summaryrefslogtreecommitdiffstats
path: root/sys/netinet/udp_usrreq.c
blob: 0966f2e842ee5df4e96f5b9905623206dd5f6842 (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
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
/*-
 * Copyright (c) 1982, 1986, 1988, 1990, 1993, 1995
 *	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.
 * 4. 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.
 *
 *	@(#)udp_usrreq.c	8.6 (Berkeley) 5/23/95
 * $FreeBSD$
 */

#include "opt_ipfw.h"
#include "opt_ipsec.h"
#include "opt_inet6.h"
#include "opt_mac.h"

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/domain.h>
#include <sys/eventhandler.h>
#include <sys/jail.h>
#include <sys/kernel.h>
#include <sys/lock.h>
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/priv.h>
#include <sys/proc.h>
#include <sys/protosw.h>
#include <sys/signalvar.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/sx.h>
#include <sys/sysctl.h>
#include <sys/syslog.h>

#include <vm/uma.h>

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

#include <netinet/in.h>
#include <netinet/in_systm.h>
#include <netinet/in_pcb.h>
#include <netinet/in_var.h>
#include <netinet/ip.h>
#ifdef INET6
#include <netinet/ip6.h>
#endif
#include <netinet/ip_icmp.h>
#include <netinet/icmp_var.h>
#include <netinet/ip_var.h>
#include <netinet/ip_options.h>
#ifdef INET6
#include <netinet6/ip6_var.h>
#endif
#include <netinet/udp.h>
#include <netinet/udp_var.h>

#ifdef FAST_IPSEC
#include <netipsec/ipsec.h>
#endif

#ifdef IPSEC
#include <netinet6/ipsec.h>
#endif

#include <machine/in_cksum.h>

#include <security/mac/mac_framework.h>

/*
 * UDP protocol implementation.
 * Per RFC 768, August, 1980.
 */

/*
 * BSD 4.2 defaulted the udp checksum to be off.  Turning off udp checksums
 * removes the only data integrity mechanism for packets and malformed
 * packets that would otherwise be discarded by bad checksums may cause
 * problems (especially for NFS data blocks).
 */
static int	udpcksum = 1;
SYSCTL_INT(_net_inet_udp, UDPCTL_CHECKSUM, checksum, CTLFLAG_RW, &udpcksum,
    0, "");

int	udp_log_in_vain = 0;
SYSCTL_INT(_net_inet_udp, OID_AUTO, log_in_vain, CTLFLAG_RW,
    &udp_log_in_vain, 0, "Log all incoming UDP packets");

static int	blackhole = 0;
SYSCTL_INT(_net_inet_udp, OID_AUTO, blackhole, CTLFLAG_RW, &blackhole, 0,
    "Do not send port unreachables for refused connects");

static int	strict_mcast_mship = 0;
SYSCTL_INT(_net_inet_udp, OID_AUTO, strict_mcast_mship, CTLFLAG_RW,
    &strict_mcast_mship, 0, "Only send multicast to member sockets");

struct	inpcbhead udb;		/* from udp_var.h */
struct	inpcbinfo udbinfo;

#ifndef UDBHASHSIZE
#define UDBHASHSIZE 16
#endif

struct	udpstat udpstat;	/* from udp_var.h */
SYSCTL_STRUCT(_net_inet_udp, UDPCTL_STATS, stats, CTLFLAG_RW, &udpstat,
    udpstat, "UDP statistics (struct udpstat, netinet/udp_var.h)");

static void	udp_append(struct inpcb *last, struct ip *ip, struct mbuf *n,
		    int off, struct sockaddr_in *udp_in);

static void	udp_detach(struct socket *so);
static int	udp_output(struct inpcb *, struct mbuf *, struct sockaddr *,
		    struct mbuf *, struct thread *);

static void
udp_zone_change(void *tag)
{

	uma_zone_set_max(udbinfo.ipi_zone, maxsockets);
}

static int
udp_inpcb_init(void *mem, int size, int flags)
{
	struct inpcb *inp = mem;

	INP_LOCK_INIT(inp, "inp", "udpinp");
	return (0);
}

void
udp_init()
{
	INP_INFO_LOCK_INIT(&udbinfo, "udp");
	LIST_INIT(&udb);
	udbinfo.listhead = &udb;
	udbinfo.hashbase = hashinit(UDBHASHSIZE, M_PCB, &udbinfo.hashmask);
	udbinfo.porthashbase = hashinit(UDBHASHSIZE, M_PCB,
	    &udbinfo.porthashmask);
	udbinfo.ipi_zone = uma_zcreate("udpcb", sizeof(struct inpcb), NULL,
	    NULL, udp_inpcb_init, NULL, UMA_ALIGN_PTR, UMA_ZONE_NOFREE);
	uma_zone_set_max(udbinfo.ipi_zone, maxsockets);
	EVENTHANDLER_REGISTER(maxsockets_change, udp_zone_change, NULL,
		EVENTHANDLER_PRI_ANY);
}

void
udp_input(struct mbuf *m, int off)
{
	int iphlen = off;
	struct ip *ip;
	struct udphdr *uh;
	struct inpcb *inp;
	int len;
	struct ip save_ip;
	struct sockaddr_in udp_in;
#ifdef IPFIREWALL_FORWARD
	struct m_tag *fwd_tag;
#endif

	udpstat.udps_ipackets++;

