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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
|
// 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"
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;
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;
} else {
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK)
expected_opsize = TCPOLEN_MPTCP_MPC_SYNACK;
else
expected_opsize = TCPOLEN_MPTCP_MPC_SYN;
}
if (opsize != expected_opsize)
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."
*
* Section 3.3.0:
* "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 don't implement DSS checksum - fall back to TCP.
*/
if (flags & MPTCP_CAP_CHECKSUM_REQD)
break;
mp_opt->mp_capable = 1;
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->dss = 1;
mp_opt->use_map = 1;
mp_opt->mpc_map = 1;
mp_opt->data_len = get_unaligned_be16(ptr);
ptr += 2;
}
pr_debug("MP_CAPABLE version=%x, flags=%x, optlen=%d sndr=%llu, rcvr=%llu len=%d",
version, flags, opsize, mp_opt->sndr_key,
mp_opt->rcvr_key, mp_opt->data_len);
break;
case MPTCPOPT_MP_JOIN:
mp_opt->mp_join = 1;
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 {
pr_warn("MP_JOIN bad option size");
mp_opt->mp_join = 0;
}
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;
}
/* RFC 6824, Section 3.3:
* If a checksum is present, but its use had
* not been negotiated in the MP_CAPABLE handshake,
* the checksum field MUST be ignored.
*/
if (opsize != expected_opsize &&
opsize != expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM)
break;
mp_opt->dss = 1;
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;
pr_debug("data_seq=%llu subflow_seq=%u data_len=%u",
mp_opt->data_seq, mp_opt->subflow_seq,
mp_opt->data_len);
}
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->add_addr = 1;
mp_opt->addr.id = *ptr++;
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->rm_addr = 1;
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->mp_prio = 1;
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->fastclose = 1;
break;
case MPTCPOPT_RST:
if (opsize != TCPOLEN_MPTCP_RST)
break;
if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_RST))
break;
mp_opt->reset = 1;
flags = *ptr++;
mp_opt->reset_transient = flags & MPTCP_RST_TRANSIENT;
mp_opt->reset_reason = *ptr;
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->mp_capable = 0;
mp_opt->mp_join = 0;
mp_opt->add_addr = 0;
mp_opt->ahmac = 0;
mp_opt->fastclose = 0;
mp_opt->addr.port = 0;
mp_opt->rm_addr = 0;
mp_opt->dss = 0;
mp_opt->mp_prio = 0;
mp_opt->reset = 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:
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;
*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;
}
/* MP_JOIN client subflow must wait for 4th ack before sending any data:
* TCP can't schedule delack timer before the subflow is fully established.
* MPTCP uses the delack timer to do 3rd ack retransmissions
*/
static void schedule_3rdack_retransmission(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
unsigned long timeout;
/* reschedule with a timeout above RTT, as we must look only for drop */
if (tp->srtt_us)
timeout = tp->srtt_us << 1;
else
timeout = TCP_TIMEOUT_INIT;
WARN_ON_ONCE(icsk->icsk_ack.pending & ICSK_ACK_TIMER);
icsk->icsk_ack.pending |= ICSK_ACK_SCHED | ICSK_ACK_TIMER;
icsk->icsk_ack.timeout = timeout;
sk_reset_timer(sk, &icsk->icsk_delack_timer, timeout);
}
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,
unsigned int remaining,
struct mptcp_out_options *opts)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct mptcp_ext *mpext;
unsigned int data_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 ext_copy.data_len in mptcp_write_options() to
* discriminate between TCPOLEN_MPTCP_MPC_ACK_DATA and
* TCPOLEN_MPTCP_MPC_ACK
*/
opts->ext_copy.data_len = data_len;
opts->suboptions = OPTION_MPTCP_MPC_ACK;
opts->sndr_key = subflow->local_key;
opts->rcvr_key = subflow->remote_key;
