forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
af_key.c
3876 lines (3289 loc) · 101 KB
/
af_key.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
/*
* net/key/af_key.c An implementation of PF_KEYv2 sockets.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
* Authors: Maxim Giryaev <[email protected]>
* David S. Miller <[email protected]>
* Alexey Kuznetsov <[email protected]>
* Kunihiro Ishiguro <[email protected]>
* Kazunori MIYAZAWA / USAGI Project <[email protected]>
* Derek Atkins <[email protected]>
*/
#include <linux/capability.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/socket.h>
#include <linux/pfkeyv2.h>
#include <linux/ipsec.h>
#include <linux/skbuff.h>
#include <linux/rtnetlink.h>
#include <linux/in.h>
#include <linux/in6.h>
#include <linux/proc_fs.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/xfrm.h>
#include <net/sock.h>
#define _X2KEY(x) ((x) == XFRM_INF ? 0 : (x))
#define _KEY2X(x) ((x) == 0 ? XFRM_INF : (x))
static int pfkey_net_id __read_mostly;
struct netns_pfkey {
/* List of all pfkey sockets. */
struct hlist_head table;
atomic_t socks_nr;
};
static DEFINE_MUTEX(pfkey_mutex);
#define DUMMY_MARK 0
static const struct xfrm_mark dummy_mark = {0, 0};
struct pfkey_sock {
/* struct sock must be the first member of struct pfkey_sock */
struct sock sk;
int registered;
int promisc;
struct {
uint8_t msg_version;
uint32_t msg_portid;
int (*dump)(struct pfkey_sock *sk);
void (*done)(struct pfkey_sock *sk);
union {
struct xfrm_policy_walk policy;
struct xfrm_state_walk state;
} u;
struct sk_buff *skb;
} dump;
};
static inline struct pfkey_sock *pfkey_sk(struct sock *sk)
{
return (struct pfkey_sock *)sk;
}
static int pfkey_can_dump(const struct sock *sk)
{
if (3 * atomic_read(&sk->sk_rmem_alloc) <= 2 * sk->sk_rcvbuf)
return 1;
return 0;
}
static void pfkey_terminate_dump(struct pfkey_sock *pfk)
{
if (pfk->dump.dump) {
if (pfk->dump.skb) {
kfree_skb(pfk->dump.skb);
pfk->dump.skb = NULL;
}
pfk->dump.done(pfk);
pfk->dump.dump = NULL;
pfk->dump.done = NULL;
}
}
static void pfkey_sock_destruct(struct sock *sk)
{
struct net *net = sock_net(sk);
struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id);
pfkey_terminate_dump(pfkey_sk(sk));
skb_queue_purge(&sk->sk_receive_queue);
if (!sock_flag(sk, SOCK_DEAD)) {
pr_err("Attempt to release alive pfkey socket: %p\n", sk);
return;
}
WARN_ON(atomic_read(&sk->sk_rmem_alloc));
WARN_ON(atomic_read(&sk->sk_wmem_alloc));
atomic_dec(&net_pfkey->socks_nr);
}
static const struct proto_ops pfkey_ops;
static void pfkey_insert(struct sock *sk)
{
struct net *net = sock_net(sk);
struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id);
mutex_lock(&pfkey_mutex);
sk_add_node_rcu(sk, &net_pfkey->table);
mutex_unlock(&pfkey_mutex);
}
static void pfkey_remove(struct sock *sk)
{
mutex_lock(&pfkey_mutex);
sk_del_node_init_rcu(sk);
mutex_unlock(&pfkey_mutex);
}
static struct proto key_proto = {
.name = "KEY",
.owner = THIS_MODULE,
.obj_size = sizeof(struct pfkey_sock),
};
static int pfkey_create(struct net *net, struct socket *sock, int protocol,
int kern)
{
struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id);
struct sock *sk;
int err;
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
return -EPERM;
if (sock->type != SOCK_RAW)
return -ESOCKTNOSUPPORT;
if (protocol != PF_KEY_V2)
return -EPROTONOSUPPORT;
err = -ENOMEM;
