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
|
/*-
* Copyright (c) 1982, 1986, 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.
*
* Copyright (c) 2012 Konstantin Belousov <kib@FreeBSD.org>
* Copyright (c) 2013 The FreeBSD Foundation
*
* Portions of this software were developed by Konstantin Belousov
* under sponsorship from the FreeBSD Foundation.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 4. Neither the name of the University nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* @(#)vfs_vnops.c 8.2 (Berkeley) 1/21/94
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/fcntl.h>
#include <sys/file.h>
#include <sys/kdb.h>
#include <sys/stat.h>
#include <sys/priv.h>
#include <sys/proc.h>
#include <sys/limits.h>
#include <sys/lock.h>
#include <sys/mount.h>
#include <sys/mutex.h>
#include <sys/namei.h>
#include <sys/vnode.h>
#include <sys/bio.h>
#include <sys/buf.h>
#include <sys/filio.h>
#include <sys/resourcevar.h>
#include <sys/rwlock.h>
#include <sys/sx.h>
#include <sys/sysctl.h>
#include <sys/ttycom.h>
#include <sys/conf.h>
#include <sys/syslog.h>
#include <sys/unistd.h>
#include <security/audit/audit.h>
#include <security/mac/mac_framework.h>
#include <vm/vm.h>
#include <vm/vm_extern.h>
#include <vm/pmap.h>
#include <vm/vm_map.h>
#include <vm/vm_object.h>
#include <vm/vm_page.h>
static fo_rdwr_t vn_read;
static fo_rdwr_t vn_write;
static fo_rdwr_t vn_io_fault;
static fo_truncate_t vn_truncate;
static fo_ioctl_t vn_ioctl;
static fo_poll_t vn_poll;
static fo_kqfilter_t vn_kqfilter;
static fo_stat_t vn_statfile;
static fo_close_t vn_closefile;
struct fileops vnops = {
.fo_read = vn_io_fault,
.fo_write = vn_io_fault,
.fo_truncate = vn_truncate,
.fo_ioctl = vn_ioctl,
.fo_poll = vn_poll,
.fo_kqfilter = vn_kqfilter,
.fo_stat = vn_statfile,
.fo_close = vn_closefile,
.fo_chmod = vn_chmod,
.fo_chown = vn_chown,
.fo_flags = DFLAG_PASSABLE | DFLAG_SEEKABLE
};
int
vn_open(ndp, flagp, cmode, fp)
struct nameidata *ndp;
int *flagp, cmode;
struct file *fp;
{
struct thread *td = ndp->ni_cnd.cn_thread;
return (vn_open_cred(ndp, flagp, cmode, 0, td->td_ucred, fp));
}
/*
* Common code for vnode open operations via a name lookup.
* Lookup the vnode and invoke VOP_CREATE if needed.
* Check permissions, and call the VOP_OPEN or VOP_CREATE routine.
*
* Note that this does NOT free nameidata for the successful case,
* due to the NDINIT being done elsewhere.
*/
int
vn_open_cred(struct nameidata *ndp, int *flagp, int cmode, u_int vn_open_flags,
struct ucred *cred, struct file *fp)
{
struct vnode *vp;
struct mount *mp;
struct thread *td = ndp->ni_cnd.cn_thread;
struct vattr vat;
struct vattr *vap = &vat;
int fmode, error;
restart:
fmode = *flagp;
if (fmode & O_CREAT) {
ndp->ni_cnd.cn_nameiop = CREATE;
ndp->ni_cnd.cn_flags = ISOPEN | LOCKPARENT | LOCKLEAF;
if ((fmode & O_EXCL) == 0 && (fmode & O_NOFOLLOW) == 0)
ndp->ni_cnd.cn_flags |= FOLLOW;
if (!(vn_open_flags & VN_OPEN_NOAUDIT))
ndp->ni_cnd.cn_flags |= AUDITVNODE1;
if (vn_open_flags & VN_OPEN_NOCAPCHECK)
ndp->ni_cnd.cn_flags |= NOCAPCHECK;
bwillwrite();
if ((error = namei(ndp)) != 0)
return (error);
if (ndp->ni_vp == NULL) {
VATTR_NULL(vap);
vap->va_type = VREG;
vap->va_mode = cmode;
if (fmode & O_EXCL)
vap->va_vaflags |= VA_EXCLUSIVE;
if (vn_start_write(ndp->ni_dvp, &mp, V_NOWAIT) != 0) {
NDFREE(ndp, NDF_ONLY_PNBUF);
vput(ndp->ni_dvp);
if ((error = vn_start_write(NULL, &mp,
V_XSLEEP | PCATCH)) != 0)
return (error);
goto restart;
}
#ifdef MAC
error = mac_vnode_check_create(cred, ndp->ni_dvp,
&ndp->ni_cnd, vap);
if (error == 0)
#endif
error = VOP_CREATE(ndp->ni_dvp, &ndp->ni_vp,
&ndp->ni_cnd, vap);
vput(ndp->ni_dvp);
vn_finished_write(mp);
if (error) {
NDFREE(ndp, NDF_ONLY_PNBUF);
return (error);
}
fmode &= ~O_TRUNC;
vp = ndp->ni_vp;
} else {
if (ndp->ni_dvp == ndp->ni_vp)
vrele(ndp->ni_dvp);
else
vput(ndp->ni_dvp);
ndp->ni_dvp = NULL;
vp = ndp->ni_vp;
if (fmode & O_EXCL) {
error = EEXIST;
goto bad;
}
fmode &= ~O_CREAT;
}
} else {
ndp->ni_cnd.cn_nameiop = LOOKUP;
ndp->ni_cnd.cn_flags = ISOPEN |
((fmode & O_NOFOLLOW) ? NOFOLLOW : FOLLOW) | LOCKLEAF;
if (!(fmode & FWRITE))
ndp->ni_cnd.cn_flags |= LOCKSHARED;
if (!(vn_open_flags & VN_OPEN_NOAUDIT))
ndp->ni_cnd.cn_flags |= AUDITVNODE1;
if (vn_open_flags & VN_OPEN_NOCAPCHECK)
ndp->ni_cnd.cn_flags |= NOCAPCHECK;
if ((error = namei(ndp)) != 0)
return (error);
vp = ndp->ni_vp;
}
error = vn_open_vnode(vp, fmode, cred, td, fp);
if (error)
goto bad;
*flagp = fmode;
return (0);
bad:
NDFREE(ndp, NDF_ONLY_PNBUF);
vput(vp);
*flagp = fmode;
ndp->ni_vp = NULL;
return (error);
}
/*
* Common code for vnode open operations once a vnode is located.
* Check permissions, and call the VOP_OPEN routine.
*/
int
vn_open_vnode(struct vnode *vp, int fmode, struct ucred *cred,
struct thread *td, struct file *fp)
{
struct mount *mp;
accmode_t accmode;
struct flock lf;
int error, have_flock, lock_flags, type;
if (vp->v_type == VLNK)
return (EMLINK);
if (vp->v_type == VSOCK)
return (EOPNOTSUPP);
if (vp->v_type != VDIR && fmode & O_DIRECTORY)
return (ENOTDIR);
accmode = 0;
if (fmode & (FWRITE | O_TRUNC)) {
if (vp->v_type == VDIR)
return (EISDIR);
accmode |= VWRITE;
}
if (fmode & FREAD)
accmode |= VREAD;
if (fmode & FEXEC)
accmode |= VEXEC;
if ((fmode & O_APPEND) && (fmode & FWRITE))
accmode |= VAPPEND;
#ifdef MAC
error = mac_vnode_check_open(cred, vp, accmode);
if (error)
return (error);
#endif
if ((fmode & O_CREAT) == 0) {
if (accmode & VWRITE) {
error = vn_writechk(vp);
if (error)
return (error);
}
if (accmode) {
error = VOP_ACCESS(vp, accmode, cred, td);
if (error)
return (error);
}
}
if ((error = VOP_OPEN(vp, fmode, cred, td, fp)) != 0)
return (error);
if (fmode & (O_EXLOCK | O_SHLOCK)) {
KASSERT(fp != NULL, ("open with flock requires fp"));
lock_flags = VOP_ISLOCKED(vp);
VOP_UNLOCK(vp, 0);
lf.l_whence = SEEK_SET;
lf.l_start = 0;
lf.l_len = 0;
if (fmode & O_EXLOCK)
lf.l_type = F_WRLCK;
else
lf.l_type = F_RDLCK;
type = F_FLOCK;
if ((fmode & FNONBLOCK) == 0)
type |= F_WAIT;
error = VOP_ADVLOCK(vp, (caddr_t)fp, F_SETLK, &lf, type);
have_flock = (error == 0);
vn_lock(vp, lock_flags | LK_RETRY);
if (error == 0 && vp->v_iflag & VI_DOOMED)
error = ENOENT;
/*
* Another thread might have used this vnode as an
* executable while the vnode lock was dropped.
