forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
subflow.c
1802 lines (1492 loc) · 48.7 KB
/
subflow.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 <linux/module.h>
#include <linux/netdevice.h>
#include <crypto/algapi.h>
#include <crypto/sha2.h>
#include <net/sock.h>
#include <net/inet_common.h>
#include <net/inet_hashtables.h>
#include <net/protocol.h>
#include <net/tcp.h>
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
#include <net/ip6_route.h>
#include <net/transp_v6.h>
#endif
#include <net/mptcp.h>
#include <uapi/linux/mptcp.h>
#include "protocol.h"
#include "mib.h"
#include <trace/events/mptcp.h>
static void mptcp_subflow_ops_undo_override(struct sock *ssk);
static void SUBFLOW_REQ_INC_STATS(struct request_sock *req,
enum linux_mptcp_mib_field field)
{
MPTCP_INC_STATS(sock_net(req_to_sk(req)), field);
}
static void subflow_req_destructor(struct request_sock *req)
{
struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
pr_debug("subflow_req=%p", subflow_req);
if (subflow_req->msk)
sock_put((struct sock *)subflow_req->msk);
mptcp_token_destroy_request(req);
tcp_request_sock_ops.destructor(req);
}
static void subflow_generate_hmac(u64 key1, u64 key2, u32 nonce1, u32 nonce2,
void *hmac)
{
u8 msg[8];
put_unaligned_be32(nonce1, &msg[0]);
put_unaligned_be32(nonce2, &msg[4]);
mptcp_crypto_hmac_sha(key1, key2, msg, 8, hmac);
}
static bool mptcp_can_accept_new_subflow(const struct mptcp_sock *msk)
{
return mptcp_is_fully_established((void *)msk) &&
READ_ONCE(msk->pm.accept_subflow);
}
/* validate received token and create truncated hmac and nonce for SYN-ACK */
static void subflow_req_create_thmac(struct mptcp_subflow_request_sock *subflow_req)
{
struct mptcp_sock *msk = subflow_req->msk;
u8 hmac[SHA256_DIGEST_SIZE];
get_random_bytes(&subflow_req->local_nonce, sizeof(u32));
subflow_generate_hmac(msk->local_key, msk->remote_key,
subflow_req->local_nonce,
subflow_req->remote_nonce, hmac);
subflow_req->thmac = get_unaligned_be64(hmac);
}
static struct mptcp_sock *subflow_token_join_request(struct request_sock *req)
{
struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
struct mptcp_sock *msk;
int local_id;
msk = mptcp_token_get_sock(subflow_req->token);
if (!msk) {
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINNOTOKEN);
return NULL;
}
local_id = mptcp_pm_get_local_id(msk, (struct sock_common *)req);
if (local_id < 0) {
sock_put((struct sock *)msk);
return NULL;
}
subflow_req->local_id = local_id;
return msk;
}
static void subflow_init_req(struct request_sock *req, const struct sock *sk_listener)
{
struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
subflow_req->mp_capable = 0;
subflow_req->mp_join = 0;
subflow_req->csum_reqd = mptcp_is_checksum_enabled(sock_net(sk_listener));
subflow_req->allow_join_id0 = mptcp_allow_join_id0(sock_net(sk_listener));
subflow_req->msk = NULL;
mptcp_token_init_request(req);
}
static bool subflow_use_different_sport(struct mptcp_sock *msk, const struct sock *sk)
{
return inet_sk(sk)->inet_sport != inet_sk((struct sock *)msk)->inet_sport;
}
static void subflow_add_reset_reason(struct sk_buff *skb, u8 reason)
{
struct mptcp_ext *mpext = skb_ext_add(skb, SKB_EXT_MPTCP);
if (mpext) {
memset(mpext, 0, sizeof(*mpext));
mpext->reset_reason = reason;
}
}
/* Init mptcp request socket.
*
* Returns an error code if a JOIN has failed and a TCP reset
* should be sent.
*/
static int subflow_check_req(struct request_sock *req,
const struct sock *sk_listener,
struct sk_buff *skb)
{
struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk_listener);
struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
struct mptcp_options_received mp_opt;
pr_debug("subflow_req=%p, listener=%p", subflow_req, listener);
#ifdef CONFIG_TCP_MD5SIG
/* no MPTCP if MD5SIG is enabled on this socket or we may run out of
* TCP option space.