sk = sk_alloc(net, PF_KEY, GFP_KERNEL, &key_proto);
if (sk == NULL)
goto out;
sock->ops = &pfkey_ops;
sock_init_data(sock, sk);
sk->sk_family = PF_KEY;
sk->sk_destruct = pfkey_sock_destruct;
atomic_inc(&net_pfkey->socks_nr);
pfkey_insert(sk);
return 0;
out:
return err;
}
static int pfkey_release(struct socket *sock)
{
struct sock *sk = sock->sk;
if (!sk)
return 0;
pfkey_remove(sk);
sock_orphan(sk);
sock->sk = NULL;
skb_queue_purge(&sk->sk_write_queue);
synchronize_rcu();
sock_put(sk);
return 0;
}
static int pfkey_broadcast_one(struct sk_buff *skb, struct sk_buff **skb2,
gfp_t allocation, struct sock *sk)
{
int err = -ENOBUFS;
sock_hold(sk);
if (*skb2 == NULL) {
if (atomic_read(&skb->users) != 1) {
*skb2 = skb_clone(skb, allocation);
} else {
*skb2 = skb;
atomic_inc(&skb->users);
}
}
if (*skb2 != NULL) {
if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) {
skb_set_owner_r(*skb2, sk);
skb_queue_tail(&sk->sk_receive_queue, *skb2);
sk->sk_data_ready(sk);
*skb2 = NULL;
err = 0;
}
}
sock_put(sk);
return err;
}
/* Send SKB to all pfkey sockets matching selected criteria. */
#define BROADCAST_ALL 0
#define BROADCAST_ONE 1
#define BROADCAST_REGISTERED 2
#define BROADCAST_PROMISC_ONLY 4
static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation,
int broadcast_flags, struct sock *one_sk,
struct net *net)
{
struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id);
struct sock *sk;
struct sk_buff *skb2 = NULL;
int err = -ESRCH;
/* XXX Do we need something like netlink_overrun? I think
* XXX PF_KEY socket apps will not mind current behavior.
*/
if (!skb)
return -ENOMEM;
rcu_read_lock();
sk_for_each_rcu(sk, &net_pfkey->table) {
struct pfkey_sock *pfk = pfkey_sk(sk);
int err2;
/* Yes, it means that if you are meant to receive this
* pfkey message you receive it twice as promiscuous
* socket.
*/
if (pfk->promisc)
pfkey_broadcast_one(skb, &skb2, allocation, sk);
/* the exact target will be processed later */
if (sk == one_sk)
continue;
if (broadcast_flags != BROADCAST_ALL) {
if (broadcast_flags & BROADCAST_PROMISC_ONLY)
continue;
if ((broadcast_flags & BROADCAST_REGISTERED) &&
!pfk->registered)
continue;
if (broadcast_flags & BROADCAST_ONE)
continue;
}
err2 = pfkey_broadcast_one(skb, &skb2, allocation, sk);
/* Error is cleare after succecful sending to at least one
* registered KM */
if ((broadcast_flags & BROADCAST_REGISTERED) && err)
err = err2;
}
rcu_read_unlock();
if (one_sk != NULL)
err = pfkey_broadcast_one(skb, &skb2, allocation, one_sk);
kfree_skb(skb2);
kfree_skb(skb);
return err;
}
static int pfkey_do_dump(struct pfkey_sock *pfk)
{
struct sadb_msg *hdr;
int rc;
rc = pfk->dump.dump(pfk);
if (rc == -ENOBUFS)
return 0;
if (pfk->dump.skb) {
if (!pfkey_can_dump(&pfk->sk))
return 0;
hdr = (struct sadb_msg *) pfk->dump.skb->data;
hdr->sadb_msg_seq = 0;
hdr->sadb_msg_errno = rc;
pfkey_broadcast(pfk->dump.skb, GFP_ATOMIC, BROADCAST_ONE,
&pfk->sk, sock_net(&pfk->sk));
pfk->dump.skb = NULL;
}
pfkey_terminate_dump(pfk);
return rc;
}
static inline void pfkey_hdr_dup(struct sadb_msg *new,
const struct sadb_msg *orig)
{
*new = *orig;
}
static int pfkey_error(const struct sadb_msg *orig, int err, struct sock *sk)
{
struct sk_buff *skb = alloc_skb(sizeof(struct sadb_msg) + 16, GFP_KERNEL);
struct sadb_msg *hdr;
if (!skb)
return -ENOBUFS;
/* Woe be to the platform trying to support PFKEY yet
* having normal errnos outside the 1-255 range, inclusive.
