u8 len;
/* When skb is not available, we better over-estimate the emitted
* options len. A full DSS option (28 bytes) is longer than
* TCPOLEN_MPTCP_MPC_ACK_DATA(22) or TCPOLEN_MPTCP_MPJ_ACK(24), so
* tell the caller to defer the estimate to
* mptcp_established_options_dss(), which will reserve enough space.
*/
if (!skb)
return false;
/* MPC/MPJ needed only on 3rd ack packet, DATA_FIN and TCP shutdown take precedence */
if (subflow->fully_established || snd_data_fin_enable ||
subflow->snd_isn != TCP_SKB_CB(skb)->seq ||
sk->sk_state != TCP_ESTABLISHED)
return false;
if (subflow->mp_capable) {
mpext = mptcp_get_ext(skb);
data_len = mpext ? mpext->data_len : 0;
/* we will check ops->data_len in mptcp_write_options() to
* discriminate between TCPOLEN_MPTCP_MPC_ACK_DATA and
* TCPOLEN_MPTCP_MPC_ACK
*/
opts->data_len = data_len;
opts->suboptions = OPTION_MPTCP_MPC_ACK;
opts->sndr_key = subflow->local_key;
opts->rcvr_key = subflow->remote_key;
opts->csum_reqd = READ_ONCE(msk->csum_enabled);
opts->allow_join_id0 = mptcp_allow_join_id0(sock_net(sk));
/* Section 3.1.
* The MP_CAPABLE option is carried on the SYN, SYN/ACK, and ACK
* packets that start the first subflow of an MPTCP connection,
* as well as the first packet that carries data
*/
if (data_len > 0) {
len = TCPOLEN_MPTCP_MPC_ACK_DATA;
if (opts->csum_reqd) {
/* we need to propagate more info to csum the pseudo hdr */
opts->data_seq = mpext->data_seq;
opts->subflow_seq = mpext->subflow_seq;
opts->csum = mpext->csum;
len += TCPOLEN_MPTCP_DSS_CHECKSUM;
}
*size = ALIGN(len, 4);
} else {
*size = TCPOLEN_MPTCP_MPC_ACK;
}
pr_debug("subflow=%p, local_key=%llu, remote_key=%llu map_len=%d",
subflow, subflow->local_key, subflow->remote_key,
data_len);
return true;
} else if (subflow->mp_join) {
opts->suboptions = OPTION_MPTCP_MPJ_ACK;
memcpy(opts->hmac, subflow->hmac, MPTCPOPT_HMAC_LEN);
*size = TCPOLEN_MPTCP_MPJ_ACK;
pr_debug("subflow=%p", subflow);
/* we can use the full delegate action helper only from BH context
* If we are in process context - sk is flushing the backlog at
* socket lock release time - just set the appropriate flag, will
* be handled by the release callback
*/
if (sock_owned_by_user(sk))
set_bit(MPTCP_DELEGATE_ACK, &subflow->delegated_status);
else
mptcp_subflow_delegate(subflow, MPTCP_DELEGATE_ACK);
return true;
}
return false;
}
static void mptcp_write_data_fin(struct mptcp_subflow_context *subflow,
struct sk_buff *skb, struct mptcp_ext *ext)
{
/* The write_seq value has already been incremented, so the actual
* sequence number for the DATA_FIN is one less.
*/
u64 data_fin_tx_seq = READ_ONCE(mptcp_sk(subflow->conn)->write_seq) - 1;
if (!ext->use_map || !skb->len) {
/* RFC6824 requires a DSS mapping with specific values
* if DATA_FIN is set but no data payload is mapped
*/
ext->data_fin = 1;
ext->use_map = 1;
ext->dsn64 = 1;
ext->data_seq = data_fin_tx_seq;
ext->subflow_seq = 0;
ext->data_len = 1;
} else if (ext->data_seq + ext->data_len == data_fin_tx_seq) {
/* If there's an existing DSS mapping and it is the
* final mapping, DATA_FIN consumes 1 additional byte of
* mapping space.