	/*
	 * Strip IP options, if any; should skip this, make available to
	 * user, and use on returned packets, but we don't yet have a way to
	 * check the checksum with options still present.
	 */
	if (iphlen > sizeof (struct ip)) {
		ip_stripoptions(m, (struct mbuf *)0);
		iphlen = sizeof(struct ip);
	}

	/*
	 * Get IP and UDP header together in first mbuf.
	 */
	ip = mtod(m, struct ip *);
	if (m->m_len < iphlen + sizeof(struct udphdr)) {
		if ((m = m_pullup(m, iphlen + sizeof(struct udphdr))) == 0) {
			udpstat.udps_hdrops++;
			return;
		}
		ip = mtod(m, struct ip *);
	}
	uh = (struct udphdr *)((caddr_t)ip + iphlen);

	/*
	 * Destination port of 0 is illegal, based on RFC768.
	 */
	if (uh->uh_dport == 0)
		goto badunlocked;

	/*
	 * Construct sockaddr format source address.  Stuff source address
	 * and datagram in user buffer.
	 */
	bzero(&udp_in, sizeof(udp_in));
	udp_in.sin_len = sizeof(udp_in);
	udp_in.sin_family = AF_INET;
	udp_in.sin_port = uh->uh_sport;
	udp_in.sin_addr = ip->ip_src;

	/*
	 * Make mbuf data length reflect UDP length.
	 * If not enough data to reflect UDP length, drop.
	 */
	len = ntohs((u_short)uh->uh_ulen);
	if (ip->ip_len != len) {
		if (len > ip->ip_len || len < sizeof(struct udphdr)) {
			udpstat.udps_badlen++;
			goto badunlocked;
		}
		m_adj(m, len - ip->ip_len);
		/* ip->ip_len = len; */
	}

	/*
	 * Save a copy of the IP header in case we want restore it for
	 * sending an ICMP error message in response.
	 */
	if (!blackhole)
		save_ip = *ip;

	/*
	 * Checksum extended UDP header and data.
	 */
	if (uh->uh_sum) {
		if (m->m_pkthdr.csum_flags & CSUM_DATA_VALID) {
			if (m->m_pkthdr.csum_flags & CSUM_PSEUDO_HDR)
				uh->uh_sum = m->m_pkthdr.csum_data;
			else
				uh->uh_sum = in_pseudo(ip->ip_src.s_addr,
				    ip->ip_dst.s_addr, htonl((u_short)len +
				    m->m_pkthdr.csum_data + IPPROTO_UDP));
			uh->uh_sum ^= 0xffff;
		} else {
			char b[9];
			bcopy(((struct ipovly *)ip)->ih_x1, b, 9);
			bzero(((struct ipovly *)ip)->ih_x1, 9);
			((struct ipovly *)ip)->ih_len = uh->uh_ulen;
			uh->uh_sum = in_cksum(m, len + sizeof (struct ip));
			bcopy(b, ((struct ipovly *)ip)->ih_x1, 9);
		}
		if (uh->uh_sum) {
			udpstat.udps_badsum++;
			m_freem(m);
			return;
		}
	} else
		udpstat.udps_nosum++;

#ifdef IPFIREWALL_FORWARD
	/*
	 * Grab info from PACKET_TAG_IPFORWARD tag prepended to the chain.
	 */
	fwd_tag = m_tag_find(m, PACKET_TAG_IPFORWARD, NULL);
	if (fwd_tag != NULL) {
		struct sockaddr_in *next_hop;

		/*
		 * Do the hack.
		 */
		next_hop = (struct sockaddr_in *)(fwd_tag + 1);
		ip->ip_dst = next_hop->sin_addr;
		uh->uh_dport = ntohs(next_hop->sin_port);

		/*
		 * Remove the tag from the packet.  We don't need it anymore.
		 */
		m_tag_delete(m, fwd_tag);
	}
#endif

	INP_INFO_RLOCK(&udbinfo);

	if (IN_MULTICAST(ntohl(ip->ip_dst.s_addr)) ||
	    in_broadcast(ip->ip_dst, m->m_pkthdr.rcvif)) {
		struct inpcb *last;