*/
err = -err;
if (err == ERESTARTSYS ||
err == ERESTARTNOHAND ||
err == ERESTARTNOINTR)
err = EINTR;
if (err >= 512)
err = EINVAL;
BUG_ON(err <= 0 || err >= 256);
hdr = (struct sadb_msg *) skb_put(skb, sizeof(struct sadb_msg));
pfkey_hdr_dup(hdr, orig);
hdr->sadb_msg_errno = (uint8_t) err;
hdr->sadb_msg_len = (sizeof(struct sadb_msg) /
sizeof(uint64_t));
pfkey_broadcast(skb, GFP_KERNEL, BROADCAST_ONE, sk, sock_net(sk));
return 0;
}
static const u8 sadb_ext_min_len[] = {
[SADB_EXT_RESERVED] = (u8) 0,
[SADB_EXT_SA] = (u8) sizeof(struct sadb_sa),
[SADB_EXT_LIFETIME_CURRENT] = (u8) sizeof(struct sadb_lifetime),
[SADB_EXT_LIFETIME_HARD] = (u8) sizeof(struct sadb_lifetime),
[SADB_EXT_LIFETIME_SOFT] = (u8) sizeof(struct sadb_lifetime),
[SADB_EXT_ADDRESS_SRC] = (u8) sizeof(struct sadb_address),
[SADB_EXT_ADDRESS_DST] = (u8) sizeof(struct sadb_address),
[SADB_EXT_ADDRESS_PROXY] = (u8) sizeof(struct sadb_address),
[SADB_EXT_KEY_AUTH] = (u8) sizeof(struct sadb_key),
[SADB_EXT_KEY_ENCRYPT] = (u8) sizeof(struct sadb_key),
[SADB_EXT_IDENTITY_SRC] = (u8) sizeof(struct sadb_ident),
[SADB_EXT_IDENTITY_DST] = (u8) sizeof(struct sadb_ident),
[SADB_EXT_SENSITIVITY] = (u8) sizeof(struct sadb_sens),
[SADB_EXT_PROPOSAL] = (u8) sizeof(struct sadb_prop),
[SADB_EXT_SUPPORTED_AUTH] = (u8) sizeof(struct sadb_supported),
[SADB_EXT_SUPPORTED_ENCRYPT] = (u8) sizeof(struct sadb_supported),
[SADB_EXT_SPIRANGE] = (u8) sizeof(struct sadb_spirange),
[SADB_X_EXT_KMPRIVATE] = (u8) sizeof(struct sadb_x_kmprivate),
[SADB_X_EXT_POLICY] = (u8) sizeof(struct sadb_x_policy),
[SADB_X_EXT_SA2] = (u8) sizeof(struct sadb_x_sa2),
[SADB_X_EXT_NAT_T_TYPE] = (u8) sizeof(struct sadb_x_nat_t_type),
[SADB_X_EXT_NAT_T_SPORT] = (u8) sizeof(struct sadb_x_nat_t_port),
[SADB_X_EXT_NAT_T_DPORT] = (u8) sizeof(struct sadb_x_nat_t_port),
[SADB_X_EXT_NAT_T_OA] = (u8) sizeof(struct sadb_address),
[SADB_X_EXT_SEC_CTX] = (u8) sizeof(struct sadb_x_sec_ctx),
[SADB_X_EXT_KMADDRESS] = (u8) sizeof(struct sadb_x_kmaddress),
[SADB_X_EXT_FILTER] = (u8) sizeof(struct sadb_x_filter),
};
/* Verify sadb_address_{len,prefixlen} against sa_family. */
static int verify_address_len(const void *p)
{
const struct sadb_address *sp = p;
const struct sockaddr *addr = (const struct sockaddr *)(sp + 1);
const struct sockaddr_in *sin;
#if IS_ENABLED(CONFIG_IPV6)
const struct sockaddr_in6 *sin6;
#endif
int len;
switch (addr->sa_family) {
case AF_INET:
len = DIV_ROUND_UP(sizeof(*sp) + sizeof(*sin), sizeof(uint64_t));
if (sp->sadb_address_len != len ||
sp->sadb_address_prefixlen > 32)
return -EINVAL;
break;
#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
len = DIV_ROUND_UP(sizeof(*sp) + sizeof(*sin6), sizeof(uint64_t));
if (sp->sadb_address_len != len ||
sp->sadb_address_prefixlen > 128)
return -EINVAL;
break;
#endif
default:
/* It is user using kernel to keep track of security
* associations for another protocol, such as
* OSPF/RSVP/RIPV2/MIP. It is user's job to verify
* lengths.
*
* XXX Actually, association/policy database is not yet
* XXX able to cope with arbitrary sockaddr families.
