summaryrefslogtreecommitdiffstats
path: root/sys/kern/vfs_mount.c
blob: 7dd1c72820b326dd08fda916969154dbcdc424b0 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
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
/*-
 * Copyright (c) 1999-2004 Poul-Henning Kamp
 * Copyright (c) 1999 Michael Smith
 * Copyright (c) 1989, 1993
 *	The Regents of the University of California.  All rights reserved.
 * (c) UNIX System Laboratories, Inc.
 * All or some portions of this file are derived from material licensed
 * to the University of California by American Telephone and Telegraph
 * Co. or Unix System Laboratories, Inc. and are reproduced herein with
 * the permission of UNIX System Laboratories, Inc.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 4. Neither the name of the University nor the names of its contributors
 *    may be used to endorse or promote products derived from this software
 *    without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE 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("$FreeBSD$");

#include <sys/param.h>
#include <sys/conf.h>
#include <sys/fcntl.h>
#include <sys/jail.h>
#include <sys/kernel.h>
#include <sys/libkern.h>
#include <sys/malloc.h>
#include <sys/mount.h>
#include <sys/mutex.h>
#include <sys/namei.h>
#include <sys/priv.h>
#include <sys/proc.h>
#include <sys/filedesc.h>
#include <sys/reboot.h>
#include <sys/sbuf.h>
#include <sys/syscallsubr.h>
#include <sys/sysproto.h>
#include <sys/sx.h>
#include <sys/sysctl.h>
#include <sys/sysent.h>
#include <sys/systm.h>
#include <sys/vnode.h>
#include <vm/uma.h>

#include <geom/geom.h>

#include <machine/stdarg.h>

#include <security/audit/audit.h>
#include <security/mac/mac_framework.h>

#define	VFS_MOUNTARG_SIZE_MAX	(1024 * 64)

static int	vfs_domount(struct thread *td, const char *fstype, char *fspath,
		    uint64_t fsflags, struct vfsoptlist **optlist);
static void	free_mntarg(struct mntarg *ma);

static int	usermount = 0;
SYSCTL_INT(_vfs, OID_AUTO, usermount, CTLFLAG_RW, &usermount, 0,
    "Unprivileged users may mount and unmount file systems");

MALLOC_DEFINE(M_MOUNT, "mount", "vfs mount structure");
static uma_zone_t mount_zone;

/* List of mounted filesystems. */
struct mntlist mountlist = TAILQ_HEAD_INITIALIZER(mountlist);

/* For any iteration/modification of mountlist */
struct mtx mountlist_mtx;
MTX_SYSINIT(mountlist, &mountlist_mtx, "mountlist", MTX_DEF);

/*
 * Global opts, taken by all filesystems
 */
static const char *global_opts[] = {
	"errmsg",
	"fstype",
	"fspath",
	"ro",
	"rw",
	"nosuid",
	"noexec",
	NULL
};

static int
mount_init(void *mem, int size, int flags)
{
	struct mount *mp;

	mp = (struct mount *)mem;
	mtx_init(&mp->mnt_mtx, "struct mount mtx", NULL, MTX_DEF);
	lockinit(&mp->mnt_explock, PVFS, "explock", 0, 0);
	return (0);
}

static void
mount_fini(void *mem, int size)
{
	struct mount *mp;

	mp = (struct mount *)mem;
	lockdestroy(&mp->mnt_explock);
	mtx_destroy(&mp->mnt_mtx);
}

static void
vfs_mount_init(void *dummy __unused)
{

	mount_zone = uma_zcreate("Mountpoints", sizeof(struct mount), NULL,
	    NULL, mount_init, mount_fini, UMA_ALIGN_PTR, UMA_ZONE_NOFREE);
}
SYSINIT(vfs_mount, SI_SUB_VFS, SI_ORDER_ANY, vfs_mount_init, NULL);

/*
 * ---------------------------------------------------------------------
 * Functions for building and sanitizing the mount options
 */

/* Remove one mount option. */
static void
vfs_freeopt(struct vfsoptlist *opts, struct vfsopt *opt)
{

	TAILQ_REMOVE(opts, opt, link);
	free(opt->name, M_MOUNT);
	if (opt->value != NULL)
		free(opt->value, M_MOUNT);
	free(opt, M_MOUNT);
}

/* Release all resources related to the mount options. */
void
vfs_freeopts(struct vfsoptlist *opts)
{
	struct vfsopt *opt;

	while (!TAILQ_EMPTY(opts)) {
		opt = TAILQ_FIRST(opts);
		vfs_freeopt(opts, opt);
	}
	free(opts, M_MOUNT);
}

void
vfs_deleteopt(struct vfsoptlist *opts, const char *name)
{
	struct vfsopt *opt, *temp;

	if (opts == NULL)
		return;
	TAILQ_FOREACH_SAFE(opt, opts, link, temp)  {
		if (strcmp(opt->name, name) == 0)
			vfs_freeopt(opts, opt);
	}
}

static int
vfs_isopt_ro(const char *opt)
{

	if (strcmp(opt, "ro") == 0 || strcmp(opt, "rdonly") == 0 ||
	    strcmp(opt, "norw") == 0)
		return (1);
	return (0);
}

static int
vfs_isopt_rw(const char *opt)
{

	if (strcmp(opt, "rw") == 0 || strcmp(opt, "noro") == 0)
		return (1);
	return (0);
}

/*
 * Check if options are equal (with or without the "no" prefix).
 */
static int
vfs_equalopts(const char *opt1, const char *opt2)
{
	char *p;

	/* "opt" vs. "opt" or "noopt" vs. "noopt" */
	if (strcmp(opt1, opt2) == 0)
		return (1);
	/* "noopt" vs. "opt" */
	if (strncmp(opt1, "no", 2) == 0 && strcmp(opt1 + 2, opt2) == 0)
		return (1);
	/* "opt" vs. "noopt" */
	if (strncmp(opt2, "no", 2) == 0 && strcmp(opt1, opt2 + 2) == 0)
		return (1);
	while ((p = strchr(opt1, '.')) != NULL &&
	    !strncmp(opt1, opt2, ++p - opt1)) {
		opt2 += p - opt1;
		opt1 = p;
		/* "foo.noopt" vs. "foo.opt" */
		if (strncmp(opt1, "no", 2) == 0 && strcmp(opt1 + 2, opt2) == 0)
			return (1);
		/* "foo.opt" vs. "foo.noopt" */
		if (strncmp(opt2, "no", 2) == 0 && strcmp(opt1, opt2 + 2) == 0)
			return (1);
	}
	/* "ro" / "rdonly" / "norw" / "rw" / "noro" */
	if ((vfs_isopt_ro(opt1) || vfs_isopt_rw(opt1)) &&
	    (vfs_isopt_ro(opt2) || vfs_isopt_rw(opt2)))
		return (1);
	return (0);
}

/*
 * If a mount option is specified several times,
 * (with or without the "no" prefix) only keep
 * the last occurrence of it.
 */
static void
vfs_sanitizeopts(struct vfsoptlist *opts)
{
	struct vfsopt *opt, *opt2, *tmp;

	TAILQ_FOREACH_REVERSE(opt, opts, vfsoptlist, link) {
		opt2 = TAILQ_PREV(opt, vfsoptlist, link);
		while (opt2 != NULL) {
			if (vfs_equalopts(opt->name, opt2->name)) {
				tmp = TAILQ_PREV(opt2, vfsoptlist, link);
				vfs_freeopt(opts, opt2);
				opt2 = tmp;
			} else {
				opt2 = TAILQ_PREV(opt2, vfsoptlist, link);
			}
		}
	}
}