/* 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)
*size = ALIGN(TCPOLEN_MPTCP_MPC_ACK_DATA, 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);
schedule_3rdack_retransmission(sk);
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,
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 dss_size = 0;
struct mptcp_ext *mpext;
unsigned int ack_size;
bool ret = false;
u64 ack_seq;
mpext = skb ? mptcp_get_ext(skb) : NULL;
if (!skb || (mpext && mpext->use_map) || snd_data_fin_enable) {
unsigned int map_size;
map_size = TCPOLEN_MPTCP_DSS_BASE + TCPOLEN_MPTCP_DSS_MAP64;
remaining -= map_size;
dss_size = map_size;
if (mpext)
opts->ext_copy = *mpext;
if (skb && snd_data_fin_enable)
mptcp_write_data_fin(subflow, skb, &opts->ext_copy);
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;
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, u8 addr_id,
struct in_addr *addr, u16 port)
{
u8 hmac[SHA256_DIGEST_SIZE];
u8 msg[7];
msg[0] = addr_id;
memcpy(&msg[1], &addr->s_addr, 4);
msg[5] = port >> 8;
msg[6] = port & 0xFF;
mptcp_crypto_hmac_sha(key1, key2, msg, 7, hmac);
return get_unaligned_be64(&hmac[SHA256_DIGEST_SIZE - sizeof(u64)]);
}
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
static u64 add_addr6_generate_hmac(u64 key1, u64 key2, u8 addr_id,
struct in6_addr *addr, u16 port)
{
u8 hmac[SHA256_DIGEST_SIZE];
u8 msg[19];
msg[0] = addr_id;
memcpy(&msg[1], &addr->s6_addr, 16);
msg[17] = port >> 8;
msg[18] = port & 0xFF;
mptcp_crypto_hmac_sha(key1, key2, msg, 19, hmac);
return get_unaligned_be64(&hmac[SHA256_DIGEST_SIZE - sizeof(u64)]);
}
#endif
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;
bool port;
int len;
if ((mptcp_pm_should_add_signal_ipv6(msk) ||
mptcp_pm_should_add_signal_port(msk)) &&
skb && skb_is_tcp_pure_ack(skb)) {
pr_debug("drop other suboptions");
opts->suboptions = 0;
opts->ext_copy.use_ack = 0;
opts->ext_copy.use_map = 0;
remaining += opt_size;
drop_other_suboptions = true;
}
if (!mptcp_pm_should_add_signal(msk) ||
!(mptcp_pm_add_addr_signal(msk, remaining, &opts->addr, &echo, &port)))
return false;
len = mptcp_add_addr_len(opts->addr.family, echo, port);
if (remaining < len)
return false;
*size = len;
if (drop_other_suboptions)
*size -= opt_size;
opts->suboptions |= OPTION_MPTCP_ADD_ADDR;
if (opts->addr.family == AF_INET) {
if (!echo) {
opts->ahmac = add_addr_generate_hmac(msk->local_key,
msk->remote_key,
opts->addr.id,
&opts->addr.addr,
ntohs(opts->addr.port));
}
}
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
else if (opts->addr.family == AF_INET6) {
if (!echo) {
opts->ahmac = add_addr6_generate_hmac(msk->local_key,
msk->remote_key,
opts->addr.id,
&opts->addr.addr6,
ntohs(opts->addr.port));
}
}
#endif
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]);
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);
if (!subflow->send_mp_prio)
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 void 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;
*size = TCPOLEN_MPTCP_RST;
opts->suboptions |= OPTION_MPTCP_RST;
opts->reset_transient = subflow->reset_transient;
opts->reset_reason = subflow->reset_reason;
}
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)))
return false;
if (unlikely(skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_RST)) {
mptcp_established_options_rst(sk, skb, size, remaining, opts);
return true;
}
snd_data_fin = mptcp_data_fin_enabled(msk);
if (mptcp_established_options_mp(sk, skb, snd_data_fin, &opt_size, remaining, opts))
ret = true;
else if (mptcp_established_options_dss(sk, skb, snd_data_fin, &opt_size, remaining, opts))
ret = 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;
*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->mp_join &&
READ_ONCE(msk->pm.server_side))
tcp_send_ack(ssk);
goto fully_established;
}
/* 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;
return subflow->mp_capable;
}
if (mp_opt->dss && mp_opt->use_ack) {
/* subflows are fully established as soon as we get any
* additional ack.