* XXX When it can, remove this -EINVAL. -DaveM
*/
return -EINVAL;
break;
}
return 0;
}
static inline int pfkey_sec_ctx_len(const struct sadb_x_sec_ctx *sec_ctx)
{
return DIV_ROUND_UP(sizeof(struct sadb_x_sec_ctx) +
sec_ctx->sadb_x_ctx_len,
sizeof(uint64_t));
}
static inline int verify_sec_ctx_len(const void *p)
{
const struct sadb_x_sec_ctx *sec_ctx = p;
int len = sec_ctx->sadb_x_ctx_len;
if (len > PAGE_SIZE)
return -EINVAL;
len = pfkey_sec_ctx_len(sec_ctx);
if (sec_ctx->sadb_x_sec_len != len)
return -EINVAL;
return 0;
}
static inline struct xfrm_user_sec_ctx *pfkey_sadb2xfrm_user_sec_ctx(const struct sadb_x_sec_ctx *sec_ctx,
gfp_t gfp)
{
struct xfrm_user_sec_ctx *uctx = NULL;
int ctx_size = sec_ctx->sadb_x_ctx_len;
uctx = kmalloc((sizeof(*uctx)+ctx_size), gfp);
if (!uctx)
return NULL;
uctx->len = pfkey_sec_ctx_len(sec_ctx);
uctx->exttype = sec_ctx->sadb_x_sec_exttype;
uctx->ctx_doi = sec_ctx->sadb_x_ctx_doi;
uctx->ctx_alg = sec_ctx->sadb_x_ctx_alg;
uctx->ctx_len = sec_ctx->sadb_x_ctx_len;
memcpy(uctx + 1, sec_ctx + 1,
uctx->ctx_len);
return uctx;
}
static int present_and_same_family(const struct sadb_address *src,
const struct sadb_address *dst)
{
const struct sockaddr *s_addr, *d_addr;
if (!src || !dst)
return 0;
s_addr = (const struct sockaddr *)(src + 1);
d_addr = (const struct sockaddr *)(dst + 1);
if (s_addr->sa_family != d_addr->sa_family)
return 0;
if (s_addr->sa_family != AF_INET
#if IS_ENABLED(CONFIG_IPV6)
&& s_addr->sa_family != AF_INET6
#endif
)
return 0;
return 1;
}
static int parse_exthdrs(struct sk_buff *skb, const struct sadb_msg *hdr, void **ext_hdrs)
{
const char *p = (char *) hdr;
int len = skb->len;
len -= sizeof(*hdr);
p += sizeof(*hdr);
while (len > 0) {
const struct sadb_ext *ehdr = (const struct sadb_ext *) p;
uint16_t ext_type;
int ext_len;
ext_len = ehdr->sadb_ext_len;
ext_len *= sizeof(uint64_t);
ext_type = ehdr->sadb_ext_type;
if (ext_len < sizeof(uint64_t) ||
ext_len > len ||
ext_type == SADB_EXT_RESERVED)
return -EINVAL;
if (ext_type <= SADB_EXT_MAX) {
int min = (int) sadb_ext_min_len[ext_type];
if (ext_len < min)
return -EINVAL;
if (ext_hdrs[ext_type-1] != NULL)
return -EINVAL;
if (ext_type == SADB_EXT_ADDRESS_SRC ||
ext_type == SADB_EXT_ADDRESS_DST ||
ext_type == SADB_EXT_ADDRESS_PROXY ||
ext_type == SADB_X_EXT_NAT_T_OA) {
if (verify_address_len(p))
return -EINVAL;
}
if (ext_type == SADB_X_EXT_SEC_CTX) {
if (verify_sec_ctx_len(p))
return -EINVAL;
}
ext_hdrs[ext_type-1] = (void *) p;
}
p += ext_len;
len -= ext_len;
}
return 0;
}
static uint16_t
pfkey_satype2proto(uint8_t satype)
{
switch (satype) {
case SADB_SATYPE_UNSPEC:
return IPSEC_PROTO_ANY;
case SADB_SATYPE_AH:
return IPPROTO_AH;
case SADB_SATYPE_ESP:
return IPPROTO_ESP;
case SADB_X_SATYPE_IPCOMP:
return IPPROTO_COMP;
break;
default:
return 0;
}
/* NOTREACHED */
}
static uint8_t
pfkey_proto2satype(uint16_t proto)
{
switch (proto) {
case IPPROTO_AH:
return SADB_SATYPE_AH;
case IPPROTO_ESP:
return SADB_SATYPE_ESP;
case IPPROTO_COMP:
return SADB_X_SATYPE_IPCOMP;
break;
default:
return 0;
}
/* NOTREACHED */
}
/* BTW, this scheme means that there is no way with PFKEY2 sockets to
* say specifically 'just raw sockets' as we encode them as 255.
