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
|
/* $OpenBSD: vfs_subr.c,v 1.30 1998/12/28 19:35:35 art Exp $ */
/* $NetBSD: vfs_subr.c,v 1.53 1996/04/22 01:39:13 christos Exp $ */
/*
* 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.
* 3. All advertising materials mentioning features or use of this software
* must display the following acknowledgement:
* This product includes software developed by the University of
* California, Berkeley and its contributors.
* 4. Neither the name of the University nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* @(#)vfs_subr.c 8.13 (Berkeley) 4/18/94
*/
/*
* External virtual filesystem routines
*/
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/proc.h>
#include <sys/mount.h>
#include <sys/time.h>
#include <sys/fcntl.h>
#include <sys/kernel.h>
#include <sys/vnode.h>
#include <sys/stat.h>
#include <sys/namei.h>
#include <sys/ucred.h>
#include <sys/buf.h>
#include <sys/errno.h>
#include <sys/malloc.h>
#include <sys/domain.h>
#include <sys/mbuf.h>
#include <sys/syscallargs.h>
#include <vm/vm.h>
#include <sys/sysctl.h>
#include <miscfs/specfs/specdev.h>
enum vtype iftovt_tab[16] = {
VNON, VFIFO, VCHR, VNON, VDIR, VNON, VBLK, VNON,
VREG, VNON, VLNK, VNON, VSOCK, VNON, VNON, VBAD,
};
int vttoif_tab[9] = {
0, S_IFREG, S_IFDIR, S_IFBLK, S_IFCHR, S_IFLNK,
S_IFSOCK, S_IFIFO, S_IFMT,
};
int doforce = 1; /* 1 => permit forcible unmounting */
int prtactive = 0; /* 1 => print out reclaim of active vnodes */
int suid_clear = 1; /* 1 => clear SUID / SGID on owner change */
/*
* Insq/Remq for the vnode usage lists.
*/
#define bufinsvn(bp, dp) LIST_INSERT_HEAD(dp, bp, b_vnbufs)
#define bufremvn(bp) { \
LIST_REMOVE(bp, b_vnbufs); \
(bp)->b_vnbufs.le_next = NOLIST; \
}
struct freelst vnode_hold_list; /* list of vnodes referencing buffers */
struct freelst vnode_free_list; /* vnode free list */
struct mntlist mountlist; /* mounted filesystem list */
struct simplelock mountlist_slock;
static struct simplelock mntid_slock;
struct simplelock mntvnode_slock;
struct simplelock vnode_free_list_slock;
struct simplelock spechash_slock;
void insmntque __P((struct vnode *, struct mount *));
int getdevvp __P((dev_t, struct vnode **, enum vtype));
int vfs_hang_addrlist __P((struct mount *, struct netexport *,
struct export_args *));
int vfs_free_netcred __P((struct radix_node *, void *));
void vfs_free_addrlist __P((struct netexport *));
static __inline__ void vputonfreelist __P((struct vnode *));
#ifdef DEBUG
void printlockedvnodes __P((void));
#endif
/*
* Initialize the vnode management data structures.
*/
void
vntblinit()
{
simple_lock_init(&mntvnode_slock);
simple_lock_init(&mntid_slock);
simple_lock_init(&spechash_slock);
TAILQ_INIT(&vnode_hold_list);
TAILQ_INIT(&vnode_free_list);
simple_lock_init(&vnode_free_list_slock);
CIRCLEQ_INIT(&mountlist);
/*
* Initialize the filesystem syncer.
*/
vn_initialize_syncerd();
}
/*
* Mark a mount point as busy. Used to synchronize access and to delay
* unmounting. Interlock is not released on failure.
*/
int
vfs_busy(mp, flags, interlkp, p)
struct mount *mp;
int flags;
struct simplelock *interlkp;
struct proc *p;
{
int lkflags;
if (mp->mnt_flag & MNT_UNMOUNT) {
if (flags & LK_NOWAIT)
return (ENOENT);
mp->mnt_flag |= MNT_MWAIT;
if (interlkp)
simple_unlock(interlkp);
/*
* Since all busy locks are shared except the exclusive
* lock granted when unmounting, the only place that a
* wakeup needs to be done is at the release of the
* exclusive lock at the end of dounmount.
*/
sleep((caddr_t)mp, PVFS);
if (interlkp)
simple_lock(interlkp);
return (ENOENT);
}
lkflags = LK_SHARED;
if (interlkp)
lkflags |= LK_INTERLOCK;
if (lockmgr(&mp->mnt_lock, lkflags, interlkp, p))
panic("vfs_busy: unexpected lock failure");
return (0);
}
/*
* Free a busy file system
*/
void
vfs_unbusy(mp, p)
struct mount *mp;
struct proc *p;
{
lockmgr(&mp->mnt_lock, LK_RELEASE, NULL, p);
}
/*
* Lookup a filesystem type, and if found allocate and initialize
* a mount structure for it.
*
* Devname is usually updated by mount(8) after booting.
*/
int
vfs_rootmountalloc(fstypename, devname, mpp)
char *fstypename;
char *devname;
struct mount **mpp;
{
struct proc *p = curproc; /* XXX */
struct vfsconf *vfsp;
struct mount *mp;
for (vfsp = vfsconf; vfsp; vfsp = vfsp->vfc_next)
if (!strcmp(vfsp->vfc_name, fstypename))
break;
if (vfsp == NULL)
return (ENODEV);
mp = malloc((u_long)sizeof(struct mount), M_MOUNT, M_WAITOK);
bzero((char *)mp, (u_long)sizeof(struct mount));
lockinit(&mp->mnt_lock, PVFS, "vfslock", 0, 0);
(void)vfs_busy(mp, LK_NOWAIT, 0, p);
LIST_INIT(&mp->mnt_vnodelist);
mp->mnt_vfc = vfsp;
mp->mnt_op = vfsp->vfc_vfsops;
mp->mnt_flag = MNT_RDONLY;
mp->mnt_vnodecovered = NULLVP;
vfsp->vfc_refcount++;
mp->mnt_stat.f_type = vfsp->vfc_typenum;
mp->mnt_flag |= vfsp->vfc_flags & MNT_VISFLAGMASK;
strncpy(mp->mnt_stat.f_fstypename, vfsp->vfc_name, MFSNAMELEN);
mp->mnt_stat.f_mntonname[0] = '/';
(void) copystr(devname, mp->mnt_stat.f_mntfromname, MNAMELEN - 1, 0);
*mpp = mp;
return (0);
}
/*
* Find an appropriate filesystem to use for the root. If a filesystem
* has not been preselected, walk through the list of known filesystems
* trying those that have mountroot routines, and try them until one
* works or we have tried them all.
*/
int
vfs_mountroot()
{
struct vfsconf *vfsp;
extern int (*mountroot)(void);
int error;
if (mountroot != NULL)
return ((*mountroot)());
for (vfsp = vfsconf; vfsp; vfsp = vfsp->vfc_next) {
if (vfsp->vfc_mountroot == NULL)
continue;
if ((error = (*vfsp->vfc_mountroot)()) == 0)
return (0);
printf("%s_mountroot failed: %d\n", vfsp->vfc_name, error);
}
return (ENODEV);
}
/*
* Lookup a mount point by filesystem identifier.
