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
|
/* $FreeBSD$ */
/* $KAME: ip_encap.c,v 1.36 2000/06/17 20:34:24 itojun Exp $ */
/*
* Copyright (C) 1995, 1996, 1997, and 1998 WIDE Project.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. Neither the name of the project nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE PROJECT AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE PROJECT OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*/
/*
* My grandfather said that there's a devil inside tunnelling technology...
*
* We have surprisingly many protocols that want packets with IP protocol
* #4 or #41. Here's a list of protocols that want protocol #41:
* RFC1933 configured tunnel
* RFC1933 automatic tunnel
* RFC2401 IPsec tunnel
* RFC2473 IPv6 generic packet tunnelling
* RFC2529 6over4 tunnel
* mobile-ip6 (uses RFC2473)
* 6to4 tunnel
* Here's a list of protocol that want protocol #4:
* RFC1853 IPv4-in-IPv4 tunnelling
* RFC2003 IPv4 encapsulation within IPv4
* RFC2344 reverse tunnelling for mobile-ip4
* RFC2401 IPsec tunnel
* Well, what can I say. They impose different en/decapsulation mechanism
* from each other, so they need separate protocol handler. The only one
* we can easily determine by protocol # is IPsec, which always has
* AH/ESP/IPComp header right after outer IP header.
*
* So, clearly good old protosw does not work for protocol #4 and #41.
* The code will let you match protocol via src/dst address pair.
*/
/* XXX is M_NETADDR correct? */
#include "opt_mrouting.h"
#include "opt_inet.h"
#include "opt_inet6.h"
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/socket.h>
#include <sys/sockio.h>
#include <sys/mbuf.h>
#include <sys/errno.h>
#include <sys/protosw.h>
#include <net/if.h>
#include <net/route.h>
#include <netinet/in.h>
#include <netinet/in_systm.h>
#include <netinet/ip.h>
#include <netinet/ip_var.h>
#include <netinet/ip_encap.h>
#ifdef MROUTING
#include <netinet/ip_mroute.h>
#endif /* MROUTING */
#include <netinet/ipprotosw.h>
#ifdef INET6
#include <netinet/ip6.h>
#include <netinet6/ip6_var.h>
#include <netinet6/ip6protosw.h>
#endif
#include <machine/stdarg.h>
#include <net/net_osdep.h>
#include <sys/kernel.h>
#include <sys/malloc.h>
MALLOC_DEFINE(M_NETADDR, "Export Host", "Export host address structure");
static void encap_add __P((struct encaptab *));
static int mask_match __P((const struct encaptab *, const struct sockaddr *,
const struct sockaddr *));
static void encap_fillarg __P((struct mbuf *, const struct encaptab *));
/* rely upon BSS initialization */
LIST_HEAD(, encaptab) encaptab;
void
encap_init()
{
#if 0
/*
* we cannot use LIST_INIT() here, since drivers may want to call
* encap_attach(), on driver attach. encap_init() will be called
* on AF_INET{,6} initialization, which happens after driver
* initialization - using LIST_INIT() here can nuke encap_attach()
* from drivers.
*/
LIST_INIT(&encaptab);
#endif
}
void
#if __STDC__
encap4_input(struct mbuf *m, ...)
#else
encap4_input(m, va_alist)
struct mbuf *m;
va_dcl
#endif
{
int off, proto;
struct ip *ip;
struct sockaddr_in s, d;
const struct ipprotosw *psw;
struct encaptab *ep, *match;
va_list ap;
int prio, matchprio;
va_start(ap, m);
off = va_arg(ap, int);
proto = va_arg(ap, int);
va_end(ap);
ip = mtod(m, struct ip *);
bzero(&s, sizeof(s));
s.sin_family = AF_INET;
s.sin_len = sizeof(struct sockaddr_in);
s.sin_addr = ip->ip_src;
bzero(&d, sizeof(d));
d.sin_family = AF_INET;
d.sin_len = sizeof(struct sockaddr_in);
d.sin_addr = ip->ip_dst;
match = NULL;
matchprio = 0;
for (ep = LIST_FIRST(&encaptab); ep; ep = LIST_NEXT(ep, chain)) {
if (ep->af != AF_INET)
continue;
if (ep->proto >= 0 && ep->proto != proto)
continue;
if (ep->func)
prio = (*ep->func)(m, off, proto, ep->arg);
else {
/*
* it's inbound traffic, we need to match in reverse
* order
*/
prio = mask_match(ep, (struct sockaddr *)&d,
(struct sockaddr *)&s);
}
/*
* We prioritize the matches by using bit length of the
* matches. mask_match() and user-supplied matching function
* should return the bit length of the matches (for example,
* if both src/dst are matched for IPv4, 64 should be returned).
