aboutsummaryrefslogtreecommitdiff
path: root/sys/compat/linux/linux_socket.c
blob: a4c5bf0b581e435f0ad70182cb6d682e9867dbdd (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
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
/*-
 * SPDX-License-Identifier: BSD-2-Clause-FreeBSD
 *
 * Copyright (c) 1995 Søren Schmidt
 * 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.
 *
 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR 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 AUTHOR 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.
 */

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

/* XXX we use functions that might not exist. */
#include "opt_compat.h"
#include "opt_inet6.h"

#include <sys/param.h>
#include <sys/proc.h>
#include <sys/systm.h>
#include <sys/sysproto.h>
#include <sys/capsicum.h>
#include <sys/fcntl.h>
#include <sys/file.h>
#include <sys/filedesc.h>
#include <sys/limits.h>
#include <sys/lock.h>
#include <sys/malloc.h>
#include <sys/mutex.h>
#include <sys/mbuf.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/syscallsubr.h>
#include <sys/uio.h>
#include <sys/stat.h>
#include <sys/syslog.h>
#include <sys/un.h>
#include <sys/unistd.h>

#include <security/audit/audit.h>

#include <net/if.h>
#include <net/vnet.h>
#include <netinet/in.h>
#include <netinet/in_systm.h>
#include <netinet/ip.h>
#include <netinet/tcp.h>
#ifdef INET6
#include <netinet/ip6.h>
#include <netinet6/ip6_var.h>
#endif

#ifdef COMPAT_LINUX32
#include <machine/../linux32/linux.h>
#include <machine/../linux32/linux32_proto.h>
#else
#include <machine/../linux/linux.h>
#include <machine/../linux/linux_proto.h>
#endif
#include <compat/linux/linux_common.h>
#include <compat/linux/linux_file.h>
#include <compat/linux/linux_mib.h>
#include <compat/linux/linux_socket.h>
#include <compat/linux/linux_timer.h>
#include <compat/linux/linux_util.h>

#define	SECURITY_CONTEXT_STRING	"unconfined"

static int linux_sendmsg_common(struct thread *, l_int, struct l_msghdr *,
					l_uint);
static int linux_recvmsg_common(struct thread *, l_int, struct l_msghdr *,
					l_uint, struct msghdr *);
static int linux_set_socket_flags(int, int *);

static int
linux_to_bsd_sockopt_level(int level)
{

	if (level == LINUX_SOL_SOCKET)
		return (SOL_SOCKET);
	/* Remaining values are RFC-defined protocol numbers. */
	return (level);
}

static int
bsd_to_linux_sockopt_level(int level)
{

	if (level == SOL_SOCKET)
		return (LINUX_SOL_SOCKET);
	return (level);
}

static int
linux_to_bsd_ip_sockopt(int opt)
{

	switch (opt) {
	/* known and translated sockopts */
	case LINUX_IP_TOS:
		return (IP_TOS);
	case LINUX_IP_TTL:
		return (IP_TTL);
	case LINUX_IP_HDRINCL:
		return (IP_HDRINCL);
	case LINUX_IP_OPTIONS:
		return (IP_OPTIONS);
	case LINUX_IP_RECVOPTS:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv4 socket option IP_RECVOPTS");
		return (IP_RECVOPTS);
	case LINUX_IP_RETOPTS:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv4 socket option IP_REETOPTS");
		return (IP_RETOPTS);
	case LINUX_IP_RECVTTL:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv4 socket option IP_RECVTTL");
		return (IP_RECVTTL);
	case LINUX_IP_RECVTOS:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv4 socket option IP_RECVTOS");
		return (IP_RECVTOS);
	case LINUX_IP_FREEBIND:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv4 socket option IP_FREEBIND");
		return (IP_BINDANY);
	case LINUX_IP_IPSEC_POLICY:
		/* we have this option, but not documented in ip(4) manpage */
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv4 socket option IP_IPSEC_POLICY");
		return (IP_IPSEC_POLICY);
	case LINUX_IP_MINTTL:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv4 socket option IP_MINTTL");
		return (IP_MINTTL);
	case LINUX_IP_MULTICAST_IF:
		return (IP_MULTICAST_IF);
	case LINUX_IP_MULTICAST_TTL:
		return (IP_MULTICAST_TTL);
	case LINUX_IP_MULTICAST_LOOP:
		return (IP_MULTICAST_LOOP);
	case LINUX_IP_ADD_MEMBERSHIP:
		return (IP_ADD_MEMBERSHIP);
	case LINUX_IP_DROP_MEMBERSHIP:
		return (IP_DROP_MEMBERSHIP);
	case LINUX_IP_UNBLOCK_SOURCE:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv4 socket option IP_UNBLOCK_SOURCE");
		return (IP_UNBLOCK_SOURCE);
	case LINUX_IP_BLOCK_SOURCE:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv4 socket option IP_BLOCK_SOURCE");
		return (IP_BLOCK_SOURCE);
	case LINUX_IP_ADD_SOURCE_MEMBERSHIP:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv4 socket option IP_ADD_SOURCE_MEMBERSHIP");
		return (IP_ADD_SOURCE_MEMBERSHIP);
	case LINUX_IP_DROP_SOURCE_MEMBERSHIP:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv4 socket option IP_DROP_SOURCE_MEMBERSHIP");
		return (IP_DROP_SOURCE_MEMBERSHIP);
	case LINUX_MCAST_JOIN_GROUP:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv4 socket option IP_MCAST_JOIN_GROUP");
		return (MCAST_JOIN_GROUP);
	case LINUX_MCAST_LEAVE_GROUP:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv4 socket option IP_MCAST_LEAVE_GROUP");
		return (MCAST_LEAVE_GROUP);
	case LINUX_MCAST_JOIN_SOURCE_GROUP:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv4 socket option IP_MCAST_JOIN_SOURCE_GROUP");
		return (MCAST_JOIN_SOURCE_GROUP);
	case LINUX_MCAST_LEAVE_SOURCE_GROUP:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv4 socket option IP_MCAST_LEAVE_SOURCE_GROUP");
		return (MCAST_LEAVE_SOURCE_GROUP);

	/* known but not implemented sockopts */
	case LINUX_IP_ROUTER_ALERT:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv4 socket option IP_ROUTER_ALERT (%d), you can not do user-space routing from linux programs",
		    opt);
		return (-2);
	case LINUX_IP_PKTINFO:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv4 socket option IP_PKTINFO (%d), you can not get extended packet info for datagram sockets in linux programs",
		    opt);
		return (-2);
	case LINUX_IP_PKTOPTIONS:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv4 socket option IP_PKTOPTIONS (%d)",
		    opt);
		return (-2);
	case LINUX_IP_MTU_DISCOVER:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv4 socket option IP_MTU_DISCOVER (%d), your linux program can not control path-MTU discovery",
		    opt);
		return (-2);
	case LINUX_IP_RECVERR:
		/* needed by steam */
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv4 socket option IP_RECVERR (%d), you can not get extended reliability info in linux programs",
		    opt);
		return (-2);
	case LINUX_IP_MTU:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv4 socket option IP_MTU (%d), your linux program can not control the MTU on this socket",
		    opt);
		return (-2);
	case LINUX_IP_XFRM_POLICY:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv4 socket option IP_XFRM_POLICY (%d)",
		    opt);
		return (-2);
	case LINUX_IP_PASSSEC:
		/* needed by steam */
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv4 socket option IP_PASSSEC (%d), you can not get IPSEC related credential information associated with this socket in linux programs -- if you do not use IPSEC, you can ignore this",
		    opt);
		return (-2);
	case LINUX_IP_TRANSPARENT:
		/* IP_BINDANY or more? */
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv4 socket option IP_TRANSPARENT (%d), you can not enable transparent proxying in linux programs -- note, IP_FREEBIND is supported, no idea if the FreeBSD IP_BINDANY is equivalent to the Linux IP_TRANSPARENT or not, any info is welcome",
		    opt);
		return (-2);
	case LINUX_IP_NODEFRAG:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv4 socket option IP_NODEFRAG (%d)",
		    opt);
		return (-2);
	case LINUX_IP_CHECKSUM:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv4 socket option IP_CHECKSUM (%d)",
		    opt);
		return (-2);
	case LINUX_IP_BIND_ADDRESS_NO_PORT:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv4 socket option IP_BIND_ADDRESS_NO_PORT (%d)",
		    opt);
		return (-2);
	case LINUX_IP_RECVFRAGSIZE:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv4 socket option IP_RECVFRAGSIZE (%d)",
		    opt);
		return (-2);
	case LINUX_MCAST_MSFILTER:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv4 socket option IP_MCAST_MSFILTER (%d)",
		    opt);
		return (-2);
	case LINUX_IP_MULTICAST_ALL:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv4 socket option IP_MULTICAST_ALL (%d), your linux program will not see all multicast groups joined by the entire system, only those the program joined itself on this socket",
		    opt);
		return (-2);
	case LINUX_IP_UNICAST_IF:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv4 socket option IP_UNICAST_IF (%d)",
		    opt);
		return (-2);

