summaryrefslogtreecommitdiffstats
path: root/include/net/xfrm.h
blob: e144a25814bd654628c4f4229f0144d02038b6c1 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
#ifndef _NET_XFRM_H
#define _NET_XFRM_H

#include <linux/compiler.h>
#include <linux/in.h>
#include <linux/xfrm.h>
#include <linux/spinlock.h>
#include <linux/list.h>
#include <linux/skbuff.h>
#include <linux/socket.h>
#include <linux/pfkeyv2.h>
#include <linux/ipsec.h>
#include <linux/in6.h>
#include <linux/mutex.h>

#include <net/sock.h>
#include <net/dst.h>
#include <net/route.h>
#include <net/ipv6.h>
#include <net/ip6_fib.h>

#define XFRM_ALIGN8(len)	(((len) + 7) & ~7)
#define MODULE_ALIAS_XFRM_MODE(family, encap) \
	MODULE_ALIAS("xfrm-mode-" __stringify(family) "-" __stringify(encap))

extern struct sock *xfrm_nl;
extern u32 sysctl_xfrm_aevent_etime;
extern u32 sysctl_xfrm_aevent_rseqth;

extern struct mutex xfrm_cfg_mutex;

/* Organization of SPD aka "XFRM rules"
   ------------------------------------

   Basic objects:
   - policy rule, struct xfrm_policy (=SPD entry)
   - bundle of transformations, struct dst_entry == struct xfrm_dst (=SA bundle)
   - instance of a transformer, struct xfrm_state (=SA)
   - template to clone xfrm_state, struct xfrm_tmpl

   SPD is plain linear list of xfrm_policy rules, ordered by priority.
   (To be compatible with existing pfkeyv2 implementations,
   many rules with priority of 0x7fffffff are allowed to exist and
   such rules are ordered in an unpredictable way, thanks to bsd folks.)

   Lookup is plain linear search until the first match with selector.

   If "action" is "block", then we prohibit the flow, otherwise:
   if "xfrms_nr" is zero, the flow passes untransformed. Otherwise,
   policy entry has list of up to XFRM_MAX_DEPTH transformations,
   described by templates xfrm_tmpl. Each template is resolved
   to a complete xfrm_state (see below) and we pack bundle of transformations
   to a dst_entry returned to requestor.

   dst -. xfrm  .-> xfrm_state #1
    |---. child .-> dst -. xfrm .-> xfrm_state #2
                     |---. child .-> dst -. xfrm .-> xfrm_state #3
                                      |---. child .-> NULL

   Bundles are cached at xrfm_policy struct (field ->bundles).


   Resolution of xrfm_tmpl
   -----------------------
   Template contains:
   1. ->mode		Mode: transport or tunnel
   2. ->id.proto	Protocol: AH/ESP/IPCOMP
   3. ->id.daddr	Remote tunnel endpoint, ignored for transport mode.
      Q: allow to resolve security gateway?
   4. ->id.spi          If not zero, static SPI.
   5. ->saddr		Local tunnel endpoint, ignored for transport mode.
   6. ->algos		List of allowed algos. Plain bitmask now.
      Q: ealgos, aalgos, calgos. What a mess...
   7. ->share		Sharing mode.
      Q: how to implement private sharing mode? To add struct sock* to
      flow id?

   Having this template we search through SAD searching for entries
   with appropriate mode/proto/algo, permitted by selector.
   If no appropriate entry found, it is requested from key manager.

   PROBLEMS:
   Q: How to find all the bundles referring to a physical path for
      PMTU discovery? Seems, dst should contain list of all parents...
      and enter to infinite locking hierarchy disaster.
      No! It is easier, we will not search for them, let them find us.
      We add genid to each dst plus pointer to genid of raw IP route,
      pmtu disc will update pmtu on raw IP route and increase its genid.
      dst_check() will see this for top level and trigger resyncing
      metrics. Plus, it will be made via sk->sk_dst_cache. Solved.
 */

/* Full description of state of transformer. */
struct xfrm_state
{
	/* Note: bydst is re-used during gc */
	struct hlist_node	bydst;
	struct hlist_node	bysrc;
	struct hlist_node	byspi;

	atomic_t		refcnt;
	spinlock_t		lock;

	struct xfrm_id		id;
	struct xfrm_selector	sel;

	u32			genid;

	/* Key manger bits */
	struct {
		u8		state;
		u8		dying;
		u32		seq;
	} km;

	/* Parameters of this state. */
	struct {
		u32		reqid;
		u8		mode;
		u8		replay_window;
		u8		aalgo, ealgo, calgo;
		u8		flags;
		u16		family;
		xfrm_address_t	saddr;
		int		header_len;
		int		trailer_len;
	} props;

	struct xfrm_lifetime_cfg lft;

	/* Data for transformer */
	struct xfrm_algo	*aalg;
	struct xfrm_algo	*ealg;
	struct xfrm_algo	*calg;