* 0 or negative return value means "it did not match".
*
* The question is, since we have two "mask" portion, we
* cannot really define total order between entries.
* For example, which of these should be preferred?
* mask_match() returns 48 (32 + 16) for both of them.
* src=3ffe::/16, dst=3ffe:501::/32
* src=3ffe:501::/32, dst=3ffe::/16
*
* We need to loop through all the possible candidates
* to get the best match - the search takes O(n) for
* n attachments (i.e. interfaces).
*/
if (prio <= 0)
continue;
if (prio > matchprio) {
matchprio = prio;
match = ep;
}
}
if (match) {
/* found a match, "match" has the best one */
psw = (const struct ipprotosw *)match->psw;
if (psw && psw->pr_input) {
encap_fillarg(m, match);
(*psw->pr_input)(m, off, proto);
} else
m_freem(m);
return;
}
/* for backward compatibility */
# ifdef MROUTING
# define COMPATFUNC ipip_input
# endif /*MROUTING*/
#ifdef COMPATFUNC
if (proto == IPPROTO_IPV4) {
COMPATFUNC(m, off, proto);
return;
}
#endif
/* last resort: inject to raw socket */
rip_input(m, off, proto);
}
#ifdef INET6
int
encap6_input(mp, offp, proto)
struct mbuf **mp;
int *offp;
int proto;
{
struct mbuf *m = *mp;
struct ip6_hdr *ip6;
struct sockaddr_in6 s, d;
const struct ip6protosw *psw;
struct encaptab *ep, *match;
int prio, matchprio;
ip6 = mtod(m, struct ip6_hdr *);
bzero(&s, sizeof(s));
s.sin6_family = AF_INET6;
s.sin6_len = sizeof(struct sockaddr_in6);
s.sin6_addr = ip6->ip6_src;
bzero(&d, sizeof(d));
d.sin6_family = AF_INET6;
d.sin6_len = sizeof(struct sockaddr_in6);
d.sin6_addr = ip6->ip6_dst;
match = NULL;
matchprio = 0;
for (ep = LIST_FIRST(&encaptab); ep; ep = LIST_NEXT(ep, chain)) {
if (ep->af != AF_INET6)
continue;
if (ep->proto >= 0 && ep->proto != proto)
continue;
if (ep->func)
prio = (*ep->func)(m, *offp, proto, ep->arg);
else {
/*
* it's inbound traffic, we need to match in reverse
* order
*/
prio = mask_match(ep, (struct sockaddr *)&d,
(struct sockaddr *)&s);
}
/* see encap4_input() for issues here */
if (prio <= 0)
continue;
if (prio > matchprio) {
matchprio = prio;
match = ep;
}
}
if (match) {
/* found a match */
psw = (const struct ip6protosw *)match->psw;
if (psw && psw->pr_input) {
encap_fillarg(m, match);
return (*psw->pr_input)(mp, offp, proto);
} else {
m_freem(m);
return IPPROTO_DONE;
}
}
/* last resort: inject to raw socket */
return rip6_input(mp, offp, proto);
}
#endif
static void
encap_add(ep)
struct encaptab *ep;
{
LIST_INSERT_HEAD(&encaptab, ep, chain);
}
/*
* sp (src ptr) is always my side, and dp (dst ptr) is always remote side.
* length of mask (sm and dm) is assumed to be same as sp/dp.
* Return value will be necessary as input (cookie) for encap_detach().