/*
 * Build a linked list of mount options from a struct uio.
 */
int
vfs_buildopts(struct uio *auio, struct vfsoptlist **options)
{
	struct vfsoptlist *opts;
	struct vfsopt *opt;
	size_t memused, namelen, optlen;
	unsigned int i, iovcnt;
	int error;

	opts = malloc(sizeof(struct vfsoptlist), M_MOUNT, M_WAITOK);
	TAILQ_INIT(opts);
	memused = 0;
	iovcnt = auio->uio_iovcnt;
	for (i = 0; i < iovcnt; i += 2) {
		namelen = auio->uio_iov[i].iov_len;
		optlen = auio->uio_iov[i + 1].iov_len;
		memused += sizeof(struct vfsopt) + optlen + namelen;
		/*
		 * Avoid consuming too much memory, and attempts to overflow
		 * memused.
		 */
		if (memused > VFS_MOUNTARG_SIZE_MAX ||
		    optlen > VFS_MOUNTARG_SIZE_MAX ||
		    namelen > VFS_MOUNTARG_SIZE_MAX) {
			error = EINVAL;
			goto bad;
		}

		opt = malloc(sizeof(struct vfsopt), M_MOUNT, M_WAITOK);
		opt->name = malloc(namelen, M_MOUNT, M_WAITOK);
		opt->value = NULL;
		opt->len = 0;
		opt->pos = i / 2;
		opt->seen = 0;

		/*
		 * Do this early, so jumps to "bad" will free the current
		 * option.
		 */
		TAILQ_INSERT_TAIL(opts, opt, link);

		if (auio->uio_segflg == UIO_SYSSPACE) {
			bcopy(auio->uio_iov[i].iov_base, opt->name, namelen);
		} else {
			error = copyin(auio->uio_iov[i].iov_base, opt->name,
			    namelen);
			if (error)
				goto bad;
		}
		/* Ensure names are null-terminated strings. */
		if (namelen == 0 || opt->name[namelen - 1] != '\0') {
			error = EINVAL;
			goto bad;
		}
		if (optlen != 0) {
			opt->len = optlen;
			opt->value = malloc(optlen, M_MOUNT, M_WAITOK);
			if (auio->uio_segflg == UIO_SYSSPACE) {
				bcopy(auio->uio_iov[i + 1].iov_base, opt->value,
				    optlen);
			} else {
				error = copyin(auio->uio_iov[i + 1].iov_base,
				    opt->value, optlen);
				if (error)
					goto bad;
			}
		}
	}
	vfs_sanitizeopts(opts);
	*options = opts;
	return (0);
bad:
	vfs_freeopts(opts);
	return (error);
}

/*
 * Merge the old mount options with the new ones passed
 * in the MNT_UPDATE case.
 *
 * XXX: This function will keep a "nofoo" option in the new
 * options.  E.g, if the option's canonical name is "foo",
 * "nofoo" ends up in the mount point's active options.
 */
static void
vfs_mergeopts(struct vfsoptlist *toopts, struct vfsoptlist *oldopts)
{
	struct vfsopt *opt, *new;

	TAILQ_FOREACH(opt, oldopts, link) {
		new = malloc(sizeof(struct vfsopt), M_MOUNT, M_WAITOK);
		new->name = strdup(opt->name, M_MOUNT);
		if (opt->len != 0) {
			new->value = malloc(opt->len, M_MOUNT, M_WAITOK);
			bcopy(opt->value, new->value, opt->len);
		} else
			new->value = NULL;
		new->len = opt->len;
		new->seen = opt->seen;
		TAILQ_INSERT_HEAD(toopts, new, link);
	}
	vfs_sanitizeopts(toopts);
}

/*
 * Mount a filesystem.
 */
int
sys_nmount(td, uap)
	struct thread *td;
	struct nmount_args /* {
		struct iovec *iovp;
		unsigned int iovcnt;
		int flags;
	} */ *uap;
{
	struct uio *auio;
	int error;
	u_int iovcnt;
	uint64_t flags;

	/*
	 * Mount flags are now 64-bits. On 32-bit archtectures only
	 * 32-bits are passed in, but from here on everything handles
	 * 64-bit flags correctly.
	 */
	flags = uap->flags;

	AUDIT_ARG_FFLAGS(flags);
	CTR4(KTR_VFS, "%s: iovp %p with iovcnt %d and flags %d", __func__,
	    uap->iovp, uap->iovcnt, flags);

	/*
	 * Filter out MNT_ROOTFS.  We do not want clients of nmount() in
	 * userspace to set this flag, but we must filter it out if we want
	 * MNT_UPDATE on the root file system to work.
	 * MNT_ROOTFS should only be set by the kernel when mounting its
	 * root file system.
	 */
	flags &= ~MNT_ROOTFS;

	iovcnt = uap->iovcnt;
	/*
	 * Check that we have an even number of iovec's
	 * and that we have at least two options.
	 */
	if ((iovcnt & 1) || (iovcnt < 4)) {
		CTR2(KTR_VFS, "%s: failed for invalid iovcnt %d", __func__,
		    uap->iovcnt);
		return (EINVAL);
	}

	error = copyinuio(uap->iovp, iovcnt, &auio);
	if (error) {
		CTR2(KTR_VFS, "%s: failed for invalid uio op with %d errno",
		    __func__, error);
		return (error);
	}
	error = vfs_donmount(td, flags, auio);

	free(auio, M_IOV);
	return (error);
}

/*
 * ---------------------------------------------------------------------
 * Various utility functions
 */

void
vfs_ref(struct mount *mp)
{

	CTR2(KTR_VFS, "%s: mp %p", __func__, mp);
	MNT_ILOCK(mp);
	MNT_REF(mp);
	MNT_IUNLOCK(mp);
}

void
vfs_rel(struct mount *mp)
{

	CTR2(KTR_VFS, "%s: mp %p", __func__, mp);
	MNT_ILOCK(mp);
	MNT_REL(mp);
	MNT_IUNLOCK(mp);
}

/*
 * Allocate and initialize the mount point struct.
 */
struct mount *
vfs_mount_alloc(struct vnode *vp, struct vfsconf *vfsp, const char *fspath,
    struct ucred *cred)
{
	struct mount *mp;

	mp = uma_zalloc(mount_zone, M_WAITOK);
	bzero(&mp->mnt_startzero,
	    __rangeof(struct mount, mnt_startzero, mnt_endzero));
	TAILQ_INIT(&mp->mnt_nvnodelist);
	mp->mnt_nvnodelistsize = 0;
	TAILQ_INIT(&mp->mnt_activevnodelist);
	mp->mnt_activevnodelistsize = 0;
	mp->mnt_ref = 0;
	(void) vfs_busy(mp, MBF_NOWAIT);
	mp->mnt_op = vfsp->vfc_vfsops;
	mp->mnt_vfc = vfsp;
	vfsp->vfc_refcount++;	/* XXX Unlocked */
	mp->mnt_stat.f_type = vfsp->vfc_typenum;
	mp->mnt_gen++;
	strlcpy(mp->mnt_stat.f_fstypename, vfsp->vfc_name, MFSNAMELEN);
	mp->mnt_vnodecovered = vp;
	mp->mnt_cred = crdup(cred);
	mp->mnt_stat.f_owner = cred->cr_uid;
	strlcpy(mp->mnt_stat.f_mntonname, fspath, MNAMELEN);
	mp->mnt_iosize_max = DFLTPHYS;
#ifdef MAC
	mac_mount_init(mp);
	mac_mount_create(cred, mp);
#endif
	arc4rand(&mp->mnt_hashseed, sizeof mp->mnt_hashseed, 0);
	TAILQ_INIT(&mp->mnt_uppers);
	return (mp);
}

/*
 * Destroy the mount struct previously allocated by vfs_mount_alloc().
 */
void
vfs_mount_destroy(struct mount *mp)
{

	MNT_ILOCK(mp);
	mp->mnt_kern_flag |= MNTK_REFEXPIRE;
	if (mp->mnt_kern_flag & MNTK_MWAIT) {
		mp->mnt_kern_flag &= ~MNTK_MWAIT;
		wakeup(mp);
	}
	while (mp->mnt_ref)
		msleep(mp, MNT_MTX(mp), PVFS, "mntref", 0);
	KASSERT(mp->mnt_ref == 0,
	    ("%s: invalid refcount in the drain path @ %s:%d", __func__,
	    __FILE__, __LINE__));
	if (mp->mnt_writeopcount != 0)
		panic("vfs_mount_destroy: nonzero writeopcount");
	if (mp->mnt_secondary_writes != 0)
		panic("vfs_mount_destroy: nonzero secondary_writes");
	mp->mnt_vfc->vfc_refcount--;
	if (!TAILQ_EMPTY(&mp->mnt_nvnodelist)) {
		struct vnode *vp;