*/
static uint8_t pfkey_proto_to_xfrm(uint8_t proto)
{
return proto == IPSEC_PROTO_ANY ? 0 : proto;
}
static uint8_t pfkey_proto_from_xfrm(uint8_t proto)
{
return proto ? proto : IPSEC_PROTO_ANY;
}
static inline int pfkey_sockaddr_len(sa_family_t family)
{
switch (family) {
case AF_INET:
return sizeof(struct sockaddr_in);
#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
return sizeof(struct sockaddr_in6);
#endif
}
return 0;
}
static
int pfkey_sockaddr_extract(const struct sockaddr *sa, xfrm_address_t *xaddr)
{
switch (sa->sa_family) {
case AF_INET:
xaddr->a4 =
((struct sockaddr_in *)sa)->sin_addr.s_addr;
return AF_INET;
#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
memcpy(xaddr->a6,
&((struct sockaddr_in6 *)sa)->sin6_addr,
sizeof(struct in6_addr));
return AF_INET6;
#endif
}
return 0;
}
static
int pfkey_sadb_addr2xfrm_addr(const struct sadb_address *addr, xfrm_address_t *xaddr)
{
return pfkey_sockaddr_extract((struct sockaddr *)(addr + 1),
xaddr);
}
static struct xfrm_state *pfkey_xfrm_state_lookup(struct net *net, const struct sadb_msg *hdr, void * const *ext_hdrs)
{
const struct sadb_sa *sa;
const struct sadb_address *addr;
uint16_t proto;
unsigned short family;
xfrm_address_t *xaddr;
sa = ext_hdrs[SADB_EXT_SA - 1];
if (sa == NULL)
return NULL;
proto = pfkey_satype2proto(hdr->sadb_msg_satype);
if (proto == 0)
return NULL;
/* sadb_address_len should be checked by caller */
addr = ext_hdrs[SADB_EXT_ADDRESS_DST - 1];
if (addr == NULL)
return NULL;
family = ((const struct sockaddr *)(addr + 1))->sa_family;
switch (family) {
case AF_INET:
xaddr = (xfrm_address_t *)&((const struct sockaddr_in *)(addr + 1))->sin_addr;
break;
#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
xaddr = (xfrm_address_t *)&((const struct sockaddr_in6 *)(addr + 1))->sin6_addr;
break;
#endif
default:
xaddr = NULL;
}
if (!xaddr)
return NULL;
return xfrm_state_lookup(net, DUMMY_MARK, xaddr, sa->sadb_sa_spi, proto, family);
}
#define PFKEY_ALIGN8(a) (1 + (((a) - 1) | (8 - 1)))
static int
pfkey_sockaddr_size(sa_family_t family)
{
return PFKEY_ALIGN8(pfkey_sockaddr_len(family));
}
static inline int pfkey_mode_from_xfrm(int mode)
{
switch(mode) {
case XFRM_MODE_TRANSPORT:
return IPSEC_MODE_TRANSPORT;
case XFRM_MODE_TUNNEL:
return IPSEC_MODE_TUNNEL;
case XFRM_MODE_BEET:
return IPSEC_MODE_BEET;
default:
return -1;
}
}
static inline int pfkey_mode_to_xfrm(int mode)
{
switch(mode) {
case IPSEC_MODE_ANY: /*XXX*/
case IPSEC_MODE_TRANSPORT:
return XFRM_MODE_TRANSPORT;
case IPSEC_MODE_TUNNEL:
return XFRM_MODE_TUNNEL;
case IPSEC_MODE_BEET:
return XFRM_MODE_BEET;
default:
return -1;
}
}
static unsigned int pfkey_sockaddr_fill(const xfrm_address_t *xaddr, __be16 port,
struct sockaddr *sa,
unsigned short family)
{
switch (family) {
case AF_INET:
{
struct sockaddr_in *sin = (struct sockaddr_in *)sa;
sin->sin_family = AF_INET;
sin->sin_port = port;
sin->sin_addr.s_addr = xaddr->a4;
memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
return 32;
}
#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
{
struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sa;
