1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
|
/*
* CDDL HEADER START
*
* The contents of this file are subject to the terms of the
* Common Development and Distribution License (the "License").
* You may not use this file except in compliance with the License.
*
* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
* or http://www.opensolaris.org/os/licensing.
* See the License for the specific language governing permissions
* and limitations under the License.
*
* When distributing Covered Code, include this CDDL HEADER in each
* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
* If applicable, add the following below this CDDL HEADER, with the
* fields enclosed by brackets "[]" replaced with your own identifying
* information: Portions Copyright [yyyy] [name of copyright owner]
*
* CDDL HEADER END
*/
/*
* Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
* Copyright (c) 2013 by Delphix. All rights reserved.
*/
/* Portions Copyright 2007 Jeremy Teo */
/* Portions Copyright 2011 Martin Matuska <mm@FreeBSD.org> */
#ifdef _KERNEL
#include <sys/types.h>
#include <sys/param.h>
#include <sys/time.h>
#include <sys/systm.h>
#include <sys/sysmacros.h>
#include <sys/resource.h>
#include <sys/mntent.h>
#include <sys/u8_textprep.h>
#include <sys/dsl_dataset.h>
#include <sys/vfs.h>
#include <sys/vnode.h>
#include <sys/file.h>
#include <sys/kmem.h>
#include <sys/errno.h>
#include <sys/unistd.h>
#include <sys/atomic.h>
#include <sys/zfs_dir.h>
#include <sys/zfs_acl.h>
#include <sys/zfs_ioctl.h>
#include <sys/zfs_rlock.h>
#include <sys/zfs_fuid.h>
#include <sys/dnode.h>
#include <sys/fs/zfs.h>
#include <sys/kidmap.h>
#endif /* _KERNEL */
#include <sys/dmu.h>
#include <sys/refcount.h>
#include <sys/stat.h>
#include <sys/zap.h>
#include <sys/zfs_znode.h>
#include <sys/sa.h>
#include <sys/zfs_sa.h>
#include <sys/zfs_stat.h>
#include <sys/refcount.h>
#include "zfs_prop.h"
#include "zfs_comutil.h"
/* Used by fstat(1). */
SYSCTL_INT(_debug_sizeof, OID_AUTO, znode, CTLFLAG_RD, 0, sizeof(znode_t),
"sizeof(znode_t)");
/*
* Define ZNODE_STATS to turn on statistic gathering. By default, it is only
* turned on when DEBUG is also defined.
*/
#ifdef DEBUG
#define ZNODE_STATS
#endif /* DEBUG */
#ifdef ZNODE_STATS
#define ZNODE_STAT_ADD(stat) ((stat)++)
#else
#define ZNODE_STAT_ADD(stat) /* nothing */
#endif /* ZNODE_STATS */
/*
* Functions needed for userland (ie: libzpool) are not put under
* #ifdef_KERNEL; the rest of the functions have dependencies
* (such as VFS logic) that will not compile easily in userland.
*/
#ifdef _KERNEL
/*
* Needed to close a small window in zfs_znode_move() that allows the zfsvfs to
* be freed before it can be safely accessed.
*/
krwlock_t zfsvfs_lock;
static kmem_cache_t *znode_cache = NULL;
/*ARGSUSED*/
static void
znode_evict_error(dmu_buf_t *dbuf, void *user_ptr)
{
/*
* We should never drop all dbuf refs without first clearing
* the eviction callback.
*/
panic("evicting znode %p\n", user_ptr);
}
extern struct vop_vector zfs_vnodeops;
extern struct vop_vector zfs_fifoops;
extern struct vop_vector zfs_shareops;
/*
* XXX: We cannot use this function as a cache constructor, because
* there is one global cache for all file systems and we need
* to pass vfsp here, which is not possible, because argument
* 'cdrarg' is defined at kmem_cache_create() time.
*/
/*ARGSUSED*/
static int
zfs_znode_cache_constructor(void *buf, void *arg, int kmflags)
{
znode_t *zp = buf;
vnode_t *vp;
vfs_t *vfsp = arg;
int error;
POINTER_INVALIDATE(&zp->z_zfsvfs);
ASSERT(!POINTER_IS_VALID(zp->z_zfsvfs));
if (vfsp != NULL) {
error = getnewvnode("zfs", vfsp, &zfs_vnodeops, &vp);
if (error != 0 && (kmflags & KM_NOSLEEP))
return (-1);
ASSERT(error == 0);
vn_lock(vp, LK_EXCLUSIVE | LK_RETRY);
zp->z_vnode = vp;
vp->v_data = (caddr_t)zp;
VN_LOCK_AREC(vp);
VN_LOCK_ASHARE(vp);
} else {
zp->z_vnode = NULL;
}
list_link_init(&zp->z_link_node);
mutex_init(&zp->z_lock, NULL, MUTEX_DEFAULT, NULL);
rw_init(&zp->z_parent_lock, NULL, RW_DEFAULT, NULL);
rw_init(&zp->z_name_lock, NULL, RW_DEFAULT, NULL);
mutex_init(&zp->z_acl_lock, NULL, MUTEX_DEFAULT, NULL);
mutex_init(&zp->z_range_lock, NULL, MUTEX_DEFAULT, NULL);
avl_create(&zp->z_range_avl, zfs_range_compare,
sizeof (rl_t), offsetof(rl_t, r_node));
zp->z_dirlocks = NULL;
zp->z_acl_cached = NULL;
zp->z_moved = 0;
return (0);
}
/*ARGSUSED*/
static void
zfs_znode_cache_destructor(void *buf, void *arg)
{
znode_t *zp = buf;
ASSERT(!POINTER_IS_VALID(zp->z_zfsvfs));
ASSERT(ZTOV(zp) == NULL);
vn_free(ZTOV(zp));
ASSERT(!list_link_active(&zp->z_link_node));
mutex_destroy(&zp->z_lock);
rw_destroy(&zp->z_parent_lock);
rw_destroy(&zp->z_name_lock);
mutex_destroy(&zp->z_acl_lock);
avl_destroy(&zp->z_range_avl);
mutex_destroy(&zp->z_range_lock);
ASSERT(zp->z_dirlocks == NULL);
ASSERT(zp->z_acl_cached == NULL);
}
#ifdef ZNODE_STATS
static struct {
uint64_t zms_zfsvfs_invalid;
uint64_t zms_zfsvfs_recheck1;
uint64_t zms_zfsvfs_unmounted;
uint64_t zms_zfsvfs_recheck2;
uint64_t zms_obj_held;
uint64_t zms_vnode_locked;
uint64_t zms_not_only_dnlc;
} znode_move_stats;
#endif /* ZNODE_STATS */
#ifdef sun
static void
zfs_znode_move_impl(znode_t *ozp, znode_t *nzp)
{
vnode_t *vp;
/* Copy fields. */
nzp->z_zfsvfs = ozp->z_zfsvfs;
/* Swap vnodes. */
vp = nzp->z_vnode;
nzp->z_vnode = ozp->z_vnode;
ozp->z_vnode = vp; /* let destructor free the overwritten vnode */
ZTOV(ozp)->v_data = ozp;
ZTOV(nzp)->v_data = nzp;
nzp->z_id = ozp->z_id;
ASSERT(ozp->z_dirlocks == NULL); /* znode not in use */
ASSERT(avl_numnodes(&ozp->z_range_avl) == 0);
nzp->z_unlinked = ozp->z_unlinked;
nzp->z_atime_dirty = ozp->z_atime_dirty;
nzp->z_zn_prefetch = ozp->z_zn_prefetch;
nzp->z_blksz = ozp->z_blksz;
nzp->z_seq = ozp->z_seq;
nzp->z_mapcnt = ozp->z_mapcnt;
nzp->z_gen = ozp->z_gen;
nzp->z_sync_cnt = ozp->z_sync_cnt;
nzp->z_is_sa = ozp->z_is_sa;
nzp->z_sa_hdl = ozp->z_sa_hdl;
bcopy(ozp->z_atime, nzp->z_atime, sizeof (uint64_t) * 2);
nzp->z_links = ozp->z_links;
nzp->z_size = ozp->z_size;
nzp->z_pflags = ozp->z_pflags;
nzp->z_uid = ozp->z_uid;
nzp->z_gid = ozp->z_gid;
nzp->z_mode = ozp->z_mode;
/*
* Since this is just an idle znode and kmem is already dealing with
* memory pressure, release any cached ACL.
*/
if (ozp->z_acl_cached) {
zfs_acl_free(ozp->z_acl_cached);
ozp->z_acl_cached = NULL;
}
sa_set_userp(nzp->z_sa_hdl, nzp);
/*
* Invalidate the original znode by clearing fields that provide a
* pointer back to the znode. Set the low bit of the vfs pointer to
* ensure that zfs_znode_move() recognizes the znode as invalid in any
* subsequent callback.
*/
ozp->z_sa_hdl = NULL;
POINTER_INVALIDATE(&ozp->z_zfsvfs);
/*
* Mark the znode.
*/
nzp->z_moved = 1;
ozp->z_moved = (uint8_t)-1;
}
/*ARGSUSED*/
static kmem_cbrc_t
zfs_znode_move(void *buf, void *newbuf, size_t size, void *arg)
{
znode_t *ozp = buf, *nzp = newbuf;
zfsvfs_t *zfsvfs;
vnode_t *vp;
/*
* The znode is on the file system's list of known znodes if the vfs
* pointer is valid. We set the low bit of the vfs pointer when freeing
* the znode to invalidate it, and the memory patterns written by kmem
* (baddcafe and deadbeef) set at least one of the two low bits. A newly
* created znode sets the vfs pointer last of all to indicate that the
* znode is known and in a valid state to be moved by this function.