		TAILQ_FOREACH(vp, &mp->mnt_nvnodelist, v_nmntvnodes)
			vprint("", vp);
		panic("unmount: dangling vnode");
	}
	KASSERT(TAILQ_EMPTY(&mp->mnt_uppers), ("mnt_uppers"));
	if (mp->mnt_nvnodelistsize != 0)
		panic("vfs_mount_destroy: nonzero nvnodelistsize");
	if (mp->mnt_activevnodelistsize != 0)
		panic("vfs_mount_destroy: nonzero activevnodelistsize");
	if (mp->mnt_lockref != 0)
		panic("vfs_mount_destroy: nonzero lock refcount");
	MNT_IUNLOCK(mp);
#ifdef MAC
	mac_mount_destroy(mp);
#endif
	if (mp->mnt_opt != NULL)
		vfs_freeopts(mp->mnt_opt);
	crfree(mp->mnt_cred);
	uma_zfree(mount_zone, mp);
}

int
vfs_donmount(struct thread *td, uint64_t fsflags, struct uio *fsoptions)
{
	struct vfsoptlist *optlist;
	struct vfsopt *opt, *tmp_opt;
	char *fstype, *fspath, *errmsg;
	int error, fstypelen, fspathlen, errmsg_len, errmsg_pos;

	errmsg = fspath = NULL;
	errmsg_len = fspathlen = 0;
	errmsg_pos = -1;

	error = vfs_buildopts(fsoptions, &optlist);
	if (error)
		return (error);

	if (vfs_getopt(optlist, "errmsg", (void **)&errmsg, &errmsg_len) == 0)
		errmsg_pos = vfs_getopt_pos(optlist, "errmsg");

	/*
	 * We need these two options before the others,
	 * and they are mandatory for any filesystem.
	 * Ensure they are NUL terminated as well.
	 */
	fstypelen = 0;
	error = vfs_getopt(optlist, "fstype", (void **)&fstype, &fstypelen);
	if (error || fstype[fstypelen - 1] != '\0') {
		error = EINVAL;
		if (errmsg != NULL)
			strncpy(errmsg, "Invalid fstype", errmsg_len);
		goto bail;
	}
	fspathlen = 0;
	error = vfs_getopt(optlist, "fspath", (void **)&fspath, &fspathlen);
	if (error || fspath[fspathlen - 1] != '\0') {
		error = EINVAL;
		if (errmsg != NULL)
			strncpy(errmsg, "Invalid fspath", errmsg_len);
		goto bail;
	}

	/*
	 * We need to see if we have the "update" option
	 * before we call vfs_domount(), since vfs_domount() has special
	 * logic based on MNT_UPDATE.  This is very important
	 * when we want to update the root filesystem.
	 */
	TAILQ_FOREACH_SAFE(opt, optlist, link, tmp_opt) {
		if (strcmp(opt->name, "update") == 0) {
			fsflags |= MNT_UPDATE;
			vfs_freeopt(optlist, opt);
		}
		else if (strcmp(opt->name, "async") == 0)
			fsflags |= MNT_ASYNC;
		else if (strcmp(opt->name, "force") == 0) {
			fsflags |= MNT_FORCE;
			vfs_freeopt(optlist, opt);
		}
		else if (strcmp(opt->name, "reload") == 0) {
			fsflags |= MNT_RELOAD;
			vfs_freeopt(optlist, opt);
		}
		else if (strcmp(opt->name, "multilabel") == 0)
			fsflags |= MNT_MULTILABEL;
		else if (strcmp(opt->name, "noasync") == 0)
			fsflags &= ~MNT_ASYNC;
		else if (strcmp(opt->name, "noatime") == 0)
			fsflags |= MNT_NOATIME;
		else if (strcmp(opt->name, "atime") == 0) {
			free(opt->name, M_MOUNT);
			opt->name = strdup("nonoatime", M_MOUNT);
		}
		else if (strcmp(opt->name, "noclusterr") == 0)
			fsflags |= MNT_NOCLUSTERR;
		else if (strcmp(opt->name, "clusterr") == 0) {
			free(opt->name, M_MOUNT);
			opt->name = strdup("nonoclusterr", M_MOUNT);
		}
		else if (strcmp(opt->name, "noclusterw") == 0)
			fsflags |= MNT_NOCLUSTERW;
		else if (strcmp(opt->name, "clusterw") == 0) {
			free(opt->name, M_MOUNT);
			opt->name = strdup("nonoclusterw", M_MOUNT);
		}
		else if (strcmp(opt->name, "noexec") == 0)
			fsflags |= MNT_NOEXEC;
		else if (strcmp(opt->name, "exec") == 0) {
			free(opt->name, M_MOUNT);
			opt->name = strdup("nonoexec", M_MOUNT);
		}
		else if (strcmp(opt->name, "nosuid") == 0)
			fsflags |= MNT_NOSUID;
		else if (strcmp(opt->name, "suid") == 0) {
			free(opt->name, M_MOUNT);
			opt->name = strdup("nonosuid", M_MOUNT);
		}
		else if (strcmp(opt->name, "nosymfollow") == 0)
			fsflags |= MNT_NOSYMFOLLOW;
		else if (strcmp(opt->name, "symfollow") == 0) {
			free(opt->name, M_MOUNT);
			opt->name = strdup("nonosymfollow", M_MOUNT);
		}
		else if (strcmp(opt->name, "noro") == 0)
			fsflags &= ~MNT_RDONLY;
		else if (strcmp(opt->name, "rw") == 0)
			fsflags &= ~MNT_RDONLY;
		else if (strcmp(opt->name, "ro") == 0)
			fsflags |= MNT_RDONLY;
		else if (strcmp(opt->name, "rdonly") == 0) {
			free(opt->name, M_MOUNT);
			opt->name = strdup("ro", M_MOUNT);
			fsflags |= MNT_RDONLY;
		}
		else if (strcmp(opt->name, "suiddir") == 0)
			fsflags |= MNT_SUIDDIR;
		else if (strcmp(opt->name, "sync") == 0)
			fsflags |= MNT_SYNCHRONOUS;
		else if (strcmp(opt->name, "union") == 0)
			fsflags |= MNT_UNION;
	}

	/*
	 * Be ultra-paranoid about making sure the type and fspath
	 * variables will fit in our mp buffers, including the
	 * terminating NUL.
	 */
	if (fstypelen > MFSNAMELEN || fspathlen > MNAMELEN) {
		error = ENAMETOOLONG;
		goto bail;
	}

	error = vfs_domount(td, fstype, fspath, fsflags, &optlist);
bail:
	/* copyout the errmsg */
	if (errmsg_pos != -1 && ((2 * errmsg_pos + 1) < fsoptions->uio_iovcnt)
	    && errmsg_len > 0 && errmsg != NULL) {
		if (fsoptions->uio_segflg == UIO_SYSSPACE) {
			bcopy(errmsg,
			    fsoptions->uio_iov[2 * errmsg_pos + 1].iov_base,
			    fsoptions->uio_iov[2 * errmsg_pos + 1].iov_len);
		} else {
			copyout(errmsg,
			    fsoptions->uio_iov[2 * errmsg_pos + 1].iov_base,
			    fsoptions->uio_iov[2 * errmsg_pos + 1].iov_len);
		}
	}

	if (optlist != NULL)
		vfs_freeopts(optlist);
	return (error);
}

/*
 * Old mount API.
 */
#ifndef _SYS_SYSPROTO_H_
struct mount_args {
	char	*type;
	char	*path;
	int	flags;
	caddr_t	data;
};
#endif
/* ARGSUSED */
int
sys_mount(td, uap)
	struct thread *td;
	struct mount_args /* {
		char *type;
		char *path;
		int flags;
		caddr_t data;
	} */ *uap;
{
	char *fstype;
	struct vfsconf *vfsp = NULL;
	struct mntarg *ma = NULL;
	uint64_t flags;
	int error;

	/*
	 * Mount flags are now 64-bits. On 32-bit architectures only
	 * 32-bits are passed in, but from here on everything handles
	 * 64-bit flags correctly.
	 */
	flags = uap->flags;

