summaryrefslogtreecommitdiff
path: root/sys/netinet/in_pcb.c
blob: 1dc2af9749e7411af30861fd694d65f134ff8211 (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
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
/*	$OpenBSD: in_pcb.c,v 1.85 2006/03/05 21:48:56 miod Exp $	*/
/*	$NetBSD: in_pcb.c,v 1.25 1996/02/13 23:41:53 christos Exp $	*/

/*
 * Copyright (c) 1982, 1986, 1991, 1993
 *	The Regents of the University of California.  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 University 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 REGENTS 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 REGENTS 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	1.1 (NRL) 17 January 1995
 *
 * NRL grants permission for redistribution and use in source and binary
 * forms, with or without modification, of the software and documentation
 * created at NRL 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. All advertising materials mentioning features or use of this software
 *    must display the following acknowledgements:
 * 	This product includes software developed by the University of
 * 	California, Berkeley and its contributors.
 * 	This product includes software developed at the Information
 * 	Technology Division, US Naval Research Laboratory.
 * 4. Neither the name of the NRL nor the names of its contributors
 *    may be used to endorse or promote products derived from this software
 *    without specific prior written permission.
 *
 * THE SOFTWARE PROVIDED BY NRL IS PROVIDED BY NRL 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 NRL 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.
 *
 * The views and conclusions contained in the software and documentation
 * are those of the authors and should not be interpreted as representing
 * official policies, either expressed or implied, of the US Naval
 * Research Laboratory (NRL).
 */

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/mbuf.h>
#include <sys/protosw.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/proc.h>
#include <sys/domain.h>

#include <net/if.h>
#include <net/route.h>

#include <netinet/in.h>
#include <netinet/in_systm.h>
#include <netinet/ip.h>
#include <netinet/in_pcb.h>
#include <netinet/in_var.h>
#include <netinet/ip_var.h>
#include <dev/rndvar.h>

#include <sys/mount.h>
#include <nfs/nfsproto.h>

#ifdef INET6
#include <netinet6/ip6_var.h>
#endif /* INET6 */
#ifdef IPSEC
#include <netinet/ip_esp.h>
#endif /* IPSEC */

struct	in_addr zeroin_addr;

extern int ipsec_auth_default_level;
extern int ipsec_esp_trans_default_level;
extern int ipsec_esp_network_default_level;
extern int ipsec_ipcomp_default_level;

/*
 * These configure the range of local port addresses assigned to
 * "unspecified" outgoing connections/packets/whatever.
 */
int ipport_firstauto = IPPORT_RESERVED;
int ipport_lastauto = IPPORT_USERRESERVED;
int ipport_hifirstauto = IPPORT_HIFIRSTAUTO;
int ipport_hilastauto = IPPORT_HILASTAUTO;

struct pool inpcb_pool;
int inpcb_pool_initalized = 0;

#define	INPCBHASH(table, faddr, fport, laddr, lport) \
	&(table)->inpt_hashtbl[(ntohl((faddr)->s_addr) + \
	ntohs((fport)) + ntohs((lport))) & (table->inpt_hash)]

#define	IN6PCBHASH(table, faddr, fport, laddr, lport) \
	&(table)->inpt_hashtbl[(ntohl((faddr)->s6_addr32[0] ^ \
	(faddr)->s6_addr32[3]) + ntohs((fport)) + ntohs((lport))) & \
	(table->inpt_hash)]

#define	INPCBLHASH(table, lport) \
	&(table)->inpt_lhashtbl[lport & table->inpt_lhash]

void
in_pcbinit(table, hashsize)
	struct inpcbtable *table;
	int hashsize;
{

	CIRCLEQ_INIT(&table->inpt_queue);
	table->inpt_hashtbl = hashinit(hashsize, M_PCB, M_NOWAIT,
	    &table->inpt_hash);
	if (table->inpt_hashtbl == NULL)
		panic("in_pcbinit: hashinit failed");
	table->inpt_lhashtbl = hashinit(hashsize, M_PCB, M_NOWAIT,
	    &table->inpt_lhash);
	if (table->inpt_lhashtbl == NULL)
		panic("in_pcbinit: hashinit failed for lport");
	table->inpt_lastport = 0;
}

struct baddynamicports baddynamicports;

