forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
l2tp_core.c
1719 lines (1445 loc) · 44.9 KB
/
l2tp_core.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-only
/* L2TP core.
*
* Copyright (c) 2008,2009,2010 Katalix Systems Ltd
*
* This file contains some code of the original L2TPv2 pppol2tp
* driver, which has the following copyright:
*
* Authors: Martijn van Oosterhout <[email protected]>
* James Chapman ([email protected])
* Contributors:
* Michal Ostrowski <[email protected]>
* Arnaldo Carvalho de Melo <[email protected]>
* David S. Miller ([email protected])
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/string.h>
#include <linux/list.h>
#include <linux/rculist.h>
#include <linux/uaccess.h>
#include <linux/kernel.h>
#include <linux/spinlock.h>
#include <linux/kthread.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/errno.h>
#include <linux/jiffies.h>
#include <linux/netdevice.h>
#include <linux/net.h>
#include <linux/inetdevice.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/udp.h>
#include <linux/l2tp.h>
#include <linux/hash.h>
#include <linux/sort.h>
#include <linux/file.h>
#include <linux/nsproxy.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/dst.h>
#include <net/ip.h>
#include <net/udp.h>
#include <net/udp_tunnel.h>
#include <net/inet_common.h>
#include <net/xfrm.h>
#include <net/protocol.h>
#include <net/inet6_connection_sock.h>
#include <net/inet_ecn.h>
#include <net/ip6_route.h>
#include <net/ip6_checksum.h>
#include <asm/byteorder.h>
#include <linux/atomic.h>
#include "l2tp_core.h"
#include "trace.h"
#define CREATE_TRACE_POINTS
#include "trace.h"
#define L2TP_DRV_VERSION "V2.0"
/* L2TP header constants */
#define L2TP_HDRFLAG_T 0x8000
#define L2TP_HDRFLAG_L 0x4000
#define L2TP_HDRFLAG_S 0x0800
#define L2TP_HDRFLAG_O 0x0200
#define L2TP_HDRFLAG_P 0x0100
#define L2TP_HDR_VER_MASK 0x000F
#define L2TP_HDR_VER_2 0x0002
#define L2TP_HDR_VER_3 0x0003
/* L2TPv3 default L2-specific sublayer */
#define L2TP_SLFLAG_S 0x40000000
#define L2TP_SL_SEQ_MASK 0x00ffffff
#define L2TP_HDR_SIZE_MAX 14
/* Default trace flags */
#define L2TP_DEFAULT_DEBUG_FLAGS 0
/* Private data stored for received packets in the skb.
*/
struct l2tp_skb_cb {
u32 ns;
u16 has_seq;
u16 length;
unsigned long expires;
};
#define L2TP_SKB_CB(skb) ((struct l2tp_skb_cb *)&(skb)->cb[sizeof(struct inet_skb_parm)])
static struct workqueue_struct *l2tp_wq;
/* per-net private data for this module */
static unsigned int l2tp_net_id;
struct l2tp_net {
struct list_head l2tp_tunnel_list;
/* Lock for write access to l2tp_tunnel_list */
spinlock_t l2tp_tunnel_list_lock;
struct hlist_head l2tp_session_hlist[L2TP_HASH_SIZE_2];
/* Lock for write access to l2tp_session_hlist */
spinlock_t l2tp_session_hlist_lock;
};
#if IS_ENABLED(CONFIG_IPV6)
static bool l2tp_sk_is_v6(struct sock *sk)
{
return sk->sk_family == PF_INET6 &&
!ipv6_addr_v4mapped(&sk->sk_v6_daddr);
}
#endif
static inline struct l2tp_net *l2tp_pernet(const struct net *net)
{
return net_generic(net, l2tp_net_id);
}
/* Session hash global list for L2TPv3.
* The session_id SHOULD be random according to RFC3931, but several
* L2TP implementations use incrementing session_ids. So we do a real
* hash on the session_id, rather than a simple bitmask.
*/
static inline struct hlist_head *
l2tp_session_id_hash_2(struct l2tp_net *pn, u32 session_id)
{
return &pn->l2tp_session_hlist[hash_32(session_id, L2TP_HASH_BITS_2)];
}
/* Session hash list.