	AUDIT_ARG_FFLAGS(flags);

	/*
	 * Filter out MNT_ROOTFS.  We do not want clients of mount() in
	 * userspace to set this flag, but we must filter it out if we want
	 * MNT_UPDATE on the root file system to work.
	 * MNT_ROOTFS should only be set by the kernel when mounting its
	 * root file system.
	 */
	flags &= ~MNT_ROOTFS;

	fstype = malloc(MFSNAMELEN, M_TEMP, M_WAITOK);
	error = copyinstr(uap->type, fstype, MFSNAMELEN, NULL);
	if (error) {
		free(fstype, M_TEMP);
		return (error);
	}

	AUDIT_ARG_TEXT(fstype);
	mtx_lock(&Giant);
	vfsp = vfs_byname_kld(fstype, td, &error);
	free(fstype, M_TEMP);
	if (vfsp == NULL) {
		mtx_unlock(&Giant);
		return (ENOENT);
	}
	if (vfsp->vfc_vfsops->vfs_cmount == NULL) {
		mtx_unlock(&Giant);
		return (EOPNOTSUPP);
	}

	ma = mount_argsu(ma, "fstype", uap->type, MNAMELEN);
	ma = mount_argsu(ma, "fspath", uap->path, MNAMELEN);
	ma = mount_argb(ma, flags & MNT_RDONLY, "noro");
	ma = mount_argb(ma, !(flags & MNT_NOSUID), "nosuid");
	ma = mount_argb(ma, !(flags & MNT_NOEXEC), "noexec");

	error = vfsp->vfc_vfsops->vfs_cmount(ma, uap->data, flags);
	mtx_unlock(&Giant);
	return (error);
}

/*
 * vfs_domount_first(): first file system mount (not update)
 */
static int
vfs_domount_first(
	struct thread *td,		/* Calling thread. */
	struct vfsconf *vfsp,		/* File system type. */
	char *fspath,			/* Mount path. */
	struct vnode *vp,		/* Vnode to be covered. */
	uint64_t fsflags,		/* Flags common to all filesystems. */
	struct vfsoptlist **optlist	/* Options local to the filesystem. */
	)
{
	struct vattr va;
	struct mount *mp;
	struct vnode *newdp;
	int error;

	mtx_assert(&Giant, MA_OWNED);
	ASSERT_VOP_ELOCKED(vp, __func__);
	KASSERT((fsflags & MNT_UPDATE) == 0, ("MNT_UPDATE shouldn't be here"));

	/*
	 * If the user is not root, ensure that they own the directory
	 * onto which we are attempting to mount.
	 */
	error = VOP_GETATTR(vp, &va, td->td_ucred);
	if (error == 0 && va.va_uid != td->td_ucred->cr_uid)
		error = priv_check_cred(td->td_ucred, PRIV_VFS_ADMIN, 0);
	if (error == 0)
		error = vinvalbuf(vp, V_SAVE, 0, 0);
	if (error == 0 && vp->v_type != VDIR)
		error = ENOTDIR;
	if (error == 0) {
		VI_LOCK(vp);
		if ((vp->v_iflag & VI_MOUNT) == 0 && vp->v_mountedhere == NULL)
			vp->v_iflag |= VI_MOUNT;
		else
			error = EBUSY;
		VI_UNLOCK(vp);
	}
	if (error != 0) {
		vput(vp);
		return (error);
	}
	VOP_UNLOCK(vp, 0);

	/* Allocate and initialize the filesystem. */
	mp = vfs_mount_alloc(vp, vfsp, fspath, td->td_ucred);
	/* XXXMAC: pass to vfs_mount_alloc? */
	mp->mnt_optnew = *optlist;
	/* Set the mount level flags. */
	mp->mnt_flag = (fsflags & (MNT_UPDATEMASK | MNT_ROOTFS | MNT_RDONLY));

	/*
	 * Mount the filesystem.
	 * XXX The final recipients of VFS_MOUNT just overwrite the ndp they
	 * get.  No freeing of cn_pnbuf.
	 */
	error = VFS_MOUNT(mp);
	if (error != 0) {
		vfs_unbusy(mp);
		vfs_mount_destroy(mp);
		VI_LOCK(vp);
		vp->v_iflag &= ~VI_MOUNT;
		VI_UNLOCK(vp);
		vrele(vp);
		return (error);
	}

	if (mp->mnt_opt != NULL)
		vfs_freeopts(mp->mnt_opt);
	mp->mnt_opt = mp->mnt_optnew;
	*optlist = NULL;
	(void)VFS_STATFS(mp, &mp->mnt_stat);

	/*
	 * Prevent external consumers of mount options from reading mnt_optnew.
	 */
	mp->mnt_optnew = NULL;

	MNT_ILOCK(mp);
	if ((mp->mnt_flag & MNT_ASYNC) != 0 &&
	    (mp->mnt_kern_flag & MNTK_NOASYNC) == 0)
		mp->mnt_kern_flag |= MNTK_ASYNC;
	else
		mp->mnt_kern_flag &= ~MNTK_ASYNC;
	MNT_IUNLOCK(mp);

	vn_lock(vp, LK_EXCLUSIVE | LK_RETRY);
	cache_purge(vp);
	VI_LOCK(vp);
	vp->v_iflag &= ~VI_MOUNT;
	VI_UNLOCK(vp);
	vp->v_mountedhere = mp;
	/* Place the new filesystem at the end of the mount list. */
	mtx_lock(&mountlist_mtx);
	TAILQ_INSERT_TAIL(&mountlist, mp, mnt_list);
	mtx_unlock(&mountlist_mtx);
	vfs_event_signal(NULL, VQ_MOUNT, 0);
	if (VFS_ROOT(mp, LK_EXCLUSIVE, &newdp))
		panic("mount: lost mount");
	VOP_UNLOCK(vp, 0);
	EVENTHANDLER_INVOKE(vfs_mounted, mp, newdp, td);
	VOP_UNLOCK(newdp, 0);
	mountcheckdirs(vp, newdp);
	vrele(newdp);
	if ((mp->mnt_flag & MNT_RDONLY) == 0)
		vfs_allocate_syncvnode(mp);
	vfs_unbusy(mp);
	return (0);
}

/*
 * vfs_domount_update(): update of mounted file system
 */
static int
vfs_domount_update(
	struct thread *td,		/* Calling thread. */
	struct vnode *vp,		/* Mount point vnode. */
	uint64_t fsflags,		/* Flags common to all filesystems. */
	struct vfsoptlist **optlist	/* Options local to the filesystem. */
	)
{
	struct oexport_args oexport;
	struct export_args export;
	struct mount *mp;
	int error, export_error;
	uint64_t flag;

	mtx_assert(&Giant, MA_OWNED);
	ASSERT_VOP_ELOCKED(vp, __func__);
	KASSERT((fsflags & MNT_UPDATE) != 0, ("MNT_UPDATE should be here"));

	if ((vp->v_vflag & VV_ROOT) == 0) {
		vput(vp);
		return (EINVAL);
	}
	mp = vp->v_mount;
	/*
	 * We only allow the filesystem to be reloaded if it
	 * is currently mounted read-only.
	 */
	flag = mp->mnt_flag;
	if ((fsflags & MNT_RELOAD) != 0 && (flag & MNT_RDONLY) == 0) {
		vput(vp);
		return (EOPNOTSUPP);	/* Needs translation */
	}
	/*
	 * Only privileged root, or (if MNT_USER is set) the user that
	 * did the original mount is permitted to update it.
	 */
	error = vfs_suser(mp, td);
	if (error != 0) {
		vput(vp);
		return (error);
	}
	if (vfs_busy(mp, MBF_NOWAIT)) {
		vput(vp);
		return (EBUSY);
	}
	VI_LOCK(vp);
	if ((vp->v_iflag & VI_MOUNT) != 0 || vp->v_mountedhere != NULL) {
		VI_UNLOCK(vp);
		vfs_unbusy(mp);
		vput(vp);
		return (EBUSY);
	}
	vp->v_iflag |= VI_MOUNT;
	VI_UNLOCK(vp);
	VOP_UNLOCK(vp, 0);