/*
 * Check if the specified port is invalid for dynamic allocation.
 */
int
in_baddynamic(port, proto)
	u_int16_t port;
	u_int16_t proto;
{


	switch (proto) {
	case IPPROTO_TCP:
		if (port == NFS_PORT)
			return (1);
		if (port < IPPORT_RESERVED/2 || port >= IPPORT_RESERVED)
			return (0);
		return (DP_ISSET(baddynamicports.tcp, port));
	case IPPROTO_UDP:
#ifdef IPSEC
		if (port == udpencap_port)
			return (1);
#endif
		if (port == NFS_PORT)
			return (1);
		if (port < IPPORT_RESERVED/2 || port >= IPPORT_RESERVED)
			return (0);
		return (DP_ISSET(baddynamicports.udp, port));
	default:
		return (0);
	}
}

int
in_pcballoc(so, v)
	struct socket *so;
	void *v;
{
	struct inpcbtable *table = v;
	struct inpcb *inp;
	int s;

	if (inpcb_pool_initalized == 0) {
		pool_init(&inpcb_pool, sizeof(struct inpcb), 0, 0, 0,
		    "inpcbpl", NULL);
		inpcb_pool_initalized = 1;
	}
	inp = pool_get(&inpcb_pool, PR_NOWAIT);
	if (inp == NULL)
		return (ENOBUFS);
	bzero((caddr_t)inp, sizeof(*inp));
	inp->inp_table = table;
	inp->inp_socket = so;
	inp->inp_seclevel[SL_AUTH] = ipsec_auth_default_level;
	inp->inp_seclevel[SL_ESP_TRANS] = ipsec_esp_trans_default_level;
	inp->inp_seclevel[SL_ESP_NETWORK] = ipsec_esp_network_default_level;
	inp->inp_seclevel[SL_IPCOMP] = ipsec_ipcomp_default_level;
	s = splnet();
	CIRCLEQ_INSERT_HEAD(&table->inpt_queue, inp, inp_queue);
	LIST_INSERT_HEAD(INPCBLHASH(table, inp->inp_lport), inp, inp_lhash);
	LIST_INSERT_HEAD(INPCBHASH(table, &inp->inp_faddr, inp->inp_fport,
	    &inp->inp_laddr, inp->inp_lport), inp, inp_hash);
	splx(s);
	so->so_pcb = inp;
	inp->inp_hops = -1;

#ifdef INET6
	/*
	 * Small change in this function to set the INP_IPV6 flag so routines
	 * outside pcb-specific routines don't need to use sotopf(), and all
	 * of it's pointer chasing, later.
	 */
	if (sotopf(so) == PF_INET6)
		inp->inp_flags = INP_IPV6;
	inp->in6p_cksum = -1;
#endif /* INET6 */
	return (0);
}

int
in_pcbbind(v, nam)
	void *v;
	struct mbuf *nam;
{
	struct inpcb *inp = v;
	struct socket *so = inp->inp_socket;
	struct inpcbtable *table = inp->inp_table;
	u_int16_t *lastport = &inp->inp_table->inpt_lastport;
	struct sockaddr_in *sin;
	struct proc *p = curproc;		/* XXX */
	u_int16_t lport = 0;
	int wild = 0, reuseport = (so->so_options & SO_REUSEPORT);
	int error;

#ifdef INET6
	if (sotopf(so) == PF_INET6)
		return in6_pcbbind(inp, nam);
#endif /* INET6 */

	if (TAILQ_EMPTY(&in_ifaddr))
		return (EADDRNOTAVAIL);
	if (inp->inp_lport || inp->inp_laddr.s_addr != INADDR_ANY)
		return (EINVAL);
	if ((so->so_options & (SO_REUSEADDR|SO_REUSEPORT)) == 0 &&
	    ((so->so_proto->pr_flags & PR_CONNREQUIRED) == 0 ||
	     (so->so_options & SO_ACCEPTCONN) == 0))
		wild = INPLOOKUP_WILDCARD;
	if (nam) {
		sin = mtod(nam, struct sockaddr_in *);
		if (nam->m_len != sizeof (*sin))
			return (EINVAL);
#ifdef notdef
		/*
		 * We should check the family, but old programs
		 * incorrectly fail to initialize it.
		 */
		if (sin->sin_family != AF_INET)
			return (EAFNOSUPPORT);
#endif
		lport = sin->sin_port;
		if (IN_MULTICAST(sin->sin_addr.s_addr)) {
			/*
			 * Treat SO_REUSEADDR as SO_REUSEPORT for multicast;
			 * allow complete duplication of binding if
			 * SO_REUSEPORT is set, or if SO_REUSEADDR is set
			 * and a multicast address is bound on both
			 * new and duplicated sockets.
			 */
			if (so->so_options & SO_REUSEADDR)
				reuseport = SO_REUSEADDR|SO_REUSEPORT;
		} else if (sin->sin_addr.s_addr != INADDR_ANY) {
			sin->sin_port = 0;		/* yech... */
			if (in_iawithaddr(sin->sin_addr, NULL) == 0)
				return (EADDRNOTAVAIL);
		}
		if (lport) {
			struct inpcb *t;