*/
struct mount *
vfs_getvfs(fsid)
fsid_t *fsid;
{
register struct mount *mp;
simple_lock(&mountlist_slock);
for (mp = mountlist.cqh_first; mp != (void *)&mountlist;
mp = mp->mnt_list.cqe_next) {
if (mp->mnt_stat.f_fsid.val[0] == fsid->val[0] &&
mp->mnt_stat.f_fsid.val[1] == fsid->val[1]) {
simple_unlock(&mountlist_slock);
return (mp);
}
}
simple_unlock(&mountlist_slock);
return ((struct mount *)0);
}
/*
* Get a new unique fsid
*/
void
vfs_getnewfsid(mp)
struct mount *mp;
{
static u_short xxxfs_mntid;
fsid_t tfsid;
int mtype;
simple_lock(&mntid_slock);
mtype = mp->mnt_vfc->vfc_typenum;
mp->mnt_stat.f_fsid.val[0] = makedev(nblkdev + mtype, 0);
mp->mnt_stat.f_fsid.val[1] = mtype;
if (xxxfs_mntid == 0)
++xxxfs_mntid;
tfsid.val[0] = makedev(nblkdev + mtype, xxxfs_mntid);
tfsid.val[1] = mtype;
if (mountlist.cqh_first != (void *)&mountlist) {
while (vfs_getvfs(&tfsid)) {
tfsid.val[0]++;
xxxfs_mntid++;
}
}
mp->mnt_stat.f_fsid.val[0] = tfsid.val[0];
simple_unlock(&mntid_slock);
}
/*
* Make a 'unique' number from a mount type name.
* Note that this is no longer used for ffs which
* now has an on-disk filesystem id.
*/
long
makefstype(type)
char *type;
{
long rv;
for (rv = 0; *type; type++) {
rv <<= 2;
rv ^= *type;
}
return rv;
}
/*
* Set vnode attributes to VNOVAL
*/
void
vattr_null(vap)
register struct vattr *vap;
{
vap->va_type = VNON;
/* XXX These next two used to be one line, but for a GCC bug. */
vap->va_size = VNOVAL;
vap->va_bytes = VNOVAL;
vap->va_mode = vap->va_nlink = vap->va_uid = vap->va_gid =
vap->va_fsid = vap->va_fileid =
vap->va_blocksize = vap->va_rdev =
vap->va_atime.tv_sec = vap->va_atime.tv_nsec =
vap->va_mtime.tv_sec = vap->va_mtime.tv_nsec =
vap->va_ctime.tv_sec = vap->va_ctime.tv_nsec =
vap->va_flags = vap->va_gen = VNOVAL;
vap->va_vaflags = 0;
}
/*
* Routines having to do with the management of the vnode table.
*/
extern int (**dead_vnodeop_p) __P((void *));
long numvnodes;
/*
* Return the next vnode from the free list.
*/
int
getnewvnode(tag, mp, vops, vpp)
enum vtagtype tag;
struct mount *mp;
int (**vops) __P((void *));
struct vnode **vpp;
{
struct proc *p = curproc; /* XXX */
struct freelst *listhd;
static int toggle;
struct vnode *vp;
#ifdef DIAGNOSTIC
int s;
#endif
/*
* We must choose whether to allocate a new vnode or recycle an
* existing one. The criterion for allocating a new one is that
* the total number of vnodes is less than the number desired or
* there are no vnodes on either free list. Generally we only
* want to recycle vnodes that have no buffers associated with
* them, so we look first on the vnode_free_list. If it is empty,
* we next consider vnodes with referencing buffers on the
* vnode_hold_list. The toggle ensures that half the time we
* will use a buffer from the vnode_hold_list, and half the time
* we will allocate a new one unless the list has grown to twice
* the desired size. We are reticent to recycle vnodes from the
* vnode_hold_list because we will lose the identity of all its
* referencing buffers.
*/
toggle ^= 1;
if (numvnodes > 2 * desiredvnodes)
toggle = 0;
simple_lock(&vnode_free_list_slock);
if ((numvnodes < desiredvnodes) ||
((TAILQ_FIRST(listhd = &vnode_free_list) == NULL) &&
((TAILQ_FIRST(listhd = &vnode_hold_list) == NULL) || toggle))) {
simple_unlock(&vnode_free_list_slock);
vp = (struct vnode *)malloc((u_long)sizeof *vp,
M_VNODE, M_WAITOK);
bzero((char *)vp, sizeof *vp);
numvnodes++;
} else {
for (vp = TAILQ_FIRST(listhd); vp != NULLVP;
vp = TAILQ_NEXT(vp, v_freelist)) {
if (simple_lock_try(&vp->v_interlock))
break;
}
/*
* Unless this is a bad time of the month, at most
* the first NCPUS items on the free list are
* locked, so this is close enough to being empty.
*/
if (vp == NULLVP) {
simple_unlock(&vnode_free_list_slock);
tablefull("vnode");
*vpp = 0;
return (ENFILE);
}
if (vp->v_usecount) {
vprint("free vnode", vp);
panic("free vnode isn't");
}
TAILQ_REMOVE(listhd, vp, v_freelist);
vp->v_flag &= ~VONFREELIST;
simple_unlock(&vnode_free_list_slock);
vp->v_lease = NULL;
if (vp->v_type != VBAD)
vgonel(vp, p);
else
simple_unlock(&vp->v_interlock);
#ifdef DIAGNOSTIC
if (vp->v_data) {
vprint("cleaned vnode", vp);
panic("cleaned vnode isn't");
}
s = splbio();
if (vp->v_numoutput)
panic("Clean vnode has pending I/O's");
splx(s);
#endif
vp->v_flag = 0;
vp->v_lastr = 0;
vp->v_ralen = 0;
vp->v_maxra = 0;
vp->v_lastw = 0;
vp->v_lasta = 0;
vp->v_cstart = 0;
vp->v_clen = 0;
vp->v_socket = 0;
}
vp->v_type = VNON;
cache_purge(vp);
vp->v_tag = tag;
vp->v_op = vops;
insmntque(vp, mp);
*vpp = vp;
vp->v_usecount = 1;
vp->v_data = 0;
return (0);
}
/*
* Move a vnode from one mount queue to another.
*/
void
insmntque(vp, mp)
register struct vnode *vp;
register struct mount *mp;
{
simple_lock(&mntvnode_slock);
/*
* Delete from old mount point vnode list, if on one.
*/
if (vp->v_mount != NULL)
LIST_REMOVE(vp, v_mntvnodes);
/*
* Insert into list of vnodes for the new mount point, if available.
*/
if ((vp->v_mount = mp) != NULL)
LIST_INSERT_HEAD(&mp->mnt_vnodelist, vp, v_mntvnodes);
simple_unlock(&mntvnode_slock);
}
/*
* Create a vnode for a block device.
* Used for root filesystem, argdev, and swap areas.
* Also used for memory file system special devices.
*/
int
bdevvp(dev, vpp)
dev_t dev;
struct vnode **vpp;
{
return (getdevvp(dev, vpp, VBLK));
}
/*
* Create a vnode for a character device.
* Used for kernfs and some console handling.
*/
int
cdevvp(dev, vpp)
dev_t dev;
struct vnode **vpp;
{
return (getdevvp(dev, vpp, VCHR));
}
/*
* Create a vnode for a device.