	/* unknown sockopts */
	default:
		return (-1);
	}
}

static int
linux_to_bsd_ip6_sockopt(int opt)
{

	switch (opt) {
	/* known and translated sockopts */
	case LINUX_IPV6_2292PKTINFO:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv6 socket option IPV6_2292PKTINFO");
		return (IPV6_2292PKTINFO);
	case LINUX_IPV6_2292HOPOPTS:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv6 socket option IPV6_2292HOPOPTS");
		return (IPV6_2292HOPOPTS);
	case LINUX_IPV6_2292DSTOPTS:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv6 socket option IPV6_2292DSTOPTS");
		return (IPV6_2292DSTOPTS);
	case LINUX_IPV6_2292RTHDR:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv6 socket option IPV6_2292RTHDR");
		return (IPV6_2292RTHDR);
	case LINUX_IPV6_2292PKTOPTIONS:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv6 socket option IPV6_2292PKTOPTIONS");
		return (IPV6_2292PKTOPTIONS);
	case LINUX_IPV6_CHECKSUM:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv6 socket option IPV6_CHECKSUM");
		return (IPV6_CHECKSUM);
	case LINUX_IPV6_2292HOPLIMIT:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv6 socket option IPV6_2292HOPLIMIT");
		return (IPV6_2292HOPLIMIT);
	case LINUX_IPV6_NEXTHOP:
		return (IPV6_NEXTHOP);
	case LINUX_IPV6_UNICAST_HOPS:
		return (IPV6_UNICAST_HOPS);
	case LINUX_IPV6_MULTICAST_IF:
		return (IPV6_MULTICAST_IF);
	case LINUX_IPV6_MULTICAST_HOPS:
		return (IPV6_MULTICAST_HOPS);
	case LINUX_IPV6_MULTICAST_LOOP:
		return (IPV6_MULTICAST_LOOP);
	case LINUX_IPV6_ADD_MEMBERSHIP:
		return (IPV6_JOIN_GROUP);
	case LINUX_IPV6_DROP_MEMBERSHIP:
		return (IPV6_LEAVE_GROUP);
	case LINUX_IPV6_V6ONLY:
		return (IPV6_V6ONLY);
	case LINUX_IPV6_IPSEC_POLICY:
		/* we have this option, but not documented in ip6(4) manpage */
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv6 socket option IPV6_IPSEC_POLICY");
		return (IPV6_IPSEC_POLICY);
	case LINUX_MCAST_JOIN_GROUP:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv6 socket option IPV6_JOIN_GROUP");
		return (IPV6_JOIN_GROUP);
	case LINUX_MCAST_LEAVE_GROUP:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv6 socket option IPV6_LEAVE_GROUP");
		return (IPV6_LEAVE_GROUP);
	case LINUX_IPV6_RECVPKTINFO:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv6 socket option IPV6_RECVPKTINFO");
		return (IPV6_RECVPKTINFO);
	case LINUX_IPV6_PKTINFO:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv6 socket option IPV6_PKTINFO");
		return (IPV6_PKTINFO);
	case LINUX_IPV6_RECVHOPLIMIT:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv6 socket option IPV6_RECVHOPLIMIT");
		return (IPV6_RECVHOPLIMIT);
	case LINUX_IPV6_HOPLIMIT:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv6 socket option IPV6_HOPLIMIT");
		return (IPV6_HOPLIMIT);
	case LINUX_IPV6_RECVHOPOPTS:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv6 socket option IPV6_RECVHOPOPTS");
		return (IPV6_RECVHOPOPTS);
	case LINUX_IPV6_HOPOPTS:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv6 socket option IPV6_HOPOPTS");
		return (IPV6_HOPOPTS);
	case LINUX_IPV6_RTHDRDSTOPTS:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv6 socket option IPV6_RTHDRDSTOPTS");
		return (IPV6_RTHDRDSTOPTS);
	case LINUX_IPV6_RECVRTHDR:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv6 socket option IPV6_RECVRTHDR");
		return (IPV6_RECVRTHDR);
	case LINUX_IPV6_RTHDR:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv6 socket option IPV6_RTHDR");
		return (IPV6_RTHDR);
	case LINUX_IPV6_RECVDSTOPTS:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv6 socket option IPV6_RECVDSTOPTS");
		return (IPV6_RECVDSTOPTS);
	case LINUX_IPV6_DSTOPTS:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv6 socket option IPV6_DSTOPTS");
		return (IPV6_DSTOPTS);
	case LINUX_IPV6_RECVPATHMTU:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv6 socket option IPV6_RECVPATHMTU");
		return (IPV6_RECVPATHMTU);
	case LINUX_IPV6_PATHMTU:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv6 socket option IPV6_PATHMTU");
		return (IPV6_PATHMTU);
	case LINUX_IPV6_DONTFRAG:
		return (IPV6_DONTFRAG);
	case LINUX_IPV6_AUTOFLOWLABEL:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv6 socket option IPV6_AUTOFLOWLABEL");
		return (IPV6_AUTOFLOWLABEL);
	case LINUX_IPV6_ORIGDSTADDR:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv6 socket option IPV6_ORIGDSTADDR");
		return (IPV6_ORIGDSTADDR);
	case LINUX_IPV6_FREEBIND:
		LINUX_RATELIMIT_MSG_NOTTESTED("IPv6 socket option IPV6_FREEBIND");
		return (IPV6_BINDANY);

	/* known but not implemented sockopts */
	case LINUX_IPV6_ADDRFORM:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv6 socket option IPV6_ADDRFORM (%d), you linux program can not convert the socket to IPv4",
		    opt);
		return (-2);
	case LINUX_IPV6_AUTHHDR:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv6 socket option IPV6_AUTHHDR (%d), your linux program can not get the authentication header info of IPv6 packets",
		    opt);
		return (-2);
	case LINUX_IPV6_FLOWINFO:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv6 socket option IPV6_FLOWINFO (%d), your linux program can not get the flowid of IPv6 packets",
		    opt);
		return (-2);
	case LINUX_IPV6_ROUTER_ALERT:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv6 socket option IPV6_ROUTER_ALERT (%d), you can not do user-space routing from linux programs",
		    opt);
		return (-2);
	case LINUX_IPV6_MTU_DISCOVER:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv6 socket option IPV6_MTU_DISCOVER (%d), your linux program can not control path-MTU discovery",
		    opt);
		return (-2);
	case LINUX_IPV6_MTU:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv6 socket option IPV6_MTU (%d), your linux program can not control the MTU on this socket",
		    opt);
		return (-2);
	case LINUX_IPV6_JOIN_ANYCAST:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv6 socket option IPV6_JOIN_ANYCAST (%d)",
		    opt);
		return (-2);
	case LINUX_IPV6_LEAVE_ANYCAST:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv6 socket option IPV6_LEAVE_ANYCAST (%d)",
		    opt);
		return (-2);
	case LINUX_IPV6_MULTICAST_ALL:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv6 socket option IPV6_MULTICAST_ALL (%d)",
		    opt);
		return (-2);
	case LINUX_IPV6_ROUTER_ALERT_ISOLATE:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv6 socket option IPV6_ROUTER_ALERT_ISOLATE (%d)",
		    opt);
		return (-2);
	case LINUX_IPV6_FLOWLABEL_MGR:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv6 socket option IPV6_FLOWLABEL_MGR (%d)",
		    opt);
		return (-2);
	case LINUX_IPV6_FLOWINFO_SEND:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv6 socket option IPV6_FLOWINFO_SEND (%d)",
		    opt);
		return (-2);
	case LINUX_IPV6_XFRM_POLICY:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv6 socket option IPV6_XFRM_POLICY (%d)",
		    opt);
		return (-2);
	case LINUX_IPV6_HDRINCL:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv6 socket option IPV6_HDRINCL (%d)",
		    opt);
		return (-2);
	case LINUX_MCAST_BLOCK_SOURCE:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv6 socket option MCAST_BLOCK_SOURCE (%d), your linux program may see more multicast stuff than it wants",
		    opt);
		return (-2);
	case LINUX_MCAST_UNBLOCK_SOURCE:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv6 socket option MCAST_UNBLOCK_SOURCE (%d), your linux program may not see all the multicast stuff it wants",
		    opt);
		return (-2);
	case LINUX_MCAST_JOIN_SOURCE_GROUP:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv6 socket option MCAST_JOIN_SOURCE_GROUP (%d), your linux program is not able to join a multicast source group",
		    opt);
		return (-2);
	case LINUX_MCAST_LEAVE_SOURCE_GROUP:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv6 socket option MCAST_LEAVE_SOURCE_GROUP (%d), your linux program is not able to leave a multicast source group -- but it was also not able to join one, so no issue",
		    opt);
		return (-2);
	case LINUX_MCAST_MSFILTER:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv6 socket option MCAST_MSFILTER (%d), your linux program can not manipulate the multicast filter, it may see more multicast data than it wants to see",
		    opt);
		return (-2);
	case LINUX_IPV6_ADDR_PREFERENCES:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv6 socket option IPV6_ADDR_PREFERENCES (%d)",
		    opt);
		return (-2);
	case LINUX_IPV6_MINHOPCOUNT:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv6 socket option IPV6_MINHOPCOUNT (%d)",
		    opt);
		return (-2);
	case LINUX_IPV6_TRANSPARENT:
		/* IP_BINDANY or more? */
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv6 socket option IPV6_TRANSPARENT (%d), you can not enable transparent proxying in linux programs -- note, IP_FREEBIND is supported, no idea if the FreeBSD IP_BINDANY is equivalent to the Linux IP_TRANSPARENT or not, any info is welcome",
		    opt);
		return (-2);
	case LINUX_IPV6_UNICAST_IF:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv6 socket option IPV6_UNICAST_IF (%d)",
		    opt);
		return (-2);
	case LINUX_IPV6_RECVFRAGSIZE:
		LINUX_RATELIMIT_MSG_OPT1(
		    "unsupported IPv6 socket option IPV6_RECVFRAGSIZE (%d)",
		    opt);
		return (-2);

