aboutsummaryrefslogtreecommitdiff
path: root/sys/netinet/ip_output.c
blob: 22f223d97d036714c82c691f3f656530454ca303 (plain) (blame)
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
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
/*-
 * SPDX-License-Identifier: BSD-3-Clause
 *
 * Copyright (c) 1982, 1986, 1988, 1990, 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.
 *
 *	@(#)ip_output.c	8.3 (Berkeley) 1/21/94
 */

#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");

#include "opt_inet.h"
#include "opt_ipsec.h"
#include "opt_kern_tls.h"
#include "opt_mbuf_stress_test.h"
#include "opt_mpath.h"
#include "opt_ratelimit.h"
#include "opt_route.h"
#include "opt_rss.h"
#include "opt_sctp.h"

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/kernel.h>
#include <sys/ktls.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/rmlock.h>
#include <sys/sdt.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/sysctl.h>
#include <sys/ucred.h>

#include <net/if.h>
#include <net/if_var.h>
#include <net/if_llatbl.h>
#include <net/netisr.h>
#include <net/pfil.h>
#include <net/route.h>
#include <net/route/nhop.h>
#include <net/rss_config.h>
#include <net/vnet.h>

#include <netinet/in.h>
#include <netinet/in_fib.h>
#include <netinet/in_kdtrace.h>
#include <netinet/in_systm.h>
#include <netinet/ip.h>
#include <netinet/in_fib.h>
#include <netinet/in_pcb.h>
#include <netinet/in_rss.h>
#include <netinet/in_var.h>
#include <netinet/ip_var.h>
#include <netinet/ip_options.h>

#include <netinet/udp.h>
#include <netinet/udp_var.h>

#ifdef SCTP
#include <netinet/sctp.h>
#include <netinet/sctp_crc32.h>
#endif

#include <netipsec/ipsec_support.h>

#include <machine/in_cksum.h>

#include <security/mac/mac_framework.h>

#ifdef MBUF_STRESS_TEST
static int mbuf_frag_size = 0;
SYSCTL_INT(_net_inet_ip, OID_AUTO, mbuf_frag_size, CTLFLAG_RW,
	&mbuf_frag_size, 0, "Fragment outgoing mbufs to this size");
#endif

static void	ip_mloopback(struct ifnet *, const struct mbuf *, int);


extern int in_mcast_loop;
extern	struct protosw inetsw[];

static inline int
ip_output_pfil(struct mbuf **mp, struct ifnet *ifp, int flags,
    struct inpcb *inp, struct sockaddr_in *dst, int *fibnum, int *error)
{
	struct m_tag *fwd_tag = NULL;
	struct mbuf *m;
	struct in_addr odst;
	struct ip *ip;
	int pflags = PFIL_OUT;

	if (flags & IP_FORWARDING)
		pflags |= PFIL_FWD;

	m = *mp;
	ip = mtod(m, struct ip *);

	/* Run through list of hooks for output packets. */
	odst.s_addr = ip->ip_dst.s_addr;
	switch (pfil_run_hooks(V_inet_pfil_head, mp, ifp, pflags, inp)) {
	case PFIL_DROPPED:
		*error = EACCES;
		/* FALLTHROUGH */
	case PFIL_CONSUMED:
		return 1; /* Finished */
	case PFIL_PASS:
		*error = 0;
	}
	m = *mp;
	ip = mtod(m, struct ip *);

	/* See if destination IP address was changed by packet filter. */
	if (odst.s_addr != ip->ip_dst.s_addr) {
		m->m_flags |= M_SKIP_FIREWALL;
		/* If destination is now ourself drop to ip_input(). */
		if (in_localip(ip->ip_dst)) {
			m->m_flags |= M_FASTFWD_OURS;
			if (m->m_pkthdr.rcvif == NULL)
				m->m_pkthdr.rcvif = V_loif;
			if (m->m_pkthdr.csum_flags & CSUM_DELAY_DATA) {
				m->m_pkthdr.csum_flags |=
					CSUM_DATA_VALID | CSUM_PSEUDO_HDR;
				m->m_pkthdr.csum_data = 0xffff;
			}
			m->m_pkthdr.csum_flags |=
				CSUM_IP_CHECKED | CSUM_IP_VALID;
#ifdef SCTP
			if (m->m_pkthdr.csum_flags & CSUM_SCTP)
				m->m_pkthdr.csum_flags |= CSUM_SCTP_VALID;
#endif
			*error = netisr_queue(NETISR_IP, m);
			return 1; /* Finished */
		}

		bzero(dst, sizeof(*dst));
		dst->sin_family = AF_INET;
		dst->sin_len = sizeof(*dst);
		dst->sin_addr = ip->ip_dst;

		return -1; /* Reloop */
	}
	/* See if fib was changed by packet filter. */
	if ((*fibnum) != M_GETFIB(m)) {
		m->m_flags |= M_SKIP_FIREWALL;
		*fibnum = M_GETFIB(m);
		return -1; /* Reloop for FIB change */
	}

	/* See if local, if yes, send it to netisr with IP_FASTFWD_OURS. */
	if (m->m_flags & M_FASTFWD_OURS) {
		if (m->m_pkthdr.rcvif == NULL)
			m->m_pkthdr.rcvif = V_loif;
		if (m->m_pkthdr.csum_flags & CSUM_DELAY_DATA) {
			m->m_pkthdr.csum_flags |=
				CSUM_DATA_VALID | CSUM_PSEUDO_HDR;
			m->m_pkthdr.csum_data = 0xffff;
		}
#ifdef SCTP
		if (m->m_pkthdr.csum_flags & CSUM_SCTP)
			m->m_pkthdr.csum_flags |= CSUM_SCTP_VALID;
#endif
		m->m_pkthdr.csum_flags |=
			CSUM_IP_CHECKED | CSUM_IP_VALID;

		*error = netisr_queue(NETISR_IP, m);
		return 1; /* Finished */
	}
	/* Or forward to some other address? */
	if ((m->m_flags & M_IP_NEXTHOP) &&
	    ((fwd_tag = m_tag_find(m, PACKET_TAG_IPFORWARD, NULL)) != NULL)) {
		bcopy((fwd_tag+1), dst, sizeof(struct sockaddr_in));
		m->m_flags |= M_SKIP_FIREWALL;
		m->m_flags &= ~M_IP_NEXTHOP;
		m_tag_delete(m, fwd_tag);

		return -1; /* Reloop for CHANGE of dst */
	}

	return 0;
}

static int
ip_output_send(struct inpcb *inp, struct ifnet *ifp, struct mbuf *m,
    const struct sockaddr_in *gw, struct route *ro, bool stamp_tag)
{
#ifdef KERN_TLS
	struct ktls_session *tls = NULL;
#endif
	struct m_snd_tag *mst;
	int error;