* Used by bdevvp (block device) for root file system etc.,
* and by cdevvp (character device) for console and kernfs.
*/
int
getdevvp(dev, vpp, type)
dev_t dev;
struct vnode **vpp;
enum vtype type;
{
register struct vnode *vp;
struct vnode *nvp;
int error;
if (dev == NODEV) {
*vpp = NULLVP;
return (0);
}
error = getnewvnode(VT_NON, NULL, spec_vnodeop_p, &nvp);
if (error) {
*vpp = NULLVP;
return (error);
}
vp = nvp;
vp->v_type = type;
if ((nvp = checkalias(vp, dev, NULL)) != 0) {
vput(vp);
vp = nvp;
}
*vpp = vp;
return (0);
}
/*
* Check to see if the new vnode represents a special device
* for which we already have a vnode (either because of
* bdevvp() or because of a different vnode representing
* the same block device). If such an alias exists, deallocate
* the existing contents and return the aliased vnode. The
* caller is responsible for filling it with its new contents.
*/
struct vnode *
checkalias(nvp, nvp_rdev, mp)
register struct vnode *nvp;
dev_t nvp_rdev;
struct mount *mp;
{
struct proc *p = curproc;
register struct vnode *vp;
struct vnode **vpp;
if (nvp->v_type != VBLK && nvp->v_type != VCHR)
return (NULLVP);
vpp = &speclisth[SPECHASH(nvp_rdev)];
loop:
simple_lock(&spechash_slock);
for (vp = *vpp; vp; vp = vp->v_specnext) {
simple_lock(&vp->v_interlock);
if (nvp_rdev != vp->v_rdev || nvp->v_type != vp->v_type) {
simple_unlock(&vp->v_interlock);
continue;
}
/*
* Alias, but not in use, so flush it out.
*/
if (vp->v_usecount == 0) {
simple_unlock(&spechash_slock);
vgonel(vp, p);
goto loop;
}
if (vget(vp, LK_EXCLUSIVE | LK_INTERLOCK, p)) {
simple_unlock(&spechash_slock);
goto loop;
}
break;
}
/*
* Common case is actually in the if statement
*/
if (vp == NULL || !(vp->v_tag == VT_NON && vp->v_type == VBLK)) {
MALLOC(nvp->v_specinfo, struct specinfo *,
sizeof(struct specinfo), M_VNODE, M_WAITOK);
nvp->v_rdev = nvp_rdev;
nvp->v_hashchain = vpp;
nvp->v_specnext = *vpp;
nvp->v_specmountpoint = NULL;
nvp->v_speclockf = NULL;
simple_unlock(&spechash_slock);
*vpp = nvp;
if (vp != NULLVP) {
nvp->v_flag |= VALIASED;
vp->v_flag |= VALIASED;
vput(vp);
}
return (NULLVP);
}
/*
* This code is the uncommon case. It is called in case
* we found an alias that was VT_NON && vtype of VBLK
* This means we found a block device that was created
* using bdevvp.
* An example of such a vnode is the root partition device vnode
* craeted in ffs_mountroot.
*
* The vnodes created by bdevvp should not be aliased (why?).
*/
simple_unlock(&spechash_slock);
VOP_UNLOCK(vp, 0, p);
simple_lock(&vp->v_interlock);
vclean(vp, 0, p);
vp->v_op = nvp->v_op;
vp->v_tag = nvp->v_tag;
nvp->v_type = VNON;
insmntque(vp, mp);
return (vp);
}
/*
* Grab a particular vnode from the free list, increment its
* reference count and lock it. The vnode lock bit is set the
* vnode is being eliminated in vgone. The process is awakened
* when the transition is completed, and an error returned to
* indicate that the vnode is no longer usable (possibly having
* been changed to a new file system type).
*/
int
vget(vp, flags, p)
struct vnode *vp;
int flags;
struct proc *p;
{
int error;
/*
* If the vnode is in the process of being cleaned out for
* another use, we wait for the cleaning to finish and then
* return failure. Cleaning is determined by checking that
* the VXLOCK flag is set.
*/
if ((flags & LK_INTERLOCK) == 0)
simple_lock(&vp->v_interlock);
if (vp->v_flag & VXLOCK) {
vp->v_flag |= VXWANT;
simple_unlock(&vp->v_interlock);
tsleep((caddr_t)vp, PINOD, "vget", 0);
return (ENOENT);
}
if ((vp->v_flag & VONFREELIST) && (vp->v_usecount == 0)) {
simple_lock(&vnode_free_list_slock);
if (vp->v_holdcnt > 0)
TAILQ_REMOVE(&vnode_hold_list, vp, v_freelist);
else
TAILQ_REMOVE(&vnode_free_list, vp, v_freelist);
simple_unlock(&vnode_free_list_slock);
vp->v_flag &= ~VONFREELIST;
}
vp->v_usecount++;
if (flags & LK_TYPE_MASK) {
if ((error = vn_lock(vp, flags | LK_INTERLOCK, p)) != 0) {
vp->v_usecount--;
if (vp->v_usecount == 0)
vputonfreelist(vp);
simple_unlock(&vp->v_interlock);
}
return (error);
}
simple_unlock(&vp->v_interlock);
return (0);
}
#ifdef DIAGNOSTIC
/*
* Vnode reference.
*/
void
vref(vp)
struct vnode *vp;
{
simple_lock(&vp->v_interlock);
if (vp->v_usecount <= 0)
panic("vref used where vget required");
vp->v_usecount++;
simple_unlock(&vp->v_interlock);
}
#endif /* DIAGNOSTIC */
static __inline__ void
vputonfreelist(vp)
struct vnode *vp;
{
struct freelst *lst;
/*
* insert at tail of LRU list
*/
#ifdef DIAGNOSTIC
if (vp->v_usecount != 0) {
panic("Use count is not zero!");
}
if (vp->v_flag & VONFREELIST) {
vprint ("vnode already on free list: ", vp);
panic ("vnode already on free list");
return;
}
#endif
vp->v_flag |= VONFREELIST;
simple_lock(&vnode_free_list_slock);
if (vp->v_holdcnt > 0)
lst = &vnode_hold_list;
else
lst = &vnode_free_list;
if (vp->v_type == VBAD)
TAILQ_INSERT_HEAD(lst, vp, v_freelist);
else
TAILQ_INSERT_TAIL(lst, vp, v_freelist);
simple_unlock(&vnode_free_list_slock);
}
/*
* vput(), just unlock and vrele()
*/
void
vput(vp)
register struct vnode *vp;
{
struct proc *p = curproc; /* XXX */
#ifdef DIAGNOSTIC
if (vp == NULL)
panic("vput: null vp");
#endif
simple_lock(&vp->v_interlock);
vp->v_usecount--;
if (vp->v_usecount > 0) {
simple_unlock(&vp->v_interlock);
VOP_UNLOCK(vp, 0, p);
return;
}
#ifdef DIAGNOSTIC
if (vp->v_usecount < 0 || vp->v_writecount != 0) {
vprint("vput: bad ref count", vp);
panic("vput: ref cnt");
}
#endif
vputonfreelist(vp);
VOP_INACTIVE(vp, p);
simple_unlock(&vp->v_interlock);
}
/*
* Vnode release - use for active VNODES.