			/* GROSS */
			if (ntohs(lport) < IPPORT_RESERVED &&
			    (error = suser(p, 0)))
				return (EACCES);
			if (so->so_euid) {
				t = in_pcblookup(table, &zeroin_addr, 0,
				    &sin->sin_addr, lport, INPLOOKUP_WILDCARD);
				if (t && (so->so_euid != t->inp_socket->so_euid))
					return (EADDRINUSE);
			}
			t = in_pcblookup(table, &zeroin_addr, 0,
			    &sin->sin_addr, lport, wild);
			if (t && (reuseport & t->inp_socket->so_options) == 0)
				return (EADDRINUSE);
		}
		inp->inp_laddr = sin->sin_addr;
	}
	if (lport == 0) {
		u_int16_t first, last;
		int count;

		if (inp->inp_flags & INP_HIGHPORT) {
			first = ipport_hifirstauto;	/* sysctl */
			last = ipport_hilastauto;
		} else if (inp->inp_flags & INP_LOWPORT) {
			if ((error = suser(p, 0)))
				return (EACCES);
			first = IPPORT_RESERVED-1; /* 1023 */
			last = 600;		   /* not IPPORT_RESERVED/2 */
		} else {
			first = ipport_firstauto;	/* sysctl */
			last  = ipport_lastauto;
		}

		/*
		 * Simple check to ensure all ports are not used up causing
		 * a deadlock here.
		 *
		 * We split the two cases (up and down) so that the direction
		 * is not being tested on each round of the loop.
		 */

		if (first > last) {
			/*
			 * counting down
			 */
			count = first - last;
			if (count)
				*lastport = first - (arc4random() % count);

			do {
				if (count-- < 0)	/* completely used? */
					return (EADDRNOTAVAIL);
				--*lastport;
				if (*lastport > first || *lastport < last)
					*lastport = first;
				lport = htons(*lastport);
			} while (in_baddynamic(*lastport, so->so_proto->pr_protocol) ||
			    in_pcblookup(table, &zeroin_addr, 0,
			    &inp->inp_laddr, lport, wild));
		} else {
			/*
			 * counting up
			 */
			count = last - first;
			if (count)
				*lastport = first + (arc4random() % count);

			do {
				if (count-- < 0)	/* completely used? */
					return (EADDRNOTAVAIL);
				++*lastport;
				if (*lastport < first || *lastport > last)
					*lastport = first;
				lport = htons(*lastport);
			} while (in_baddynamic(*lastport, so->so_proto->pr_protocol) ||
			    in_pcblookup(table, &zeroin_addr, 0,
			    &inp->inp_laddr, lport, wild));
		}
	}
	inp->inp_lport = lport;
	in_pcbrehash(inp);
	return (0);
}

/*
 * Connect from a socket to a specified address.
 * Both address and port must be specified in argument sin.
 * If don't have a local address for this socket yet,
 * then pick one.
 */
int
in_pcbconnect(v, nam)
	void *v;
	struct mbuf *nam;
{
	struct inpcb *inp = v;
	struct sockaddr_in *ifaddr = NULL;
	struct sockaddr_in *sin = mtod(nam, struct sockaddr_in *);

#ifdef INET6
	if (sotopf(inp->inp_socket) == PF_INET6)
		return (in6_pcbconnect(inp, nam));
	if ((inp->inp_flags & INP_IPV6) != 0)
		panic("IPv6 pcb passed into in_pcbconnect");
#endif /* INET6 */

	if (nam->m_len != sizeof (*sin))
		return (EINVAL);
	if (sin->sin_family != AF_INET)
		return (EAFNOSUPPORT);
	if (sin->sin_port == 0)
		return (EADDRNOTAVAIL);
	if (!TAILQ_EMPTY(&in_ifaddr)) {
		/*
		 * If the destination address is INADDR_ANY,
		 * use the primary local address.
		 * If the supplied address is INADDR_BROADCAST,
		 * and the primary interface supports broadcast,
		 * choose the broadcast address for that interface.
		 */
		if (sin->sin_addr.s_addr == INADDR_ANY)
			sin->sin_addr = TAILQ_FIRST(&in_ifaddr)->ia_addr.sin_addr;
		else if (sin->sin_addr.s_addr == INADDR_BROADCAST &&
		  (TAILQ_FIRST(&in_ifaddr)->ia_ifp->if_flags & IFF_BROADCAST))
			sin->sin_addr = TAILQ_FIRST(&in_ifaddr)->ia_broadaddr.sin_addr;
	}
	if (inp->inp_laddr.s_addr == INADDR_ANY) {
		int error;
		ifaddr = in_selectsrc(sin, &inp->inp_route,
			inp->inp_socket->so_options, inp->inp_moptions, &error);
		if (ifaddr == NULL) {
			if (error == 0)
				error = EADDRNOTAVAIL;
			return error;
		}
	}
	if (in_pcbhashlookup(inp->inp_table, sin->sin_addr, sin->sin_port,
	    inp->inp_laddr.s_addr ? inp->inp_laddr : ifaddr->sin_addr,
	    inp->inp_lport) != 0)
		return (EADDRINUSE);
	if (inp->inp_laddr.s_addr == INADDR_ANY) {
		if (inp->inp_lport == 0 &&
		    in_pcbbind(inp, (struct mbuf *)0) == EADDRNOTAVAIL)
			return (EADDRNOTAVAIL);
		inp->inp_laddr = ifaddr->sin_addr;
	}
	inp->inp_faddr = sin->sin_addr;
	inp->inp_fport = sin->sin_port;
	in_pcbrehash(inp);
#ifdef IPSEC
	{
		int error; /* This is just ignored */