	MPASS((m->m_pkthdr.csum_flags & CSUM_SND_TAG) == 0);
	mst = NULL;

#ifdef KERN_TLS
	/*
	 * If this is an unencrypted TLS record, save a reference to
	 * the record.  This local reference is used to call
	 * ktls_output_eagain after the mbuf has been freed (thus
	 * dropping the mbuf's reference) in if_output.
	 */
	if (m->m_next != NULL && mbuf_has_tls_session(m->m_next)) {
		tls = ktls_hold(m->m_next->m_epg_tls);
		mst = tls->snd_tag;

		/*
		 * If a TLS session doesn't have a valid tag, it must
		 * have had an earlier ifp mismatch, so drop this
		 * packet.
		 */
		if (mst == NULL) {
			error = EAGAIN;
			goto done;
		}
	}
#endif
#ifdef RATELIMIT
	if (inp != NULL && mst == NULL) {
		if ((inp->inp_flags2 & INP_RATE_LIMIT_CHANGED) != 0 ||
		    (inp->inp_snd_tag != NULL &&
		    inp->inp_snd_tag->ifp != ifp))
			in_pcboutput_txrtlmt(inp, ifp, m);

		if (inp->inp_snd_tag != NULL)
			mst = inp->inp_snd_tag;
	}
#endif
	if (stamp_tag && mst != NULL) {
		KASSERT(m->m_pkthdr.rcvif == NULL,
		    ("trying to add a send tag to a forwarded packet"));
		if (mst->ifp != ifp) {
			error = EAGAIN;
			goto done;
		}

		/* stamp send tag on mbuf */
		m->m_pkthdr.snd_tag = m_snd_tag_ref(mst);
		m->m_pkthdr.csum_flags |= CSUM_SND_TAG;
	}

	error = (*ifp->if_output)(ifp, m, (const struct sockaddr *)gw, ro);

done:
	/* Check for route change invalidating send tags. */
#ifdef KERN_TLS
	if (tls != NULL) {
		if (error == EAGAIN)
			error = ktls_output_eagain(inp, tls);
		ktls_free(tls);
	}
#endif
#ifdef RATELIMIT
	if (error == EAGAIN)
		in_pcboutput_eagain(inp);
#endif
	return (error);
}

/* rte<>ro_flags translation */
static inline void
rt_update_ro_flags(struct route *ro)
{
	int nh_flags = ro->ro_nh->nh_flags;

	ro->ro_flags &= ~ (RT_REJECT|RT_BLACKHOLE|RT_HAS_GW);

	ro->ro_flags |= (nh_flags & NHF_REJECT) ? RT_REJECT : 0;
	ro->ro_flags |= (nh_flags & NHF_BLACKHOLE) ? RT_BLACKHOLE : 0;
	ro->ro_flags |= (nh_flags & NHF_GATEWAY) ? RT_HAS_GW : 0;
}

/*
 * IP output.  The packet in mbuf chain m contains a skeletal IP
 * header (with len, off, ttl, proto, tos, src, dst).
 * The mbuf chain containing the packet will be freed.
 * The mbuf opt, if present, will not be freed.
 * If route ro is present and has ro_rt initialized, route lookup would be
 * skipped and ro->ro_rt would be used. If ro is present but ro->ro_rt is NULL,
 * then result of route lookup is stored in ro->ro_rt.
 *
 * In the IP forwarding case, the packet will arrive with options already
 * inserted, so must have a NULL opt pointer.
 */
int
ip_output(struct mbuf *m, struct mbuf *opt, struct route *ro, int flags,
    struct ip_moptions *imo, struct inpcb *inp)
{
	struct rm_priotracker in_ifa_tracker;
	struct ip *ip;
	struct ifnet *ifp = NULL;	/* keep compiler happy */
	struct mbuf *m0;
	int hlen = sizeof (struct ip);
	int mtu;
	int error = 0;
	struct sockaddr_in *dst, sin;
	const struct sockaddr_in *gw;
	struct in_ifaddr *ia;
	struct in_addr src;
	int isbroadcast;
	uint16_t ip_len, ip_off;
	uint32_t fibnum;
#if defined(IPSEC) || defined(IPSEC_SUPPORT)
	int no_route_but_check_spd = 0;
#endif

	M_ASSERTPKTHDR(m);
	NET_EPOCH_ASSERT();

	if (inp != NULL) {
		INP_LOCK_ASSERT(inp);
		M_SETFIB(m, inp->inp_inc.inc_fibnum);
		if ((flags & IP_NODEFAULTFLOWID) == 0) {
			m->m_pkthdr.flowid = inp->inp_flowid;
			M_HASHTYPE_SET(m, inp->inp_flowtype);
		}
#ifdef NUMA
		m->m_pkthdr.numa_domain = inp->inp_numa_domain;
#endif
	}

	if (opt) {
		int len = 0;
		m = ip_insertoptions(m, opt, &len);
		if (len != 0)
			hlen = len; /* ip->ip_hl is updated above */
	}
	ip = mtod(m, struct ip *);
	ip_len = ntohs(ip->ip_len);
	ip_off = ntohs(ip->ip_off);

	if ((flags & (IP_FORWARDING|IP_RAWOUTPUT)) == 0) {
		ip->ip_v = IPVERSION;
		ip->ip_hl = hlen >> 2;
		ip_fillid(ip);
	} else {
		/* Header already set, fetch hlen from there */
		hlen = ip->ip_hl << 2;
	}
	if ((flags & IP_FORWARDING) == 0)
		IPSTAT_INC(ips_localout);