* If count drops to zero, call inactive routine and return to freelist.
*/
void
vrele(vp)
register struct vnode *vp;
{
struct proc *p = curproc; /* XXX */
#ifdef DIAGNOSTIC
if (vp == NULL)
panic("vrele: null vp");
#endif
simple_lock(&vp->v_interlock);
vp->v_usecount--;
if (vp->v_usecount > 0) {
simple_unlock(&vp->v_interlock);
return;
}
#ifdef DIAGNOSTIC
if (vp->v_usecount < 0 || vp->v_writecount != 0) {
vprint("vrele: bad ref count", vp);
panic("vrele: ref cnt");
}
#endif
vputonfreelist(vp);
if (vn_lock(vp, LK_EXCLUSIVE|LK_INTERLOCK, p) == 0)
VOP_INACTIVE(vp, p);
}
#ifdef DIAGNOSTIC
/*
* Page or buffer structure gets a reference.
*/
void
vhold(vp)
register struct vnode *vp;
{
/*
* If it is on the freelist and the hold count is currently
* zero, move it to the hold list.
*/
simple_lock(&vp->v_interlock);
if ((vp->v_flag & VONFREELIST) &&
vp->v_holdcnt == 0 && vp->v_usecount == 0) {
simple_lock(&vnode_free_list_slock);
TAILQ_REMOVE(&vnode_free_list, vp, v_freelist);
TAILQ_INSERT_TAIL(&vnode_hold_list, vp, v_freelist);
simple_unlock(&vnode_free_list_slock);
}
vp->v_holdcnt++;
simple_unlock(&vp->v_interlock);
}
/*
* Page or buffer structure frees a reference.
*/
void
holdrele(vp)
register struct vnode *vp;
{
simple_lock(&vp->v_interlock);
if (vp->v_holdcnt <= 0)
panic("holdrele: holdcnt");
vp->v_holdcnt--;
/*
* If it is on the holdlist and the hold count drops to
* zero, move it to the free list.
*/
if ((vp->v_flag & VONFREELIST) &&
vp->v_holdcnt == 0 && vp->v_usecount == 0) {
simple_lock(&vnode_free_list_slock);
TAILQ_REMOVE(&vnode_hold_list, vp, v_freelist);
TAILQ_INSERT_TAIL(&vnode_free_list, vp, v_freelist);
simple_unlock(&vnode_free_list_slock);
}
simple_unlock(&vp->v_interlock);
}
#endif /* DIAGNOSTIC */
/*
* Remove any vnodes in the vnode table belonging to mount point mp.
*
* If MNT_NOFORCE is specified, there should not be any active ones,
* return error if any are found (nb: this is a user error, not a
* system error). If MNT_FORCE is specified, detach any active vnodes
* that are found.
*/
#ifdef DEBUG
int busyprt = 0; /* print out busy vnodes */
struct ctldebug debug1 = { "busyprt", &busyprt };
#endif
int
vflush(mp, skipvp, flags)
struct mount *mp;
struct vnode *skipvp;
int flags;
{
struct proc *p = curproc;
register struct vnode *vp, *nvp;
int busy = 0;
simple_lock(&mntvnode_slock);
loop:
for (vp = mp->mnt_vnodelist.lh_first; vp; vp = nvp) {
if (vp->v_mount != mp)
goto loop;
nvp = vp->v_mntvnodes.le_next;
/*
* Skip over a selected vnode.
*/
if (vp == skipvp)
continue;
simple_lock(&vp->v_interlock);
/*
* Skip over a vnodes marked VSYSTEM.
*/
if ((flags & SKIPSYSTEM) && (vp->v_flag & VSYSTEM)) {
simple_unlock(&vp->v_interlock);
continue;
}
/*
* If WRITECLOSE is set, only flush out regular file
* vnodes open for writing.
*/
if ((flags & WRITECLOSE) &&
(vp->v_writecount == 0 || vp->v_type != VREG)) {
simple_unlock(&vp->v_interlock);
continue;
}
/*
* With v_usecount == 0, all we need to do is clear
* out the vnode data structures and we are done.
*/
if (vp->v_usecount == 0) {
simple_unlock(&mntvnode_slock);
vgonel(vp, p);
simple_lock(&mntvnode_slock);
continue;
}
/*
* If FORCECLOSE is set, forcibly close the vnode.
* For block or character devices, revert to an
* anonymous device. For all other files, just kill them.
*/
if (flags & FORCECLOSE) {
simple_unlock(&mntvnode_slock);
if (vp->v_type != VBLK && vp->v_type != VCHR) {
vgonel(vp, p);
} else {
vclean(vp, 0, p);
vp->v_op = spec_vnodeop_p;
insmntque(vp, (struct mount *)0);
}
simple_lock(&mntvnode_slock);
continue;
}
#ifdef DEBUG
if (busyprt)
vprint("vflush: busy vnode", vp);
#endif
simple_unlock(&vp->v_interlock);
busy++;
}
simple_unlock(&mntvnode_slock);
if (busy)
return (EBUSY);
return (0);
}
/*
* Disassociate the underlying file system from a vnode.
* The vnode interlock is held on entry.
*/
void
vclean(vp, flags, p)
register struct vnode *vp;
int flags;
struct proc *p;
{
int active;
/*
* Check to see if the vnode is in use.
* If so we have to reference it before we clean it out
* so that its count cannot fall to zero and generate a
* race against ourselves to recycle it.
*/
if ((active = vp->v_usecount) != 0)
vp->v_usecount++;
/*
* Prevent the vnode from being recycled or
* brought into use while we clean it out.
*/
if (vp->v_flag & VXLOCK)
panic("vclean: deadlock");
vp->v_flag |= VXLOCK;
/*
* Even if the count is zero, the VOP_INACTIVE routine may still
* have the object locked while it cleans it out. The VOP_LOCK
* ensures that the VOP_INACTIVE routine is done with its work.
* For active vnodes, it ensures that no other activity can
* occur while the underlying object is being cleaned out.
*/
VOP_LOCK(vp, LK_DRAIN | LK_INTERLOCK, p);
/*
* Clean out any buffers associated with the vnode.
*/
if (flags & DOCLOSE)
vinvalbuf(vp, V_SAVE, NOCRED, p, 0, 0);
/*
* If purging an active vnode, it must be closed and
* deactivated before being reclaimed. Note that the
* VOP_INACTIVE will unlock the vnode
*/
if (active) {
if (flags & DOCLOSE)
VOP_CLOSE(vp, FNONBLOCK, NOCRED, p);
VOP_INACTIVE(vp, p);
} else {
/*
* Any other processes trying to obtain this lock must first
* wait for VXLOCK to clear, then call the new lock operation.
*/
VOP_UNLOCK(vp, 0, p);
}
/*
* Reclaim the vnode.
*/
if (VOP_RECLAIM(vp, p))
panic("vclean: cannot reclaim");
if (active) {
simple_lock(&vp->v_interlock);
vp->v_usecount--;
if (vp->v_usecount == 0) {
if (vp->v_holdcnt > 0)
panic("vclean: not clean");
vputonfreelist(vp);
}
simple_unlock(&vp->v_interlock);
}
cache_purge(vp);
if (vp->v_vnlock) {
if ((vp->v_vnlock->lk_flags & LK_DRAINED) == 0)
vprint("vclean: lock not drained", vp);
FREE(vp->v_vnlock, M_VNODE);
vp->v_vnlock = NULL;
}
/*
* Done with purge, notify sleepers of the grim news.