*/
subflow->fully_established = 1;
WRITE_ONCE(msk->fully_established, true);
goto fully_established;
}
if (mp_opt->add_addr) {
WRITE_ONCE(msk->fully_established, true);
return true;
}
/* 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->mp_capable) {
if (subflow->mp_join)
goto reset;
subflow->mp_capable = 0;
pr_fallback(msk);
__mptcp_do_fallback(msk);
return false;
}
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);
fully_established:
/* 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) {
clear_3rdack_retransmission(ssk);
mptcp_pm_subflow_established(msk);
} else {
mptcp_pm_fully_established(msk, ssk, GFP_ATOMIC);
}
return true;
reset:
mptcp_subflow_reset(ssk);
return false;
}
static u64 expand_ack(u64 old_ack, u64 cur_ack, bool use_64bit)
{
u32 old_ack32, cur_ack32;
if (use_64bit)
return cur_ack;
old_ack32 = (u32)old_ack;
cur_ack32 = (u32)cur_ack;
cur_ack = (old_ack & GENMASK_ULL(63, 32)) + cur_ack32;
if (unlikely(before(cur_ack32, old_ack32)))
return cur_ack + (1LL << 32);
return cur_ack;
}
static void ack_update_msk(struct mptcp_sock *msk,
struct sock *ssk,
struct mptcp_options_received *mp_opt)
{
u64 new_wnd_end, new_snd_una, snd_nxt = READ_ONCE(msk->snd_nxt);
struct sock *sk = (struct sock *)msk;
u64 old_snd_una;
mptcp_data_lock(sk);
/* avoid ack expansion on update conflict, to reduce the risk of
* wrongly expanding to a future ack sequence number, which is way
* more dangerous than missing an ack
*/
old_snd_una = msk->snd_una;
new_snd_una = expand_ack(old_snd_una, mp_opt->data_ack, mp_opt->ack64);
/* ACK for data not even sent yet? Ignore. */
if (after64(new_snd_una, snd_nxt))
new_snd_una = old_snd_una;
new_wnd_end = new_snd_una + tcp_sk(ssk)->snd_wnd;
if (after64(new_wnd_end, msk->wnd_end))
msk->wnd_end = new_wnd_end;
/* this assumes mptcp_incoming_options() is invoked after tcp_ack() */
if (after64(msk->wnd_end, READ_ONCE(msk->snd_nxt)))
__mptcp_check_push(sk, ssk);
if (after64(new_snd_una, old_snd_una)) {
msk->snd_una = new_snd_una;
__mptcp_data_acked(sk);
}
mptcp_data_unlock(sk);
}
bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool use_64bit)
{
/* Skip if DATA_FIN was already received.
* If updating simultaneously with the recvmsg loop, values
* should match. If they mismatch, the peer is misbehaving and
* we will prefer the most recent information.
*/
if (READ_ONCE(msk->rcv_data_fin))
return false;
WRITE_ONCE(msk->rcv_data_fin_seq,
expand_ack(READ_ONCE(msk->ack_seq), data_fin_seq, use_64bit));
WRITE_ONCE(msk->rcv_data_fin, 1);
return true;
}
static bool add_addr_hmac_valid(struct mptcp_sock *msk,
struct mptcp_options_received *mp_opt)
{
u64 hmac = 0;
if (mp_opt->echo)
return true;
if (mp_opt->addr.family == AF_INET)
hmac = add_addr_generate_hmac(msk->remote_key,
msk->local_key,
mp_opt->addr.id, &mp_opt->addr.addr,
ntohs(mp_opt->addr.port));
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
else
hmac = add_addr6_generate_hmac(msk->remote_key,
msk->local_key,
mp_opt->addr.id, &mp_opt->addr.addr6,
ntohs(mp_opt->addr.port));
#endif
pr_debug("msk=%p, ahmac=%llu, mp_opt->ahmac=%llu\n",
msk, (unsigned long long)hmac,
(unsigned long long)mp_opt->ahmac);
return hmac == mp_opt->ahmac;
}
void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
struct mptcp_options_received mp_opt;
struct mptcp_ext *mpext;
if (__mptcp_check_fallback(msk)) {
/* Keep it simple and unconditionally trigger send data cleanup and
* pending queue spooling. We will need to acquire the data lock
* for more accurate checks, and once the lock is acquired, such
* helpers are cheap.
