forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
pm_netlink.c
2098 lines (1725 loc) · 51.3 KB
/
pm_netlink.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) 2020, Red Hat, Inc.
*/
#define pr_fmt(fmt) "MPTCP: " fmt
#include <linux/inet.h>
#include <linux/kernel.h>
#include <net/tcp.h>
#include <net/netns/generic.h>
#include <net/mptcp.h>
#include <net/genetlink.h>
#include <uapi/linux/mptcp.h>
#include "protocol.h"
#include "mib.h"
/* forward declaration */
static struct genl_family mptcp_genl_family;
static int pm_nl_pernet_id;
struct mptcp_pm_addr_entry {
struct list_head list;
struct mptcp_addr_info addr;
u8 flags;
int ifindex;
struct socket *lsk;
};
struct mptcp_pm_add_entry {
struct list_head list;
struct mptcp_addr_info addr;
struct timer_list add_timer;
struct mptcp_sock *sock;
u8 retrans_times;
};
#define MAX_ADDR_ID 255
#define BITMAP_SZ DIV_ROUND_UP(MAX_ADDR_ID + 1, BITS_PER_LONG)
struct pm_nl_pernet {
/* protects pernet updates */
spinlock_t lock;
struct list_head local_addr_list;
unsigned int addrs;
unsigned int stale_loss_cnt;
unsigned int add_addr_signal_max;
unsigned int add_addr_accept_max;
unsigned int local_addr_max;
unsigned int subflows_max;
unsigned int next_id;
unsigned long id_bitmap[BITMAP_SZ];
};
#define MPTCP_PM_ADDR_MAX 8
#define ADD_ADDR_RETRANS_MAX 3
static bool addresses_equal(const struct mptcp_addr_info *a,
struct mptcp_addr_info *b, bool use_port)
{
bool addr_equals = false;
if (a->family == b->family) {
if (a->family == AF_INET)
addr_equals = a->addr.s_addr == b->addr.s_addr;
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
else
addr_equals = !ipv6_addr_cmp(&a->addr6, &b->addr6);
} else if (a->family == AF_INET) {
if (ipv6_addr_v4mapped(&b->addr6))
addr_equals = a->addr.s_addr == b->addr6.s6_addr32[3];
} else if (b->family == AF_INET) {
if (ipv6_addr_v4mapped(&a->addr6))
addr_equals = a->addr6.s6_addr32[3] == b->addr.s_addr;
#endif
}
if (!addr_equals)
return false;
if (!use_port)
return true;
return a->port == b->port;
}
static bool address_zero(const struct mptcp_addr_info *addr)
{
struct mptcp_addr_info zero;
memset(&zero, 0, sizeof(zero));
zero.family = addr->family;
return addresses_equal(addr, &zero, true);
}
static void local_address(const struct sock_common *skc,
struct mptcp_addr_info *addr)
{
addr->family = skc->skc_family;
addr->port = htons(skc->skc_num);
if (addr->family == AF_INET)
addr->addr.s_addr = skc->skc_rcv_saddr;
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
else if (addr->family == AF_INET6)
addr->addr6 = skc->skc_v6_rcv_saddr;
#endif
}
static void remote_address(const struct sock_common *skc,
struct mptcp_addr_info *addr)
{
addr->family = skc->skc_family;
addr->port = skc->skc_dport;
if (addr->family == AF_INET)
addr->addr.s_addr = skc->skc_daddr;
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
else if (addr->family == AF_INET6)
addr->addr6 = skc->skc_v6_daddr;
#endif
}
static bool lookup_subflow_by_saddr(const struct list_head *list,
struct mptcp_addr_info *saddr)
{
struct mptcp_subflow_context *subflow;
struct mptcp_addr_info cur;
struct sock_common *skc;
list_for_each_entry(subflow, list, node) {
skc = (struct sock_common *)mptcp_subflow_tcp_sock(subflow);
local_address(skc, &cur);
if (addresses_equal(&cur, saddr, saddr->port))
return true;
}
return false;
}
