summaryrefslogtreecommitdiffstats
path: root/sys/netinet6/in6_rmx.c
blob: 14587bd59bbf77d3dec4c9ceb602e7e353f90167 (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
/*	$FreeBSD$	*/
/*	$KAME: in6_rmx.c,v 1.11 2001/07/26 06:53:16 jinmei 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.
 */

/*
 * Copyright 1994, 1995 Massachusetts Institute of Technology
 *
 * Permission to use, copy, modify, and distribute this software and
 * its documentation for any purpose and without fee is hereby
 * granted, provided that both the above copyright notice and this
 * permission notice appear in all copies, that both the above
 * copyright notice and this permission notice appear in all
 * supporting documentation, and that the name of M.I.T. not be used
 * in advertising or publicity pertaining to distribution of the
 * software without specific, written prior permission.  M.I.T. makes
 * no representations about the suitability of this software for any
 * purpose.  It is provided "as is" without express or implied
 * warranty.
 *
 * THIS SOFTWARE IS PROVIDED BY M.I.T. ``AS IS''.  M.I.T. DISCLAIMS
 * ALL EXPRESS OR IMPLIED WARRANTIES WITH REGARD TO THIS SOFTWARE,
 * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
 * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. IN NO EVENT
 * SHALL M.I.T. 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.
 *
 */

/*
 * This code does two things necessary for the enhanced TCP metrics to
 * function in a useful manner:
 *  1) It marks all non-host routes as `cloning', thus ensuring that
 *     every actual reference to such a route actually gets turned
 *     into a reference to a host route to the specific destination
 *     requested.
 *  2) When such routes lose all their references, it arranges for them
 *     to be deleted in some random collection of circumstances, so that
 *     a large quantity of stale routing data is not kept in kernel memory
 *     indefinitely.  See in6_rtqtimo() below for the exact mechanism.
 */

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/kernel.h>
#include <sys/sysctl.h>
#include <sys/queue.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/mbuf.h>
#include <sys/syslog.h>

#include <net/if.h>
#include <net/route.h>
#include <netinet/in.h>
#include <netinet/ip_var.h>
#include <netinet/in_var.h>

#include <netinet/ip6.h>
#include <netinet6/ip6_var.h>

#include <netinet/icmp6.h>

#include <netinet/tcp.h>
#include <netinet/tcp_seq.h>
#include <netinet/tcp_timer.h>
#include <netinet/tcp_var.h>

extern int	in6_inithead __P((void **head, int off));

#define RTPRF_OURS		RTF_PROTO3	/* set on routes we manage */

/*
 * Do what we need to do when inserting a route.
 */
static struct radix_node *
in6_addroute(void *v_arg, void *n_arg, struct radix_node_head *head,
	    struct radix_node *treenodes)
{
	struct rtentry *rt = (struct rtentry *)treenodes;
	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)rt_key(rt);
	struct radix_node *ret;

	/*
	 * For IPv6, all unicast non-host routes are automatically cloning.
	 */
	if (IN6_IS_ADDR_MULTICAST(&sin6->sin6_addr))
		rt->rt_flags |= RTF_MULTICAST;

	if (!(rt->rt_flags & (RTF_HOST | RTF_CLONING | RTF_MULTICAST))) {
		rt->rt_flags |= RTF_PRCLONING;
	}

	/*
	 * A little bit of help for both IPv6 output and input:
	 *   For local addresses, we make sure that RTF_LOCAL is set,
	 *   with the thought that this might one day be used to speed up
	 *   ip_input().
	 *
	 * We also mark routes to multicast addresses as such, because
	 * it's easy to do and might be useful (but this is much more
	 * dubious since it's so easy to inspect the address).  (This
	 * is done above.)
	 *
	 * XXX
	 * should elaborate the code.
	 */
	if (rt->rt_flags & RTF_HOST) {
		if (IN6_ARE_ADDR_EQUAL(&satosin6(rt->rt_ifa->ifa_addr)
					->sin6_addr,
				       &sin6->sin6_addr)) {
			rt->rt_flags |= RTF_LOCAL;
		}
	}