	/* unknown sockopts */
	default:
		return (-1);
	}
}

static int
linux_to_bsd_so_sockopt(int opt)
{

	switch (opt) {
	case LINUX_SO_DEBUG:
		return (SO_DEBUG);
	case LINUX_SO_REUSEADDR:
		return (SO_REUSEADDR);
	case LINUX_SO_TYPE:
		return (SO_TYPE);
	case LINUX_SO_ERROR:
		return (SO_ERROR);
	case LINUX_SO_DONTROUTE:
		return (SO_DONTROUTE);
	case LINUX_SO_BROADCAST:
		return (SO_BROADCAST);
	case LINUX_SO_SNDBUF:
	case LINUX_SO_SNDBUFFORCE:
		return (SO_SNDBUF);
	case LINUX_SO_RCVBUF:
	case LINUX_SO_RCVBUFFORCE:
		return (SO_RCVBUF);
	case LINUX_SO_KEEPALIVE:
		return (SO_KEEPALIVE);
	case LINUX_SO_OOBINLINE:
		return (SO_OOBINLINE);
	case LINUX_SO_LINGER:
		return (SO_LINGER);
	case LINUX_SO_REUSEPORT:
		return (SO_REUSEPORT_LB);
	case LINUX_SO_PASSCRED:
		return (LOCAL_CREDS_PERSISTENT);
	case LINUX_SO_PEERCRED:
		return (LOCAL_PEERCRED);
	case LINUX_SO_RCVLOWAT:
		return (SO_RCVLOWAT);
	case LINUX_SO_SNDLOWAT:
		return (SO_SNDLOWAT);
	case LINUX_SO_RCVTIMEO:
		return (SO_RCVTIMEO);
	case LINUX_SO_SNDTIMEO:
		return (SO_SNDTIMEO);
	case LINUX_SO_TIMESTAMP:
		return (SO_TIMESTAMP);
	case LINUX_SO_ACCEPTCONN:
		return (SO_ACCEPTCONN);
	case LINUX_SO_PROTOCOL:
		return (SO_PROTOCOL);
	}
	return (-1);
}

static int
linux_to_bsd_tcp_sockopt(int opt)
{

	switch (opt) {
	case LINUX_TCP_NODELAY:
		return (TCP_NODELAY);
	case LINUX_TCP_MAXSEG:
		return (TCP_MAXSEG);
	case LINUX_TCP_CORK:
		return (TCP_NOPUSH);
	case LINUX_TCP_KEEPIDLE:
		return (TCP_KEEPIDLE);
	case LINUX_TCP_KEEPINTVL:
		return (TCP_KEEPINTVL);
	case LINUX_TCP_KEEPCNT:
		return (TCP_KEEPCNT);
	case LINUX_TCP_MD5SIG:
		return (TCP_MD5SIG);
	}
	return (-1);
}

static int
linux_to_bsd_msg_flags(int flags)
{
	int ret_flags = 0;

	if (flags & LINUX_MSG_OOB)
		ret_flags |= MSG_OOB;
	if (flags & LINUX_MSG_PEEK)
		ret_flags |= MSG_PEEK;
	if (flags & LINUX_MSG_DONTROUTE)
		ret_flags |= MSG_DONTROUTE;
	if (flags & LINUX_MSG_CTRUNC)
		ret_flags |= MSG_CTRUNC;
	if (flags & LINUX_MSG_TRUNC)
		ret_flags |= MSG_TRUNC;
	if (flags & LINUX_MSG_DONTWAIT)
		ret_flags |= MSG_DONTWAIT;
	if (flags & LINUX_MSG_EOR)
		ret_flags |= MSG_EOR;
	if (flags & LINUX_MSG_WAITALL)
		ret_flags |= MSG_WAITALL;
	if (flags & LINUX_MSG_NOSIGNAL)
		ret_flags |= MSG_NOSIGNAL;
	if (flags & LINUX_MSG_PROXY)
		LINUX_RATELIMIT_MSG_OPT1("socket message flag MSG_PROXY (%d) not handled",
		    LINUX_MSG_PROXY);
	if (flags & LINUX_MSG_FIN)
		LINUX_RATELIMIT_MSG_OPT1("socket message flag MSG_FIN (%d) not handled",
		    LINUX_MSG_FIN);
	if (flags & LINUX_MSG_SYN)
		LINUX_RATELIMIT_MSG_OPT1("socket message flag MSG_SYN (%d) not handled",
		    LINUX_MSG_SYN);
	if (flags & LINUX_MSG_CONFIRM)
		LINUX_RATELIMIT_MSG_OPT1("socket message flag MSG_CONFIRM (%d) not handled",
		    LINUX_MSG_CONFIRM);
	if (flags & LINUX_MSG_RST)
		LINUX_RATELIMIT_MSG_OPT1("socket message flag MSG_RST (%d) not handled",
		    LINUX_MSG_RST);
	if (flags & LINUX_MSG_ERRQUEUE)
		LINUX_RATELIMIT_MSG_OPT1("socket message flag MSG_ERRQUEUE (%d) not handled",
		    LINUX_MSG_ERRQUEUE);
	return (ret_flags);
}

static int
linux_to_bsd_cmsg_type(int cmsg_type)
{

	switch (cmsg_type) {
	case LINUX_SCM_RIGHTS:
		return (SCM_RIGHTS);
	case LINUX_SCM_CREDENTIALS:
		return (SCM_CREDS);
	}
	return (-1);
}

static int
bsd_to_linux_cmsg_type(int cmsg_type)
{

	switch (cmsg_type) {
	case SCM_RIGHTS:
		return (LINUX_SCM_RIGHTS);
	case SCM_CREDS:
		return (LINUX_SCM_CREDENTIALS);
	case SCM_CREDS2:
		return (LINUX_SCM_CREDENTIALS);
	case SCM_TIMESTAMP:
		return (LINUX_SCM_TIMESTAMP);
	}
	return (-1);
}

static int
linux_to_bsd_msghdr(struct msghdr *bhdr, const struct l_msghdr *lhdr)
{
	if (lhdr->msg_controllen > INT_MAX)
		return (ENOBUFS);

	bhdr->msg_name		= PTRIN(lhdr->msg_name);
	bhdr->msg_namelen	= lhdr->msg_namelen;
	bhdr->msg_iov		= PTRIN(lhdr->msg_iov);
	bhdr->msg_iovlen	= lhdr->msg_iovlen;
	bhdr->msg_control	= PTRIN(lhdr->msg_control);

	/*
	 * msg_controllen is skipped since BSD and LINUX control messages
	 * are potentially different sizes (e.g. the cred structure used
	 * by SCM_CREDS is different between the two operating system).
	 *
	 * The caller can set it (if necessary) after converting all the
	 * control messages.
	 */

	bhdr->msg_flags		= linux_to_bsd_msg_flags(lhdr->msg_flags);
	return (0);
}

static int
bsd_to_linux_msghdr(const struct msghdr *bhdr, struct l_msghdr *lhdr)
{
	lhdr->msg_name		= PTROUT(bhdr->msg_name);
	lhdr->msg_namelen	= bhdr->msg_namelen;
	lhdr->msg_iov		= PTROUT(bhdr->msg_iov);
	lhdr->msg_iovlen	= bhdr->msg_iovlen;
	lhdr->msg_control	= PTROUT(bhdr->msg_control);

	/*
	 * msg_controllen is skipped since BSD and LINUX control messages
	 * are potentially different sizes (e.g. the cred structure used
	 * by SCM_CREDS is different between the two operating system).
	 *
	 * The caller can set it (if necessary) after converting all the
	 * control messages.
	 */

	/* msg_flags skipped */
	return (0);
}

static int
linux_set_socket_flags(int lflags, int *flags)
{

	if (lflags & ~(LINUX_SOCK_CLOEXEC | LINUX_SOCK_NONBLOCK))
		return (EINVAL);
	if (lflags & LINUX_SOCK_NONBLOCK)
		*flags |= SOCK_NONBLOCK;
	if (lflags & LINUX_SOCK_CLOEXEC)
		*flags |= SOCK_CLOEXEC;
	return (0);
}

static int
linux_copyout_sockaddr(const struct sockaddr *sa, void *uaddr, size_t len)
{
	struct l_sockaddr *lsa;
	int error;

	error = bsd_to_linux_sockaddr(sa, &lsa, len);
	if (error != 0)
		return (error);
	
	error = copyout(lsa, uaddr, len);
	free(lsa, M_SONAME);

	return (error);
}

static int
linux_sendit(struct thread *td, int s, struct msghdr *mp, int flags,
    struct mbuf *control, enum uio_seg segflg)
{
	struct sockaddr *to;
	int error, len;

	if (mp->msg_name != NULL) {
		len = mp->msg_namelen;
		error = linux_to_bsd_sockaddr(mp->msg_name, &to, &len);
		if (error != 0)
			return (error);
		mp->msg_name = to;
	} else
		to = NULL;

	error = kern_sendit(td, s, mp, linux_to_bsd_msg_flags(flags), control,
	    segflg);

	if (to)
		free(to, M_SONAME);
	return (error);
}

/* Return 0 if IP_HDRINCL is set for the given socket. */
static int
linux_check_hdrincl(struct thread *td, int s)
{
	int error, optval;
	socklen_t size_val;

	size_val = sizeof(optval);
	error = kern_getsockopt(td, s, IPPROTO_IP, IP_HDRINCL,
	    &optval, UIO_SYSSPACE, &size_val);
	if (error != 0)
		return (error);

	return (optval == 0);
}

/*
 * Updated sendto() when IP_HDRINCL is set:
 * tweak endian-dependent fields in the IP packet.
 */
static int
linux_sendto_hdrincl(struct thread *td, struct linux_sendto_args *linux_args)
{
/*
 * linux_ip_copysize defines how many bytes we should copy
 * from the beginning of the IP packet before we customize it for BSD.
 * It should include all the fields we modify (ip_len and ip_off).
 */
#define linux_ip_copysize	8

	struct ip *packet;
	struct msghdr msg;
	struct iovec aiov[1];
	int error;