sin6->sin6_family = AF_INET6;
sin6->sin6_port = port;
sin6->sin6_flowinfo = 0;
sin6->sin6_addr = *(struct in6_addr *)xaddr->a6;
sin6->sin6_scope_id = 0;
return 128;
}
#endif
}
return 0;
}
static struct sk_buff *__pfkey_xfrm_state2msg(const struct xfrm_state *x,
int add_keys, int hsc)
{
struct sk_buff *skb;
struct sadb_msg *hdr;
struct sadb_sa *sa;
struct sadb_lifetime *lifetime;
struct sadb_address *addr;
struct sadb_key *key;
struct sadb_x_sa2 *sa2;
struct sadb_x_sec_ctx *sec_ctx;
struct xfrm_sec_ctx *xfrm_ctx;
int ctx_size = 0;
int size;
int auth_key_size = 0;
int encrypt_key_size = 0;
int sockaddr_size;
struct xfrm_encap_tmpl *natt = NULL;
int mode;
/* address family check */
sockaddr_size = pfkey_sockaddr_size(x->props.family);
if (!sockaddr_size)
return ERR_PTR(-EINVAL);
/* base, SA, (lifetime (HSC),) address(SD), (address(P),)
key(AE), (identity(SD),) (sensitivity)> */
size = sizeof(struct sadb_msg) +sizeof(struct sadb_sa) +
sizeof(struct sadb_lifetime) +
((hsc & 1) ? sizeof(struct sadb_lifetime) : 0) +
((hsc & 2) ? sizeof(struct sadb_lifetime) : 0) +
sizeof(struct sadb_address)*2 +
sockaddr_size*2 +
sizeof(struct sadb_x_sa2);
if ((xfrm_ctx = x->security)) {
ctx_size = PFKEY_ALIGN8(xfrm_ctx->ctx_len);
size += sizeof(struct sadb_x_sec_ctx) + ctx_size;
}
/* identity & sensitivity */
if (!xfrm_addr_equal(&x->sel.saddr, &x->props.saddr, x->props.family))
size += sizeof(struct sadb_address) + sockaddr_size;
if (add_keys) {
if (x->aalg && x->aalg->alg_key_len) {
auth_key_size =
PFKEY_ALIGN8((x->aalg->alg_key_len + 7) / 8);
size += sizeof(struct sadb_key) + auth_key_size;
}
if (x->ealg && x->ealg->alg_key_len) {
encrypt_key_size =
PFKEY_ALIGN8((x->ealg->alg_key_len+7) / 8);
size += sizeof(struct sadb_key) + encrypt_key_size;
}
}
if (x->encap)
natt = x->encap;
if (natt && natt->encap_type) {
size += sizeof(struct sadb_x_nat_t_type);
size += sizeof(struct sadb_x_nat_t_port);
size += sizeof(struct sadb_x_nat_t_port);
}
skb = alloc_skb(size + 16, GFP_ATOMIC);
if (skb == NULL)
return ERR_PTR(-ENOBUFS);
/* call should fill header later */
hdr = (struct sadb_msg *) skb_put(skb, sizeof(struct sadb_msg));
memset(hdr, 0, size); /* XXX do we need this ? */
hdr->sadb_msg_len = size / sizeof(uint64_t);
/* sa */
sa = (struct sadb_sa *) skb_put(skb, sizeof(struct sadb_sa));
sa->sadb_sa_len = sizeof(struct sadb_sa)/sizeof(uint64_t);
sa->sadb_sa_exttype = SADB_EXT_SA;
sa->sadb_sa_spi = x->id.spi;
sa->sadb_sa_replay = x->props.replay_window;
switch (x->km.state) {
case XFRM_STATE_VALID:
sa->sadb_sa_state = x->km.dying ?
SADB_SASTATE_DYING : SADB_SASTATE_MATURE;
break;
case XFRM_STATE_ACQ:
sa->sadb_sa_state = SADB_SASTATE_LARVAL;
break;
default:
sa->sadb_sa_state = SADB_SASTATE_DEAD;
break;
}
sa->sadb_sa_auth = 0;
if (x->aalg) {
struct xfrm_algo_desc *a = xfrm_aalg_get_byname(x->aalg->alg_name, 0);
sa->sadb_sa_auth = (a && a->pfkey_supported) ?
a->desc.sadb_alg_id : 0;
}
sa->sadb_sa_encrypt = 0;
BUG_ON(x->ealg && x->calg);
if (x->ealg) {
struct xfrm_algo_desc *a = xfrm_ealg_get_byname(x->ealg->alg_name, 0);
sa->sadb_sa_encrypt = (a && a->pfkey_supported) ?