	if (!rt->rt_rmx.rmx_mtu && !(rt->rt_rmx.rmx_locks & RTV_MTU)
	    && rt->rt_ifp)
		rt->rt_rmx.rmx_mtu = rt->rt_ifp->if_mtu;

	ret = rn_addroute(v_arg, n_arg, head, treenodes);
	if (ret == NULL && rt->rt_flags & RTF_HOST) {
		struct rtentry *rt2;
		/*
		 * We are trying to add a host route, but can't.
		 * Find out if it is because of an
		 * ARP entry and delete it if so.
		 */
		rt2 = rtalloc1((struct sockaddr *)sin6, 0,
				RTF_CLONING | RTF_PRCLONING);
		if (rt2) {
			if (rt2->rt_flags & RTF_LLINFO &&
				rt2->rt_flags & RTF_HOST &&
				rt2->rt_gateway &&
				rt2->rt_gateway->sa_family == AF_LINK) {
				rtrequest(RTM_DELETE,
					  (struct sockaddr *)rt_key(rt2),
					  rt2->rt_gateway,
					  rt_mask(rt2), rt2->rt_flags, 0);
				ret = rn_addroute(v_arg, n_arg, head,
					treenodes);
			}
			RTFREE(rt2);
		}
	} else if (ret == NULL && rt->rt_flags & RTF_CLONING) {
		struct rtentry *rt2;
		/*
		 * We are trying to add a net route, but can't.
		 * The following case should be allowed, so we'll make a
		 * special check for this:
		 *	Two IPv6 addresses with the same prefix is assigned
		 *	to a single interrface.
		 *	# ifconfig if0 inet6 3ffe:0501::1 prefix 64 alias (*1)
		 *	# ifconfig if0 inet6 3ffe:0501::2 prefix 64 alias (*2)
		 *	In this case, (*1) and (*2) want to add the same
		 *	net route entry, 3ffe:0501:: -> if0.
		 *	This case should not raise an error.
		 */
		rt2 = rtalloc1((struct sockaddr *)sin6, 0,
				RTF_CLONING | RTF_PRCLONING);
		if (rt2) {
			if ((rt2->rt_flags & (RTF_CLONING|RTF_HOST|RTF_GATEWAY))
					== RTF_CLONING
			 && rt2->rt_gateway
			 && rt2->rt_gateway->sa_family == AF_LINK
			 && rt2->rt_ifp == rt->rt_ifp) {
				ret = rt2->rt_nodes;
			}
			RTFREE(rt2);
		}
	}
	return ret;
}

/*
 * This code is the inverse of in6_clsroute: on first reference, if we
 * were managing the route, stop doing so and set the expiration timer
 * back off again.
 */
static struct radix_node *
in6_matroute(void *v_arg, struct radix_node_head *head)
{
	struct radix_node *rn = rn_match(v_arg, head);
	struct rtentry *rt = (struct rtentry *)rn;

	if (rt && rt->rt_refcnt == 0) { /* this is first reference */
		if (rt->rt_flags & RTPRF_OURS) {
			rt->rt_flags &= ~RTPRF_OURS;
			rt->rt_rmx.rmx_expire = 0;
		}
	}
	return rn;
}

SYSCTL_DECL(_net_inet6_ip6);

static int rtq_reallyold = 60*60;
	/* one hour is ``really old'' */
SYSCTL_INT(_net_inet6_ip6, IPV6CTL_RTEXPIRE, rtexpire,
	CTLFLAG_RW, &rtq_reallyold , 0, "");
				
static int rtq_minreallyold = 10;
	/* never automatically crank down to less */
SYSCTL_INT(_net_inet6_ip6, IPV6CTL_RTMINEXPIRE, rtminexpire,
	CTLFLAG_RW, &rtq_minreallyold , 0, "");
				
static int rtq_toomany = 128;
	/* 128 cached routes is ``too many'' */
SYSCTL_INT(_net_inet6_ip6, IPV6CTL_RTMAXCACHE, rtmaxcache,
	CTLFLAG_RW, &rtq_toomany , 0, "");
				