	/* Check that the packet isn't too big or too small. */
	if (linux_args->len < linux_ip_copysize ||
	    linux_args->len > IP_MAXPACKET)
		return (EINVAL);

	packet = (struct ip *)malloc(linux_args->len, M_LINUX, M_WAITOK);

	/* Make kernel copy of the packet to be sent */
	if ((error = copyin(PTRIN(linux_args->msg), packet,
	    linux_args->len)))
		goto goout;

	/* Convert fields from Linux to BSD raw IP socket format */
	packet->ip_len = linux_args->len;
	packet->ip_off = ntohs(packet->ip_off);

	/* Prepare the msghdr and iovec structures describing the new packet */
	msg.msg_name = PTRIN(linux_args->to);
	msg.msg_namelen = linux_args->tolen;
	msg.msg_iov = aiov;
	msg.msg_iovlen = 1;
	msg.msg_control = NULL;
	msg.msg_flags = 0;
	aiov[0].iov_base = (char *)packet;
	aiov[0].iov_len = linux_args->len;
	error = linux_sendit(td, linux_args->s, &msg, linux_args->flags,
	    NULL, UIO_SYSSPACE);
goout:
	free(packet, M_LINUX);
	return (error);
}

static const char *linux_netlink_names[] = {
	[LINUX_NETLINK_ROUTE] = "ROUTE",
	[LINUX_NETLINK_SOCK_DIAG] = "SOCK_DIAG",
	[LINUX_NETLINK_NFLOG] = "NFLOG",
	[LINUX_NETLINK_SELINUX] = "SELINUX",
	[LINUX_NETLINK_AUDIT] = "AUDIT",
	[LINUX_NETLINK_FIB_LOOKUP] = "FIB_LOOKUP",
	[LINUX_NETLINK_NETFILTER] = "NETFILTER",
	[LINUX_NETLINK_KOBJECT_UEVENT] = "KOBJECT_UEVENT",
};

int
linux_socket(struct thread *td, struct linux_socket_args *args)
{
	int domain, retval_socket, type;

	type = args->type & LINUX_SOCK_TYPE_MASK;
	if (type < 0 || type > LINUX_SOCK_MAX)
		return (EINVAL);
	retval_socket = linux_set_socket_flags(args->type & ~LINUX_SOCK_TYPE_MASK,
		&type);
	if (retval_socket != 0)
		return (retval_socket);
	domain = linux_to_bsd_domain(args->domain);
	if (domain == -1) {
		/* Mask off SOCK_NONBLOCK / CLOEXEC for error messages. */
		type = args->type & LINUX_SOCK_TYPE_MASK;
		if (args->domain == LINUX_AF_NETLINK &&
		    args->protocol == LINUX_NETLINK_AUDIT) {
			; /* Do nothing, quietly. */
		} else if (args->domain == LINUX_AF_NETLINK) {
			const char *nl_name;

			if (args->protocol >= 0 &&
			    args->protocol < nitems(linux_netlink_names))
				nl_name = linux_netlink_names[args->protocol];
			else
				nl_name = NULL;
			if (nl_name != NULL)
				linux_msg(curthread,
				    "unsupported socket(AF_NETLINK, %d, "
				    "NETLINK_%s)", type, nl_name);
			else
				linux_msg(curthread,
				    "unsupported socket(AF_NETLINK, %d, %d)",
				    type, args->protocol);
		} else {
			linux_msg(curthread, "unsupported socket domain %d, "
			    "type %d, protocol %d", args->domain, type,
			    args->protocol);
		}
		return (EAFNOSUPPORT);
	}

	retval_socket = kern_socket(td, domain, type, args->protocol);
	if (retval_socket)
		return (retval_socket);

	if (type == SOCK_RAW
	    && (args->protocol == IPPROTO_RAW || args->protocol == 0)
	    && domain == PF_INET) {
		/* It's a raw IP socket: set the IP_HDRINCL option. */
		int hdrincl;

		hdrincl = 1;
		/* We ignore any error returned by kern_setsockopt() */
		kern_setsockopt(td, td->td_retval[0], IPPROTO_IP, IP_HDRINCL,
		    &hdrincl, UIO_SYSSPACE, sizeof(hdrincl));
	}
#ifdef INET6
	/*
	 * Linux AF_INET6 socket has IPV6_V6ONLY setsockopt set to 0 by default
	 * and some apps depend on this. So, set V6ONLY to 0 for Linux apps.
	 * For simplicity we do this unconditionally of the net.inet6.ip6.v6only
	 * sysctl value.
	 */
	if (domain == PF_INET6) {
		int v6only;

		v6only = 0;
		/* We ignore any error returned by setsockopt() */
		kern_setsockopt(td, td->td_retval[0], IPPROTO_IPV6, IPV6_V6ONLY,
		    &v6only, UIO_SYSSPACE, sizeof(v6only));
	}
#endif

	return (retval_socket);
}

int
linux_bind(struct thread *td, struct linux_bind_args *args)
{
	struct sockaddr *sa;
	int error;

	error = linux_to_bsd_sockaddr(PTRIN(args->name), &sa,
	    &args->namelen);
	if (error != 0)
		return (error);

	error = kern_bindat(td, AT_FDCWD, args->s, sa);
	free(sa, M_SONAME);

	/* XXX */
	if (error == EADDRNOTAVAIL && args->namelen != sizeof(struct sockaddr_in))
		return (EINVAL);
	return (error);
}

int
linux_connect(struct thread *td, struct linux_connect_args *args)
{
	struct socket *so;
	struct sockaddr *sa;
	struct file *fp;
	u_int fflag;
	int error;

	error = linux_to_bsd_sockaddr(PTRIN(args->name), &sa,
	    &args->namelen);
	if (error != 0)
		return (error);

	error = kern_connectat(td, AT_FDCWD, args->s, sa);
	free(sa, M_SONAME);
	if (error != EISCONN)
		return (error);

	/*
	 * Linux doesn't return EISCONN the first time it occurs,
	 * when on a non-blocking socket. Instead it returns the
	 * error getsockopt(SOL_SOCKET, SO_ERROR) would return on BSD.
	 */
	error = getsock_cap(td, args->s, &cap_connect_rights,
	    &fp, &fflag, NULL);
	if (error != 0)
		return (error);

	error = EISCONN;
	so = fp->f_data;
	if (fflag & FNONBLOCK) {
		SOCK_LOCK(so);
		if (so->so_emuldata == 0)
			error = so->so_error;
		so->so_emuldata = (void *)1;
		SOCK_UNLOCK(so);
	}
	fdrop(fp, td);

	return (error);
}

int
linux_listen(struct thread *td, struct linux_listen_args *args)
{

	return (kern_listen(td, args->s, args->backlog));
}

static int
linux_accept_common(struct thread *td, int s, l_uintptr_t addr,
    l_uintptr_t namelen, int flags)
{
	struct sockaddr *sa;
	struct file *fp, *fp1;
	int bflags, len;
	struct socket *so;
	int error, error1;

	bflags = 0;
	fp = NULL;
	sa = NULL;

	error = linux_set_socket_flags(flags, &bflags);
	if (error != 0)
		return (error);

	if (PTRIN(addr) == NULL) {
		len = 0;
		error = kern_accept4(td, s, NULL, NULL, bflags, NULL);
	} else {
		error = copyin(PTRIN(namelen), &len, sizeof(len));
		if (error != 0)
			return (error);
		if (len < 0)
			return (EINVAL);
		error = kern_accept4(td, s, &sa, &len, bflags, &fp);
	}

	/*
	 * Translate errno values into ones used by Linux.
	 */
	if (error != 0) {
		/*
		 * XXX. This is wrong, different sockaddr structures
		 * have different sizes.
		 */
		switch (error) {
		case EFAULT:
			if (namelen != sizeof(struct sockaddr_in))
				error = EINVAL;
			break;
		case EINVAL:
			error1 = getsock_cap(td, s, &cap_accept_rights, &fp1, NULL, NULL);
			if (error1 != 0) {
				error = error1;
				break;
			}
			so = fp1->f_data;
			if (so->so_type == SOCK_DGRAM)
				error = EOPNOTSUPP;
			fdrop(fp1, td);
			break;
		}
		return (error);
	}

	if (len != 0) {
		error = linux_copyout_sockaddr(sa, PTRIN(addr), len);