*/
zfsvfs = ozp->z_zfsvfs;
if (!POINTER_IS_VALID(zfsvfs)) {
ZNODE_STAT_ADD(znode_move_stats.zms_zfsvfs_invalid);
return (KMEM_CBRC_DONT_KNOW);
}
/*
* Close a small window in which it's possible that the filesystem could
* be unmounted and freed, and zfsvfs, though valid in the previous
* statement, could point to unrelated memory by the time we try to
* prevent the filesystem from being unmounted.
*/
rw_enter(&zfsvfs_lock, RW_WRITER);
if (zfsvfs != ozp->z_zfsvfs) {
rw_exit(&zfsvfs_lock);
ZNODE_STAT_ADD(znode_move_stats.zms_zfsvfs_recheck1);
return (KMEM_CBRC_DONT_KNOW);
}
/*
* If the znode is still valid, then so is the file system. We know that
* no valid file system can be freed while we hold zfsvfs_lock, so we
* can safely ensure that the filesystem is not and will not be
* unmounted. The next statement is equivalent to ZFS_ENTER().
*/
rrw_enter(&zfsvfs->z_teardown_lock, RW_READER, FTAG);
if (zfsvfs->z_unmounted) {
ZFS_EXIT(zfsvfs);
rw_exit(&zfsvfs_lock);
ZNODE_STAT_ADD(znode_move_stats.zms_zfsvfs_unmounted);
return (KMEM_CBRC_DONT_KNOW);
}
rw_exit(&zfsvfs_lock);
mutex_enter(&zfsvfs->z_znodes_lock);
/*
* Recheck the vfs pointer in case the znode was removed just before
* acquiring the lock.
*/
if (zfsvfs != ozp->z_zfsvfs) {
mutex_exit(&zfsvfs->z_znodes_lock);
ZFS_EXIT(zfsvfs);
ZNODE_STAT_ADD(znode_move_stats.zms_zfsvfs_recheck2);
return (KMEM_CBRC_DONT_KNOW);
}
/*
* At this point we know that as long as we hold z_znodes_lock, the
* znode cannot be freed and fields within the znode can be safely
* accessed. Now, prevent a race with zfs_zget().
*/
if (ZFS_OBJ_HOLD_TRYENTER(zfsvfs, ozp->z_id) == 0) {
mutex_exit(&zfsvfs->z_znodes_lock);
ZFS_EXIT(zfsvfs);
ZNODE_STAT_ADD(znode_move_stats.zms_obj_held);
return (KMEM_CBRC_LATER);
}
vp = ZTOV(ozp);
if (mutex_tryenter(&vp->v_lock) == 0) {
ZFS_OBJ_HOLD_EXIT(zfsvfs, ozp->z_id);
mutex_exit(&zfsvfs->z_znodes_lock);
ZFS_EXIT(zfsvfs);
ZNODE_STAT_ADD(znode_move_stats.zms_vnode_locked);
return (KMEM_CBRC_LATER);
}
/* Only move znodes that are referenced _only_ by the DNLC. */
if (vp->v_count != 1 || !vn_in_dnlc(vp)) {
mutex_exit(&vp->v_lock);
ZFS_OBJ_HOLD_EXIT(zfsvfs, ozp->z_id);
mutex_exit(&zfsvfs->z_znodes_lock);
ZFS_EXIT(zfsvfs);
ZNODE_STAT_ADD(znode_move_stats.zms_not_only_dnlc);
return (KMEM_CBRC_LATER);
}
/*
* The znode is known and in a valid state to move. We're holding the
* locks needed to execute the critical section.
*/
zfs_znode_move_impl(ozp, nzp);
mutex_exit(&vp->v_lock);
ZFS_OBJ_HOLD_EXIT(zfsvfs, ozp->z_id);
list_link_replace(&ozp->z_link_node, &nzp->z_link_node);
mutex_exit(&zfsvfs->z_znodes_lock);
ZFS_EXIT(zfsvfs);
return (KMEM_CBRC_YES);
}
#endif /* sun */
void
zfs_znode_init(void)
{
/*
* Initialize zcache
*/
rw_init(&zfsvfs_lock, NULL, RW_DEFAULT, NULL);
ASSERT(znode_cache == NULL);
znode_cache = kmem_cache_create("zfs_znode_cache",
sizeof (znode_t), 0, /* zfs_znode_cache_constructor */ NULL,
zfs_znode_cache_destructor, NULL, NULL, NULL, 0);
kmem_cache_set_move(znode_cache, zfs_znode_move);
}
void
zfs_znode_fini(void)
{
#ifdef sun
/*
* Cleanup vfs & vnode ops
*/
zfs_remove_op_tables();
#endif /* sun */
/*
* Cleanup zcache
*/
if (znode_cache)
kmem_cache_destroy(znode_cache);
znode_cache = NULL;
rw_destroy(&zfsvfs_lock);
}
#ifdef sun
struct vnodeops *zfs_dvnodeops;
struct vnodeops *zfs_fvnodeops;
struct vnodeops *zfs_symvnodeops;
struct vnodeops *zfs_xdvnodeops;
struct vnodeops *zfs_evnodeops;
struct vnodeops *zfs_sharevnodeops;
void
zfs_remove_op_tables()
{
/*
* Remove vfs ops
*/
ASSERT(zfsfstype);
(void) vfs_freevfsops_by_type(zfsfstype);
zfsfstype = 0;
/*
* Remove vnode ops
*/
if (zfs_dvnodeops)
vn_freevnodeops(zfs_dvnodeops);
if (zfs_fvnodeops)
vn_freevnodeops(zfs_fvnodeops);
if (zfs_symvnodeops)
vn_freevnodeops(zfs_symvnodeops);
if (zfs_xdvnodeops)
vn_freevnodeops(zfs_xdvnodeops);
if (zfs_evnodeops)
vn_freevnodeops(zfs_evnodeops);
if (zfs_sharevnodeops)
vn_freevnodeops(zfs_sharevnodeops);
zfs_dvnodeops = NULL;
zfs_fvnodeops = NULL;
zfs_symvnodeops = NULL;
zfs_xdvnodeops = NULL;
zfs_evnodeops = NULL;
zfs_sharevnodeops = NULL;
}
extern const fs_operation_def_t zfs_dvnodeops_template[];
extern const fs_operation_def_t zfs_fvnodeops_template[];
extern const fs_operation_def_t zfs_xdvnodeops_template[];
extern const fs_operation_def_t zfs_symvnodeops_template[];
extern const fs_operation_def_t zfs_evnodeops_template[];
extern const fs_operation_def_t zfs_sharevnodeops_template[];
int
zfs_create_op_tables()
{
int error;
/*
* zfs_dvnodeops can be set if mod_remove() calls mod_installfs()
* due to a failure to remove the the 2nd modlinkage (zfs_modldrv).
* In this case we just return as the ops vectors are already set up.
*/
if (zfs_dvnodeops)
return (0);
error = vn_make_ops(MNTTYPE_ZFS, zfs_dvnodeops_template,
&zfs_dvnodeops);
if (error)
return (error);
error = vn_make_ops(MNTTYPE_ZFS, zfs_fvnodeops_template,
&zfs_fvnodeops);
if (error)
return (error);
error = vn_make_ops(MNTTYPE_ZFS, zfs_symvnodeops_template,
&zfs_symvnodeops);
if (error)
return (error);
error = vn_make_ops(MNTTYPE_ZFS, zfs_xdvnodeops_template,
&zfs_xdvnodeops);
if (error)
return (error);
error = vn_make_ops(MNTTYPE_ZFS, zfs_evnodeops_template,
&zfs_evnodeops);
if (error)
return (error);
error = vn_make_ops(MNTTYPE_ZFS, zfs_sharevnodeops_template,
&zfs_sharevnodeops);
return (error);
}
#endif /* sun */
int
zfs_create_share_dir(zfsvfs_t *zfsvfs, dmu_tx_t *tx)
{
zfs_acl_ids_t acl_ids;
vattr_t vattr;
znode_t *sharezp;
vnode_t *vp, vnode;
znode_t *zp;
int error;
vattr.va_mask = AT_MODE|AT_UID|AT_GID|AT_TYPE;
vattr.va_type = VDIR;
vattr.va_mode = S_IFDIR|0555;
vattr.va_uid = crgetuid(kcred);
vattr.va_gid = crgetgid(kcred);
sharezp = kmem_cache_alloc(znode_cache, KM_SLEEP);
zfs_znode_cache_constructor(sharezp, zfsvfs->z_parent->z_vfs, 0);
ASSERT(!POINTER_IS_VALID(sharezp->z_zfsvfs));
sharezp->z_moved = 0;
sharezp->z_unlinked = 0;
sharezp->z_atime_dirty = 0;
sharezp->z_zfsvfs = zfsvfs;
sharezp->z_is_sa = zfsvfs->z_use_sa;
sharezp->z_vnode = &vnode;
vnode.v_data = sharezp;
vp = ZTOV(sharezp);
vp->v_type = VDIR;
VERIFY(0 == zfs_acl_ids_create(sharezp, IS_ROOT_NODE, &vattr,
kcred, NULL, &acl_ids));
zfs_mknode(sharezp, &vattr, tx, kcred, IS_ROOT_NODE, &zp, &acl_ids);
ASSERT3P(zp, ==, sharezp);
POINTER_INVALIDATE(&sharezp->z_zfsvfs);
error = zap_add(zfsvfs->z_os, MASTER_NODE_OBJ,
ZFS_SHARES_DIR, 8, 1, &sharezp->z_id, tx);
zfsvfs->z_shares_dir = sharezp->z_id;
zfs_acl_ids_free(&acl_ids);
ZTOV(sharezp)->v_data = NULL;
ZTOV(sharezp)->v_count = 0;
ZTOV(sharezp)->v_holdcnt = 0;
zp->z_vnode = NULL;
sa_handle_destroy(sharezp->z_sa_hdl);
sharezp->z_vnode = NULL;
kmem_cache_free(znode_cache, sharezp);
return (error);
}
/*
* define a couple of values we need available
* for both 64 and 32 bit environments.