static bool lookup_subflow_by_daddr(const struct list_head *list,
struct mptcp_addr_info *daddr)
{
struct mptcp_subflow_context *subflow;
struct mptcp_addr_info cur;
struct sock_common *skc;
list_for_each_entry(subflow, list, node) {
skc = (struct sock_common *)mptcp_subflow_tcp_sock(subflow);
remote_address(skc, &cur);
if (addresses_equal(&cur, daddr, daddr->port))
return true;
}
return false;
}
static struct mptcp_pm_addr_entry *
select_local_address(const struct pm_nl_pernet *pernet,
struct mptcp_sock *msk)
{
struct mptcp_pm_addr_entry *entry, *ret = NULL;
struct sock *sk = (struct sock *)msk;
msk_owned_by_me(msk);
rcu_read_lock();
__mptcp_flush_join_list(msk);
list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW))
continue;
if (entry->addr.family != sk->sk_family) {
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
if ((entry->addr.family == AF_INET &&
!ipv6_addr_v4mapped(&sk->sk_v6_daddr)) ||
(sk->sk_family == AF_INET &&
!ipv6_addr_v4mapped(&entry->addr.addr6)))
#endif
continue;
}
/* avoid any address already in use by subflows and
* pending join
*/
if (!lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) {
ret = entry;
break;
}
}
rcu_read_unlock();
return ret;
}
static struct mptcp_pm_addr_entry *
select_signal_address(struct pm_nl_pernet *pernet, unsigned int pos)
{
struct mptcp_pm_addr_entry *entry, *ret = NULL;
int i = 0;
rcu_read_lock();
/* do not keep any additional per socket state, just signal
* the address list in order.
* Note: removal from the local address list during the msk life-cycle
* can lead to additional addresses not being announced.
*/
list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL))
continue;
if (i++ == pos) {
ret = entry;
break;
}
}
rcu_read_unlock();
return ret;
}
unsigned int mptcp_pm_get_add_addr_signal_max(struct mptcp_sock *msk)
{
struct pm_nl_pernet *pernet;
pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id);
return READ_ONCE(pernet->add_addr_signal_max);
}
EXPORT_SYMBOL_GPL(mptcp_pm_get_add_addr_signal_max);
unsigned int mptcp_pm_get_add_addr_accept_max(struct mptcp_sock *msk)
{
struct pm_nl_pernet *pernet;
pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id);
return READ_ONCE(pernet->add_addr_accept_max);
}
EXPORT_SYMBOL_GPL(mptcp_pm_get_add_addr_accept_max);
unsigned int mptcp_pm_get_subflows_max(struct mptcp_sock *msk)
{
struct pm_nl_pernet *pernet;
pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id);
return READ_ONCE(pernet->subflows_max);
}
EXPORT_SYMBOL_GPL(mptcp_pm_get_subflows_max);
unsigned int mptcp_pm_get_local_addr_max(struct mptcp_sock *msk)
{
struct pm_nl_pernet *pernet;
pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id);
return READ_ONCE(pernet->local_addr_max);
}
EXPORT_SYMBOL_GPL(mptcp_pm_get_local_addr_max);
static void check_work_pending(struct mptcp_sock *msk)
{
if (msk->pm.add_addr_signaled == mptcp_pm_get_add_addr_signal_max(msk) &&
(msk->pm.local_addr_used == mptcp_pm_get_local_addr_max(msk) ||
msk->pm.subflows == mptcp_pm_get_subflows_max(msk)))
WRITE_ONCE(msk->pm.work_pending, false);
}
struct mptcp_pm_add_entry *
mptcp_lookup_anno_list_by_saddr(struct mptcp_sock *msk,
struct mptcp_addr_info *addr)
{
struct mptcp_pm_add_entry *entry;
lockdep_assert_held(&msk->pm.lock);
list_for_each_entry(entry, &msk->pm.anno_list, list) {
if (addresses_equal(&entry->addr, addr, true))