		/*
		 * XXX: We should also copyout the len, shouldn't we?
		 */

		if (error != 0) {
			fdclose(td, fp, td->td_retval[0]);
			td->td_retval[0] = 0;
		}
	}
	if (fp != NULL)
		fdrop(fp, td);
	free(sa, M_SONAME);
	return (error);
}

int
linux_accept(struct thread *td, struct linux_accept_args *args)
{

	return (linux_accept_common(td, args->s, args->addr,
	    args->namelen, 0));
}

int
linux_accept4(struct thread *td, struct linux_accept4_args *args)
{

	return (linux_accept_common(td, args->s, args->addr,
	    args->namelen, args->flags));
}

int
linux_getsockname(struct thread *td, struct linux_getsockname_args *args)
{
	struct sockaddr *sa;
	int len, error;

	error = copyin(PTRIN(args->namelen), &len, sizeof(len));
	if (error != 0)
		return (error);

	error = kern_getsockname(td, args->s, &sa, &len);
	if (error != 0)
		return (error);

	if (len != 0)
		error = linux_copyout_sockaddr(sa, PTRIN(args->addr), len);

	free(sa, M_SONAME);
	if (error == 0)
		error = copyout(&len, PTRIN(args->namelen), sizeof(len));
	return (error);
}

int
linux_getpeername(struct thread *td, struct linux_getpeername_args *args)
{
	struct sockaddr *sa;
	int len, error;

	error = copyin(PTRIN(args->namelen), &len, sizeof(len));
	if (error != 0)
		return (error);
	if (len < 0)
		return (EINVAL);

	error = kern_getpeername(td, args->s, &sa, &len);
	if (error != 0)
		return (error);

	if (len != 0)
		error = linux_copyout_sockaddr(sa, PTRIN(args->addr), len);

	free(sa, M_SONAME);
	if (error == 0)
		error = copyout(&len, PTRIN(args->namelen), sizeof(len));
	return (error);
}

int
linux_socketpair(struct thread *td, struct linux_socketpair_args *args)
{
	int domain, error, sv[2], type;

	domain = linux_to_bsd_domain(args->domain);
	if (domain != PF_LOCAL)
		return (EAFNOSUPPORT);
	type = args->type & LINUX_SOCK_TYPE_MASK;
	if (type < 0 || type > LINUX_SOCK_MAX)
		return (EINVAL);
	error = linux_set_socket_flags(args->type & ~LINUX_SOCK_TYPE_MASK,
	    &type);
	if (error != 0)
		return (error);
	if (args->protocol != 0 && args->protocol != PF_UNIX) {
		/*
		 * Use of PF_UNIX as protocol argument is not right,
		 * but Linux does it.
		 * Do not map PF_UNIX as its Linux value is identical
		 * to FreeBSD one.
		 */
		return (EPROTONOSUPPORT);
	}
	error = kern_socketpair(td, domain, type, 0, sv);
	if (error != 0)
                return (error);
        error = copyout(sv, PTRIN(args->rsv), 2 * sizeof(int));
        if (error != 0) {
                (void)kern_close(td, sv[0]);
                (void)kern_close(td, sv[1]);
        }
	return (error);
}

#if defined(__i386__) || (defined(__amd64__) && defined(COMPAT_LINUX32))
struct linux_send_args {
	register_t s;
	register_t msg;
	register_t len;
	register_t flags;
};

static int
linux_send(struct thread *td, struct linux_send_args *args)
{
	struct sendto_args /* {
		int s;
		caddr_t buf;
		int len;
		int flags;
		caddr_t to;
		int tolen;
	} */ bsd_args;
	struct file *fp;
	int error, fflag;

	bsd_args.s = args->s;
	bsd_args.buf = (caddr_t)PTRIN(args->msg);
	bsd_args.len = args->len;
	bsd_args.flags = linux_to_bsd_msg_flags(args->flags);
	bsd_args.to = NULL;
	bsd_args.tolen = 0;
	error = sys_sendto(td, &bsd_args);
	if (error == ENOTCONN) {
		/*
		 * Linux doesn't return ENOTCONN for non-blocking sockets.
		 * Instead it returns the EAGAIN.
		 */
		error = getsock_cap(td, args->s, &cap_send_rights, &fp,
		    &fflag, NULL);
		if (error == 0) {
			if (fflag & FNONBLOCK)
				error = EAGAIN;
			fdrop(fp, td);
		}
	}
	return (error);
}

struct linux_recv_args {
	register_t s;
	register_t msg;
	register_t len;
	register_t flags;
};

static int
linux_recv(struct thread *td, struct linux_recv_args *args)
{
	struct recvfrom_args /* {
		int s;
		caddr_t buf;
		int len;
		int flags;
		struct sockaddr *from;
		socklen_t fromlenaddr;
	} */ bsd_args;

	bsd_args.s = args->s;
	bsd_args.buf = (caddr_t)PTRIN(args->msg);
	bsd_args.len = args->len;
	bsd_args.flags = linux_to_bsd_msg_flags(args->flags);
	bsd_args.from = NULL;
	bsd_args.fromlenaddr = 0;
	return (sys_recvfrom(td, &bsd_args));
}
#endif /* __i386__ || (__amd64__ && COMPAT_LINUX32) */

int
linux_sendto(struct thread *td, struct linux_sendto_args *args)
{
	struct msghdr msg;
	struct iovec aiov;

	if (linux_check_hdrincl(td, args->s) == 0)
		/* IP_HDRINCL set, tweak the packet before sending */
		return (linux_sendto_hdrincl(td, args));

	msg.msg_name = PTRIN(args->to);
	msg.msg_namelen = args->tolen;
	msg.msg_iov = &aiov;
	msg.msg_iovlen = 1;
	msg.msg_control = NULL;
	msg.msg_flags = 0;
	aiov.iov_base = PTRIN(args->msg);
	aiov.iov_len = args->len;
	return (linux_sendit(td, args->s, &msg, args->flags, NULL,
	    UIO_USERSPACE));
}

int
linux_recvfrom(struct thread *td, struct linux_recvfrom_args *args)
{
	struct sockaddr *sa;
	struct msghdr msg;
	struct iovec aiov;
	int error, fromlen;

	if (PTRIN(args->fromlen) != NULL) {
		error = copyin(PTRIN(args->fromlen), &fromlen,
		    sizeof(fromlen));
		if (error != 0)
			return (error);
		if (fromlen < 0)
			return (EINVAL);
		sa = malloc(fromlen, M_SONAME, M_WAITOK);
	} else {
		fromlen = 0;
		sa = NULL;
	}

	msg.msg_name = sa;
	msg.msg_namelen = fromlen;
	msg.msg_iov = &aiov;
	msg.msg_iovlen = 1;
	aiov.iov_base = PTRIN(args->buf);
	aiov.iov_len = args->len;
	msg.msg_control = 0;
	msg.msg_flags = linux_to_bsd_msg_flags(args->flags);

	error = kern_recvit(td, args->s, &msg, UIO_SYSSPACE, NULL);
	if (error != 0)
		goto out;

	if (PTRIN(args->from) != NULL)
		error = linux_copyout_sockaddr(sa, PTRIN(args->from), msg.msg_namelen);

	if (error == 0 && PTRIN(args->fromlen) != NULL)
		error = copyout(&msg.msg_namelen, PTRIN(args->fromlen),
		    sizeof(msg.msg_namelen));
out:
	free(sa, M_SONAME);
	return (error);
}

static int
linux_sendmsg_common(struct thread *td, l_int s, struct l_msghdr *msghdr,
    l_uint flags)
{
	struct cmsghdr *cmsg;
	struct mbuf *control;
	struct msghdr msg;
	struct l_cmsghdr linux_cmsg;
	struct l_cmsghdr *ptr_cmsg;
	struct l_msghdr linux_msghdr;
	struct iovec *iov;
	socklen_t datalen;
	struct sockaddr *sa;
	struct socket *so;
	sa_family_t sa_family;
	struct file *fp;
	void *data;
	l_size_t len;
	l_size_t clen;
	int error, fflag;

	error = copyin(msghdr, &linux_msghdr, sizeof(linux_msghdr));
	if (error != 0)
		return (error);

	/*
	 * Some Linux applications (ping) define a non-NULL control data
	 * pointer, but a msg_controllen of 0, which is not allowed in the
	 * FreeBSD system call interface.  NULL the msg_control pointer in
	 * order to handle this case.  This should be checked, but allows the
	 * Linux ping to work.
	 */
	if (PTRIN(linux_msghdr.msg_control) != NULL &&
	    linux_msghdr.msg_controllen == 0)
		linux_msghdr.msg_control = PTROUT(NULL);

	error = linux_to_bsd_msghdr(&msg, &linux_msghdr);
	if (error != 0)
		return (error);