	/* Data for encapsulator */
	struct xfrm_encap_tmpl	*encap;

	/* Data for care-of address */
	xfrm_address_t	*coaddr;

	/* IPComp needs an IPIP tunnel for handling uncompressed packets */
	struct xfrm_state	*tunnel;

	/* If a tunnel, number of users + 1 */
	atomic_t		tunnel_users;

	/* State for replay detection */
	struct xfrm_replay_state replay;

	/* Replay detection state at the time we sent the last notification */
	struct xfrm_replay_state preplay;

	/* internal flag that only holds state for delayed aevent at the
	 * moment
	*/
	u32			xflags;

	/* Replay detection notification settings */
	u32			replay_maxage;
	u32			replay_maxdiff;

	/* Replay detection notification timer */
	struct timer_list	rtimer;

	/* Statistics */
	struct xfrm_stats	stats;

	struct xfrm_lifetime_cur curlft;
	struct timer_list	timer;

	/* Last used time */
	u64			lastused;

	/* Reference to data common to all the instances of this
	 * transformer. */
	struct xfrm_type	*type;
	struct xfrm_mode	*mode;

	/* Security context */
	struct xfrm_sec_ctx	*security;

	/* Private data of this transformer, format is opaque,
	 * interpreted by xfrm_type methods. */
	void			*data;
};

/* xflags - make enum if more show up */
#define XFRM_TIME_DEFER	1

enum {
	XFRM_STATE_VOID,
	XFRM_STATE_ACQ,
	XFRM_STATE_VALID,
	XFRM_STATE_ERROR,
	XFRM_STATE_EXPIRED,
	XFRM_STATE_DEAD
};

/* callback structure passed from either netlink or pfkey */
struct km_event
{
	union {
		u32 hard;
		u32 proto;
		u32 byid;
		u32 aevent;
		u32 type;
	} data;

	u32	seq;
	u32	pid;
	u32	event;
};

struct xfrm_type;
struct xfrm_dst;
struct xfrm_policy_afinfo {
	unsigned short		family;
	struct xfrm_type	*type_map[IPPROTO_MAX];
	struct xfrm_mode	*mode_map[XFRM_MODE_MAX];
	struct dst_ops		*dst_ops;
	void			(*garbage_collect)(void);
	int			(*dst_lookup)(struct xfrm_dst **dst, struct flowi *fl);
	int			(*get_saddr)(xfrm_address_t *saddr, xfrm_address_t *daddr);
	struct dst_entry	*(*find_bundle)(struct flowi *fl, struct xfrm_policy *policy);
	int			(*bundle_create)(struct xfrm_policy *policy, 
						 struct xfrm_state **xfrm, 
						 int nx,
						 struct flowi *fl, 
						 struct dst_entry **dst_p);
	void			(*decode_session)(struct sk_buff *skb,
						  struct flowi *fl);
};

extern int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo);
extern int xfrm_policy_unregister_afinfo(struct xfrm_policy_afinfo *afinfo);
extern void km_policy_notify(struct xfrm_policy *xp, int dir, struct km_event *c);
extern void km_state_notify(struct xfrm_state *x, struct km_event *c);
#define XFRM_ACQ_EXPIRES	30

struct xfrm_tmpl;
extern int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol);
extern void km_state_expired(struct xfrm_state *x, int hard, u32 pid);
extern int __xfrm_state_delete(struct xfrm_state *x);

struct xfrm_state_afinfo {
	unsigned short		family;
	int			(*init_flags)(struct xfrm_state *x);
	void			(*init_tempsel)(struct xfrm_state *x, struct flowi *fl,
						struct xfrm_tmpl *tmpl,
						xfrm_address_t *daddr, xfrm_address_t *saddr);
	int			(*tmpl_sort)(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n);
	int			(*state_sort)(struct xfrm_state **dst, struct xfrm_state **src, int n);
	int			(*output)(struct sk_buff *skb);
};

extern int xfrm_state_register_afinfo(struct xfrm_state_afinfo *afinfo);
extern int xfrm_state_unregister_afinfo(struct xfrm_state_afinfo *afinfo);
extern struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned short family);
extern void xfrm_state_put_afinfo(struct xfrm_state_afinfo *afinfo);

extern void xfrm_state_delete_tunnel(struct xfrm_state *x);

struct xfrm_type
{
	char			*description;
	struct module		*owner;
	__u8			proto;
	__u8			flags;
#define XFRM_TYPE_NON_FRAGMENT	1