		/*
		 * Deliver a multicast or broadcast datagram to *all* sockets
		 * for which the local and remote addresses and ports match
		 * those of the incoming datagram.  This allows more than one
		 * process to receive multi/broadcasts on the same port.
		 * (This really ought to be done for unicast datagrams as
		 * well, but that would cause problems with existing
		 * applications that open both address-specific sockets and a
		 * wildcard socket listening to the same port -- they would
		 * end up receiving duplicates of every unicast datagram.
		 * Those applications open the multiple sockets to overcome
		 * an inadequacy of the UDP socket interface, but for
		 * backwards compatibility we avoid the problem here rather
		 * than fixing the interface.  Maybe 4.5BSD will remedy
		 * this?)
		 */
		last = NULL;
		LIST_FOREACH(inp, &udb, inp_list) {
			if (inp->inp_lport != uh->uh_dport)
				continue;
#ifdef INET6
			if ((inp->inp_vflag & INP_IPV4) == 0)
				continue;
#endif
			if (inp->inp_laddr.s_addr != INADDR_ANY) {
				if (inp->inp_laddr.s_addr != ip->ip_dst.s_addr)
					continue;
			}
			if (inp->inp_faddr.s_addr != INADDR_ANY) {
				if (inp->inp_faddr.s_addr !=
				    ip->ip_src.s_addr ||
				    inp->inp_fport != uh->uh_sport)
					continue;
			}

			/*
			 * Check multicast packets to make sure they are only
			 * sent to sockets with multicast memberships for the
			 * packet's destination address and arrival interface
			 */
#define MSHIP(_inp, n) ((_inp)->inp_moptions->imo_membership[(n)])
#define NMSHIPS(_inp) ((_inp)->inp_moptions->imo_num_memberships)
			INP_LOCK(inp);
			if (strict_mcast_mship && inp->inp_moptions != NULL) {
				int mship, foundmship = 0;

				for (mship = 0; mship < NMSHIPS(inp);
				    mship++) {
					if (MSHIP(inp, mship)->inm_addr.s_addr
					    == ip->ip_dst.s_addr &&
					    MSHIP(inp, mship)->inm_ifp
					    == m->m_pkthdr.rcvif) {
						foundmship = 1;
						break;
					}
				}
				if (foundmship == 0) {
					INP_UNLOCK(inp);
					continue;
				}
			}
#undef NMSHIPS
#undef MSHIP
			if (last != NULL) {
				struct mbuf *n;

				n = m_copy(m, 0, M_COPYALL);
				if (n != NULL)
					udp_append(last, ip, n, iphlen +
					    sizeof(struct udphdr), &udp_in);
				INP_UNLOCK(last);
			}
			last = inp;
			/*
			 * Don't look for additional matches if this one does
			 * not have either the SO_REUSEPORT or SO_REUSEADDR
			 * socket options set.  This heuristic avoids
			 * searching through all pcbs in the common case of a
			 * non-shared port.  It assumes that an application
			 * will never clear these options after setting them.
			 */
			if ((last->inp_socket->so_options &
			    (SO_REUSEPORT|SO_REUSEADDR)) == 0)
				break;
		}

		if (last == NULL) {
			/*
			 * No matching pcb found; discard datagram.  (No need
			 * to send an ICMP Port Unreachable for a broadcast
			 * or multicast datgram.)
			 */
			udpstat.udps_noportbcast++;
			goto badheadlocked;
		}
		udp_append(last, ip, m, iphlen + sizeof(struct udphdr),
		    &udp_in);
		INP_UNLOCK(last);
		INP_INFO_RUNLOCK(&udbinfo);
		return;
	}

	/*
	 * Locate pcb for datagram.
	 */
	inp = in_pcblookup_hash(&udbinfo, ip->ip_src, uh->uh_sport,
	    ip->ip_dst, uh->uh_dport, 1, m->m_pkthdr.rcvif);
	if (inp == NULL) {
		if (udp_log_in_vain) {
			char buf[4*sizeof "123"];

			strcpy(buf, inet_ntoa(ip->ip_dst));
			log(LOG_INFO,
			    "Connection attempt to UDP %s:%d from %s:%d\n",
			    buf, ntohs(uh->uh_dport), inet_ntoa(ip->ip_src),
			    ntohs(uh->uh_sport));
		}
		udpstat.udps_noport++;
		if (m->m_flags & (M_BCAST | M_MCAST)) {
			udpstat.udps_noportbcast++;
			goto badheadlocked;
		}
		if (blackhole)
			goto badheadlocked;
		if (badport_bandlim(BANDLIM_ICMP_UNREACH) < 0)
			goto badheadlocked;
		*ip = save_ip;
		ip->ip_len += iphlen;
		icmp_error(m, ICMP_UNREACH, ICMP_UNREACH_PORT, 0, 0);
		INP_INFO_RUNLOCK(&udbinfo);
		return;
	}

	/*
	 * Check the minimum TTL for socket.
	 */
	INP_LOCK(inp);
	if (inp->inp_ip_minttl && inp->inp_ip_minttl > ip->ip_ttl)
		goto badheadlocked;
	udp_append(inp, ip, m, iphlen + sizeof(struct udphdr), &udp_in);
	INP_UNLOCK(inp);
	INP_INFO_RUNLOCK(&udbinfo);
	return;

badheadlocked:
	if (inp)
		INP_UNLOCK(inp);
	INP_INFO_RUNLOCK(&udbinfo);
badunlocked:
	m_freem(m);
}