*/
const struct encaptab *
encap_attach(af, proto, sp, sm, dp, dm, psw, arg)
int af;
int proto;
const struct sockaddr *sp, *sm;
const struct sockaddr *dp, *dm;
const struct protosw *psw;
void *arg;
{
struct encaptab *ep;
int error;
int s;
s = splnet();
/* sanity check on args */
if (sp->sa_len > sizeof(ep->src) || dp->sa_len > sizeof(ep->dst)) {
error = EINVAL;
goto fail;
}
if (sp->sa_len != dp->sa_len) {
error = EINVAL;
goto fail;
}
if (af != sp->sa_family || af != dp->sa_family) {
error = EINVAL;
goto fail;
}
/* check if anyone have already attached with exactly same config */
for (ep = LIST_FIRST(&encaptab); ep; ep = LIST_NEXT(ep, chain)) {
if (ep->af != af)
continue;
if (ep->proto != proto)
continue;
if (ep->src.ss_len != sp->sa_len ||
bcmp(&ep->src, sp, sp->sa_len) != 0 ||
bcmp(&ep->srcmask, sm, sp->sa_len) != 0)
continue;
if (ep->dst.ss_len != dp->sa_len ||
bcmp(&ep->dst, dp, dp->sa_len) != 0 ||
bcmp(&ep->dstmask, dm, dp->sa_len) != 0)
continue;
error = EEXIST;
goto fail;
}
ep = malloc(sizeof(*ep), M_NETADDR, M_NOWAIT); /*XXX*/
if (ep == NULL) {
error = ENOBUFS;
goto fail;
}
bzero(ep, sizeof(*ep));
ep->af = af;
ep->proto = proto;
bcopy(sp, &ep->src, sp->sa_len);
bcopy(sm, &ep->srcmask, sp->sa_len);
bcopy(dp, &ep->dst, dp->sa_len);
bcopy(dm, &ep->dstmask, dp->sa_len);
ep->psw = psw;
ep->arg = arg;
encap_add(ep);
error = 0;
splx(s);
return ep;
fail:
splx(s);
return NULL;
}
const struct encaptab *
encap_attach_func(af, proto, func, psw, arg)
int af;
int proto;
int (*func) __P((const struct mbuf *, int, int, void *));
const struct protosw *psw;
void *arg;
{
struct encaptab *ep;
int error;
int s;
s = splnet();
/* sanity check on args */
if (!func) {
error = EINVAL;
goto fail;
}
ep = malloc(sizeof(*ep), M_NETADDR, M_NOWAIT); /*XXX*/
if (ep == NULL) {
error = ENOBUFS;
goto fail;
}
bzero(ep, sizeof(*ep));
ep->af = af;
ep->proto = proto;
ep->func = func;
ep->psw = psw;
ep->arg = arg;
encap_add(ep);
error = 0;
splx(s);
return ep;
fail:
splx(s);
return NULL;
}
int
encap_detach(cookie)
const struct encaptab *cookie;
{
const struct encaptab *ep = cookie;
struct encaptab *p;
for (p = LIST_FIRST(&encaptab); p; p = LIST_NEXT(p, chain)) {
if (p == ep) {
LIST_REMOVE(p, chain);
free(p, M_NETADDR); /*XXX*/
return 0;
}
}
return EINVAL;
}
static int
mask_match(ep, sp, dp)
const struct encaptab *ep;
const struct sockaddr *sp;
const struct sockaddr *dp;
{
struct sockaddr_storage s;
struct sockaddr_storage d;
int i;
const u_int8_t *p, *q;
u_int8_t *r;
int matchlen;
if (sp->sa_len > sizeof(s) || dp->sa_len > sizeof(d))
return 0;
if (sp->sa_family != ep->af || dp->sa_family != ep->af)
return 0;
if (sp->sa_len != ep->src.ss_len || dp->sa_len != ep->dst.ss_len)
return 0;
matchlen = 0;
p = (const u_int8_t *)sp;
q = (const u_int8_t *)&ep->srcmask;
r = (u_int8_t *)&s;
for (i = 0 ; i < sp->sa_len; i++) {
r[i] = p[i] & q[i];
/* XXX estimate */
matchlen += (q[i] ? 8 : 0);
}
p = (const u_int8_t *)dp;
q = (const u_int8_t *)&ep->dstmask;
r = (u_int8_t *)&d;
for (i = 0 ; i < dp->sa_len; i++) {
r[i] = p[i] & q[i];
/* XXX rough estimate */
matchlen += (q[i] ? 8 : 0);
}
/* need to overwrite len/family portion as we don't compare them */
s.ss_len = sp->sa_len;
s.ss_family = sp->sa_family;
d.ss_len = dp->sa_len;
d.ss_family = dp->sa_family;
if (bcmp(&s, &ep->src, ep->src.ss_len) == 0 &&
bcmp(&d, &ep->dst, ep->dst.ss_len) == 0) {
return matchlen;
} else
return 0;
}
static void
encap_fillarg(m, ep)
struct mbuf *m;
const struct encaptab *ep;
{
#if 0
m->m_pkthdr.aux = ep->arg;
#else
struct mbuf *n;
n = m_aux_add(m, AF_INET, IPPROTO_IPV4);
if (n) {
*mtod(n, void **) = ep->arg;
n->m_len = sizeof(void *);
}
#endif
}
void *
encap_getarg(m)
struct mbuf *m;
{
void *p;
#if 0
p = m->m_pkthdr.aux;
m->m_pkthdr.aux = NULL;
return p;
#else
struct mbuf *n;
p = NULL;
n = m_aux_find(m, AF_INET, IPPROTO_IPV4);
if (n) {
if (n->m_len == sizeof(void *))
p = *mtod(n, void **);
m_aux_delete(m, n);
}
return p;
#endif
}
|