	int			(*init_state)(struct xfrm_state *x);
	void			(*destructor)(struct xfrm_state *);
	int			(*input)(struct xfrm_state *, struct sk_buff *skb);
	int			(*output)(struct xfrm_state *, struct sk_buff *pskb);
	int			(*reject)(struct xfrm_state *, struct sk_buff *, struct flowi *);
	int			(*hdr_offset)(struct xfrm_state *, struct sk_buff *, u8 **);
	xfrm_address_t		*(*local_addr)(struct xfrm_state *, xfrm_address_t *);
	xfrm_address_t		*(*remote_addr)(struct xfrm_state *, xfrm_address_t *);
	/* Estimate maximal size of result of transformation of a dgram */
	u32			(*get_mtu)(struct xfrm_state *, int size);
};

extern int xfrm_register_type(struct xfrm_type *type, unsigned short family);
extern int xfrm_unregister_type(struct xfrm_type *type, unsigned short family);
extern struct xfrm_type *xfrm_get_type(u8 proto, unsigned short family);
extern void xfrm_put_type(struct xfrm_type *type);

struct xfrm_mode {
	int (*input)(struct xfrm_state *x, struct sk_buff *skb);
	int (*output)(struct xfrm_state *x,struct sk_buff *skb);

	struct module *owner;
	unsigned int encap;
};

extern int xfrm_register_mode(struct xfrm_mode *mode, int family);
extern int xfrm_unregister_mode(struct xfrm_mode *mode, int family);
extern struct xfrm_mode *xfrm_get_mode(unsigned int encap, int family);
extern void xfrm_put_mode(struct xfrm_mode *mode);

struct xfrm_tmpl
{
/* id in template is interpreted as:
 * daddr - destination of tunnel, may be zero for transport mode.
 * spi   - zero to acquire spi. Not zero if spi is static, then
 *	   daddr must be fixed too.
 * proto - AH/ESP/IPCOMP
 */
	struct xfrm_id		id;

/* Source address of tunnel. Ignored, if it is not a tunnel. */
	xfrm_address_t		saddr;

	unsigned short		encap_family;

	__u32			reqid;

/* Mode: transport, tunnel etc. */
	__u8			mode;

/* Sharing mode: unique, this session only, this user only etc. */
	__u8			share;

/* May skip this transfomration if no SA is found */
	__u8			optional;

/* Bit mask of algos allowed for acquisition */
	__u32			aalgos;
	__u32			ealgos;
	__u32			calgos;
};

#define XFRM_MAX_DEPTH		6

struct xfrm_policy
{
	struct xfrm_policy	*next;
	struct hlist_node	bydst;
	struct hlist_node	byidx;

	/* This lock only affects elements except for entry. */
	rwlock_t		lock;
	atomic_t		refcnt;
	struct timer_list	timer;

	u32			priority;
	u32			index;
	struct xfrm_selector	selector;
	struct xfrm_lifetime_cfg lft;
	struct xfrm_lifetime_cur curlft;
	struct dst_entry       *bundles;
	u16			family;
	u8			type;
	u8			action;
	u8			flags;
	u8			dead;
	u8			xfrm_nr;
	/* XXX 1 byte hole, try to pack */
	struct xfrm_sec_ctx	*security;
	struct xfrm_tmpl       	xfrm_vec[XFRM_MAX_DEPTH];
};

struct xfrm_migrate {
	xfrm_address_t		old_daddr;
	xfrm_address_t		old_saddr;
	xfrm_address_t		new_daddr;
	xfrm_address_t		new_saddr;
	u8			proto;
	u8			mode;
	u16			reserved;
	u32			reqid;
	u16			old_family;
	u16			new_family;
};

#define XFRM_KM_TIMEOUT                30
/* which seqno */
#define XFRM_REPLAY_SEQ		1
#define XFRM_REPLAY_OSEQ	2
#define XFRM_REPLAY_SEQ_MASK	3
/* what happened */
#define XFRM_REPLAY_UPDATE	XFRM_AE_CR
#define XFRM_REPLAY_TIMEOUT	XFRM_AE_CE

/* default aevent timeout in units of 100ms */
#define XFRM_AE_ETIME			10
/* Async Event timer multiplier */
#define XFRM_AE_ETH_M			10
/* default seq threshold size */
#define XFRM_AE_SEQT_SIZE		2

struct xfrm_mgr
{
	struct list_head	list;
	char			*id;
	int			(*notify)(struct xfrm_state *x, struct km_event *c);
	int			(*acquire)(struct xfrm_state *x, struct xfrm_tmpl *, struct xfrm_policy *xp, int dir);
	struct xfrm_policy	*(*compile_policy)(struct sock *sk, int opt, u8 *data, int len, int *dir);
	int			(*new_mapping)(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport);
	int			(*notify_policy)(struct xfrm_policy *x, int dir, struct km_event *c);
	int			(*report)(u8 proto, struct xfrm_selector *sel, xfrm_address_t *addr);
	int			(*migrate)(struct xfrm_selector *sel, u8 dir, u8 type, struct xfrm_migrate *m, int num_bundles);
};

extern int xfrm_register_km(struct xfrm_mgr *km);
extern int xfrm_unregister_km(struct xfrm_mgr *km);

extern unsigned int xfrm_policy_count[XFRM_POLICY_MAX*2];