/*
 * Subroutine of udp_input(), which appends the provided mbuf chain to the
 * passed pcb/socket.  The caller must provide a sockaddr_in via udp_in that
 * contains the source address.  If the socket ends up being an IPv6 socket,
 * udp_append() will convert to a sockaddr_in6 before passing the address
 * into the socket code.
 */
static void
udp_append(struct inpcb *inp, struct ip *ip, struct mbuf *n, int off,
    struct sockaddr_in *udp_in)
{
	struct sockaddr *append_sa;
	struct socket *so;
	struct mbuf *opts = 0;
#ifdef INET6
	struct sockaddr_in6 udp_in6;
#endif

	INP_LOCK_ASSERT(inp);

#if defined(IPSEC) || defined(FAST_IPSEC)
	/* check AH/ESP integrity. */
	if (ipsec4_in_reject(n, inp)) {
#ifdef IPSEC
		ipsecstat.in_polvio++;
#endif
		m_freem(n);
		return;
	}
#endif /*IPSEC || FAST_IPSEC*/
#ifdef MAC
	if (mac_check_inpcb_deliver(inp, n) != 0) {
		m_freem(n);
		return;
	}
#endif
	if (inp->inp_flags & INP_CONTROLOPTS ||
	    inp->inp_socket->so_options & (SO_TIMESTAMP | SO_BINTIME)) {
#ifdef INET6
		if (inp->inp_vflag & INP_IPV6) {
			int savedflags;

			savedflags = inp->inp_flags;
			inp->inp_flags &= ~INP_UNMAPPABLEOPTS;
			ip6_savecontrol(inp, n, &opts);
			inp->inp_flags = savedflags;
		} else
#endif
			ip_savecontrol(inp, &opts, ip, n);
	}
#ifdef INET6
	if (inp->inp_vflag & INP_IPV6) {
		bzero(&udp_in6, sizeof(udp_in6));
		udp_in6.sin6_len = sizeof(udp_in6);
		udp_in6.sin6_family = AF_INET6;
		in6_sin_2_v4mapsin6(udp_in, &udp_in6);
		append_sa = (struct sockaddr *)&udp_in6;
	} else
#endif
		append_sa = (struct sockaddr *)udp_in;
	m_adj(n, off);

	so = inp->inp_socket;
	SOCKBUF_LOCK(&so->so_rcv);
	if (sbappendaddr_locked(&so->so_rcv, append_sa, n, opts) == 0) {
		m_freem(n);
		if (opts)
			m_freem(opts);
		udpstat.udps_fullsock++;
		SOCKBUF_UNLOCK(&so->so_rcv);
	} else
		sorwakeup_locked(so);
}

/*
 * Notify a udp user of an asynchronous error; just wake up so that they can
 * collect error status.
 */
struct inpcb *
udp_notify(struct inpcb *inp, int errno)
{

	inp->inp_socket->so_error = errno;
	sorwakeup(inp->inp_socket);
	sowwakeup(inp->inp_socket);
	return (inp);
}

void
udp_ctlinput(int cmd, struct sockaddr *sa, void *vip)
{
	struct ip *ip = vip;
	struct udphdr *uh;
	struct inpcb *(*notify)(struct inpcb *, int) = udp_notify;
	struct in_addr faddr;
	struct inpcb *inp;

	faddr = ((struct sockaddr_in *)sa)->sin_addr;
	if (sa->sa_family != AF_INET || faddr.s_addr == INADDR_ANY)
		return;

	/*
	 * Redirects don't need to be handled up here.
	 */
	if (PRC_IS_REDIRECT(cmd))
		return;

	/*
	 * Hostdead is ugly because it goes linearly through all PCBs.
	 *
	 * XXX: We never get this from ICMP, otherwise it makes an excellent
	 * DoS attack on machines with many connections.
	 */
	if (cmd == PRC_HOSTDEAD)
		ip = 0;
	else if ((unsigned)cmd >= PRC_NCMDS || inetctlerrmap[cmd] == 0)
		return;
	if (ip) {
		uh = (struct udphdr *)((caddr_t)ip + (ip->ip_hl << 2));
		INP_INFO_RLOCK(&udbinfo);
		inp = in_pcblookup_hash(&udbinfo, faddr, uh->uh_dport,
		    ip->ip_src, uh->uh_sport, 0, NULL);
		if (inp != NULL) {
			INP_LOCK(inp);
			if (inp->inp_socket != NULL) {
				(*notify)(inp, inetctlerrmap[cmd]);
			}
			INP_UNLOCK(inp);
		}
		INP_INFO_RUNLOCK(&udbinfo);
	} else
		in_pcbnotifyall(&udbinfo, faddr, inetctlerrmap[cmd], notify);
}

static int
udp_pcblist(SYSCTL_HANDLER_ARGS)
{
	int error, i, n;
	struct inpcb *inp, **inp_list;
	inp_gen_t gencnt;
	struct xinpgen xig;

	/*
	 * The process of preparing the TCB list is too time-consuming and
	 * resource-intensive to repeat twice on every request.
	 */
	if (req->oldptr == 0) {
		n = udbinfo.ipi_count;
		req->oldidx = 2 * (sizeof xig)
			+ (n + n/8) * sizeof(struct xinpcb);
		return (0);
	}

	if (req->newptr != 0)
		return (EPERM);