*/
#ifndef NBITSMINOR64
#define NBITSMINOR64 32
#endif
#ifndef MAXMAJ64
#define MAXMAJ64 0xffffffffUL
#endif
#ifndef MAXMIN64
#define MAXMIN64 0xffffffffUL
#endif
/*
* Create special expldev for ZFS private use.
* Can't use standard expldev since it doesn't do
* what we want. The standard expldev() takes a
* dev32_t in LP64 and expands it to a long dev_t.
* We need an interface that takes a dev32_t in ILP32
* and expands it to a long dev_t.
*/
static uint64_t
zfs_expldev(dev_t dev)
{
return (((uint64_t)major(dev) << NBITSMINOR64) | minor(dev));
}
/*
* Special cmpldev for ZFS private use.
* Can't use standard cmpldev since it takes
* a long dev_t and compresses it to dev32_t in
* LP64. We need to do a compaction of a long dev_t
* to a dev32_t in ILP32.
*/
dev_t
zfs_cmpldev(uint64_t dev)
{
return (makedev((dev >> NBITSMINOR64), (dev & MAXMIN64)));
}
static void
zfs_znode_sa_init(zfsvfs_t *zfsvfs, znode_t *zp,
dmu_buf_t *db, dmu_object_type_t obj_type, sa_handle_t *sa_hdl)
{
ASSERT(!POINTER_IS_VALID(zp->z_zfsvfs) || (zfsvfs == zp->z_zfsvfs));
ASSERT(MUTEX_HELD(ZFS_OBJ_MUTEX(zfsvfs, zp->z_id)));
mutex_enter(&zp->z_lock);
ASSERT(zp->z_sa_hdl == NULL);
ASSERT(zp->z_acl_cached == NULL);
if (sa_hdl == NULL) {
VERIFY(0 == sa_handle_get_from_db(zfsvfs->z_os, db, zp,
SA_HDL_SHARED, &zp->z_sa_hdl));
} else {
zp->z_sa_hdl = sa_hdl;
sa_set_userp(sa_hdl, zp);
}
zp->z_is_sa = (obj_type == DMU_OT_SA) ? B_TRUE : B_FALSE;
/*
* Slap on VROOT if we are the root znode
*/
if (zp->z_id == zfsvfs->z_root)
ZTOV(zp)->v_flag |= VROOT;
mutex_exit(&zp->z_lock);
vn_exists(ZTOV(zp));
}
void
zfs_znode_dmu_fini(znode_t *zp)
{
ASSERT(MUTEX_HELD(ZFS_OBJ_MUTEX(zp->z_zfsvfs, zp->z_id)) ||
zp->z_unlinked ||
RW_WRITE_HELD(&zp->z_zfsvfs->z_teardown_inactive_lock));
sa_handle_destroy(zp->z_sa_hdl);
zp->z_sa_hdl = NULL;
}
static void
zfs_vnode_forget(vnode_t *vp)
{
/* copied from insmntque_stddtr */
vp->v_data = NULL;
vp->v_op = &dead_vnodeops;
vgone(vp);
vput(vp);
}
/*
* Construct a new znode/vnode and intialize.
*
* This does not do a call to dmu_set_user() that is
* up to the caller to do, in case you don't want to
* return the znode
*/
static znode_t *
zfs_znode_alloc(zfsvfs_t *zfsvfs, dmu_buf_t *db, int blksz,
dmu_object_type_t obj_type, sa_handle_t *hdl)
{
znode_t *zp;
vnode_t *vp;
uint64_t mode;
uint64_t parent;
sa_bulk_attr_t bulk[9];
int count = 0;
zp = kmem_cache_alloc(znode_cache, KM_SLEEP);
zfs_znode_cache_constructor(zp, zfsvfs->z_parent->z_vfs, 0);
ASSERT(zp->z_dirlocks == NULL);
ASSERT(!POINTER_IS_VALID(zp->z_zfsvfs));
zp->z_moved = 0;
/*
* Defer setting z_zfsvfs until the znode is ready to be a candidate for
* the zfs_znode_move() callback.
*/
zp->z_sa_hdl = NULL;
zp->z_unlinked = 0;
zp->z_atime_dirty = 0;
zp->z_mapcnt = 0;
zp->z_id = db->db_object;
zp->z_blksz = blksz;
zp->z_seq = 0x7A4653;
zp->z_sync_cnt = 0;
vp = ZTOV(zp);
zfs_znode_sa_init(zfsvfs, zp, db, obj_type, hdl);
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_MODE(zfsvfs), NULL, &mode, 8);
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_GEN(zfsvfs), NULL, &zp->z_gen, 8);
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_SIZE(zfsvfs), NULL,
&zp->z_size, 8);
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_LINKS(zfsvfs), NULL,
&zp->z_links, 8);
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_FLAGS(zfsvfs), NULL,
&zp->z_pflags, 8);
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_PARENT(zfsvfs), NULL, &parent, 8);
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_ATIME(zfsvfs), NULL,
&zp->z_atime, 16);
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_UID(zfsvfs), NULL,
&zp->z_uid, 8);
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_GID(zfsvfs), NULL,
&zp->z_gid, 8);
if (sa_bulk_lookup(zp->z_sa_hdl, bulk, count) != 0 || zp->z_gen == 0) {
if (hdl == NULL)
sa_handle_destroy(zp->z_sa_hdl);
zfs_vnode_forget(vp);
zp->z_vnode = NULL;
kmem_cache_free(znode_cache, zp);
return (NULL);
}
zp->z_mode = mode;
vp->v_type = IFTOVT((mode_t)mode);
switch (vp->v_type) {
case VDIR:
zp->z_zn_prefetch = B_TRUE; /* z_prefetch default is enabled */
break;
#ifdef sun
case VBLK:
case VCHR:
{
uint64_t rdev;
VERIFY(sa_lookup(zp->z_sa_hdl, SA_ZPL_RDEV(zfsvfs),
&rdev, sizeof (rdev)) == 0);
vp->v_rdev = zfs_cmpldev(rdev);
}
break;
#endif /* sun */
case VFIFO:
#ifdef sun
case VSOCK:
case VDOOR:
#endif /* sun */
vp->v_op = &zfs_fifoops;
break;
case VREG:
if (parent == zfsvfs->z_shares_dir) {
ASSERT(zp->z_uid == 0 && zp->z_gid == 0);
vp->v_op = &zfs_shareops;
}
break;
#ifdef sun
case VLNK:
vn_setops(vp, zfs_symvnodeops);
break;
default:
vn_setops(vp, zfs_evnodeops);
break;
#endif /* sun */
}
if (vp->v_type != VFIFO)
VN_LOCK_ASHARE(vp);
mutex_enter(&zfsvfs->z_znodes_lock);
list_insert_tail(&zfsvfs->z_all_znodes, zp);
membar_producer();
/*
* Everything else must be valid before assigning z_zfsvfs makes the
* znode eligible for zfs_znode_move().
*/
zp->z_zfsvfs = zfsvfs;
mutex_exit(&zfsvfs->z_znodes_lock);
VFS_HOLD(zfsvfs->z_vfs);
return (zp);
}
static uint64_t empty_xattr;
static uint64_t pad[4];
static zfs_acl_phys_t acl_phys;
/*
* Create a new DMU object to hold a zfs znode.
*
* IN: dzp - parent directory for new znode
* vap - file attributes for new znode
* tx - dmu transaction id for zap operations
* cr - credentials of caller
* flag - flags:
* IS_ROOT_NODE - new object will be root
* IS_XATTR - new object is an attribute
* bonuslen - length of bonus buffer
* setaclp - File/Dir initial ACL
* fuidp - Tracks fuid allocation.
*
* OUT: zpp - allocated znode
*
*/
void
zfs_mknode(znode_t *dzp, vattr_t *vap, dmu_tx_t *tx, cred_t *cr,
uint_t flag, znode_t **zpp, zfs_acl_ids_t *acl_ids)
{
uint64_t crtime[2], atime[2], mtime[2], ctime[2];
uint64_t mode, size, links, parent, pflags;
uint64_t dzp_pflags = 0;
uint64_t rdev = 0;
zfsvfs_t *zfsvfs = dzp->z_zfsvfs;
dmu_buf_t *db;
timestruc_t now;
uint64_t gen, obj;
int err;
int bonuslen;
sa_handle_t *sa_hdl;
dmu_object_type_t obj_type;
sa_bulk_attr_t sa_attrs[ZPL_END];
int cnt = 0;
zfs_acl_locator_cb_t locate = { 0 };
ASSERT(vap && (vap->va_mask & (AT_TYPE|AT_MODE)) == (AT_TYPE|AT_MODE));
if (zfsvfs->z_replay) {
obj = vap->va_nodeid;
now = vap->va_ctime; /* see zfs_replay_create() */
gen = vap->va_nblocks; /* ditto */
} else {
obj = 0;
gethrestime(&now);
gen = dmu_tx_get_txg(tx);
}
obj_type = zfsvfs->z_use_sa ? DMU_OT_SA : DMU_OT_ZNODE;
bonuslen = (obj_type == DMU_OT_SA) ?
DN_MAX_BONUSLEN : ZFS_OLD_ZNODE_PHYS_SIZE;
/*
* Create a new DMU object.
*/
/*
* There's currently no mechanism for pre-reading the blocks that will
* be needed to allocate a new object, so we accept the small chance
* that there will be an i/o error and we will fail one of the
* assertions below.