/* Audit Information */
struct xfrm_audit
{
	uid_t	loginuid;
	u32	secid;
};

#ifdef CONFIG_AUDITSYSCALL
extern void xfrm_audit_log(uid_t auid, u32 secid, int type, int result,
		    struct xfrm_policy *xp, struct xfrm_state *x);
#else
#define xfrm_audit_log(a,s,t,r,p,x) do { ; } while (0)
#endif /* CONFIG_AUDITSYSCALL */

static inline void xfrm_pol_hold(struct xfrm_policy *policy)
{
	if (likely(policy != NULL))
		atomic_inc(&policy->refcnt);
}

extern void __xfrm_policy_destroy(struct xfrm_policy *policy);

static inline void xfrm_pol_put(struct xfrm_policy *policy)
{
	if (atomic_dec_and_test(&policy->refcnt))
		__xfrm_policy_destroy(policy);
}

#ifdef CONFIG_XFRM_SUB_POLICY
static inline void xfrm_pols_put(struct xfrm_policy **pols, int npols)
{
	int i;
	for (i = npols - 1; i >= 0; --i)
		xfrm_pol_put(pols[i]);
}
#else
static inline void xfrm_pols_put(struct xfrm_policy **pols, int npols)
{
	xfrm_pol_put(pols[0]);
}
#endif

extern void __xfrm_state_destroy(struct xfrm_state *);

static inline void __xfrm_state_put(struct xfrm_state *x)
{
	atomic_dec(&x->refcnt);
}

static inline void xfrm_state_put(struct xfrm_state *x)
{
	if (atomic_dec_and_test(&x->refcnt))
		__xfrm_state_destroy(x);
}

static inline void xfrm_state_hold(struct xfrm_state *x)
{
	atomic_inc(&x->refcnt);
}

static __inline__ int addr_match(void *token1, void *token2, int prefixlen)
{
	__be32 *a1 = token1;
	__be32 *a2 = token2;
	int pdw;
	int pbi;

	pdw = prefixlen >> 5;	  /* num of whole __u32 in prefix */
	pbi = prefixlen &  0x1f;  /* num of bits in incomplete u32 in prefix */

	if (pdw)
		if (memcmp(a1, a2, pdw << 2))
			return 0;

	if (pbi) {
		__be32 mask;

		mask = htonl((0xffffffff) << (32 - pbi));

		if ((a1[pdw] ^ a2[pdw]) & mask)
			return 0;
	}

	return 1;
}

static __inline__
__be16 xfrm_flowi_sport(struct flowi *fl)
{
	__be16 port;
	switch(fl->proto) {
	case IPPROTO_TCP:
	case IPPROTO_UDP:
	case IPPROTO_UDPLITE:
	case IPPROTO_SCTP:
		port = fl->fl_ip_sport;
		break;
	case IPPROTO_ICMP:
	case IPPROTO_ICMPV6:
		port = htons(fl->fl_icmp_type);
		break;
#ifdef CONFIG_IPV6_MIP6
	case IPPROTO_MH:
		port = htons(fl->fl_mh_type);
		break;
#endif
	default:
		port = 0;	/*XXX*/
	}
	return port;
}

static __inline__
__be16 xfrm_flowi_dport(struct flowi *fl)
{
	__be16 port;
	switch(fl->proto) {
	case IPPROTO_TCP:
	case IPPROTO_UDP:
	case IPPROTO_UDPLITE:
	case IPPROTO_SCTP:
		port = fl->fl_ip_dport;
		break;
	case IPPROTO_ICMP:
	case IPPROTO_ICMPV6:
		port = htons(fl->fl_icmp_code);
		break;
	default:
		port = 0;	/*XXX*/
	}
	return port;
}

extern int xfrm_selector_match(struct xfrm_selector *sel, struct flowi *fl,
			       unsigned short family);

#ifdef CONFIG_SECURITY_NETWORK_XFRM
/*	If neither has a context --> match
 * 	Otherwise, both must have a context and the sids, doi, alg must match
 */
static inline int xfrm_sec_ctx_match(struct xfrm_sec_ctx *s1, struct xfrm_sec_ctx *s2)
{
	return ((!s1 && !s2) ||
		(s1 && s2 &&
		 (s1->ctx_sid == s2->ctx_sid) &&
		 (s1->ctx_doi == s2->ctx_doi) &&
		 (s1->ctx_alg == s2->ctx_alg)));
}
#else
static inline int xfrm_sec_ctx_match(struct xfrm_sec_ctx *s1, struct xfrm_sec_ctx *s2)
{
	return 1;
}
#endif