* Ensure the vnode is still able to be opened for
* writing after the lock has been obtained.
*/
if (error == 0 && accmode & VWRITE)
error = vn_writechk(vp);
if (error) {
VOP_UNLOCK(vp, 0);
if (have_flock) {
lf.l_whence = SEEK_SET;
lf.l_start = 0;
lf.l_len = 0;
lf.l_type = F_UNLCK;
(void) VOP_ADVLOCK(vp, fp, F_UNLCK, &lf,
F_FLOCK);
}
vn_start_write(vp, &mp, V_WAIT);
vn_lock(vp, lock_flags | LK_RETRY);
(void)VOP_CLOSE(vp, fmode, cred, td);
vn_finished_write(mp);
return (error);
}
fp->f_flag |= FHASLOCK;
}
if (fmode & FWRITE) {
VOP_ADD_WRITECOUNT(vp, 1);
CTR3(KTR_VFS, "%s: vp %p v_writecount increased to %d",
__func__, vp, vp->v_writecount);
}
ASSERT_VOP_LOCKED(vp, "vn_open_vnode");
return (0);
}
/*
* Check for write permissions on the specified vnode.
* Prototype text segments cannot be written.
*/
int
vn_writechk(vp)
register struct vnode *vp;
{
ASSERT_VOP_LOCKED(vp, "vn_writechk");
/*
* If there's shared text associated with
* the vnode, try to free it up once. If
* we fail, we can't allow writing.
*/
if (VOP_IS_TEXT(vp))
return (ETXTBSY);
return (0);
}
/*
* Vnode close call
*/
int
vn_close(vp, flags, file_cred, td)
register struct vnode *vp;
int flags;
struct ucred *file_cred;
struct thread *td;
{
struct mount *mp;
int error, lock_flags;
if (!(flags & FWRITE) && vp->v_mount != NULL &&
vp->v_mount->mnt_kern_flag & MNTK_EXTENDED_SHARED)
lock_flags = LK_SHARED;
else
lock_flags = LK_EXCLUSIVE;
vn_start_write(vp, &mp, V_WAIT);
vn_lock(vp, lock_flags | LK_RETRY);
if (flags & FWRITE) {
VNASSERT(vp->v_writecount > 0, vp,
("vn_close: negative writecount"));
VOP_ADD_WRITECOUNT(vp, -1);
CTR3(KTR_VFS, "%s: vp %p v_writecount decreased to %d",
__func__, vp, vp->v_writecount);
}
error = VOP_CLOSE(vp, flags, file_cred, td);
vput(vp);
vn_finished_write(mp);
return (error);
}
/*
* Heuristic to detect sequential operation.
*/
static int
sequential_heuristic(struct uio *uio, struct file *fp)
{
if (atomic_load_acq_int(&(fp->f_flag)) & FRDAHEAD)
return (fp->f_seqcount << IO_SEQSHIFT);
/*
* Offset 0 is handled specially. open() sets f_seqcount to 1 so
* that the first I/O is normally considered to be slightly
* sequential. Seeking to offset 0 doesn't change sequentiality
* unless previous seeks have reduced f_seqcount to 0, in which
* case offset 0 is not special.
*/
if ((uio->uio_offset == 0 && fp->f_seqcount > 0) ||
uio->uio_offset == fp->f_nextoff) {
/*
* f_seqcount is in units of fixed-size blocks so that it
* depends mainly on the amount of sequential I/O and not
* much on the number of sequential I/O's. The fixed size
* of 16384 is hard-coded here since it is (not quite) just
* a magic size that works well here. This size is more
* closely related to the best I/O size for real disks than
* to any block size used by software.
*/
fp->f_seqcount += howmany(uio->uio_resid, 16384);
if (fp->f_seqcount > IO_SEQMAX)
fp->f_seqcount = IO_SEQMAX;
return (fp->f_seqcount << IO_SEQSHIFT);
}
/* Not sequential. Quickly draw-down sequentiality. */
if (fp->f_seqcount > 1)
fp->f_seqcount = 1;
else
fp->f_seqcount = 0;
return (0);
}
/*
* Package up an I/O request on a vnode into a uio and do it.
*/
int
vn_rdwr(enum uio_rw rw, struct vnode *vp, void *base, int len, off_t offset,
enum uio_seg segflg, int ioflg, struct ucred *active_cred,
struct ucred *file_cred, ssize_t *aresid, struct thread *td)
{
struct uio auio;
struct iovec aiov;
struct mount *mp;
struct ucred *cred;
void *rl_cookie;
int error, lock_flags;
auio.uio_iov = &aiov;
auio.uio_iovcnt = 1;
aiov.iov_base = base;
aiov.iov_len = len;
auio.uio_resid = len;
auio.uio_offset = offset;
auio.uio_segflg = segflg;
auio.uio_rw = rw;
auio.uio_td = td;
error = 0;
if ((ioflg & IO_NODELOCKED) == 0) {
if (rw == UIO_READ) {
rl_cookie = vn_rangelock_rlock(vp, offset,
offset + len);
} else {
rl_cookie = vn_rangelock_wlock(vp, offset,
offset + len);
}
mp = NULL;
if (rw == UIO_WRITE) {
if (vp->v_type != VCHR &&
(error = vn_start_write(vp, &mp, V_WAIT | PCATCH))
!= 0)
goto out;
if (MNT_SHARED_WRITES(mp) ||
((mp == NULL) && MNT_SHARED_WRITES(vp->v_mount)))
lock_flags = LK_SHARED;
else
lock_flags = LK_EXCLUSIVE;
} else
lock_flags = LK_SHARED;
vn_lock(vp, lock_flags | LK_RETRY);
} else
rl_cookie = NULL;
ASSERT_VOP_LOCKED(vp, "IO_NODELOCKED with no vp lock held");
#ifdef MAC
if ((ioflg & IO_NOMACCHECK) == 0) {
if (rw == UIO_READ)
error = mac_vnode_check_read(active_cred, file_cred,
vp);
else
error = mac_vnode_check_write(active_cred, file_cred,
vp);
}
#endif
if (error == 0) {
if (file_cred != NULL)
cred = file_cred;
else
cred = active_cred;
if (rw == UIO_READ)
error = VOP_READ(vp, &auio, ioflg, cred);
else
error = VOP_WRITE(vp, &auio, ioflg, cred);
}
if (aresid)
*aresid = auio.uio_resid;
else
if (auio.uio_resid && error == 0)
error = EIO;
if ((ioflg & IO_NODELOCKED) == 0) {
VOP_UNLOCK(vp, 0);
if (mp != NULL)
vn_finished_write(mp);
}
out:
if (rl_cookie != NULL)
vn_rangelock_unlock(vp, rl_cookie);
return (error);
}
/*
* Package up an I/O request on a vnode into a uio and do it. The I/O
* request is split up into smaller chunks and we try to avoid saturating
* the buffer cache while potentially holding a vnode locked, so we
* check bwillwrite() before calling vn_rdwr(). We also call kern_yield()
* to give other processes a chance to lock the vnode (either other processes
* core'ing the same binary, or unrelated processes scanning the directory).