* The session_id SHOULD be random according to RFC2661, but several
* L2TP implementations (Cisco and Microsoft) use incrementing
* session_ids. So we do a real hash on the session_id, rather than a
* simple bitmask.
*/
static inline struct hlist_head *
l2tp_session_id_hash(struct l2tp_tunnel *tunnel, u32 session_id)
{
return &tunnel->session_hlist[hash_32(session_id, L2TP_HASH_BITS)];
}
static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel)
{
trace_free_tunnel(tunnel);
sock_put(tunnel->sock);
/* the tunnel is freed in the socket destructor */
}
static void l2tp_session_free(struct l2tp_session *session)
{
trace_free_session(session);
if (session->tunnel)
l2tp_tunnel_dec_refcount(session->tunnel);
kfree(session);
}
struct l2tp_tunnel *l2tp_sk_to_tunnel(struct sock *sk)
{
struct l2tp_tunnel *tunnel = sk->sk_user_data;
if (tunnel)
if (WARN_ON(tunnel->magic != L2TP_TUNNEL_MAGIC))
return NULL;
return tunnel;
}
EXPORT_SYMBOL_GPL(l2tp_sk_to_tunnel);
void l2tp_tunnel_inc_refcount(struct l2tp_tunnel *tunnel)
{
refcount_inc(&tunnel->ref_count);
}
EXPORT_SYMBOL_GPL(l2tp_tunnel_inc_refcount);
void l2tp_tunnel_dec_refcount(struct l2tp_tunnel *tunnel)
{
if (refcount_dec_and_test(&tunnel->ref_count))
l2tp_tunnel_free(tunnel);
}
EXPORT_SYMBOL_GPL(l2tp_tunnel_dec_refcount);
void l2tp_session_inc_refcount(struct l2tp_session *session)
{
refcount_inc(&session->ref_count);
}
EXPORT_SYMBOL_GPL(l2tp_session_inc_refcount);
void l2tp_session_dec_refcount(struct l2tp_session *session)
{
if (refcount_dec_and_test(&session->ref_count))
l2tp_session_free(session);
}
EXPORT_SYMBOL_GPL(l2tp_session_dec_refcount);
/* Lookup a tunnel. A new reference is held on the returned tunnel. */
struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id)
{
const struct l2tp_net *pn = l2tp_pernet(net);
struct l2tp_tunnel *tunnel;
rcu_read_lock_bh();
list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
if (tunnel->tunnel_id == tunnel_id &&
refcount_inc_not_zero(&tunnel->ref_count)) {
rcu_read_unlock_bh();
return tunnel;
}
}
rcu_read_unlock_bh();
return NULL;
}
EXPORT_SYMBOL_GPL(l2tp_tunnel_get);
struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth)
{
const struct l2tp_net *pn = l2tp_pernet(net);
struct l2tp_tunnel *tunnel;
int count = 0;
rcu_read_lock_bh();
list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
if (++count > nth &&
refcount_inc_not_zero(&tunnel->ref_count)) {
rcu_read_unlock_bh();
return tunnel;
}
}
rcu_read_unlock_bh();
return NULL;
}
EXPORT_SYMBOL_GPL(l2tp_tunnel_get_nth);
struct l2tp_session *l2tp_tunnel_get_session(struct l2tp_tunnel *tunnel,
u32 session_id)
{
struct hlist_head *session_list;
struct l2tp_session *session;
session_list = l2tp_session_id_hash(tunnel, session_id);
read_lock_bh(&tunnel->hlist_lock);
hlist_for_each_entry(session, session_list, hlist)
if (session->session_id == session_id) {
l2tp_session_inc_refcount(session);
read_unlock_bh(&tunnel->hlist_lock);
return session;
}
read_unlock_bh(&tunnel->hlist_lock);
return NULL;
}
EXPORT_SYMBOL_GPL(l2tp_tunnel_get_session);
struct l2tp_session *l2tp_session_get(const struct net *net, u32 session_id)
{
struct hlist_head *session_list;
struct l2tp_session *session;
session_list = l2tp_session_id_hash_2(l2tp_pernet(net), session_id);
rcu_read_lock_bh();
hlist_for_each_entry_rcu(session, session_list, global_hlist)
if (session->session_id == session_id) {
l2tp_session_inc_refcount(session);
rcu_read_unlock_bh();
return session;
}
rcu_read_unlock_bh();
return NULL;
}
EXPORT_SYMBOL_GPL(l2tp_session_get);
struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth)
{
int hash;
struct l2tp_session *session;
int count = 0;
read_lock_bh(&tunnel->hlist_lock);
for (hash = 0; hash < L2TP_HASH_SIZE; hash++) {
hlist_for_each_entry(session, &tunnel->session_hlist[hash], hlist) {
if (++count > nth) {
l2tp_session_inc_refcount(session);
read_unlock_bh(&tunnel->hlist_lock);
return session;
}
}
}
read_unlock_bh(&tunnel->hlist_lock);
return NULL;
}
EXPORT_SYMBOL_GPL(l2tp_session_get_nth);
/* Lookup a session by interface name.