	/*
	 * OK, now we're committed to doing something.
	 */
	INP_INFO_RLOCK(&udbinfo);
	gencnt = udbinfo.ipi_gencnt;
	n = udbinfo.ipi_count;
	INP_INFO_RUNLOCK(&udbinfo);

	error = sysctl_wire_old_buffer(req, 2 * (sizeof xig)
		+ n * sizeof(struct xinpcb));
	if (error != 0)
		return (error);

	xig.xig_len = sizeof xig;
	xig.xig_count = n;
	xig.xig_gen = gencnt;
	xig.xig_sogen = so_gencnt;
	error = SYSCTL_OUT(req, &xig, sizeof xig);
	if (error)
		return (error);

	inp_list = malloc(n * sizeof *inp_list, M_TEMP, M_WAITOK);
	if (inp_list == 0)
		return (ENOMEM);

	INP_INFO_RLOCK(&udbinfo);
	for (inp = LIST_FIRST(udbinfo.listhead), i = 0; inp && i < n;
	     inp = LIST_NEXT(inp, inp_list)) {
		INP_LOCK(inp);
		if (inp->inp_gencnt <= gencnt &&
		    cr_canseesocket(req->td->td_ucred, inp->inp_socket) == 0)
			inp_list[i++] = inp;
		INP_UNLOCK(inp);
	}
	INP_INFO_RUNLOCK(&udbinfo);
	n = i;

	error = 0;
	for (i = 0; i < n; i++) {
		inp = inp_list[i];
		INP_LOCK(inp);
		if (inp->inp_gencnt <= gencnt) {
			struct xinpcb xi;
			bzero(&xi, sizeof(xi));
			xi.xi_len = sizeof xi;
			/* XXX should avoid extra copy */
			bcopy(inp, &xi.xi_inp, sizeof *inp);
			if (inp->inp_socket)
				sotoxsocket(inp->inp_socket, &xi.xi_socket);
			xi.xi_inp.inp_gencnt = inp->inp_gencnt;
			INP_UNLOCK(inp);
			error = SYSCTL_OUT(req, &xi, sizeof xi);
		} else
			INP_UNLOCK(inp);
	}
	if (!error) {
		/*
		 * Give the user an updated idea of our state.  If the
		 * generation differs from what we told her before, she knows
		 * that something happened while we were processing this
		 * request, and it might be necessary to retry.
		 */
		INP_INFO_RLOCK(&udbinfo);
		xig.xig_gen = udbinfo.ipi_gencnt;
		xig.xig_sogen = so_gencnt;
		xig.xig_count = udbinfo.ipi_count;
		INP_INFO_RUNLOCK(&udbinfo);
		error = SYSCTL_OUT(req, &xig, sizeof xig);
	}
	free(inp_list, M_TEMP);
	return (error);
}

SYSCTL_PROC(_net_inet_udp, UDPCTL_PCBLIST, pcblist, CTLFLAG_RD, 0, 0,
    udp_pcblist, "S,xinpcb", "List of active UDP sockets");

static int
udp_getcred(SYSCTL_HANDLER_ARGS)
{
	struct xucred xuc;
	struct sockaddr_in addrs[2];
	struct inpcb *inp;
	int error;

	error = priv_check_cred(req->td->td_ucred, PRIV_NETINET_GETCRED,
	    SUSER_ALLOWJAIL);
	if (error)
		return (error);
	error = SYSCTL_IN(req, addrs, sizeof(addrs));
	if (error)
		return (error);
	INP_INFO_RLOCK(&udbinfo);
	inp = in_pcblookup_hash(&udbinfo, addrs[1].sin_addr, addrs[1].sin_port,
				addrs[0].sin_addr, addrs[0].sin_port, 1, NULL);
	if (inp == NULL || inp->inp_socket == NULL) {
		error = ENOENT;
		goto out;
	}
	error = cr_canseesocket(req->td->td_ucred, inp->inp_socket);
	if (error)
		goto out;
	cru2x(inp->inp_socket->so_cred, &xuc);
out:
	INP_INFO_RUNLOCK(&udbinfo);
	if (error == 0)
		error = SYSCTL_OUT(req, &xuc, sizeof(struct xucred));
	return (error);
}

SYSCTL_PROC(_net_inet_udp, OID_AUTO, getcred,
    CTLTYPE_OPAQUE|CTLFLAG_RW|CTLFLAG_PRISON, 0, 0,
    udp_getcred, "S,xucred", "Get the xucred of a UDP connection");

static int
udp_output(struct inpcb *inp, struct mbuf *m, struct sockaddr *addr,
    struct mbuf *control, struct thread *td)
{
	struct udpiphdr *ui;
	int len = m->m_pkthdr.len;
	struct in_addr faddr, laddr;
	struct cmsghdr *cm;
	struct sockaddr_in *sin, src;
	int error = 0;
	int ipflags;
	u_short fport, lport;
	int unlock_udbinfo;