	/*
	 * dst/gw handling:
	 *
	 * gw is readonly but can point either to dst OR rt_gateway,
	 * therefore we need restore gw if we're redoing lookup.
	 */
	fibnum = (inp != NULL) ? inp->inp_inc.inc_fibnum : M_GETFIB(m);
	if (ro != NULL)
		dst = (struct sockaddr_in *)&ro->ro_dst;
	else
		dst = &sin;
	if (ro == NULL || ro->ro_nh == NULL) {
		bzero(dst, sizeof(*dst));
		dst->sin_family = AF_INET;
		dst->sin_len = sizeof(*dst);
		dst->sin_addr = ip->ip_dst;
	}
	gw = dst;
again:
	/*
	 * Validate route against routing table additions;
	 * a better/more specific route might have been added.
	 */
	if (inp != NULL && ro != NULL && ro->ro_nh != NULL)
		NH_VALIDATE(ro, &inp->inp_rt_cookie, fibnum);
	/*
	 * If there is a cached route,
	 * check that it is to the same destination
	 * and is still up.  If not, free it and try again.
	 * The address family should also be checked in case of sharing the
	 * cache with IPv6.
	 * Also check whether routing cache needs invalidation.
	 */
	if (ro != NULL && ro->ro_nh != NULL &&
	    ((!NH_IS_VALID(ro->ro_nh)) || !RT_LINK_IS_UP(ro->ro_nh->nh_ifp) ||
	    dst->sin_family != AF_INET ||
	    dst->sin_addr.s_addr != ip->ip_dst.s_addr))
		RO_INVALIDATE_CACHE(ro);
	ia = NULL;
	/*
	 * If routing to interface only, short circuit routing lookup.
	 * The use of an all-ones broadcast address implies this; an
	 * interface is specified by the broadcast address of an interface,
	 * or the destination address of a ptp interface.
	 */
	if (flags & IP_SENDONES) {
		if ((ia = ifatoia(ifa_ifwithbroadaddr(sintosa(dst),
						      M_GETFIB(m)))) == NULL &&
		    (ia = ifatoia(ifa_ifwithdstaddr(sintosa(dst),
						    M_GETFIB(m)))) == NULL) {
			IPSTAT_INC(ips_noroute);
			error = ENETUNREACH;
			goto bad;
		}
		ip->ip_dst.s_addr = INADDR_BROADCAST;
		dst->sin_addr = ip->ip_dst;
		ifp = ia->ia_ifp;
		mtu = ifp->if_mtu;
		ip->ip_ttl = 1;
		isbroadcast = 1;
		src = IA_SIN(ia)->sin_addr;
	} else if (flags & IP_ROUTETOIF) {
		if ((ia = ifatoia(ifa_ifwithdstaddr(sintosa(dst),
						    M_GETFIB(m)))) == NULL &&
		    (ia = ifatoia(ifa_ifwithnet(sintosa(dst), 0,
						M_GETFIB(m)))) == NULL) {
			IPSTAT_INC(ips_noroute);
			error = ENETUNREACH;
			goto bad;
		}
		ifp = ia->ia_ifp;
		mtu = ifp->if_mtu;
		ip->ip_ttl = 1;
		isbroadcast = ifp->if_flags & IFF_BROADCAST ?
		    in_ifaddr_broadcast(dst->sin_addr, ia) : 0;
		src = IA_SIN(ia)->sin_addr;
	} else if (IN_MULTICAST(ntohl(ip->ip_dst.s_addr)) &&
	    imo != NULL && imo->imo_multicast_ifp != NULL) {
		/*
		 * Bypass the normal routing lookup for multicast
		 * packets if the interface is specified.
		 */
		ifp = imo->imo_multicast_ifp;
		mtu = ifp->if_mtu;
		IFP_TO_IA(ifp, ia, &in_ifa_tracker);
		isbroadcast = 0;	/* fool gcc */
		/* Interface may have no addresses. */
		if (ia != NULL)
			src = IA_SIN(ia)->sin_addr;
		else
			src.s_addr = INADDR_ANY;
	} else if (ro != NULL) {
		if (ro->ro_nh == NULL) {
			/*
			 * We want to do any cloning requested by the link
			 * layer, as this is probably required in all cases
			 * for correct operation (as it is for ARP).
			 */
			uint32_t flowid;
#ifdef RADIX_MPATH
			flowid = ntohl(ip->ip_src.s_addr ^ ip->ip_dst.s_addr);
#else
			flowid = m->m_pkthdr.flowid;
#endif
			ro->ro_nh = fib4_lookup(fibnum, dst->sin_addr, 0,
			    NHR_REF, flowid);

			if (ro->ro_nh == NULL || (!NH_IS_VALID(ro->ro_nh)) ||
			    !RT_LINK_IS_UP(ro->ro_nh->nh_ifp)) {
#if defined(IPSEC) || defined(IPSEC_SUPPORT)
				/*
				 * There is no route for this packet, but it is
				 * possible that a matching SPD entry exists.
				 */
				no_route_but_check_spd = 1;
				mtu = 0; /* Silence GCC warning. */
				goto sendit;
#endif
				IPSTAT_INC(ips_noroute);
				error = EHOSTUNREACH;
				goto bad;
			}
		}
		ia = ifatoia(ro->ro_nh->nh_ifa);
		ifp = ro->ro_nh->nh_ifp;
		counter_u64_add(ro->ro_nh->nh_pksent, 1);
		rt_update_ro_flags(ro);
		if (ro->ro_nh->nh_flags & NHF_GATEWAY)
			gw = &ro->ro_nh->gw4_sa;
		if (ro->ro_nh->nh_flags & NHF_HOST)
			isbroadcast = (ro->ro_nh->nh_flags & NHF_BROADCAST);
		else if (ifp->if_flags & IFF_BROADCAST)
			isbroadcast = in_ifaddr_broadcast(gw->sin_addr, ia);
		else
			isbroadcast = 0;
		if (ro->ro_nh->nh_flags & NHF_HOST)
			mtu = ro->ro_nh->nh_mtu;
		else
			mtu = ifp->if_mtu;
		src = IA_SIN(ia)->sin_addr;
	} else {
		struct nhop4_extended nh;

		bzero(&nh, sizeof(nh));
		if (fib4_lookup_nh_ext(M_GETFIB(m), ip->ip_dst, 0, 0, &nh) !=
		    0) {
#if defined(IPSEC) || defined(IPSEC_SUPPORT)
			/*
			 * There is no route for this packet, but it is
			 * possible that a matching SPD entry exists.
			 */
			no_route_but_check_spd = 1;
			mtu = 0; /* Silence GCC warning. */
			goto sendit;
#endif
			IPSTAT_INC(ips_noroute);
			error = EHOSTUNREACH;
			goto bad;
		}
		ifp = nh.nh_ifp;
		mtu = nh.nh_mtu;
		/*
		 * We are rewriting here dst to be gw actually, contradicting
		 * comment at the beginning of the function. However, in this
		 * case we are always dealing with on stack dst.
		 * In case if pfil(9) sends us back to beginning of the
		 * function, the dst would be rewritten by ip_output_pfil().
		 */
		MPASS(dst == &sin);
		dst->sin_addr = nh.nh_addr;
		ia = nh.nh_ia;
		src = nh.nh_src;
		isbroadcast = (((nh.nh_flags & (NHF_HOST | NHF_BROADCAST)) ==
		    (NHF_HOST | NHF_BROADCAST)) ||
		    ((ifp->if_flags & IFF_BROADCAST) &&
		    in_ifaddr_broadcast(dst->sin_addr, ia)));
	}