* This is very inefficient but is only used by management interfaces.
*/
struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net,
const char *ifname)
{
struct l2tp_net *pn = l2tp_pernet(net);
int hash;
struct l2tp_session *session;
rcu_read_lock_bh();
for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++) {
hlist_for_each_entry_rcu(session, &pn->l2tp_session_hlist[hash], global_hlist) {
if (!strcmp(session->ifname, ifname)) {
l2tp_session_inc_refcount(session);
rcu_read_unlock_bh();
return session;
}
}
}
rcu_read_unlock_bh();
return NULL;
}
EXPORT_SYMBOL_GPL(l2tp_session_get_by_ifname);
int l2tp_session_register(struct l2tp_session *session,
struct l2tp_tunnel *tunnel)
{
struct l2tp_session *session_walk;
struct hlist_head *g_head;
struct hlist_head *head;
struct l2tp_net *pn;
int err;
head = l2tp_session_id_hash(tunnel, session->session_id);
write_lock_bh(&tunnel->hlist_lock);
if (!tunnel->acpt_newsess) {
err = -ENODEV;
goto err_tlock;
}
hlist_for_each_entry(session_walk, head, hlist)
if (session_walk->session_id == session->session_id) {
err = -EEXIST;
goto err_tlock;
}
if (tunnel->version == L2TP_HDR_VER_3) {
pn = l2tp_pernet(tunnel->l2tp_net);
g_head = l2tp_session_id_hash_2(pn, session->session_id);
spin_lock_bh(&pn->l2tp_session_hlist_lock);
/* IP encap expects session IDs to be globally unique, while
* UDP encap doesn't.
*/
hlist_for_each_entry(session_walk, g_head, global_hlist)
if (session_walk->session_id == session->session_id &&
(session_walk->tunnel->encap == L2TP_ENCAPTYPE_IP ||
tunnel->encap == L2TP_ENCAPTYPE_IP)) {
err = -EEXIST;
goto err_tlock_pnlock;
}
l2tp_tunnel_inc_refcount(tunnel);
hlist_add_head_rcu(&session->global_hlist, g_head);
spin_unlock_bh(&pn->l2tp_session_hlist_lock);
} else {
l2tp_tunnel_inc_refcount(tunnel);
}
hlist_add_head(&session->hlist, head);
write_unlock_bh(&tunnel->hlist_lock);
trace_register_session(session);
return 0;
err_tlock_pnlock:
spin_unlock_bh(&pn->l2tp_session_hlist_lock);
err_tlock:
write_unlock_bh(&tunnel->hlist_lock);
return err;
}
EXPORT_SYMBOL_GPL(l2tp_session_register);
/*****************************************************************************
* Receive data handling
*****************************************************************************/
/* Queue a skb in order. We come here only if the skb has an L2TP sequence
* number.
*/
static void l2tp_recv_queue_skb(struct l2tp_session *session, struct sk_buff *skb)
{
struct sk_buff *skbp;
struct sk_buff *tmp;
u32 ns = L2TP_SKB_CB(skb)->ns;
spin_lock_bh(&session->reorder_q.lock);
skb_queue_walk_safe(&session->reorder_q, skbp, tmp) {
if (L2TP_SKB_CB(skbp)->ns > ns) {
__skb_queue_before(&session->reorder_q, skbp, skb);
atomic_long_inc(&session->stats.rx_oos_packets);
goto out;
}
}
__skb_queue_tail(&session->reorder_q, skb);
out:
spin_unlock_bh(&session->reorder_q.lock);
}
/* Dequeue a single skb.