*/
int
vn_rdwr_inchunks(rw, vp, base, len, offset, segflg, ioflg, active_cred,
file_cred, aresid, td)
enum uio_rw rw;
struct vnode *vp;
void *base;
size_t len;
off_t offset;
enum uio_seg segflg;
int ioflg;
struct ucred *active_cred;
struct ucred *file_cred;
size_t *aresid;
struct thread *td;
{
int error = 0;
ssize_t iaresid;
do {
int chunk;
/*
* Force `offset' to a multiple of MAXBSIZE except possibly
* for the first chunk, so that filesystems only need to
* write full blocks except possibly for the first and last
* chunks.
*/
chunk = MAXBSIZE - (uoff_t)offset % MAXBSIZE;
if (chunk > len)
chunk = len;
if (rw != UIO_READ && vp->v_type == VREG)
bwillwrite();
iaresid = 0;
error = vn_rdwr(rw, vp, base, chunk, offset, segflg,
ioflg, active_cred, file_cred, &iaresid, td);
len -= chunk; /* aresid calc already includes length */
if (error)
break;
offset += chunk;
base = (char *)base + chunk;
kern_yield(PRI_USER);
} while (len);
if (aresid)
*aresid = len + iaresid;
return (error);
}
off_t
foffset_lock(struct file *fp, int flags)
{
struct mtx *mtxp;
off_t res;
KASSERT((flags & FOF_OFFSET) == 0, ("FOF_OFFSET passed"));
#if OFF_MAX <= LONG_MAX
/*
* Caller only wants the current f_offset value. Assume that
* the long and shorter integer types reads are atomic.
*/
if ((flags & FOF_NOLOCK) != 0)
return (fp->f_offset);
#endif
/*
* According to McKusick the vn lock was protecting f_offset here.
* It is now protected by the FOFFSET_LOCKED flag.
*/
mtxp = mtx_pool_find(mtxpool_sleep, fp);
mtx_lock(mtxp);
if ((flags & FOF_NOLOCK) == 0) {
while (fp->f_vnread_flags & FOFFSET_LOCKED) {
fp->f_vnread_flags |= FOFFSET_LOCK_WAITING;
msleep(&fp->f_vnread_flags, mtxp, PUSER -1,
"vofflock", 0);
}
fp->f_vnread_flags |= FOFFSET_LOCKED;
}
res = fp->f_offset;
mtx_unlock(mtxp);
return (res);
}
void
foffset_unlock(struct file *fp, off_t val, int flags)
{
struct mtx *mtxp;
KASSERT((flags & FOF_OFFSET) == 0, ("FOF_OFFSET passed"));
#if OFF_MAX <= LONG_MAX
if ((flags & FOF_NOLOCK) != 0) {
if ((flags & FOF_NOUPDATE) == 0)
fp->f_offset = val;
if ((flags & FOF_NEXTOFF) != 0)
fp->f_nextoff = val;
return;
}
#endif
mtxp = mtx_pool_find(mtxpool_sleep, fp);
mtx_lock(mtxp);
if ((flags & FOF_NOUPDATE) == 0)
fp->f_offset = val;
if ((flags & FOF_NEXTOFF) != 0)
fp->f_nextoff = val;
if ((flags & FOF_NOLOCK) == 0) {
KASSERT((fp->f_vnread_flags & FOFFSET_LOCKED) != 0,
("Lost FOFFSET_LOCKED"));
if (fp->f_vnread_flags & FOFFSET_LOCK_WAITING)
wakeup(&fp->f_vnread_flags);
fp->f_vnread_flags = 0;
}
mtx_unlock(mtxp);
}
void
foffset_lock_uio(struct file *fp, struct uio *uio, int flags)
{
if ((flags & FOF_OFFSET) == 0)
uio->uio_offset = foffset_lock(fp, flags);
}
void
foffset_unlock_uio(struct file *fp, struct uio *uio, int flags)
{
if ((flags & FOF_OFFSET) == 0)
foffset_unlock(fp, uio->uio_offset, flags);
}
static int
get_advice(struct file *fp, struct uio *uio)
{
struct mtx *mtxp;
int ret;
ret = POSIX_FADV_NORMAL;
if (fp->f_advice == NULL)
return (ret);
mtxp = mtx_pool_find(mtxpool_sleep, fp);
mtx_lock(mtxp);
if (uio->uio_offset >= fp->f_advice->fa_start &&
uio->uio_offset + uio->uio_resid <= fp->f_advice->fa_end)
ret = fp->f_advice->fa_advice;
mtx_unlock(mtxp);
return (ret);
}
/*
* File table vnode read routine.
*/
static int
vn_read(fp, uio, active_cred, flags, td)
struct file *fp;
struct uio *uio;
struct ucred *active_cred;
int flags;
struct thread *td;
{
struct vnode *vp;
struct mtx *mtxp;
int error, ioflag;
int advice;
off_t offset, start, end;
KASSERT(uio->uio_td == td, ("uio_td %p is not td %p",
uio->uio_td, td));
KASSERT(flags & FOF_OFFSET, ("No FOF_OFFSET"));
vp = fp->f_vnode;
ioflag = 0;
if (fp->f_flag & FNONBLOCK)
ioflag |= IO_NDELAY;
if (fp->f_flag & O_DIRECT)
ioflag |= IO_DIRECT;
advice = get_advice(fp, uio);
vn_lock(vp, LK_SHARED | LK_RETRY);
switch (advice) {
case POSIX_FADV_NORMAL:
case POSIX_FADV_SEQUENTIAL:
case POSIX_FADV_NOREUSE:
ioflag |= sequential_heuristic(uio, fp);
break;
case POSIX_FADV_RANDOM:
/* Disable read-ahead for random I/O. */
break;
}
offset = uio->uio_offset;
#ifdef MAC
error = mac_vnode_check_read(active_cred, fp->f_cred, vp);
if (error == 0)
#endif
error = VOP_READ(vp, uio, ioflag, fp->f_cred);
fp->f_nextoff = uio->uio_offset;
VOP_UNLOCK(vp, 0);
if (error == 0 && advice == POSIX_FADV_NOREUSE &&
offset != uio->uio_offset) {
/*
* Use POSIX_FADV_DONTNEED to flush clean pages and
* buffers for the backing file after a
* POSIX_FADV_NOREUSE read(2). To optimize the common
* case of using POSIX_FADV_NOREUSE with sequential
* access, track the previous implicit DONTNEED
* request and grow this request to include the
* current read(2) in addition to the previous
* DONTNEED. With purely sequential access this will
* cause the DONTNEED requests to continously grow to
* cover all of the previously read regions of the
* file. This allows filesystem blocks that are
* accessed by multiple calls to read(2) to be flushed
* once the last read(2) finishes.
*/
start = offset;
end = uio->uio_offset - 1;
mtxp = mtx_pool_find(mtxpool_sleep, fp);
mtx_lock(mtxp);
if (fp->f_advice != NULL &&
fp->f_advice->fa_advice == POSIX_FADV_NOREUSE) {
if (start != 0 && fp->f_advice->fa_prevend + 1 == start)
start = fp->f_advice->fa_prevstart;
else if (fp->f_advice->fa_prevstart != 0 &&
fp->f_advice->fa_prevstart == end + 1)
end = fp->f_advice->fa_prevend;
fp->f_advice->fa_prevstart = start;
fp->f_advice->fa_prevend = end;
}
mtx_unlock(mtxp);
error = VOP_ADVISE(vp, start, end, POSIX_FADV_DONTNEED);
}
return (error);
}
/*
* File table vnode write routine.