	MNT_ILOCK(mp);
	mp->mnt_flag &= ~MNT_UPDATEMASK;
	mp->mnt_flag |= fsflags & (MNT_RELOAD | MNT_FORCE | MNT_UPDATE |
	    MNT_SNAPSHOT | MNT_ROOTFS | MNT_UPDATEMASK | MNT_RDONLY);
	if ((mp->mnt_flag & MNT_ASYNC) == 0)
		mp->mnt_kern_flag &= ~MNTK_ASYNC;
	MNT_IUNLOCK(mp);
	mp->mnt_optnew = *optlist;
	vfs_mergeopts(mp->mnt_optnew, mp->mnt_opt);

	/*
	 * Mount the filesystem.
	 * XXX The final recipients of VFS_MOUNT just overwrite the ndp they
	 * get.  No freeing of cn_pnbuf.
	 */
	error = VFS_MOUNT(mp);

	export_error = 0;
	if (error == 0) {
		/* Process the export option. */
		if (vfs_copyopt(mp->mnt_optnew, "export", &export,
		    sizeof(export)) == 0) {
			export_error = vfs_export(mp, &export);
		} else if (vfs_copyopt(mp->mnt_optnew, "export", &oexport,
		    sizeof(oexport)) == 0) {
			export.ex_flags = oexport.ex_flags;
			export.ex_root = oexport.ex_root;
			export.ex_anon = oexport.ex_anon;
			export.ex_addr = oexport.ex_addr;
			export.ex_addrlen = oexport.ex_addrlen;
			export.ex_mask = oexport.ex_mask;
			export.ex_masklen = oexport.ex_masklen;
			export.ex_indexfile = oexport.ex_indexfile;
			export.ex_numsecflavors = 0;
			export_error = vfs_export(mp, &export);
		}
	}

	MNT_ILOCK(mp);
	if (error == 0) {
		mp->mnt_flag &=	~(MNT_UPDATE | MNT_RELOAD | MNT_FORCE |
		    MNT_SNAPSHOT);
	} else {
		/*
		 * If we fail, restore old mount flags. MNT_QUOTA is special,
		 * because it is not part of MNT_UPDATEMASK, but it could have
		 * changed in the meantime if quotactl(2) was called.
		 * All in all we want current value of MNT_QUOTA, not the old
		 * one.
		 */
		mp->mnt_flag = (mp->mnt_flag & MNT_QUOTA) | (flag & ~MNT_QUOTA);
	}
	if ((mp->mnt_flag & MNT_ASYNC) != 0 &&
	    (mp->mnt_kern_flag & MNTK_NOASYNC) == 0)
		mp->mnt_kern_flag |= MNTK_ASYNC;
	else
		mp->mnt_kern_flag &= ~MNTK_ASYNC;
	MNT_IUNLOCK(mp);

	if (error != 0)
		goto end;

	if (mp->mnt_opt != NULL)
		vfs_freeopts(mp->mnt_opt);
	mp->mnt_opt = mp->mnt_optnew;
	*optlist = NULL;
	(void)VFS_STATFS(mp, &mp->mnt_stat);
	/*
	 * Prevent external consumers of mount options from reading
	 * mnt_optnew.
	 */
	mp->mnt_optnew = NULL;

	if ((mp->mnt_flag & MNT_RDONLY) == 0)
		vfs_allocate_syncvnode(mp);
	else
		vfs_deallocate_syncvnode(mp);
end:
	vfs_unbusy(mp);
	VI_LOCK(vp);
	vp->v_iflag &= ~VI_MOUNT;
	VI_UNLOCK(vp);
	vrele(vp);
	return (error != 0 ? error : export_error);
}

/*
 * vfs_domount(): actually attempt a filesystem mount.
 */
static int
vfs_domount(
	struct thread *td,		/* Calling thread. */
	const char *fstype,		/* Filesystem type. */
	char *fspath,			/* Mount path. */
	uint64_t fsflags,		/* Flags common to all filesystems. */
	struct vfsoptlist **optlist	/* Options local to the filesystem. */
	)
{
	struct vfsconf *vfsp;
	struct nameidata nd;
	struct vnode *vp;
	char *pathbuf;
	int error;

	/*
	 * Be ultra-paranoid about making sure the type and fspath
	 * variables will fit in our mp buffers, including the
	 * terminating NUL.
	 */
	if (strlen(fstype) >= MFSNAMELEN || strlen(fspath) >= MNAMELEN)
		return (ENAMETOOLONG);

	if (jailed(td->td_ucred) || usermount == 0) {
		if ((error = priv_check(td, PRIV_VFS_MOUNT)) != 0)
			return (error);
	}

	/*
	 * Do not allow NFS export or MNT_SUIDDIR by unprivileged users.
	 */
	if (fsflags & MNT_EXPORTED) {
		error = priv_check(td, PRIV_VFS_MOUNT_EXPORTED);
		if (error)
			return (error);
	}
	if (fsflags & MNT_SUIDDIR) {
		error = priv_check(td, PRIV_VFS_MOUNT_SUIDDIR);
		if (error)
			return (error);
	}
	/*
	 * Silently enforce MNT_NOSUID and MNT_USER for unprivileged users.
	 */
	if ((fsflags & (MNT_NOSUID | MNT_USER)) != (MNT_NOSUID | MNT_USER)) {
		if (priv_check(td, PRIV_VFS_MOUNT_NONUSER) != 0)
			fsflags |= MNT_NOSUID | MNT_USER;
	}

	/* Load KLDs before we lock the covered vnode to avoid reversals. */
	vfsp = NULL;
	if ((fsflags & MNT_UPDATE) == 0) {
		/* Don't try to load KLDs if we're mounting the root. */
		if (fsflags & MNT_ROOTFS)
			vfsp = vfs_byname(fstype);
		else
			vfsp = vfs_byname_kld(fstype, td, &error);
		if (vfsp == NULL)
			return (ENODEV);
		if (jailed(td->td_ucred) && !(vfsp->vfc_flags & VFCF_JAIL))
			return (EPERM);
	}

	/*
	 * Get vnode to be covered or mount point's vnode in case of MNT_UPDATE.
	 */
	NDINIT(&nd, LOOKUP, FOLLOW | LOCKLEAF | AUDITVNODE1,
	    UIO_SYSSPACE, fspath, td);
	error = namei(&nd);
	if (error != 0)
		return (error);
	mtx_lock(&Giant);
	NDFREE(&nd, NDF_ONLY_PNBUF);
	vp = nd.ni_vp;
	if ((fsflags & MNT_UPDATE) == 0) {
		pathbuf = malloc(MNAMELEN, M_TEMP, M_WAITOK);
		strcpy(pathbuf, fspath);
		error = vn_path_to_global_path(td, vp, pathbuf, MNAMELEN);
		/* debug.disablefullpath == 1 results in ENODEV */
		if (error == 0 || error == ENODEV) {
			error = vfs_domount_first(td, vfsp, pathbuf, vp,
			    fsflags, optlist);
		}
		free(pathbuf, M_TEMP);
	} else
		error = vfs_domount_update(td, vp, fsflags, optlist);
	mtx_unlock(&Giant);

	ASSERT_VI_UNLOCKED(vp, __func__);
	ASSERT_VOP_UNLOCKED(vp, __func__);

	return (error);
}

/*
 * Unmount a filesystem.
 *
 * Note: unmount takes a path to the vnode mounted on as argument, not
 * special file (as before).
 */
#ifndef _SYS_SYSPROTO_H_
struct unmount_args {
	char	*path;
	int	flags;
};
#endif
/* ARGSUSED */
int
sys_unmount(td, uap)
	struct thread *td;
	register struct unmount_args /* {
		char *path;
		int flags;
	} */ *uap;
{
	struct nameidata nd;
	struct mount *mp;
	char *pathbuf;
	int error, id0, id1;