*/
static void l2tp_recv_dequeue_skb(struct l2tp_session *session, struct sk_buff *skb)
{
struct l2tp_tunnel *tunnel = session->tunnel;
int length = L2TP_SKB_CB(skb)->length;
/* We're about to requeue the skb, so return resources
* to its current owner (a socket receive buffer).
*/
skb_orphan(skb);
atomic_long_inc(&tunnel->stats.rx_packets);
atomic_long_add(length, &tunnel->stats.rx_bytes);
atomic_long_inc(&session->stats.rx_packets);
atomic_long_add(length, &session->stats.rx_bytes);
if (L2TP_SKB_CB(skb)->has_seq) {
/* Bump our Nr */
session->nr++;
session->nr &= session->nr_max;
trace_session_seqnum_update(session);
}
/* call private receive handler */
if (session->recv_skb)
(*session->recv_skb)(session, skb, L2TP_SKB_CB(skb)->length);
else
kfree_skb(skb);
}
/* Dequeue skbs from the session's reorder_q, subject to packet order.
* Skbs that have been in the queue for too long are simply discarded.
*/
static void l2tp_recv_dequeue(struct l2tp_session *session)
{
struct sk_buff *skb;
struct sk_buff *tmp;
/* If the pkt at the head of the queue has the nr that we
* expect to send up next, dequeue it and any other
* in-sequence packets behind it.
*/
start:
spin_lock_bh(&session->reorder_q.lock);
skb_queue_walk_safe(&session->reorder_q, skb, tmp) {
struct l2tp_skb_cb *cb = L2TP_SKB_CB(skb);
/* If the packet has been pending on the queue for too long, discard it */
if (time_after(jiffies, cb->expires)) {
atomic_long_inc(&session->stats.rx_seq_discards);
atomic_long_inc(&session->stats.rx_errors);
trace_session_pkt_expired(session, cb->ns);
session->reorder_skip = 1;
__skb_unlink(skb, &session->reorder_q);
kfree_skb(skb);
continue;
}
if (cb->has_seq) {
if (session->reorder_skip) {
session->reorder_skip = 0;
session->nr = cb->ns;
trace_session_seqnum_reset(session);
}
if (cb->ns != session->nr)
goto out;
}
__skb_unlink(skb, &session->reorder_q);
/* Process the skb. We release the queue lock while we
* do so to let other contexts process the queue.
*/
spin_unlock_bh(&session->reorder_q.lock);
l2tp_recv_dequeue_skb(session, skb);
goto start;
}
out:
spin_unlock_bh(&session->reorder_q.lock);
}
static int l2tp_seq_check_rx_window(struct l2tp_session *session, u32 nr)
{
u32 nws;
if (nr >= session->nr)
nws = nr - session->nr;
else
nws = (session->nr_max + 1) - (session->nr - nr);
return nws < session->nr_window_size;
}
/* If packet has sequence numbers, queue it if acceptable. Returns 0 if
* acceptable, else non-zero.
*/
static int l2tp_recv_data_seq(struct l2tp_session *session, struct sk_buff *skb)
{
struct l2tp_skb_cb *cb = L2TP_SKB_CB(skb);
if (!l2tp_seq_check_rx_window(session, cb->ns)) {
/* Packet sequence number is outside allowed window.
* Discard it.
*/
trace_session_pkt_outside_rx_window(session, cb->ns);
goto discard;
}
if (session->reorder_timeout != 0) {
/* Packet reordering enabled. Add skb to session's
* reorder queue, in order of ns.
*/
l2tp_recv_queue_skb(session, skb);
goto out;
}
/* Packet reordering disabled. Discard out-of-sequence packets, while
* tracking the number if in-sequence packets after the first OOS packet
* is seen. After nr_oos_count_max in-sequence packets, reset the
* sequence number to re-enable packet reception.
*/
if (cb->ns == session->nr) {
skb_queue_tail(&session->reorder_q, skb);
} else {
u32 nr_oos = cb->ns;
u32 nr_next = (session->nr_oos + 1) & session->nr_max;
if (nr_oos == nr_next)
session->nr_oos_count++;
else
session->nr_oos_count = 0;
session->nr_oos = nr_oos;
if (session->nr_oos_count > session->nr_oos_count_max) {
session->reorder_skip = 1;
}
if (!session->reorder_skip) {
atomic_long_inc(&session->stats.rx_seq_discards);
trace_session_pkt_oos(session, cb->ns);
goto discard;
}
skb_queue_tail(&session->reorder_q, skb);
}
out:
return 0;
discard:
return 1;
}
/* Do receive processing of L2TP data frames. We handle both L2TPv2
* and L2TPv3 data frames here.