*/
static int
vn_write(fp, uio, active_cred, flags, td)
struct file *fp;
struct uio *uio;
struct ucred *active_cred;
int flags;
struct thread *td;
{
struct vnode *vp;
struct mount *mp;
struct mtx *mtxp;
int error, ioflag, lock_flags;
int advice;
off_t offset, start, end;
KASSERT(uio->uio_td == td, ("uio_td %p is not td %p",
uio->uio_td, td));
KASSERT(flags & FOF_OFFSET, ("No FOF_OFFSET"));
vp = fp->f_vnode;
if (vp->v_type == VREG)
bwillwrite();
ioflag = IO_UNIT;
if (vp->v_type == VREG && (fp->f_flag & O_APPEND))
ioflag |= IO_APPEND;
if (fp->f_flag & FNONBLOCK)
ioflag |= IO_NDELAY;
if (fp->f_flag & O_DIRECT)
ioflag |= IO_DIRECT;
if ((fp->f_flag & O_FSYNC) ||
(vp->v_mount && (vp->v_mount->mnt_flag & MNT_SYNCHRONOUS)))
ioflag |= IO_SYNC;
mp = NULL;
if (vp->v_type != VCHR &&
(error = vn_start_write(vp, &mp, V_WAIT | PCATCH)) != 0)
goto unlock;
advice = get_advice(fp, uio);
if (MNT_SHARED_WRITES(mp) ||
(mp == NULL && MNT_SHARED_WRITES(vp->v_mount))) {
lock_flags = LK_SHARED;
} else {
lock_flags = LK_EXCLUSIVE;
}
vn_lock(vp, lock_flags | LK_RETRY);
switch (advice) {
case POSIX_FADV_NORMAL:
case POSIX_FADV_SEQUENTIAL:
case POSIX_FADV_NOREUSE:
ioflag |= sequential_heuristic(uio, fp);
break;
case POSIX_FADV_RANDOM:
/* XXX: Is this correct? */
break;
}
offset = uio->uio_offset;
#ifdef MAC
error = mac_vnode_check_write(active_cred, fp->f_cred, vp);
if (error == 0)
#endif
error = VOP_WRITE(vp, uio, ioflag, fp->f_cred);
fp->f_nextoff = uio->uio_offset;
VOP_UNLOCK(vp, 0);
if (vp->v_type != VCHR)
vn_finished_write(mp);
if (error == 0 && advice == POSIX_FADV_NOREUSE &&
offset != uio->uio_offset) {
/*
* Use POSIX_FADV_DONTNEED to flush clean pages and
* buffers for the backing file after a
* POSIX_FADV_NOREUSE write(2). To optimize the
* common case of using POSIX_FADV_NOREUSE with
* sequential access, track the previous implicit
* DONTNEED request and grow this request to include
* the current write(2) in addition to the previous
* DONTNEED. With purely sequential access this will
* cause the DONTNEED requests to continously grow to
* cover all of the previously written regions of the
* file.
*
* Note that the blocks just written are almost
* certainly still dirty, so this only works when
* VOP_ADVISE() calls from subsequent writes push out
* the data written by this write(2) once the backing
* buffers are clean. However, as compared to forcing
* IO_DIRECT, this gives much saner behavior. Write
* clustering is still allowed, and clean pages are
* merely moved to the cache page queue rather than
* outright thrown away. This means a subsequent
* read(2) can still avoid hitting the disk if the
* pages have not been reclaimed.
*
* This does make POSIX_FADV_NOREUSE largely useless
* with non-sequential access. However, sequential
* access is the more common use case and the flag is
* merely advisory.
*/
start = offset;
end = uio->uio_offset - 1;
mtxp = mtx_pool_find(mtxpool_sleep, fp);
mtx_lock(mtxp);
if (fp->f_advice != NULL &&
fp->f_advice->fa_advice == POSIX_FADV_NOREUSE) {
if (start != 0 && fp->f_advice->fa_prevend + 1 == start)
start = fp->f_advice->fa_prevstart;
else if (fp->f_advice->fa_prevstart != 0 &&
fp->f_advice->fa_prevstart == end + 1)
end = fp->f_advice->fa_prevend;
fp->f_advice->fa_prevstart = start;
fp->f_advice->fa_prevend = end;
}
mtx_unlock(mtxp);
error = VOP_ADVISE(vp, start, end, POSIX_FADV_DONTNEED);
}
unlock:
return (error);
}
static const int io_hold_cnt = 16;
static int vn_io_fault_enable = 1;
SYSCTL_INT(_debug, OID_AUTO, vn_io_fault_enable, CTLFLAG_RW,
&vn_io_fault_enable, 0, "Enable vn_io_fault lock avoidance");
static u_long vn_io_faults_cnt;
SYSCTL_ULONG(_debug, OID_AUTO, vn_io_faults, CTLFLAG_RD,
&vn_io_faults_cnt, 0, "Count of vn_io_fault lock avoidance triggers");
/*
* The vn_io_fault() is a wrapper around vn_read() and vn_write() to
* prevent the following deadlock:
*
* Assume that the thread A reads from the vnode vp1 into userspace
* buffer buf1 backed by the pages of vnode vp2. If a page in buf1 is
* currently not resident, then system ends up with the call chain
* vn_read() -> VOP_READ(vp1) -> uiomove() -> [Page Fault] ->
* vm_fault(buf1) -> vnode_pager_getpages(vp2) -> VOP_GETPAGES(vp2)
* which establishes lock order vp1->vn_lock, then vp2->vn_lock.
* If, at the same time, thread B reads from vnode vp2 into buffer buf2
* backed by the pages of vnode vp1, and some page in buf2 is not
* resident, we get a reversed order vp2->vn_lock, then vp1->vn_lock.
*
* To prevent the lock order reversal and deadlock, vn_io_fault() does
* not allow page faults to happen during VOP_READ() or VOP_WRITE().
* Instead, it first tries to do the whole range i/o with pagefaults
* disabled. If all pages in the i/o buffer are resident and mapped,
* VOP will succeed (ignoring the genuine filesystem errors).
* Otherwise, we get back EFAULT, and vn_io_fault() falls back to do
* i/o in chunks, with all pages in the chunk prefaulted and held
* using vm_fault_quick_hold_pages().
*
* Filesystems using this deadlock avoidance scheme should use the
* array of the held pages from uio, saved in the curthread->td_ma,
* instead of doing uiomove(). A helper function
* vn_io_fault_uiomove() converts uiomove request into
* uiomove_fromphys() over td_ma array.
*
* Since vnode locks do not cover the whole i/o anymore, rangelocks
* make the current i/o request atomic with respect to other i/os and
* truncations.
*/
static int
vn_io_fault(struct file *fp, struct uio *uio, struct ucred *active_cred,
int flags, struct thread *td)
{
vm_page_t ma[io_hold_cnt + 2];
struct uio *uio_clone, short_uio;
struct iovec short_iovec[1];
fo_rdwr_t *doio;
struct vnode *vp;
void *rl_cookie;
struct mount *mp;
vm_page_t *prev_td_ma;
int cnt, error, save, saveheld, prev_td_ma_cnt;
vm_offset_t addr, end;
vm_prot_t prot;
size_t len, resid;
ssize_t adv;
if (uio->uio_rw == UIO_READ)
doio = vn_read;
else
doio = vn_write;
vp = fp->f_vnode;
foffset_lock_uio(fp, uio, flags);
if (uio->uio_segflg != UIO_USERSPACE || vp->v_type != VREG ||
((mp = vp->v_mount) != NULL &&
(mp->mnt_kern_flag & MNTK_NO_IOPF) == 0) ||
!vn_io_fault_enable) {
error = doio(fp, uio, active_cred, flags | FOF_OFFSET, td);
goto out_last;
}
/*
* The UFS follows IO_UNIT directive and replays back both
* uio_offset and uio_resid if an error is encountered during the
* operation. But, since the iovec may be already advanced,
* uio is still in an inconsistent state.
*
* Cache a copy of the original uio, which is advanced to the redo
* point using UIO_NOCOPY below.