	AUDIT_ARG_VALUE(uap->flags);
	if (jailed(td->td_ucred) || usermount == 0) {
		error = priv_check(td, PRIV_VFS_UNMOUNT);
		if (error)
			return (error);
	}

	pathbuf = malloc(MNAMELEN, M_TEMP, M_WAITOK);
	error = copyinstr(uap->path, pathbuf, MNAMELEN, NULL);
	if (error) {
		free(pathbuf, M_TEMP);
		return (error);
	}
	mtx_lock(&Giant);
	if (uap->flags & MNT_BYFSID) {
		AUDIT_ARG_TEXT(pathbuf);
		/* Decode the filesystem ID. */
		if (sscanf(pathbuf, "FSID:%d:%d", &id0, &id1) != 2) {
			mtx_unlock(&Giant);
			free(pathbuf, M_TEMP);
			return (EINVAL);
		}

		mtx_lock(&mountlist_mtx);
		TAILQ_FOREACH_REVERSE(mp, &mountlist, mntlist, mnt_list) {
			if (mp->mnt_stat.f_fsid.val[0] == id0 &&
			    mp->mnt_stat.f_fsid.val[1] == id1)
				break;
		}
		mtx_unlock(&mountlist_mtx);
	} else {
		/*
		 * Try to find global path for path argument.
		 */
		NDINIT(&nd, LOOKUP, FOLLOW | LOCKLEAF | AUDITVNODE1,
		    UIO_SYSSPACE, pathbuf, td);
		if (namei(&nd) == 0) {
			NDFREE(&nd, NDF_ONLY_PNBUF);
			error = vn_path_to_global_path(td, nd.ni_vp, pathbuf,
			    MNAMELEN);
			if (error == 0 || error == ENODEV)
				vput(nd.ni_vp);
		}
		mtx_lock(&mountlist_mtx);
		TAILQ_FOREACH_REVERSE(mp, &mountlist, mntlist, mnt_list) {
			if (strcmp(mp->mnt_stat.f_mntonname, pathbuf) == 0)
				break;
		}
		mtx_unlock(&mountlist_mtx);
	}
	free(pathbuf, M_TEMP);
	if (mp == NULL) {
		/*
		 * Previously we returned ENOENT for a nonexistent path and
		 * EINVAL for a non-mountpoint.  We cannot tell these apart
		 * now, so in the !MNT_BYFSID case return the more likely
		 * EINVAL for compatibility.
		 */
		mtx_unlock(&Giant);
		return ((uap->flags & MNT_BYFSID) ? ENOENT : EINVAL);
	}

	/*
	 * Don't allow unmounting the root filesystem.
	 */
	if (mp->mnt_flag & MNT_ROOTFS) {
		mtx_unlock(&Giant);
		return (EINVAL);
	}
	error = dounmount(mp, uap->flags, td);
	mtx_unlock(&Giant);
	return (error);
}

/*
 * Do the actual filesystem unmount.
 */
int
dounmount(mp, flags, td)
	struct mount *mp;
	int flags;
	struct thread *td;
{
	struct vnode *coveredvp, *fsrootvp;
	int error;
	uint64_t async_flag;
	int mnt_gen_r;

	mtx_assert(&Giant, MA_OWNED);

	if ((coveredvp = mp->mnt_vnodecovered) != NULL) {
		mnt_gen_r = mp->mnt_gen;
		VI_LOCK(coveredvp);
		vholdl(coveredvp);
		vn_lock(coveredvp, LK_EXCLUSIVE | LK_INTERLOCK | LK_RETRY);
		vdrop(coveredvp);
		/*
		 * Check for mp being unmounted while waiting for the
		 * covered vnode lock.
		 */
		if (coveredvp->v_mountedhere != mp ||
		    coveredvp->v_mountedhere->mnt_gen != mnt_gen_r) {
			VOP_UNLOCK(coveredvp, 0);
			return (EBUSY);
		}
	}
	/*
	 * Only privileged root, or (if MNT_USER is set) the user that did the
	 * original mount is permitted to unmount this filesystem.
	 */
	error = vfs_suser(mp, td);
	if (error) {
		if (coveredvp)
			VOP_UNLOCK(coveredvp, 0);
		return (error);
	}

	vn_start_write(NULL, &mp, V_WAIT);
	MNT_ILOCK(mp);
	if ((mp->mnt_kern_flag & MNTK_UNMOUNT) != 0 ||
	    !TAILQ_EMPTY(&mp->mnt_uppers)) {
		MNT_IUNLOCK(mp);
		if (coveredvp)
			VOP_UNLOCK(coveredvp, 0);
		vn_finished_write(mp);
		return (EBUSY);
	}
	mp->mnt_kern_flag |= MNTK_UNMOUNT | MNTK_NOINSMNTQ;
	/* Allow filesystems to detect that a forced unmount is in progress. */
	if (flags & MNT_FORCE) {
		mp->mnt_kern_flag |= MNTK_UNMOUNTF;
		MNT_IUNLOCK(mp);
		/*
		 * Must be done after setting MNTK_UNMOUNTF and before
		 * waiting for mnt_lockref to become 0.
		 */
		VFS_PURGE(mp);
		MNT_ILOCK(mp);
	}
	error = 0;
	if (mp->mnt_lockref) {
		mp->mnt_kern_flag |= MNTK_DRAINING;
		error = msleep(&mp->mnt_lockref, MNT_MTX(mp), PVFS,
		    "mount drain", 0);
	}
	MNT_IUNLOCK(mp);
	KASSERT(mp->mnt_lockref == 0,
	    ("%s: invalid lock refcount in the drain path @ %s:%d",
	    __func__, __FILE__, __LINE__));
	KASSERT(error == 0,
	    ("%s: invalid return value for msleep in the drain path @ %s:%d",
	    __func__, __FILE__, __LINE__));

	if (mp->mnt_flag & MNT_EXPUBLIC)
		vfs_setpublicfs(NULL, NULL, NULL);

	vfs_msync(mp, MNT_WAIT);
	MNT_ILOCK(mp);
	async_flag = mp->mnt_flag & MNT_ASYNC;
	mp->mnt_flag &= ~MNT_ASYNC;
	mp->mnt_kern_flag &= ~MNTK_ASYNC;
	MNT_IUNLOCK(mp);
	cache_purgevfs(mp);	/* remove cache entries for this file sys */
	vfs_deallocate_syncvnode(mp);
	/*
	 * For forced unmounts, move process cdir/rdir refs on the fs root
	 * vnode to the covered vnode.  For non-forced unmounts we want
	 * such references to cause an EBUSY error.
	 */
	if ((flags & MNT_FORCE) &&
	    VFS_ROOT(mp, LK_EXCLUSIVE, &fsrootvp) == 0) {
		if (mp->mnt_vnodecovered != NULL)
			mountcheckdirs(fsrootvp, mp->mnt_vnodecovered);
		if (fsrootvp == rootvnode) {
			vrele(rootvnode);
			rootvnode = NULL;
		}
		vput(fsrootvp);
	}
	if (((mp->mnt_flag & MNT_RDONLY) ||
	     (error = VFS_SYNC(mp, MNT_WAIT)) == 0) || (flags & MNT_FORCE) != 0)
		error = VFS_UNMOUNT(mp, flags);
	vn_finished_write(mp);
	/*
	 * If we failed to flush the dirty blocks for this mount point,
	 * undo all the cdir/rdir and rootvnode changes we made above.
	 * Unless we failed to do so because the device is reporting that
	 * it doesn't exist anymore.
	 */
	if (error && error != ENXIO) {
		if ((flags & MNT_FORCE) &&
		    VFS_ROOT(mp, LK_EXCLUSIVE, &fsrootvp) == 0) {
			if (mp->mnt_vnodecovered != NULL)
				mountcheckdirs(mp->mnt_vnodecovered, fsrootvp);
			if (rootvnode == NULL) {
				rootvnode = fsrootvp;
				vref(rootvnode);
			}
			vput(fsrootvp);
		}
		MNT_ILOCK(mp);
		mp->mnt_kern_flag &= ~MNTK_NOINSMNTQ;
		if ((mp->mnt_flag & MNT_RDONLY) == 0) {
			MNT_IUNLOCK(mp);
			vfs_allocate_syncvnode(mp);
			MNT_ILOCK(mp);
		}
		mp->mnt_kern_flag &= ~(MNTK_UNMOUNT | MNTK_UNMOUNTF);
		mp->mnt_flag |= async_flag;
		if ((mp->mnt_flag & MNT_ASYNC) != 0 &&
		    (mp->mnt_kern_flag & MNTK_NOASYNC) == 0)
			mp->mnt_kern_flag |= MNTK_ASYNC;
		if (mp->mnt_kern_flag & MNTK_MWAIT) {
			mp->mnt_kern_flag &= ~MNTK_MWAIT;
			wakeup(mp);
		}
		MNT_IUNLOCK(mp);
		if (coveredvp)
			VOP_UNLOCK(coveredvp, 0);
		return (error);
	}
	mtx_lock(&mountlist_mtx);
	TAILQ_REMOVE(&mountlist, mp, mnt_list);
	mtx_unlock(&mountlist_mtx);
	EVENTHANDLER_INVOKE(vfs_unmounted, mp, td);
	if (coveredvp != NULL) {
		coveredvp->v_mountedhere = NULL;
		vput(coveredvp);
	}
	vfs_event_signal(NULL, VQ_UNMOUNT, 0);
	vfs_mount_destroy(mp);
	return (0);
}