*
* L2TPv2 Data Message Header
*
* 0 1 2 3
* 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
* |T|L|x|x|S|x|O|P|x|x|x|x| Ver | Length (opt) |
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
* | Tunnel ID | Session ID |
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
* | Ns (opt) | Nr (opt) |
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
* | Offset Size (opt) | Offset pad... (opt)
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*
* Data frames are marked by T=0. All other fields are the same as
* those in L2TP control frames.
*
* L2TPv3 Data Message Header
*
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
* | L2TP Session Header |
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
* | L2-Specific Sublayer |
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
* | Tunnel Payload ...
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*
* L2TPv3 Session Header Over IP
*
* 0 1 2 3
* 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
* | Session ID |
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
* | Cookie (optional, maximum 64 bits)...
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
* |
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*
* L2TPv3 L2-Specific Sublayer Format
*
* 0 1 2 3
* 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
* |x|S|x|x|x|x|x|x| Sequence Number |
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*
* Cookie value and sublayer format are negotiated with the peer when
* the session is set up. Unlike L2TPv2, we do not need to parse the
* packet header to determine if optional fields are present.
*
* Caller must already have parsed the frame and determined that it is
* a data (not control) frame before coming here. Fields up to the
* session-id have already been parsed and ptr points to the data
* after the session-id.
*/
void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
unsigned char *ptr, unsigned char *optr, u16 hdrflags,
int length)
{
struct l2tp_tunnel *tunnel = session->tunnel;
int offset;
/* Parse and check optional cookie */
if (session->peer_cookie_len > 0) {
if (memcmp(ptr, &session->peer_cookie[0], session->peer_cookie_len)) {
pr_debug_ratelimited("%s: cookie mismatch (%u/%u). Discarding.\n",
tunnel->name, tunnel->tunnel_id,
session->session_id);
atomic_long_inc(&session->stats.rx_cookie_discards);
goto discard;
}
ptr += session->peer_cookie_len;
}
/* Handle the optional sequence numbers. Sequence numbers are
* in different places for L2TPv2 and L2TPv3.
*
* If we are the LAC, enable/disable sequence numbers under
* the control of the LNS. If no sequence numbers present but
* we were expecting them, discard frame.
*/
L2TP_SKB_CB(skb)->has_seq = 0;
if (tunnel->version == L2TP_HDR_VER_2) {
if (hdrflags & L2TP_HDRFLAG_S) {
/* Store L2TP info in the skb */
L2TP_SKB_CB(skb)->ns = ntohs(*(__be16 *)ptr);
L2TP_SKB_CB(skb)->has_seq = 1;
ptr += 2;
/* Skip past nr in the header */
ptr += 2;
}
} else if (session->l2specific_type == L2TP_L2SPECTYPE_DEFAULT) {
u32 l2h = ntohl(*(__be32 *)ptr);
if (l2h & 0x40000000) {
/* Store L2TP info in the skb */
L2TP_SKB_CB(skb)->ns = l2h & 0x00ffffff;
L2TP_SKB_CB(skb)->has_seq = 1;
}
ptr += 4;
}
if (L2TP_SKB_CB(skb)->has_seq) {
/* Received a packet with sequence numbers. If we're the LAC,
* check if we sre sending sequence numbers and if not,
* configure it so.
*/
if (!session->lns_mode && !session->send_seq) {
trace_session_seqnum_lns_enable(session);
session->send_seq = 1;
l2tp_session_set_header_len(session, tunnel->version);
}
} else {
/* No sequence numbers.
* If user has configured mandatory sequence numbers, discard.
*/
if (session->recv_seq) {
pr_debug_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n",
session->name);
atomic_long_inc(&session->stats.rx_seq_discards);
goto discard;
}
/* If we're the LAC and we're sending sequence numbers, the
* LNS has requested that we no longer send sequence numbers.
* If we're the LNS and we're sending sequence numbers, the
* LAC is broken. Discard the frame.