*/
if (rcu_access_pointer(tcp_sk(sk_listener)->md5sig_info))
return -EINVAL;
#endif
mptcp_get_options(sk_listener, skb, &mp_opt);
if (mp_opt.mp_capable) {
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE);
if (mp_opt.mp_join)
return 0;
} else if (mp_opt.mp_join) {
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNRX);
}
if (mp_opt.mp_capable && listener->request_mptcp) {
int err, retries = MPTCP_TOKEN_MAX_RETRIES;
subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq;
again:
do {
get_random_bytes(&subflow_req->local_key, sizeof(subflow_req->local_key));
} while (subflow_req->local_key == 0);
if (unlikely(req->syncookie)) {
mptcp_crypto_key_sha(subflow_req->local_key,
&subflow_req->token,
&subflow_req->idsn);
if (mptcp_token_exists(subflow_req->token)) {
if (retries-- > 0)
goto again;
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_TOKENFALLBACKINIT);
} else {
subflow_req->mp_capable = 1;
}
return 0;
}
err = mptcp_token_new_request(req);
if (err == 0)
subflow_req->mp_capable = 1;
else if (retries-- > 0)
goto again;
else
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_TOKENFALLBACKINIT);
} else if (mp_opt.mp_join && listener->request_mptcp) {
subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq;
subflow_req->mp_join = 1;
subflow_req->backup = mp_opt.backup;
subflow_req->remote_id = mp_opt.join_id;
subflow_req->token = mp_opt.token;
subflow_req->remote_nonce = mp_opt.nonce;
subflow_req->msk = subflow_token_join_request(req);
/* Can't fall back to TCP in this case. */
if (!subflow_req->msk) {
subflow_add_reset_reason(skb, MPTCP_RST_EMPTCP);
return -EPERM;
}
if (subflow_use_different_sport(subflow_req->msk, sk_listener)) {
pr_debug("syn inet_sport=%d %d",
ntohs(inet_sk(sk_listener)->inet_sport),
ntohs(inet_sk((struct sock *)subflow_req->msk)->inet_sport));
if (!mptcp_pm_sport_in_anno_list(subflow_req->msk, sk_listener)) {
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTSYNRX);
return -EPERM;
}
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINPORTSYNRX);
}
subflow_req_create_thmac(subflow_req);
if (unlikely(req->syncookie)) {
if (mptcp_can_accept_new_subflow(subflow_req->msk))
subflow_init_req_cookie_join_save(subflow_req, skb);
else
return -EPERM;
}
pr_debug("token=%u, remote_nonce=%u msk=%p", subflow_req->token,
subflow_req->remote_nonce, subflow_req->msk);
}
return 0;
}
int mptcp_subflow_init_cookie_req(struct request_sock *req,
const struct sock *sk_listener,
struct sk_buff *skb)
{
struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk_listener);
struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
struct mptcp_options_received mp_opt;
int err;
subflow_init_req(req, sk_listener);
mptcp_get_options(sk_listener, skb, &mp_opt);
if (mp_opt.mp_capable && mp_opt.mp_join)
return -EINVAL;
if (mp_opt.mp_capable && listener->request_mptcp) {
if (mp_opt.sndr_key == 0)
return -EINVAL;
subflow_req->local_key = mp_opt.rcvr_key;
err = mptcp_token_new_request(req);
if (err)
return err;
subflow_req->mp_capable = 1;
subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq - 1;
} else if (mp_opt.mp_join && listener->request_mptcp) {
if (!mptcp_token_join_cookie_init_state(subflow_req, skb))
return -EINVAL;
subflow_req->mp_join = 1;
subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq - 1;
}
return 0;
}
EXPORT_SYMBOL_GPL(mptcp_subflow_init_cookie_req);
static struct dst_entry *subflow_v4_route_req(const struct sock *sk,
struct sk_buff *skb,
struct flowi *fl,
struct request_sock *req)
{
struct dst_entry *dst;
int err;
tcp_rsk(req)->is_mptcp = 1;