	/* Catch a possible divide by zero later. */
	KASSERT(mtu > 0, ("%s: mtu %d <= 0, ro=%p (nh_flags=0x%08x) ifp=%p",
	    __func__, mtu, ro,
	    (ro != NULL && ro->ro_nh != NULL) ? ro->ro_nh->nh_flags : 0, ifp));

	if (IN_MULTICAST(ntohl(ip->ip_dst.s_addr))) {
		m->m_flags |= M_MCAST;
		/*
		 * IP destination address is multicast.  Make sure "gw"
		 * still points to the address in "ro".  (It may have been
		 * changed to point to a gateway address, above.)
		 */
		gw = dst;
		/*
		 * See if the caller provided any multicast options
		 */
		if (imo != NULL) {
			ip->ip_ttl = imo->imo_multicast_ttl;
			if (imo->imo_multicast_vif != -1)
				ip->ip_src.s_addr =
				    ip_mcast_src ?
				    ip_mcast_src(imo->imo_multicast_vif) :
				    INADDR_ANY;
		} else
			ip->ip_ttl = IP_DEFAULT_MULTICAST_TTL;
		/*
		 * Confirm that the outgoing interface supports multicast.
		 */
		if ((imo == NULL) || (imo->imo_multicast_vif == -1)) {
			if ((ifp->if_flags & IFF_MULTICAST) == 0) {
				IPSTAT_INC(ips_noroute);
				error = ENETUNREACH;
				goto bad;
			}
		}
		/*
		 * If source address not specified yet, use address
		 * of outgoing interface.
		 */
		if (ip->ip_src.s_addr == INADDR_ANY)
			ip->ip_src = src;

		if ((imo == NULL && in_mcast_loop) ||
		    (imo && imo->imo_multicast_loop)) {
			/*
			 * Loop back multicast datagram if not expressly
			 * forbidden to do so, even if we are not a member
			 * of the group; ip_input() will filter it later,
			 * thus deferring a hash lookup and mutex acquisition
			 * at the expense of a cheap copy using m_copym().
			 */
			ip_mloopback(ifp, m, hlen);
		} else {
			/*
			 * If we are acting as a multicast router, perform
			 * multicast forwarding as if the packet had just
			 * arrived on the interface to which we are about
			 * to send.  The multicast forwarding function
			 * recursively calls this function, using the
			 * IP_FORWARDING flag to prevent infinite recursion.
			 *
			 * Multicasts that are looped back by ip_mloopback(),
			 * above, will be forwarded by the ip_input() routine,
			 * if necessary.
			 */
			if (V_ip_mrouter && (flags & IP_FORWARDING) == 0) {
				/*
				 * If rsvp daemon is not running, do not
				 * set ip_moptions. This ensures that the packet
				 * is multicast and not just sent down one link
				 * as prescribed by rsvpd.
				 */
				if (!V_rsvp_on)
					imo = NULL;
				if (ip_mforward &&
				    ip_mforward(ip, ifp, m, imo) != 0) {
					m_freem(m);
					goto done;
				}
			}
		}

		/*
		 * Multicasts with a time-to-live of zero may be looped-
		 * back, above, but must not be transmitted on a network.
		 * Also, multicasts addressed to the loopback interface
		 * are not sent -- the above call to ip_mloopback() will
		 * loop back a copy. ip_input() will drop the copy if
		 * this host does not belong to the destination group on
		 * the loopback interface.
		 */
		if (ip->ip_ttl == 0 || ifp->if_flags & IFF_LOOPBACK) {
			m_freem(m);
			goto done;
		}

		goto sendit;
	}

	/*
	 * If the source address is not specified yet, use the address
	 * of the outoing interface.
	 */
	if (ip->ip_src.s_addr == INADDR_ANY)
		ip->ip_src = src;

	/*
	 * Look for broadcast address and
	 * verify user is allowed to send
	 * such a packet.
	 */
	if (isbroadcast) {
		if ((ifp->if_flags & IFF_BROADCAST) == 0) {
			error = EADDRNOTAVAIL;
			goto bad;
		}
		if ((flags & IP_ALLOWBROADCAST) == 0) {
			error = EACCES;
			goto bad;
		}
		/* don't allow broadcast messages to be fragmented */
		if (ip_len > mtu) {
			error = EMSGSIZE;
			goto bad;
		}
		m->m_flags |= M_BCAST;
	} else {
		m->m_flags &= ~M_BCAST;
	}

sendit:
#if defined(IPSEC) || defined(IPSEC_SUPPORT)
	if (IPSEC_ENABLED(ipv4)) {
		if ((error = IPSEC_OUTPUT(ipv4, m, inp)) != 0) {
			if (error == EINPROGRESS)
				error = 0;
			goto done;
		}
	}
	/*
	 * Check if there was a route for this packet; return error if not.
	 */
	if (no_route_but_check_spd) {
		IPSTAT_INC(ips_noroute);
		error = EHOSTUNREACH;
		goto bad;
	}
	/* Update variables that are affected by ipsec4_output(). */
	ip = mtod(m, struct ip *);
	hlen = ip->ip_hl << 2;
#endif /* IPSEC */

	/* Jump over all PFIL processing if hooks are not active. */
	if (PFIL_HOOKED_OUT(V_inet_pfil_head)) {
		switch (ip_output_pfil(&m, ifp, flags, inp, dst, &fibnum,
		    &error)) {
		case 1: /* Finished */
			goto done;

		case 0: /* Continue normally */
			ip = mtod(m, struct ip *);
			break;

		case -1: /* Need to try again */
			/* Reset everything for a new round */
			if (ro != NULL) {
				RO_NHFREE(ro);
				ro->ro_prepend = NULL;
			}
			gw = dst;
			ip = mtod(m, struct ip *);
			goto again;

		}
	}

	/* IN_LOOPBACK must not appear on the wire - RFC1122. */
	if (IN_LOOPBACK(ntohl(ip->ip_dst.s_addr)) ||
	    IN_LOOPBACK(ntohl(ip->ip_src.s_addr))) {
		if ((ifp->if_flags & IFF_LOOPBACK) == 0) {
			IPSTAT_INC(ips_badaddr);
			error = EADDRNOTAVAIL;
			goto bad;
		}
	}

	m->m_pkthdr.csum_flags |= CSUM_IP;
	if (m->m_pkthdr.csum_flags & CSUM_DELAY_DATA & ~ifp->if_hwassist) {
		m = mb_unmapped_to_ext(m);
		if (m == NULL) {
			IPSTAT_INC(ips_odropped);
			error = ENOBUFS;
			goto bad;
		}
		in_delayed_cksum(m);
		m->m_pkthdr.csum_flags &= ~CSUM_DELAY_DATA;
	} else if ((ifp->if_capenable & IFCAP_NOMAP) == 0) {
		m = mb_unmapped_to_ext(m);
		if (m == NULL) {
			IPSTAT_INC(ips_odropped);
			error = ENOBUFS;
			goto bad;
		}
	}
#ifdef SCTP
	if (m->m_pkthdr.csum_flags & CSUM_SCTP & ~ifp->if_hwassist) {
		m = mb_unmapped_to_ext(m);
		if (m == NULL) {
			IPSTAT_INC(ips_odropped);
			error = ENOBUFS;
			goto bad;
		}
		sctp_delayed_cksum(m, (uint32_t)(ip->ip_hl << 2));
		m->m_pkthdr.csum_flags &= ~CSUM_SCTP;
	}
#endif