		/* Cause an IPsec SA to be established. */
		ipsp_spd_inp(NULL, AF_INET, 0, &error, IPSP_DIRECTION_OUT,
		    NULL, inp, NULL);
	}
#endif
	return (0);
}

void
in_pcbdisconnect(v)
	void *v;
{
	struct inpcb *inp = v;

	switch (sotopf(inp->inp_socket)) {
#ifdef INET6
	case PF_INET6:
		inp->inp_faddr6 = in6addr_any;
		break;
#endif
	case PF_INET:
		inp->inp_faddr.s_addr = INADDR_ANY;
		break;
	}

	inp->inp_fport = 0;
	in_pcbrehash(inp);
	if (inp->inp_socket->so_state & SS_NOFDREF)
		in_pcbdetach(inp);
}

void
in_pcbdetach(v)
	void *v;
{
	struct inpcb *inp = v;
	struct socket *so = inp->inp_socket;
	int s;

	so->so_pcb = 0;
	sofree(so);
	if (inp->inp_options)
		(void)m_freem(inp->inp_options);
	if (inp->inp_route.ro_rt)
		rtfree(inp->inp_route.ro_rt);
#ifdef INET6
	if (inp->inp_flags & INP_IPV6)
		ip6_freemoptions(inp->inp_moptions6);
	else
#endif
		ip_freemoptions(inp->inp_moptions);
#ifdef IPSEC
	/* IPsec cleanup here */
	s = spltdb();
	if (inp->inp_tdb_in)
		TAILQ_REMOVE(&inp->inp_tdb_in->tdb_inp_in,
			     inp, inp_tdb_in_next);
	if (inp->inp_tdb_out)
	        TAILQ_REMOVE(&inp->inp_tdb_out->tdb_inp_out, inp,
			     inp_tdb_out_next);
	if (inp->inp_ipsec_remotecred)
		ipsp_reffree(inp->inp_ipsec_remotecred);
	if (inp->inp_ipsec_remoteauth)
		ipsp_reffree(inp->inp_ipsec_remoteauth);
	if (inp->inp_ipo)
		ipsec_delete_policy(inp->inp_ipo);
	splx(s);
#endif
	s = splnet();
	LIST_REMOVE(inp, inp_lhash);
	LIST_REMOVE(inp, inp_hash);
	CIRCLEQ_REMOVE(&inp->inp_table->inpt_queue, inp, inp_queue);
	splx(s);
	pool_put(&inpcb_pool, inp);
}

void
in_setsockaddr(inp, nam)
	struct inpcb *inp;
	struct mbuf *nam;
{
	struct sockaddr_in *sin;

	nam->m_len = sizeof (*sin);
	sin = mtod(nam, struct sockaddr_in *);
	bzero((caddr_t)sin, sizeof (*sin));
	sin->sin_family = AF_INET;
	sin->sin_len = sizeof(*sin);
	sin->sin_port = inp->inp_lport;
	sin->sin_addr = inp->inp_laddr;
}

void
in_setpeeraddr(inp, nam)
	struct inpcb *inp;
	struct mbuf *nam;
{
	struct sockaddr_in *sin;

#ifdef INET6
	if (sotopf(inp->inp_socket) == PF_INET6) {
		in6_setpeeraddr(inp, nam);
		return;
	}
#endif /* INET6 */

	nam->m_len = sizeof (*sin);
	sin = mtod(nam, struct sockaddr_in *);
	bzero((caddr_t)sin, sizeof (*sin));
	sin->sin_family = AF_INET;
	sin->sin_len = sizeof(*sin);
	sin->sin_port = inp->inp_fport;
	sin->sin_addr = inp->inp_faddr;
}

/*
 * Pass some notification to all connections of a protocol
 * associated with address dst.  The "usual action" will be
 * taken, depending on the ctlinput cmd.  The caller must filter any
 * cmds that are uninteresting (e.g., no error in the map).
 * Call the protocol specific routine (if any) to report
 * any errors for each matching socket.
 *
 * Must be called at splsoftnet.
 */
void
in_pcbnotifyall(table, dst, errno, notify)
	struct inpcbtable *table;
	struct sockaddr *dst;
	int errno;
	void (*notify)(struct inpcb *, int);
{
	struct inpcb *inp, *oinp;
	struct in_addr faddr;

	splassert(IPL_SOFTNET);