a->desc.sadb_alg_id : 0;
}
/* KAME compatible: sadb_sa_encrypt is overloaded with calg id */
if (x->calg) {
struct xfrm_algo_desc *a = xfrm_calg_get_byname(x->calg->alg_name, 0);
sa->sadb_sa_encrypt = (a && a->pfkey_supported) ?
a->desc.sadb_alg_id : 0;
}
sa->sadb_sa_flags = 0;
if (x->props.flags & XFRM_STATE_NOECN)
sa->sadb_sa_flags |= SADB_SAFLAGS_NOECN;
if (x->props.flags & XFRM_STATE_DECAP_DSCP)
sa->sadb_sa_flags |= SADB_SAFLAGS_DECAP_DSCP;
if (x->props.flags & XFRM_STATE_NOPMTUDISC)
sa->sadb_sa_flags |= SADB_SAFLAGS_NOPMTUDISC;
/* hard time */
if (hsc & 2) {
lifetime = (struct sadb_lifetime *) skb_put(skb,
sizeof(struct sadb_lifetime));
lifetime->sadb_lifetime_len =
sizeof(struct sadb_lifetime)/sizeof(uint64_t);
lifetime->sadb_lifetime_exttype = SADB_EXT_LIFETIME_HARD;
lifetime->sadb_lifetime_allocations = _X2KEY(x->lft.hard_packet_limit);
lifetime->sadb_lifetime_bytes = _X2KEY(x->lft.hard_byte_limit);
lifetime->sadb_lifetime_addtime = x->lft.hard_add_expires_seconds;
lifetime->sadb_lifetime_usetime = x->lft.hard_use_expires_seconds;
}
/* soft time */
if (hsc & 1) {
lifetime = (struct sadb_lifetime *) skb_put(skb,
sizeof(struct sadb_lifetime));
lifetime->sadb_lifetime_len =
sizeof(struct sadb_lifetime)/sizeof(uint64_t);
lifetime->sadb_lifetime_exttype = SADB_EXT_LIFETIME_SOFT;
lifetime->sadb_lifetime_allocations = _X2KEY(x->lft.soft_packet_limit);
lifetime->sadb_lifetime_bytes = _X2KEY(x->lft.soft_byte_limit);
lifetime->sadb_lifetime_addtime = x->lft.soft_add_expires_seconds;
lifetime->sadb_lifetime_usetime = x->lft.soft_use_expires_seconds;
}
/* current time */
lifetime = (struct sadb_lifetime *) skb_put(skb,
sizeof(struct sadb_lifetime));
lifetime->sadb_lifetime_len =
sizeof(struct sadb_lifetime)/sizeof(uint64_t);
lifetime->sadb_lifetime_exttype = SADB_EXT_LIFETIME_CURRENT;
lifetime->sadb_lifetime_allocations = x->curlft.packets;
lifetime->sadb_lifetime_bytes = x->curlft.bytes;
lifetime->sadb_lifetime_addtime = x->curlft.add_time;
lifetime->sadb_lifetime_usetime = x->curlft.use_time;
/* src address */
addr = (struct sadb_address*) skb_put(skb,
sizeof(struct sadb_address)+sockaddr_size);
addr->sadb_address_len =
(sizeof(struct sadb_address)+sockaddr_size)/
sizeof(uint64_t);
addr->sadb_address_exttype = SADB_EXT_ADDRESS_SRC;
/* "if the ports are non-zero, then the sadb_address_proto field,
normally zero, MUST be filled in with the transport
protocol's number." - RFC2367 */
addr->sadb_address_proto = 0;
addr->sadb_address_reserved = 0;
addr->sadb_address_prefixlen =
pfkey_sockaddr_fill(&x->props.saddr, 0,
(struct sockaddr *) (addr + 1),
x->props.family);
if (!addr->sadb_address_prefixlen)
BUG();
/* dst address */
addr = (struct sadb_address*) skb_put(skb,
sizeof(struct sadb_address)+sockaddr_size);
addr->sadb_address_len =
(sizeof(struct sadb_address)+sockaddr_size)/
sizeof(uint64_t);
addr->sadb_address_exttype = SADB_EXT_ADDRESS_DST;
addr->sadb_address_proto = 0;
addr->sadb_address_reserved = 0;
addr->sadb_address_prefixlen =
pfkey_sockaddr_fill(&x->id.daddr, 0,