return entry;
}
return NULL;
}
bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk)
{
struct mptcp_pm_add_entry *entry;
struct mptcp_addr_info saddr;
bool ret = false;
local_address((struct sock_common *)sk, &saddr);
spin_lock_bh(&msk->pm.lock);
list_for_each_entry(entry, &msk->pm.anno_list, list) {
if (addresses_equal(&entry->addr, &saddr, true)) {
ret = true;
goto out;
}
}
out:
spin_unlock_bh(&msk->pm.lock);
return ret;
}
static void mptcp_pm_add_timer(struct timer_list *timer)
{
struct mptcp_pm_add_entry *entry = from_timer(entry, timer, add_timer);
struct mptcp_sock *msk = entry->sock;
struct sock *sk = (struct sock *)msk;
pr_debug("msk=%p", msk);
if (!msk)
return;
if (inet_sk_state_load(sk) == TCP_CLOSE)
return;
if (!entry->addr.id)
return;
if (mptcp_pm_should_add_signal_addr(msk)) {
sk_reset_timer(sk, timer, jiffies + TCP_RTO_MAX / 8);
goto out;
}
spin_lock_bh(&msk->pm.lock);
if (!mptcp_pm_should_add_signal_addr(msk)) {
pr_debug("retransmit ADD_ADDR id=%d", entry->addr.id);
mptcp_pm_announce_addr(msk, &entry->addr, false);
mptcp_pm_add_addr_send_ack(msk);
entry->retrans_times++;
}
if (entry->retrans_times < ADD_ADDR_RETRANS_MAX)
sk_reset_timer(sk, timer,
jiffies + mptcp_get_add_addr_timeout(sock_net(sk)));
spin_unlock_bh(&msk->pm.lock);
if (entry->retrans_times == ADD_ADDR_RETRANS_MAX)
mptcp_pm_subflow_established(msk);
out:
__sock_put(sk);
}
struct mptcp_pm_add_entry *
mptcp_pm_del_add_timer(struct mptcp_sock *msk,
struct mptcp_addr_info *addr, bool check_id)
{
struct mptcp_pm_add_entry *entry;
struct sock *sk = (struct sock *)msk;
spin_lock_bh(&msk->pm.lock);
entry = mptcp_lookup_anno_list_by_saddr(msk, addr);
if (entry && (!check_id || entry->addr.id == addr->id))
entry->retrans_times = ADD_ADDR_RETRANS_MAX;
spin_unlock_bh(&msk->pm.lock);
if (entry && (!check_id || entry->addr.id == addr->id))
sk_stop_timer_sync(sk, &entry->add_timer);
return entry;
}
static bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
struct mptcp_pm_addr_entry *entry)
{
struct mptcp_pm_add_entry *add_entry = NULL;
struct sock *sk = (struct sock *)msk;
struct net *net = sock_net(sk);
lockdep_assert_held(&msk->pm.lock);
if (mptcp_lookup_anno_list_by_saddr(msk, &entry->addr))
return false;
add_entry = kmalloc(sizeof(*add_entry), GFP_ATOMIC);
if (!add_entry)
return false;
list_add(&add_entry->list, &msk->pm.anno_list);
add_entry->addr = entry->addr;
add_entry->sock = msk;
add_entry->retrans_times = 0;
timer_setup(&add_entry->add_timer, mptcp_pm_add_timer, 0);
sk_reset_timer(sk, &add_entry->add_timer,
jiffies + mptcp_get_add_addr_timeout(net));
return true;
}
void mptcp_pm_free_anno_list(struct mptcp_sock *msk)
{
struct mptcp_pm_add_entry *entry, *tmp;
struct sock *sk = (struct sock *)msk;
LIST_HEAD(free_list);
pr_debug("msk=%p", msk);
spin_lock_bh(&msk->pm.lock);
list_splice_init(&msk->pm.anno_list, &free_list);
spin_unlock_bh(&msk->pm.lock);
list_for_each_entry_safe(entry, tmp, &free_list, list) {
sk_stop_timer_sync(sk, &entry->add_timer);
kfree(entry);
}
}
static bool lookup_address_in_vec(struct mptcp_addr_info *addrs, unsigned int nr,
struct mptcp_addr_info *addr)
{
int i;
for (i = 0; i < nr; i++) {
if (addresses_equal(&addrs[i], addr, addr->port))
return true;
}
return false;
}
/* Fill all the remote addresses into the array addrs[],
* and return the array size.