subflow_init_req(req, sk);
dst = tcp_request_sock_ipv4_ops.route_req(sk, skb, fl, req);
if (!dst)
return NULL;
err = subflow_check_req(req, sk, skb);
if (err == 0)
return dst;
dst_release(dst);
if (!req->syncookie)
tcp_request_sock_ops.send_reset(sk, skb);
return NULL;
}
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
static struct dst_entry *subflow_v6_route_req(const struct sock *sk,
struct sk_buff *skb,
struct flowi *fl,
struct request_sock *req)
{
struct dst_entry *dst;
int err;
tcp_rsk(req)->is_mptcp = 1;
subflow_init_req(req, sk);
dst = tcp_request_sock_ipv6_ops.route_req(sk, skb, fl, req);
if (!dst)
return NULL;
err = subflow_check_req(req, sk, skb);
if (err == 0)
return dst;
dst_release(dst);
if (!req->syncookie)
tcp6_request_sock_ops.send_reset(sk, skb);
return NULL;
}
#endif
/* validate received truncated hmac and create hmac for third ACK */
static bool subflow_thmac_valid(struct mptcp_subflow_context *subflow)
{
u8 hmac[SHA256_DIGEST_SIZE];
u64 thmac;
subflow_generate_hmac(subflow->remote_key, subflow->local_key,
subflow->remote_nonce, subflow->local_nonce,
hmac);
thmac = get_unaligned_be64(hmac);
pr_debug("subflow=%p, token=%u, thmac=%llu, subflow->thmac=%llu\n",
subflow, subflow->token,
(unsigned long long)thmac,
(unsigned long long)subflow->thmac);
return thmac == subflow->thmac;
}
void mptcp_subflow_reset(struct sock *ssk)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
struct sock *sk = subflow->conn;
/* must hold: tcp_done() could drop last reference on parent */
sock_hold(sk);
tcp_set_state(ssk, TCP_CLOSE);
tcp_send_active_reset(ssk, GFP_ATOMIC);
tcp_done(ssk);
if (!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &mptcp_sk(sk)->flags) &&
schedule_work(&mptcp_sk(sk)->work))
return; /* worker will put sk for us */
sock_put(sk);
}
static bool subflow_use_different_dport(struct mptcp_sock *msk, const struct sock *sk)
{
return inet_sk(sk)->inet_dport != inet_sk((struct sock *)msk)->inet_dport;
}
void __mptcp_set_connected(struct sock *sk)
{
if (sk->sk_state == TCP_SYN_SENT) {
inet_sk_state_store(sk, TCP_ESTABLISHED);
sk->sk_state_change(sk);
}
}
static void mptcp_set_connected(struct sock *sk)
{
mptcp_data_lock(sk);
if (!sock_owned_by_user(sk))
__mptcp_set_connected(sk);
else
set_bit(MPTCP_CONNECTED, &mptcp_sk(sk)->flags);
mptcp_data_unlock(sk);
}
static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct mptcp_options_received mp_opt;
struct sock *parent = subflow->conn;
subflow->icsk_af_ops->sk_rx_dst_set(sk, skb);
/* be sure no special action on any packet other than syn-ack */
if (subflow->conn_finished)
return;
mptcp_propagate_sndbuf(parent, sk);
subflow->rel_write_seq = 1;
subflow->conn_finished = 1;
subflow->ssn_offset = TCP_SKB_CB(skb)->seq;
pr_debug("subflow=%p synack seq=%x", subflow, subflow->ssn_offset);
mptcp_get_options(sk, skb, &mp_opt);
if (subflow->request_mptcp) {
if (!mp_opt.mp_capable) {
MPTCP_INC_STATS(sock_net(sk),
MPTCP_MIB_MPCAPABLEACTIVEFALLBACK);
mptcp_do_fallback(sk);
pr_fallback(mptcp_sk(subflow->conn));
goto fallback;
}
if (mp_opt.csum_reqd)
WRITE_ONCE(mptcp_sk(parent)->csum_enabled, true);
if (mp_opt.deny_join_id0)
WRITE_ONCE(mptcp_sk(parent)->pm.remote_deny_join_id0, true);
subflow->mp_capable = 1;
subflow->can_ack = 1;
subflow->remote_key = mp_opt.sndr_key;
pr_debug("subflow=%p, remote_key=%llu", subflow,
subflow->remote_key);
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEACK);
mptcp_finish_connect(sk);
mptcp_set_connected(parent);
} else if (subflow->request_join) {
u8 hmac[SHA256_DIGEST_SIZE];
if (!mp_opt.mp_join) {