/*
 * On last reference drop, mark the route as belong to us so that it can be
 * timed out.
 */
static void
in6_clsroute(struct radix_node *rn, struct radix_node_head *head)
{
	struct rtentry *rt = (struct rtentry *)rn;

	if (!(rt->rt_flags & RTF_UP))
		return;		/* prophylactic measures */

	if ((rt->rt_flags & (RTF_LLINFO | RTF_HOST)) != RTF_HOST)
		return;

	if ((rt->rt_flags & (RTF_WASCLONED | RTPRF_OURS)) != RTF_WASCLONED)
		return;

	/*
	 * As requested by David Greenman:
	 * If rtq_reallyold is 0, just delete the route without
	 * waiting for a timeout cycle to kill it.
	 */
	if (rtq_reallyold != 0) {
		rt->rt_flags |= RTPRF_OURS;
		rt->rt_rmx.rmx_expire = time_second + rtq_reallyold;
	} else {
		rtrequest(RTM_DELETE,
			  (struct sockaddr *)rt_key(rt),
			  rt->rt_gateway, rt_mask(rt),
			  rt->rt_flags, 0);
	}
}

struct rtqk_arg {
	struct radix_node_head *rnh;
	int mode;
	int updating;
	int draining;
	int killed;
	int found;
	time_t nextstop;
};

/*
 * Get rid of old routes.  When draining, this deletes everything, even when
 * the timeout is not expired yet.  When updating, this makes sure that
 * nothing has a timeout longer than the current value of rtq_reallyold.
 */
static int
in6_rtqkill(struct radix_node *rn, void *rock)
{
	struct rtqk_arg *ap = rock;
	struct rtentry *rt = (struct rtentry *)rn;
	int err;

	if (rt->rt_flags & RTPRF_OURS) {
		ap->found++;

		if (ap->draining || rt->rt_rmx.rmx_expire <= time_second) {
			if (rt->rt_refcnt > 0)
				panic("rtqkill route really not free");

			err = rtrequest(RTM_DELETE,
					(struct sockaddr *)rt_key(rt),
					rt->rt_gateway, rt_mask(rt),
					rt->rt_flags, 0);
			if (err) {
				log(LOG_WARNING, "in6_rtqkill: error %d", err);
			} else {
				ap->killed++;
			}
		} else {
			if (ap->updating
			   && (rt->rt_rmx.rmx_expire - time_second
			       > rtq_reallyold)) {
				rt->rt_rmx.rmx_expire = time_second
					+ rtq_reallyold;
			}
			ap->nextstop = lmin(ap->nextstop,
					    rt->rt_rmx.rmx_expire);
		}
	}

	return 0;
}

#define RTQ_TIMEOUT	60*10	/* run no less than once every ten minutes */
static int rtq_timeout = RTQ_TIMEOUT;

static void
in6_rtqtimo(void *rock)
{
	struct radix_node_head *rnh = rock;
	struct rtqk_arg arg;
	struct timeval atv;
	static time_t last_adjusted_timeout = 0;
	int s;

	arg.found = arg.killed = 0;
	arg.rnh = rnh;
	arg.nextstop = time_second + rtq_timeout;
	arg.draining = arg.updating = 0;
	s = splnet();
	RADIX_NODE_HEAD_LOCK(rnh);
	rnh->rnh_walktree(rnh, in6_rtqkill, &arg);
	RADIX_NODE_HEAD_UNLOCK(rnh);
	splx(s);