#ifdef COMPAT_LINUX32
	error = linux32_copyiniov(PTRIN(msg.msg_iov), msg.msg_iovlen,
	    &iov, EMSGSIZE);
#else
	error = copyiniov(msg.msg_iov, msg.msg_iovlen, &iov, EMSGSIZE);
#endif
	if (error != 0)
		return (error);

	control = NULL;

	error = kern_getsockname(td, s, &sa, &datalen);
	if (error != 0)
		goto bad;
	sa_family = sa->sa_family;
	free(sa, M_SONAME);

	if (flags & LINUX_MSG_OOB) {
		error = EOPNOTSUPP;
		if (sa_family == AF_UNIX)
			goto bad;

		error = getsock_cap(td, s, &cap_send_rights, &fp,
		    &fflag, NULL);
		if (error != 0)
			goto bad;
		so = fp->f_data;
		if (so->so_type != SOCK_STREAM)
			error = EOPNOTSUPP;
		fdrop(fp, td);
		if (error != 0)
			goto bad;
	}

	if (linux_msghdr.msg_controllen >= sizeof(struct l_cmsghdr)) {
		error = ENOBUFS;
		control = m_get(M_WAITOK, MT_CONTROL);
		MCLGET(control, M_WAITOK);
		data = mtod(control, void *);
		datalen = 0;

		ptr_cmsg = PTRIN(linux_msghdr.msg_control);
		clen = linux_msghdr.msg_controllen;
		do {
			error = copyin(ptr_cmsg, &linux_cmsg,
			    sizeof(struct l_cmsghdr));
			if (error != 0)
				goto bad;

			error = EINVAL;
			if (linux_cmsg.cmsg_len < sizeof(struct l_cmsghdr) ||
			    linux_cmsg.cmsg_len > clen)
				goto bad;

			if (datalen + CMSG_HDRSZ > MCLBYTES)
				goto bad;

			/*
			 * Now we support only SCM_RIGHTS and SCM_CRED,
			 * so return EINVAL in any other cmsg_type
			 */
			cmsg = data;
			cmsg->cmsg_type =
			    linux_to_bsd_cmsg_type(linux_cmsg.cmsg_type);
			cmsg->cmsg_level =
			    linux_to_bsd_sockopt_level(linux_cmsg.cmsg_level);
			if (cmsg->cmsg_type == -1
			    || cmsg->cmsg_level != SOL_SOCKET) {
				linux_msg(curthread,
				    "unsupported sendmsg cmsg level %d type %d",
				    linux_cmsg.cmsg_level, linux_cmsg.cmsg_type);
				goto bad;
			}

			/*
			 * Some applications (e.g. pulseaudio) attempt to
			 * send ancillary data even if the underlying protocol
			 * doesn't support it which is not allowed in the
			 * FreeBSD system call interface.
			 */
			if (sa_family != AF_UNIX)
				goto next;

			if (cmsg->cmsg_type == SCM_CREDS) {
				len = sizeof(struct cmsgcred);
				if (datalen + CMSG_SPACE(len) > MCLBYTES)
					goto bad;

				/*
				 * The lower levels will fill in the structure
				 */
				memset(CMSG_DATA(data), 0, len);
			} else {
				len = linux_cmsg.cmsg_len - L_CMSG_HDRSZ;
				if (datalen + CMSG_SPACE(len) < datalen ||
				    datalen + CMSG_SPACE(len) > MCLBYTES)
					goto bad;

				error = copyin(LINUX_CMSG_DATA(ptr_cmsg),
				    CMSG_DATA(data), len);
				if (error != 0)
					goto bad;
			}

			cmsg->cmsg_len = CMSG_LEN(len);
			data = (char *)data + CMSG_SPACE(len);
			datalen += CMSG_SPACE(len);

next:
			if (clen <= LINUX_CMSG_ALIGN(linux_cmsg.cmsg_len))
				break;

			clen -= LINUX_CMSG_ALIGN(linux_cmsg.cmsg_len);
			ptr_cmsg = (struct l_cmsghdr *)((char *)ptr_cmsg +
			    LINUX_CMSG_ALIGN(linux_cmsg.cmsg_len));
		} while(clen >= sizeof(struct l_cmsghdr));

		control->m_len = datalen;
		if (datalen == 0) {
			m_freem(control);
			control = NULL;
		}
	}

	msg.msg_iov = iov;
	msg.msg_flags = 0;
	error = linux_sendit(td, s, &msg, flags, control, UIO_USERSPACE);
	control = NULL;

bad:
	m_freem(control);
	free(iov, M_IOV);
	return (error);
}

int
linux_sendmsg(struct thread *td, struct linux_sendmsg_args *args)
{

	return (linux_sendmsg_common(td, args->s, PTRIN(args->msg),
	    args->flags));
}

int
linux_sendmmsg(struct thread *td, struct linux_sendmmsg_args *args)
{
	struct l_mmsghdr *msg;
	l_uint retval;
	int error, datagrams;

	if (args->vlen > UIO_MAXIOV)
		args->vlen = UIO_MAXIOV;

	msg = PTRIN(args->msg);
	datagrams = 0;
	while (datagrams < args->vlen) {
		error = linux_sendmsg_common(td, args->s, &msg->msg_hdr,
		    args->flags);
		if (error != 0)
			break;

		retval = td->td_retval[0];
		error = copyout(&retval, &msg->msg_len, sizeof(msg->msg_len));
		if (error != 0)
			break;
		++msg;
		++datagrams;
	}
	if (error == 0)
		td->td_retval[0] = datagrams;
	return (error);
}

static int
linux_recvmsg_common(struct thread *td, l_int s, struct l_msghdr *msghdr,
    l_uint flags, struct msghdr *msg)
{
	struct cmsghdr *cm;
	struct cmsgcred *cmcred;
	struct sockcred2 *scred;
	struct l_cmsghdr *linux_cmsg = NULL;
	struct l_ucred linux_ucred;
	socklen_t datalen, maxlen, outlen;
	struct l_msghdr linux_msghdr;
	struct iovec *iov, *uiov;
	struct mbuf *control = NULL;
	struct mbuf **controlp;
	struct timeval *ftmvl;
	struct sockaddr *sa;
	l_timeval ltmvl;
	caddr_t outbuf;
	void *data;
	int error, i, fd, fds, *fdp;

	error = copyin(msghdr, &linux_msghdr, sizeof(linux_msghdr));
	if (error != 0)
		return (error);

	error = linux_to_bsd_msghdr(msg, &linux_msghdr);
	if (error != 0)
		return (error);

#ifdef COMPAT_LINUX32
	error = linux32_copyiniov(PTRIN(msg->msg_iov), msg->msg_iovlen,
	    &iov, EMSGSIZE);
#else
	error = copyiniov(msg->msg_iov, msg->msg_iovlen, &iov, EMSGSIZE);
#endif
	if (error != 0)
		return (error);

	if (msg->msg_name != NULL && msg->msg_namelen > 0) {
		msg->msg_namelen = min(msg->msg_namelen, SOCK_MAXADDRLEN);
		sa = malloc(msg->msg_namelen, M_SONAME, M_WAITOK);
		msg->msg_name = sa;
	} else {
		sa = NULL;
		msg->msg_name = NULL;
	}

	uiov = msg->msg_iov;
	msg->msg_iov = iov;
	controlp = (msg->msg_control != NULL) ? &control : NULL;
	error = kern_recvit(td, s, msg, UIO_SYSSPACE, controlp);
	msg->msg_iov = uiov;
	if (error != 0)
		goto bad;

	/*
	 * Note that kern_recvit() updates msg->msg_namelen.
	 */
	if (msg->msg_name != NULL && msg->msg_namelen > 0) {
		msg->msg_name = PTRIN(linux_msghdr.msg_name);
		error = linux_copyout_sockaddr(sa,
		    PTRIN(msg->msg_name), msg->msg_namelen);
		if (error != 0)
			goto bad;
	}

	error = bsd_to_linux_msghdr(msg, &linux_msghdr);
	if (error != 0)
		goto bad;

	maxlen = linux_msghdr.msg_controllen;
	linux_msghdr.msg_controllen = 0;
	if (control) {
		linux_cmsg = malloc(L_CMSG_HDRSZ, M_LINUX, M_WAITOK | M_ZERO);

		msg->msg_control = mtod(control, struct cmsghdr *);
		msg->msg_controllen = control->m_len;

		cm = CMSG_FIRSTHDR(msg);
		outbuf = PTRIN(linux_msghdr.msg_control);
		outlen = 0;
		while (cm != NULL) {
			linux_cmsg->cmsg_type =
			    bsd_to_linux_cmsg_type(cm->cmsg_type);
			linux_cmsg->cmsg_level =
			    bsd_to_linux_sockopt_level(cm->cmsg_level);
			if (linux_cmsg->cmsg_type == -1 ||
			    cm->cmsg_level != SOL_SOCKET) {
				linux_msg(curthread,
				    "unsupported recvmsg cmsg level %d type %d",
				    cm->cmsg_level, cm->cmsg_type);
				error = EINVAL;
				goto bad;
			}

			data = CMSG_DATA(cm);
			datalen = (caddr_t)cm + cm->cmsg_len - (caddr_t)data;

			switch (cm->cmsg_type) {
			case SCM_RIGHTS:
				if (flags & LINUX_MSG_CMSG_CLOEXEC) {
					fds = datalen / sizeof(int);
					fdp = data;
					for (i = 0; i < fds; i++) {
						fd = *fdp++;
						(void)kern_fcntl(td, fd,
						    F_SETFD, FD_CLOEXEC);
					}
				}
				break;

			case SCM_CREDS:
				/*
				 * Currently LOCAL_CREDS is never in
				 * effect for Linux so no need to worry
				 * about sockcred
				 */
				if (datalen != sizeof(*cmcred)) {
					error = EMSGSIZE;
					goto bad;
				}
				cmcred = (struct cmsgcred *)data;
				bzero(&linux_ucred, sizeof(linux_ucred));
				linux_ucred.pid = cmcred->cmcred_pid;
				linux_ucred.uid = cmcred->cmcred_uid;
				linux_ucred.gid = cmcred->cmcred_gid;
				data = &linux_ucred;
				datalen = sizeof(linux_ucred);
				break;