subflow->reset_reason = MPTCP_RST_EMPTCP;
goto do_reset;
}
subflow->thmac = mp_opt.thmac;
subflow->remote_nonce = mp_opt.nonce;
pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u", subflow,
subflow->thmac, subflow->remote_nonce);
if (!subflow_thmac_valid(subflow)) {
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINACKMAC);
subflow->reset_reason = MPTCP_RST_EMPTCP;
goto do_reset;
}
if (!mptcp_finish_join(sk))
goto do_reset;
subflow_generate_hmac(subflow->local_key, subflow->remote_key,
subflow->local_nonce,
subflow->remote_nonce,
hmac);
memcpy(subflow->hmac, hmac, MPTCPOPT_HMAC_LEN);
subflow->mp_join = 1;
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX);
if (subflow_use_different_dport(mptcp_sk(parent), sk)) {
pr_debug("synack inet_dport=%d %d",
ntohs(inet_sk(sk)->inet_dport),
ntohs(inet_sk(parent)->inet_dport));
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINPORTSYNACKRX);
}
} else if (mptcp_check_fallback(sk)) {
fallback:
mptcp_rcv_space_init(mptcp_sk(parent), sk);
mptcp_set_connected(parent);
}
return;
do_reset:
subflow->reset_transient = 0;
mptcp_subflow_reset(sk);
}
struct request_sock_ops mptcp_subflow_request_sock_ops;
EXPORT_SYMBOL_GPL(mptcp_subflow_request_sock_ops);
static struct tcp_request_sock_ops subflow_request_sock_ipv4_ops;
static int subflow_v4_conn_request(struct sock *sk, struct sk_buff *skb)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
pr_debug("subflow=%p", subflow);
/* Never answer to SYNs sent to broadcast or multicast */
if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
goto drop;
return tcp_conn_request(&mptcp_subflow_request_sock_ops,
&subflow_request_sock_ipv4_ops,
sk, skb);
drop:
tcp_listendrop(sk);
return 0;
}
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
static struct tcp_request_sock_ops subflow_request_sock_ipv6_ops;
static struct inet_connection_sock_af_ops subflow_v6_specific;
static struct inet_connection_sock_af_ops subflow_v6m_specific;
static struct proto tcpv6_prot_override;
static int subflow_v6_conn_request(struct sock *sk, struct sk_buff *skb)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
pr_debug("subflow=%p", subflow);
if (skb->protocol == htons(ETH_P_IP))
return subflow_v4_conn_request(sk, skb);
if (!ipv6_unicast_destination(skb))
goto drop;
if (ipv6_addr_v4mapped(&ipv6_hdr(skb)->saddr)) {
__IP6_INC_STATS(sock_net(sk), NULL, IPSTATS_MIB_INHDRERRORS);
return 0;
}
return tcp_conn_request(&mptcp_subflow_request_sock_ops,
&subflow_request_sock_ipv6_ops, sk, skb);
drop:
tcp_listendrop(sk);
return 0; /* don't send reset */
}
#endif
/* validate hmac received in third ACK */
static bool subflow_hmac_valid(const struct request_sock *req,
const struct mptcp_options_received *mp_opt)
{
const struct mptcp_subflow_request_sock *subflow_req;
u8 hmac[SHA256_DIGEST_SIZE];
struct mptcp_sock *msk;
subflow_req = mptcp_subflow_rsk(req);
msk = subflow_req->msk;
if (!msk)
return false;
subflow_generate_hmac(msk->remote_key, msk->local_key,
subflow_req->remote_nonce,
subflow_req->local_nonce, hmac);
return !crypto_memneq(hmac, mp_opt->hmac, MPTCPOPT_HMAC_LEN);
}
static void mptcp_sock_destruct(struct sock *sk)
{
/* if new mptcp socket isn't accepted, it is free'd
* from the tcp listener sockets request queue, linked
* from req->sk. The tcp socket is released.
* This calls the ULP release function which will
* also remove the mptcp socket, via
* sock_put(ctx->conn).
*
* Problem is that the mptcp socket will be in
* ESTABLISHED state and will not have the SOCK_DEAD flag.
* Both result in warnings from inet_sock_destruct.