	/*
	 * If small enough for interface, or the interface will take
	 * care of the fragmentation for us, we can just send directly.
	 */
	if (ip_len <= mtu ||
	    (m->m_pkthdr.csum_flags & ifp->if_hwassist & CSUM_TSO) != 0) {
		ip->ip_sum = 0;
		if (m->m_pkthdr.csum_flags & CSUM_IP & ~ifp->if_hwassist) {
			ip->ip_sum = in_cksum(m, hlen);
			m->m_pkthdr.csum_flags &= ~CSUM_IP;
		}

		/*
		 * Record statistics for this interface address.
		 * With CSUM_TSO the byte/packet count will be slightly
		 * incorrect because we count the IP+TCP headers only
		 * once instead of for every generated packet.
		 */
		if (!(flags & IP_FORWARDING) && ia) {
			if (m->m_pkthdr.csum_flags & CSUM_TSO)
				counter_u64_add(ia->ia_ifa.ifa_opackets,
				    m->m_pkthdr.len / m->m_pkthdr.tso_segsz);
			else
				counter_u64_add(ia->ia_ifa.ifa_opackets, 1);

			counter_u64_add(ia->ia_ifa.ifa_obytes, m->m_pkthdr.len);
		}
#ifdef MBUF_STRESS_TEST
		if (mbuf_frag_size && m->m_pkthdr.len > mbuf_frag_size)
			m = m_fragment(m, M_NOWAIT, mbuf_frag_size);
#endif
		/*
		 * Reset layer specific mbuf flags
		 * to avoid confusing lower layers.
		 */
		m_clrprotoflags(m);
		IP_PROBE(send, NULL, NULL, ip, ifp, ip, NULL);
		error = ip_output_send(inp, ifp, m, gw, ro,
		    (flags & IP_NO_SND_TAG_RL) ? false : true);
		goto done;
	}

	/* Balk when DF bit is set or the interface didn't support TSO. */
	if ((ip_off & IP_DF) || (m->m_pkthdr.csum_flags & CSUM_TSO)) {
		error = EMSGSIZE;
		IPSTAT_INC(ips_cantfrag);
		goto bad;
	}

	/*
	 * Too large for interface; fragment if possible. If successful,
	 * on return, m will point to a list of packets to be sent.
	 */
	error = ip_fragment(ip, &m, mtu, ifp->if_hwassist);
	if (error)
		goto bad;
	for (; m; m = m0) {
		m0 = m->m_nextpkt;
		m->m_nextpkt = 0;
		if (error == 0) {
			/* Record statistics for this interface address. */
			if (ia != NULL) {
				counter_u64_add(ia->ia_ifa.ifa_opackets, 1);
				counter_u64_add(ia->ia_ifa.ifa_obytes,
				    m->m_pkthdr.len);
			}
			/*
			 * Reset layer specific mbuf flags
			 * to avoid confusing upper layers.
			 */
			m_clrprotoflags(m);

			IP_PROBE(send, NULL, NULL, mtod(m, struct ip *), ifp,
			    mtod(m, struct ip *), NULL);
			error = ip_output_send(inp, ifp, m, gw, ro, true);
		} else
			m_freem(m);
	}

	if (error == 0)
		IPSTAT_INC(ips_fragmented);

done:
	return (error);
 bad:
	m_freem(m);
	goto done;
}

/*
 * Create a chain of fragments which fit the given mtu. m_frag points to the
 * mbuf to be fragmented; on return it points to the chain with the fragments.
 * Return 0 if no error. If error, m_frag may contain a partially built
 * chain of fragments that should be freed by the caller.
 *
 * if_hwassist_flags is the hw offload capabilities (see if_data.ifi_hwassist)
 */
int
ip_fragment(struct ip *ip, struct mbuf **m_frag, int mtu,
    u_long if_hwassist_flags)
{
	int error = 0;
	int hlen = ip->ip_hl << 2;
	int len = (mtu - hlen) & ~7;	/* size of payload in each fragment */
	int off;
	struct mbuf *m0 = *m_frag;	/* the original packet		*/
	int firstlen;
	struct mbuf **mnext;
	int nfrags;
	uint16_t ip_len, ip_off;

	ip_len = ntohs(ip->ip_len);
	ip_off = ntohs(ip->ip_off);

	if (ip_off & IP_DF) {	/* Fragmentation not allowed */
		IPSTAT_INC(ips_cantfrag);
		return EMSGSIZE;
	}

	/*
	 * Must be able to put at least 8 bytes per fragment.
	 */
	if (len < 8)
		return EMSGSIZE;

	/*
	 * If the interface will not calculate checksums on
	 * fragmented packets, then do it here.
	 */
	if (m0->m_pkthdr.csum_flags & CSUM_DELAY_DATA) {
		m0 = mb_unmapped_to_ext(m0);
		if (m0 == NULL) {
			error = ENOBUFS;
			IPSTAT_INC(ips_odropped);
			goto done;
		}
		in_delayed_cksum(m0);
		m0->m_pkthdr.csum_flags &= ~CSUM_DELAY_DATA;
	}
#ifdef SCTP
	if (m0->m_pkthdr.csum_flags & CSUM_SCTP) {
		m0 = mb_unmapped_to_ext(m0);
		if (m0 == NULL) {
			error = ENOBUFS;
			IPSTAT_INC(ips_odropped);
			goto done;
		}
		sctp_delayed_cksum(m0, hlen);
		m0->m_pkthdr.csum_flags &= ~CSUM_SCTP;
	}
#endif
	if (len > PAGE_SIZE) {
		/*
		 * Fragment large datagrams such that each segment
		 * contains a multiple of PAGE_SIZE amount of data,
		 * plus headers. This enables a receiver to perform
		 * page-flipping zero-copy optimizations.
		 *
		 * XXX When does this help given that sender and receiver
		 * could have different page sizes, and also mtu could
		 * be less than the receiver's page size ?
		 */
		int newlen;

		off = MIN(mtu, m0->m_pkthdr.len);

		/*
		 * firstlen (off - hlen) must be aligned on an
		 * 8-byte boundary
		 */
		if (off < hlen)
			goto smart_frag_failure;
		off = ((off - hlen) & ~7) + hlen;
		newlen = (~PAGE_MASK) & mtu;
		if ((newlen + sizeof (struct ip)) > mtu) {
			/* we failed, go back the default */
smart_frag_failure:
			newlen = len;
			off = hlen + len;
		}
		len = newlen;