*/
if (vap->va_type == VDIR) {
if (zfsvfs->z_replay) {
err = zap_create_claim_norm(zfsvfs->z_os, obj,
zfsvfs->z_norm, DMU_OT_DIRECTORY_CONTENTS,
obj_type, bonuslen, tx);
ASSERT0(err);
} else {
obj = zap_create_norm(zfsvfs->z_os,
zfsvfs->z_norm, DMU_OT_DIRECTORY_CONTENTS,
obj_type, bonuslen, tx);
}
} else {
if (zfsvfs->z_replay) {
err = dmu_object_claim(zfsvfs->z_os, obj,
DMU_OT_PLAIN_FILE_CONTENTS, 0,
obj_type, bonuslen, tx);
ASSERT0(err);
} else {
obj = dmu_object_alloc(zfsvfs->z_os,
DMU_OT_PLAIN_FILE_CONTENTS, 0,
obj_type, bonuslen, tx);
}
}
getnewvnode_reserve(1);
ZFS_OBJ_HOLD_ENTER(zfsvfs, obj);
VERIFY(0 == sa_buf_hold(zfsvfs->z_os, obj, NULL, &db));
/*
* If this is the root, fix up the half-initialized parent pointer
* to reference the just-allocated physical data area.
*/
if (flag & IS_ROOT_NODE) {
dzp->z_id = obj;
} else {
dzp_pflags = dzp->z_pflags;
}
/*
* If parent is an xattr, so am I.
*/
if (dzp_pflags & ZFS_XATTR) {
flag |= IS_XATTR;
}
if (zfsvfs->z_use_fuids)
pflags = ZFS_ARCHIVE | ZFS_AV_MODIFIED;
else
pflags = 0;
if (vap->va_type == VDIR) {
size = 2; /* contents ("." and "..") */
links = (flag & (IS_ROOT_NODE | IS_XATTR)) ? 2 : 1;
} else {
size = links = 0;
}
if (vap->va_type == VBLK || vap->va_type == VCHR) {
rdev = zfs_expldev(vap->va_rdev);
}
parent = dzp->z_id;
mode = acl_ids->z_mode;
if (flag & IS_XATTR)
pflags |= ZFS_XATTR;
/*
* No execs denied will be deterimed when zfs_mode_compute() is called.
*/
pflags |= acl_ids->z_aclp->z_hints &
(ZFS_ACL_TRIVIAL|ZFS_INHERIT_ACE|ZFS_ACL_AUTO_INHERIT|
ZFS_ACL_DEFAULTED|ZFS_ACL_PROTECTED);
ZFS_TIME_ENCODE(&now, crtime);
ZFS_TIME_ENCODE(&now, ctime);
if (vap->va_mask & AT_ATIME) {
ZFS_TIME_ENCODE(&vap->va_atime, atime);
} else {
ZFS_TIME_ENCODE(&now, atime);
}
if (vap->va_mask & AT_MTIME) {
ZFS_TIME_ENCODE(&vap->va_mtime, mtime);
} else {
ZFS_TIME_ENCODE(&now, mtime);
}
/* Now add in all of the "SA" attributes */
VERIFY(0 == sa_handle_get_from_db(zfsvfs->z_os, db, NULL, SA_HDL_SHARED,
&sa_hdl));
/*
* Setup the array of attributes to be replaced/set on the new file
*
* order for DMU_OT_ZNODE is critical since it needs to be constructed
* in the old znode_phys_t format. Don't change this ordering
*/
if (obj_type == DMU_OT_ZNODE) {
SA_ADD_BULK_ATTR(sa_attrs, cnt, SA_ZPL_ATIME(zfsvfs),
NULL, &atime, 16);
SA_ADD_BULK_ATTR(sa_attrs, cnt, SA_ZPL_MTIME(zfsvfs),
NULL, &mtime, 16);
SA_ADD_BULK_ATTR(sa_attrs, cnt, SA_ZPL_CTIME(zfsvfs),
NULL, &ctime, 16);
SA_ADD_BULK_ATTR(sa_attrs, cnt, SA_ZPL_CRTIME(zfsvfs),
NULL, &crtime, 16);
SA_ADD_BULK_ATTR(sa_attrs, cnt, SA_ZPL_GEN(zfsvfs),
NULL, &gen, 8);
SA_ADD_BULK_ATTR(sa_attrs, cnt, SA_ZPL_MODE(zfsvfs),
NULL, &mode, 8);
SA_ADD_BULK_ATTR(sa_attrs, cnt, SA_ZPL_SIZE(zfsvfs),
NULL, &size, 8);
SA_ADD_BULK_ATTR(sa_attrs, cnt, SA_ZPL_PARENT(zfsvfs),
NULL, &parent, 8);
} else {
SA_ADD_BULK_ATTR(sa_attrs, cnt, SA_ZPL_MODE(zfsvfs),
NULL, &mode, 8);
SA_ADD_BULK_ATTR(sa_attrs, cnt, SA_ZPL_SIZE(zfsvfs),
NULL, &size, 8);
SA_ADD_BULK_ATTR(sa_attrs, cnt, SA_ZPL_GEN(zfsvfs),
NULL, &gen, 8);
SA_ADD_BULK_ATTR(sa_attrs, cnt, SA_ZPL_UID(zfsvfs), NULL,
&acl_ids->z_fuid, 8);
SA_ADD_BULK_ATTR(sa_attrs, cnt, SA_ZPL_GID(zfsvfs), NULL,
&acl_ids->z_fgid, 8);
SA_ADD_BULK_ATTR(sa_attrs, cnt, SA_ZPL_PARENT(zfsvfs),
NULL, &parent, 8);
SA_ADD_BULK_ATTR(sa_attrs, cnt, SA_ZPL_FLAGS(zfsvfs),
NULL, &pflags, 8);
SA_ADD_BULK_ATTR(sa_attrs, cnt, SA_ZPL_ATIME(zfsvfs),
NULL, &atime, 16);
SA_ADD_BULK_ATTR(sa_attrs, cnt, SA_ZPL_MTIME(zfsvfs),
NULL, &mtime, 16);
SA_ADD_BULK_ATTR(sa_attrs, cnt, SA_ZPL_CTIME(zfsvfs),
NULL, &ctime, 16);
SA_ADD_BULK_ATTR(sa_attrs, cnt, SA_ZPL_CRTIME(zfsvfs),
NULL, &crtime, 16);
}
SA_ADD_BULK_ATTR(sa_attrs, cnt, SA_ZPL_LINKS(zfsvfs), NULL, &links, 8);
if (obj_type == DMU_OT_ZNODE) {
SA_ADD_BULK_ATTR(sa_attrs, cnt, SA_ZPL_XATTR(zfsvfs), NULL,
&empty_xattr, 8);
}
if (obj_type == DMU_OT_ZNODE ||
(vap->va_type == VBLK || vap->va_type == VCHR)) {
SA_ADD_BULK_ATTR(sa_attrs, cnt, SA_ZPL_RDEV(zfsvfs),
NULL, &rdev, 8);
}
if (obj_type == DMU_OT_ZNODE) {
SA_ADD_BULK_ATTR(sa_attrs, cnt, SA_ZPL_FLAGS(zfsvfs),
NULL, &pflags, 8);
SA_ADD_BULK_ATTR(sa_attrs, cnt, SA_ZPL_UID(zfsvfs), NULL,
&acl_ids->z_fuid, 8);
SA_ADD_BULK_ATTR(sa_attrs, cnt, SA_ZPL_GID(zfsvfs), NULL,
&acl_ids->z_fgid, 8);
SA_ADD_BULK_ATTR(sa_attrs, cnt, SA_ZPL_PAD(zfsvfs), NULL, pad,
sizeof (uint64_t) * 4);
SA_ADD_BULK_ATTR(sa_attrs, cnt, SA_ZPL_ZNODE_ACL(zfsvfs), NULL,
&acl_phys, sizeof (zfs_acl_phys_t));
} else if (acl_ids->z_aclp->z_version >= ZFS_ACL_VERSION_FUID) {
SA_ADD_BULK_ATTR(sa_attrs, cnt, SA_ZPL_DACL_COUNT(zfsvfs), NULL,
&acl_ids->z_aclp->z_acl_count, 8);
locate.cb_aclp = acl_ids->z_aclp;
SA_ADD_BULK_ATTR(sa_attrs, cnt, SA_ZPL_DACL_ACES(zfsvfs),
zfs_acl_data_locator, &locate,
acl_ids->z_aclp->z_acl_bytes);
mode = zfs_mode_compute(mode, acl_ids->z_aclp, &pflags,
acl_ids->z_fuid, acl_ids->z_fgid);
}
VERIFY(sa_replace_all_by_template(sa_hdl, sa_attrs, cnt, tx) == 0);
if (!(flag & IS_ROOT_NODE)) {
*zpp = zfs_znode_alloc(zfsvfs, db, 0, obj_type, sa_hdl);
ASSERT(*zpp != NULL);
} else {
/*
* If we are creating the root node, the "parent" we
* passed in is the znode for the root.