/* A struct encoding bundle of transformations to apply to some set of flow.
 *
 * dst->child points to the next element of bundle.
 * dst->xfrm  points to an instanse of transformer.
 *
 * Due to unfortunate limitations of current routing cache, which we
 * have no time to fix, it mirrors struct rtable and bound to the same
 * routing key, including saddr,daddr. However, we can have many of
 * bundles differing by session id. All the bundles grow from a parent
 * policy rule.
 */
struct xfrm_dst
{
	union {
		struct xfrm_dst		*next;
		struct dst_entry	dst;
		struct rtable		rt;
		struct rt6_info		rt6;
	} u;
	struct dst_entry *route;
	u32 genid;
	u32 route_mtu_cached;
	u32 child_mtu_cached;
	u32 route_cookie;
	u32 path_cookie;
};

static inline void xfrm_dst_destroy(struct xfrm_dst *xdst)
{
	dst_release(xdst->route);
	if (likely(xdst->u.dst.xfrm))
		xfrm_state_put(xdst->u.dst.xfrm);
}

extern void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev);

struct sec_path
{
	atomic_t		refcnt;
	int			len;
	struct xfrm_state	*xvec[XFRM_MAX_DEPTH];
};

static inline struct sec_path *
secpath_get(struct sec_path *sp)
{
	if (sp)
		atomic_inc(&sp->refcnt);
	return sp;
}

extern void __secpath_destroy(struct sec_path *sp);

static inline void
secpath_put(struct sec_path *sp)
{
	if (sp && atomic_dec_and_test(&sp->refcnt))
		__secpath_destroy(sp);
}

extern struct sec_path *secpath_dup(struct sec_path *src);

static inline void
secpath_reset(struct sk_buff *skb)
{
#ifdef CONFIG_XFRM
	secpath_put(skb->sp);
	skb->sp = NULL;
#endif
}

static inline int
xfrm_addr_any(xfrm_address_t *addr, unsigned short family)
{
	switch (family) {
	case AF_INET:
		return addr->a4 == 0;
	case AF_INET6:
		return ipv6_addr_any((struct in6_addr *)&addr->a6);
	}
	return 0;
}

static inline int
__xfrm4_state_addr_cmp(struct xfrm_tmpl *tmpl, struct xfrm_state *x)
{
	return	(tmpl->saddr.a4 &&
		 tmpl->saddr.a4 != x->props.saddr.a4);
}

static inline int
__xfrm6_state_addr_cmp(struct xfrm_tmpl *tmpl, struct xfrm_state *x)
{
	return	(!ipv6_addr_any((struct in6_addr*)&tmpl->saddr) &&
		 ipv6_addr_cmp((struct in6_addr *)&tmpl->saddr, (struct in6_addr*)&x->props.saddr));
}

static inline int
xfrm_state_addr_cmp(struct xfrm_tmpl *tmpl, struct xfrm_state *x, unsigned short family)
{
	switch (family) {
	case AF_INET:
		return __xfrm4_state_addr_cmp(tmpl, x);
	case AF_INET6:
		return __xfrm6_state_addr_cmp(tmpl, x);
	}
	return !0;
}

#ifdef CONFIG_XFRM

extern int __xfrm_policy_check(struct sock *, int dir, struct sk_buff *skb, unsigned short family);

static inline int xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, unsigned short family)
{
	if (sk && sk->sk_policy[XFRM_POLICY_IN])
		return __xfrm_policy_check(sk, dir, skb, family);

	return	(!xfrm_policy_count[dir] && !skb->sp) ||
		(skb->dst->flags & DST_NOPOLICY) ||
		__xfrm_policy_check(sk, dir, skb, family);
}

static inline int xfrm4_policy_check(struct sock *sk, int dir, struct sk_buff *skb)
{
	return xfrm_policy_check(sk, dir, skb, AF_INET);
}

static inline int xfrm6_policy_check(struct sock *sk, int dir, struct sk_buff *skb)
{
	return xfrm_policy_check(sk, dir, skb, AF_INET6);
}

extern int xfrm_decode_session(struct sk_buff *skb, struct flowi *fl, unsigned short family);
extern int __xfrm_route_forward(struct sk_buff *skb, unsigned short family);

static inline int xfrm_route_forward(struct sk_buff *skb, unsigned short family)
{
	return	!xfrm_policy_count[XFRM_POLICY_OUT] ||
		(skb->dst->flags & DST_NOXFRM) ||
		__xfrm_route_forward(skb, family);
}

static inline int xfrm4_route_forward(struct sk_buff *skb)
{
	return xfrm_route_forward(skb, AF_INET);
}

static inline int xfrm6_route_forward(struct sk_buff *skb)
{
	return xfrm_route_forward(skb, AF_INET6);
}

extern int __xfrm_sk_clone_policy(struct sock *sk);

static inline int xfrm_sk_clone_policy(struct sock *sk)
{
	if (unlikely(sk->sk_policy[0] || sk->sk_policy[1]))
		return __xfrm_sk_clone_policy(sk);
	return 0;
}

extern int xfrm_policy_delete(struct xfrm_policy *pol, int dir);

static inline void xfrm_sk_free_policy(struct sock *sk)
{
	if (unlikely(sk->sk_policy[0] != NULL)) {
		xfrm_policy_delete(sk->sk_policy[0], XFRM_POLICY_MAX);
		sk->sk_policy[0] = NULL;
	}
	if (unlikely(sk->sk_policy[1] != NULL)) {
		xfrm_policy_delete(sk->sk_policy[1], XFRM_POLICY_MAX+1);
		sk->sk_policy[1] = NULL;
	}
}