*/
ext->data_fin = 1;
ext->data_len++;
}
}
static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
bool snd_data_fin_enable,
unsigned int *size,
struct mptcp_out_options *opts)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
unsigned int dss_size = 0;
struct mptcp_ext *mpext;
unsigned int ack_size;
bool ret = false;
u64 ack_seq;
opts->csum_reqd = READ_ONCE(msk->csum_enabled);
mpext = skb ? mptcp_get_ext(skb) : NULL;
if (!skb || (mpext && mpext->use_map) || snd_data_fin_enable) {
unsigned int map_size = TCPOLEN_MPTCP_DSS_BASE + TCPOLEN_MPTCP_DSS_MAP64;
if (mpext) {
if (opts->csum_reqd)
map_size += TCPOLEN_MPTCP_DSS_CHECKSUM;
opts->ext_copy = *mpext;
}
dss_size = map_size;
if (skb && snd_data_fin_enable)
mptcp_write_data_fin(subflow, skb, &opts->ext_copy);
opts->suboptions = OPTION_MPTCP_DSS;
ret = true;
}
/* passive sockets msk will set the 'can_ack' after accept(), even
* if the first subflow may have the already the remote key handy
*/
opts->ext_copy.use_ack = 0;
if (!READ_ONCE(msk->can_ack)) {
*size = ALIGN(dss_size, 4);
return ret;
}
ack_seq = READ_ONCE(msk->ack_seq);
if (READ_ONCE(msk->use_64bit_ack)) {
ack_size = TCPOLEN_MPTCP_DSS_ACK64;
opts->ext_copy.data_ack = ack_seq;
opts->ext_copy.ack64 = 1;
} else {
ack_size = TCPOLEN_MPTCP_DSS_ACK32;
opts->ext_copy.data_ack32 = (uint32_t)ack_seq;
opts->ext_copy.ack64 = 0;
}
opts->ext_copy.use_ack = 1;
opts->suboptions = OPTION_MPTCP_DSS;
WRITE_ONCE(msk->old_wspace, __mptcp_space((struct sock *)msk));
/* Add kind/length/subtype/flag overhead if mapping is not populated */
if (dss_size == 0)
ack_size += TCPOLEN_MPTCP_DSS_BASE;
dss_size += ack_size;
*size = ALIGN(dss_size, 4);
return true;
}
static u64 add_addr_generate_hmac(u64 key1, u64 key2,
struct mptcp_addr_info *addr)
{
u16 port = ntohs(addr->port);
u8 hmac[SHA256_DIGEST_SIZE];
u8 msg[19];
int i = 0;
msg[i++] = addr->id;
if (addr->family == AF_INET) {
memcpy(&msg[i], &addr->addr.s_addr, 4);
i += 4;
}
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
else if (addr->family == AF_INET6) {
memcpy(&msg[i], &addr->addr6.s6_addr, 16);
i += 16;
}
#endif
msg[i++] = port >> 8;
msg[i++] = port & 0xFF;
mptcp_crypto_hmac_sha(key1, key2, msg, i, hmac);
return get_unaligned_be64(&hmac[SHA256_DIGEST_SIZE - sizeof(u64)]);
}
static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *skb,
unsigned int *size,
unsigned int remaining,
struct mptcp_out_options *opts)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
bool drop_other_suboptions = false;
unsigned int opt_size = *size;
bool echo;
int len;
/* add addr will strip the existing options, be sure to avoid breaking
* MPC/MPJ handshakes
*/
if (!mptcp_pm_should_add_signal(msk) ||
(opts->suboptions & (OPTION_MPTCP_MPJ_ACK | OPTION_MPTCP_MPC_ACK)) ||
!mptcp_pm_add_addr_signal(msk, skb, opt_size, remaining, &opts->addr,
&echo, &drop_other_suboptions))
return false;
if (drop_other_suboptions)
remaining += opt_size;
len = mptcp_add_addr_len(opts->addr.family, echo, !!opts->addr.port);
if (remaining < len)
return false;
*size = len;
if (drop_other_suboptions) {
pr_debug("drop other suboptions");
opts->suboptions = 0;
/* note that e.g. DSS could have written into the memory
* aliased by ahmac, we must reset the field here
* to avoid appending the hmac even for ADD_ADDR echo
* options
*/
opts->ahmac = 0;
*size -= opt_size;
}
opts->suboptions |= OPTION_MPTCP_ADD_ADDR;
if (!echo) {
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ADDADDRTX);
opts->ahmac = add_addr_generate_hmac(msk->local_key,
msk->remote_key,
&opts->addr);
} else {
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADDTX);
}
pr_debug("addr_id=%d, ahmac=%llu, echo=%d, port=%d",
opts->addr.id, opts->ahmac, echo, ntohs(opts->addr.port));
return true;
}
static bool mptcp_established_options_rm_addr(struct sock *sk,
unsigned int *size,
unsigned int remaining,
struct mptcp_out_options *opts)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
struct mptcp_rm_list rm_list;
int i, len;