	/*
	 * udp_output() may need to temporarily bind or connect the current
	 * inpcb.  As such, we don't know up front what inpcb locks we will
	 * need.  Do any work to decide what is needed up front before
	 * acquiring locks.
	 */
	if (len + sizeof(struct udpiphdr) > IP_MAXPACKET) {
		if (control)
			m_freem(control);
		m_freem(m);
		return (EMSGSIZE);
	}

	src.sin_family = 0;
	if (control != NULL) {
		/*
		 * XXX: Currently, we assume all the optional information is
		 * stored in a single mbuf.
		 */
		if (control->m_next) {
			m_freem(control);
			m_freem(m);
			return (EINVAL);
		}
		for (; control->m_len > 0;
		    control->m_data += CMSG_ALIGN(cm->cmsg_len),
		    control->m_len -= CMSG_ALIGN(cm->cmsg_len)) {
			cm = mtod(control, struct cmsghdr *);
			if (control->m_len < sizeof(*cm) || cm->cmsg_len == 0 ||
			    cm->cmsg_len > control->m_len) {
				error = EINVAL;
				break;
			}
			if (cm->cmsg_level != IPPROTO_IP)
				continue;

			switch (cm->cmsg_type) {
			case IP_SENDSRCADDR:
				if (cm->cmsg_len !=
				    CMSG_LEN(sizeof(struct in_addr))) {
					error = EINVAL;
					break;
				}
				bzero(&src, sizeof(src));
				src.sin_family = AF_INET;
				src.sin_len = sizeof(src);
				src.sin_port = inp->inp_lport;
				src.sin_addr = *(struct in_addr *)CMSG_DATA(cm);
				break;
			default:
				error = ENOPROTOOPT;
				break;
			}
			if (error)
				break;
		}
		m_freem(control);
	}
	if (error) {
		m_freem(m);
		return (error);
	}

	if (src.sin_family == AF_INET || addr != NULL) {
		INP_INFO_WLOCK(&udbinfo);
		unlock_udbinfo = 1;
	} else
		unlock_udbinfo = 0;
	INP_LOCK(inp);

#ifdef MAC
	mac_create_mbuf_from_inpcb(inp, m);
#endif

	/*
	 * If the IP_SENDSRCADDR control message was specified, override the
	 * source address for this datagram. Its use is invalidated if the
	 * address thus specified is incomplete or clobbers other inpcbs.
	 */
	laddr = inp->inp_laddr;
	lport = inp->inp_lport;
	if (src.sin_family == AF_INET) {
		if ((lport == 0) ||
		    (laddr.s_addr == INADDR_ANY &&
		     src.sin_addr.s_addr == INADDR_ANY)) {
			error = EINVAL;
			goto release;
		}
		error = in_pcbbind_setup(inp, (struct sockaddr *)&src,
		    &laddr.s_addr, &lport, td->td_ucred);
		if (error)
			goto release;
	}

	if (addr) {
		sin = (struct sockaddr_in *)addr;
		if (jailed(td->td_ucred))
			prison_remote_ip(td->td_ucred, 0,
			    &sin->sin_addr.s_addr);
		if (inp->inp_faddr.s_addr != INADDR_ANY) {
			error = EISCONN;
			goto release;
		}
		error = in_pcbconnect_setup(inp, addr, &laddr.s_addr, &lport,
		    &faddr.s_addr, &fport, NULL, td->td_ucred);
		if (error)
			goto release;

		/* Commit the local port if newly assigned. */
		if (inp->inp_laddr.s_addr == INADDR_ANY &&
		    inp->inp_lport == 0) {
			/*
			 * Remember addr if jailed, to prevent rebinding.
			 */
			if (jailed(td->td_ucred))
				inp->inp_laddr = laddr;
			inp->inp_lport = lport;
			if (in_pcbinshash(inp) != 0) {
				inp->inp_lport = 0;
				error = EAGAIN;
				goto release;
			}
			inp->inp_flags |= INP_ANONPORT;
		}
	} else {
		faddr = inp->inp_faddr;
		fport = inp->inp_fport;
		if (faddr.s_addr == INADDR_ANY) {
			error = ENOTCONN;
			goto release;
		}
	}

	/*
	 * Calculate data length and get a mbuf for UDP, IP, and possible
	 * link-layer headers.  Immediate slide the data pointer back forward
	 * since we won't use that space at this layer.
	 */
	M_PREPEND(m, sizeof(struct udpiphdr) + max_linkhdr, M_DONTWAIT);
	if (m == NULL) {
		error = ENOBUFS;
		goto release;
	}
	m->m_data += max_linkhdr;
	m->m_len -= max_linkhdr;
	m->m_pkthdr.len -= max_linkhdr;