*/
vp->v_op = dead_vnodeop_p;
vp->v_tag = VT_NON;
vp->v_flag &= ~VXLOCK;
#ifdef DIAGNOSTIC
vp->v_flag &= ~VLOCKSWORK;
#endif
if (vp->v_flag & VXWANT) {
vp->v_flag &= ~VXWANT;
wakeup((caddr_t)vp);
}
}
/*
* Recycle an unused vnode to the front of the free list.
* Release the passed interlock if the vnode will be recycled.
*/
int
vrecycle(vp, inter_lkp, p)
struct vnode *vp;
struct simplelock *inter_lkp;
struct proc *p;
{
simple_lock(&vp->v_interlock);
if (vp->v_usecount == 0) {
if (inter_lkp)
simple_unlock(inter_lkp);
vgonel(vp, p);
return (1);
}
simple_unlock(&vp->v_interlock);
return (0);
}
/*
* Eliminate all activity associated with a vnode
* in preparation for reuse.
*/
void
vgone(vp)
register struct vnode *vp;
{
struct proc *p = curproc;
simple_lock (&vp->v_interlock);
vgonel(vp, p);
}
/*
* vgone, with the vp interlock held.
*/
void
vgonel(vp, p)
struct vnode *vp;
struct proc *p;
{
register struct vnode *vq;
struct vnode *vx;
/*
* If a vgone (or vclean) is already in progress,
* wait until it is done and return.
*/
if (vp->v_flag & VXLOCK) {
vp->v_flag |= VXWANT;
simple_unlock(&vp->v_interlock);
tsleep((caddr_t)vp, PINOD, "vgone", 0);
return;
}
/*
* Clean out the filesystem specific data.
*/
vclean(vp, DOCLOSE, p);
/*
* Delete from old mount point vnode list, if on one.
*/
if (vp->v_mount != NULL)
insmntque(vp, (struct mount *)0);
/*
* If special device, remove it from special device alias list
* if it is on one.
*/
if ((vp->v_type == VBLK || vp->v_type == VCHR) && vp->v_specinfo != 0) {
simple_lock(&spechash_slock);
if (*vp->v_hashchain == vp) {
*vp->v_hashchain = vp->v_specnext;
} else {
for (vq = *vp->v_hashchain; vq; vq = vq->v_specnext) {
if (vq->v_specnext != vp)
continue;
vq->v_specnext = vp->v_specnext;
break;
}
if (vq == NULL)
panic("missing bdev");
}
if (vp->v_flag & VALIASED) {
vx = NULL;
for (vq = *vp->v_hashchain; vq; vq = vq->v_specnext) {
if (vq->v_rdev != vp->v_rdev ||
vq->v_type != vp->v_type)
continue;
if (vx)
break;
vx = vq;
}
if (vx == NULL)
panic("missing alias");
if (vq == NULL)
vx->v_flag &= ~VALIASED;
vp->v_flag &= ~VALIASED;
}
simple_unlock(&spechash_slock);
FREE(vp->v_specinfo, M_VNODE);
vp->v_specinfo = NULL;
}
/*
* If it is on the freelist and not already at the head,
* move it to the head of the list.
*/
vp->v_type = VBAD;
if ((vp->v_flag & VONFREELIST) &&
vp->v_usecount == 0) {
simple_lock(&vnode_free_list_slock);
if (vp->v_holdcnt > 0)
panic("vgonel: not clean");
if (TAILQ_FIRST(&vnode_free_list) != vp) {
TAILQ_REMOVE(&vnode_free_list, vp, v_freelist);
TAILQ_INSERT_HEAD(&vnode_free_list, vp, v_freelist);
}
simple_unlock(&vnode_free_list_slock);
}
}
/*
* Lookup a vnode by device number.
*/
int
vfinddev(dev, type, vpp)
dev_t dev;
enum vtype type;
struct vnode **vpp;
{
register struct vnode *vp;
int rc =0;
simple_lock(&spechash_slock);
for (vp = speclisth[SPECHASH(dev)]; vp; vp = vp->v_specnext) {
if (dev != vp->v_rdev || type != vp->v_type)
continue;
*vpp = vp;
rc = 1;
break;
}
simple_unlock(&spechash_slock);
return (rc);
}
/*
* Calculate the total number of references to a special device.
*/
int
vcount(vp)
struct vnode *vp;
{
struct vnode *vq, *vnext;
int count;
loop:
if ((vp->v_flag & VALIASED) == 0)
return (vp->v_usecount);
simple_lock(&spechash_slock);
for (count = 0, vq = *vp->v_hashchain; vq; vq = vnext) {
vnext = vq->v_specnext;
if (vq->v_rdev != vp->v_rdev || vq->v_type != vp->v_type)
continue;
/*
* Alias, but not in use, so flush it out.
*/
if (vq->v_usecount == 0 && vq != vp) {
simple_unlock(&spechash_slock);
vgone(vq);
goto loop;
}
count += vq->v_usecount;
}
simple_unlock(&spechash_slock);
return (count);
}
/*
* Print out a description of a vnode.
*/
static char *typename[] =
{ "VNON", "VREG", "VDIR", "VBLK", "VCHR", "VLNK", "VSOCK", "VFIFO", "VBAD" };
void
vprint(label, vp)
char *label;
register struct vnode *vp;
{
char buf[64];
if (label != NULL)
printf("%s: ", label);
printf("type %s, usecount %d, writecount %d, holdcount %ld,",
typename[vp->v_type], vp->v_usecount, vp->v_writecount,
vp->v_holdcnt);
buf[0] = '\0';
if (vp->v_flag & VROOT)
strcat(buf, "|VROOT");
if (vp->v_flag & VTEXT)
strcat(buf, "|VTEXT");
if (vp->v_flag & VSYSTEM)
strcat(buf, "|VSYSTEM");
if (vp->v_flag & VXLOCK)
strcat(buf, "|VXLOCK");
if (vp->v_flag & VXWANT)
strcat(buf, "|VXWANT");
if (vp->v_flag & VBWAIT)
strcat(buf, "|VBWAIT");
if (vp->v_flag & VALIASED)
strcat(buf, "|VALIASED");
if (buf[0] != '\0')
printf(" flags (%s)", &buf[1]);
if (vp->v_data == NULL) {
printf("\n");
} else {
printf("\n\t");
VOP_PRINT(vp);
}
}
#ifdef DEBUG
/*
* List all of the locked vnodes in the system.
* Called when debugging the kernel.
*/
void
printlockedvnodes()
{
struct proc *p = curproc;
register struct mount *mp, *nmp;
register struct vnode *vp;
printf("Locked vnodes\n");
simple_lock(&mountlist_slock);
for (mp = CIRCLEQ_FIRST(&mountlist); mp != (void *)&mountlist;
mp = nmp) {
if (vfs_busy(mp, LK_NOWAIT, &mountlist_slock, p)) {
nmp = CIRCLEQ_NEXT(mp, mnt_list);
continue;
}
for (vp = mp->mnt_vnodelist.lh_first;
vp != NULL;
vp = vp->v_mntvnodes.le_next) {
if (VOP_ISLOCKED(vp))
vprint((char *)0, vp);
}
simple_lock(&mountlist_slock);
nmp = CIRCLEQ_NEXT(mp, mnt_list);
vfs_unbusy(mp, p);
}
simple_unlock(&mountlist_slock);
}
#endif
/*
* Top level filesystem related information gathering.