*/
mptcp_data_lock(subflow->conn);
if (sk_stream_memory_free(sk))
__mptcp_check_push(subflow->conn, sk);
__mptcp_data_acked(subflow->conn);
mptcp_data_unlock(subflow->conn);
return;
}
mptcp_get_options(skb, &mp_opt);
if (!check_fully_established(msk, sk, subflow, skb, &mp_opt))
return;
if (mp_opt.fastclose &&
msk->local_key == mp_opt.rcvr_key) {
WRITE_ONCE(msk->rcv_fastclose, true);
mptcp_schedule_work((struct sock *)msk);
}
if (mp_opt.add_addr && add_addr_hmac_valid(msk, &mp_opt)) {
if (!mp_opt.echo) {
mptcp_pm_add_addr_received(msk, &mp_opt.addr);
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ADDADDR);
} else {
mptcp_pm_add_addr_echoed(msk, &mp_opt.addr);
mptcp_pm_del_add_timer(msk, &mp_opt.addr);
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADD);
}
if (mp_opt.addr.port)
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_PORTADD);
mp_opt.add_addr = 0;
}
if (mp_opt.rm_addr) {
mptcp_pm_rm_addr_received(msk, &mp_opt.rm_list);
mp_opt.rm_addr = 0;
}
if (mp_opt.mp_prio) {
mptcp_pm_mp_prio_received(sk, mp_opt.backup);
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPPRIORX);
mp_opt.mp_prio = 0;
}
if (mp_opt.reset) {
subflow->reset_seen = 1;
subflow->reset_reason = mp_opt.reset_reason;
subflow->reset_transient = mp_opt.reset_transient;
}
if (!mp_opt.dss)
return;
/* we can't wait for recvmsg() to update the ack_seq, otherwise
* monodirectional flows will stuck
*/
if (mp_opt.use_ack)
ack_update_msk(msk, sk, &mp_opt);
/* Zero-data-length packets are dropped by the caller and not
* propagated to the MPTCP layer, so the skb extension does not
* need to be allocated or populated. DATA_FIN information, if
* present, needs to be updated here before the skb is freed.
*/
if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) {
if (mp_opt.data_fin && mp_opt.data_len == 1 &&
mptcp_update_rcv_data_fin(msk, mp_opt.data_seq, mp_opt.dsn64) &&
schedule_work(&msk->work))
sock_hold(subflow->conn);
return;
}
mpext = skb_ext_add(skb, SKB_EXT_MPTCP);
if (!mpext)
return;
memset(mpext, 0, sizeof(*mpext));
if (mp_opt.use_map) {
if (mp_opt.mpc_map) {
/* this is an MP_CAPABLE carrying MPTCP data
* we know this map the first chunk of data
*/
mptcp_crypto_key_sha(subflow->remote_key, NULL,
&mpext->data_seq);
mpext->data_seq++;
mpext->subflow_seq = 1;
mpext->dsn64 = 1;
mpext->mpc_map = 1;
mpext->data_fin = 0;
} else {
mpext->data_seq = mp_opt.data_seq;
mpext->subflow_seq = mp_opt.subflow_seq;
mpext->dsn64 = mp_opt.dsn64;
mpext->data_fin = mp_opt.data_fin;
}
mpext->data_len = mp_opt.data_len;
mpext->use_map = 1;
}
}
static void mptcp_set_rwin(const struct tcp_sock *tp)
{
const struct sock *ssk = (const struct sock *)tp;
const struct mptcp_subflow_context *subflow;