#else

static inline void xfrm_sk_free_policy(struct sock *sk) {}
static inline int xfrm_sk_clone_policy(struct sock *sk) { return 0; }
static inline int xfrm6_route_forward(struct sk_buff *skb) { return 1; }  
static inline int xfrm4_route_forward(struct sk_buff *skb) { return 1; } 
static inline int xfrm6_policy_check(struct sock *sk, int dir, struct sk_buff *skb)
{ 
	return 1; 
} 
static inline int xfrm4_policy_check(struct sock *sk, int dir, struct sk_buff *skb)
{
	return 1;
}
static inline int xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, unsigned short family)
{
	return 1;
}
#endif

static __inline__
xfrm_address_t *xfrm_flowi_daddr(struct flowi *fl, unsigned short family)
{
	switch (family){
	case AF_INET:
		return (xfrm_address_t *)&fl->fl4_dst;
	case AF_INET6:
		return (xfrm_address_t *)&fl->fl6_dst;
	}
	return NULL;
}

static __inline__
xfrm_address_t *xfrm_flowi_saddr(struct flowi *fl, unsigned short family)
{
	switch (family){
	case AF_INET:
		return (xfrm_address_t *)&fl->fl4_src;
	case AF_INET6:
		return (xfrm_address_t *)&fl->fl6_src;
	}
	return NULL;
}

static __inline__ int
__xfrm4_state_addr_check(struct xfrm_state *x,
			 xfrm_address_t *daddr, xfrm_address_t *saddr)
{
	if (daddr->a4 == x->id.daddr.a4 &&
	    (saddr->a4 == x->props.saddr.a4 || !saddr->a4 || !x->props.saddr.a4))
		return 1;
	return 0;
}

static __inline__ int
__xfrm6_state_addr_check(struct xfrm_state *x,
			 xfrm_address_t *daddr, xfrm_address_t *saddr)
{
	if (!ipv6_addr_cmp((struct in6_addr *)daddr, (struct in6_addr *)&x->id.daddr) &&
	    (!ipv6_addr_cmp((struct in6_addr *)saddr, (struct in6_addr *)&x->props.saddr)|| 
	     ipv6_addr_any((struct in6_addr *)saddr) || 
	     ipv6_addr_any((struct in6_addr *)&x->props.saddr)))
		return 1;
	return 0;
}

static __inline__ int
xfrm_state_addr_check(struct xfrm_state *x,
		      xfrm_address_t *daddr, xfrm_address_t *saddr,
		      unsigned short family)
{
	switch (family) {
	case AF_INET:
		return __xfrm4_state_addr_check(x, daddr, saddr);
	case AF_INET6:
		return __xfrm6_state_addr_check(x, daddr, saddr);
	}
	return 0;
}

static __inline__ int
xfrm_state_addr_flow_check(struct xfrm_state *x, struct flowi *fl,
			   unsigned short family)
{
	switch (family) {
	case AF_INET:
		return __xfrm4_state_addr_check(x,
						(xfrm_address_t *)&fl->fl4_dst,
						(xfrm_address_t *)&fl->fl4_src);
	case AF_INET6:
		return __xfrm6_state_addr_check(x,
						(xfrm_address_t *)&fl->fl6_dst,
						(xfrm_address_t *)&fl->fl6_src);
	}
	return 0;
}

static inline int xfrm_state_kern(struct xfrm_state *x)
{
	return atomic_read(&x->tunnel_users);
}

static inline int xfrm_id_proto_match(u8 proto, u8 userproto)
{
	return (!userproto || proto == userproto ||
		(userproto == IPSEC_PROTO_ANY && (proto == IPPROTO_AH ||
						  proto == IPPROTO_ESP ||
						  proto == IPPROTO_COMP)));
}

/*
 * xfrm algorithm information
 */
struct xfrm_algo_auth_info {
	u16 icv_truncbits;
	u16 icv_fullbits;
};

struct xfrm_algo_encr_info {
	u16 blockbits;
	u16 defkeybits;
};

struct xfrm_algo_comp_info {
	u16 threshold;
};

struct xfrm_algo_desc {
	char *name;
	char *compat;
	u8 available:1;
	union {
		struct xfrm_algo_auth_info auth;
		struct xfrm_algo_encr_info encr;
		struct xfrm_algo_comp_info comp;
	} uinfo;
	struct sadb_alg desc;
};