*/
int
vfs_sysctl(name, namelen, oldp, oldlenp, newp, newlen, p)
int *name;
u_int namelen;
void *oldp;
size_t *oldlenp;
void *newp;
size_t newlen;
struct proc *p;
{
struct vfsconf *vfsp;
/* all sysctl names at this level are at least name and field */
if (namelen < 2)
return (ENOTDIR); /* overloaded */
if (name[0] != VFS_GENERIC) {
for (vfsp = vfsconf; vfsp; vfsp = vfsp->vfc_next)
if (vfsp->vfc_typenum == name[0])
break;
if (vfsp == NULL)
return (EOPNOTSUPP);
return ((*vfsp->vfc_vfsops->vfs_sysctl)(&name[1], namelen - 1,
oldp, oldlenp, newp, newlen, p));
}
switch (name[1]) {
case VFS_MAXTYPENUM:
return (sysctl_rdint(oldp, oldlenp, newp, maxvfsconf));
case VFS_CONF:
if (namelen < 3)
return (ENOTDIR); /* overloaded */
for (vfsp = vfsconf; vfsp; vfsp = vfsp->vfc_next)
if (vfsp->vfc_typenum == name[2])
break;
if (vfsp == NULL)
return (EOPNOTSUPP);
return (sysctl_rdstruct(oldp, oldlenp, newp, vfsp,
sizeof(struct vfsconf)));
}
return (EOPNOTSUPP);
}
int kinfo_vdebug = 1;
int kinfo_vgetfailed;
#define KINFO_VNODESLOP 10
/*
* Dump vnode list (via sysctl).
* Copyout address of vnode followed by vnode.
*/
/* ARGSUSED */
int
sysctl_vnode(where, sizep, p)
char *where;
size_t *sizep;
struct proc *p;
{
register struct mount *mp, *nmp;
struct vnode *vp, *nvp;
register char *bp = where, *savebp;
char *ewhere;
int error;
#define VPTRSZ sizeof (struct vnode *)
#define VNODESZ sizeof (struct vnode)
if (where == NULL) {
*sizep = (numvnodes + KINFO_VNODESLOP) * (VPTRSZ + VNODESZ);
return (0);
}
ewhere = where + *sizep;
simple_lock(&mountlist_slock);
for (mp = mountlist.cqh_first; mp != (void *)&mountlist; mp = nmp) {
if (vfs_busy(mp, LK_NOWAIT, &mountlist_slock, p)) {
nmp = mp->mnt_list.cqe_next;
continue;
}
savebp = bp;
again:
for (vp = mp->mnt_vnodelist.lh_first;
vp != NULL;
vp = nvp) {
/*
* Check that the vp is still associated with
* this filesystem. RACE: could have been
* recycled onto the same filesystem.
*/
if (vp->v_mount != mp) {
simple_unlock(&mntvnode_slock);
if (kinfo_vdebug)
printf("kinfo: vp changed\n");
bp = savebp;
goto again;
}
nvp = vp->v_mntvnodes.le_next;
if (bp + VPTRSZ + VNODESZ > ewhere) {
simple_unlock(&mntvnode_slock);
*sizep = bp - where;
return (ENOMEM);
}
if ((error = copyout((caddr_t)&vp, bp, VPTRSZ)) ||
(error = copyout((caddr_t)vp, bp + VPTRSZ, VNODESZ)))
return (error);
bp += VPTRSZ + VNODESZ;
simple_lock(&mntvnode_slock);
}
simple_unlock(&mntvnode_slock);
simple_lock(&mountlist_slock);
nmp = mp->mnt_list.cqe_next;
vfs_unbusy(mp, p);
}
simple_unlock(&mountlist_slock);
*sizep = bp - where;
return (0);
}
/*
* Check to see if a filesystem is mounted on a block device.
*/
int
vfs_mountedon(vp)
register struct vnode *vp;
{
register struct vnode *vq;
int error = 0;
if (vp->v_specmountpoint != NULL)
return (EBUSY);
if (vp->v_flag & VALIASED) {
simple_lock(&spechash_slock);
for (vq = *vp->v_hashchain; vq; vq = vq->v_specnext) {
if (vq->v_rdev != vp->v_rdev ||
vq->v_type != vp->v_type)
continue;
if (vq->v_specmountpoint != NULL) {
error = EBUSY;
break;
}
}
simple_unlock(&spechash_slock);
}
return (error);
}
/*
* Build hash lists of net addresses and hang them off the mount point.
* Called by ufs_mount() to set up the lists of export addresses.
*/
int
vfs_hang_addrlist(mp, nep, argp)
struct mount *mp;
struct netexport *nep;
struct export_args *argp;
{
register struct netcred *np;
register struct radix_node_head *rnh;
register int i;
struct radix_node *rn;
struct sockaddr *saddr, *smask = 0;
struct domain *dom;
int error;
if (argp->ex_addrlen == 0) {
if (mp->mnt_flag & MNT_DEFEXPORTED)
return (EPERM);
np = &nep->ne_defexported;
np->netc_exflags = argp->ex_flags;
np->netc_anon = argp->ex_anon;
np->netc_anon.cr_ref = 1;
mp->mnt_flag |= MNT_DEFEXPORTED;
return (0);
}
i = sizeof(struct netcred) + argp->ex_addrlen + argp->ex_masklen;
np = (struct netcred *)malloc(i, M_NETADDR, M_WAITOK);
bzero((caddr_t)np, i);
saddr = (struct sockaddr *)(np + 1);
error = copyin(argp->ex_addr, (caddr_t)saddr, argp->ex_addrlen);
if (error)
goto out;
if (saddr->sa_len > argp->ex_addrlen)
saddr->sa_len = argp->ex_addrlen;
if (argp->ex_masklen) {
smask = (struct sockaddr *)((caddr_t)saddr + argp->ex_addrlen);
error = copyin(argp->ex_mask, (caddr_t)smask, argp->ex_masklen);
if (error)
goto out;
if (smask->sa_len > argp->ex_masklen)
smask->sa_len = argp->ex_masklen;
}
i = saddr->sa_family;
if ((rnh = nep->ne_rtable[i]) == 0) {
/*
* Seems silly to initialize every AF when most are not
* used, do so on demand here
*/
for (dom = domains; dom; dom = dom->dom_next)
if (dom->dom_family == i && dom->dom_rtattach) {
dom->dom_rtattach((void **)&nep->ne_rtable[i],
dom->dom_rtoffset);
break;
}
if ((rnh = nep->ne_rtable[i]) == 0) {
error = ENOBUFS;
goto out;
}
}
rn = (*rnh->rnh_addaddr)((caddr_t)saddr, (caddr_t)smask, rnh,
np->netc_rnodes);
if (rn == 0 || np != (struct netcred *)rn) { /* already exists */
error = EPERM;
goto out;
}
np->netc_exflags = argp->ex_flags;
np->netc_anon = argp->ex_anon;
np->netc_anon.cr_ref = 1;
return (0);
out:
free(np, M_NETADDR);
return (error);
}
/* ARGSUSED */
int
vfs_free_netcred(rn, w)
struct radix_node *rn;
void *w;
{
register struct radix_node_head *rnh = (struct radix_node_head *)w;
(*rnh->rnh_deladdr)(rn->rn_key, rn->rn_mask, rnh);
free((caddr_t)rn, M_NETADDR);
return (0);
}
/*
* Free the net address hash lists that are hanging off the mount points.