*/
if (!session->lns_mode && session->send_seq) {
trace_session_seqnum_lns_disable(session);
session->send_seq = 0;
l2tp_session_set_header_len(session, tunnel->version);
} else if (session->send_seq) {
pr_debug_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n",
session->name);
atomic_long_inc(&session->stats.rx_seq_discards);
goto discard;
}
}
/* Session data offset is defined only for L2TPv2 and is
* indicated by an optional 16-bit value in the header.
*/
if (tunnel->version == L2TP_HDR_VER_2) {
/* If offset bit set, skip it. */
if (hdrflags & L2TP_HDRFLAG_O) {
offset = ntohs(*(__be16 *)ptr);
ptr += 2 + offset;
}
}
offset = ptr - optr;
if (!pskb_may_pull(skb, offset))
goto discard;
__skb_pull(skb, offset);
/* Prepare skb for adding to the session's reorder_q. Hold
* packets for max reorder_timeout or 1 second if not
* reordering.
*/
L2TP_SKB_CB(skb)->length = length;
L2TP_SKB_CB(skb)->expires = jiffies +
(session->reorder_timeout ? session->reorder_timeout : HZ);
/* Add packet to the session's receive queue. Reordering is done here, if
* enabled. Saved L2TP protocol info is stored in skb->sb[].
*/
if (L2TP_SKB_CB(skb)->has_seq) {
if (l2tp_recv_data_seq(session, skb))
goto discard;
} else {
/* No sequence numbers. Add the skb to the tail of the
* reorder queue. This ensures that it will be
* delivered after all previous sequenced skbs.
*/
skb_queue_tail(&session->reorder_q, skb);
}
/* Try to dequeue as many skbs from reorder_q as we can. */
l2tp_recv_dequeue(session);
return;
discard:
atomic_long_inc(&session->stats.rx_errors);
kfree_skb(skb);
}
EXPORT_SYMBOL_GPL(l2tp_recv_common);
/* Drop skbs from the session's reorder_q
*/
static void l2tp_session_queue_purge(struct l2tp_session *session)
{
struct sk_buff *skb = NULL;
while ((skb = skb_dequeue(&session->reorder_q))) {
atomic_long_inc(&session->stats.rx_errors);
kfree_skb(skb);
}
}
/* Internal UDP receive frame. Do the real work of receiving an L2TP data frame
* here. The skb is not on a list when we get here.
* Returns 0 if the packet was a data packet and was successfully passed on.
* Returns 1 if the packet was not a good data packet and could not be
* forwarded. All such packets are passed up to userspace to deal with.
*/
static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb)
{
struct l2tp_session *session = NULL;
unsigned char *ptr, *optr;
u16 hdrflags;
u32 tunnel_id, session_id;
u16 version;
int length;
/* UDP has verified checksum */
/* UDP always verifies the packet length. */
__skb_pull(skb, sizeof(struct udphdr));
/* Short packet? */
if (!pskb_may_pull(skb, L2TP_HDR_SIZE_MAX)) {
pr_debug_ratelimited("%s: recv short packet (len=%d)\n",
tunnel->name, skb->len);
goto invalid;
}
/* Point to L2TP header */
optr = skb->data;
ptr = skb->data;
/* Get L2TP header flags */
hdrflags = ntohs(*(__be16 *)ptr);
/* Check protocol version */
version = hdrflags & L2TP_HDR_VER_MASK;
if (version != tunnel->version) {
pr_debug_ratelimited("%s: recv protocol version mismatch: got %d expected %d\n",
tunnel->name, version, tunnel->version);
goto invalid;
}
/* Get length of L2TP packet */
length = skb->len;
/* If type is control packet, it is handled by userspace. */
if (hdrflags & L2TP_HDRFLAG_T)
goto pass;
/* Skip flags */
ptr += 2;
if (tunnel->version == L2TP_HDR_VER_2) {
/* If length is present, skip it */
if (hdrflags & L2TP_HDRFLAG_L)
ptr += 2;
/* Extract tunnel and session ID */
tunnel_id = ntohs(*(__be16 *)ptr);
ptr += 2;
session_id = ntohs(*(__be16 *)ptr);
ptr += 2;
} else {
ptr += 2; /* skip reserved bits */
tunnel_id = tunnel->tunnel_id;
session_id = ntohl(*(__be32 *)ptr);
ptr += 4;
}
/* Find the session context */
session = l2tp_tunnel_get_session(tunnel, session_id);
if (!session || !session->recv_skb) {
if (session)
l2tp_session_dec_refcount(session);
/* Not found? Pass to userspace to deal with */
pr_debug_ratelimited("%s: no session found (%u/%u). Passing up.\n",
tunnel->name, tunnel_id, session_id);
goto pass;
}
if (tunnel->version == L2TP_HDR_VER_3 &&
l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) {
l2tp_session_dec_refcount(session);
goto invalid;
}
l2tp_recv_common(session, skb, ptr, optr, hdrflags, length);
l2tp_session_dec_refcount(session);
return 0;
invalid:
atomic_long_inc(&tunnel->stats.rx_invalid);
pass:
/* Put UDP header back */
__skb_push(skb, sizeof(struct udphdr));
return 1;
}
/* UDP encapsulation receive handler. See net/ipv4/udp.c.