/*
 * Report errors during filesystem mounting.
 */
void
vfs_mount_error(struct mount *mp, const char *fmt, ...)
{
	struct vfsoptlist *moptlist = mp->mnt_optnew;
	va_list ap;
	int error, len;
	char *errmsg;

	error = vfs_getopt(moptlist, "errmsg", (void **)&errmsg, &len);
	if (error || errmsg == NULL || len <= 0)
		return;

	va_start(ap, fmt);
	vsnprintf(errmsg, (size_t)len, fmt, ap);
	va_end(ap);
}

void
vfs_opterror(struct vfsoptlist *opts, const char *fmt, ...)
{
	va_list ap;
	int error, len;
	char *errmsg;

	error = vfs_getopt(opts, "errmsg", (void **)&errmsg, &len);
	if (error || errmsg == NULL || len <= 0)
		return;

	va_start(ap, fmt);
	vsnprintf(errmsg, (size_t)len, fmt, ap);
	va_end(ap);
}

/*
 * ---------------------------------------------------------------------
 * Functions for querying mount options/arguments from filesystems.
 */

/*
 * Check that no unknown options are given
 */
int
vfs_filteropt(struct vfsoptlist *opts, const char **legal)
{
	struct vfsopt *opt;
	char errmsg[255];
	const char **t, *p, *q;
	int ret = 0;

	TAILQ_FOREACH(opt, opts, link) {
		p = opt->name;
		q = NULL;
		if (p[0] == 'n' && p[1] == 'o')
			q = p + 2;
		for(t = global_opts; *t != NULL; t++) {
			if (strcmp(*t, p) == 0)
				break;
			if (q != NULL) {
				if (strcmp(*t, q) == 0)
					break;
			}
		}
		if (*t != NULL)
			continue;
		for(t = legal; *t != NULL; t++) {
			if (strcmp(*t, p) == 0)
				break;
			if (q != NULL) {
				if (strcmp(*t, q) == 0)
					break;
			}
		}
		if (*t != NULL)
			continue;
		snprintf(errmsg, sizeof(errmsg),
		    "mount option <%s> is unknown", p);
		ret = EINVAL;
	}
	if (ret != 0) {
		TAILQ_FOREACH(opt, opts, link) {
			if (strcmp(opt->name, "errmsg") == 0) {
				strncpy((char *)opt->value, errmsg, opt->len);
				break;
			}
		}
		if (opt == NULL)
			printf("%s\n", errmsg);
	}
	return (ret);
}

/*
 * Get a mount option by its name.
 *
 * Return 0 if the option was found, ENOENT otherwise.
 * If len is non-NULL it will be filled with the length
 * of the option. If buf is non-NULL, it will be filled
 * with the address of the option.
 */
int
vfs_getopt(opts, name, buf, len)
	struct vfsoptlist *opts;
	const char *name;
	void **buf;
	int *len;
{
	struct vfsopt *opt;

	KASSERT(opts != NULL, ("vfs_getopt: caller passed 'opts' as NULL"));

	TAILQ_FOREACH(opt, opts, link) {
		if (strcmp(name, opt->name) == 0) {
			opt->seen = 1;
			if (len != NULL)
				*len = opt->len;
			if (buf != NULL)
				*buf = opt->value;
			return (0);
		}
	}
	return (ENOENT);
}

int
vfs_getopt_pos(struct vfsoptlist *opts, const char *name)
{
	struct vfsopt *opt;

	if (opts == NULL)
		return (-1);

	TAILQ_FOREACH(opt, opts, link) {
		if (strcmp(name, opt->name) == 0) {
			opt->seen = 1;
			return (opt->pos);
		}
	}
	return (-1);
}

int
vfs_getopt_size(struct vfsoptlist *opts, const char *name, off_t *value)
{
	char *opt_value, *vtp;
	quad_t iv;
	int error, opt_len;

	error = vfs_getopt(opts, name, (void **)&opt_value, &opt_len);
	if (error != 0)
		return (error);
	if (opt_len == 0 || opt_value == NULL)
		return (EINVAL);
	if (opt_value[0] == '\0' || opt_value[opt_len - 1] != '\0')
		return (EINVAL);
	iv = strtoq(opt_value, &vtp, 0);
	if (vtp == opt_value || (vtp[0] != '\0' && vtp[1] != '\0'))
		return (EINVAL);
	if (iv < 0)
		return (EINVAL);
	switch (vtp[0]) {
	case 't':
	case 'T':
		iv *= 1024;
	case 'g':
	case 'G':
		iv *= 1024;
	case 'm':
	case 'M':
		iv *= 1024;
	case 'k':
	case 'K':
		iv *= 1024;
	case '\0':
		break;
	default:
		return (EINVAL);
	}
	*value = iv;

	return (0);
}

char *
vfs_getopts(struct vfsoptlist *opts, const char *name, int *error)
{
	struct vfsopt *opt;

	*error = 0;
	TAILQ_FOREACH(opt, opts, link) {
		if (strcmp(name, opt->name) != 0)
			continue;
		opt->seen = 1;
		if (opt->len == 0 ||
		    ((char *)opt->value)[opt->len - 1] != '\0') {
			*error = EINVAL;
			return (NULL);
		}
		return (opt->value);
	}
	*error = ENOENT;
	return (NULL);
}

int
vfs_flagopt(struct vfsoptlist *opts, const char *name, uint64_t *w,
	uint64_t val)
{
	struct vfsopt *opt;

	TAILQ_FOREACH(opt, opts, link) {
		if (strcmp(name, opt->name) == 0) {
			opt->seen = 1;
			if (w != NULL)
				*w |= val;
			return (1);
		}
	}
	if (w != NULL)
		*w &= ~val;
	return (0);
}

int
vfs_scanopt(struct vfsoptlist *opts, const char *name, const char *fmt, ...)
{
	va_list ap;
	struct vfsopt *opt;
	int ret;

	KASSERT(opts != NULL, ("vfs_getopt: caller passed 'opts' as NULL"));

	TAILQ_FOREACH(opt, opts, link) {
		if (strcmp(name, opt->name) != 0)
			continue;
		opt->seen = 1;
		if (opt->len == 0 || opt->value == NULL)
			return (0);
		if (((char *)opt->value)[opt->len - 1] != '\0')
			return (0);
		va_start(ap, fmt);
		ret = vsscanf(opt->value, fmt, ap);
		va_end(ap);
		return (ret);
	}
	return (0);
}

int
vfs_setopt(struct vfsoptlist *opts, const char *name, void *value, int len)
{
	struct vfsopt *opt;

	TAILQ_FOREACH(opt, opts, link) {
		if (strcmp(name, opt->name) != 0)
			continue;
		opt->seen = 1;
		if (opt->value == NULL)
			opt->len = len;
		else {
			if (opt->len != len)
				return (EINVAL);
			bcopy(value, opt->value, len);
		}
		return (0);
	}
	return (ENOENT);
}

int
vfs_setopt_part(struct vfsoptlist *opts, const char *name, void *value, int len)
{
	struct vfsopt *opt;