*/
uio_clone = cloneuio(uio);
resid = uio->uio_resid;
short_uio.uio_segflg = UIO_USERSPACE;
short_uio.uio_rw = uio->uio_rw;
short_uio.uio_td = uio->uio_td;
if (uio->uio_rw == UIO_READ) {
prot = VM_PROT_WRITE;
rl_cookie = vn_rangelock_rlock(vp, uio->uio_offset,
uio->uio_offset + uio->uio_resid);
} else {
prot = VM_PROT_READ;
if ((fp->f_flag & O_APPEND) != 0 || (flags & FOF_OFFSET) == 0)
/* For appenders, punt and lock the whole range. */
rl_cookie = vn_rangelock_wlock(vp, 0, OFF_MAX);
else
rl_cookie = vn_rangelock_wlock(vp, uio->uio_offset,
uio->uio_offset + uio->uio_resid);
}
save = vm_fault_disable_pagefaults();
error = doio(fp, uio, active_cred, flags | FOF_OFFSET, td);
if (error != EFAULT)
goto out;
atomic_add_long(&vn_io_faults_cnt, 1);
uio_clone->uio_segflg = UIO_NOCOPY;
uiomove(NULL, resid - uio->uio_resid, uio_clone);
uio_clone->uio_segflg = uio->uio_segflg;
saveheld = curthread_pflags_set(TDP_UIOHELD);
prev_td_ma = td->td_ma;
prev_td_ma_cnt = td->td_ma_cnt;
while (uio_clone->uio_resid != 0) {
len = uio_clone->uio_iov->iov_len;
if (len == 0) {
KASSERT(uio_clone->uio_iovcnt >= 1,
("iovcnt underflow"));
uio_clone->uio_iov++;
uio_clone->uio_iovcnt--;
continue;
}
addr = (vm_offset_t)uio_clone->uio_iov->iov_base;
end = round_page(addr + len);
cnt = howmany(end - trunc_page(addr), PAGE_SIZE);
/*
* A perfectly misaligned address and length could cause
* both the start and the end of the chunk to use partial
* page. +2 accounts for such a situation.
*/
if (cnt > io_hold_cnt + 2) {
len = io_hold_cnt * PAGE_SIZE;
KASSERT(howmany(round_page(addr + len) -
trunc_page(addr), PAGE_SIZE) <= io_hold_cnt + 2,
("cnt overflow"));
}
cnt = vm_fault_quick_hold_pages(&td->td_proc->p_vmspace->vm_map,
addr, len, prot, ma, io_hold_cnt + 2);
if (cnt == -1) {
error = EFAULT;
break;
}
short_uio.uio_iov = &short_iovec[0];
short_iovec[0].iov_base = (void *)addr;
short_uio.uio_iovcnt = 1;
short_uio.uio_resid = short_iovec[0].iov_len = len;
short_uio.uio_offset = uio_clone->uio_offset;
td->td_ma = ma;
td->td_ma_cnt = cnt;
error = doio(fp, &short_uio, active_cred, flags | FOF_OFFSET,
td);
vm_page_unhold_pages(ma, cnt);
adv = len - short_uio.uio_resid;
uio_clone->uio_iov->iov_base =
(char *)uio_clone->uio_iov->iov_base + adv;
uio_clone->uio_iov->iov_len -= adv;
uio_clone->uio_resid -= adv;
uio_clone->uio_offset += adv;
uio->uio_resid -= adv;
uio->uio_offset += adv;
if (error != 0 || adv == 0)
break;
}
td->td_ma = prev_td_ma;
td->td_ma_cnt = prev_td_ma_cnt;
curthread_pflags_restore(saveheld);
out:
vm_fault_enable_pagefaults(save);
vn_rangelock_unlock(vp, rl_cookie);
free(uio_clone, M_IOV);
out_last:
foffset_unlock_uio(fp, uio, flags);
return (error);
}
/*
* Helper function to perform the requested uiomove operation using
* the held pages for io->uio_iov[0].iov_base buffer instead of
* copyin/copyout. Access to the pages with uiomove_fromphys()
* instead of iov_base prevents page faults that could occur due to
* pmap_collect() invalidating the mapping created by
* vm_fault_quick_hold_pages(), or pageout daemon, page laundry or
* object cleanup revoking the write access from page mappings.
*
* Filesystems specified MNTK_NO_IOPF shall use vn_io_fault_uiomove()
* instead of plain uiomove().
*/
int
vn_io_fault_uiomove(char *data, int xfersize, struct uio *uio)
{
struct uio transp_uio;
struct iovec transp_iov[1];
struct thread *td;
size_t adv;
int error, pgadv;
td = curthread;
if ((td->td_pflags & TDP_UIOHELD) == 0 ||
uio->uio_segflg != UIO_USERSPACE)
return (uiomove(data, xfersize, uio));
KASSERT(uio->uio_iovcnt == 1, ("uio_iovcnt %d", uio->uio_iovcnt));
transp_iov[0].iov_base = data;
transp_uio.uio_iov = &transp_iov[0];
transp_uio.uio_iovcnt = 1;
if (xfersize > uio->uio_resid)
xfersize = uio->uio_resid;
transp_uio.uio_resid = transp_iov[0].iov_len = xfersize;
transp_uio.uio_offset = 0;
transp_uio.uio_segflg = UIO_SYSSPACE;
/*
* Since transp_iov points to data, and td_ma page array
* corresponds to original uio->uio_iov, we need to invert the
* direction of the i/o operation as passed to
* uiomove_fromphys().
*/
switch (uio->uio_rw) {
case UIO_WRITE:
transp_uio.uio_rw = UIO_READ;
break;
case UIO_READ:
transp_uio.uio_rw = UIO_WRITE;
break;
}
transp_uio.uio_td = uio->uio_td;
error = uiomove_fromphys(td->td_ma,
((vm_offset_t)uio->uio_iov->iov_base) & PAGE_MASK,
xfersize, &transp_uio);
adv = xfersize - transp_uio.uio_resid;
pgadv =
(((vm_offset_t)uio->uio_iov->iov_base + adv) >> PAGE_SHIFT) -
(((vm_offset_t)uio->uio_iov->iov_base) >> PAGE_SHIFT);
td->td_ma += pgadv;
KASSERT(td->td_ma_cnt >= pgadv, ("consumed pages %d %d", td->td_ma_cnt,
pgadv));
td->td_ma_cnt -= pgadv;
uio->uio_iov->iov_base = (char *)uio->uio_iov->iov_base + adv;
uio->uio_iov->iov_len -= adv;
uio->uio_resid -= adv;
uio->uio_offset += adv;
return (error);
}
int
vn_io_fault_pgmove(vm_page_t ma[], vm_offset_t offset, int xfersize,
struct uio *uio)
{
struct thread *td;
vm_offset_t iov_base;
int cnt, pgadv;
td = curthread;
if ((td->td_pflags & TDP_UIOHELD) == 0 ||
uio->uio_segflg != UIO_USERSPACE)
return (uiomove_fromphys(ma, offset, xfersize, uio));
KASSERT(uio->uio_iovcnt == 1, ("uio_iovcnt %d", uio->uio_iovcnt));
cnt = xfersize > uio->uio_resid ? uio->uio_resid : xfersize;
iov_base = (vm_offset_t)uio->uio_iov->iov_base;
switch (uio->uio_rw) {
case UIO_WRITE:
pmap_copy_pages(td->td_ma, iov_base & PAGE_MASK, ma,
offset, cnt);
break;
case UIO_READ:
pmap_copy_pages(ma, offset, td->td_ma, iov_base & PAGE_MASK,
cnt);
break;
}
pgadv = ((iov_base + cnt) >> PAGE_SHIFT) - (iov_base >> PAGE_SHIFT);
td->td_ma += pgadv;
KASSERT(td->td_ma_cnt >= pgadv, ("consumed pages %d %d", td->td_ma_cnt,
pgadv));
td->td_ma_cnt -= pgadv;
uio->uio_iov->iov_base = (char *)(iov_base + cnt);
uio->uio_iov->iov_len -= cnt;
uio->uio_resid -= cnt;
uio->uio_offset += cnt;
return (0);
}
/*
* File table truncate routine.