#ifdef INET6
	/*
	 * See in6_pcbnotify() for IPv6 codepath.  By the time this
	 * gets called, the addresses passed are either definitely IPv4 or
	 * IPv6; *_pcbnotify() never gets called with v4-mapped v6 addresses.
	 */
#endif /* INET6 */

	if (dst->sa_family != AF_INET)
		return;
	faddr = satosin(dst)->sin_addr;
	if (faddr.s_addr == INADDR_ANY)
		return;

	for (inp = CIRCLEQ_FIRST(&table->inpt_queue);
	    inp != CIRCLEQ_END(&table->inpt_queue);) {
#ifdef INET6
		if (inp->inp_flags & INP_IPV6) {
			inp = CIRCLEQ_NEXT(inp, inp_queue);
			continue;
		}
#endif
		if (inp->inp_faddr.s_addr != faddr.s_addr ||
		    inp->inp_socket == 0) {
			inp = CIRCLEQ_NEXT(inp, inp_queue);
			continue;
		}
		oinp = inp;
		inp = CIRCLEQ_NEXT(inp, inp_queue);
		if (notify)
			(*notify)(oinp, errno);
	}
}

/*
 * Check for alternatives when higher level complains
 * about service problems.  For now, invalidate cached
 * routing information.  If the route was created dynamically
 * (by a redirect), time to try a default gateway again.
 */
void
in_losing(inp)
	struct inpcb *inp;
{
	struct rtentry *rt;
	struct rt_addrinfo info;

	if ((rt = inp->inp_route.ro_rt)) {
		inp->inp_route.ro_rt = 0;
		bzero((caddr_t)&info, sizeof(info));
		info.rti_info[RTAX_DST] = &inp->inp_route.ro_dst;
		info.rti_info[RTAX_GATEWAY] = rt->rt_gateway;
		info.rti_info[RTAX_NETMASK] = rt_mask(rt);
		rt_missmsg(RTM_LOSING, &info, rt->rt_flags, 0);
		if (rt->rt_flags & RTF_DYNAMIC)
			(void) rtrequest(RTM_DELETE, rt_key(rt),
				rt->rt_gateway, rt_mask(rt), rt->rt_flags,
				(struct rtentry **)0);
		/*
		 * A new route can be allocated
		 * the next time output is attempted.
		 * rtfree() needs to be called in anycase because the inp
		 * is still holding a reference to rt.
		 */
		rtfree(rt);
	}
}

/*
 * After a routing change, flush old routing
 * and allocate a (hopefully) better one.
 */
void
in_rtchange(inp, errno)
	struct inpcb *inp;
	int errno;
{
	if (inp->inp_route.ro_rt) {
		rtfree(inp->inp_route.ro_rt);
		inp->inp_route.ro_rt = 0;
		/*
		 * A new route can be allocated the next time
		 * output is attempted.
		 */
	}
}

struct inpcb *
in_pcblookup(table, faddrp, fport_arg, laddrp, lport_arg, flags)
	struct inpcbtable *table;
	void *faddrp, *laddrp;
	u_int fport_arg, lport_arg;
	int flags;
{
	struct inpcb *inp, *match = 0;
	int matchwild = 3, wildcard;
	u_int16_t fport = fport_arg, lport = lport_arg;
	struct in_addr faddr = *(struct in_addr *)faddrp;
	struct in_addr laddr = *(struct in_addr *)laddrp;

	for (inp = LIST_FIRST(INPCBLHASH(table, lport)); inp;
	    inp = LIST_NEXT(inp, inp_lhash)) {
		if (inp->inp_lport != lport)
			continue;
		wildcard = 0;
#ifdef INET6
		if (flags & INPLOOKUP_IPV6) {
			struct in6_addr *laddr6 = (struct in6_addr *)laddrp;
			struct in6_addr *faddr6 = (struct in6_addr *)faddrp;

			if (!(inp->inp_flags & INP_IPV6))
				continue;

			if (!IN6_IS_ADDR_UNSPECIFIED(&inp->inp_laddr6)) {
				if (IN6_IS_ADDR_UNSPECIFIED(laddr6))
					wildcard++;
				else if (!IN6_ARE_ADDR_EQUAL(&inp->inp_laddr6, laddr6))
					continue;
			} else {
				if (!IN6_IS_ADDR_UNSPECIFIED(laddr6))
					wildcard++;
			}

			if (!IN6_IS_ADDR_UNSPECIFIED(&inp->inp_faddr6)) {
				if (IN6_IS_ADDR_UNSPECIFIED(faddr6))
					wildcard++;
				else if (!IN6_ARE_ADDR_EQUAL(&inp->inp_faddr6,
				    faddr6) || inp->inp_fport != fport)
					continue;
			} else {
				if (!IN6_IS_ADDR_UNSPECIFIED(faddr6))
					wildcard++;
			}
		} else
#endif /* INET6 */
		{
#ifdef INET6
		        if (inp->inp_flags & INP_IPV6)
			        continue;
#endif /* INET6 */