	} else {
		off = hlen + len;
	}

	firstlen = off - hlen;
	mnext = &m0->m_nextpkt;		/* pointer to next packet */

	/*
	 * Loop through length of segment after first fragment,
	 * make new header and copy data of each part and link onto chain.
	 * Here, m0 is the original packet, m is the fragment being created.
	 * The fragments are linked off the m_nextpkt of the original
	 * packet, which after processing serves as the first fragment.
	 */
	for (nfrags = 1; off < ip_len; off += len, nfrags++) {
		struct ip *mhip;	/* ip header on the fragment */
		struct mbuf *m;
		int mhlen = sizeof (struct ip);

		m = m_gethdr(M_NOWAIT, MT_DATA);
		if (m == NULL) {
			error = ENOBUFS;
			IPSTAT_INC(ips_odropped);
			goto done;
		}
		/*
		 * Make sure the complete packet header gets copied
		 * from the originating mbuf to the newly created
		 * mbuf. This also ensures that existing firewall
		 * classification(s), VLAN tags and so on get copied
		 * to the resulting fragmented packet(s):
		 */
		if (m_dup_pkthdr(m, m0, M_NOWAIT) == 0) {
			m_free(m);
			error = ENOBUFS;
			IPSTAT_INC(ips_odropped);
			goto done;
		}
		/*
		 * In the first mbuf, leave room for the link header, then
		 * copy the original IP header including options. The payload
		 * goes into an additional mbuf chain returned by m_copym().
		 */
		m->m_data += max_linkhdr;
		mhip = mtod(m, struct ip *);
		*mhip = *ip;
		if (hlen > sizeof (struct ip)) {
			mhlen = ip_optcopy(ip, mhip) + sizeof (struct ip);
			mhip->ip_v = IPVERSION;
			mhip->ip_hl = mhlen >> 2;
		}
		m->m_len = mhlen;
		/* XXX do we need to add ip_off below ? */
		mhip->ip_off = ((off - hlen) >> 3) + ip_off;
		if (off + len >= ip_len)
			len = ip_len - off;
		else
			mhip->ip_off |= IP_MF;
		mhip->ip_len = htons((u_short)(len + mhlen));
		m->m_next = m_copym(m0, off, len, M_NOWAIT);
		if (m->m_next == NULL) {	/* copy failed */
			m_free(m);
			error = ENOBUFS;	/* ??? */
			IPSTAT_INC(ips_odropped);
			goto done;
		}
		m->m_pkthdr.len = mhlen + len;
#ifdef MAC
		mac_netinet_fragment(m0, m);
#endif
		mhip->ip_off = htons(mhip->ip_off);
		mhip->ip_sum = 0;
		if (m->m_pkthdr.csum_flags & CSUM_IP & ~if_hwassist_flags) {
			mhip->ip_sum = in_cksum(m, mhlen);
			m->m_pkthdr.csum_flags &= ~CSUM_IP;
		}
		*mnext = m;
		mnext = &m->m_nextpkt;
	}
	IPSTAT_ADD(ips_ofragments, nfrags);

	/*
	 * Update first fragment by trimming what's been copied out
	 * and updating header.
	 */
	m_adj(m0, hlen + firstlen - ip_len);
	m0->m_pkthdr.len = hlen + firstlen;
	ip->ip_len = htons((u_short)m0->m_pkthdr.len);
	ip->ip_off = htons(ip_off | IP_MF);
	ip->ip_sum = 0;
	if (m0->m_pkthdr.csum_flags & CSUM_IP & ~if_hwassist_flags) {
		ip->ip_sum = in_cksum(m0, hlen);
		m0->m_pkthdr.csum_flags &= ~CSUM_IP;
	}

done:
	*m_frag = m0;
	return error;
}

void
in_delayed_cksum(struct mbuf *m)
{
	struct ip *ip;
	struct udphdr *uh;
	uint16_t cklen, csum, offset;

	ip = mtod(m, struct ip *);
	offset = ip->ip_hl << 2 ;

	if (m->m_pkthdr.csum_flags & CSUM_UDP) {
		/* if udp header is not in the first mbuf copy udplen */
		if (offset + sizeof(struct udphdr) > m->m_len) {
			m_copydata(m, offset + offsetof(struct udphdr,
			    uh_ulen), sizeof(cklen), (caddr_t)&cklen);
			cklen = ntohs(cklen);
		} else {
			uh = (struct udphdr *)mtodo(m, offset);
			cklen = ntohs(uh->uh_ulen);
		}
		csum = in_cksum_skip(m, cklen + offset, offset);
		if (csum == 0)
			csum = 0xffff;
	} else {
		cklen = ntohs(ip->ip_len);
		csum = in_cksum_skip(m, cklen, offset);
	}
	offset += m->m_pkthdr.csum_data;	/* checksum offset */

	if (offset + sizeof(csum) > m->m_len)
		m_copyback(m, offset, sizeof(csum), (caddr_t)&csum);
	else
		*(u_short *)mtodo(m, offset) = csum;
}

/*
 * IP socket option processing.
 */
int
ip_ctloutput(struct socket *so, struct sockopt *sopt)
{
	struct inpcb *inp = sotoinpcb(so);
	int	error, optval;
#ifdef	RSS
	uint32_t rss_bucket;
	int retval;
#endif

	error = optval = 0;
	if (sopt->sopt_level != IPPROTO_IP) {
		error = EINVAL;

		if (sopt->sopt_level == SOL_SOCKET &&
		    sopt->sopt_dir == SOPT_SET) {
			switch (sopt->sopt_name) {
			case SO_REUSEADDR:
				INP_WLOCK(inp);
				if ((so->so_options & SO_REUSEADDR) != 0)
					inp->inp_flags2 |= INP_REUSEADDR;
				else
					inp->inp_flags2 &= ~INP_REUSEADDR;
				INP_WUNLOCK(inp);
				error = 0;
				break;
			case SO_REUSEPORT:
				INP_WLOCK(inp);
				if ((so->so_options & SO_REUSEPORT) != 0)
					inp->inp_flags2 |= INP_REUSEPORT;
				else
					inp->inp_flags2 &= ~INP_REUSEPORT;
				INP_WUNLOCK(inp);
				error = 0;
				break;
			case SO_REUSEPORT_LB:
				INP_WLOCK(inp);
				if ((so->so_options & SO_REUSEPORT_LB) != 0)
					inp->inp_flags2 |= INP_REUSEPORT_LB;
				else
					inp->inp_flags2 &= ~INP_REUSEPORT_LB;
				INP_WUNLOCK(inp);
				error = 0;
				break;
			case SO_SETFIB:
				INP_WLOCK(inp);
				inp->inp_inc.inc_fibnum = so->so_fibnum;
				INP_WUNLOCK(inp);
				error = 0;
				break;
			case SO_MAX_PACING_RATE:
#ifdef RATELIMIT
				INP_WLOCK(inp);
				inp->inp_flags2 |= INP_RATE_LIMIT_CHANGED;
				INP_WUNLOCK(inp);
				error = 0;
#else
				error = EOPNOTSUPP;
#endif
				break;
			default:
				break;
			}
		}
		return (error);
	}