*/
static int
vn_truncate(struct file *fp, off_t length, struct ucred *active_cred,
struct thread *td)
{
struct vattr vattr;
struct mount *mp;
struct vnode *vp;
void *rl_cookie;
int error;
vp = fp->f_vnode;
/*
* Lock the whole range for truncation. Otherwise split i/o
* might happen partly before and partly after the truncation.
*/
rl_cookie = vn_rangelock_wlock(vp, 0, OFF_MAX);
error = vn_start_write(vp, &mp, V_WAIT | PCATCH);
if (error)
goto out1;
vn_lock(vp, LK_EXCLUSIVE | LK_RETRY);
if (vp->v_type == VDIR) {
error = EISDIR;
goto out;
}
#ifdef MAC
error = mac_vnode_check_write(active_cred, fp->f_cred, vp);
if (error)
goto out;
#endif
error = vn_writechk(vp);
if (error == 0) {
VATTR_NULL(&vattr);
vattr.va_size = length;
error = VOP_SETATTR(vp, &vattr, fp->f_cred);
}
out:
VOP_UNLOCK(vp, 0);
vn_finished_write(mp);
out1:
vn_rangelock_unlock(vp, rl_cookie);
return (error);
}
/*
* File table vnode stat routine.
*/
static int
vn_statfile(fp, sb, active_cred, td)
struct file *fp;
struct stat *sb;
struct ucred *active_cred;
struct thread *td;
{
struct vnode *vp = fp->f_vnode;
int error;
vn_lock(vp, LK_SHARED | LK_RETRY);
error = vn_stat(vp, sb, active_cred, fp->f_cred, td);
VOP_UNLOCK(vp, 0);
return (error);
}
/*
* Stat a vnode; implementation for the stat syscall
*/
int
vn_stat(vp, sb, active_cred, file_cred, td)
struct vnode *vp;
register struct stat *sb;
struct ucred *active_cred;
struct ucred *file_cred;
struct thread *td;
{
struct vattr vattr;
register struct vattr *vap;
int error;
u_short mode;
#ifdef MAC
error = mac_vnode_check_stat(active_cred, file_cred, vp);
if (error)
return (error);
#endif
vap = &vattr;
/*
* Initialize defaults for new and unusual fields, so that file
* systems which don't support these fields don't need to know
* about them.
*/
vap->va_birthtime.tv_sec = -1;
vap->va_birthtime.tv_nsec = 0;
vap->va_fsid = VNOVAL;
vap->va_rdev = NODEV;
error = VOP_GETATTR(vp, vap, active_cred);
if (error)
return (error);
/*
* Zero the spare stat fields
*/
bzero(sb, sizeof *sb);
/*
* Copy from vattr table
*/
if (vap->va_fsid != VNOVAL)
sb->st_dev = vap->va_fsid;
else
sb->st_dev = vp->v_mount->mnt_stat.f_fsid.val[0];
sb->st_ino = vap->va_fileid;
mode = vap->va_mode;
switch (vap->va_type) {
case VREG:
mode |= S_IFREG;
break;
case VDIR:
mode |= S_IFDIR;
break;
case VBLK:
mode |= S_IFBLK;
break;
case VCHR:
mode |= S_IFCHR;
break;
case VLNK:
mode |= S_IFLNK;
break;
case VSOCK:
mode |= S_IFSOCK;
break;
case VFIFO:
mode |= S_IFIFO;
break;
default:
return (EBADF);
};
sb->st_mode = mode;
sb->st_nlink = vap->va_nlink;
sb->st_uid = vap->va_uid;
sb->st_gid = vap->va_gid;
sb->st_rdev = vap->va_rdev;
if (vap->va_size > OFF_MAX)
return (EOVERFLOW);
sb->st_size = vap->va_size;
sb->st_atim = vap->va_atime;
sb->st_mtim = vap->va_mtime;
sb->st_ctim = vap->va_ctime;
sb->st_birthtim = vap->va_birthtime;
/*
* According to www.opengroup.org, the meaning of st_blksize is
* "a filesystem-specific preferred I/O block size for this
* object. In some filesystem types, this may vary from file
* to file"
* Use miminum/default of PAGE_SIZE (e.g. for VCHR).
*/
sb->st_blksize = max(PAGE_SIZE, vap->va_blocksize);
sb->st_flags = vap->va_flags;
if (priv_check(td, PRIV_VFS_GENERATION))
sb->st_gen = 0;
else
sb->st_gen = vap->va_gen;
sb->st_blocks = vap->va_bytes / S_BLKSIZE;
return (0);
}
/*
* File table vnode ioctl routine.
*/
static int
vn_ioctl(fp, com, data, active_cred, td)
struct file *fp;
u_long com;
void *data;
struct ucred *active_cred;
struct thread *td;
{
struct vattr vattr;
struct vnode *vp;
int error;
vp = fp->f_vnode;
switch (vp->v_type) {
case VDIR:
case VREG:
switch (com) {
case FIONREAD:
vn_lock(vp, LK_SHARED | LK_RETRY);
error = VOP_GETATTR(vp, &vattr, active_cred);
VOP_UNLOCK(vp, 0);
if (error == 0)
*(int *)data = vattr.va_size - fp->f_offset;
return (error);
case FIONBIO:
case FIOASYNC:
return (0);
default:
return (VOP_IOCTL(vp, com, data, fp->f_flag,
active_cred, td));
}
default:
return (ENOTTY);
}
}
/*
* File table vnode poll routine.
*/
static int
vn_poll(fp, events, active_cred, td)
struct file *fp;
int events;
struct ucred *active_cred;
struct thread *td;
{
struct vnode *vp;
int error;
vp = fp->f_vnode;
#ifdef MAC
vn_lock(vp, LK_EXCLUSIVE | LK_RETRY);
error = mac_vnode_check_poll(active_cred, fp->f_cred, vp);
VOP_UNLOCK(vp, 0);
if (!error)
#endif
error = VOP_POLL(vp, events, fp->f_cred, td);
return (error);
}
/*
* Acquire the requested lock and then check for validity. LK_RETRY
* permits vn_lock to return doomed vnodes.
*/
int
_vn_lock(struct vnode *vp, int flags, char *file, int line)
{
int error;
VNASSERT((flags & LK_TYPE_MASK) != 0, vp,
("vn_lock called with no locktype."));
do {
#ifdef DEBUG_VFS_LOCKS
KASSERT(vp->v_holdcnt != 0,
("vn_lock %p: zero hold count", vp));
#endif
error = VOP_LOCK1(vp, flags, file, line);
flags &= ~LK_INTERLOCK; /* Interlock is always dropped. */
KASSERT((flags & LK_RETRY) == 0 || error == 0,
("LK_RETRY set with incompatible flags (0x%x) or an error occured (%d)",
flags, error));
/*
* Callers specify LK_RETRY if they wish to get dead vnodes.
* If RETRY is not set, we return ENOENT instead.
*/
if (error == 0 && vp->v_iflag & VI_DOOMED &&
(flags & LK_RETRY) == 0) {
VOP_UNLOCK(vp, 0);
error = ENOENT;
break;
}
} while (flags & LK_RETRY && error != 0);
return (error);
}
/*
* File table vnode close routine.