/* XFRM tunnel handlers.  */
struct xfrm_tunnel {
	int (*handler)(struct sk_buff *skb);
	int (*err_handler)(struct sk_buff *skb, __u32 info);

	struct xfrm_tunnel *next;
	int priority;
};

struct xfrm6_tunnel {
	int (*handler)(struct sk_buff *skb);
	int (*err_handler)(struct sk_buff *skb, struct inet6_skb_parm *opt,
			   int type, int code, int offset, __be32 info);
	struct xfrm6_tunnel *next;
	int priority;
};

extern void xfrm_init(void);
extern void xfrm4_init(void);
extern void xfrm6_init(void);
extern void xfrm6_fini(void);
extern void xfrm_state_init(void);
extern void xfrm4_state_init(void);
extern void xfrm6_state_init(void);
extern void xfrm6_state_fini(void);

extern int xfrm_state_walk(u8 proto, int (*func)(struct xfrm_state *, int, void*), void *);
extern struct xfrm_state *xfrm_state_alloc(void);
extern struct xfrm_state *xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr, 
					  struct flowi *fl, struct xfrm_tmpl *tmpl,
					  struct xfrm_policy *pol, int *err,
					  unsigned short family);
extern int xfrm_state_check_expire(struct xfrm_state *x);
extern void xfrm_state_insert(struct xfrm_state *x);
extern int xfrm_state_add(struct xfrm_state *x);
extern int xfrm_state_update(struct xfrm_state *x);
extern struct xfrm_state *xfrm_state_lookup(xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family);
extern struct xfrm_state *xfrm_state_lookup_byaddr(xfrm_address_t *daddr, xfrm_address_t *saddr, u8 proto, unsigned short family);
#ifdef CONFIG_XFRM_SUB_POLICY
extern int xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src,
			  int n, unsigned short family);
extern int xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src,
			   int n, unsigned short family);
#else
static inline int xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src,
				 int n, unsigned short family)
{
	return -ENOSYS;
}

static inline int xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src,
				  int n, unsigned short family)
{
	return -ENOSYS;
}
#endif
extern struct xfrm_state *xfrm_find_acq_byseq(u32 seq);
extern int xfrm_state_delete(struct xfrm_state *x);
extern void xfrm_state_flush(u8 proto, struct xfrm_audit *audit_info);
extern int xfrm_replay_check(struct xfrm_state *x, __be32 seq);
extern void xfrm_replay_advance(struct xfrm_state *x, __be32 seq);
extern void xfrm_replay_notify(struct xfrm_state *x, int event);
extern int xfrm_state_check(struct xfrm_state *x, struct sk_buff *skb);
extern int xfrm_state_mtu(struct xfrm_state *x, int mtu);
extern int xfrm_init_state(struct xfrm_state *x);
extern int xfrm4_rcv(struct sk_buff *skb);
extern int xfrm4_output(struct sk_buff *skb);
extern int xfrm4_tunnel_register(struct xfrm_tunnel *handler, unsigned short family);
extern int xfrm4_tunnel_deregister(struct xfrm_tunnel *handler, unsigned short family);
extern int xfrm6_rcv_spi(struct sk_buff *skb, __be32 spi);
extern int xfrm6_rcv(struct sk_buff **pskb);
extern int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr,
			    xfrm_address_t *saddr, u8 proto);
extern int xfrm6_tunnel_register(struct xfrm6_tunnel *handler, unsigned short family);
extern int xfrm6_tunnel_deregister(struct xfrm6_tunnel *handler, unsigned short family);
extern __be32 xfrm6_tunnel_alloc_spi(xfrm_address_t *saddr);
extern void xfrm6_tunnel_free_spi(xfrm_address_t *saddr);
extern __be32 xfrm6_tunnel_spi_lookup(xfrm_address_t *saddr);
extern int xfrm6_output(struct sk_buff *skb);
extern int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb,
				 u8 **prevhdr);

#ifdef CONFIG_XFRM
extern int xfrm4_rcv_encap(struct sk_buff *skb, __u16 encap_type);
extern int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen);
extern int xfrm_dst_lookup(struct xfrm_dst **dst, struct flowi *fl, unsigned short family);
#else
static inline int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen)
{
 	return -ENOPROTOOPT;
} 

static inline int xfrm4_rcv_encap(struct sk_buff *skb, __u16 encap_type)
{
 	/* should not happen */
 	kfree_skb(skb);
	return 0;
}
static inline int xfrm_dst_lookup(struct xfrm_dst **dst, struct flowi *fl, unsigned short family)
{
	return -EINVAL;
} 
#endif