*/
static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk, bool fullmesh,
struct mptcp_addr_info *addrs)
{
struct sock *sk = (struct sock *)msk, *ssk;
struct mptcp_subflow_context *subflow;
struct mptcp_addr_info remote = { 0 };
unsigned int subflows_max;
int i = 0;
subflows_max = mptcp_pm_get_subflows_max(msk);
/* Non-fullmesh endpoint, fill in the single entry
* corresponding to the primary MPC subflow remote address
*/
if (!fullmesh) {
remote_address((struct sock_common *)sk, &remote);
msk->pm.subflows++;
addrs[i++] = remote;
} else {
mptcp_for_each_subflow(msk, subflow) {
ssk = mptcp_subflow_tcp_sock(subflow);
remote_address((struct sock_common *)ssk, &remote);
if (!lookup_address_in_vec(addrs, i, &remote) &&
msk->pm.subflows < subflows_max) {
msk->pm.subflows++;
addrs[i++] = remote;
}
}
}
return i;
}
static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
{
struct sock *sk = (struct sock *)msk;
struct mptcp_pm_addr_entry *local;
unsigned int add_addr_signal_max;
unsigned int local_addr_max;
struct pm_nl_pernet *pernet;
unsigned int subflows_max;
pernet = net_generic(sock_net(sk), pm_nl_pernet_id);
add_addr_signal_max = mptcp_pm_get_add_addr_signal_max(msk);
local_addr_max = mptcp_pm_get_local_addr_max(msk);
subflows_max = mptcp_pm_get_subflows_max(msk);
pr_debug("local %d:%d signal %d:%d subflows %d:%d\n",
msk->pm.local_addr_used, local_addr_max,
msk->pm.add_addr_signaled, add_addr_signal_max,
msk->pm.subflows, subflows_max);
/* check first for announce */
if (msk->pm.add_addr_signaled < add_addr_signal_max) {
local = select_signal_address(pernet,
msk->pm.add_addr_signaled);
if (local) {
if (mptcp_pm_alloc_anno_list(msk, local)) {
msk->pm.add_addr_signaled++;
mptcp_pm_announce_addr(msk, &local->addr, false);
mptcp_pm_nl_addr_send_ack(msk);
}
} else {
/* pick failed, avoid fourther attempts later */
msk->pm.local_addr_used = add_addr_signal_max;
}
check_work_pending(msk);
}
/* check if should create a new subflow */
if (msk->pm.local_addr_used < local_addr_max &&
msk->pm.subflows < subflows_max &&
!READ_ONCE(msk->pm.remote_deny_join_id0)) {
local = select_local_address(pernet, msk);
if (local) {
bool fullmesh = !!(local->flags & MPTCP_PM_ADDR_FLAG_FULLMESH);
struct mptcp_addr_info addrs[MPTCP_PM_ADDR_MAX];
int i, nr;
msk->pm.local_addr_used++;
check_work_pending(msk);
nr = fill_remote_addresses_vec(msk, fullmesh, addrs);
spin_unlock_bh(&msk->pm.lock);
for (i = 0; i < nr; i++)
__mptcp_subflow_connect(sk, &local->addr, &addrs[i]);
spin_lock_bh(&msk->pm.lock);
return;
}
/* lookup failed, avoid fourther attempts later */
msk->pm.local_addr_used = local_addr_max;
check_work_pending(msk);
}
}
static void mptcp_pm_nl_fully_established(struct mptcp_sock *msk)
{
mptcp_pm_create_subflow_or_signal_addr(msk);
}
static void mptcp_pm_nl_subflow_established(struct mptcp_sock *msk)
{
mptcp_pm_create_subflow_or_signal_addr(msk);
}
/* Fill all the local addresses into the array addrs[],
* and return the array size.