*/
*zpp = dzp;
(*zpp)->z_sa_hdl = sa_hdl;
}
(*zpp)->z_pflags = pflags;
(*zpp)->z_mode = mode;
if (vap->va_mask & AT_XVATTR)
zfs_xvattr_set(*zpp, (xvattr_t *)vap, tx);
if (obj_type == DMU_OT_ZNODE ||
acl_ids->z_aclp->z_version < ZFS_ACL_VERSION_FUID) {
err = zfs_aclset_common(*zpp, acl_ids->z_aclp, cr, tx);
ASSERT0(err);
}
if (!(flag & IS_ROOT_NODE)) {
vnode_t *vp;
vp = ZTOV(*zpp);
vp->v_vflag |= VV_FORCEINSMQ;
err = insmntque(vp, zfsvfs->z_vfs);
vp->v_vflag &= ~VV_FORCEINSMQ;
KASSERT(err == 0, ("insmntque() failed: error %d", err));
}
ZFS_OBJ_HOLD_EXIT(zfsvfs, obj);
getnewvnode_drop_reserve();
}
/*
* zfs_xvattr_set only updates the in-core attributes
* it is assumed the caller will be doing an sa_bulk_update
* to push the changes out
*/
void
zfs_xvattr_set(znode_t *zp, xvattr_t *xvap, dmu_tx_t *tx)
{
xoptattr_t *xoap;
xoap = xva_getxoptattr(xvap);
ASSERT(xoap);
if (XVA_ISSET_REQ(xvap, XAT_CREATETIME)) {
uint64_t times[2];
ZFS_TIME_ENCODE(&xoap->xoa_createtime, times);
(void) sa_update(zp->z_sa_hdl, SA_ZPL_CRTIME(zp->z_zfsvfs),
×, sizeof (times), tx);
XVA_SET_RTN(xvap, XAT_CREATETIME);
}
if (XVA_ISSET_REQ(xvap, XAT_READONLY)) {
ZFS_ATTR_SET(zp, ZFS_READONLY, xoap->xoa_readonly,
zp->z_pflags, tx);
XVA_SET_RTN(xvap, XAT_READONLY);
}
if (XVA_ISSET_REQ(xvap, XAT_HIDDEN)) {
ZFS_ATTR_SET(zp, ZFS_HIDDEN, xoap->xoa_hidden,
zp->z_pflags, tx);
XVA_SET_RTN(xvap, XAT_HIDDEN);
}
if (XVA_ISSET_REQ(xvap, XAT_SYSTEM)) {
ZFS_ATTR_SET(zp, ZFS_SYSTEM, xoap->xoa_system,
zp->z_pflags, tx);
XVA_SET_RTN(xvap, XAT_SYSTEM);
}
if (XVA_ISSET_REQ(xvap, XAT_ARCHIVE)) {
ZFS_ATTR_SET(zp, ZFS_ARCHIVE, xoap->xoa_archive,
zp->z_pflags, tx);
XVA_SET_RTN(xvap, XAT_ARCHIVE);
}
if (XVA_ISSET_REQ(xvap, XAT_IMMUTABLE)) {
ZFS_ATTR_SET(zp, ZFS_IMMUTABLE, xoap->xoa_immutable,
zp->z_pflags, tx);
XVA_SET_RTN(xvap, XAT_IMMUTABLE);
}
if (XVA_ISSET_REQ(xvap, XAT_NOUNLINK)) {
ZFS_ATTR_SET(zp, ZFS_NOUNLINK, xoap->xoa_nounlink,
zp->z_pflags, tx);
XVA_SET_RTN(xvap, XAT_NOUNLINK);
}
if (XVA_ISSET_REQ(xvap, XAT_APPENDONLY)) {
ZFS_ATTR_SET(zp, ZFS_APPENDONLY, xoap->xoa_appendonly,
zp->z_pflags, tx);
XVA_SET_RTN(xvap, XAT_APPENDONLY);
}
if (XVA_ISSET_REQ(xvap, XAT_NODUMP)) {
ZFS_ATTR_SET(zp, ZFS_NODUMP, xoap->xoa_nodump,
zp->z_pflags, tx);
XVA_SET_RTN(xvap, XAT_NODUMP);
}
if (XVA_ISSET_REQ(xvap, XAT_OPAQUE)) {
ZFS_ATTR_SET(zp, ZFS_OPAQUE, xoap->xoa_opaque,
zp->z_pflags, tx);
XVA_SET_RTN(xvap, XAT_OPAQUE);
}
if (XVA_ISSET_REQ(xvap, XAT_AV_QUARANTINED)) {
ZFS_ATTR_SET(zp, ZFS_AV_QUARANTINED,
xoap->xoa_av_quarantined, zp->z_pflags, tx);
XVA_SET_RTN(xvap, XAT_AV_QUARANTINED);
}
if (XVA_ISSET_REQ(xvap, XAT_AV_MODIFIED)) {
ZFS_ATTR_SET(zp, ZFS_AV_MODIFIED, xoap->xoa_av_modified,
zp->z_pflags, tx);
XVA_SET_RTN(xvap, XAT_AV_MODIFIED);
}
if (XVA_ISSET_REQ(xvap, XAT_AV_SCANSTAMP)) {
zfs_sa_set_scanstamp(zp, xvap, tx);
XVA_SET_RTN(xvap, XAT_AV_SCANSTAMP);
}
if (XVA_ISSET_REQ(xvap, XAT_REPARSE)) {
ZFS_ATTR_SET(zp, ZFS_REPARSE, xoap->xoa_reparse,
zp->z_pflags, tx);
XVA_SET_RTN(xvap, XAT_REPARSE);
}
if (XVA_ISSET_REQ(xvap, XAT_OFFLINE)) {
ZFS_ATTR_SET(zp, ZFS_OFFLINE, xoap->xoa_offline,
zp->z_pflags, tx);
XVA_SET_RTN(xvap, XAT_OFFLINE);
}
if (XVA_ISSET_REQ(xvap, XAT_SPARSE)) {
ZFS_ATTR_SET(zp, ZFS_SPARSE, xoap->xoa_sparse,
zp->z_pflags, tx);
XVA_SET_RTN(xvap, XAT_SPARSE);
}
}
int
zfs_zget(zfsvfs_t *zfsvfs, uint64_t obj_num, znode_t **zpp)
{
dmu_object_info_t doi;
dmu_buf_t *db;
znode_t *zp;
vnode_t *vp;
sa_handle_t *hdl;
struct thread *td;
int locked;
int err;
td = curthread;
getnewvnode_reserve(1);
again:
*zpp = NULL;
ZFS_OBJ_HOLD_ENTER(zfsvfs, obj_num);
err = sa_buf_hold(zfsvfs->z_os, obj_num, NULL, &db);
if (err) {
ZFS_OBJ_HOLD_EXIT(zfsvfs, obj_num);
getnewvnode_drop_reserve();
return (err);
}
dmu_object_info_from_db(db, &doi);
if (doi.doi_bonus_type != DMU_OT_SA &&
(doi.doi_bonus_type != DMU_OT_ZNODE ||
(doi.doi_bonus_type == DMU_OT_ZNODE &&
doi.doi_bonus_size < sizeof (znode_phys_t)))) {
sa_buf_rele(db, NULL);
ZFS_OBJ_HOLD_EXIT(zfsvfs, obj_num);
#ifdef __FreeBSD__
getnewvnode_drop_reserve();
#endif
return (SET_ERROR(EINVAL));
}
hdl = dmu_buf_get_user(db);
if (hdl != NULL) {
zp = sa_get_userdata(hdl);
/*
* Since "SA" does immediate eviction we
* should never find a sa handle that doesn't
* know about the znode.
*/
ASSERT3P(zp, !=, NULL);
mutex_enter(&zp->z_lock);
ASSERT3U(zp->z_id, ==, obj_num);
if (zp->z_unlinked) {
err = SET_ERROR(ENOENT);
} else {
vp = ZTOV(zp);
*zpp = zp;
err = 0;
}
sa_buf_rele(db, NULL);
/* Don't let the vnode disappear after ZFS_OBJ_HOLD_EXIT. */
if (err == 0)
VN_HOLD(vp);
mutex_exit(&zp->z_lock);
ZFS_OBJ_HOLD_EXIT(zfsvfs, obj_num);
if (err == 0) {
locked = VOP_ISLOCKED(vp);
VI_LOCK(vp);
if ((vp->v_iflag & VI_DOOMED) != 0 &&
locked != LK_EXCLUSIVE) {
/*
* The vnode is doomed and this thread doesn't
* hold the exclusive lock on it, so the vnode
* must be being reclaimed by another thread.
* Otherwise the doomed vnode is being reclaimed
* by this thread and zfs_zget is called from
* ZIL internals.
*/
VI_UNLOCK(vp);
VN_RELE(vp);
goto again;
}
VI_UNLOCK(vp);
}
getnewvnode_drop_reserve();
return (err);
}
/*
* Not found create new znode/vnode
* but only if file exists.
*
* There is a small window where zfs_vget() could
* find this object while a file create is still in
* progress. This is checked for in zfs_znode_alloc()
*
* if zfs_znode_alloc() fails it will drop the hold on the
* bonus buffer.