	/*
	 * Attempt to be somewhat dynamic about this:
	 * If there are ``too many'' routes sitting around taking up space,
	 * then crank down the timeout, and see if we can't make some more
	 * go away.  However, we make sure that we will never adjust more
	 * than once in rtq_timeout seconds, to keep from cranking down too
	 * hard.
	 */
	if ((arg.found - arg.killed > rtq_toomany)
	   && (time_second - last_adjusted_timeout >= rtq_timeout)
	   && rtq_reallyold > rtq_minreallyold) {
		rtq_reallyold = 2*rtq_reallyold / 3;
		if (rtq_reallyold < rtq_minreallyold) {
			rtq_reallyold = rtq_minreallyold;
		}

		last_adjusted_timeout = time_second;
#ifdef DIAGNOSTIC
		log(LOG_DEBUG, "in6_rtqtimo: adjusted rtq_reallyold to %d",
		    rtq_reallyold);
#endif
		arg.found = arg.killed = 0;
		arg.updating = 1;
		s = splnet();
		RADIX_NODE_HEAD_LOCK(rnh);
		rnh->rnh_walktree(rnh, in6_rtqkill, &arg);
		RADIX_NODE_HEAD_UNLOCK(rnh);
		splx(s);
	}

	atv.tv_usec = 0;
	atv.tv_sec = arg.nextstop;
	timeout(in6_rtqtimo, rock, tvtohz(&atv));
}

/*
 * Age old PMTUs.
 */
struct mtuex_arg {
	struct radix_node_head *rnh;
	time_t nextstop;
};

static int
in6_mtuexpire(struct radix_node *rn, void *rock)
{
	struct rtentry *rt = (struct rtentry *)rn;
	struct mtuex_arg *ap = rock;

	/* sanity */
	if (!rt)
		panic("rt == NULL in in6_mtuexpire");

	if (rt->rt_rmx.rmx_expire && !(rt->rt_flags & RTF_PROBEMTU)) {
		if (rt->rt_rmx.rmx_expire <= time_second) {
			rt->rt_flags |= RTF_PROBEMTU;
		} else {
			ap->nextstop = lmin(ap->nextstop,
					rt->rt_rmx.rmx_expire);
		}
	}

	return 0;
}

#define	MTUTIMO_DEFAULT	(60*1)

static void
in6_mtutimo(void *rock)
{
	struct radix_node_head *rnh = rock;
	struct mtuex_arg arg;
	struct timeval atv;
	int s;

	arg.rnh = rnh;
	arg.nextstop = time_second + MTUTIMO_DEFAULT;
	s = splnet();
	RADIX_NODE_HEAD_LOCK(rnh);
	rnh->rnh_walktree(rnh, in6_mtuexpire, &arg);
	RADIX_NODE_HEAD_UNLOCK(rnh);
	splx(s);

	atv.tv_usec = 0;
	atv.tv_sec = arg.nextstop;
	if (atv.tv_sec < time_second) {
		printf("invalid mtu expiration time on routing table\n");
		arg.nextstop = time_second + 30;	/* last resort */
	}
	timeout(in6_mtutimo, rock, tvtohz(&atv));
}

#if 0
void
in6_rtqdrain()
{
	struct radix_node_head *rnh = rt_tables[AF_INET6];
	struct rtqk_arg arg;
	int s;
	arg.found = arg.killed = 0;
	arg.rnh = rnh;
	arg.nextstop = 0;
	arg.draining = 1;
	arg.updating = 0;
	s = splnet();
	RADIX_NODE_HEAD_LOCK(rnh);
	rnh->rnh_walktree(rnh, in6_rtqkill, &arg);
	RADIX_NODE_HEAD_UNLOCK(rnh);
	splx(s);
}
#endif

/*
 * Initialize our routing tree.
 */
int
in6_inithead(void **head, int off)
{
	struct radix_node_head *rnh;

	if (!rn_inithead(head, off))
		return 0;

	if (head != (void **)&rt_tables[AF_INET6]) /* BOGUS! */
		return 1;	/* only do this for the real routing table */

	rnh = *head;
	rnh->rnh_addaddr = in6_addroute;
	rnh->rnh_matchaddr = in6_matroute;
	rnh->rnh_close = in6_clsroute;
	in6_rtqtimo(rnh);	/* kick off timeout first time */
	in6_mtutimo(rnh);	/* kick off timeout first time */
	return 1;
}
OpenPOWER on IntegriCloud