struct xfrm_policy *xfrm_policy_alloc(gfp_t gfp);
extern int xfrm_policy_walk(u8 type, int (*func)(struct xfrm_policy *, int, int, void*), void *);
int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl);
struct xfrm_policy *xfrm_policy_bysel_ctx(u8 type, int dir,
					  struct xfrm_selector *sel,
					  struct xfrm_sec_ctx *ctx, int delete,
					  int *err);
struct xfrm_policy *xfrm_policy_byid(u8, int dir, u32 id, int delete, int *err);
void xfrm_policy_flush(u8 type, struct xfrm_audit *audit_info);
u32 xfrm_get_acqseq(void);
void xfrm_alloc_spi(struct xfrm_state *x, __be32 minspi, __be32 maxspi);
struct xfrm_state * xfrm_find_acq(u8 mode, u32 reqid, u8 proto,
				  xfrm_address_t *daddr, xfrm_address_t *saddr,
				  int create, unsigned short family);
extern void xfrm_policy_flush(u8 type, struct xfrm_audit *audit_info);
extern int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol);
extern int xfrm_bundle_ok(struct xfrm_policy *pol, struct xfrm_dst *xdst,
			  struct flowi *fl, int family, int strict);
extern void xfrm_init_pmtu(struct dst_entry *dst);

#ifdef CONFIG_XFRM_MIGRATE
extern int km_migrate(struct xfrm_selector *sel, u8 dir, u8 type,
		      struct xfrm_migrate *m, int num_bundles);
extern struct xfrm_state * xfrm_migrate_state_find(struct xfrm_migrate *m);
extern struct xfrm_state * xfrm_state_migrate(struct xfrm_state *x,
					      struct xfrm_migrate *m);
extern int xfrm_migrate(struct xfrm_selector *sel, u8 dir, u8 type,
			struct xfrm_migrate *m, int num_bundles);
#endif

extern wait_queue_head_t km_waitq;
extern int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport);
extern void km_policy_expired(struct xfrm_policy *pol, int dir, int hard, u32 pid);
extern int km_report(u8 proto, struct xfrm_selector *sel, xfrm_address_t *addr);

extern void xfrm_input_init(void);
extern int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, __be32 *spi, __be32 *seq);

extern void xfrm_probe_algs(void);
extern int xfrm_count_auth_supported(void);
extern int xfrm_count_enc_supported(void);
extern struct xfrm_algo_desc *xfrm_aalg_get_byidx(unsigned int idx);
extern struct xfrm_algo_desc *xfrm_ealg_get_byidx(unsigned int idx);
extern struct xfrm_algo_desc *xfrm_aalg_get_byid(int alg_id);
extern struct xfrm_algo_desc *xfrm_ealg_get_byid(int alg_id);
extern struct xfrm_algo_desc *xfrm_calg_get_byid(int alg_id);
extern struct xfrm_algo_desc *xfrm_aalg_get_byname(char *name, int probe);
extern struct xfrm_algo_desc *xfrm_ealg_get_byname(char *name, int probe);
extern struct xfrm_algo_desc *xfrm_calg_get_byname(char *name, int probe);

struct hash_desc;
struct scatterlist;
typedef int (icv_update_fn_t)(struct hash_desc *, struct scatterlist *,
			      unsigned int);

extern int skb_icv_walk(const struct sk_buff *skb, struct hash_desc *tfm,
			int offset, int len, icv_update_fn_t icv_update);

static inline int xfrm_addr_cmp(xfrm_address_t *a, xfrm_address_t *b,
				int family)
{
	switch (family) {
	default:
	case AF_INET:
		return (__force __u32)a->a4 - (__force __u32)b->a4;
	case AF_INET6:
		return ipv6_addr_cmp((struct in6_addr *)a,
				     (struct in6_addr *)b);
	}
}

static inline int xfrm_policy_id2dir(u32 index)
{
	return index & 7;
}

static inline int xfrm_aevent_is_on(void)
{
	struct sock *nlsk;
	int ret = 0;

	rcu_read_lock();
	nlsk = rcu_dereference(xfrm_nl);
	if (nlsk)
		ret = netlink_has_listeners(nlsk, XFRMNLGRP_AEVENTS);
	rcu_read_unlock();
	return ret;
}

static inline void xfrm_aevent_doreplay(struct xfrm_state *x)
{
	if (xfrm_aevent_is_on())
		xfrm_replay_notify(x, XFRM_REPLAY_UPDATE);
}

#ifdef CONFIG_XFRM_MIGRATE
static inline struct xfrm_algo *xfrm_algo_clone(struct xfrm_algo *orig)
{
	return (struct xfrm_algo *)kmemdup(orig, sizeof(*orig) + orig->alg_key_len, GFP_KERNEL);
}

static inline void xfrm_states_put(struct xfrm_state **states, int n)
{
	int i;
	for (i = 0; i < n; i++)
		xfrm_state_put(*(states + i));
}

static inline void xfrm_states_delete(struct xfrm_state **states, int n)
{
	int i;
	for (i = 0; i < n; i++)
		xfrm_state_delete(*(states + i));
}
#endif

#endif	/* _NET_XFRM_H */