struct mptcp_sock *msk;
u64 ack_seq;
subflow = mptcp_subflow_ctx(ssk);
msk = mptcp_sk(subflow->conn);
ack_seq = READ_ONCE(msk->ack_seq) + tp->rcv_wnd;
if (after64(ack_seq, READ_ONCE(msk->rcv_wnd_sent)))
WRITE_ONCE(msk->rcv_wnd_sent, ack_seq);
}
void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
struct mptcp_out_options *opts)
{
if ((OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_SYNACK |
OPTION_MPTCP_MPC_ACK) & opts->suboptions) {
u8 len;
if (OPTION_MPTCP_MPC_SYN & opts->suboptions)
len = TCPOLEN_MPTCP_MPC_SYN;
else if (OPTION_MPTCP_MPC_SYNACK & opts->suboptions)
len = TCPOLEN_MPTCP_MPC_SYNACK;
else if (opts->ext_copy.data_len)
len = TCPOLEN_MPTCP_MPC_ACK_DATA;
else
len = TCPOLEN_MPTCP_MPC_ACK;
*ptr++ = mptcp_option(MPTCPOPT_MP_CAPABLE, len,
MPTCP_SUPPORTED_VERSION,
MPTCP_CAP_HMAC_SHA256);
if (!((OPTION_MPTCP_MPC_SYNACK | OPTION_MPTCP_MPC_ACK) &
opts->suboptions))
goto mp_capable_done;
put_unaligned_be64(opts->sndr_key, ptr);
ptr += 2;
if (!((OPTION_MPTCP_MPC_ACK) & opts->suboptions))
goto mp_capable_done;
put_unaligned_be64(opts->rcvr_key, ptr);
ptr += 2;
if (!opts->ext_copy.data_len)
goto mp_capable_done;
put_unaligned_be32(opts->ext_copy.data_len << 16 |
TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
ptr += 1;
}
mp_capable_done:
if (OPTION_MPTCP_ADD_ADDR & opts->suboptions) {
u8 len = TCPOLEN_MPTCP_ADD_ADDR_BASE;
u8 echo = MPTCP_ADDR_ECHO;
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
if (opts->addr.family == AF_INET6)
len = TCPOLEN_MPTCP_ADD_ADDR6_BASE;
#endif
if (opts->addr.port)
len += TCPOLEN_MPTCP_PORT_LEN;
if (opts->ahmac) {
len += sizeof(opts->ahmac);
echo = 0;
}
*ptr++ = mptcp_option(MPTCPOPT_ADD_ADDR,
len, echo, opts->addr.id);
if (opts->addr.family == AF_INET) {
memcpy((u8 *)ptr, (u8 *)&opts->addr.addr.s_addr, 4);
ptr += 1;
}
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
else if (opts->addr.family == AF_INET6) {
memcpy((u8 *)ptr, opts->addr.addr6.s6_addr, 16);
ptr += 4;
}
#endif
if (!opts->addr.port) {
if (opts->ahmac) {
put_unaligned_be64(opts->ahmac, ptr);
ptr += 2;
}
} else {
u16 port = ntohs(opts->addr.port);
if (opts->ahmac) {
u8 *bptr = (u8 *)ptr;
put_unaligned_be16(port, bptr);
bptr += 2;
put_unaligned_be64(opts->ahmac, bptr);
bptr += 8;
put_unaligned_be16(TCPOPT_NOP << 8 |
TCPOPT_NOP, bptr);
ptr += 3;
} else {
put_unaligned_be32(port << 16 |
TCPOPT_NOP << 8 |
TCPOPT_NOP, ptr);
ptr += 1;
}
}
}
if (OPTION_MPTCP_RM_ADDR & opts->suboptions) {
u8 i = 1;
*ptr++ = mptcp_option(MPTCPOPT_RM_ADDR,
TCPOLEN_MPTCP_RM_ADDR_BASE + opts->rm_list.nr,
0, opts->rm_list.ids[0]);
while (i < opts->rm_list.nr) {
u8 id1, id2, id3, id4;
id1 = opts->rm_list.ids[i];
id2 = i + 1 < opts->rm_list.nr ? opts->rm_list.ids[i + 1] : TCPOPT_NOP;