*/
static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk,
struct mptcp_addr_info *addrs)
{
struct sock *sk = (struct sock *)msk;
struct mptcp_pm_addr_entry *entry;
struct mptcp_addr_info local;
struct pm_nl_pernet *pernet;
unsigned int subflows_max;
int i = 0;
pernet = net_generic(sock_net(sk), pm_nl_pernet_id);
subflows_max = mptcp_pm_get_subflows_max(msk);
rcu_read_lock();
__mptcp_flush_join_list(msk);
list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
if (!(entry->flags & MPTCP_PM_ADDR_FLAG_FULLMESH))
continue;
if (entry->addr.family != sk->sk_family) {
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
if ((entry->addr.family == AF_INET &&
!ipv6_addr_v4mapped(&sk->sk_v6_daddr)) ||
(sk->sk_family == AF_INET &&
!ipv6_addr_v4mapped(&entry->addr.addr6)))
#endif
continue;
}
if (msk->pm.subflows < subflows_max) {
msk->pm.subflows++;
addrs[i++] = entry->addr;
}
}
rcu_read_unlock();
/* If the array is empty, fill in the single
* 'IPADDRANY' local address
*/
if (!i) {
memset(&local, 0, sizeof(local));
local.family = msk->pm.remote.family;
msk->pm.subflows++;
addrs[i++] = local;
}
return i;
}
static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
{
struct mptcp_addr_info addrs[MPTCP_PM_ADDR_MAX];
struct sock *sk = (struct sock *)msk;
unsigned int add_addr_accept_max;
struct mptcp_addr_info remote;
unsigned int subflows_max;
int i, nr;
add_addr_accept_max = mptcp_pm_get_add_addr_accept_max(msk);
subflows_max = mptcp_pm_get_subflows_max(msk);
pr_debug("accepted %d:%d remote family %d",
msk->pm.add_addr_accepted, add_addr_accept_max,
msk->pm.remote.family);
if (lookup_subflow_by_daddr(&msk->conn_list, &msk->pm.remote))
goto add_addr_echo;
/* connect to the specified remote address, using whatever
* local address the routing configuration will pick.
*/
remote = msk->pm.remote;
if (!remote.port)
remote.port = sk->sk_dport;
nr = fill_local_addresses_vec(msk, addrs);
msk->pm.add_addr_accepted++;
if (msk->pm.add_addr_accepted >= add_addr_accept_max ||
msk->pm.subflows >= subflows_max)
WRITE_ONCE(msk->pm.accept_addr, false);
spin_unlock_bh(&msk->pm.lock);
for (i = 0; i < nr; i++)
__mptcp_subflow_connect(sk, &addrs[i], &remote);
spin_lock_bh(&msk->pm.lock);
add_addr_echo:
mptcp_pm_announce_addr(msk, &msk->pm.remote, true);
mptcp_pm_nl_addr_send_ack(msk);
}
void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk)
{
struct mptcp_subflow_context *subflow;
msk_owned_by_me(msk);
lockdep_assert_held(&msk->pm.lock);
if (!mptcp_pm_should_add_signal(msk) &&
!mptcp_pm_should_rm_signal(msk))
return;
__mptcp_flush_join_list(msk);
subflow = list_first_entry_or_null(&msk->conn_list, typeof(*subflow), node);
if (subflow) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
spin_unlock_bh(&msk->pm.lock);
pr_debug("send ack for %s",
mptcp_pm_should_add_signal(msk) ? "add_addr" : "rm_addr");
mptcp_subflow_send_ack(ssk);