			case SCM_CREDS2:
				scred = data;
				bzero(&linux_ucred, sizeof(linux_ucred));
				linux_ucred.pid = scred->sc_pid;
				linux_ucred.uid = scred->sc_uid;
				linux_ucred.gid = scred->sc_gid;
				data = &linux_ucred;
				datalen = sizeof(linux_ucred);
				break;

			case SCM_TIMESTAMP:
				if (datalen != sizeof(struct timeval)) {
					error = EMSGSIZE;
					goto bad;
				}
				ftmvl = (struct timeval *)data;
				ltmvl.tv_sec = ftmvl->tv_sec;
				ltmvl.tv_usec = ftmvl->tv_usec;
				data = &ltmvl;
				datalen = sizeof(ltmvl);
				break;
			}

			if (outlen + LINUX_CMSG_LEN(datalen) > maxlen) {
				if (outlen == 0) {
					error = EMSGSIZE;
					goto bad;
				} else {
					linux_msghdr.msg_flags |= LINUX_MSG_CTRUNC;
					m_dispose_extcontrolm(control);
					goto out;
				}
			}

			linux_cmsg->cmsg_len = LINUX_CMSG_LEN(datalen);

			error = copyout(linux_cmsg, outbuf, L_CMSG_HDRSZ);
			if (error != 0)
				goto bad;
			outbuf += L_CMSG_HDRSZ;

			error = copyout(data, outbuf, datalen);
			if (error != 0)
				goto bad;

			outbuf += LINUX_CMSG_ALIGN(datalen);
			outlen += LINUX_CMSG_LEN(datalen);

			cm = CMSG_NXTHDR(msg, cm);
		}
		linux_msghdr.msg_controllen = outlen;
	}

out:
	error = copyout(&linux_msghdr, msghdr, sizeof(linux_msghdr));

bad:
	if (control != NULL) {
		if (error != 0)
			m_dispose_extcontrolm(control);
		m_freem(control);
	}
	free(iov, M_IOV);
	free(linux_cmsg, M_LINUX);
	free(sa, M_SONAME);

	return (error);
}

int
linux_recvmsg(struct thread *td, struct linux_recvmsg_args *args)
{
	struct msghdr bsd_msg;

	return (linux_recvmsg_common(td, args->s, PTRIN(args->msg),
	    args->flags, &bsd_msg));
}

int
linux_recvmmsg(struct thread *td, struct linux_recvmmsg_args *args)
{
	struct l_mmsghdr *msg;
	struct msghdr bsd_msg;
	struct l_timespec lts;
	struct timespec ts, tts;
	l_uint retval;
	int error, datagrams;

	if (args->timeout) {
		error = copyin(args->timeout, &lts, sizeof(struct l_timespec));
		if (error != 0)
			return (error);
		error = linux_to_native_timespec(&ts, &lts);
		if (error != 0)
			return (error);
		getnanotime(&tts);
		timespecadd(&tts, &ts, &tts);
	}

	msg = PTRIN(args->msg);
	datagrams = 0;
	while (datagrams < args->vlen) {
		error = linux_recvmsg_common(td, args->s, &msg->msg_hdr,
		    args->flags & ~LINUX_MSG_WAITFORONE, &bsd_msg);
		if (error != 0)
			break;

		retval = td->td_retval[0];
		error = copyout(&retval, &msg->msg_len, sizeof(msg->msg_len));
		if (error != 0)
			break;
		++msg;
		++datagrams;

		/*
		 * MSG_WAITFORONE turns on MSG_DONTWAIT after one packet.
		 */
		if (args->flags & LINUX_MSG_WAITFORONE)
			args->flags |= LINUX_MSG_DONTWAIT;

		/*
		 * See BUGS section of recvmmsg(2).
		 */
		if (args->timeout) {
			getnanotime(&ts);
			timespecsub(&ts, &tts, &ts);
			if (!timespecisset(&ts) || ts.tv_sec > 0)
				break;
		}
		/* Out of band data, return right away. */
		if (bsd_msg.msg_flags & MSG_OOB)
			break;
	}
	if (error == 0)
		td->td_retval[0] = datagrams;
	return (error);
}

int
linux_shutdown(struct thread *td, struct linux_shutdown_args *args)
{

	return (kern_shutdown(td, args->s, args->how));
}

int
linux_setsockopt(struct thread *td, struct linux_setsockopt_args *args)
{
	l_timeval linux_tv;
	struct sockaddr *sa;
	struct timeval tv;
	socklen_t len;
	int error, level, name;

	level = linux_to_bsd_sockopt_level(args->level);
	switch (level) {
	case SOL_SOCKET:
		name = linux_to_bsd_so_sockopt(args->optname);
		switch (name) {
		case LOCAL_CREDS_PERSISTENT:
			level = SOL_LOCAL;
			break;
		case SO_RCVTIMEO:
			/* FALLTHROUGH */
		case SO_SNDTIMEO:
			error = copyin(PTRIN(args->optval), &linux_tv,
			    sizeof(linux_tv));
			if (error != 0)
				return (error);
			tv.tv_sec = linux_tv.tv_sec;
			tv.tv_usec = linux_tv.tv_usec;
			return (kern_setsockopt(td, args->s, level,
			    name, &tv, UIO_SYSSPACE, sizeof(tv)));
			/* NOTREACHED */
		default:
			break;
		}
		break;
	case IPPROTO_IP:
		if (args->optname == LINUX_IP_RECVERR &&
		    linux_ignore_ip_recverr) {
			/*
			 * XXX: This is a hack to unbreak DNS resolution
			 *	with glibc 2.30 and above.
			 */
			return (0);
		}
		name = linux_to_bsd_ip_sockopt(args->optname);
		break;
	case IPPROTO_IPV6:
		name = linux_to_bsd_ip6_sockopt(args->optname);
		break;
	case IPPROTO_TCP:
		name = linux_to_bsd_tcp_sockopt(args->optname);
		break;
	default:
		name = -1;
		break;
	}
	if (name < 0) {
		if (name == -1)
			linux_msg(curthread,
			    "unsupported setsockopt level %d optname %d",
			    args->level, args->optname);
		return (ENOPROTOOPT);
	}

	if (name == IPV6_NEXTHOP) {
		len = args->optlen;
		error = linux_to_bsd_sockaddr(PTRIN(args->optval), &sa, &len);
		if (error != 0)
			return (error);

		error = kern_setsockopt(td, args->s, level,
		    name, sa, UIO_SYSSPACE, len);
		free(sa, M_SONAME);
	} else {
		error = kern_setsockopt(td, args->s, level,
		    name, PTRIN(args->optval), UIO_USERSPACE, args->optlen);
	}

	return (error);
}

static int
linux_getsockopt_so_peersec(struct thread *td,
    struct linux_getsockopt_args *args)
{
	socklen_t len;
	int error;

	len = sizeof(SECURITY_CONTEXT_STRING);
	if (args->optlen < len) {
		error = copyout(&len, PTRIN(args->optlen), sizeof(len));
		if (error == 0)
			error = ERANGE;
		return (error);
	}

	error = copyout(SECURITY_CONTEXT_STRING,
	    PTRIN(args->optval), sizeof(SECURITY_CONTEXT_STRING));
	if (error == 0)
		error = copyout(&len, PTRIN(args->optlen), sizeof(len));
	return (error);
}

int
linux_getsockopt(struct thread *td, struct linux_getsockopt_args *args)
{
	l_timeval linux_tv;
	struct timeval tv;
	socklen_t tv_len, xulen, len;
	struct sockaddr *sa;
	struct xucred xu;
	struct l_ucred lxu;
	int error, level, name, newval;

	level = linux_to_bsd_sockopt_level(args->level);
	switch (level) {
	case SOL_SOCKET:
		if (args->optname == LINUX_SO_PEERSEC)
			return (linux_getsockopt_so_peersec(td, args));
		name = linux_to_bsd_so_sockopt(args->optname);
		switch (name) {
		case LOCAL_CREDS_PERSISTENT:
			level = SOL_LOCAL;
			break;
		case SO_RCVTIMEO:
			/* FALLTHROUGH */
		case SO_SNDTIMEO:
			tv_len = sizeof(tv);
			error = kern_getsockopt(td, args->s, level,
			    name, &tv, UIO_SYSSPACE, &tv_len);
			if (error != 0)
				return (error);
			linux_tv.tv_sec = tv.tv_sec;
			linux_tv.tv_usec = tv.tv_usec;
			return (copyout(&linux_tv, PTRIN(args->optval),
			    sizeof(linux_tv)));
			/* NOTREACHED */
		case LOCAL_PEERCRED:
			if (args->optlen < sizeof(lxu))
				return (EINVAL);
			/*
			 * LOCAL_PEERCRED is not served at the SOL_SOCKET level,
			 * but by the Unix socket's level 0.
			 */
			level = 0;
			xulen = sizeof(xu);
			error = kern_getsockopt(td, args->s, level,
			    name, &xu, UIO_SYSSPACE, &xulen);
			if (error != 0)
				return (error);
			lxu.pid = xu.cr_pid;
			lxu.uid = xu.cr_uid;
			lxu.gid = xu.cr_gid;
			return (copyout(&lxu, PTRIN(args->optval), sizeof(lxu)));
			/* NOTREACHED */
		case SO_ERROR:
			len = sizeof(newval);
			error = kern_getsockopt(td, args->s, level,
			    name, &newval, UIO_SYSSPACE, &len);
			if (error != 0)
				return (error);
			newval = -bsd_to_linux_errno(newval);
			return (copyout(&newval, PTRIN(args->optval), len));
			/* NOTREACHED */
		default:
			break;
		}
		break;
	case IPPROTO_IP:
		name = linux_to_bsd_ip_sockopt(args->optname);
		break;
	case IPPROTO_IPV6:
		name = linux_to_bsd_ip6_sockopt(args->optname);
		break;
	case IPPROTO_TCP:
		name = linux_to_bsd_tcp_sockopt(args->optname);
		break;
	default:
		name = -1;
		break;
	}
	if (name < 0) {
		if (name == -1)
			linux_msg(curthread,
			    "unsupported getsockopt level %d optname %d",
			    args->level, args->optname);
		return (EINVAL);
	}