	switch (sopt->sopt_dir) {
	case SOPT_SET:
		switch (sopt->sopt_name) {
		case IP_OPTIONS:
#ifdef notyet
		case IP_RETOPTS:
#endif
		{
			struct mbuf *m;
			if (sopt->sopt_valsize > MLEN) {
				error = EMSGSIZE;
				break;
			}
			m = m_get(sopt->sopt_td ? M_WAITOK : M_NOWAIT, MT_DATA);
			if (m == NULL) {
				error = ENOBUFS;
				break;
			}
			m->m_len = sopt->sopt_valsize;
			error = sooptcopyin(sopt, mtod(m, char *), m->m_len,
					    m->m_len);
			if (error) {
				m_free(m);
				break;
			}
			INP_WLOCK(inp);
			error = ip_pcbopts(inp, sopt->sopt_name, m);
			INP_WUNLOCK(inp);
			return (error);
		}

		case IP_BINDANY:
			if (sopt->sopt_td != NULL) {
				error = priv_check(sopt->sopt_td,
				    PRIV_NETINET_BINDANY);
				if (error)
					break;
			}
			/* FALLTHROUGH */
		case IP_BINDMULTI:
#ifdef	RSS
		case IP_RSS_LISTEN_BUCKET:
#endif
		case IP_TOS:
		case IP_TTL:
		case IP_MINTTL:
		case IP_RECVOPTS:
		case IP_RECVRETOPTS:
		case IP_ORIGDSTADDR:
		case IP_RECVDSTADDR:
		case IP_RECVTTL:
		case IP_RECVIF:
		case IP_ONESBCAST:
		case IP_DONTFRAG:
		case IP_RECVTOS:
		case IP_RECVFLOWID:
#ifdef	RSS
		case IP_RECVRSSBUCKETID:
#endif
			error = sooptcopyin(sopt, &optval, sizeof optval,
					    sizeof optval);
			if (error)
				break;

			switch (sopt->sopt_name) {
			case IP_TOS:
				inp->inp_ip_tos = optval;
				break;

			case IP_TTL:
				inp->inp_ip_ttl = optval;
				break;

			case IP_MINTTL:
				if (optval >= 0 && optval <= MAXTTL)
					inp->inp_ip_minttl = optval;
				else
					error = EINVAL;
				break;

#define	OPTSET(bit) do {						\
	INP_WLOCK(inp);							\
	if (optval)							\
		inp->inp_flags |= bit;					\
	else								\
		inp->inp_flags &= ~bit;					\
	INP_WUNLOCK(inp);						\
} while (0)

#define	OPTSET2(bit, val) do {						\
	INP_WLOCK(inp);							\
	if (val)							\
		inp->inp_flags2 |= bit;					\
	else								\
		inp->inp_flags2 &= ~bit;				\
	INP_WUNLOCK(inp);						\
} while (0)

			case IP_RECVOPTS:
				OPTSET(INP_RECVOPTS);
				break;

			case IP_RECVRETOPTS:
				OPTSET(INP_RECVRETOPTS);
				break;

			case IP_RECVDSTADDR:
				OPTSET(INP_RECVDSTADDR);
				break;

			case IP_ORIGDSTADDR:
				OPTSET2(INP_ORIGDSTADDR, optval);
				break;

			case IP_RECVTTL:
				OPTSET(INP_RECVTTL);
				break;

			case IP_RECVIF:
				OPTSET(INP_RECVIF);
				break;

			case IP_ONESBCAST:
				OPTSET(INP_ONESBCAST);
				break;
			case IP_DONTFRAG:
				OPTSET(INP_DONTFRAG);
				break;
			case IP_BINDANY:
				OPTSET(INP_BINDANY);
				break;
			case IP_RECVTOS:
				OPTSET(INP_RECVTOS);
				break;
			case IP_BINDMULTI:
				OPTSET2(INP_BINDMULTI, optval);
				break;
			case IP_RECVFLOWID:
				OPTSET2(INP_RECVFLOWID, optval);
				break;
#ifdef	RSS
			case IP_RSS_LISTEN_BUCKET:
				if ((optval >= 0) &&
				    (optval < rss_getnumbuckets())) {
					inp->inp_rss_listen_bucket = optval;
					OPTSET2(INP_RSS_BUCKET_SET, 1);
				} else {
					error = EINVAL;
				}
				break;
			case IP_RECVRSSBUCKETID:
				OPTSET2(INP_RECVRSSBUCKETID, optval);
				break;
#endif
			}
			break;
#undef OPTSET
#undef OPTSET2

		/*
		 * Multicast socket options are processed by the in_mcast
		 * module.
		 */
		case IP_MULTICAST_IF:
		case IP_MULTICAST_VIF:
		case IP_MULTICAST_TTL:
		case IP_MULTICAST_LOOP:
		case IP_ADD_MEMBERSHIP:
		case IP_DROP_MEMBERSHIP:
		case IP_ADD_SOURCE_MEMBERSHIP:
		case IP_DROP_SOURCE_MEMBERSHIP:
		case IP_BLOCK_SOURCE:
		case IP_UNBLOCK_SOURCE:
		case IP_MSFILTER:
		case MCAST_JOIN_GROUP:
		case MCAST_LEAVE_GROUP:
		case MCAST_JOIN_SOURCE_GROUP:
		case MCAST_LEAVE_SOURCE_GROUP:
		case MCAST_BLOCK_SOURCE:
		case MCAST_UNBLOCK_SOURCE:
			error = inp_setmoptions(inp, sopt);
			break;

		case IP_PORTRANGE:
			error = sooptcopyin(sopt, &optval, sizeof optval,
					    sizeof optval);
			if (error)
				break;

			INP_WLOCK(inp);
			switch (optval) {
			case IP_PORTRANGE_DEFAULT:
				inp->inp_flags &= ~(INP_LOWPORT);
				inp->inp_flags &= ~(INP_HIGHPORT);
				break;

			case IP_PORTRANGE_HIGH:
				inp->inp_flags &= ~(INP_LOWPORT);
				inp->inp_flags |= INP_HIGHPORT;
				break;

			case IP_PORTRANGE_LOW:
				inp->inp_flags &= ~(INP_HIGHPORT);
				inp->inp_flags |= INP_LOWPORT;
				break;

			default:
				error = EINVAL;
				break;
			}
			INP_WUNLOCK(inp);
			break;