spin_lock_bh(&msk->pm.lock);
}
}
static int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
struct mptcp_addr_info *addr,
u8 bkup)
{
struct mptcp_subflow_context *subflow;
pr_debug("bkup=%d", bkup);
mptcp_for_each_subflow(msk, subflow) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
struct sock *sk = (struct sock *)msk;
struct mptcp_addr_info local;
local_address((struct sock_common *)ssk, &local);
if (!addresses_equal(&local, addr, addr->port))
continue;
subflow->backup = bkup;
subflow->send_mp_prio = 1;
subflow->request_bkup = bkup;
__MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPPRIOTX);
spin_unlock_bh(&msk->pm.lock);
pr_debug("send ack for mp_prio");
mptcp_subflow_send_ack(ssk);
spin_lock_bh(&msk->pm.lock);
return 0;
}
return -EINVAL;
}
static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
const struct mptcp_rm_list *rm_list,
enum linux_mptcp_mib_field rm_type)
{
struct mptcp_subflow_context *subflow, *tmp;
struct sock *sk = (struct sock *)msk;
u8 i;
pr_debug("%s rm_list_nr %d",
rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow", rm_list->nr);
msk_owned_by_me(msk);
if (!rm_list->nr)
return;
if (list_empty(&msk->conn_list))
return;
for (i = 0; i < rm_list->nr; i++) {
list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
int how = RCV_SHUTDOWN | SEND_SHUTDOWN;
u8 id = subflow->local_id;
if (rm_type == MPTCP_MIB_RMADDR)
id = subflow->remote_id;
if (rm_list->ids[i] != id)
continue;
pr_debug(" -> %s rm_list_ids[%d]=%u local_id=%u remote_id=%u",
rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow",
i, rm_list->ids[i], subflow->local_id, subflow->remote_id);
spin_unlock_bh(&msk->pm.lock);
mptcp_subflow_shutdown(sk, ssk, how);
mptcp_close_ssk(sk, ssk, subflow);
spin_lock_bh(&msk->pm.lock);
if (rm_type == MPTCP_MIB_RMADDR) {
msk->pm.add_addr_accepted--;
WRITE_ONCE(msk->pm.accept_addr, true);
} else if (rm_type == MPTCP_MIB_RMSUBFLOW) {
msk->pm.local_addr_used--;
}
msk->pm.subflows--;
__MPTCP_INC_STATS(sock_net(sk), rm_type);
}
}
}
static void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk)
{
mptcp_pm_nl_rm_addr_or_subflow(msk, &msk->pm.rm_list_rx, MPTCP_MIB_RMADDR);
}
void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk,
const struct mptcp_rm_list *rm_list)
{
mptcp_pm_nl_rm_addr_or_subflow(msk, rm_list, MPTCP_MIB_RMSUBFLOW);
}
void mptcp_pm_nl_work(struct mptcp_sock *msk)
{
struct mptcp_pm_data *pm = &msk->pm;
msk_owned_by_me(msk);
spin_lock_bh(&msk->pm.lock);
pr_debug("msk=%p status=%x", msk, pm->status);
if (pm->status & BIT(MPTCP_PM_ADD_ADDR_RECEIVED)) {
pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_RECEIVED);
mptcp_pm_nl_add_addr_received(msk);
}
if (pm->status & BIT(MPTCP_PM_ADD_ADDR_SEND_ACK)) {
pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_SEND_ACK);
mptcp_pm_nl_addr_send_ack(msk);
}
if (pm->status & BIT(MPTCP_PM_RM_ADDR_RECEIVED)) {