*/
zp = zfs_znode_alloc(zfsvfs, db, doi.doi_data_block_size,
doi.doi_bonus_type, NULL);
if (zp == NULL) {
err = SET_ERROR(ENOENT);
} else {
*zpp = zp;
}
if (err == 0) {
vnode_t *vp = ZTOV(zp);
err = insmntque(vp, zfsvfs->z_vfs);
if (err == 0)
VOP_UNLOCK(vp, 0);
else {
zp->z_vnode = NULL;
zfs_znode_dmu_fini(zp);
zfs_znode_free(zp);
*zpp = NULL;
}
}
ZFS_OBJ_HOLD_EXIT(zfsvfs, obj_num);
getnewvnode_drop_reserve();
return (err);
}
int
zfs_rezget(znode_t *zp)
{
zfsvfs_t *zfsvfs = zp->z_zfsvfs;
dmu_object_info_t doi;
dmu_buf_t *db;
vnode_t *vp;
uint64_t obj_num = zp->z_id;
uint64_t mode, size;
sa_bulk_attr_t bulk[8];
int err;
int count = 0;
uint64_t gen;
ZFS_OBJ_HOLD_ENTER(zfsvfs, obj_num);
mutex_enter(&zp->z_acl_lock);
if (zp->z_acl_cached) {
zfs_acl_free(zp->z_acl_cached);
zp->z_acl_cached = NULL;
}
mutex_exit(&zp->z_acl_lock);
ASSERT(zp->z_sa_hdl == NULL);
err = sa_buf_hold(zfsvfs->z_os, obj_num, NULL, &db);
if (err) {
ZFS_OBJ_HOLD_EXIT(zfsvfs, obj_num);
return (err);
}
dmu_object_info_from_db(db, &doi);
if (doi.doi_bonus_type != DMU_OT_SA &&
(doi.doi_bonus_type != DMU_OT_ZNODE ||
(doi.doi_bonus_type == DMU_OT_ZNODE &&
doi.doi_bonus_size < sizeof (znode_phys_t)))) {
sa_buf_rele(db, NULL);
ZFS_OBJ_HOLD_EXIT(zfsvfs, obj_num);
return (SET_ERROR(EINVAL));
}
zfs_znode_sa_init(zfsvfs, zp, db, doi.doi_bonus_type, NULL);
size = zp->z_size;
/* reload cached values */
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_GEN(zfsvfs), NULL,
&gen, sizeof (gen));
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_SIZE(zfsvfs), NULL,
&zp->z_size, sizeof (zp->z_size));
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_LINKS(zfsvfs), NULL,
&zp->z_links, sizeof (zp->z_links));
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_FLAGS(zfsvfs), NULL,
&zp->z_pflags, sizeof (zp->z_pflags));
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_ATIME(zfsvfs), NULL,
&zp->z_atime, sizeof (zp->z_atime));
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_UID(zfsvfs), NULL,
&zp->z_uid, sizeof (zp->z_uid));
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_GID(zfsvfs), NULL,
&zp->z_gid, sizeof (zp->z_gid));
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_MODE(zfsvfs), NULL,
&mode, sizeof (mode));
if (sa_bulk_lookup(zp->z_sa_hdl, bulk, count)) {
zfs_znode_dmu_fini(zp);
ZFS_OBJ_HOLD_EXIT(zfsvfs, obj_num);
return (SET_ERROR(EIO));
}
zp->z_mode = mode;
if (gen != zp->z_gen) {
zfs_znode_dmu_fini(zp);
ZFS_OBJ_HOLD_EXIT(zfsvfs, obj_num);
return (SET_ERROR(EIO));
}
/*
* XXXPJD: Not sure how is that possible, but under heavy
* zfs recv -F load it happens that z_gen is the same, but
* vnode type is different than znode type. This would mean
* that for example regular file was replaced with directory
* which has the same object number.
*/
vp = ZTOV(zp);
if (vp != NULL &&
vp->v_type != IFTOVT((mode_t)zp->z_mode)) {
zfs_znode_dmu_fini(zp);
ZFS_OBJ_HOLD_EXIT(zfsvfs, obj_num);
return (EIO);
}
zp->z_unlinked = (zp->z_links == 0);
zp->z_blksz = doi.doi_data_block_size;
if (vp != NULL) {
vn_pages_remove(vp, 0, 0);
if (zp->z_size != size)
vnode_pager_setsize(vp, zp->z_size);
}
ZFS_OBJ_HOLD_EXIT(zfsvfs, obj_num);
return (0);
}
void
zfs_znode_delete(znode_t *zp, dmu_tx_t *tx)
{
zfsvfs_t *zfsvfs = zp->z_zfsvfs;
objset_t *os = zfsvfs->z_os;
uint64_t obj = zp->z_id;
uint64_t acl_obj = zfs_external_acl(zp);
ZFS_OBJ_HOLD_ENTER(zfsvfs, obj);
if (acl_obj) {
VERIFY(!zp->z_is_sa);
VERIFY(0 == dmu_object_free(os, acl_obj, tx));
}
VERIFY(0 == dmu_object_free(os, obj, tx));
zfs_znode_dmu_fini(zp);
ZFS_OBJ_HOLD_EXIT(zfsvfs, obj);
zfs_znode_free(zp);
}
void
zfs_zinactive(znode_t *zp)
{
zfsvfs_t *zfsvfs = zp->z_zfsvfs;
uint64_t z_id = zp->z_id;
ASSERT(zp->z_sa_hdl);
/*
* Don't allow a zfs_zget() while were trying to release this znode
*/
ZFS_OBJ_HOLD_ENTER(zfsvfs, z_id);
mutex_enter(&zp->z_lock);
/*
* If this was the last reference to a file with no links,
* remove the file from the file system.
*/
if (zp->z_unlinked) {
mutex_exit(&zp->z_lock);
ZFS_OBJ_HOLD_EXIT(zfsvfs, z_id);
zfs_rmnode(zp);
return;
}
mutex_exit(&zp->z_lock);
zfs_znode_dmu_fini(zp);
ZFS_OBJ_HOLD_EXIT(zfsvfs, z_id);
zfs_znode_free(zp);
}
void
zfs_znode_free(znode_t *zp)
{
zfsvfs_t *zfsvfs = zp->z_zfsvfs;
ASSERT(zp->z_sa_hdl == NULL);
zp->z_vnode = NULL;
mutex_enter(&zfsvfs->z_znodes_lock);
POINTER_INVALIDATE(&zp->z_zfsvfs);
list_remove(&zfsvfs->z_all_znodes, zp);
mutex_exit(&zfsvfs->z_znodes_lock);
if (zp->z_acl_cached) {
zfs_acl_free(zp->z_acl_cached);
zp->z_acl_cached = NULL;
}
kmem_cache_free(znode_cache, zp);
VFS_RELE(zfsvfs->z_vfs);
}
void
zfs_tstamp_update_setup(znode_t *zp, uint_t flag, uint64_t mtime[2],
uint64_t ctime[2], boolean_t have_tx)
{
timestruc_t now;
gethrestime(&now);
if (have_tx) { /* will sa_bulk_update happen really soon? */
zp->z_atime_dirty = 0;
zp->z_seq++;
} else {
zp->z_atime_dirty = 1;
}
if (flag & AT_ATIME) {
ZFS_TIME_ENCODE(&now, zp->z_atime);
}
if (flag & AT_MTIME) {
ZFS_TIME_ENCODE(&now, mtime);
if (zp->z_zfsvfs->z_use_fuids) {
zp->z_pflags |= (ZFS_ARCHIVE |
ZFS_AV_MODIFIED);
}
}
if (flag & AT_CTIME) {
ZFS_TIME_ENCODE(&now, ctime);
if (zp->z_zfsvfs->z_use_fuids)
zp->z_pflags |= ZFS_ARCHIVE;
}
}
/*
* Grow the block size for a file.
*
* IN: zp - znode of file to free data in.
* size - requested block size
* tx - open transaction.
*
* NOTE: this function assumes that the znode is write locked.
*/
void
zfs_grow_blocksize(znode_t *zp, uint64_t size, dmu_tx_t *tx)
{
int error;
u_longlong_t dummy;
if (size <= zp->z_blksz)
return;
/*
* If the file size is already greater than the current blocksize,
* we will not grow. If there is more than one block in a file,
* the blocksize cannot change.
*/
if (zp->z_blksz && zp->z_size > zp->z_blksz)
return;
error = dmu_object_set_blocksize(zp->z_zfsvfs->z_os, zp->z_id,
size, 0, tx);
if (error == ENOTSUP)
return;
ASSERT0(error);
/* What blocksize did we actually get? */
dmu_object_size_from_db(sa_get_db(zp->z_sa_hdl), &zp->z_blksz, &dummy);
}
#ifdef sun
/*
* This is a dummy interface used when pvn_vplist_dirty() should *not*
* be calling back into the fs for a putpage(). E.g.: when truncating
* a file, the pages being "thrown away* don't need to be written out.
*/
/* ARGSUSED */
static int
zfs_no_putpage(vnode_t *vp, page_t *pp, u_offset_t *offp, size_t *lenp,
int flags, cred_t *cr)
{
ASSERT(0);
return (0);
}
#endif /* sun */
/*
* Increase the file length
*
* IN: zp - znode of file to free data in.
* end - new end-of-file
*
* RETURN: 0 if success
* error code if failure
*/
static int
zfs_extend(znode_t *zp, uint64_t end)
{
zfsvfs_t *zfsvfs = zp->z_zfsvfs;
dmu_tx_t *tx;
rl_t *rl;
uint64_t newblksz;
int error;
/*
* We will change zp_size, lock the whole file.
*/
rl = zfs_range_lock(zp, 0, UINT64_MAX, RL_WRITER);
/*
* Nothing to do if file already at desired length.
*/
if (end <= zp->z_size) {
zfs_range_unlock(rl);
return (0);
}
top:
tx = dmu_tx_create(zfsvfs->z_os);
dmu_tx_hold_sa(tx, zp->z_sa_hdl, B_FALSE);
zfs_sa_upgrade_txholds(tx, zp);
if (end > zp->z_blksz &&
(!ISP2(zp->z_blksz) || zp->z_blksz < zfsvfs->z_max_blksz)) {
/*
* We are growing the file past the current block size.
*/
if (zp->z_blksz > zp->z_zfsvfs->z_max_blksz) {
ASSERT(!ISP2(zp->z_blksz));
newblksz = MIN(end, SPA_MAXBLOCKSIZE);
} else {
newblksz = MIN(end, zp->z_zfsvfs->z_max_blksz);
}
dmu_tx_hold_write(tx, zp->z_id, 0, newblksz);
} else {
newblksz = 0;
}
error = dmu_tx_assign(tx, TXG_NOWAIT);
if (error) {
if (error == ERESTART) {
dmu_tx_wait(tx);
dmu_tx_abort(tx);
goto top;
}
dmu_tx_abort(tx);
zfs_range_unlock(rl);
return (error);
}
if (newblksz)
zfs_grow_blocksize(zp, newblksz, tx);
zp->z_size = end;
VERIFY(0 == sa_update(zp->z_sa_hdl, SA_ZPL_SIZE(zp->z_zfsvfs),
&zp->z_size, sizeof (zp->z_size), tx));
vnode_pager_setsize(ZTOV(zp), end);
zfs_range_unlock(rl);
dmu_tx_commit(tx);
return (0);
}
/*
* Free space in a file.