*/
static int
vn_closefile(fp, td)
struct file *fp;
struct thread *td;
{
struct vnode *vp;
struct flock lf;
int error;
vp = fp->f_vnode;
fp->f_ops = &badfileops;
if (fp->f_type == DTYPE_VNODE && fp->f_flag & FHASLOCK)
vref(vp);
error = vn_close(vp, fp->f_flag, fp->f_cred, td);
if (fp->f_type == DTYPE_VNODE && fp->f_flag & FHASLOCK) {
lf.l_whence = SEEK_SET;
lf.l_start = 0;
lf.l_len = 0;
lf.l_type = F_UNLCK;
(void) VOP_ADVLOCK(vp, fp, F_UNLCK, &lf, F_FLOCK);
vrele(vp);
}
return (error);
}
/*
* Preparing to start a filesystem write operation. If the operation is
* permitted, then we bump the count of operations in progress and
* proceed. If a suspend request is in progress, we wait until the
* suspension is over, and then proceed.
*/
static int
vn_start_write_locked(struct mount *mp, int flags)
{
int error;
mtx_assert(MNT_MTX(mp), MA_OWNED);
error = 0;
/*
* Check on status of suspension.
*/
if ((curthread->td_pflags & TDP_IGNSUSP) == 0 ||
mp->mnt_susp_owner != curthread) {
while ((mp->mnt_kern_flag & MNTK_SUSPEND) != 0) {
if (flags & V_NOWAIT) {
error = EWOULDBLOCK;
goto unlock;
}
error = msleep(&mp->mnt_flag, MNT_MTX(mp),
(PUSER - 1) | (flags & PCATCH), "suspfs", 0);
if (error)
goto unlock;
}
}
if (flags & V_XSLEEP)
goto unlock;
mp->mnt_writeopcount++;
unlock:
if (error != 0 || (flags & V_XSLEEP) != 0)
MNT_REL(mp);
MNT_IUNLOCK(mp);
return (error);
}
int
vn_start_write(vp, mpp, flags)
struct vnode *vp;
struct mount **mpp;
int flags;
{
struct mount *mp;
int error;
error = 0;
/*
* If a vnode is provided, get and return the mount point that
* to which it will write.
*/
if (vp != NULL) {
if ((error = VOP_GETWRITEMOUNT(vp, mpp)) != 0) {
*mpp = NULL;
if (error != EOPNOTSUPP)
return (error);
return (0);
}
}
if ((mp = *mpp) == NULL)
return (0);
/*
* VOP_GETWRITEMOUNT() returns with the mp refcount held through
* a vfs_ref().
* As long as a vnode is not provided we need to acquire a
* refcount for the provided mountpoint too, in order to
* emulate a vfs_ref().
*/
MNT_ILOCK(mp);
if (vp == NULL)
MNT_REF(mp);
return (vn_start_write_locked(mp, flags));
}
/*
* Secondary suspension. Used by operations such as vop_inactive
* routines that are needed by the higher level functions. These
* are allowed to proceed until all the higher level functions have
* completed (indicated by mnt_writeopcount dropping to zero). At that
* time, these operations are halted until the suspension is over.
*/
int
vn_start_secondary_write(vp, mpp, flags)
struct vnode *vp;
struct mount **mpp;
int flags;
{
struct mount *mp;
int error;
retry:
if (vp != NULL) {
if ((error = VOP_GETWRITEMOUNT(vp, mpp)) != 0) {
*mpp = NULL;
if (error != EOPNOTSUPP)
return (error);
return (0);
}
}
/*
* If we are not suspended or have not yet reached suspended
* mode, then let the operation proceed.
*/
if ((mp = *mpp) == NULL)
return (0);
/*
* VOP_GETWRITEMOUNT() returns with the mp refcount held through
* a vfs_ref().
* As long as a vnode is not provided we need to acquire a
* refcount for the provided mountpoint too, in order to
* emulate a vfs_ref().
*/
MNT_ILOCK(mp);
if (vp == NULL)
MNT_REF(mp);
if ((mp->mnt_kern_flag & (MNTK_SUSPENDED | MNTK_SUSPEND2)) == 0) {
mp->mnt_secondary_writes++;
mp->mnt_secondary_accwrites++;
MNT_IUNLOCK(mp);
return (0);
}
if (flags & V_NOWAIT) {
MNT_REL(mp);
MNT_IUNLOCK(mp);
return (EWOULDBLOCK);
}
/*
* Wait for the suspension to finish.
*/
error = msleep(&mp->mnt_flag, MNT_MTX(mp),
(PUSER - 1) | (flags & PCATCH) | PDROP, "suspfs", 0);
vfs_rel(mp);
if (error == 0)
goto retry;
return (error);
}
/*
* Filesystem write operation has completed. If we are suspending and this
* operation is the last one, notify the suspender that the suspension is
* now in effect.
*/
void
vn_finished_write(mp)
struct mount *mp;
{
if (mp == NULL)
return;
MNT_ILOCK(mp);
MNT_REL(mp);
mp->mnt_writeopcount--;
if (mp->mnt_writeopcount < 0)
panic("vn_finished_write: neg cnt");
if ((mp->mnt_kern_flag & MNTK_SUSPEND) != 0 &&
mp->mnt_writeopcount <= 0)
wakeup(&mp->mnt_writeopcount);
MNT_IUNLOCK(mp);
}
/*
* Filesystem secondary write operation has completed. If we are
* suspending and this operation is the last one, notify the suspender
* that the suspension is now in effect.
*/
void
vn_finished_secondary_write(mp)
struct mount *mp;
{
if (mp == NULL)
return;
MNT_ILOCK(mp);
MNT_REL(mp);
mp->mnt_secondary_writes--;
if (mp->mnt_secondary_writes < 0)
panic("vn_finished_secondary_write: neg cnt");
if ((mp->mnt_kern_flag & MNTK_SUSPEND) != 0 &&
mp->mnt_secondary_writes <= 0)
wakeup(&mp->mnt_secondary_writes);
MNT_IUNLOCK(mp);
}
/*
* Request a filesystem to suspend write operations.
*/
int
vfs_write_suspend(mp)
struct mount *mp;
{
int error;
MNT_ILOCK(mp);
if (mp->mnt_susp_owner == curthread) {
MNT_IUNLOCK(mp);
return (EALREADY);
}
while (mp->mnt_kern_flag & MNTK_SUSPEND)
msleep(&mp->mnt_flag, MNT_MTX(mp), PUSER - 1, "wsuspfs", 0);
mp->mnt_kern_flag |= MNTK_SUSPEND;
mp->mnt_susp_owner = curthread;
if (mp->mnt_writeopcount > 0)
(void) msleep(&mp->mnt_writeopcount,
MNT_MTX(mp), (PUSER - 1)|PDROP, "suspwt", 0);
else
MNT_IUNLOCK(mp);
if ((error = VFS_SYNC(mp, MNT_SUSPEND)) != 0)
vfs_write_resume(mp, 0);
return (error);
}
/*
* Request a filesystem to resume write operations.
*/
void
vfs_write_resume(struct mount *mp, int flags)
{
MNT_ILOCK(mp);
if ((mp->mnt_kern_flag & MNTK_SUSPEND) != 0) {
KASSERT(mp->mnt_susp_owner == curthread, ("mnt_susp_owner"));
mp->mnt_kern_flag &= ~(MNTK_SUSPEND | MNTK_SUSPEND2 |
MNTK_SUSPENDED);
mp->mnt_susp_owner = NULL;
wakeup(&mp->mnt_writeopcount);
wakeup(&mp->mnt_flag);
curthread->td_pflags &= ~TDP_IGNSUSP;
if ((flags & VR_START_WRITE) != 0) {
MNT_REF(mp);
mp->mnt_writeopcount++;
}
MNT_IUNLOCK(mp);
if ((flags & VR_NO_SUSPCLR) == 0)
VFS_SUSP_CLEAN(mp);
} else if ((flags & VR_START_WRITE) != 0) {
MNT_REF(mp);
vn_start_write_locked(mp, 0);
} else {
MNT_IUNLOCK(mp);
}
}
/*
* Implement kqueues for files by translating it to vnode operation.
*/
static int
vn_kqfilter(struct file *fp, struct knote *kn)
{
return (VOP_KQFILTER(fp->f_vnode, kn));
}
/*
* Simplified in-kernel wrapper calls for extended attribute access.