*/
if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) {
sk->sk_state = TCP_CLOSE;
WARN_ON_ONCE(sk->sk_socket);
sock_orphan(sk);
}
mptcp_destroy_common(mptcp_sk(sk));
inet_sock_destruct(sk);
}
static void mptcp_force_close(struct sock *sk)
{
/* the msk is not yet exposed to user-space */
inet_sk_state_store(sk, TCP_CLOSE);
sk_common_release(sk);
}
static void subflow_ulp_fallback(struct sock *sk,
struct mptcp_subflow_context *old_ctx)
{
struct inet_connection_sock *icsk = inet_csk(sk);
mptcp_subflow_tcp_fallback(sk, old_ctx);
icsk->icsk_ulp_ops = NULL;
rcu_assign_pointer(icsk->icsk_ulp_data, NULL);
tcp_sk(sk)->is_mptcp = 0;
mptcp_subflow_ops_undo_override(sk);
}
static void subflow_drop_ctx(struct sock *ssk)
{
struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(ssk);
if (!ctx)
return;
subflow_ulp_fallback(ssk, ctx);
if (ctx->conn)
sock_put(ctx->conn);
kfree_rcu(ctx, rcu);
}
void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
struct mptcp_options_received *mp_opt)
{
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
subflow->remote_key = mp_opt->sndr_key;
subflow->fully_established = 1;
subflow->can_ack = 1;
WRITE_ONCE(msk->fully_established, true);
}
static struct sock *subflow_syn_recv_sock(const struct sock *sk,
struct sk_buff *skb,
struct request_sock *req,
struct dst_entry *dst,
struct request_sock *req_unhash,
bool *own_req)
{
struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk);
struct mptcp_subflow_request_sock *subflow_req;
struct mptcp_options_received mp_opt;
bool fallback, fallback_is_fatal;
struct sock *new_msk = NULL;
struct sock *child;
pr_debug("listener=%p, req=%p, conn=%p", listener, req, listener->conn);
/* After child creation we must look for 'mp_capable' even when options
* are not parsed
*/
mp_opt.mp_capable = 0;
/* hopefully temporary handling for MP_JOIN+syncookie */
subflow_req = mptcp_subflow_rsk(req);
fallback_is_fatal = tcp_rsk(req)->is_mptcp && subflow_req->mp_join;
fallback = !tcp_rsk(req)->is_mptcp;
if (fallback)
goto create_child;
/* if the sk is MP_CAPABLE, we try to fetch the client key */
if (subflow_req->mp_capable) {
/* we can receive and accept an in-window, out-of-order pkt,
* which may not carry the MP_CAPABLE opt even on mptcp enabled
* paths: always try to extract the peer key, and fallback
* for packets missing it.
* Even OoO DSS packets coming legitly after dropped or
* reordered MPC will cause fallback, but we don't have other
* options.
*/
mptcp_get_options(sk, skb, &mp_opt);
if (!mp_opt.mp_capable) {
fallback = true;
goto create_child;
}
new_msk = mptcp_sk_clone(listener->conn, &mp_opt, req);
if (!new_msk)
fallback = true;
} else if (subflow_req->mp_join) {
mptcp_get_options(sk, skb, &mp_opt);
if (!mp_opt.mp_join || !subflow_hmac_valid(req, &mp_opt) ||
!mptcp_can_accept_new_subflow(subflow_req->msk)) {
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC);
fallback = true;
}
}
create_child:
child = listener->icsk_af_ops->syn_recv_sock(sk, skb, req, dst,
req_unhash, own_req);
if (child && *own_req) {
struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(child);
tcp_rsk(req)->drop_req = false;
/* we need to fallback on ctx allocation failure and on pre-reqs
* checking above. In the latter scenario we additionally need
* to reset the context to non MPTCP status.