*
* IN: zp - znode of file to free data in.
* off - start of section to free.
* len - length of section to free.
*
* RETURN: 0 if success
* error code if failure
*/
static int
zfs_free_range(znode_t *zp, uint64_t off, uint64_t len)
{
zfsvfs_t *zfsvfs = zp->z_zfsvfs;
rl_t *rl;
int error;
/*
* Lock the range being freed.
*/
rl = zfs_range_lock(zp, off, len, RL_WRITER);
/*
* Nothing to do if file already at desired length.
*/
if (off >= zp->z_size) {
zfs_range_unlock(rl);
return (0);
}
if (off + len > zp->z_size)
len = zp->z_size - off;
error = dmu_free_long_range(zfsvfs->z_os, zp->z_id, off, len);
if (error == 0) {
/*
* In FreeBSD we cannot free block in the middle of a file,
* but only at the end of a file, so this code path should
* never happen.
*/
vnode_pager_setsize(ZTOV(zp), off);
}
zfs_range_unlock(rl);
return (error);
}
/*
* Truncate a file
*
* IN: zp - znode of file to free data in.
* end - new end-of-file.
*
* RETURN: 0 if success
* error code if failure
*/
static int
zfs_trunc(znode_t *zp, uint64_t end)
{
zfsvfs_t *zfsvfs = zp->z_zfsvfs;
vnode_t *vp = ZTOV(zp);
dmu_tx_t *tx;
rl_t *rl;
int error;
sa_bulk_attr_t bulk[2];
int count = 0;
/*
* We will change zp_size, lock the whole file.
*/
rl = zfs_range_lock(zp, 0, UINT64_MAX, RL_WRITER);
/*
* Nothing to do if file already at desired length.
*/
if (end >= zp->z_size) {
zfs_range_unlock(rl);
return (0);
}
error = dmu_free_long_range(zfsvfs->z_os, zp->z_id, end, -1);
if (error) {
zfs_range_unlock(rl);
return (error);
}
top:
tx = dmu_tx_create(zfsvfs->z_os);
dmu_tx_hold_sa(tx, zp->z_sa_hdl, B_FALSE);
zfs_sa_upgrade_txholds(tx, zp);
error = dmu_tx_assign(tx, TXG_NOWAIT);
if (error) {
if (error == ERESTART) {
dmu_tx_wait(tx);
dmu_tx_abort(tx);
goto top;
}
dmu_tx_abort(tx);
zfs_range_unlock(rl);
return (error);
}
zp->z_size = end;
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_SIZE(zfsvfs),
NULL, &zp->z_size, sizeof (zp->z_size));
if (end == 0) {
zp->z_pflags &= ~ZFS_SPARSE;
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_FLAGS(zfsvfs),
NULL, &zp->z_pflags, 8);
}
VERIFY(sa_bulk_update(zp->z_sa_hdl, bulk, count, tx) == 0);
dmu_tx_commit(tx);
/*
* Clear any mapped pages in the truncated region. This has to
* happen outside of the transaction to avoid the possibility of
* a deadlock with someone trying to push a page that we are
* about to invalidate.
*/
vnode_pager_setsize(vp, end);
zfs_range_unlock(rl);
return (0);
}
/*
* Free space in a file
*
* IN: zp - znode of file to free data in.
* off - start of range
* len - end of range (0 => EOF)
* flag - current file open mode flags.
* log - TRUE if this action should be logged
*
* RETURN: 0 if success
* error code if failure
*/
int
zfs_freesp(znode_t *zp, uint64_t off, uint64_t len, int flag, boolean_t log)
{
vnode_t *vp = ZTOV(zp);
dmu_tx_t *tx;
zfsvfs_t *zfsvfs = zp->z_zfsvfs;
zilog_t *zilog = zfsvfs->z_log;
uint64_t mode;
uint64_t mtime[2], ctime[2];
sa_bulk_attr_t bulk[3];
int count = 0;
int error;
if ((error = sa_lookup(zp->z_sa_hdl, SA_ZPL_MODE(zfsvfs), &mode,
sizeof (mode))) != 0)
return (error);
if (off > zp->z_size) {
error = zfs_extend(zp, off+len);
if (error == 0 && log)
goto log;
else
return (error);
}
/*
* Check for any locks in the region to be freed.
*/
if (MANDLOCK(vp, (mode_t)mode)) {
uint64_t length = (len ? len : zp->z_size - off);
if (error = chklock(vp, FWRITE, off, length, flag, NULL))
return (error);
}
if (len == 0) {
error = zfs_trunc(zp, off);
} else {
if ((error = zfs_free_range(zp, off, len)) == 0 &&
off + len > zp->z_size)
error = zfs_extend(zp, off+len);
}
if (error || !log)
return (error);
log:
tx = dmu_tx_create(zfsvfs->z_os);
dmu_tx_hold_sa(tx, zp->z_sa_hdl, B_FALSE);
zfs_sa_upgrade_txholds(tx, zp);
error = dmu_tx_assign(tx, TXG_NOWAIT);
if (error) {
if (error == ERESTART) {
dmu_tx_wait(tx);
dmu_tx_abort(tx);
goto log;
}
dmu_tx_abort(tx);
return (error);
}
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_MTIME(zfsvfs), NULL, mtime, 16);
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_CTIME(zfsvfs), NULL, ctime, 16);
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_FLAGS(zfsvfs),
NULL, &zp->z_pflags, 8);
zfs_tstamp_update_setup(zp, CONTENT_MODIFIED, mtime, ctime, B_TRUE);
error = sa_bulk_update(zp->z_sa_hdl, bulk, count, tx);
ASSERT(error == 0);
zfs_log_truncate(zilog, tx, TX_TRUNCATE, zp, off, len);
dmu_tx_commit(tx);
return (0);
}
void
zfs_create_fs(objset_t *os, cred_t *cr, nvlist_t *zplprops, dmu_tx_t *tx)
{
zfsvfs_t zfsvfs;
uint64_t moid, obj, sa_obj, version;
uint64_t sense = ZFS_CASE_SENSITIVE;
uint64_t norm = 0;
nvpair_t *elem;
int error;
int i;
znode_t *rootzp = NULL;
vnode_t vnode;
vattr_t vattr;
znode_t *zp;
zfs_acl_ids_t acl_ids;
/*
* First attempt to create master node.
*/
/*
* In an empty objset, there are no blocks to read and thus
* there can be no i/o errors (which we assert below).
*/
moid = MASTER_NODE_OBJ;
error = zap_create_claim(os, moid, DMU_OT_MASTER_NODE,
DMU_OT_NONE, 0, tx);
ASSERT(error == 0);
/*
* Set starting attributes.
*/
version = zfs_zpl_version_map(spa_version(dmu_objset_spa(os)));
elem = NULL;
while ((elem = nvlist_next_nvpair(zplprops, elem)) != NULL) {
/* For the moment we expect all zpl props to be uint64_ts */
uint64_t val;
char *name;
ASSERT(nvpair_type(elem) == DATA_TYPE_UINT64);
VERIFY(nvpair_value_uint64(elem, &val) == 0);
name = nvpair_name(elem);
if (strcmp(name, zfs_prop_to_name(ZFS_PROP_VERSION)) == 0) {
if (val < version)
version = val;
} else {
error = zap_update(os, moid, name, 8, 1, &val, tx);
}
ASSERT(error == 0);
if (strcmp(name, zfs_prop_to_name(ZFS_PROP_NORMALIZE)) == 0)
norm = val;
else if (strcmp(name, zfs_prop_to_name(ZFS_PROP_CASE)) == 0)
sense = val;
}
ASSERT(version != 0);
error = zap_update(os, moid, ZPL_VERSION_STR, 8, 1, &version, tx);
/*
* Create zap object used for SA attribute registration
*/
if (version >= ZPL_VERSION_SA) {
sa_obj = zap_create(os, DMU_OT_SA_MASTER_NODE,
DMU_OT_NONE, 0, tx);
error = zap_add(os, moid, ZFS_SA_ATTRS, 8, 1, &sa_obj, tx);
ASSERT(error == 0);
} else {
sa_obj = 0;
}
/*
* Create a delete queue.
*/
obj = zap_create(os, DMU_OT_UNLINKED_SET, DMU_OT_NONE, 0, tx);
error = zap_add(os, moid, ZFS_UNLINKED_SET, 8, 1, &obj, tx);
ASSERT(error == 0);
/*
* Create root znode. Create minimal znode/vnode/zfsvfs
* to allow zfs_mknode to work.
*/
VATTR_NULL(&vattr);
vattr.va_mask = AT_MODE|AT_UID|AT_GID|AT_TYPE;
vattr.va_type = VDIR;
vattr.va_mode = S_IFDIR|0755;
vattr.va_uid = crgetuid(cr);
vattr.va_gid = crgetgid(cr);
bzero(&zfsvfs, sizeof (zfsvfs_t));
rootzp = kmem_cache_alloc(znode_cache, KM_SLEEP);
zfs_znode_cache_constructor(rootzp, NULL, 0);
ASSERT(!POINTER_IS_VALID(rootzp->z_zfsvfs));
rootzp->z_moved = 0;
rootzp->z_unlinked = 0;
rootzp->z_atime_dirty = 0;
rootzp->z_is_sa = USE_SA(version, os);
vnode.v_type = VDIR;
vnode.v_data = rootzp;
rootzp->z_vnode = &vnode;
zfsvfs.z_os = os;
zfsvfs.z_parent = &zfsvfs;
zfsvfs.z_version = version;
zfsvfs.z_use_fuids = USE_FUIDS(version, os);
zfsvfs.z_use_sa = USE_SA(version, os);
zfsvfs.z_norm = norm;
error = sa_setup(os, sa_obj, zfs_attr_table, ZPL_END,
&zfsvfs.z_attr_table);
ASSERT(error == 0);
/*
* Fold case on file systems that are always or sometimes case
* insensitive.