			if (inp->inp_faddr.s_addr != INADDR_ANY) {
				if (faddr.s_addr == INADDR_ANY)
					wildcard++;
				else if (inp->inp_faddr.s_addr != faddr.s_addr ||
				    inp->inp_fport != fport)
					continue;
			} else {
				if (faddr.s_addr != INADDR_ANY)
					wildcard++;
			}
			if (inp->inp_laddr.s_addr != INADDR_ANY) {
				if (laddr.s_addr == INADDR_ANY)
					wildcard++;
				else if (inp->inp_laddr.s_addr != laddr.s_addr)
					continue;
			} else {
				if (laddr.s_addr != INADDR_ANY)
					wildcard++;
			}
		}
		if ((!wildcard || (flags & INPLOOKUP_WILDCARD)) &&
		    wildcard < matchwild) {
			match = inp;
			if ((matchwild = wildcard) == 0)
				break;
		}
	}
	return (match);
}

struct rtentry *
in_pcbrtentry(inp)
	struct inpcb *inp;
{
	struct route *ro;

	ro = &inp->inp_route;

	/*
	 * No route yet, so try to acquire one.
	 */
	if (ro->ro_rt == NULL) {
#ifdef INET6
		bzero(ro, sizeof(struct route_in6));
#else
		bzero(ro, sizeof(struct route));
#endif

		switch(sotopf(inp->inp_socket)) {
#ifdef INET6
		case PF_INET6:
			if (IN6_IS_ADDR_UNSPECIFIED(&inp->inp_faddr6))
				break;
			ro->ro_dst.sa_family = AF_INET6;
			ro->ro_dst.sa_len = sizeof(struct sockaddr_in6);
			((struct sockaddr_in6 *) &ro->ro_dst)->sin6_addr =
			    inp->inp_faddr6;
			rtalloc(ro);
			break;
#endif /* INET6 */
		case PF_INET:
			if (inp->inp_faddr.s_addr == INADDR_ANY)
				break;
			ro->ro_dst.sa_family = AF_INET;
			ro->ro_dst.sa_len = sizeof(ro->ro_dst);
			satosin(&ro->ro_dst)->sin_addr = inp->inp_faddr;
			rtalloc(ro);
			break;
		}
	}
	return (ro->ro_rt);
}

struct sockaddr_in *
in_selectsrc(sin, ro, soopts, mopts, errorp)
	struct sockaddr_in *sin;
	struct route *ro;
	int soopts;
	struct ip_moptions *mopts;
	int *errorp;
{
	struct sockaddr_in *sin2;
	struct in_ifaddr *ia;

	ia = (struct in_ifaddr *)0;
	/*
	 * If route is known or can be allocated now,
	 * our src addr is taken from the i/f, else punt.
	 */
	if (ro->ro_rt &&
	    (satosin(&ro->ro_dst)->sin_addr.s_addr !=
		sin->sin_addr.s_addr ||
	    soopts & SO_DONTROUTE)) {
		RTFREE(ro->ro_rt);
		ro->ro_rt = (struct rtentry *)0;
	}
	if ((soopts & SO_DONTROUTE) == 0 && /*XXX*/
	    (ro->ro_rt == (struct rtentry *)0 ||
	    ro->ro_rt->rt_ifp == (struct ifnet *)0)) {
		/* No route yet, so try to acquire one */
		ro->ro_dst.sa_family = AF_INET;
		ro->ro_dst.sa_len = sizeof(struct sockaddr_in);
		satosin(&ro->ro_dst)->sin_addr = sin->sin_addr;
		rtalloc(ro);

		/*
		 * It is important to bzero out the rest of the
		 * struct sockaddr_in when mixing v6 & v4!
		 */
		sin2 = (struct sockaddr_in *)&ro->ro_dst;
		bzero(sin2->sin_zero, sizeof(sin2->sin_zero));
	}
	/*
	 * If we found a route, use the address
	 * corresponding to the outgoing interface
	 * unless it is the loopback (in case a route
	 * to our address on another net goes to loopback).
	 */
	if (ro->ro_rt && !(ro->ro_rt->rt_ifp->if_flags & IFF_LOOPBACK))
		ia = ifatoia(ro->ro_rt->rt_ifa);
	if (ia == 0) {
		u_int16_t fport = sin->sin_port;

		sin->sin_port = 0;
		ia = ifatoia(ifa_ifwithdstaddr(sintosa(sin)));
		if (ia == 0)
			ia = ifatoia(ifa_ifwithnet(sintosa(sin)));
		sin->sin_port = fport;
		if (ia == 0)
			ia = TAILQ_FIRST(&in_ifaddr);
		if (ia == 0) {
			*errorp = EADDRNOTAVAIL;
			return NULL;
		}
	}
	/*
	 * If the destination address is multicast and an outgoing
	 * interface has been set as a multicast option, use the
	 * address of that interface as our source address.
	 */
	if (IN_MULTICAST(sin->sin_addr.s_addr) && mopts != NULL) {
		struct ip_moptions *imo;
		struct ifnet *ifp;