(struct sockaddr *) (addr + 1),
x->props.family);
if (!addr->sadb_address_prefixlen)
BUG();
if (!xfrm_addr_equal(&x->sel.saddr, &x->props.saddr,
x->props.family)) {
addr = (struct sadb_address*) skb_put(skb,
sizeof(struct sadb_address)+sockaddr_size);
addr->sadb_address_len =
(sizeof(struct sadb_address)+sockaddr_size)/
sizeof(uint64_t);
addr->sadb_address_exttype = SADB_EXT_ADDRESS_PROXY;
addr->sadb_address_proto =
pfkey_proto_from_xfrm(x->sel.proto);
addr->sadb_address_prefixlen = x->sel.prefixlen_s;
addr->sadb_address_reserved = 0;
pfkey_sockaddr_fill(&x->sel.saddr, x->sel.sport,
(struct sockaddr *) (addr + 1),
x->props.family);
}
/* auth key */
if (add_keys && auth_key_size) {
key = (struct sadb_key *) skb_put(skb,
sizeof(struct sadb_key)+auth_key_size);
key->sadb_key_len = (sizeof(struct sadb_key) + auth_key_size) /
sizeof(uint64_t);
key->sadb_key_exttype = SADB_EXT_KEY_AUTH;
key->sadb_key_bits = x->aalg->alg_key_len;
key->sadb_key_reserved = 0;
memcpy(key + 1, x->aalg->alg_key, (x->aalg->alg_key_len+7)/8);
}
/* encrypt key */
if (add_keys && encrypt_key_size) {
key = (struct sadb_key *) skb_put(skb,
sizeof(struct sadb_key)+encrypt_key_size);
key->sadb_key_len = (sizeof(struct sadb_key) +
encrypt_key_size) / sizeof(uint64_t);
key->sadb_key_exttype = SADB_EXT_KEY_ENCRYPT;
key->sadb_key_bits = x->ealg->alg_key_len;
key->sadb_key_reserved = 0;
memcpy(key + 1, x->ealg->alg_key,
(x->ealg->alg_key_len+7)/8);
}
/* sa */
sa2 = (struct sadb_x_sa2 *) skb_put(skb, sizeof(struct sadb_x_sa2));
sa2->sadb_x_sa2_len = sizeof(struct sadb_x_sa2)/sizeof(uint64_t);
sa2->sadb_x_sa2_exttype = SADB_X_EXT_SA2;
if ((mode = pfkey_mode_from_xfrm(x->props.mode)) < 0) {
kfree_skb(skb);
return ERR_PTR(-EINVAL);
}
sa2->sadb_x_sa2_mode = mode;
sa2->sadb_x_sa2_reserved1 = 0;
sa2->sadb_x_sa2_reserved2 = 0;
sa2->sadb_x_sa2_sequence = 0;
sa2->sadb_x_sa2_reqid = x->props.reqid;
if (natt && natt->encap_type) {
struct sadb_x_nat_t_type *n_type;
struct sadb_x_nat_t_port *n_port;
/* type */
n_type = (struct sadb_x_nat_t_type*) skb_put(skb, sizeof(*n_type));
n_type->sadb_x_nat_t_type_len = sizeof(*n_type)/sizeof(uint64_t);
n_type->sadb_x_nat_t_type_exttype = SADB_X_EXT_NAT_T_TYPE;
n_type->sadb_x_nat_t_type_type = natt->encap_type;
n_type->sadb_x_nat_t_type_reserved[0] = 0;
n_type->sadb_x_nat_t_type_reserved[1] = 0;
n_type->sadb_x_nat_t_type_reserved[2] = 0;
/* source port */
n_port = (struct sadb_x_nat_t_port*) skb_put(skb, sizeof (*n_port));
n_port->sadb_x_nat_t_port_len = sizeof(*n_port)/sizeof(uint64_t);
n_port->sadb_x_nat_t_port_exttype = SADB_X_EXT_NAT_T_SPORT;
n_port->sadb_x_nat_t_port_port = natt->encap_sport;
n_port->sadb_x_nat_t_port_reserved = 0;
/* dest port */
n_port = (struct sadb_x_nat_t_port*) skb_put(skb, sizeof (*n_port));
n_port->sadb_x_nat_t_port_len = sizeof(*n_port)/sizeof(uint64_t);
n_port->sadb_x_nat_t_port_exttype = SADB_X_EXT_NAT_T_DPORT;
n_port->sadb_x_nat_t_port_port = natt->encap_dport;
n_port->sadb_x_nat_t_port_reserved = 0;
}
/* security context */
if (xfrm_ctx) {