*/
void
vfs_free_addrlist(nep)
struct netexport *nep;
{
register int i;
register struct radix_node_head *rnh;
for (i = 0; i <= AF_MAX; i++)
if ((rnh = nep->ne_rtable[i]) != NULL) {
(*rnh->rnh_walktree)(rnh, vfs_free_netcred, rnh);
free((caddr_t)rnh, M_RTABLE);
nep->ne_rtable[i] = 0;
}
}
int
vfs_export(mp, nep, argp)
struct mount *mp;
struct netexport *nep;
struct export_args *argp;
{
int error;
if (argp->ex_flags & MNT_DELEXPORT) {
vfs_free_addrlist(nep);
mp->mnt_flag &= ~(MNT_EXPORTED | MNT_DEFEXPORTED);
}
if (argp->ex_flags & MNT_EXPORTED) {
if ((error = vfs_hang_addrlist(mp, nep, argp)) != 0)
return (error);
mp->mnt_flag |= MNT_EXPORTED;
}
return (0);
}
struct netcred *
vfs_export_lookup(mp, nep, nam)
register struct mount *mp;
struct netexport *nep;
struct mbuf *nam;
{
register struct netcred *np;
register struct radix_node_head *rnh;
struct sockaddr *saddr;
np = NULL;
if (mp->mnt_flag & MNT_EXPORTED) {
/*
* Lookup in the export list first.
*/
if (nam != NULL) {
saddr = mtod(nam, struct sockaddr *);
rnh = nep->ne_rtable[saddr->sa_family];
if (rnh != NULL) {
np = (struct netcred *)
(*rnh->rnh_matchaddr)((caddr_t)saddr,
rnh);
if (np && np->netc_rnodes->rn_flags & RNF_ROOT)
np = NULL;
}
}
/*
* If no address match, use the default if it exists.
*/
if (np == NULL && mp->mnt_flag & MNT_DEFEXPORTED)
np = &nep->ne_defexported;
}
return (np);
}
/*
* Do the usual access checking.
* file_mode, uid and gid are from the vnode in question,
* while acc_mode and cred are from the VOP_ACCESS parameter list
*/
int
vaccess(file_mode, uid, gid, acc_mode, cred)
mode_t file_mode;
uid_t uid;
gid_t gid;
mode_t acc_mode;
struct ucred *cred;
{
mode_t mask;
/* User id 0 always gets access. */
if (cred->cr_uid == 0)
return 0;
mask = 0;
/* Otherwise, check the owner. */
if (cred->cr_uid == uid) {
if (acc_mode & VEXEC)
mask |= S_IXUSR;
if (acc_mode & VREAD)
mask |= S_IRUSR;
if (acc_mode & VWRITE)
mask |= S_IWUSR;
return (file_mode & mask) == mask ? 0 : EACCES;
}
/* Otherwise, check the groups. */
if (cred->cr_gid == gid || groupmember(gid, cred)) {
if (acc_mode & VEXEC)
mask |= S_IXGRP;
if (acc_mode & VREAD)
mask |= S_IRGRP;
if (acc_mode & VWRITE)
mask |= S_IWGRP;
return (file_mode & mask) == mask ? 0 : EACCES;
}
/* Otherwise, check everyone else. */
if (acc_mode & VEXEC)
mask |= S_IXOTH;
if (acc_mode & VREAD)
mask |= S_IROTH;
if (acc_mode & VWRITE)
mask |= S_IWOTH;
return (file_mode & mask) == mask ? 0 : EACCES;
}
/*
* Unmount all file systems.
* We traverse the list in reverse order under the assumption that doing so
* will avoid needing to worry about dependencies.
*/
void
vfs_unmountall()
{
register struct mount *mp, *nmp;
int allerror, error, again = 1;
retry:
for (allerror = 0,
mp = mountlist.cqh_last; mp != (void *)&mountlist; mp = nmp) {
nmp = mp->mnt_list.cqe_prev;
if ((error = dounmount(mp, MNT_FORCE, curproc)) != 0) {
printf("unmount of %s failed with error %d\n",
mp->mnt_stat.f_mntonname, error);
allerror = 1;
}
}
if (allerror) {
printf("WARNING: some file systems would not unmount\n");
if (again) {
printf("retrying\n");
again = 0;
goto retry;
}
}
}
/*
* Sync and unmount file systems before shutting down.
*/
void
vfs_shutdown()
{
register struct buf *bp;
int iter, nbusy;
/* XXX Should suspend scheduling. */
(void) spl0();
printf("syncing disks... ");
if (panicstr == 0) {
/* Release inodes held by texts before update. */
vnode_pager_umount(NULL);
#ifdef notdef
vnshutdown();
#endif
/* Sync before unmount, in case we hang on something. */
sys_sync(&proc0, (void *)0, (register_t *)0);
/* Unmount file systems. */
vfs_unmountall();
}
/* Sync again after unmount, just in case. */
sys_sync(&proc0, (void *)0, (register_t *)0);
/* Wait for sync to finish. */
for (iter = 0; iter < 20; iter++) {
nbusy = 0;
for (bp = &buf[nbuf]; --bp >= buf; )
if ((bp->b_flags & (B_BUSY|B_INVAL)) == B_BUSY)
nbusy++;
if (nbusy == 0)
break;
printf("%d ", nbusy);
DELAY(40000 * iter);
}
if (nbusy)
printf("giving up\n");
else
printf("done\n");
}
/*
* posix file system related system variables.
*/
int
fs_posix_sysctl(name, namelen, oldp, oldlenp, newp, newlen, p)
int *name;
u_int namelen;
void *oldp;
size_t *oldlenp;
void *newp;
size_t newlen;
struct proc *p;
{
/* all sysctl names at this level are terminal */
if (namelen != 1)
return (ENOTDIR);
switch (name[0]) {
case FS_POSIX_SETUID:
if (newp && securelevel > 0)
return (EPERM);
return(sysctl_int(oldp, oldlenp, newp, newlen, &suid_clear));
default:
return (EOPNOTSUPP);
}
/* NOTREACHED */
}
/*
* file system related system variables.
*/
int
fs_sysctl(name, namelen, oldp, oldlenp, newp, newlen, p)
int *name;
u_int namelen;
void *oldp;
size_t *oldlenp;
void *newp;
size_t newlen;
struct proc *p;
{
sysctlfn *fn;
switch (name[0]) {
case FS_POSIX:
fn = fs_posix_sysctl;
break;
default:
return (EOPNOTSUPP);
}
return (*fn)(name + 1, namelen - 1, oldp, oldlenp, newp, newlen, p);
}
/*
* Routines dealing with vnodes and buffers
*/
/*
* Update outstanding I/O count and do wakeup if requested.