		imo = mopts;
		if (imo->imo_multicast_ifp != NULL) {
			ifp = imo->imo_multicast_ifp;
			TAILQ_FOREACH(ia, &in_ifaddr, ia_list)
				if (ia->ia_ifp == ifp)
					break;
			if (ia == 0) {
				*errorp = EADDRNOTAVAIL;
				return NULL;
			}
		}
	}
	return satosin(&ia->ia_addr);
}

void
in_pcbrehash(inp)
	struct inpcb *inp;
{
	struct inpcbtable *table = inp->inp_table;
	int s;

	s = splnet();
	LIST_REMOVE(inp, inp_lhash);
	LIST_INSERT_HEAD(INPCBLHASH(table, inp->inp_lport), inp, inp_lhash);
	LIST_REMOVE(inp, inp_hash);
#ifdef INET6
	if (inp->inp_flags & INP_IPV6) {
		LIST_INSERT_HEAD(IN6PCBHASH(table, &inp->inp_faddr6,
		    inp->inp_fport, &inp->inp_laddr6, inp->inp_lport),
		    inp, inp_hash);
	} else {
#endif /* INET6 */
		LIST_INSERT_HEAD(INPCBHASH(table, &inp->inp_faddr,
		    inp->inp_fport, &inp->inp_laddr, inp->inp_lport),
		    inp, inp_hash);
#ifdef INET6
	}
#endif /* INET6 */
	splx(s);
}

#ifdef DIAGNOSTIC
int	in_pcbnotifymiss = 0;
#endif

/*
 * The in(6)_pcbhashlookup functions are used to locate connected sockets
 * quickly:
 * 		faddr.fport <-> laddr.lport
 * No wildcard matching is done so that listening sockets are not found.
 * If the functions return NULL in(6)_pcblookup_listen can be used to
 * find a listening/bound socket that may accept the connection.
 * After those two lookups no other are necessary.
 */
struct inpcb *
in_pcbhashlookup(table, faddr, fport_arg, laddr, lport_arg)
	struct inpcbtable *table;
	struct in_addr faddr, laddr;
	u_int fport_arg, lport_arg;
{
	struct inpcbhead *head;
	struct inpcb *inp;
	u_int16_t fport = fport_arg, lport = lport_arg;

	head = INPCBHASH(table, &faddr, fport, &laddr, lport);
	LIST_FOREACH(inp, head, inp_hash) {
#ifdef INET6
		if (inp->inp_flags & INP_IPV6)
			continue;	/*XXX*/
#endif
		if (inp->inp_faddr.s_addr == faddr.s_addr &&
		    inp->inp_fport == fport &&
		    inp->inp_lport == lport &&
		    inp->inp_laddr.s_addr == laddr.s_addr) {
			/*
			 * Move this PCB to the head of hash chain so that
			 * repeated accesses are quicker.  This is analogous to
			 * the historic single-entry PCB cache.
			 */
			if (inp != LIST_FIRST(head)) {
				LIST_REMOVE(inp, inp_hash);
				LIST_INSERT_HEAD(head, inp, inp_hash);
			}
			break;
		}
	}
#ifdef DIAGNOSTIC
	if (inp == NULL && in_pcbnotifymiss) {
		printf("in_pcbhashlookup: faddr=%08x fport=%d laddr=%08x lport=%d\n",
		    ntohl(faddr.s_addr), ntohs(fport),
		    ntohl(laddr.s_addr), ntohs(lport));
	}
#endif
	return (inp);
}

#ifdef INET6
struct inpcb *
in6_pcbhashlookup(table, faddr, fport_arg, laddr, lport_arg)
	struct inpcbtable *table;
	struct in6_addr *faddr, *laddr;
	u_int fport_arg, lport_arg;
{
	struct inpcbhead *head;
	struct inpcb *inp;
	u_int16_t fport = fport_arg, lport = lport_arg;

	head = IN6PCBHASH(table, faddr, fport, laddr, lport);
	LIST_FOREACH(inp, head, inp_hash) {
		if (!(inp->inp_flags & INP_IPV6))
			continue;
		if (IN6_ARE_ADDR_EQUAL(&inp->inp_faddr6, faddr) &&
		    inp->inp_fport == fport && inp->inp_lport == lport &&
		    IN6_ARE_ADDR_EQUAL(&inp->inp_laddr6, laddr)) {
			/*
			 * Move this PCB to the head of hash chain so that
			 * repeated accesses are quicker.  This is analogous to
			 * the historic single-entry PCB cache.
			 */
			if (inp != LIST_FIRST(head)) {
				LIST_REMOVE(inp, inp_hash);
				LIST_INSERT_HEAD(head, inp, inp_hash);
			}
			break;
		}
	}
#ifdef DIAGNOSTIC
	if (inp == NULL && in_pcbnotifymiss) {
		printf("in6_pcbhashlookup: faddr=");
		printf(" fport=%d laddr=", ntohs(fport));
		printf(" lport=%d\n", ntohs(lport));
	}
#endif
	return (inp);
}
#endif /* INET6 */