pm->status &= ~BIT(MPTCP_PM_RM_ADDR_RECEIVED);
mptcp_pm_nl_rm_addr_received(msk);
}
if (pm->status & BIT(MPTCP_PM_ESTABLISHED)) {
pm->status &= ~BIT(MPTCP_PM_ESTABLISHED);
mptcp_pm_nl_fully_established(msk);
}
if (pm->status & BIT(MPTCP_PM_SUBFLOW_ESTABLISHED)) {
pm->status &= ~BIT(MPTCP_PM_SUBFLOW_ESTABLISHED);
mptcp_pm_nl_subflow_established(msk);
}
spin_unlock_bh(&msk->pm.lock);
}
static bool address_use_port(struct mptcp_pm_addr_entry *entry)
{
return (entry->flags &
(MPTCP_PM_ADDR_FLAG_SIGNAL | MPTCP_PM_ADDR_FLAG_SUBFLOW)) ==
MPTCP_PM_ADDR_FLAG_SIGNAL;
}
static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
struct mptcp_pm_addr_entry *entry)
{
struct mptcp_pm_addr_entry *cur;
unsigned int addr_max;
int ret = -EINVAL;
spin_lock_bh(&pernet->lock);
/* to keep the code simple, don't do IDR-like allocation for address ID,
* just bail when we exceed limits
*/
if (pernet->next_id == MAX_ADDR_ID)
pernet->next_id = 1;
if (pernet->addrs >= MPTCP_PM_ADDR_MAX)
goto out;
if (test_bit(entry->addr.id, pernet->id_bitmap))
goto out;
/* do not insert duplicate address, differentiate on port only
* singled addresses
*/
list_for_each_entry(cur, &pernet->local_addr_list, list) {
if (addresses_equal(&cur->addr, &entry->addr,
address_use_port(entry) &&
address_use_port(cur)))
goto out;
}
if (!entry->addr.id) {
find_next:
entry->addr.id = find_next_zero_bit(pernet->id_bitmap,
MAX_ADDR_ID + 1,
pernet->next_id);
if ((!entry->addr.id || entry->addr.id > MAX_ADDR_ID) &&
pernet->next_id != 1) {
pernet->next_id = 1;
goto find_next;
}
}
if (!entry->addr.id || entry->addr.id > MAX_ADDR_ID)
goto out;
__set_bit(entry->addr.id, pernet->id_bitmap);
if (entry->addr.id > pernet->next_id)
pernet->next_id = entry->addr.id;
if (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL) {
addr_max = pernet->add_addr_signal_max;
WRITE_ONCE(pernet->add_addr_signal_max, addr_max + 1);
}
if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) {
addr_max = pernet->local_addr_max;
WRITE_ONCE(pernet->local_addr_max, addr_max + 1);
}
pernet->addrs++;
list_add_tail_rcu(&entry->list, &pernet->local_addr_list);
ret = entry->addr.id;
out:
spin_unlock_bh(&pernet->lock);
return ret;
}
static int mptcp_pm_nl_create_listen_socket(struct sock *sk,
struct mptcp_pm_addr_entry *entry)
{
struct sockaddr_storage addr;
struct mptcp_sock *msk;
struct socket *ssock;
int backlog = 1024;
int err;
err = sock_create_kern(sock_net(sk), entry->addr.family,
SOCK_STREAM, IPPROTO_MPTCP, &entry->lsk);
if (err)
return err;
msk = mptcp_sk(entry->lsk->sk);
if (!msk) {
err = -EINVAL;
goto out;
}
ssock = __mptcp_nmpc_socket(msk);
if (!ssock) {
err = -EINVAL;
goto out;
}
mptcp_info2sockaddr(&entry->addr, &addr, entry->addr.family);
err = kernel_bind(ssock, (struct sockaddr *)&addr,
sizeof(struct sockaddr_in));
if (err) {
pr_warn("kernel_bind error, err=%d", err);
goto out;
}