* Return codes:
* 0 : success.
* <0: error
* >0: skb should be passed up to userspace as UDP.
*/
int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
{
struct l2tp_tunnel *tunnel;
/* Note that this is called from the encap_rcv hook inside an
* RCU-protected region, but without the socket being locked.
* Hence we use rcu_dereference_sk_user_data to access the
* tunnel data structure rather the usual l2tp_sk_to_tunnel
* accessor function.
*/
tunnel = rcu_dereference_sk_user_data(sk);
if (!tunnel)
goto pass_up;
if (WARN_ON(tunnel->magic != L2TP_TUNNEL_MAGIC))
goto pass_up;
if (l2tp_udp_recv_core(tunnel, skb))
goto pass_up;
return 0;
pass_up:
return 1;
}
EXPORT_SYMBOL_GPL(l2tp_udp_encap_recv);
/************************************************************************
* Transmit handling
***********************************************************************/
/* Build an L2TP header for the session into the buffer provided.
*/
static int l2tp_build_l2tpv2_header(struct l2tp_session *session, void *buf)
{
struct l2tp_tunnel *tunnel = session->tunnel;
__be16 *bufp = buf;
__be16 *optr = buf;
u16 flags = L2TP_HDR_VER_2;
u32 tunnel_id = tunnel->peer_tunnel_id;
u32 session_id = session->peer_session_id;
if (session->send_seq)
flags |= L2TP_HDRFLAG_S;
/* Setup L2TP header. */
*bufp++ = htons(flags);
*bufp++ = htons(tunnel_id);
*bufp++ = htons(session_id);
if (session->send_seq) {
*bufp++ = htons(session->ns);
*bufp++ = 0;
session->ns++;
session->ns &= 0xffff;
trace_session_seqnum_update(session);
}
return bufp - optr;
}
static int l2tp_build_l2tpv3_header(struct l2tp_session *session, void *buf)
{
struct l2tp_tunnel *tunnel = session->tunnel;
char *bufp = buf;
char *optr = bufp;
/* Setup L2TP header. The header differs slightly for UDP and
* IP encapsulations. For UDP, there is 4 bytes of flags.
*/
if (tunnel->encap == L2TP_ENCAPTYPE_UDP) {
u16 flags = L2TP_HDR_VER_3;
*((__be16 *)bufp) = htons(flags);
bufp += 2;
*((__be16 *)bufp) = 0;
bufp += 2;
}
*((__be32 *)bufp) = htonl(session->peer_session_id);
bufp += 4;
if (session->cookie_len) {
memcpy(bufp, &session->cookie[0], session->cookie_len);
bufp += session->cookie_len;
}
if (session->l2specific_type == L2TP_L2SPECTYPE_DEFAULT) {
u32 l2h = 0;
if (session->send_seq) {
l2h = 0x40000000 | session->ns;
session->ns++;
session->ns &= 0xffffff;
trace_session_seqnum_update(session);
}
*((__be32 *)bufp) = htonl(l2h);
bufp += 4;
}
return bufp - optr;
}
/* Queue the packet to IP for output: tunnel socket lock must be held */
static int l2tp_xmit_queue(struct l2tp_tunnel *tunnel, struct sk_buff *skb, struct flowi *fl)
{
int err;