*/
if (!ctx || fallback) {
if (fallback_is_fatal) {
subflow_add_reset_reason(skb, MPTCP_RST_EMPTCP);
goto dispose_child;
}
subflow_drop_ctx(child);
goto out;
}
/* ssk inherits options of listener sk */
ctx->setsockopt_seq = listener->setsockopt_seq;
if (ctx->mp_capable) {
/* this can't race with mptcp_close(), as the msk is
* not yet exposted to user-space
*/
inet_sk_state_store((void *)new_msk, TCP_ESTABLISHED);
/* record the newly created socket as the first msk
* subflow, but don't link it yet into conn_list
*/
WRITE_ONCE(mptcp_sk(new_msk)->first, child);
/* new mpc subflow takes ownership of the newly
* created mptcp socket
*/
new_msk->sk_destruct = mptcp_sock_destruct;
mptcp_sk(new_msk)->setsockopt_seq = ctx->setsockopt_seq;
mptcp_pm_new_connection(mptcp_sk(new_msk), child, 1);
mptcp_token_accept(subflow_req, mptcp_sk(new_msk));
ctx->conn = new_msk;
new_msk = NULL;
/* with OoO packets we can reach here without ingress
* mpc option
*/
if (mp_opt.mp_capable)
mptcp_subflow_fully_established(ctx, &mp_opt);
} else if (ctx->mp_join) {
struct mptcp_sock *owner;
owner = subflow_req->msk;
if (!owner) {
subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT);
goto dispose_child;
}
/* move the msk reference ownership to the subflow */
subflow_req->msk = NULL;
ctx->conn = (struct sock *)owner;
if (subflow_use_different_sport(owner, sk)) {
pr_debug("ack inet_sport=%d %d",
ntohs(inet_sk(sk)->inet_sport),
ntohs(inet_sk((struct sock *)owner)->inet_sport));
if (!mptcp_pm_sport_in_anno_list(owner, sk)) {
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTACKRX);
goto dispose_child;
}
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINPORTACKRX);
}
if (!mptcp_finish_join(child))
goto dispose_child;
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKRX);
tcp_rsk(req)->drop_req = true;
}
}
out:
/* dispose of the left over mptcp master, if any */
if (unlikely(new_msk))
mptcp_force_close(new_msk);
/* check for expected invariant - should never trigger, just help
* catching eariler subtle bugs
*/
WARN_ON_ONCE(child && *own_req && tcp_sk(child)->is_mptcp &&
(!mptcp_subflow_ctx(child) ||
!mptcp_subflow_ctx(child)->conn));
return child;
dispose_child:
subflow_drop_ctx(child);
tcp_rsk(req)->drop_req = true;
inet_csk_prepare_for_destroy_sock(child);
tcp_done(child);
req->rsk_ops->send_reset(sk, skb);
/* The last child reference will be released by the caller */
return child;
}
static struct inet_connection_sock_af_ops subflow_specific;
static struct proto tcp_prot_override;
enum mapping_status {
MAPPING_OK,
MAPPING_INVALID,
MAPPING_EMPTY,
MAPPING_DATA_FIN,
MAPPING_DUMMY
};
static void dbg_bad_map(struct mptcp_subflow_context *subflow, u32 ssn)
{
pr_debug("Bad mapping: ssn=%d map_seq=%d map_data_len=%d",
ssn, subflow->map_subflow_seq, subflow->map_data_len);
}
static bool skb_is_fully_mapped(struct sock *ssk, struct sk_buff *skb)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
unsigned int skb_consumed;
skb_consumed = tcp_sk(ssk)->copied_seq - TCP_SKB_CB(skb)->seq;
if (WARN_ON_ONCE(skb_consumed >= skb->len))
return true;
return skb->len - skb_consumed <= subflow->map_data_len -
mptcp_subflow_get_map_offset(subflow);
}
static bool validate_mapping(struct sock *ssk, struct sk_buff *skb)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
u32 ssn = tcp_sk(ssk)->copied_seq - subflow->ssn_offset;
if (unlikely(before(ssn, subflow->map_subflow_seq))) {
/* Mapping covers data later in the subflow stream,
* currently unsupported.
*/
dbg_bad_map(subflow, ssn);
return false;
}
if (unlikely(!before(ssn, subflow->map_subflow_seq +
subflow->map_data_len))) {
/* Mapping does covers past subflow data, invalid */
dbg_bad_map(subflow, ssn);
return false;
}
return true;
}
static enum mapping_status validate_data_csum(struct sock *ssk, struct sk_buff *skb,
bool csum_reqd)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
struct csum_pseudo_header header;
u32 offset, seq, delta;
__wsum csum;
int len;
if (!csum_reqd)
return MAPPING_OK;
/* mapping already validated on previous traversal */
if (subflow->map_csum_len == subflow->map_data_len)
return MAPPING_OK;
/* traverse the receive queue, ensuring it contains a full
* DSS mapping and accumulating the related csum.