id3 = i + 2 < opts->rm_list.nr ? opts->rm_list.ids[i + 2] : TCPOPT_NOP;
id4 = i + 3 < opts->rm_list.nr ? opts->rm_list.ids[i + 3] : TCPOPT_NOP;
put_unaligned_be32(id1 << 24 | id2 << 16 | id3 << 8 | id4, ptr);
ptr += 1;
i += 4;
}
}
if (OPTION_MPTCP_PRIO & opts->suboptions) {
const struct sock *ssk = (const struct sock *)tp;
struct mptcp_subflow_context *subflow;
subflow = mptcp_subflow_ctx(ssk);
subflow->send_mp_prio = 0;
*ptr++ = mptcp_option(MPTCPOPT_MP_PRIO,
TCPOLEN_MPTCP_PRIO,
opts->backup, TCPOPT_NOP);
}
if (OPTION_MPTCP_MPJ_SYN & opts->suboptions) {
*ptr++ = mptcp_option(MPTCPOPT_MP_JOIN,
TCPOLEN_MPTCP_MPJ_SYN,
opts->backup, opts->join_id);
put_unaligned_be32(opts->token, ptr);
ptr += 1;
put_unaligned_be32(opts->nonce, ptr);
ptr += 1;
}
if (OPTION_MPTCP_MPJ_SYNACK & opts->suboptions) {
*ptr++ = mptcp_option(MPTCPOPT_MP_JOIN,
TCPOLEN_MPTCP_MPJ_SYNACK,
opts->backup, opts->join_id);
put_unaligned_be64(opts->thmac, ptr);
ptr += 2;
put_unaligned_be32(opts->nonce, ptr);
ptr += 1;
}
if (OPTION_MPTCP_MPJ_ACK & opts->suboptions) {
*ptr++ = mptcp_option(MPTCPOPT_MP_JOIN,
TCPOLEN_MPTCP_MPJ_ACK, 0, 0);
memcpy(ptr, opts->hmac, MPTCPOPT_HMAC_LEN);
ptr += 5;
}
if (OPTION_MPTCP_RST & opts->suboptions)
*ptr++ = mptcp_option(MPTCPOPT_RST,
TCPOLEN_MPTCP_RST,
opts->reset_transient,
opts->reset_reason);
if (opts->ext_copy.use_ack || opts->ext_copy.use_map) {
struct mptcp_ext *mpext = &opts->ext_copy;
u8 len = TCPOLEN_MPTCP_DSS_BASE;
u8 flags = 0;
if (mpext->use_ack) {
flags = MPTCP_DSS_HAS_ACK;
if (mpext->ack64) {
len += TCPOLEN_MPTCP_DSS_ACK64;
flags |= MPTCP_DSS_ACK64;
} else {
len += TCPOLEN_MPTCP_DSS_ACK32;
}
}
if (mpext->use_map) {
len += TCPOLEN_MPTCP_DSS_MAP64;
/* Use only 64-bit mapping flags for now, add
* support for optional 32-bit mappings later.
*/
flags |= MPTCP_DSS_HAS_MAP | MPTCP_DSS_DSN64;
if (mpext->data_fin)
flags |= MPTCP_DSS_DATA_FIN;
}
*ptr++ = mptcp_option(MPTCPOPT_DSS, len, 0, flags);
if (mpext->use_ack) {
if (mpext->ack64) {
put_unaligned_be64(mpext->data_ack, ptr);
ptr += 2;
} else {
put_unaligned_be32(mpext->data_ack32, ptr);
ptr += 1;
}
}
if (mpext->use_map) {
put_unaligned_be64(mpext->data_seq, ptr);
ptr += 2;
put_unaligned_be32(mpext->subflow_seq, ptr);
ptr += 1;
put_unaligned_be32(mpext->data_len << 16 |
TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
}
}
if (tp)
mptcp_set_rwin(tp);
}
__be32 mptcp_get_reset_option(const struct sk_buff *skb)
{
const struct mptcp_ext *ext = mptcp_get_ext(skb);
u8 flags, reason;
if (ext) {
flags = ext->reset_transient;
reason = ext->reset_reason;
return mptcp_option(MPTCPOPT_RST, TCPOLEN_MPTCP_RST,
flags, reason);
}
return htonl(0u);
}
EXPORT_SYMBOL_GPL(mptcp_get_reset_option);
|