if (!mptcp_pm_should_rm_signal(msk) ||
!(mptcp_pm_rm_addr_signal(msk, remaining, &rm_list)))
return false;
len = mptcp_rm_addr_len(&rm_list);
if (len < 0)
return false;
if (remaining < len)
return false;
*size = len;
opts->suboptions |= OPTION_MPTCP_RM_ADDR;
opts->rm_list = rm_list;
for (i = 0; i < opts->rm_list.nr; i++)
pr_debug("rm_list_ids[%d]=%d", i, opts->rm_list.ids[i]);
MPTCP_ADD_STATS(sock_net(sk), MPTCP_MIB_RMADDRTX, opts->rm_list.nr);
return true;
}
static bool mptcp_established_options_mp_prio(struct sock *sk,
unsigned int *size,
unsigned int remaining,
struct mptcp_out_options *opts)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
/* can't send MP_PRIO with MPC, as they share the same option space:
* 'backup'. Also it makes no sense at all
*/
if (!subflow->send_mp_prio || (opts->suboptions & OPTIONS_MPTCP_MPC))
return false;
/* account for the trailing 'nop' option */
if (remaining < TCPOLEN_MPTCP_PRIO_ALIGN)
return false;
*size = TCPOLEN_MPTCP_PRIO_ALIGN;
opts->suboptions |= OPTION_MPTCP_PRIO;
opts->backup = subflow->request_bkup;
pr_debug("prio=%d", opts->backup);
return true;
}
static noinline bool mptcp_established_options_rst(struct sock *sk, struct sk_buff *skb,
unsigned int *size,
unsigned int remaining,
struct mptcp_out_options *opts)
{
const struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
if (remaining < TCPOLEN_MPTCP_RST)
return false;
*size = TCPOLEN_MPTCP_RST;
opts->suboptions |= OPTION_MPTCP_RST;
opts->reset_transient = subflow->reset_transient;
opts->reset_reason = subflow->reset_reason;
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPRSTTX);
return true;
}
static bool mptcp_established_options_fastclose(struct sock *sk,
unsigned int *size,
unsigned int remaining,
struct mptcp_out_options *opts)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
if (likely(!subflow->send_fastclose))
return false;
if (remaining < TCPOLEN_MPTCP_FASTCLOSE)
return false;
*size = TCPOLEN_MPTCP_FASTCLOSE;
opts->suboptions |= OPTION_MPTCP_FASTCLOSE;
opts->rcvr_key = msk->remote_key;
pr_debug("FASTCLOSE key=%llu", opts->rcvr_key);
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFASTCLOSETX);
return true;
}
static bool mptcp_established_options_mp_fail(struct sock *sk,
unsigned int *size,
unsigned int remaining,
struct mptcp_out_options *opts)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
if (likely(!subflow->send_mp_fail))
return false;
if (remaining < TCPOLEN_MPTCP_FAIL)
return false;
*size = TCPOLEN_MPTCP_FAIL;
opts->suboptions |= OPTION_MPTCP_FAIL;
opts->fail_seq = subflow->map_seq;
pr_debug("MP_FAIL fail_seq=%llu", opts->fail_seq);
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFAILTX);
return true;
}
bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
unsigned int *size, unsigned int remaining,
struct mptcp_out_options *opts)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
unsigned int opt_size = 0;
bool snd_data_fin;
bool ret = false;
opts->suboptions = 0;
if (unlikely(__mptcp_check_fallback(msk) && !mptcp_check_infinite_map(skb)))
return false;
if (unlikely(skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_RST)) {
if (mptcp_established_options_fastclose(sk, &opt_size, remaining, opts) ||
mptcp_established_options_mp_fail(sk, &opt_size, remaining, opts)) {
*size += opt_size;
remaining -= opt_size;
}
/* MP_RST can be used with MP_FASTCLOSE and MP_FAIL if there is room */
if (mptcp_established_options_rst(sk, skb, &opt_size, remaining, opts)) {
*size += opt_size;
remaining -= opt_size;
}
return true;
}
snd_data_fin = mptcp_data_fin_enabled(msk);
if (mptcp_established_options_mp(sk, skb, snd_data_fin, &opt_size, opts))
ret = true;
else if (mptcp_established_options_dss(sk, skb, snd_data_fin, &opt_size, opts)) {
unsigned int mp_fail_size;
ret = true;
if (mptcp_established_options_mp_fail(sk, &mp_fail_size,
remaining - opt_size, opts)) {
*size += opt_size + mp_fail_size;
remaining -= opt_size - mp_fail_size;
return true;
}
}