* Preserve the accoumlate csum across multiple calls, to compute
* the csum only once
*/
delta = subflow->map_data_len - subflow->map_csum_len;
for (;;) {
seq = tcp_sk(ssk)->copied_seq + subflow->map_csum_len;
offset = seq - TCP_SKB_CB(skb)->seq;
/* if the current skb has not been accounted yet, csum its contents
* up to the amount covered by the current DSS
*/
if (offset < skb->len) {
__wsum csum;
len = min(skb->len - offset, delta);
csum = skb_checksum(skb, offset, len, 0);
subflow->map_data_csum = csum_block_add(subflow->map_data_csum, csum,
subflow->map_csum_len);
delta -= len;
subflow->map_csum_len += len;
}
if (delta == 0)
break;
if (skb_queue_is_last(&ssk->sk_receive_queue, skb)) {
/* if this subflow is closed, the partial mapping
* will be never completed; flush the pending skbs, so
* that subflow_sched_work_if_closed() can kick in
*/
if (unlikely(ssk->sk_state == TCP_CLOSE))
while ((skb = skb_peek(&ssk->sk_receive_queue)))
sk_eat_skb(ssk, skb);
/* not enough data to validate the csum */
return MAPPING_EMPTY;
}
/* the DSS mapping for next skbs will be validated later,
* when a get_mapping_status call will process such skb
*/
skb = skb->next;
}
/* note that 'map_data_len' accounts only for the carried data, does
* not include the eventual seq increment due to the data fin,
* while the pseudo header requires the original DSS data len,
* including that
*/
header.data_seq = cpu_to_be64(subflow->map_seq);
header.subflow_seq = htonl(subflow->map_subflow_seq);
header.data_len = htons(subflow->map_data_len + subflow->map_data_fin);
header.csum = 0;
csum = csum_partial(&header, sizeof(header), subflow->map_data_csum);
if (unlikely(csum_fold(csum))) {
MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DATACSUMERR);
return subflow->mp_join ? MAPPING_INVALID : MAPPING_DUMMY;
}
return MAPPING_OK;
}
static enum mapping_status get_mapping_status(struct sock *ssk,
struct mptcp_sock *msk)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
bool csum_reqd = READ_ONCE(msk->csum_enabled);
struct mptcp_ext *mpext;
struct sk_buff *skb;
u16 data_len;
u64 map_seq;
skb = skb_peek(&ssk->sk_receive_queue);
if (!skb)
return MAPPING_EMPTY;
if (mptcp_check_fallback(ssk))
return MAPPING_DUMMY;
mpext = mptcp_get_ext(skb);
if (!mpext || !mpext->use_map) {
if (!subflow->map_valid && !skb->len) {
/* the TCP stack deliver 0 len FIN pkt to the receive
* queue, that is the only 0len pkts ever expected here,
* and we can admit no mapping only for 0 len pkts
*/
if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN))
WARN_ONCE(1, "0len seq %d:%d flags %x",
TCP_SKB_CB(skb)->seq,
TCP_SKB_CB(skb)->end_seq,
TCP_SKB_CB(skb)->tcp_flags);
sk_eat_skb(ssk, skb);
return MAPPING_EMPTY;
}
if (!subflow->map_valid)
return MAPPING_INVALID;
goto validate_seq;
}
trace_get_mapping_status(mpext);
data_len = mpext->data_len;
if (data_len == 0) {
MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPRX);
return MAPPING_INVALID;
}
if (mpext->data_fin == 1) {
if (data_len == 1) {
bool updated = mptcp_update_rcv_data_fin(msk, mpext->data_seq,
mpext->dsn64);
pr_debug("DATA_FIN with no payload seq=%llu", mpext->data_seq);
if (subflow->map_valid) {
/* A DATA_FIN might arrive in a DSS
* option before the previous mapping
* has been fully consumed. Continue
* handling the existing mapping.
*/
skb_ext_del(skb, SKB_EXT_MPTCP);
return MAPPING_OK;
} else {
if (updated && schedule_work(&msk->work))
sock_hold((struct sock *)msk);
return MAPPING_DATA_FIN;
}
} else {
u64 data_fin_seq = mpext->data_seq + data_len - 1;
/* If mpext->data_seq is a 32-bit value, data_fin_seq
* must also be limited to 32 bits.
*/
if (!mpext->dsn64)
data_fin_seq &= GENMASK_ULL(31, 0);
mptcp_update_rcv_data_fin(msk, data_fin_seq, mpext->dsn64);
pr_debug("DATA_FIN with mapping seq=%llu dsn64=%d",
data_fin_seq, mpext->dsn64);
}
/* Adjust for DATA_FIN using 1 byte of sequence space */
data_len--;
}