*/
if (sense == ZFS_CASE_INSENSITIVE || sense == ZFS_CASE_MIXED)
zfsvfs.z_norm |= U8_TEXTPREP_TOUPPER;
mutex_init(&zfsvfs.z_znodes_lock, NULL, MUTEX_DEFAULT, NULL);
list_create(&zfsvfs.z_all_znodes, sizeof (znode_t),
offsetof(znode_t, z_link_node));
for (i = 0; i != ZFS_OBJ_MTX_SZ; i++)
mutex_init(&zfsvfs.z_hold_mtx[i], NULL, MUTEX_DEFAULT, NULL);
rootzp->z_zfsvfs = &zfsvfs;
VERIFY(0 == zfs_acl_ids_create(rootzp, IS_ROOT_NODE, &vattr,
cr, NULL, &acl_ids));
zfs_mknode(rootzp, &vattr, tx, cr, IS_ROOT_NODE, &zp, &acl_ids);
ASSERT3P(zp, ==, rootzp);
error = zap_add(os, moid, ZFS_ROOT_OBJ, 8, 1, &rootzp->z_id, tx);
ASSERT(error == 0);
zfs_acl_ids_free(&acl_ids);
POINTER_INVALIDATE(&rootzp->z_zfsvfs);
sa_handle_destroy(rootzp->z_sa_hdl);
rootzp->z_vnode = NULL;
kmem_cache_free(znode_cache, rootzp);
/*
* Create shares directory
*/
error = zfs_create_share_dir(&zfsvfs, tx);
ASSERT(error == 0);
for (i = 0; i != ZFS_OBJ_MTX_SZ; i++)
mutex_destroy(&zfsvfs.z_hold_mtx[i]);
}
#endif /* _KERNEL */
static int
zfs_sa_setup(objset_t *osp, sa_attr_type_t **sa_table)
{
uint64_t sa_obj = 0;
int error;
error = zap_lookup(osp, MASTER_NODE_OBJ, ZFS_SA_ATTRS, 8, 1, &sa_obj);
if (error != 0 && error != ENOENT)
return (error);
error = sa_setup(osp, sa_obj, zfs_attr_table, ZPL_END, sa_table);
return (error);
}
static int
zfs_grab_sa_handle(objset_t *osp, uint64_t obj, sa_handle_t **hdlp,
dmu_buf_t **db, void *tag)
{
dmu_object_info_t doi;
int error;
if ((error = sa_buf_hold(osp, obj, tag, db)) != 0)
return (error);
dmu_object_info_from_db(*db, &doi);
if ((doi.doi_bonus_type != DMU_OT_SA &&
doi.doi_bonus_type != DMU_OT_ZNODE) ||
doi.doi_bonus_type == DMU_OT_ZNODE &&
doi.doi_bonus_size < sizeof (znode_phys_t)) {
sa_buf_rele(*db, tag);
return (SET_ERROR(ENOTSUP));
}
error = sa_handle_get(osp, obj, NULL, SA_HDL_PRIVATE, hdlp);
if (error != 0) {
sa_buf_rele(*db, tag);
return (error);
}
return (0);
}
void
zfs_release_sa_handle(sa_handle_t *hdl, dmu_buf_t *db, void *tag)
{
sa_handle_destroy(hdl);
sa_buf_rele(db, tag);
}
/*
* Given an object number, return its parent object number and whether
* or not the object is an extended attribute directory.
*/
static int
zfs_obj_to_pobj(objset_t *osp, sa_handle_t *hdl, sa_attr_type_t *sa_table,
uint64_t *pobjp, int *is_xattrdir)
{
uint64_t parent;
uint64_t pflags;
uint64_t mode;
uint64_t parent_mode;
sa_bulk_attr_t bulk[3];
sa_handle_t *sa_hdl;
dmu_buf_t *sa_db;
int count = 0;
int error;
SA_ADD_BULK_ATTR(bulk, count, sa_table[ZPL_PARENT], NULL,
&parent, sizeof (parent));
SA_ADD_BULK_ATTR(bulk, count, sa_table[ZPL_FLAGS], NULL,
&pflags, sizeof (pflags));
SA_ADD_BULK_ATTR(bulk, count, sa_table[ZPL_MODE], NULL,
&mode, sizeof (mode));
if ((error = sa_bulk_lookup(hdl, bulk, count)) != 0)
return (error);
/*
* When a link is removed its parent pointer is not changed and will
* be invalid. There are two cases where a link is removed but the
* file stays around, when it goes to the delete queue and when there
* are additional links.
*/
error = zfs_grab_sa_handle(osp, parent, &sa_hdl, &sa_db, FTAG);
if (error != 0)
return (error);
error = sa_lookup(sa_hdl, ZPL_MODE, &parent_mode, sizeof (parent_mode));
zfs_release_sa_handle(sa_hdl, sa_db, FTAG);
if (error != 0)
return (error);
*is_xattrdir = ((pflags & ZFS_XATTR) != 0) && S_ISDIR(mode);
/*
* Extended attributes can be applied to files, directories, etc.
* Otherwise the parent must be a directory.
*/
if (!*is_xattrdir && !S_ISDIR(parent_mode))
return (SET_ERROR(EINVAL));
*pobjp = parent;
return (0);
}
/*
* Given an object number, return some zpl level statistics
*/
static int
zfs_obj_to_stats_impl(sa_handle_t *hdl, sa_attr_type_t *sa_table,
zfs_stat_t *sb)
{
sa_bulk_attr_t bulk[4];
int count = 0;
SA_ADD_BULK_ATTR(bulk, count, sa_table[ZPL_MODE], NULL,
&sb->zs_mode, sizeof (sb->zs_mode));
SA_ADD_BULK_ATTR(bulk, count, sa_table[ZPL_GEN], NULL,
&sb->zs_gen, sizeof (sb->zs_gen));
SA_ADD_BULK_ATTR(bulk, count, sa_table[ZPL_LINKS], NULL,
&sb->zs_links, sizeof (sb->zs_links));
SA_ADD_BULK_ATTR(bulk, count, sa_table[ZPL_CTIME], NULL,
&sb->zs_ctime, sizeof (sb->zs_ctime));
return (sa_bulk_lookup(hdl, bulk, count));
}
static int
zfs_obj_to_path_impl(objset_t *osp, uint64_t obj, sa_handle_t *hdl,
sa_attr_type_t *sa_table, char *buf, int len)
{
sa_handle_t *sa_hdl;
sa_handle_t *prevhdl = NULL;
dmu_buf_t *prevdb = NULL;
dmu_buf_t *sa_db = NULL;
char *path = buf + len - 1;
int error;
*path = '\0';
sa_hdl = hdl;
for (;;) {
uint64_t pobj;
char component[MAXNAMELEN + 2];
size_t complen;
int is_xattrdir;
if (prevdb)
zfs_release_sa_handle(prevhdl, prevdb, FTAG);
if ((error = zfs_obj_to_pobj(osp, sa_hdl, sa_table, &pobj,
&is_xattrdir)) != 0)
break;
if (pobj == obj) {
if (path[0] != '/')
*--path = '/';
break;
}
component[0] = '/';
if (is_xattrdir) {
(void) sprintf(component + 1, "<xattrdir>");
} else {
error = zap_value_search(osp, pobj, obj,
ZFS_DIRENT_OBJ(-1ULL), component + 1);
if (error != 0)
break;
}
complen = strlen(component);
path -= complen;
ASSERT(path >= buf);
bcopy(component, path, complen);
obj = pobj;
if (sa_hdl != hdl) {
prevhdl = sa_hdl;
prevdb = sa_db;
}
error = zfs_grab_sa_handle(osp, obj, &sa_hdl, &sa_db, FTAG);
if (error != 0) {
sa_hdl = prevhdl;
sa_db = prevdb;
break;
}
}
if (sa_hdl != NULL && sa_hdl != hdl) {
ASSERT(sa_db != NULL);
zfs_release_sa_handle(sa_hdl, sa_db, FTAG);
}
if (error == 0)
(void) memmove(buf, path, buf + len - path);
return (error);
}
int
zfs_obj_to_path(objset_t *osp, uint64_t obj, char *buf, int len)
{
sa_attr_type_t *sa_table;
sa_handle_t *hdl;
dmu_buf_t *db;
int error;
error = zfs_sa_setup(osp, &sa_table);
if (error != 0)
return (error);
error = zfs_grab_sa_handle(osp, obj, &hdl, &db, FTAG);
if (error != 0)
return (error);
error = zfs_obj_to_path_impl(osp, obj, hdl, sa_table, buf, len);
zfs_release_sa_handle(hdl, db, FTAG);
return (error);
}
int
zfs_obj_to_stats(objset_t *osp, uint64_t obj, zfs_stat_t *sb,
char *buf, int len)
{
char *path = buf + len - 1;
sa_attr_type_t *sa_table;
sa_handle_t *hdl;
dmu_buf_t *db;
int error;
*path = '\0';
error = zfs_sa_setup(osp, &sa_table);
if (error != 0)
return (error);
error = zfs_grab_sa_handle(osp, obj, &hdl, &db, FTAG);
if (error != 0)
return (error);
error = zfs_obj_to_stats_impl(hdl, sa_table, sb);
if (error != 0) {
zfs_release_sa_handle(hdl, db, FTAG);
return (error);
}
error = zfs_obj_to_path_impl(osp, obj, hdl, sa_table, buf, len);
zfs_release_sa_handle(hdl, db, FTAG);
return (error);
}
|