#if defined(IPSEC) || defined(IPSEC_SUPPORT)
		case IP_IPSEC_POLICY:
			if (IPSEC_ENABLED(ipv4)) {
				error = IPSEC_PCBCTL(ipv4, inp, sopt);
				break;
			}
			/* FALLTHROUGH */
#endif /* IPSEC */

		default:
			error = ENOPROTOOPT;
			break;
		}
		break;

	case SOPT_GET:
		switch (sopt->sopt_name) {
		case IP_OPTIONS:
		case IP_RETOPTS:
			INP_RLOCK(inp);
			if (inp->inp_options) {
				struct mbuf *options;

				options = m_copym(inp->inp_options, 0,
				    M_COPYALL, M_NOWAIT);
				INP_RUNLOCK(inp);
				if (options != NULL) {
					error = sooptcopyout(sopt,
							     mtod(options, char *),
							     options->m_len);
					m_freem(options);
				} else
					error = ENOMEM;
			} else {
				INP_RUNLOCK(inp);
				sopt->sopt_valsize = 0;
			}
			break;

		case IP_TOS:
		case IP_TTL:
		case IP_MINTTL:
		case IP_RECVOPTS:
		case IP_RECVRETOPTS:
		case IP_ORIGDSTADDR:
		case IP_RECVDSTADDR:
		case IP_RECVTTL:
		case IP_RECVIF:
		case IP_PORTRANGE:
		case IP_ONESBCAST:
		case IP_DONTFRAG:
		case IP_BINDANY:
		case IP_RECVTOS:
		case IP_BINDMULTI:
		case IP_FLOWID:
		case IP_FLOWTYPE:
		case IP_RECVFLOWID:
#ifdef	RSS
		case IP_RSSBUCKETID:
		case IP_RECVRSSBUCKETID:
#endif
			switch (sopt->sopt_name) {

			case IP_TOS:
				optval = inp->inp_ip_tos;
				break;

			case IP_TTL:
				optval = inp->inp_ip_ttl;
				break;

			case IP_MINTTL:
				optval = inp->inp_ip_minttl;
				break;

#define	OPTBIT(bit)	(inp->inp_flags & bit ? 1 : 0)
#define	OPTBIT2(bit)	(inp->inp_flags2 & bit ? 1 : 0)

			case IP_RECVOPTS:
				optval = OPTBIT(INP_RECVOPTS);
				break;

			case IP_RECVRETOPTS:
				optval = OPTBIT(INP_RECVRETOPTS);
				break;

			case IP_RECVDSTADDR:
				optval = OPTBIT(INP_RECVDSTADDR);
				break;

			case IP_ORIGDSTADDR:
				optval = OPTBIT2(INP_ORIGDSTADDR);
				break;

			case IP_RECVTTL:
				optval = OPTBIT(INP_RECVTTL);
				break;

			case IP_RECVIF:
				optval = OPTBIT(INP_RECVIF);
				break;

			case IP_PORTRANGE:
				if (inp->inp_flags & INP_HIGHPORT)
					optval = IP_PORTRANGE_HIGH;
				else if (inp->inp_flags & INP_LOWPORT)
					optval = IP_PORTRANGE_LOW;
				else
					optval = 0;
				break;

			case IP_ONESBCAST:
				optval = OPTBIT(INP_ONESBCAST);
				break;
			case IP_DONTFRAG:
				optval = OPTBIT(INP_DONTFRAG);
				break;
			case IP_BINDANY:
				optval = OPTBIT(INP_BINDANY);
				break;
			case IP_RECVTOS:
				optval = OPTBIT(INP_RECVTOS);
				break;
			case IP_FLOWID:
				optval = inp->inp_flowid;
				break;
			case IP_FLOWTYPE:
				optval = inp->inp_flowtype;
				break;
			case IP_RECVFLOWID:
				optval = OPTBIT2(INP_RECVFLOWID);
				break;
#ifdef	RSS
			case IP_RSSBUCKETID:
				retval = rss_hash2bucket(inp->inp_flowid,
				    inp->inp_flowtype,
				    &rss_bucket);
				if (retval == 0)
					optval = rss_bucket;
				else
					error = EINVAL;
				break;
			case IP_RECVRSSBUCKETID:
				optval = OPTBIT2(INP_RECVRSSBUCKETID);
				break;
#endif
			case IP_BINDMULTI:
				optval = OPTBIT2(INP_BINDMULTI);
				break;
			}
			error = sooptcopyout(sopt, &optval, sizeof optval);
			break;

		/*
		 * Multicast socket options are processed by the in_mcast
		 * module.
		 */
		case IP_MULTICAST_IF:
		case IP_MULTICAST_VIF:
		case IP_MULTICAST_TTL:
		case IP_MULTICAST_LOOP:
		case IP_MSFILTER:
			error = inp_getmoptions(inp, sopt);
			break;

#if defined(IPSEC) || defined(IPSEC_SUPPORT)
		case IP_IPSEC_POLICY:
			if (IPSEC_ENABLED(ipv4)) {
				error = IPSEC_PCBCTL(ipv4, inp, sopt);
				break;
			}
			/* FALLTHROUGH */
#endif /* IPSEC */

		default:
			error = ENOPROTOOPT;
			break;
		}
		break;
	}
	return (error);
}

/*
 * Routine called from ip_output() to loop back a copy of an IP multicast
 * packet to the input queue of a specified interface.  Note that this
 * calls the output routine of the loopback "driver", but with an interface
 * pointer that might NOT be a loopback interface -- evil, but easier than
 * replicating that code here.
 */
static void
ip_mloopback(struct ifnet *ifp, const struct mbuf *m, int hlen)
{
	struct ip *ip;
	struct mbuf *copym;

	/*
	 * Make a deep copy of the packet because we're going to
	 * modify the pack in order to generate checksums.
	 */
	copym = m_dup(m, M_NOWAIT);
	if (copym != NULL && (!M_WRITABLE(copym) || copym->m_len < hlen))
		copym = m_pullup(copym, hlen);
	if (copym != NULL) {
		/* If needed, compute the checksum and mark it as valid. */
		if (copym->m_pkthdr.csum_flags & CSUM_DELAY_DATA) {
			in_delayed_cksum(copym);
			copym->m_pkthdr.csum_flags &= ~CSUM_DELAY_DATA;
			copym->m_pkthdr.csum_flags |=
			    CSUM_DATA_VALID | CSUM_PSEUDO_HDR;
			copym->m_pkthdr.csum_data = 0xffff;
		}
		/*
		 * We don't bother to fragment if the IP length is greater
		 * than the interface's MTU.  Can this possibly matter?
		 */
		ip = mtod(copym, struct ip *);
		ip->ip_sum = 0;
		ip->ip_sum = in_cksum(copym, hlen);
		if_simloop(ifp, copym, AF_INET, 0);
	}
}