* Both calls pass in a NULL credential, authorizing as "kernel" access.
* Set IO_NODELOCKED in ioflg if the vnode is already locked.
*/
int
vn_extattr_get(struct vnode *vp, int ioflg, int attrnamespace,
const char *attrname, int *buflen, char *buf, struct thread *td)
{
struct uio auio;
struct iovec iov;
int error;
iov.iov_len = *buflen;
iov.iov_base = buf;
auio.uio_iov = &iov;
auio.uio_iovcnt = 1;
auio.uio_rw = UIO_READ;
auio.uio_segflg = UIO_SYSSPACE;
auio.uio_td = td;
auio.uio_offset = 0;
auio.uio_resid = *buflen;
if ((ioflg & IO_NODELOCKED) == 0)
vn_lock(vp, LK_SHARED | LK_RETRY);
ASSERT_VOP_LOCKED(vp, "IO_NODELOCKED with no vp lock held");
/* authorize attribute retrieval as kernel */
error = VOP_GETEXTATTR(vp, attrnamespace, attrname, &auio, NULL, NULL,
td);
if ((ioflg & IO_NODELOCKED) == 0)
VOP_UNLOCK(vp, 0);
if (error == 0) {
*buflen = *buflen - auio.uio_resid;
}
return (error);
}
/*
* XXX failure mode if partially written?
*/
int
vn_extattr_set(struct vnode *vp, int ioflg, int attrnamespace,
const char *attrname, int buflen, char *buf, struct thread *td)
{
struct uio auio;
struct iovec iov;
struct mount *mp;
int error;
iov.iov_len = buflen;
iov.iov_base = buf;
auio.uio_iov = &iov;
auio.uio_iovcnt = 1;
auio.uio_rw = UIO_WRITE;
auio.uio_segflg = UIO_SYSSPACE;
auio.uio_td = td;
auio.uio_offset = 0;
auio.uio_resid = buflen;
if ((ioflg & IO_NODELOCKED) == 0) {
if ((error = vn_start_write(vp, &mp, V_WAIT)) != 0)
return (error);
vn_lock(vp, LK_EXCLUSIVE | LK_RETRY);
}
ASSERT_VOP_LOCKED(vp, "IO_NODELOCKED with no vp lock held");
/* authorize attribute setting as kernel */
error = VOP_SETEXTATTR(vp, attrnamespace, attrname, &auio, NULL, td);
if ((ioflg & IO_NODELOCKED) == 0) {
vn_finished_write(mp);
VOP_UNLOCK(vp, 0);
}
return (error);
}
int
vn_extattr_rm(struct vnode *vp, int ioflg, int attrnamespace,
const char *attrname, struct thread *td)
{
struct mount *mp;
int error;
if ((ioflg & IO_NODELOCKED) == 0) {
if ((error = vn_start_write(vp, &mp, V_WAIT)) != 0)
return (error);
vn_lock(vp, LK_EXCLUSIVE | LK_RETRY);
}
ASSERT_VOP_LOCKED(vp, "IO_NODELOCKED with no vp lock held");
/* authorize attribute removal as kernel */
error = VOP_DELETEEXTATTR(vp, attrnamespace, attrname, NULL, td);
if (error == EOPNOTSUPP)
error = VOP_SETEXTATTR(vp, attrnamespace, attrname, NULL,
NULL, td);
if ((ioflg & IO_NODELOCKED) == 0) {
vn_finished_write(mp);
VOP_UNLOCK(vp, 0);
}
return (error);
}
int
vn_vget_ino(struct vnode *vp, ino_t ino, int lkflags, struct vnode **rvp)
{
struct mount *mp;
int ltype, error;
mp = vp->v_mount;
ltype = VOP_ISLOCKED(vp);
KASSERT(ltype == LK_EXCLUSIVE || ltype == LK_SHARED,
("vn_vget_ino: vp not locked"));
error = vfs_busy(mp, MBF_NOWAIT);
if (error != 0) {
vfs_ref(mp);
VOP_UNLOCK(vp, 0);
error = vfs_busy(mp, 0);
vn_lock(vp, ltype | LK_RETRY);
vfs_rel(mp);
if (error != 0)
return (ENOENT);
if (vp->v_iflag & VI_DOOMED) {
vfs_unbusy(mp);
return (ENOENT);
}
}
VOP_UNLOCK(vp, 0);
error = VFS_VGET(mp, ino, lkflags, rvp);
vfs_unbusy(mp);
vn_lock(vp, ltype | LK_RETRY);
if (vp->v_iflag & VI_DOOMED) {
if (error == 0)
vput(*rvp);
error = ENOENT;
}
return (error);
}
int
vn_rlimit_fsize(const struct vnode *vp, const struct uio *uio,
const struct thread *td)
{
if (vp->v_type != VREG || td == NULL)
return (0);
PROC_LOCK(td->td_proc);
if ((uoff_t)uio->uio_offset + uio->uio_resid >
lim_cur(td->td_proc, RLIMIT_FSIZE)) {
kern_psignal(td->td_proc, SIGXFSZ);
PROC_UNLOCK(td->td_proc);
return (EFBIG);
}
PROC_UNLOCK(td->td_proc);
return (0);
}
int
vn_chmod(struct file *fp, mode_t mode, struct ucred *active_cred,
struct thread *td)
{
struct vnode *vp;
vp = fp->f_vnode;
#ifdef AUDIT
vn_lock(vp, LK_SHARED | LK_RETRY);
AUDIT_ARG_VNODE1(vp);
VOP_UNLOCK(vp, 0);
#endif
return (setfmode(td, active_cred, vp, mode));
}
int
vn_chown(struct file *fp, uid_t uid, gid_t gid, struct ucred *active_cred,
struct thread *td)
{
struct vnode *vp;
vp = fp->f_vnode;
#ifdef AUDIT
vn_lock(vp, LK_SHARED | LK_RETRY);
AUDIT_ARG_VNODE1(vp);
VOP_UNLOCK(vp, 0);
#endif
return (setfown(td, active_cred, vp, uid, gid));
}
void
vn_pages_remove(struct vnode *vp, vm_pindex_t start, vm_pindex_t end)
{
vm_object_t object;
if ((object = vp->v_object) == NULL)
return;
VM_OBJECT_WLOCK(object);
vm_object_page_remove(object, start, end, 0);
VM_OBJECT_WUNLOCK(object);
}
int
vn_bmap_seekhole(struct vnode *vp, u_long cmd, off_t *off, struct ucred *cred)
{
struct vattr va;
daddr_t bn, bnp;
uint64_t bsize;
off_t noff;
int error;
KASSERT(cmd == FIOSEEKHOLE || cmd == FIOSEEKDATA,
("Wrong command %lu", cmd));
if (vn_lock(vp, LK_SHARED) != 0)
return (EBADF);
if (vp->v_type != VREG) {
error = ENOTTY;
goto unlock;
}
error = VOP_GETATTR(vp, &va, cred);
if (error != 0)
goto unlock;
noff = *off;
if (noff >= va.va_size) {
error = ENXIO;
goto unlock;
}
bsize = vp->v_mount->mnt_stat.f_iosize;
for (bn = noff / bsize; noff < va.va_size; bn++, noff += bsize) {
error = VOP_BMAP(vp, bn, NULL, &bnp, NULL, NULL);
if (error == EOPNOTSUPP) {
error = ENOTTY;
goto unlock;
}
if ((bnp == -1 && cmd == FIOSEEKHOLE) ||
(bnp != -1 && cmd == FIOSEEKDATA)) {
noff = bn * bsize;
if (noff < *off)
noff = *off;
goto unlock;
}
}
if (noff > va.va_size)
noff = va.va_size;
/* noff == va.va_size. There is an implicit hole at the end of file. */
if (cmd == FIOSEEKDATA)
error = ENXIO;
unlock:
VOP_UNLOCK(vp, 0);
if (error == 0)
*off = noff;
return (error);
}
|