*
* Manipulates v_numoutput. Must be called at splbio()
*/
void
vwakeup(bp)
register struct buf *bp;
{
register struct vnode *vp;
bp->b_flags &= ~B_WRITEINPROG;
if ((vp = bp->b_vp) != NULL) {
if (--vp->v_numoutput < 0)
panic("vwakeup: neg numoutput");
if ((vp->v_flag & VBWAIT) && vp->v_numoutput <= 0) {
vp->v_flag &= ~VBWAIT;
wakeup((caddr_t)&vp->v_numoutput);
}
}
}
/*
* Flush out and invalidate all buffers associated with a vnode.
* Called with the underlying object locked.
*/
int
vinvalbuf(vp, flags, cred, p, slpflag, slptimeo)
register struct vnode *vp;
int flags;
struct ucred *cred;
struct proc *p;
int slpflag, slptimeo;
{
register struct buf *bp;
struct buf *nbp, *blist;
int s, error;
if (flags & V_SAVE) {
s = splbio();
while (vp->v_numoutput) {
vp->v_flag |= VBWAIT;
sleep((caddr_t)&vp->v_numoutput, PRIBIO + 1);
}
if (vp->v_dirtyblkhd.lh_first != NULL) {
splx(s);
if ((error = VOP_FSYNC(vp, cred, MNT_WAIT, p)) != 0)
return (error);
s = splbio();
if (vp->v_numoutput > 0 ||
vp->v_dirtyblkhd.lh_first != NULL)
panic("vinvalbuf: dirty bufs");
}
splx(s);
}
loop:
s = splbio();
for (;;) {
if ((blist = vp->v_cleanblkhd.lh_first) &&
(flags & V_SAVEMETA))
while (blist && blist->b_lblkno < 0)
blist = blist->b_vnbufs.le_next;
if (!blist && (blist = vp->v_dirtyblkhd.lh_first) &&
(flags & V_SAVEMETA))
while (blist && blist->b_lblkno < 0)
blist = blist->b_vnbufs.le_next;
if (!blist)
break;
for (bp = blist; bp; bp = nbp) {
nbp = bp->b_vnbufs.le_next;
if (flags & V_SAVEMETA && bp->b_lblkno < 0)
continue;
if (bp->b_flags & B_BUSY) {
bp->b_flags |= B_WANTED;
error = tsleep((caddr_t)bp,
slpflag | (PRIBIO + 1), "vinvalbuf",
slptimeo);
if (error) {
splx(s);
return (error);
}
break;
}
bp->b_flags |= B_BUSY | B_VFLUSH;
/*
* XXX Since there are no node locks for NFS, I believe
* there is a slight chance that a delayed write will
* occur while sleeping just above, so check for it.
*/
if ((bp->b_flags & B_DELWRI) && (flags & V_SAVE)) {
splx(s);
(void) VOP_BWRITE(bp);
goto loop;
}
bp->b_flags |= B_INVAL;
brelse(bp);
}
}
if (!(flags & V_SAVEMETA) &&
(vp->v_dirtyblkhd.lh_first || vp->v_cleanblkhd.lh_first))
panic("vinvalbuf: flush failed");
splx(s);
return (0);
}
void
vflushbuf(vp, sync)
register struct vnode *vp;
int sync;
{
register struct buf *bp, *nbp;
int s;
loop:
s = splbio();
for (bp = vp->v_dirtyblkhd.lh_first; bp; bp = nbp) {
nbp = bp->b_vnbufs.le_next;
if ((bp->b_flags & B_BUSY))
continue;
if ((bp->b_flags & B_DELWRI) == 0)
panic("vflushbuf: not dirty");
bp->b_flags |= B_BUSY | B_VFLUSH;
splx(s);
/*
* Wait for I/O associated with indirect blocks to complete,
* since there is no way to quickly wait for them below.
*/
if (bp->b_vp == vp || sync == 0)
(void) bawrite(bp);
else
(void) bwrite(bp);
goto loop;
}
if (sync == 0) {
splx(s);
return;
}
while (vp->v_numoutput) {
vp->v_flag |= VBWAIT;
tsleep((caddr_t)&vp->v_numoutput, PRIBIO + 1, "vflushbuf", 0);
}
splx(s);
if (vp->v_dirtyblkhd.lh_first != NULL) {
vprint("vflushbuf: dirty", vp);
goto loop;
}
}
/*
* Associate a buffer with a vnode.
*
* Manipulates buffer vnode queues. Must be called at splbio().
*/
void
bgetvp(vp, bp)
register struct vnode *vp;
register struct buf *bp;
{
if (bp->b_vp)
panic("bgetvp: not free");
VHOLD(vp);
bp->b_vp = vp;
if (vp->v_type == VBLK || vp->v_type == VCHR)
bp->b_dev = vp->v_rdev;
else
bp->b_dev = NODEV;
/*
* Insert onto list for new vnode.
*/
bufinsvn(bp, &vp->v_cleanblkhd);
}
/*
* Disassociate a buffer from a vnode.
*
* Manipulates vnode buffer queues. Must be called at splbio().
*/
void
brelvp(bp)
register struct buf *bp;
{
struct vnode *vp;
struct buf *wasdirty;
if ((vp = bp->b_vp) == (struct vnode *) 0)
panic("brelvp: NULL");
/*
* Delete from old vnode list, if on one.
*/
wasdirty = vp->v_dirtyblkhd.lh_first;
if (bp->b_vnbufs.le_next != NOLIST)
bufremvn(bp);
if (wasdirty && LIST_FIRST(&vp->v_dirtyblkhd) == NULL)
LIST_REMOVE(vp, v_synclist);
bp->b_vp = (struct vnode *) 0;
HOLDRELE(vp);
}
/*
* Reassign a buffer from one vnode to another. Used to assign buffers
* to the appropriate clean or dirty list and to add newly dirty vnodes
* to the appropriate filesystem syncer list.
*
* Manipulates vnode buffer queues. Must be called at splbio().
*/
void
reassignbuf(bp, newvp)
register struct buf *bp;
register struct vnode *newvp;
{
struct buflists *listheadp;
struct buf *wasdirty;
int delay;
if (newvp == NULL) {
printf("reassignbuf: NULL");
return;
}
/*
* Delete from old vnode list, if on one.
*/
wasdirty = newvp->v_dirtyblkhd.lh_first;
if (bp->b_vnbufs.le_next != NOLIST)
bufremvn(bp);
/*
* If dirty, put on list of dirty buffers;
* otherwise insert onto list of clean buffers.
*/
if ((bp->b_flags & B_DELWRI) == 0) {
listheadp = &newvp->v_cleanblkhd;
if (wasdirty && LIST_FIRST(&newvp->v_dirtyblkhd) == NULL)
LIST_REMOVE(newvp, v_synclist);
} else {
listheadp = &newvp->v_dirtyblkhd;
if (LIST_FIRST(listheadp) == NULL) {
switch (newvp->v_type) {
case VDIR:
delay = syncdelay / 3;
break;
case VBLK:
if (newvp->v_specmountpoint != NULL) {
delay = syncdelay / 2;
break;
}
/* fall through */
default:
delay = syncdelay;
}
vn_syncer_add_to_worklist(newvp, delay);
}
}
bufinsvn(bp, listheadp);
}
|