err = kernel_listen(ssock, backlog);
if (err) {
pr_warn("kernel_listen error, err=%d", err);
goto out;
}
return 0;
out:
sock_release(entry->lsk);
return err;
}
int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc)
{
struct mptcp_pm_addr_entry *entry;
struct mptcp_addr_info skc_local;
struct mptcp_addr_info msk_local;
struct pm_nl_pernet *pernet;
int ret = -1;
if (WARN_ON_ONCE(!msk))
return -1;
/* The 0 ID mapping is defined by the first subflow, copied into the msk
* addr
*/
local_address((struct sock_common *)msk, &msk_local);
local_address((struct sock_common *)skc, &skc_local);
if (addresses_equal(&msk_local, &skc_local, false))
return 0;
if (address_zero(&skc_local))
return 0;
pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id);
rcu_read_lock();
list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
if (addresses_equal(&entry->addr, &skc_local, entry->addr.port)) {
ret = entry->addr.id;
break;
}
}
rcu_read_unlock();
if (ret >= 0)
return ret;
/* address not found, add to local list */
entry = kmalloc(sizeof(*entry), GFP_ATOMIC);
if (!entry)
return -ENOMEM;
entry->addr = skc_local;
entry->addr.id = 0;
entry->addr.port = 0;
entry->ifindex = 0;
entry->flags = 0;
entry->lsk = NULL;
ret = mptcp_pm_nl_append_new_local_addr(pernet, entry);
if (ret < 0)
kfree(entry);
return ret;
}
void mptcp_pm_nl_data_init(struct mptcp_sock *msk)
{
struct mptcp_pm_data *pm = &msk->pm;
bool subflows;
subflows = !!mptcp_pm_get_subflows_max(msk);
WRITE_ONCE(pm->work_pending, (!!mptcp_pm_get_local_addr_max(msk) && subflows) ||
!!mptcp_pm_get_add_addr_signal_max(msk));
WRITE_ONCE(pm->accept_addr, !!mptcp_pm_get_add_addr_accept_max(msk) && subflows);
WRITE_ONCE(pm->accept_subflow, subflows);
}
#define MPTCP_PM_CMD_GRP_OFFSET 0
#define MPTCP_PM_EV_GRP_OFFSET 1
static const struct genl_multicast_group mptcp_pm_mcgrps[] = {
[MPTCP_PM_CMD_GRP_OFFSET] = { .name = MPTCP_PM_CMD_GRP_NAME, },
[MPTCP_PM_EV_GRP_OFFSET] = { .name = MPTCP_PM_EV_GRP_NAME,
.flags = GENL_UNS_ADMIN_PERM,
},
};
static const struct nla_policy
mptcp_pm_addr_policy[MPTCP_PM_ADDR_ATTR_MAX + 1] = {
[MPTCP_PM_ADDR_ATTR_FAMILY] = { .type = NLA_U16, },
[MPTCP_PM_ADDR_ATTR_ID] = { .type = NLA_U8, },
[MPTCP_PM_ADDR_ATTR_ADDR4] = { .type = NLA_U32, },
[MPTCP_PM_ADDR_ATTR_ADDR6] =
NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)),
[MPTCP_PM_ADDR_ATTR_PORT] = { .type = NLA_U16 },
[MPTCP_PM_ADDR_ATTR_FLAGS] = { .type = NLA_U32 },
[MPTCP_PM_ADDR_ATTR_IF_IDX] = { .type = NLA_S32 },
};
static const struct nla_policy mptcp_pm_policy[MPTCP_PM_ATTR_MAX + 1] = {
[MPTCP_PM_ATTR_ADDR] =
NLA_POLICY_NESTED(mptcp_pm_addr_policy),
[MPTCP_PM_ATTR_RCV_ADD_ADDRS] = { .type = NLA_U32, },
[MPTCP_PM_ATTR_SUBFLOWS] = { .type = NLA_U32, },
};
void mptcp_pm_nl_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk)
{
struct mptcp_subflow_context *iter, *subflow = mptcp_subflow_ctx(ssk);