/* we reserved enough space for the above options, and exceeding the
* TCP option space would be fatal
*/
if (WARN_ON_ONCE(opt_size > remaining))
return false;
*size += opt_size;
remaining -= opt_size;
if (mptcp_established_options_add_addr(sk, skb, &opt_size, remaining, opts)) {
*size += opt_size;
remaining -= opt_size;
ret = true;
} else if (mptcp_established_options_rm_addr(sk, &opt_size, remaining, opts)) {
*size += opt_size;
remaining -= opt_size;
ret = true;
}
if (mptcp_established_options_mp_prio(sk, &opt_size, remaining, opts)) {
*size += opt_size;
remaining -= opt_size;
ret = true;
}
return ret;
}
bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
struct mptcp_out_options *opts)
{
struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
if (subflow_req->mp_capable) {
opts->suboptions = OPTION_MPTCP_MPC_SYNACK;
opts->sndr_key = subflow_req->local_key;
opts->csum_reqd = subflow_req->csum_reqd;
opts->allow_join_id0 = subflow_req->allow_join_id0;
*size = TCPOLEN_MPTCP_MPC_SYNACK;
pr_debug("subflow_req=%p, local_key=%llu",
subflow_req, subflow_req->local_key);
return true;
} else if (subflow_req->mp_join) {
opts->suboptions = OPTION_MPTCP_MPJ_SYNACK;
opts->backup = subflow_req->backup;
opts->join_id = subflow_req->local_id;
opts->thmac = subflow_req->thmac;
opts->nonce = subflow_req->local_nonce;
pr_debug("req=%p, bkup=%u, id=%u, thmac=%llu, nonce=%u",
subflow_req, opts->backup, opts->join_id,
opts->thmac, opts->nonce);
*size = TCPOLEN_MPTCP_MPJ_SYNACK;
return true;
}
return false;
}
static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
struct mptcp_subflow_context *subflow,
struct sk_buff *skb,
struct mptcp_options_received *mp_opt)
{
/* here we can process OoO, in-window pkts, only in-sequence 4th ack
* will make the subflow fully established
*/
if (likely(subflow->fully_established)) {
/* on passive sockets, check for 3rd ack retransmission
* note that msk is always set by subflow_syn_recv_sock()
* for mp_join subflows
*/
if (TCP_SKB_CB(skb)->seq == subflow->ssn_offset + 1 &&
TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq &&
subflow->mp_join && (mp_opt->suboptions & OPTIONS_MPTCP_MPJ) &&
!subflow->request_join)
tcp_send_ack(ssk);
goto check_notify;
}
/* we must process OoO packets before the first subflow is fully
* established. OoO packets are instead a protocol violation
* for MP_JOIN subflows as the peer must not send any data
* before receiving the forth ack - cfr. RFC 8684 section 3.2.
*/
if (TCP_SKB_CB(skb)->seq != subflow->ssn_offset + 1) {
if (subflow->mp_join)
goto reset;
if (subflow->is_mptfo && mp_opt->suboptions & OPTION_MPTCP_MPC_ACK)
goto set_fully_established;
return subflow->mp_capable;
}
if (subflow->remote_key_valid &&
(((mp_opt->suboptions & OPTION_MPTCP_DSS) && mp_opt->use_ack) ||
((mp_opt->suboptions & OPTION_MPTCP_ADD_ADDR) && !mp_opt->echo))) {
/* subflows are fully established as soon as we get any
* additional ack, including ADD_ADDR.
*/
subflow->fully_established = 1;
WRITE_ONCE(msk->fully_established, true);
goto check_notify;
}
/* If the first established packet does not contain MP_CAPABLE + data
* then fallback to TCP. Fallback scenarios requires a reset for
* MP_JOIN subflows.
*/
if (!(mp_opt->suboptions & OPTIONS_MPTCP_MPC)) {
if (subflow->mp_join)
goto reset;
subflow->mp_capable = 0;
pr_fallback(msk);
mptcp_do_fallback(ssk);
return false;
}
if (mp_opt->deny_join_id0)
WRITE_ONCE(msk->pm.remote_deny_join_id0, true);
set_fully_established:
if (unlikely(!READ_ONCE(msk->pm.server_side)))
pr_warn_once("bogus mpc option on established client sk");
mptcp_subflow_fully_established(subflow, mp_opt);
check_notify:
/* if the subflow is not already linked into the conn_list, we can't
* notify the PM: this subflow is still on the listener queue
* and the PM possibly acquiring the subflow lock could race with
* the listener close
*/
if (likely(subflow->pm_notified) || list_empty(&subflow->node))
return true;
subflow->pm_notified = 1;
if (subflow->mp_join) {