	if (name == IPV6_NEXTHOP) {
		error = copyin(PTRIN(args->optlen), &len, sizeof(len));
                if (error != 0)
                        return (error);
		sa = malloc(len, M_SONAME, M_WAITOK);

		error = kern_getsockopt(td, args->s, level,
		    name, sa, UIO_SYSSPACE, &len);
		if (error != 0)
			goto out;

		error = linux_copyout_sockaddr(sa, PTRIN(args->optval), len);
		if (error == 0)
			error = copyout(&len, PTRIN(args->optlen),
			    sizeof(len));
out:
		free(sa, M_SONAME);
	} else {
		if (args->optval) {
			error = copyin(PTRIN(args->optlen), &len, sizeof(len));
			if (error != 0)
				return (error);
		}
		error = kern_getsockopt(td, args->s, level,
		    name, PTRIN(args->optval), UIO_USERSPACE, &len);
		if (error == 0)
			error = copyout(&len, PTRIN(args->optlen),
			    sizeof(len));
	}

	return (error);
}

static int
linux_sendfile_common(struct thread *td, l_int out, l_int in,
    l_loff_t *offset, l_size_t count)
{
	off_t bytes_read;
	int error;
	l_loff_t current_offset;
	struct file *fp;

	AUDIT_ARG_FD(in);
	error = fget_read(td, in, &cap_pread_rights, &fp);
	if (error != 0)
		return (error);

	if (offset != NULL) {
		current_offset = *offset;
	} else {
		error = (fp->f_ops->fo_flags & DFLAG_SEEKABLE) != 0 ?
		    fo_seek(fp, 0, SEEK_CUR, td) : ESPIPE;
		if (error != 0)
			goto drop;
		current_offset = td->td_uretoff.tdu_off;
	}

	bytes_read = 0;

	/* Linux cannot have 0 count. */
	if (count <= 0 || current_offset < 0) {
		error = EINVAL;
		goto drop;
	}

	error = fo_sendfile(fp, out, NULL, NULL, current_offset, count,
	    &bytes_read, 0, td);
	if (error != 0)
		goto drop;
	current_offset += bytes_read;

	if (offset != NULL) {
		*offset = current_offset;
	} else {
		error = fo_seek(fp, current_offset, SEEK_SET, td);
		if (error != 0)
			goto drop;
	}

	td->td_retval[0] = (ssize_t)bytes_read;
drop:
	fdrop(fp, td);
	return (error);
}

int
linux_sendfile(struct thread *td, struct linux_sendfile_args *arg)
{
	/*
	 * Differences between FreeBSD and Linux sendfile:
	 * - Linux doesn't send anything when count is 0 (FreeBSD uses 0 to
	 *   mean send the whole file.)  In linux_sendfile given fds are still
	 *   checked for validity when the count is 0.
	 * - Linux can send to any fd whereas FreeBSD only supports sockets.
	 *   The same restriction follows for linux_sendfile.
	 * - Linux doesn't have an equivalent for FreeBSD's flags and sf_hdtr.
	 * - Linux takes an offset pointer and updates it to the read location.
	 *   FreeBSD takes in an offset and a 'bytes read' parameter which is
	 *   only filled if it isn't NULL.  We use this parameter to update the
	 *   offset pointer if it exists.
	 * - Linux sendfile returns bytes read on success while FreeBSD
	 *   returns 0.  We use the 'bytes read' parameter to get this value.
	 */

	l_loff_t offset64;
	l_long offset;
	int ret;
	int error;

	if (arg->offset != NULL) {
		error = copyin(arg->offset, &offset, sizeof(offset));
		if (error != 0)
			return (error);
		offset64 = (l_loff_t)offset;
	}

	ret = linux_sendfile_common(td, arg->out, arg->in,
	    arg->offset != NULL ? &offset64 : NULL, arg->count);

	if (arg->offset != NULL) {
#if defined(__i386__) || defined(__arm__) || \
    (defined(__amd64__) && defined(COMPAT_LINUX32))
		if (offset64 > INT32_MAX)
			return (EOVERFLOW);
#endif
		offset = (l_long)offset64;
		error = copyout(&offset, arg->offset, sizeof(offset));
		if (error != 0)
			return (error);
	}

	return (ret);
}

#if defined(__i386__) || defined(__arm__) || \
    (defined(__amd64__) && defined(COMPAT_LINUX32))

int
linux_sendfile64(struct thread *td, struct linux_sendfile64_args *arg)
{
	l_loff_t offset;
	int ret;
	int error;

	if (arg->offset != NULL) {
		error = copyin(arg->offset, &offset, sizeof(offset));
		if (error != 0)
			return (error);
	}

	ret = linux_sendfile_common(td, arg->out, arg->in,
		arg->offset != NULL ? &offset : NULL, arg->count);

	if (arg->offset != NULL) {
		error = copyout(&offset, arg->offset, sizeof(offset));
		if (error != 0)
			return (error);
	}

	return (ret);
}

/* Argument list sizes for linux_socketcall */
static const unsigned char lxs_args_cnt[] = {
	0 /* unused*/,		3 /* socket */,
	3 /* bind */,		3 /* connect */,
	2 /* listen */,		3 /* accept */,
	3 /* getsockname */,	3 /* getpeername */,
	4 /* socketpair */,	4 /* send */,
	4 /* recv */,		6 /* sendto */,
	6 /* recvfrom */,	2 /* shutdown */,
	5 /* setsockopt */,	5 /* getsockopt */,
	3 /* sendmsg */,	3 /* recvmsg */,
	4 /* accept4 */,	5 /* recvmmsg */,
	4 /* sendmmsg */,	4 /* sendfile */
};
#define	LINUX_ARGS_CNT		(nitems(lxs_args_cnt) - 1)
#define	LINUX_ARG_SIZE(x)	(lxs_args_cnt[x] * sizeof(l_ulong))

int
linux_socketcall(struct thread *td, struct linux_socketcall_args *args)
{
	l_ulong a[6];
#if defined(__amd64__) && defined(COMPAT_LINUX32)
	register_t l_args[6];
#endif
	void *arg;
	int error;

	if (args->what < LINUX_SOCKET || args->what > LINUX_ARGS_CNT)
		return (EINVAL);
	error = copyin(PTRIN(args->args), a, LINUX_ARG_SIZE(args->what));
	if (error != 0)
		return (error);

#if defined(__amd64__) && defined(COMPAT_LINUX32)
	for (int i = 0; i < lxs_args_cnt[args->what]; ++i)
		l_args[i] = a[i];
	arg = l_args;
#else
	arg = a;
#endif
	switch (args->what) {
	case LINUX_SOCKET:
		return (linux_socket(td, arg));
	case LINUX_BIND:
		return (linux_bind(td, arg));
	case LINUX_CONNECT:
		return (linux_connect(td, arg));
	case LINUX_LISTEN:
		return (linux_listen(td, arg));
	case LINUX_ACCEPT:
		return (linux_accept(td, arg));
	case LINUX_GETSOCKNAME:
		return (linux_getsockname(td, arg));
	case LINUX_GETPEERNAME:
		return (linux_getpeername(td, arg));
	case LINUX_SOCKETPAIR:
		return (linux_socketpair(td, arg));
	case LINUX_SEND:
		return (linux_send(td, arg));
	case LINUX_RECV:
		return (linux_recv(td, arg));
	case LINUX_SENDTO:
		return (linux_sendto(td, arg));
	case LINUX_RECVFROM:
		return (linux_recvfrom(td, arg));
	case LINUX_SHUTDOWN:
		return (linux_shutdown(td, arg));
	case LINUX_SETSOCKOPT:
		return (linux_setsockopt(td, arg));
	case LINUX_GETSOCKOPT:
		return (linux_getsockopt(td, arg));
	case LINUX_SENDMSG:
		return (linux_sendmsg(td, arg));
	case LINUX_RECVMSG:
		return (linux_recvmsg(td, arg));
	case LINUX_ACCEPT4:
		return (linux_accept4(td, arg));
	case LINUX_RECVMMSG:
		return (linux_recvmmsg(td, arg));
	case LINUX_SENDMMSG:
		return (linux_sendmmsg(td, arg));
	case LINUX_SENDFILE:
		return (linux_sendfile(td, arg));
	}

	linux_msg(td, "socket type %d not implemented", args->what);
	return (ENOSYS);
}
#endif /* __i386__ || __arm__ || (__amd64__ && COMPAT_LINUX32) */