/*
 * The in(6)_pcblookup_listen functions are used to locate listening
 * sockets quickly.  This are sockets with unspecified foreign address
 * and port:
 *		*.*     <-> laddr.lport
 *		*.*     <->     *.lport
 */
struct inpcb *
in_pcblookup_listen(table, laddr, lport_arg, reverse)
	struct inpcbtable *table;
	struct in_addr laddr;
	u_int lport_arg;
	int reverse;
{
	struct inpcbhead *head;
	struct in_addr *key1, *key2;
	struct inpcb *inp;
	u_int16_t lport = lport_arg;

	if (reverse) {
		key1 = &zeroin_addr;
		key2 = &laddr;
	} else {
		key1 = &laddr;
		key2 = &zeroin_addr;
	}

	head = INPCBHASH(table, &zeroin_addr, 0, key1, lport);
	LIST_FOREACH(inp, head, inp_hash) {
#ifdef INET6
		if (inp->inp_flags & INP_IPV6)
			continue;	/*XXX*/
#endif
		if (inp->inp_lport == lport && inp->inp_fport == 0 &&
		    inp->inp_laddr.s_addr == key1->s_addr &&
		    inp->inp_faddr.s_addr == INADDR_ANY)
			break;
	}
	if (inp == NULL && key1->s_addr != key2->s_addr) {
		head = INPCBHASH(table, &zeroin_addr, 0, key2, lport);
		LIST_FOREACH(inp, head, inp_hash) {
#ifdef INET6
			if (inp->inp_flags & INP_IPV6)
				continue;	/*XXX*/
#endif
			if (inp->inp_lport == lport && inp->inp_fport == 0 &&
			    inp->inp_laddr.s_addr == key2->s_addr &&
			    inp->inp_faddr.s_addr == INADDR_ANY)
				break;
		}
	}
#ifdef DIAGNOSTIC
	if (inp == NULL && in_pcbnotifymiss) {
		printf("in_pcblookup_listen: laddr=%08x lport=%d\n",
		    ntohl(laddr.s_addr), ntohs(lport));
	}
#endif
	/*
	 * Move this PCB to the head of hash chain so that
	 * repeated accesses are quicker.  This is analogous to
	 * the historic single-entry PCB cache.
	 */
	if (inp != NULL && inp != LIST_FIRST(head)) {
		LIST_REMOVE(inp, inp_hash);
		LIST_INSERT_HEAD(head, inp, inp_hash);
	}
	return (inp);
}

#ifdef INET6
struct inpcb *
in6_pcblookup_listen(table, laddr, lport_arg, reverse)
	struct inpcbtable *table;
	struct in6_addr *laddr;
	u_int lport_arg;
	int reverse;
{
	struct inpcbhead *head;
	struct in6_addr *key1, *key2;
	struct inpcb *inp;
	u_int16_t lport = lport_arg;

	if (reverse) {
		key1 = &zeroin6_addr;
		key2 = laddr;
	} else {
		key1 = laddr;
		key2 = &zeroin6_addr;
	}

	head = IN6PCBHASH(table, &zeroin6_addr, 0, key1, lport);
	LIST_FOREACH(inp, head, inp_hash) {
		if (!(inp->inp_flags & INP_IPV6))
			continue;
		if (inp->inp_lport == lport && inp->inp_fport == 0 &&
		    IN6_ARE_ADDR_EQUAL(&inp->inp_laddr6, key1) &&
		    IN6_IS_ADDR_UNSPECIFIED(&inp->inp_faddr6))
			break;
	}
	if (inp == NULL && ! IN6_ARE_ADDR_EQUAL(key1, key2)) {
		head = IN6PCBHASH(table, &zeroin6_addr, 0, key2, lport);
		LIST_FOREACH(inp, head, inp_hash) {
			if (!(inp->inp_flags & INP_IPV6))
				continue;
			if (inp->inp_lport == lport && inp->inp_fport == 0 &&
		    	    IN6_ARE_ADDR_EQUAL(&inp->inp_laddr6, key2) &&
			    IN6_IS_ADDR_UNSPECIFIED(&inp->inp_faddr6))
				break;
		}
	}
#ifdef DIAGNOSTIC
	if (inp == NULL && in_pcbnotifymiss) {
		printf("in6_pcblookup_listen: laddr= lport=%d\n",
		    ntohs(lport));
	}
#endif
	/*
	 * Move this PCB to the head of hash chain so that
	 * repeated accesses are quicker.  This is analogous to
	 * the historic single-entry PCB cache.
	 */
	if (inp != NULL && inp != LIST_FIRST(head)) {
		LIST_REMOVE(inp, inp_hash);
		LIST_INSERT_HEAD(head, inp, inp_hash);
	}
	return (inp);
}
#endif /* INET6 */