	/*
	 * Fill in mbuf with extended UDP header and addresses and length put
	 * into network format.
	 */
	ui = mtod(m, struct udpiphdr *);
	bzero(ui->ui_x1, sizeof(ui->ui_x1));	/* XXX still needed? */
	ui->ui_pr = IPPROTO_UDP;
	ui->ui_src = laddr;
	ui->ui_dst = faddr;
	ui->ui_sport = lport;
	ui->ui_dport = fport;
	ui->ui_ulen = htons((u_short)len + sizeof(struct udphdr));

	/*
	 * Set the Don't Fragment bit in the IP header.
	 */
	if (inp->inp_flags & INP_DONTFRAG) {
		struct ip *ip;

		ip = (struct ip *)&ui->ui_i;
		ip->ip_off |= IP_DF;
	}

	ipflags = 0;
	if (inp->inp_socket->so_options & SO_DONTROUTE)
		ipflags |= IP_ROUTETOIF;
	if (inp->inp_socket->so_options & SO_BROADCAST)
		ipflags |= IP_ALLOWBROADCAST;
	if (inp->inp_flags & INP_ONESBCAST)
		ipflags |= IP_SENDONES;

	/*
	 * Set up checksum and output datagram.
	 */
	if (udpcksum) {
		if (inp->inp_flags & INP_ONESBCAST)
			faddr.s_addr = INADDR_BROADCAST;
		ui->ui_sum = in_pseudo(ui->ui_src.s_addr, faddr.s_addr,
		    htons((u_short)len + sizeof(struct udphdr) + IPPROTO_UDP));
		m->m_pkthdr.csum_flags = CSUM_UDP;
		m->m_pkthdr.csum_data = offsetof(struct udphdr, uh_sum);
	} else
		ui->ui_sum = 0;
	((struct ip *)ui)->ip_len = sizeof (struct udpiphdr) + len;
	((struct ip *)ui)->ip_ttl = inp->inp_ip_ttl;	/* XXX */
	((struct ip *)ui)->ip_tos = inp->inp_ip_tos;	/* XXX */
	udpstat.udps_opackets++;

	if (unlock_udbinfo)
		INP_INFO_WUNLOCK(&udbinfo);
	error = ip_output(m, inp->inp_options, NULL, ipflags,
	    inp->inp_moptions, inp);
	INP_UNLOCK(inp);
	return (error);

release:
	INP_UNLOCK(inp);
	if (unlock_udbinfo)
		INP_INFO_WUNLOCK(&udbinfo);
	m_freem(m);
	return (error);
}

u_long	udp_sendspace = 9216;		/* really max datagram size */
					/* 40 1K datagrams */
SYSCTL_ULONG(_net_inet_udp, UDPCTL_MAXDGRAM, maxdgram, CTLFLAG_RW,
    &udp_sendspace, 0, "Maximum outgoing UDP datagram size");

u_long	udp_recvspace = 40 * (1024 +
#ifdef INET6
				      sizeof(struct sockaddr_in6)
#else
				      sizeof(struct sockaddr_in)
#endif
				      );
SYSCTL_ULONG(_net_inet_udp, UDPCTL_RECVSPACE, recvspace, CTLFLAG_RW,
    &udp_recvspace, 0, "Maximum space for incoming UDP datagrams");

static void
udp_abort(struct socket *so)
{
	struct inpcb *inp;

	inp = sotoinpcb(so);
	KASSERT(inp != NULL, ("udp_abort: inp == NULL"));
	INP_INFO_WLOCK(&udbinfo);
	INP_LOCK(inp);
	if (inp->inp_faddr.s_addr != INADDR_ANY) {
		in_pcbdisconnect(inp);
		inp->inp_laddr.s_addr = INADDR_ANY;
		soisdisconnected(so);
	}
	INP_UNLOCK(inp);
	INP_INFO_WUNLOCK(&udbinfo);
}

static int
udp_attach(struct socket *so, int proto, struct thread *td)
{
	struct inpcb *inp;
	int error;

	inp = sotoinpcb(so);
	KASSERT(inp == NULL, ("udp_attach: inp != NULL"));
	error = soreserve(so, udp_sendspace, udp_recvspace);
	if (error)
		return (error);
	INP_INFO_WLOCK(&udbinfo);
	error = in_pcballoc(so, &udbinfo);
	if (error) {
		INP_INFO_WUNLOCK(&udbinfo);
		return (error);
	}

	inp = (struct inpcb *)so->so_pcb;
	INP_INFO_WUNLOCK(&udbinfo);
	inp->inp_vflag |= INP_IPV4;
	inp->inp_ip_ttl = ip_defttl;
	INP_UNLOCK(inp);
	return (0);
}

static int
udp_bind(struct socket *so, struct sockaddr *nam, struct thread *td)
{
	struct inpcb *inp;
	int error;

	inp = sotoinpcb(so);
	KASSERT(inp != NULL, ("udp_bind: inp == NULL"));
	INP_INFO_WLOCK(&udbinfo);
	INP_LOCK(inp);
	error = in_pcbbind(inp, nam, td->td_ucred);
	INP_UNLOCK(inp);
	INP_INFO_WUNLOCK(&udbinfo);
	return (error);
}

static void
udp_close(struct socket *so)
{
	struct inpcb *inp;