	TAILQ_FOREACH(opt, opts, link) {
		if (strcmp(name, opt->name) != 0)
			continue;
		opt->seen = 1;
		if (opt->value == NULL)
			opt->len = len;
		else {
			if (opt->len < len)
				return (EINVAL);
			opt->len = len;
			bcopy(value, opt->value, len);
		}
		return (0);
	}
	return (ENOENT);
}

int
vfs_setopts(struct vfsoptlist *opts, const char *name, const char *value)
{
	struct vfsopt *opt;

	TAILQ_FOREACH(opt, opts, link) {
		if (strcmp(name, opt->name) != 0)
			continue;
		opt->seen = 1;
		if (opt->value == NULL)
			opt->len = strlen(value) + 1;
		else if (strlcpy(opt->value, value, opt->len) >= opt->len)
			return (EINVAL);
		return (0);
	}
	return (ENOENT);
}

/*
 * Find and copy a mount option.
 *
 * The size of the buffer has to be specified
 * in len, if it is not the same length as the
 * mount option, EINVAL is returned.
 * Returns ENOENT if the option is not found.
 */
int
vfs_copyopt(opts, name, dest, len)
	struct vfsoptlist *opts;
	const char *name;
	void *dest;
	int len;
{
	struct vfsopt *opt;

	KASSERT(opts != NULL, ("vfs_copyopt: caller passed 'opts' as NULL"));

	TAILQ_FOREACH(opt, opts, link) {
		if (strcmp(name, opt->name) == 0) {
			opt->seen = 1;
			if (len != opt->len)
				return (EINVAL);
			bcopy(opt->value, dest, opt->len);
			return (0);
		}
	}
	return (ENOENT);
}

int
__vfs_statfs(struct mount *mp, struct statfs *sbp)
{
	int error;

	error = mp->mnt_op->vfs_statfs(mp, &mp->mnt_stat);
	if (sbp != &mp->mnt_stat)
		*sbp = mp->mnt_stat;
	return (error);
}

void
vfs_mountedfrom(struct mount *mp, const char *from)
{

	bzero(mp->mnt_stat.f_mntfromname, sizeof mp->mnt_stat.f_mntfromname);
	strlcpy(mp->mnt_stat.f_mntfromname, from,
	    sizeof mp->mnt_stat.f_mntfromname);
}

/*
 * ---------------------------------------------------------------------
 * This is the api for building mount args and mounting filesystems from
 * inside the kernel.
 *
 * The API works by accumulation of individual args.  First error is
 * latched.
 *
 * XXX: should be documented in new manpage kernel_mount(9)
 */

/* A memory allocation which must be freed when we are done */
struct mntaarg {
	SLIST_ENTRY(mntaarg)	next;
};

/* The header for the mount arguments */
struct mntarg {
	struct iovec *v;
	int len;
	int error;
	SLIST_HEAD(, mntaarg)	list;
};

/*
 * Add a boolean argument.
 *
 * flag is the boolean value.
 * name must start with "no".
 */
struct mntarg *
mount_argb(struct mntarg *ma, int flag, const char *name)
{

	KASSERT(name[0] == 'n' && name[1] == 'o',
	    ("mount_argb(...,%s): name must start with 'no'", name));

	return (mount_arg(ma, name + (flag ? 2 : 0), NULL, 0));
}

/*
 * Add an argument printf style
 */
struct mntarg *
mount_argf(struct mntarg *ma, const char *name, const char *fmt, ...)
{
	va_list ap;
	struct mntaarg *maa;
	struct sbuf *sb;
	int len;

	if (ma == NULL) {
		ma = malloc(sizeof *ma, M_MOUNT, M_WAITOK | M_ZERO);
		SLIST_INIT(&ma->list);
	}
	if (ma->error)
		return (ma);

	ma->v = realloc(ma->v, sizeof *ma->v * (ma->len + 2),
	    M_MOUNT, M_WAITOK);
	ma->v[ma->len].iov_base = (void *)(uintptr_t)name;
	ma->v[ma->len].iov_len = strlen(name) + 1;
	ma->len++;

	sb = sbuf_new_auto();
	va_start(ap, fmt);
	sbuf_vprintf(sb, fmt, ap);
	va_end(ap);
	sbuf_finish(sb);
	len = sbuf_len(sb) + 1;
	maa = malloc(sizeof *maa + len, M_MOUNT, M_WAITOK | M_ZERO);
	SLIST_INSERT_HEAD(&ma->list, maa, next);
	bcopy(sbuf_data(sb), maa + 1, len);
	sbuf_delete(sb);

	ma->v[ma->len].iov_base = maa + 1;
	ma->v[ma->len].iov_len = len;
	ma->len++;

	return (ma);
}

/*
 * Add an argument which is a userland string.
 */
struct mntarg *
mount_argsu(struct mntarg *ma, const char *name, const void *val, int len)
{
	struct mntaarg *maa;
	char *tbuf;

	if (val == NULL)
		return (ma);
	if (ma == NULL) {
		ma = malloc(sizeof *ma, M_MOUNT, M_WAITOK | M_ZERO);
		SLIST_INIT(&ma->list);
	}
	if (ma->error)
		return (ma);
	maa = malloc(sizeof *maa + len, M_MOUNT, M_WAITOK | M_ZERO);
	SLIST_INSERT_HEAD(&ma->list, maa, next);
	tbuf = (void *)(maa + 1);
	ma->error = copyinstr(val, tbuf, len, NULL);
	return (mount_arg(ma, name, tbuf, -1));
}

/*
 * Plain argument.
 *
 * If length is -1, treat value as a C string.
 */
struct mntarg *
mount_arg(struct mntarg *ma, const char *name, const void *val, int len)
{

	if (ma == NULL) {
		ma = malloc(sizeof *ma, M_MOUNT, M_WAITOK | M_ZERO);
		SLIST_INIT(&ma->list);
	}
	if (ma->error)
		return (ma);

	ma->v = realloc(ma->v, sizeof *ma->v * (ma->len + 2),
	    M_MOUNT, M_WAITOK);
	ma->v[ma->len].iov_base = (void *)(uintptr_t)name;
	ma->v[ma->len].iov_len = strlen(name) + 1;
	ma->len++;

	ma->v[ma->len].iov_base = (void *)(uintptr_t)val;
	if (len < 0)
		ma->v[ma->len].iov_len = strlen(val) + 1;
	else
		ma->v[ma->len].iov_len = len;
	ma->len++;
	return (ma);
}

/*
 * Free a mntarg structure
 */
static void
free_mntarg(struct mntarg *ma)
{
	struct mntaarg *maa;

	while (!SLIST_EMPTY(&ma->list)) {
		maa = SLIST_FIRST(&ma->list);
		SLIST_REMOVE_HEAD(&ma->list, next);
		free(maa, M_MOUNT);
	}
	free(ma->v, M_MOUNT);
	free(ma, M_MOUNT);
}

/*
 * Mount a filesystem
 */
int
kernel_mount(struct mntarg *ma, uint64_t flags)
{
	struct uio auio;
	int error;

	KASSERT(ma != NULL, ("kernel_mount NULL ma"));
	KASSERT(ma->v != NULL, ("kernel_mount NULL ma->v"));
	KASSERT(!(ma->len & 1), ("kernel_mount odd ma->len (%d)", ma->len));

	auio.uio_iov = ma->v;
	auio.uio_iovcnt = ma->len;
	auio.uio_segflg = UIO_SYSSPACE;

	error = ma->error;
	if (!error)
		error = vfs_donmount(curthread, flags, &auio);
	free_mntarg(ma);
	return (error);
}

/*
 * A printflike function to mount a filesystem.
 */
int
kernel_vmount(int flags, ...)
{
	struct mntarg *ma = NULL;
	va_list ap;
	const char *cp;
	const void *vp;
	int error;

	va_start(ap, flags);
	for (;;) {
		cp = va_arg(ap, const char *);
		if (cp == NULL)
			break;
		vp = va_arg(ap, const void *);
		ma = mount_arg(ma, cp, vp, (vp != NULL ? -1 : 0));
	}
	va_end(ap);

	error = kernel_mount(ma, flags);
	return (error);
}

void
vfs_oexport_conv(const struct oexport_args *oexp, struct export_args *exp)
{

	bcopy(oexp, exp, sizeof(*oexp));
	exp->ex_numsecflavors = 0;
}
OpenPOWER on IntegriCloud