	inp = sotoinpcb(so);
	KASSERT(inp != NULL, ("udp_close: inp == NULL"));
	INP_INFO_WLOCK(&udbinfo);
	INP_LOCK(inp);
	if (inp->inp_faddr.s_addr != INADDR_ANY) {
		in_pcbdisconnect(inp);
		inp->inp_laddr.s_addr = INADDR_ANY;
		soisdisconnected(so);
	}
	INP_UNLOCK(inp);
	INP_INFO_WUNLOCK(&udbinfo);
}

static int
udp_connect(struct socket *so, struct sockaddr *nam, struct thread *td)
{
	struct inpcb *inp;
	int error;
	struct sockaddr_in *sin;

	inp = sotoinpcb(so);
	KASSERT(inp != NULL, ("udp_connect: inp == NULL"));
	INP_INFO_WLOCK(&udbinfo);
	INP_LOCK(inp);
	if (inp->inp_faddr.s_addr != INADDR_ANY) {
		INP_UNLOCK(inp);
		INP_INFO_WUNLOCK(&udbinfo);
		return (EISCONN);
	}
	sin = (struct sockaddr_in *)nam;
	if (jailed(td->td_ucred))
		prison_remote_ip(td->td_ucred, 0, &sin->sin_addr.s_addr);
	error = in_pcbconnect(inp, nam, td->td_ucred);
	if (error == 0)
		soisconnected(so);
	INP_UNLOCK(inp);
	INP_INFO_WUNLOCK(&udbinfo);
	return (error);
}

static void
udp_detach(struct socket *so)
{
	struct inpcb *inp;

	inp = sotoinpcb(so);
	KASSERT(inp != NULL, ("udp_detach: inp == NULL"));
	KASSERT(inp->inp_faddr.s_addr == INADDR_ANY,
	    ("udp_detach: not disconnected"));
	INP_INFO_WLOCK(&udbinfo);
	INP_LOCK(inp);
	in_pcbdetach(inp);
	in_pcbfree(inp);
	INP_INFO_WUNLOCK(&udbinfo);
}

static int
udp_disconnect(struct socket *so)
{
	struct inpcb *inp;

	inp = sotoinpcb(so);
	KASSERT(inp != NULL, ("udp_disconnect: inp == NULL"));
	INP_INFO_WLOCK(&udbinfo);
	INP_LOCK(inp);
	if (inp->inp_faddr.s_addr == INADDR_ANY) {
		INP_INFO_WUNLOCK(&udbinfo);
		INP_UNLOCK(inp);
		return (ENOTCONN);
	}

	in_pcbdisconnect(inp);
	inp->inp_laddr.s_addr = INADDR_ANY;
	SOCK_LOCK(so);
	so->so_state &= ~SS_ISCONNECTED;		/* XXX */
	SOCK_UNLOCK(so);
	INP_UNLOCK(inp);
	INP_INFO_WUNLOCK(&udbinfo);
	return (0);
}

static int
udp_send(struct socket *so, int flags, struct mbuf *m, struct sockaddr *addr,
    struct mbuf *control, struct thread *td)
{
	struct inpcb *inp;

	inp = sotoinpcb(so);
	KASSERT(inp != NULL, ("udp_send: inp == NULL"));
	return (udp_output(inp, m, addr, control, td));
}

int
udp_shutdown(struct socket *so)
{
	struct inpcb *inp;

	inp = sotoinpcb(so);
	KASSERT(inp != NULL, ("udp_shutdown: inp == NULL"));
	INP_LOCK(inp);
	socantsendmore(so);
	INP_UNLOCK(inp);
	return (0);
}

/*
 * This is the wrapper function for in_setsockaddr.  We just pass down the
 * pcbinfo for in_setsockaddr() to lock.  We don't want to do the locking
 * here because in_setsockaddr() will call malloc and might block.
 */
static int
udp_sockaddr(struct socket *so, struct sockaddr **nam)
{

	return (in_setsockaddr(so, nam, &udbinfo));
}

/*
 * This is the wrapper function for in_setpeeraddr().  We just pass down the
 * pcbinfo for in_setpeeraddr() to lock.
 */
static int
udp_peeraddr(struct socket *so, struct sockaddr **nam)
{

	return (in_setpeeraddr(so, nam, &udbinfo));
}

struct pr_usrreqs udp_usrreqs = {
	.pru_abort =		udp_abort,
	.pru_attach =		udp_attach,
	.pru_bind =		udp_bind,
	.pru_connect =		udp_connect,
	.pru_control =		in_control,
	.pru_detach =		udp_detach,
	.pru_disconnect =	udp_disconnect,
	.pru_peeraddr =		udp_peeraddr,
	.pru_send =		udp_send,
	.pru_sosend =		sosend_dgram,
	.pru_shutdown =		udp_shutdown,
	.pru_sockaddr =		udp_sockaddr,
	.pru_sosetlabel =	in_pcbsosetlabel,
	.pru_close =		udp_close,
};
OpenPOWER on IntegriCloud